diff --git "a/checkpoint-2976480/trainer_state.json" "b/checkpoint-2976480/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2976480/trainer_state.json" @@ -0,0 +1,35215 @@ +{ + "best_metric": 3.8424384593963623, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/det-noun/transformer/3/checkpoints/checkpoint-915840", + "epoch": 1.0250006060157382, + "eval_steps": 10, + "global_step": 2976480, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 4.999998362119627e-05, + "loss": 10.9867, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8188, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.1835, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9731, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8049, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.6919, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.5929, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5265, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4448, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.3876, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3349, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.2996, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 5.252, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989098268236324e-05, + "loss": 5.2013, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988259673485272e-05, + "loss": 5.169, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.98742107873422e-05, + "loss": 5.1205, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.1131, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.0688, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0388, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0171, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.0046, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 4.9732, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.949, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9289, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9131, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790384069844466e-05, + "loss": 4.8832, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 4.8692, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.8472, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8306, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756856658606115e-05, + "loss": 4.8169, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748487089899324e-05, + "loss": 4.801, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 4.7901, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 4.7837, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.97233456261715e-05, + "loss": 4.766, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 4.7526, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.7394, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 4.732, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968981821493315e-05, + "loss": 4.708, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.968143226742263e-05, + "loss": 4.7085, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 4.6763, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.676, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6717, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.6711, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.6394, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 4.6469, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.6351, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.624, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.631, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 4.5917, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.9589219602414374e-05, + "loss": 4.596, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958083365490385e-05, + "loss": 4.6007, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957244770739333e-05, + "loss": 4.5934, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956406175988281e-05, + "loss": 4.5741, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 4.5553, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.9547306243665496e-05, + "loss": 4.5644, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 4.5456, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530534348644456e-05, + "loss": 4.5687, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522148401133936e-05, + "loss": 4.5196, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951377883242715e-05, + "loss": 4.5405, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.5284, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 4.519, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948862098989559e-05, + "loss": 4.5238, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.94802514211888e-05, + "loss": 4.5042, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 4.4887, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.4921, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945509357865724e-05, + "loss": 4.5044, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944672400995045e-05, + "loss": 4.4773, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943833806243993e-05, + "loss": 4.4797, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.4621, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942156616741889e-05, + "loss": 4.4626, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.941318021990837e-05, + "loss": 4.4778, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404810651201585e-05, + "loss": 4.4757, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396424703691065e-05, + "loss": 4.4492, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388038756180545e-05, + "loss": 4.4624, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379652808670025e-05, + "loss": 4.469, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371283239963234e-05, + "loss": 4.4506, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.936291367125644e-05, + "loss": 4.4324, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.935452772374592e-05, + "loss": 4.4365, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.93461417762354e-05, + "loss": 4.4335, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.933775582872488e-05, + "loss": 4.4242, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.932936988121436e-05, + "loss": 4.4206, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932098393370384e-05, + "loss": 4.421, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931259798619332e-05, + "loss": 4.4231, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930421203868281e-05, + "loss": 4.415, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929584246997602e-05, + "loss": 4.3941, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.92874565224655e-05, + "loss": 4.3988, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927907057495498e-05, + "loss": 4.3989, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927068462744446e-05, + "loss": 4.3941, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926231505873767e-05, + "loss": 4.3936, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925394549003088e-05, + "loss": 4.3833, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924555954252036e-05, + "loss": 4.3797, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923717359500984e-05, + "loss": 4.3711, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.9228804026303046e-05, + "loss": 4.3805, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.922041807879253e-05, + "loss": 4.3709, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921203213128201e-05, + "loss": 4.3724, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920364618377149e-05, + "loss": 4.3711, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919526023626097e-05, + "loss": 4.356, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918687428875045e-05, + "loss": 4.36, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917848834123993e-05, + "loss": 4.3544, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917010239372941e-05, + "loss": 4.3531, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.916171644621889e-05, + "loss": 4.3542, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.915333049870837e-05, + "loss": 4.3366, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914494455119785e-05, + "loss": 4.3458, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.9136558603687325e-05, + "loss": 4.3404, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.912818903498054e-05, + "loss": 4.3341, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.911980308747002e-05, + "loss": 4.3239, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.911143351876323e-05, + "loss": 4.3253, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910304757125272e-05, + "loss": 4.3271, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.90946616237422e-05, + "loss": 4.3202, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908627567623168e-05, + "loss": 4.3199, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907788972872115e-05, + "loss": 4.3123, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.906950378121063e-05, + "loss": 4.3048, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906111783370011e-05, + "loss": 4.3245, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.9052748264993326e-05, + "loss": 4.3036, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.90443623174828e-05, + "loss": 4.3089, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903597636997228e-05, + "loss": 4.3083, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902759042246176e-05, + "loss": 4.3084, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.9019220853754975e-05, + "loss": 4.2999, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.9010834906244455e-05, + "loss": 4.2949, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.9002448958733935e-05, + "loss": 4.3087, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994063011223415e-05, + "loss": 4.2963, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985677063712895e-05, + "loss": 4.2821, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977291116202375e-05, + "loss": 4.284, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968905168691855e-05, + "loss": 4.2797, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960535599985064e-05, + "loss": 4.2796, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952149652474544e-05, + "loss": 4.2748, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943763704964024e-05, + "loss": 4.2781, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935377757453504e-05, + "loss": 4.2666, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.892700818874671e-05, + "loss": 4.2687, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.891862224123619e-05, + "loss": 4.2634, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.891025267252941e-05, + "loss": 4.282, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890186672501889e-05, + "loss": 4.2746, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889348077750837e-05, + "loss": 4.2588, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888509482999785e-05, + "loss": 4.2572, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.887670888248733e-05, + "loss": 4.2601, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886832293497681e-05, + "loss": 4.2647, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885993698746629e-05, + "loss": 4.2618, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.88515674187595e-05, + "loss": 4.2571, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884318147124898e-05, + "loss": 4.2547, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883479552373846e-05, + "loss": 4.2523, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882640957622794e-05, + "loss": 4.2486, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881802362871742e-05, + "loss": 4.2392, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.88096376812069e-05, + "loss": 4.2481, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880125173369638e-05, + "loss": 4.2378, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879286578618586e-05, + "loss": 4.2281, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878449621747907e-05, + "loss": 4.2429, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877611026996855e-05, + "loss": 4.2358, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876774070126176e-05, + "loss": 4.2391, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875935475375124e-05, + "loss": 4.2288, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875096880624072e-05, + "loss": 4.229, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.196639060974121, + "eval_runtime": 303.4597, + "eval_samples_per_second": 1257.468, + "eval_steps_per_second": 39.297, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.87425828587302e-05, + "loss": 4.2195, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.873419691121968e-05, + "loss": 4.216, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.872581096370916e-05, + "loss": 4.2308, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.871744139500237e-05, + "loss": 4.2157, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.870905544749185e-05, + "loss": 4.224, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.870066949998133e-05, + "loss": 4.2076, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.869228355247081e-05, + "loss": 4.2151, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.868389760496029e-05, + "loss": 4.2022, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.8675528036253507e-05, + "loss": 4.2087, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.8667142088742986e-05, + "loss": 4.2036, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.865875614123246e-05, + "loss": 4.2122, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865037019372194e-05, + "loss": 4.2067, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.864198424621142e-05, + "loss": 4.1908, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.86335982987009e-05, + "loss": 4.1899, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.862521235119038e-05, + "loss": 4.1881, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.861684278248359e-05, + "loss": 4.1862, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.860845683497307e-05, + "loss": 4.1898, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860007088746255e-05, + "loss": 4.1818, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.859168493995203e-05, + "loss": 4.1836, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.858329899244151e-05, + "loss": 4.198, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.8574913044930995e-05, + "loss": 4.1833, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.8566527097420475e-05, + "loss": 4.1834, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.8558141149909955e-05, + "loss": 4.178, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.8549771581203164e-05, + "loss": 4.1907, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.854140201249637e-05, + "loss": 4.1615, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.853301606498585e-05, + "loss": 4.1778, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.852463011747533e-05, + "loss": 4.1667, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.851624416996481e-05, + "loss": 4.1646, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.850785822245429e-05, + "loss": 4.1627, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.849947227494377e-05, + "loss": 4.1577, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849110270623698e-05, + "loss": 4.1629, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848271675872646e-05, + "loss": 4.174, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847433081121595e-05, + "loss": 4.1604, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846594486370543e-05, + "loss": 4.1622, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845757529499864e-05, + "loss": 4.1519, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844918934748812e-05, + "loss": 4.1588, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.84408033999776e-05, + "loss": 4.1498, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843241745246708e-05, + "loss": 4.1557, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842403150495656e-05, + "loss": 4.1361, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.841564555744604e-05, + "loss": 4.1451, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840727598873925e-05, + "loss": 4.1404, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.839889004122873e-05, + "loss": 4.1549, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839050409371821e-05, + "loss": 4.1322, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.8382118146207687e-05, + "loss": 4.1427, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.8373732198697167e-05, + "loss": 4.1423, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.836536262999038e-05, + "loss": 4.1332, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.835697668247986e-05, + "loss": 4.1457, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.834859073496934e-05, + "loss": 4.1181, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834020478745882e-05, + "loss": 4.1267, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.8331818839948295e-05, + "loss": 4.1391, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.832344927124151e-05, + "loss": 4.1309, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.831506332373099e-05, + "loss": 4.1236, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.830667737622047e-05, + "loss": 4.1184, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.8298291428709944e-05, + "loss": 4.1233, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.828992186000316e-05, + "loss": 4.1115, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.828153591249264e-05, + "loss": 4.1297, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.827314996498212e-05, + "loss": 4.1034, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.82647640174716e-05, + "loss": 4.1173, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.8256394448764816e-05, + "loss": 4.1173, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.8248008501254296e-05, + "loss": 4.1114, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.823962255374377e-05, + "loss": 4.12, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.823123660623325e-05, + "loss": 4.11, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.822285065872273e-05, + "loss": 4.0959, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.8214481090015945e-05, + "loss": 4.0978, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.820609514250542e-05, + "loss": 4.1209, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.81977091949949e-05, + "loss": 4.099, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.818932324748438e-05, + "loss": 4.1004, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.8180953678777594e-05, + "loss": 4.0928, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.8172567731267074e-05, + "loss": 4.0949, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.8164181783756554e-05, + "loss": 4.1078, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.8155795836246034e-05, + "loss": 4.1109, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.814742626753924e-05, + "loss": 4.0962, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.813904032002872e-05, + "loss": 4.1079, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.81306543725182e-05, + "loss": 4.1115, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.812226842500768e-05, + "loss": 4.1053, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.811388247749716e-05, + "loss": 4.0862, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.810551290879037e-05, + "loss": 4.0988, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.809712696127985e-05, + "loss": 4.0922, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.808874101376933e-05, + "loss": 4.0919, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808035506625881e-05, + "loss": 4.0883, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807198549755203e-05, + "loss": 4.0924, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806359955004151e-05, + "loss": 4.0995, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805521360253099e-05, + "loss": 4.092, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804682765502047e-05, + "loss": 4.0732, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803844170750995e-05, + "loss": 4.0788, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.8030072138803156e-05, + "loss": 4.082, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.8021686191292636e-05, + "loss": 4.0847, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.8013300243782116e-05, + "loss": 4.0864, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.8004930675075325e-05, + "loss": 4.0729, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.7996544727564805e-05, + "loss": 4.0803, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.7988158780054285e-05, + "loss": 4.0633, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.7979772832543765e-05, + "loss": 4.0786, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.7971386885033245e-05, + "loss": 4.0778, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.796301731632646e-05, + "loss": 4.0748, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.795463136881594e-05, + "loss": 4.0811, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.794624542130542e-05, + "loss": 4.0674, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.79378594737949e-05, + "loss": 4.0701, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.792948990508811e-05, + "loss": 4.0743, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.792110395757759e-05, + "loss": 4.072, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.791271801006707e-05, + "loss": 4.0679, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.790433206255655e-05, + "loss": 4.0625, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.789596249384976e-05, + "loss": 4.0623, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.788757654633924e-05, + "loss": 4.0683, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.787919059882872e-05, + "loss": 4.067, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.78708046513182e-05, + "loss": 4.0473, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.7862451461415144e-05, + "loss": 4.0617, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.7854065513904624e-05, + "loss": 4.0629, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.7845679566394104e-05, + "loss": 4.0583, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.7837293618883584e-05, + "loss": 4.0527, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.7828907671373064e-05, + "loss": 4.0534, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.7820521723862544e-05, + "loss": 4.0466, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.7812135776352024e-05, + "loss": 4.0683, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.7803749828841504e-05, + "loss": 4.0499, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.779538026013471e-05, + "loss": 4.0567, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.778699431262419e-05, + "loss": 4.054, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.777860836511367e-05, + "loss": 4.0641, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.777023879640689e-05, + "loss": 4.0501, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.776185284889637e-05, + "loss": 4.0531, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.775346690138585e-05, + "loss": 4.0605, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.774508095387533e-05, + "loss": 4.0504, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773669500636481e-05, + "loss": 4.0437, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772830905885429e-05, + "loss": 4.0455, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.771992311134377e-05, + "loss": 4.0396, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771153716383325e-05, + "loss": 4.0427, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770316759512646e-05, + "loss": 4.0438, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.769478164761594e-05, + "loss": 4.0426, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.768639570010542e-05, + "loss": 4.0346, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.76780097525949e-05, + "loss": 4.0375, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.7669640183888106e-05, + "loss": 4.0342, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.7661254236377586e-05, + "loss": 4.0521, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765286828886707e-05, + "loss": 4.0513, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764448234135655e-05, + "loss": 4.0381, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.763611277264976e-05, + "loss": 4.0268, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762772682513924e-05, + "loss": 4.0409, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761934087762872e-05, + "loss": 4.0408, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.7610954930118195e-05, + "loss": 4.0414, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.760258536141141e-05, + "loss": 4.0351, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.759419941390089e-05, + "loss": 4.0395, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.758581346639037e-05, + "loss": 4.032, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.7577427518879844e-05, + "loss": 4.0345, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.756905795017306e-05, + "loss": 4.029, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.756067200266254e-05, + "loss": 4.032, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.755228605515202e-05, + "loss": 4.0251, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.75439001076415e-05, + "loss": 4.0203, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.7535530538934716e-05, + "loss": 4.0334, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.7527144591424196e-05, + "loss": 4.0297, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.751875864391367e-05, + "loss": 4.0321, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.751037269640315e-05, + "loss": 4.0236, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.7502003127696365e-05, + "loss": 4.0225, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.027788162231445, + "eval_runtime": 303.457, + "eval_samples_per_second": 1257.48, + "eval_steps_per_second": 39.297, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.7493617180185845e-05, + "loss": 4.0158, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748523123267532e-05, + "loss": 4.0142, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.74768452851648e-05, + "loss": 4.028, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.746845933765428e-05, + "loss": 4.0171, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.7460073390143764e-05, + "loss": 4.0283, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.7451687442633244e-05, + "loss": 4.0091, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.7443301495122724e-05, + "loss": 4.0209, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434915547612204e-05, + "loss": 4.0089, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.7426529600101684e-05, + "loss": 4.0165, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.7418143652591164e-05, + "loss": 4.0115, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.7409757705080644e-05, + "loss": 4.0191, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.740138813637385e-05, + "loss": 4.0151, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739301856766706e-05, + "loss": 4.0006, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738463262015654e-05, + "loss": 4.0035, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737624667264602e-05, + "loss": 4.0019, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.73678607251355e-05, + "loss": 4.0036, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735947477762498e-05, + "loss": 4.0038, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735108883011446e-05, + "loss": 3.9981, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734270288260394e-05, + "loss": 4.0003, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733433331389716e-05, + "loss": 4.0191, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732594736638664e-05, + "loss": 4.0057, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731756141887612e-05, + "loss": 4.0058, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.73091754713656e-05, + "loss": 4.0033, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730080590265881e-05, + "loss": 4.0088, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729241995514829e-05, + "loss": 3.9858, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728403400763777e-05, + "loss": 4.0007, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727564806012725e-05, + "loss": 3.9984, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.7267278491420456e-05, + "loss": 3.9915, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.7258892543909936e-05, + "loss": 3.9876, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.7250506596399416e-05, + "loss": 3.9854, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.7242120648888896e-05, + "loss": 3.9936, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723375108018211e-05, + "loss": 4.0054, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.722536513267159e-05, + "loss": 3.9925, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721697918516107e-05, + "loss": 3.9946, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720859323765055e-05, + "loss": 3.9877, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720022366894376e-05, + "loss": 3.9898, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719183772143324e-05, + "loss": 3.9823, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.718345177392272e-05, + "loss": 3.9958, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.71750658264122e-05, + "loss": 3.9708, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.716669625770541e-05, + "loss": 3.9843, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.715831031019489e-05, + "loss": 3.9782, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.714992436268437e-05, + "loss": 3.9956, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714153841517385e-05, + "loss": 3.9753, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.7133168846467065e-05, + "loss": 3.9809, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.7124782898956545e-05, + "loss": 3.9846, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.7116396951446025e-05, + "loss": 3.9747, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.7108011003935505e-05, + "loss": 3.9841, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.7099641435228714e-05, + "loss": 3.9657, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.709127186652192e-05, + "loss": 3.9721, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.70828859190114e-05, + "loss": 3.9831, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.707449997150088e-05, + "loss": 3.9738, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706611402399036e-05, + "loss": 3.9708, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705772807647984e-05, + "loss": 3.967, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704934212896932e-05, + "loss": 3.9747, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.70409561814588e-05, + "loss": 3.9573, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703257023394828e-05, + "loss": 3.9757, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.70242006652415e-05, + "loss": 3.9536, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.701581471773098e-05, + "loss": 3.9702, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.700742877022045e-05, + "loss": 3.9733, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.699904282270993e-05, + "loss": 3.9615, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699067325400315e-05, + "loss": 3.9682, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.698228730649263e-05, + "loss": 3.9688, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.69739013589821e-05, + "loss": 3.9479, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696551541147158e-05, + "loss": 3.9562, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.69571458427648e-05, + "loss": 3.967, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694875989525428e-05, + "loss": 3.9625, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694039032654749e-05, + "loss": 3.9604, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693200437903697e-05, + "loss": 3.9467, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692361843152645e-05, + "loss": 3.9526, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.6915232484015926e-05, + "loss": 3.9672, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.6906846536505406e-05, + "loss": 3.9687, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.6898460588994886e-05, + "loss": 3.9533, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.6890074641484366e-05, + "loss": 3.9694, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.6881688693973846e-05, + "loss": 3.9718, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.6873319125267055e-05, + "loss": 3.9741, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.6864933177756535e-05, + "loss": 3.9432, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.6856547230246015e-05, + "loss": 3.9642, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6848161282735495e-05, + "loss": 3.9555, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683979171402871e-05, + "loss": 3.9522, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.6831422145321926e-05, + "loss": 3.9557, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.68230361978114e-05, + "loss": 3.9576, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681465025030088e-05, + "loss": 3.9606, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.680626430279036e-05, + "loss": 3.9599, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679787835527984e-05, + "loss": 3.938, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678949240776932e-05, + "loss": 3.9465, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.67811064602588e-05, + "loss": 3.9476, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.677272051274828e-05, + "loss": 3.9519, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676435094404149e-05, + "loss": 3.9569, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675596499653097e-05, + "loss": 3.9406, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674757904902045e-05, + "loss": 3.9492, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.6739193101509935e-05, + "loss": 3.9345, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.673083991160687e-05, + "loss": 3.9477, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.672245396409635e-05, + "loss": 3.9479, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.671406801658583e-05, + "loss": 3.9466, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670568206907531e-05, + "loss": 3.9512, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.669729612156479e-05, + "loss": 3.9468, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.668891017405427e-05, + "loss": 3.9383, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668052422654375e-05, + "loss": 3.9494, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667213827903323e-05, + "loss": 3.9465, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666376871032644e-05, + "loss": 3.9429, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665538276281592e-05, + "loss": 3.9334, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.66469968153054e-05, + "loss": 3.9384, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663861086779488e-05, + "loss": 3.9442, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.66302412990881e-05, + "loss": 3.9455, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662185535157758e-05, + "loss": 3.9211, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661348578287079e-05, + "loss": 3.9367, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660509983536027e-05, + "loss": 3.9445, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659671388784975e-05, + "loss": 3.9365, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.658832794033923e-05, + "loss": 3.9303, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.6579941992828707e-05, + "loss": 3.9347, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.6571556045318187e-05, + "loss": 3.9274, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.6563170097807667e-05, + "loss": 3.9457, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.6554800529100876e-05, + "loss": 3.9293, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.6546414581590356e-05, + "loss": 3.9391, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.6538028634079836e-05, + "loss": 3.9374, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.652964268656932e-05, + "loss": 3.9415, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.652127311786253e-05, + "loss": 3.9315, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651288717035201e-05, + "loss": 3.939, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650450122284149e-05, + "loss": 3.9428, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649611527533097e-05, + "loss": 3.933, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648772932782045e-05, + "loss": 3.9228, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.647934338030993e-05, + "loss": 3.9287, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.6470957432799404e-05, + "loss": 3.9236, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.646258786409262e-05, + "loss": 3.9302, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.64542019165821e-05, + "loss": 3.9255, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.644581596907158e-05, + "loss": 3.9292, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.643743002156106e-05, + "loss": 3.9195, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.6429060452854276e-05, + "loss": 3.9208, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.6420674505343756e-05, + "loss": 3.9211, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.6412304936636965e-05, + "loss": 3.9382, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.6403918989126445e-05, + "loss": 3.9372, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.6395533041615925e-05, + "loss": 3.9282, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.6387147094105405e-05, + "loss": 3.9151, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.637876114659488e-05, + "loss": 3.9263, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.6370391577888094e-05, + "loss": 3.9312, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.6362005630377574e-05, + "loss": 3.9278, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.6353619682867054e-05, + "loss": 3.9221, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.634523373535653e-05, + "loss": 3.9263, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.6336847787846014e-05, + "loss": 3.9224, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.6328461840335494e-05, + "loss": 3.9317, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.6320075892824974e-05, + "loss": 3.9137, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.6311689945314454e-05, + "loss": 3.9265, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.630332037660766e-05, + "loss": 3.9153, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629493442909714e-05, + "loss": 3.91, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.628654848158662e-05, + "loss": 3.9259, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.62781625340761e-05, + "loss": 3.9248, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626977658656558e-05, + "loss": 3.9218, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626139063905506e-05, + "loss": 3.9176, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625300469154454e-05, + "loss": 3.9119, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.9528229236602783, + "eval_runtime": 303.3267, + "eval_samples_per_second": 1258.02, + "eval_steps_per_second": 39.314, + "step": 228960 + }, + { + "epoch": 0.0, + "learning_rate": 4.624461874403402e-05, + "loss": 3.9121, + "step": 229376 + }, + { + "epoch": 0.0, + "learning_rate": 4.62362327965235e-05, + "loss": 3.9064, + "step": 229888 + }, + { + "epoch": 0.0, + "learning_rate": 4.622784684901298e-05, + "loss": 3.9211, + "step": 230400 + }, + { + "epoch": 0.0, + "learning_rate": 4.621946090150246e-05, + "loss": 3.9098, + "step": 230912 + }, + { + "epoch": 0.0, + "learning_rate": 4.621107495399194e-05, + "loss": 3.929, + "step": 231424 + }, + { + "epoch": 0.0, + "learning_rate": 4.620268900648142e-05, + "loss": 3.9017, + "step": 231936 + }, + { + "epoch": 0.0, + "learning_rate": 4.61943030589709e-05, + "loss": 3.9199, + "step": 232448 + }, + { + "epoch": 0.0, + "learning_rate": 4.618591711146038e-05, + "loss": 3.9029, + "step": 232960 + }, + { + "epoch": 0.0, + "learning_rate": 4.617753116394986e-05, + "loss": 3.916, + "step": 233472 + }, + { + "epoch": 0.0, + "learning_rate": 4.616914521643934e-05, + "loss": 3.9103, + "step": 233984 + }, + { + "epoch": 0.0, + "learning_rate": 4.616077564773255e-05, + "loss": 3.9088, + "step": 234496 + }, + { + "epoch": 0.0, + "learning_rate": 4.615238970022203e-05, + "loss": 3.9171, + "step": 235008 + }, + { + "epoch": 0.0, + "learning_rate": 4.614400375271151e-05, + "loss": 3.898, + "step": 235520 + }, + { + "epoch": 0.0, + "learning_rate": 4.613561780520099e-05, + "loss": 3.9037, + "step": 236032 + }, + { + "epoch": 0.0, + "learning_rate": 4.612723185769047e-05, + "loss": 3.9007, + "step": 236544 + }, + { + "epoch": 0.0, + "learning_rate": 4.611884591017995e-05, + "loss": 3.9023, + "step": 237056 + }, + { + "epoch": 0.0, + "learning_rate": 4.611045996266943e-05, + "loss": 3.9029, + "step": 237568 + }, + { + "epoch": 0.0, + "learning_rate": 4.610209039396265e-05, + "loss": 3.8981, + "step": 238080 + }, + { + "epoch": 0.0, + "learning_rate": 4.609370444645213e-05, + "loss": 3.9011, + "step": 238592 + }, + { + "epoch": 0.0, + "learning_rate": 4.6085318498941607e-05, + "loss": 3.9191, + "step": 239104 + }, + { + "epoch": 0.0, + "learning_rate": 4.6076932551431087e-05, + "loss": 3.9056, + "step": 239616 + }, + { + "epoch": 0.0, + "learning_rate": 4.6068546603920566e-05, + "loss": 3.9064, + "step": 240128 + }, + { + "epoch": 0.0, + "learning_rate": 4.6060160656410046e-05, + "loss": 3.906, + "step": 240640 + }, + { + "epoch": 0.0, + "learning_rate": 4.6051774708899526e-05, + "loss": 3.9078, + "step": 241152 + }, + { + "epoch": 0.0, + "learning_rate": 4.6043388761389006e-05, + "loss": 3.8897, + "step": 241664 + }, + { + "epoch": 0.0, + "learning_rate": 4.6035019192682215e-05, + "loss": 3.9097, + "step": 242176 + }, + { + "epoch": 0.0, + "learning_rate": 4.6026633245171695e-05, + "loss": 3.8961, + "step": 242688 + }, + { + "epoch": 0.0, + "learning_rate": 4.6018247297661175e-05, + "loss": 3.8933, + "step": 243200 + }, + { + "epoch": 0.0, + "learning_rate": 4.6009861350150655e-05, + "loss": 3.887, + "step": 243712 + }, + { + "epoch": 0.01, + "learning_rate": 4.6001491781443864e-05, + "loss": 3.8944, + "step": 244224 + }, + { + "epoch": 0.01, + "learning_rate": 4.5993105833933344e-05, + "loss": 3.8952, + "step": 244736 + }, + { + "epoch": 0.01, + "learning_rate": 4.598471988642283e-05, + "loss": 3.9108, + "step": 245248 + }, + { + "epoch": 0.01, + "learning_rate": 4.597633393891231e-05, + "loss": 3.9, + "step": 245760 + }, + { + "epoch": 0.01, + "learning_rate": 4.596796437020552e-05, + "loss": 3.899, + "step": 246272 + }, + { + "epoch": 0.01, + "learning_rate": 4.595959480149873e-05, + "loss": 3.8882, + "step": 246784 + }, + { + "epoch": 0.01, + "learning_rate": 4.595120885398821e-05, + "loss": 3.8986, + "step": 247296 + }, + { + "epoch": 0.01, + "learning_rate": 4.594282290647769e-05, + "loss": 3.8851, + "step": 247808 + }, + { + "epoch": 0.01, + "learning_rate": 4.593443695896717e-05, + "loss": 3.9021, + "step": 248320 + }, + { + "epoch": 0.01, + "learning_rate": 4.592606739026038e-05, + "loss": 3.8762, + "step": 248832 + }, + { + "epoch": 0.01, + "learning_rate": 4.591768144274986e-05, + "loss": 3.8888, + "step": 249344 + }, + { + "epoch": 0.01, + "learning_rate": 4.590929549523934e-05, + "loss": 3.8866, + "step": 249856 + }, + { + "epoch": 0.01, + "learning_rate": 4.590090954772882e-05, + "loss": 3.9024, + "step": 250368 + }, + { + "epoch": 0.01, + "learning_rate": 4.58925236002183e-05, + "loss": 3.8849, + "step": 250880 + }, + { + "epoch": 0.01, + "learning_rate": 4.5884154031511514e-05, + "loss": 3.8875, + "step": 251392 + }, + { + "epoch": 0.01, + "learning_rate": 4.5875768084000994e-05, + "loss": 3.8897, + "step": 251904 + }, + { + "epoch": 0.01, + "learning_rate": 4.5867382136490474e-05, + "loss": 3.8865, + "step": 252416 + }, + { + "epoch": 0.01, + "learning_rate": 4.5858996188979954e-05, + "loss": 3.8922, + "step": 252928 + }, + { + "epoch": 0.01, + "learning_rate": 4.585061024146943e-05, + "loss": 3.8788, + "step": 253440 + }, + { + "epoch": 0.01, + "learning_rate": 4.584224067276264e-05, + "loss": 3.8754, + "step": 253952 + }, + { + "epoch": 0.01, + "learning_rate": 4.583385472525212e-05, + "loss": 3.8918, + "step": 254464 + }, + { + "epoch": 0.01, + "learning_rate": 4.58254687777416e-05, + "loss": 3.8824, + "step": 254976 + }, + { + "epoch": 0.01, + "learning_rate": 4.5817082830231076e-05, + "loss": 3.8821, + "step": 255488 + }, + { + "epoch": 0.01, + "learning_rate": 4.5808696882720556e-05, + "loss": 3.8797, + "step": 256000 + }, + { + "epoch": 0.01, + "learning_rate": 4.5800310935210036e-05, + "loss": 3.883, + "step": 256512 + }, + { + "epoch": 0.01, + "learning_rate": 4.579194136650325e-05, + "loss": 3.8671, + "step": 257024 + }, + { + "epoch": 0.01, + "learning_rate": 4.578355541899273e-05, + "loss": 3.8873, + "step": 257536 + }, + { + "epoch": 0.01, + "learning_rate": 4.577516947148221e-05, + "loss": 3.8636, + "step": 258048 + }, + { + "epoch": 0.01, + "learning_rate": 4.576678352397169e-05, + "loss": 3.8828, + "step": 258560 + }, + { + "epoch": 0.01, + "learning_rate": 4.575839757646117e-05, + "loss": 3.8799, + "step": 259072 + }, + { + "epoch": 0.01, + "learning_rate": 4.575001162895065e-05, + "loss": 3.881, + "step": 259584 + }, + { + "epoch": 0.01, + "learning_rate": 4.574162568144013e-05, + "loss": 3.8751, + "step": 260096 + }, + { + "epoch": 0.01, + "learning_rate": 4.573325611273334e-05, + "loss": 3.8828, + "step": 260608 + }, + { + "epoch": 0.01, + "learning_rate": 4.572487016522282e-05, + "loss": 3.8594, + "step": 261120 + }, + { + "epoch": 0.01, + "learning_rate": 4.57164842177123e-05, + "loss": 3.8725, + "step": 261632 + }, + { + "epoch": 0.01, + "learning_rate": 4.570809827020178e-05, + "loss": 3.8805, + "step": 262144 + }, + { + "epoch": 0.01, + "learning_rate": 4.569972870149499e-05, + "loss": 3.8764, + "step": 262656 + }, + { + "epoch": 0.01, + "learning_rate": 4.5691359132788205e-05, + "loss": 3.8666, + "step": 263168 + }, + { + "epoch": 0.01, + "learning_rate": 4.5682973185277685e-05, + "loss": 3.8656, + "step": 263680 + }, + { + "epoch": 0.01, + "learning_rate": 4.5674587237767165e-05, + "loss": 3.8654, + "step": 264192 + }, + { + "epoch": 0.01, + "learning_rate": 4.5666201290256645e-05, + "loss": 3.8762, + "step": 264704 + }, + { + "epoch": 0.01, + "learning_rate": 4.5657815342746125e-05, + "loss": 3.8831, + "step": 265216 + }, + { + "epoch": 0.01, + "learning_rate": 4.5649445774039334e-05, + "loss": 3.869, + "step": 265728 + }, + { + "epoch": 0.01, + "learning_rate": 4.5641059826528814e-05, + "loss": 3.8837, + "step": 266240 + }, + { + "epoch": 0.01, + "learning_rate": 4.5632673879018294e-05, + "loss": 3.8848, + "step": 266752 + }, + { + "epoch": 0.01, + "learning_rate": 4.5624287931507774e-05, + "loss": 3.8914, + "step": 267264 + }, + { + "epoch": 0.01, + "learning_rate": 4.561591836280098e-05, + "loss": 3.856, + "step": 267776 + }, + { + "epoch": 0.01, + "learning_rate": 4.560753241529046e-05, + "loss": 3.8764, + "step": 268288 + }, + { + "epoch": 0.01, + "learning_rate": 4.559914646777994e-05, + "loss": 3.8758, + "step": 268800 + }, + { + "epoch": 0.01, + "learning_rate": 4.559076052026943e-05, + "loss": 3.8643, + "step": 269312 + }, + { + "epoch": 0.01, + "learning_rate": 4.558237457275891e-05, + "loss": 3.8731, + "step": 269824 + }, + { + "epoch": 0.01, + "learning_rate": 4.557398862524839e-05, + "loss": 3.8763, + "step": 270336 + }, + { + "epoch": 0.01, + "learning_rate": 4.556560267773787e-05, + "loss": 3.879, + "step": 270848 + }, + { + "epoch": 0.01, + "learning_rate": 4.555723310903108e-05, + "loss": 3.8683, + "step": 271360 + }, + { + "epoch": 0.01, + "learning_rate": 4.554884716152056e-05, + "loss": 3.8613, + "step": 271872 + }, + { + "epoch": 0.01, + "learning_rate": 4.554046121401004e-05, + "loss": 3.8604, + "step": 272384 + }, + { + "epoch": 0.01, + "learning_rate": 4.553207526649952e-05, + "loss": 3.8648, + "step": 272896 + }, + { + "epoch": 0.01, + "learning_rate": 4.552370569779273e-05, + "loss": 3.8716, + "step": 273408 + }, + { + "epoch": 0.01, + "learning_rate": 4.551531975028221e-05, + "loss": 3.8746, + "step": 273920 + }, + { + "epoch": 0.01, + "learning_rate": 4.550693380277169e-05, + "loss": 3.8591, + "step": 274432 + }, + { + "epoch": 0.02, + "learning_rate": 4.549854785526117e-05, + "loss": 3.8661, + "step": 274944 + }, + { + "epoch": 0.02, + "learning_rate": 4.549016190775065e-05, + "loss": 3.8531, + "step": 275456 + }, + { + "epoch": 0.02, + "learning_rate": 4.5481792339043864e-05, + "loss": 3.8634, + "step": 275968 + }, + { + "epoch": 0.02, + "learning_rate": 4.5473406391533343e-05, + "loss": 3.8678, + "step": 276480 + }, + { + "epoch": 0.02, + "learning_rate": 4.5465020444022823e-05, + "loss": 3.8632, + "step": 276992 + }, + { + "epoch": 0.02, + "learning_rate": 4.54566344965123e-05, + "loss": 3.8727, + "step": 277504 + }, + { + "epoch": 0.02, + "learning_rate": 4.544826492780551e-05, + "loss": 3.866, + "step": 278016 + }, + { + "epoch": 0.02, + "learning_rate": 4.543987898029499e-05, + "loss": 3.8587, + "step": 278528 + }, + { + "epoch": 0.02, + "learning_rate": 4.543149303278447e-05, + "loss": 3.8669, + "step": 279040 + }, + { + "epoch": 0.02, + "learning_rate": 4.542310708527395e-05, + "loss": 3.8673, + "step": 279552 + }, + { + "epoch": 0.02, + "learning_rate": 4.541472113776343e-05, + "loss": 3.8674, + "step": 280064 + }, + { + "epoch": 0.02, + "learning_rate": 4.540633519025291e-05, + "loss": 3.8523, + "step": 280576 + }, + { + "epoch": 0.02, + "learning_rate": 4.5397949242742385e-05, + "loss": 3.8577, + "step": 281088 + }, + { + "epoch": 0.02, + "learning_rate": 4.5389563295231865e-05, + "loss": 3.8636, + "step": 281600 + }, + { + "epoch": 0.02, + "learning_rate": 4.538119372652508e-05, + "loss": 3.8706, + "step": 282112 + }, + { + "epoch": 0.02, + "learning_rate": 4.53728241578183e-05, + "loss": 3.8467, + "step": 282624 + }, + { + "epoch": 0.02, + "learning_rate": 4.5364454589111506e-05, + "loss": 3.8525, + "step": 283136 + }, + { + "epoch": 0.02, + "learning_rate": 4.5356068641600986e-05, + "loss": 3.8669, + "step": 283648 + }, + { + "epoch": 0.02, + "learning_rate": 4.5347682694090466e-05, + "loss": 3.8581, + "step": 284160 + }, + { + "epoch": 0.02, + "learning_rate": 4.5339296746579946e-05, + "loss": 3.8519, + "step": 284672 + }, + { + "epoch": 0.02, + "learning_rate": 4.5330910799069426e-05, + "loss": 3.8527, + "step": 285184 + }, + { + "epoch": 0.02, + "learning_rate": 4.5322524851558906e-05, + "loss": 3.8551, + "step": 285696 + }, + { + "epoch": 0.02, + "learning_rate": 4.5314138904048386e-05, + "loss": 3.8628, + "step": 286208 + }, + { + "epoch": 0.02, + "learning_rate": 4.530575295653786e-05, + "loss": 3.8536, + "step": 286720 + }, + { + "epoch": 0.02, + "learning_rate": 4.529736700902734e-05, + "loss": 3.8552, + "step": 287232 + }, + { + "epoch": 0.02, + "learning_rate": 4.5288997440320555e-05, + "loss": 3.8618, + "step": 287744 + }, + { + "epoch": 0.02, + "learning_rate": 4.5280611492810035e-05, + "loss": 3.8638, + "step": 288256 + }, + { + "epoch": 0.02, + "learning_rate": 4.5272225545299515e-05, + "loss": 3.8633, + "step": 288768 + }, + { + "epoch": 0.02, + "learning_rate": 4.5263839597788995e-05, + "loss": 3.8552, + "step": 289280 + }, + { + "epoch": 0.02, + "learning_rate": 4.5255453650278475e-05, + "loss": 3.8695, + "step": 289792 + }, + { + "epoch": 0.02, + "learning_rate": 4.5247067702767955e-05, + "loss": 3.8579, + "step": 290304 + }, + { + "epoch": 0.02, + "learning_rate": 4.5238698134061164e-05, + "loss": 3.843, + "step": 290816 + }, + { + "epoch": 0.02, + "learning_rate": 4.5230312186550644e-05, + "loss": 3.8537, + "step": 291328 + }, + { + "epoch": 0.02, + "learning_rate": 4.5221926239040124e-05, + "loss": 3.8499, + "step": 291840 + }, + { + "epoch": 0.02, + "learning_rate": 4.5213540291529604e-05, + "loss": 3.8561, + "step": 292352 + }, + { + "epoch": 0.02, + "learning_rate": 4.520517072282281e-05, + "loss": 3.846, + "step": 292864 + }, + { + "epoch": 0.02, + "learning_rate": 4.519678477531229e-05, + "loss": 3.8563, + "step": 293376 + }, + { + "epoch": 0.02, + "learning_rate": 4.518839882780177e-05, + "loss": 3.8442, + "step": 293888 + }, + { + "epoch": 0.02, + "learning_rate": 4.518001288029125e-05, + "loss": 3.8468, + "step": 294400 + }, + { + "epoch": 0.02, + "learning_rate": 4.517162693278074e-05, + "loss": 3.8462, + "step": 294912 + }, + { + "epoch": 0.02, + "learning_rate": 4.516325736407395e-05, + "loss": 3.8659, + "step": 295424 + }, + { + "epoch": 0.02, + "learning_rate": 4.515487141656343e-05, + "loss": 3.8587, + "step": 295936 + }, + { + "epoch": 0.02, + "learning_rate": 4.514648546905291e-05, + "loss": 3.8558, + "step": 296448 + }, + { + "epoch": 0.02, + "learning_rate": 4.513809952154239e-05, + "loss": 3.8407, + "step": 296960 + }, + { + "epoch": 0.02, + "learning_rate": 4.51297299528356e-05, + "loss": 3.8541, + "step": 297472 + }, + { + "epoch": 0.02, + "learning_rate": 4.512134400532508e-05, + "loss": 3.8591, + "step": 297984 + }, + { + "epoch": 0.02, + "learning_rate": 4.511295805781456e-05, + "loss": 3.8507, + "step": 298496 + }, + { + "epoch": 0.02, + "learning_rate": 4.510457211030404e-05, + "loss": 3.8487, + "step": 299008 + }, + { + "epoch": 0.02, + "learning_rate": 4.5096202541597246e-05, + "loss": 3.8558, + "step": 299520 + }, + { + "epoch": 0.02, + "learning_rate": 4.5087816594086726e-05, + "loss": 3.849, + "step": 300032 + }, + { + "epoch": 0.02, + "learning_rate": 4.5079430646576206e-05, + "loss": 3.8594, + "step": 300544 + }, + { + "epoch": 0.02, + "learning_rate": 4.507104469906569e-05, + "loss": 3.8377, + "step": 301056 + }, + { + "epoch": 0.02, + "learning_rate": 4.506265875155517e-05, + "loss": 3.8537, + "step": 301568 + }, + { + "epoch": 0.02, + "learning_rate": 4.505428918284838e-05, + "loss": 3.8419, + "step": 302080 + }, + { + "epoch": 0.02, + "learning_rate": 4.504590323533786e-05, + "loss": 3.8423, + "step": 302592 + }, + { + "epoch": 0.02, + "learning_rate": 4.503751728782734e-05, + "loss": 3.8496, + "step": 303104 + }, + { + "epoch": 0.02, + "learning_rate": 4.502913134031682e-05, + "loss": 3.8553, + "step": 303616 + }, + { + "epoch": 0.02, + "learning_rate": 4.50207453928063e-05, + "loss": 3.8486, + "step": 304128 + }, + { + "epoch": 0.02, + "learning_rate": 4.501237582409951e-05, + "loss": 3.8421, + "step": 304640 + }, + { + "epoch": 0.02, + "learning_rate": 4.500398987658899e-05, + "loss": 3.8437, + "step": 305152 + }, + { + "epoch": 0.03, + "eval_loss": 3.9119937419891357, + "eval_runtime": 303.505, + "eval_samples_per_second": 1257.281, + "eval_steps_per_second": 39.291, + "step": 305280 + }, + { + "epoch": 1.0, + "learning_rate": 4.499560392907847e-05, + "loss": 3.8453, + "step": 305664 + }, + { + "epoch": 1.0, + "learning_rate": 4.498721798156795e-05, + "loss": 3.8371, + "step": 306176 + }, + { + "epoch": 1.0, + "learning_rate": 4.497883203405743e-05, + "loss": 3.8472, + "step": 306688 + }, + { + "epoch": 1.0, + "learning_rate": 4.497046246535065e-05, + "loss": 3.8403, + "step": 307200 + }, + { + "epoch": 1.0, + "learning_rate": 4.496207651784013e-05, + "loss": 3.8567, + "step": 307712 + }, + { + "epoch": 1.0, + "learning_rate": 4.495369057032961e-05, + "loss": 3.8368, + "step": 308224 + }, + { + "epoch": 1.0, + "learning_rate": 4.4945304622819087e-05, + "loss": 3.8441, + "step": 308736 + }, + { + "epoch": 1.0, + "learning_rate": 4.4936935054112296e-05, + "loss": 3.8328, + "step": 309248 + }, + { + "epoch": 1.0, + "learning_rate": 4.4928549106601776e-05, + "loss": 3.8448, + "step": 309760 + }, + { + "epoch": 1.0, + "learning_rate": 4.4920163159091256e-05, + "loss": 3.8439, + "step": 310272 + }, + { + "epoch": 1.0, + "learning_rate": 4.4911777211580736e-05, + "loss": 3.8382, + "step": 310784 + }, + { + "epoch": 1.0, + "learning_rate": 4.4903407642873945e-05, + "loss": 3.8431, + "step": 311296 + }, + { + "epoch": 1.0, + "learning_rate": 4.4895021695363425e-05, + "loss": 3.8281, + "step": 311808 + }, + { + "epoch": 1.0, + "learning_rate": 4.4886635747852905e-05, + "loss": 3.8336, + "step": 312320 + }, + { + "epoch": 1.0, + "learning_rate": 4.4878249800342385e-05, + "loss": 3.8333, + "step": 312832 + }, + { + "epoch": 1.0, + "learning_rate": 4.4869863852831864e-05, + "loss": 3.8315, + "step": 313344 + }, + { + "epoch": 1.0, + "learning_rate": 4.486149428412508e-05, + "loss": 3.835, + "step": 313856 + }, + { + "epoch": 1.0, + "learning_rate": 4.485310833661456e-05, + "loss": 3.8316, + "step": 314368 + }, + { + "epoch": 1.0, + "learning_rate": 4.484472238910404e-05, + "loss": 3.8339, + "step": 314880 + }, + { + "epoch": 1.0, + "learning_rate": 4.483633644159352e-05, + "loss": 3.8461, + "step": 315392 + }, + { + "epoch": 1.0, + "learning_rate": 4.482796687288673e-05, + "loss": 3.8406, + "step": 315904 + }, + { + "epoch": 1.0, + "learning_rate": 4.481958092537621e-05, + "loss": 3.8381, + "step": 316416 + }, + { + "epoch": 1.0, + "learning_rate": 4.481119497786569e-05, + "loss": 3.8402, + "step": 316928 + }, + { + "epoch": 1.0, + "learning_rate": 4.480280903035516e-05, + "loss": 3.8403, + "step": 317440 + }, + { + "epoch": 1.0, + "learning_rate": 4.479443946164838e-05, + "loss": 3.8218, + "step": 317952 + }, + { + "epoch": 1.0, + "learning_rate": 4.478605351413786e-05, + "loss": 3.8402, + "step": 318464 + }, + { + "epoch": 1.0, + "learning_rate": 4.477766756662734e-05, + "loss": 3.828, + "step": 318976 + }, + { + "epoch": 1.0, + "learning_rate": 4.476928161911682e-05, + "loss": 3.8241, + "step": 319488 + }, + { + "epoch": 1.0, + "learning_rate": 4.47608956716063e-05, + "loss": 3.8204, + "step": 320000 + }, + { + "epoch": 1.0, + "learning_rate": 4.4752526102899514e-05, + "loss": 3.8277, + "step": 320512 + }, + { + "epoch": 1.01, + "learning_rate": 4.4744140155388994e-05, + "loss": 3.8278, + "step": 321024 + }, + { + "epoch": 1.01, + "learning_rate": 4.473575420787847e-05, + "loss": 3.8439, + "step": 321536 + }, + { + "epoch": 1.01, + "learning_rate": 4.472736826036795e-05, + "loss": 3.8348, + "step": 322048 + }, + { + "epoch": 1.01, + "learning_rate": 4.471898231285743e-05, + "loss": 3.8298, + "step": 322560 + }, + { + "epoch": 1.01, + "learning_rate": 4.4710612744150636e-05, + "loss": 3.8221, + "step": 323072 + }, + { + "epoch": 1.01, + "learning_rate": 4.4702226796640116e-05, + "loss": 3.8332, + "step": 323584 + }, + { + "epoch": 1.01, + "learning_rate": 4.4693840849129596e-05, + "loss": 3.8259, + "step": 324096 + }, + { + "epoch": 1.01, + "learning_rate": 4.4685454901619076e-05, + "loss": 3.8312, + "step": 324608 + }, + { + "epoch": 1.01, + "learning_rate": 4.4677085332912285e-05, + "loss": 3.81, + "step": 325120 + }, + { + "epoch": 1.01, + "learning_rate": 4.466869938540177e-05, + "loss": 3.8218, + "step": 325632 + }, + { + "epoch": 1.01, + "learning_rate": 4.466031343789125e-05, + "loss": 3.8223, + "step": 326144 + }, + { + "epoch": 1.01, + "learning_rate": 4.465192749038073e-05, + "loss": 3.8384, + "step": 326656 + }, + { + "epoch": 1.01, + "learning_rate": 4.464355792167394e-05, + "loss": 3.8246, + "step": 327168 + }, + { + "epoch": 1.01, + "learning_rate": 4.463517197416342e-05, + "loss": 3.8221, + "step": 327680 + }, + { + "epoch": 1.01, + "learning_rate": 4.46267860266529e-05, + "loss": 3.826, + "step": 328192 + }, + { + "epoch": 1.01, + "learning_rate": 4.461840007914238e-05, + "loss": 3.821, + "step": 328704 + }, + { + "epoch": 1.01, + "learning_rate": 4.461003051043559e-05, + "loss": 3.8294, + "step": 329216 + }, + { + "epoch": 1.01, + "learning_rate": 4.460164456292507e-05, + "loss": 3.8153, + "step": 329728 + }, + { + "epoch": 1.01, + "learning_rate": 4.459325861541455e-05, + "loss": 3.811, + "step": 330240 + }, + { + "epoch": 1.01, + "learning_rate": 4.458487266790403e-05, + "loss": 3.8283, + "step": 330752 + }, + { + "epoch": 1.01, + "learning_rate": 4.457648672039351e-05, + "loss": 3.8179, + "step": 331264 + }, + { + "epoch": 1.01, + "learning_rate": 4.4568117151686725e-05, + "loss": 3.8188, + "step": 331776 + }, + { + "epoch": 1.01, + "learning_rate": 4.4559731204176205e-05, + "loss": 3.8134, + "step": 332288 + }, + { + "epoch": 1.01, + "learning_rate": 4.4551345256665685e-05, + "loss": 3.8216, + "step": 332800 + }, + { + "epoch": 1.01, + "learning_rate": 4.4542959309155165e-05, + "loss": 3.804, + "step": 333312 + }, + { + "epoch": 1.01, + "learning_rate": 4.4534589740448374e-05, + "loss": 3.819, + "step": 333824 + }, + { + "epoch": 1.01, + "learning_rate": 4.4526203792937854e-05, + "loss": 3.806, + "step": 334336 + }, + { + "epoch": 1.01, + "learning_rate": 4.4517817845427334e-05, + "loss": 3.8164, + "step": 334848 + }, + { + "epoch": 1.01, + "learning_rate": 4.4509431897916814e-05, + "loss": 3.8191, + "step": 335360 + }, + { + "epoch": 1.01, + "learning_rate": 4.4501045950406294e-05, + "loss": 3.816, + "step": 335872 + }, + { + "epoch": 1.01, + "learning_rate": 4.44926763816995e-05, + "loss": 3.8116, + "step": 336384 + }, + { + "epoch": 1.01, + "learning_rate": 4.448429043418898e-05, + "loss": 3.8238, + "step": 336896 + }, + { + "epoch": 1.01, + "learning_rate": 4.447590448667846e-05, + "loss": 3.7989, + "step": 337408 + }, + { + "epoch": 1.01, + "learning_rate": 4.446751853916794e-05, + "loss": 3.8038, + "step": 337920 + }, + { + "epoch": 1.01, + "learning_rate": 4.445913259165742e-05, + "loss": 3.8182, + "step": 338432 + }, + { + "epoch": 1.01, + "learning_rate": 4.445074664414691e-05, + "loss": 3.8133, + "step": 338944 + }, + { + "epoch": 1.01, + "learning_rate": 4.444236069663639e-05, + "loss": 3.8095, + "step": 339456 + }, + { + "epoch": 1.01, + "learning_rate": 4.44339911279296e-05, + "loss": 3.802, + "step": 339968 + }, + { + "epoch": 1.01, + "learning_rate": 4.442560518041908e-05, + "loss": 3.8026, + "step": 340480 + }, + { + "epoch": 1.01, + "learning_rate": 4.441721923290856e-05, + "loss": 3.8127, + "step": 340992 + }, + { + "epoch": 1.01, + "learning_rate": 4.440883328539804e-05, + "loss": 3.8202, + "step": 341504 + }, + { + "epoch": 1.01, + "learning_rate": 4.440046371669125e-05, + "loss": 3.8124, + "step": 342016 + }, + { + "epoch": 1.01, + "learning_rate": 4.439207776918073e-05, + "loss": 3.8209, + "step": 342528 + }, + { + "epoch": 1.01, + "learning_rate": 4.438369182167021e-05, + "loss": 3.8218, + "step": 343040 + }, + { + "epoch": 1.01, + "learning_rate": 4.437530587415969e-05, + "loss": 3.8342, + "step": 343552 + }, + { + "epoch": 1.01, + "learning_rate": 4.43669363054529e-05, + "loss": 3.8007, + "step": 344064 + }, + { + "epoch": 1.01, + "learning_rate": 4.435855035794238e-05, + "loss": 3.8115, + "step": 344576 + }, + { + "epoch": 1.01, + "learning_rate": 4.4350164410431864e-05, + "loss": 3.821, + "step": 345088 + }, + { + "epoch": 1.01, + "learning_rate": 4.4341778462921344e-05, + "loss": 3.8002, + "step": 345600 + }, + { + "epoch": 1.01, + "learning_rate": 4.4333392515410824e-05, + "loss": 3.8149, + "step": 346112 + }, + { + "epoch": 1.01, + "learning_rate": 4.43250065679003e-05, + "loss": 3.8145, + "step": 346624 + }, + { + "epoch": 1.01, + "learning_rate": 4.431663699919351e-05, + "loss": 3.8157, + "step": 347136 + }, + { + "epoch": 1.01, + "learning_rate": 4.430825105168299e-05, + "loss": 3.8111, + "step": 347648 + }, + { + "epoch": 1.01, + "learning_rate": 4.429986510417247e-05, + "loss": 3.801, + "step": 348160 + }, + { + "epoch": 1.01, + "learning_rate": 4.4291479156661946e-05, + "loss": 3.8011, + "step": 348672 + }, + { + "epoch": 1.01, + "learning_rate": 4.428310958795516e-05, + "loss": 3.8038, + "step": 349184 + }, + { + "epoch": 1.01, + "learning_rate": 4.427472364044464e-05, + "loss": 3.8102, + "step": 349696 + }, + { + "epoch": 1.01, + "learning_rate": 4.426633769293412e-05, + "loss": 3.817, + "step": 350208 + }, + { + "epoch": 1.01, + "learning_rate": 4.42579517454236e-05, + "loss": 3.7992, + "step": 350720 + }, + { + "epoch": 1.02, + "learning_rate": 4.424958217671682e-05, + "loss": 3.8065, + "step": 351232 + }, + { + "epoch": 1.02, + "learning_rate": 4.42411962292063e-05, + "loss": 3.7943, + "step": 351744 + }, + { + "epoch": 1.02, + "learning_rate": 4.423281028169577e-05, + "loss": 3.8035, + "step": 352256 + }, + { + "epoch": 1.02, + "learning_rate": 4.422442433418525e-05, + "loss": 3.8083, + "step": 352768 + }, + { + "epoch": 1.02, + "learning_rate": 4.4216054765478466e-05, + "loss": 3.8078, + "step": 353280 + }, + { + "epoch": 1.02, + "learning_rate": 4.4207668817967946e-05, + "loss": 3.815, + "step": 353792 + }, + { + "epoch": 1.02, + "learning_rate": 4.419928287045742e-05, + "loss": 3.8051, + "step": 354304 + }, + { + "epoch": 1.02, + "learning_rate": 4.41908969229469e-05, + "loss": 3.8021, + "step": 354816 + }, + { + "epoch": 1.02, + "learning_rate": 4.4182527354240115e-05, + "loss": 3.8056, + "step": 355328 + }, + { + "epoch": 1.02, + "learning_rate": 4.4174141406729595e-05, + "loss": 3.8052, + "step": 355840 + }, + { + "epoch": 1.02, + "learning_rate": 4.416575545921907e-05, + "loss": 3.811, + "step": 356352 + }, + { + "epoch": 1.02, + "learning_rate": 4.4157369511708555e-05, + "loss": 3.7956, + "step": 356864 + }, + { + "epoch": 1.02, + "learning_rate": 4.414899994300177e-05, + "loss": 3.8019, + "step": 357376 + }, + { + "epoch": 1.02, + "learning_rate": 4.4140613995491244e-05, + "loss": 3.8023, + "step": 357888 + }, + { + "epoch": 1.02, + "learning_rate": 4.4132228047980724e-05, + "loss": 3.8115, + "step": 358400 + }, + { + "epoch": 1.02, + "learning_rate": 4.4123842100470204e-05, + "loss": 3.79, + "step": 358912 + }, + { + "epoch": 1.02, + "learning_rate": 4.4115456152959684e-05, + "loss": 3.7973, + "step": 359424 + }, + { + "epoch": 1.02, + "learning_rate": 4.410708658425289e-05, + "loss": 3.809, + "step": 359936 + }, + { + "epoch": 1.02, + "learning_rate": 4.409870063674237e-05, + "loss": 3.8019, + "step": 360448 + }, + { + "epoch": 1.02, + "learning_rate": 4.409033106803559e-05, + "loss": 3.7907, + "step": 360960 + }, + { + "epoch": 1.02, + "learning_rate": 4.408194512052507e-05, + "loss": 3.8014, + "step": 361472 + }, + { + "epoch": 1.02, + "learning_rate": 4.407355917301454e-05, + "loss": 3.7939, + "step": 361984 + }, + { + "epoch": 1.02, + "learning_rate": 4.406517322550402e-05, + "loss": 3.8103, + "step": 362496 + }, + { + "epoch": 1.02, + "learning_rate": 4.405678727799351e-05, + "loss": 3.795, + "step": 363008 + }, + { + "epoch": 1.02, + "learning_rate": 4.404840133048299e-05, + "loss": 3.7945, + "step": 363520 + }, + { + "epoch": 1.02, + "learning_rate": 4.404001538297247e-05, + "loss": 3.8077, + "step": 364032 + }, + { + "epoch": 1.02, + "learning_rate": 4.403162943546195e-05, + "loss": 3.8119, + "step": 364544 + }, + { + "epoch": 1.02, + "learning_rate": 4.402325986675516e-05, + "loss": 3.803, + "step": 365056 + }, + { + "epoch": 1.02, + "learning_rate": 4.401487391924464e-05, + "loss": 3.8012, + "step": 365568 + }, + { + "epoch": 1.02, + "learning_rate": 4.400648797173412e-05, + "loss": 3.8068, + "step": 366080 + }, + { + "epoch": 1.02, + "learning_rate": 4.39981020242236e-05, + "loss": 3.7988, + "step": 366592 + }, + { + "epoch": 1.02, + "learning_rate": 4.398973245551681e-05, + "loss": 3.7908, + "step": 367104 + }, + { + "epoch": 1.02, + "learning_rate": 4.3981346508006287e-05, + "loss": 3.8025, + "step": 367616 + }, + { + "epoch": 1.02, + "learning_rate": 4.3972960560495767e-05, + "loss": 3.7912, + "step": 368128 + }, + { + "epoch": 1.02, + "learning_rate": 4.3964574612985247e-05, + "loss": 3.8, + "step": 368640 + }, + { + "epoch": 1.02, + "learning_rate": 4.3956205044278456e-05, + "loss": 3.7909, + "step": 369152 + }, + { + "epoch": 1.02, + "learning_rate": 4.394781909676794e-05, + "loss": 3.7982, + "step": 369664 + }, + { + "epoch": 1.02, + "learning_rate": 4.393943314925742e-05, + "loss": 3.7879, + "step": 370176 + }, + { + "epoch": 1.02, + "learning_rate": 4.39310472017469e-05, + "loss": 3.7873, + "step": 370688 + }, + { + "epoch": 1.02, + "learning_rate": 4.392266125423638e-05, + "loss": 3.7947, + "step": 371200 + }, + { + "epoch": 1.02, + "learning_rate": 4.391429168552959e-05, + "loss": 3.8047, + "step": 371712 + }, + { + "epoch": 1.02, + "learning_rate": 4.390590573801907e-05, + "loss": 3.8038, + "step": 372224 + }, + { + "epoch": 1.02, + "learning_rate": 4.389751979050855e-05, + "loss": 3.8035, + "step": 372736 + }, + { + "epoch": 1.02, + "learning_rate": 4.388913384299803e-05, + "loss": 3.7836, + "step": 373248 + }, + { + "epoch": 1.02, + "learning_rate": 4.388076427429124e-05, + "loss": 3.8021, + "step": 373760 + }, + { + "epoch": 1.02, + "learning_rate": 4.387237832678072e-05, + "loss": 3.8014, + "step": 374272 + }, + { + "epoch": 1.02, + "learning_rate": 4.38639923792702e-05, + "loss": 3.7999, + "step": 374784 + }, + { + "epoch": 1.02, + "learning_rate": 4.385562281056341e-05, + "loss": 3.7899, + "step": 375296 + }, + { + "epoch": 1.02, + "learning_rate": 4.3847236863052896e-05, + "loss": 3.8036, + "step": 375808 + }, + { + "epoch": 1.02, + "learning_rate": 4.3838850915542376e-05, + "loss": 3.7903, + "step": 376320 + }, + { + "epoch": 1.02, + "learning_rate": 4.3830464968031856e-05, + "loss": 3.8065, + "step": 376832 + }, + { + "epoch": 1.02, + "learning_rate": 4.3822079020521336e-05, + "loss": 3.7802, + "step": 377344 + }, + { + "epoch": 1.02, + "learning_rate": 4.3813709451814545e-05, + "loss": 3.8048, + "step": 377856 + }, + { + "epoch": 1.02, + "learning_rate": 4.3805323504304025e-05, + "loss": 3.7856, + "step": 378368 + }, + { + "epoch": 1.02, + "learning_rate": 4.3796937556793505e-05, + "loss": 3.7881, + "step": 378880 + }, + { + "epoch": 1.02, + "learning_rate": 4.3788551609282985e-05, + "loss": 3.7985, + "step": 379392 + }, + { + "epoch": 1.02, + "learning_rate": 4.3780165661772465e-05, + "loss": 3.7946, + "step": 379904 + }, + { + "epoch": 1.02, + "learning_rate": 4.3771796093065674e-05, + "loss": 3.798, + "step": 380416 + }, + { + "epoch": 1.02, + "learning_rate": 4.3763410145555154e-05, + "loss": 3.7822, + "step": 380928 + }, + { + "epoch": 1.02, + "learning_rate": 4.3755024198044634e-05, + "loss": 3.7953, + "step": 381440 + }, + { + "epoch": 1.03, + "eval_loss": 3.887127637863159, + "eval_runtime": 303.6757, + "eval_samples_per_second": 1256.574, + "eval_steps_per_second": 39.269, + "step": 381600 + }, + { + "epoch": 0.0, + "learning_rate": 4.3746638250534114e-05, + "loss": 3.7867, + "step": 381952 + }, + { + "epoch": 0.0, + "learning_rate": 4.3738252303023594e-05, + "loss": 3.7837, + "step": 382464 + }, + { + "epoch": 0.0, + "learning_rate": 4.372986635551308e-05, + "loss": 3.7945, + "step": 382976 + }, + { + "epoch": 0.0, + "learning_rate": 4.3721480408002554e-05, + "loss": 3.7888, + "step": 383488 + }, + { + "epoch": 0.0, + "learning_rate": 4.3713094460492034e-05, + "loss": 3.7996, + "step": 384000 + }, + { + "epoch": 0.0, + "learning_rate": 4.3704708512981514e-05, + "loss": 3.7841, + "step": 384512 + }, + { + "epoch": 0.0, + "learning_rate": 4.3696322565470993e-05, + "loss": 3.7852, + "step": 385024 + }, + { + "epoch": 0.0, + "learning_rate": 4.3687936617960473e-05, + "loss": 3.785, + "step": 385536 + }, + { + "epoch": 0.0, + "learning_rate": 4.367956704925368e-05, + "loss": 3.7905, + "step": 386048 + }, + { + "epoch": 0.0, + "learning_rate": 4.367118110174316e-05, + "loss": 3.7909, + "step": 386560 + }, + { + "epoch": 0.0, + "learning_rate": 4.366279515423264e-05, + "loss": 3.7843, + "step": 387072 + }, + { + "epoch": 0.0, + "learning_rate": 4.365440920672212e-05, + "loss": 3.7934, + "step": 387584 + }, + { + "epoch": 0.0, + "learning_rate": 4.364603963801533e-05, + "loss": 3.7777, + "step": 388096 + }, + { + "epoch": 0.0, + "learning_rate": 4.363765369050482e-05, + "loss": 3.7827, + "step": 388608 + }, + { + "epoch": 0.0, + "learning_rate": 4.36292677429943e-05, + "loss": 3.7832, + "step": 389120 + }, + { + "epoch": 0.0, + "learning_rate": 4.362088179548378e-05, + "loss": 3.776, + "step": 389632 + }, + { + "epoch": 0.0, + "learning_rate": 4.361251222677699e-05, + "loss": 3.7846, + "step": 390144 + }, + { + "epoch": 0.0, + "learning_rate": 4.360412627926647e-05, + "loss": 3.7759, + "step": 390656 + }, + { + "epoch": 0.0, + "learning_rate": 4.359574033175595e-05, + "loss": 3.7771, + "step": 391168 + }, + { + "epoch": 0.0, + "learning_rate": 4.358735438424543e-05, + "loss": 3.7976, + "step": 391680 + }, + { + "epoch": 0.0, + "learning_rate": 4.3578984815538636e-05, + "loss": 3.7861, + "step": 392192 + }, + { + "epoch": 0.0, + "learning_rate": 4.3570598868028116e-05, + "loss": 3.7937, + "step": 392704 + }, + { + "epoch": 0.0, + "learning_rate": 4.3562212920517596e-05, + "loss": 3.7855, + "step": 393216 + }, + { + "epoch": 0.0, + "learning_rate": 4.3553826973007076e-05, + "loss": 3.7891, + "step": 393728 + }, + { + "epoch": 0.0, + "learning_rate": 4.3545441025496556e-05, + "loss": 3.7707, + "step": 394240 + }, + { + "epoch": 0.0, + "learning_rate": 4.353707145678977e-05, + "loss": 3.7914, + "step": 394752 + }, + { + "epoch": 0.0, + "learning_rate": 4.352868550927925e-05, + "loss": 3.7794, + "step": 395264 + }, + { + "epoch": 0.0, + "learning_rate": 4.352029956176873e-05, + "loss": 3.7694, + "step": 395776 + }, + { + "epoch": 0.0, + "learning_rate": 4.351191361425821e-05, + "loss": 3.7711, + "step": 396288 + }, + { + "epoch": 0.0, + "learning_rate": 4.350354404555142e-05, + "loss": 3.7751, + "step": 396800 + }, + { + "epoch": 0.01, + "learning_rate": 4.34951580980409e-05, + "loss": 3.78, + "step": 397312 + }, + { + "epoch": 0.01, + "learning_rate": 4.348677215053038e-05, + "loss": 3.7898, + "step": 397824 + }, + { + "epoch": 0.01, + "learning_rate": 4.347838620301986e-05, + "loss": 3.7874, + "step": 398336 + }, + { + "epoch": 0.01, + "learning_rate": 4.347001663431307e-05, + "loss": 3.7796, + "step": 398848 + }, + { + "epoch": 0.01, + "learning_rate": 4.346163068680255e-05, + "loss": 3.775, + "step": 399360 + }, + { + "epoch": 0.01, + "learning_rate": 4.345324473929203e-05, + "loss": 3.7803, + "step": 399872 + }, + { + "epoch": 0.01, + "learning_rate": 4.344485879178151e-05, + "loss": 3.775, + "step": 400384 + }, + { + "epoch": 0.01, + "learning_rate": 4.3436489223074726e-05, + "loss": 3.7783, + "step": 400896 + }, + { + "epoch": 0.01, + "learning_rate": 4.3428103275564206e-05, + "loss": 3.7662, + "step": 401408 + }, + { + "epoch": 0.01, + "learning_rate": 4.3419717328053685e-05, + "loss": 3.7686, + "step": 401920 + }, + { + "epoch": 0.01, + "learning_rate": 4.3411331380543165e-05, + "loss": 3.7729, + "step": 402432 + }, + { + "epoch": 0.01, + "learning_rate": 4.3402945433032645e-05, + "loss": 3.7871, + "step": 402944 + }, + { + "epoch": 0.01, + "learning_rate": 4.3394575864325854e-05, + "loss": 3.7768, + "step": 403456 + }, + { + "epoch": 0.01, + "learning_rate": 4.3386189916815334e-05, + "loss": 3.7716, + "step": 403968 + }, + { + "epoch": 0.01, + "learning_rate": 4.3377803969304814e-05, + "loss": 3.7788, + "step": 404480 + }, + { + "epoch": 0.01, + "learning_rate": 4.3369418021794294e-05, + "loss": 3.7687, + "step": 404992 + }, + { + "epoch": 0.01, + "learning_rate": 4.3361048453087503e-05, + "loss": 3.7787, + "step": 405504 + }, + { + "epoch": 0.01, + "learning_rate": 4.3352662505576983e-05, + "loss": 3.7668, + "step": 406016 + }, + { + "epoch": 0.01, + "learning_rate": 4.334427655806646e-05, + "loss": 3.7604, + "step": 406528 + }, + { + "epoch": 0.01, + "learning_rate": 4.333589061055594e-05, + "loss": 3.7779, + "step": 407040 + }, + { + "epoch": 0.01, + "learning_rate": 4.332752104184916e-05, + "loss": 3.7709, + "step": 407552 + }, + { + "epoch": 0.01, + "learning_rate": 4.331913509433864e-05, + "loss": 3.77, + "step": 408064 + }, + { + "epoch": 0.01, + "learning_rate": 4.331074914682812e-05, + "loss": 3.7698, + "step": 408576 + }, + { + "epoch": 0.01, + "learning_rate": 4.33023631993176e-05, + "loss": 3.7679, + "step": 409088 + }, + { + "epoch": 0.01, + "learning_rate": 4.329397725180708e-05, + "loss": 3.7597, + "step": 409600 + }, + { + "epoch": 0.01, + "learning_rate": 4.328560768310029e-05, + "loss": 3.7677, + "step": 410112 + }, + { + "epoch": 0.01, + "learning_rate": 4.327722173558977e-05, + "loss": 3.7599, + "step": 410624 + }, + { + "epoch": 0.01, + "learning_rate": 4.326883578807925e-05, + "loss": 3.7645, + "step": 411136 + }, + { + "epoch": 0.01, + "learning_rate": 4.326044984056873e-05, + "loss": 3.7743, + "step": 411648 + }, + { + "epoch": 0.01, + "learning_rate": 4.325208027186194e-05, + "loss": 3.7639, + "step": 412160 + }, + { + "epoch": 0.01, + "learning_rate": 4.324369432435142e-05, + "loss": 3.7657, + "step": 412672 + }, + { + "epoch": 0.01, + "learning_rate": 4.32353083768409e-05, + "loss": 3.7758, + "step": 413184 + }, + { + "epoch": 0.01, + "learning_rate": 4.322692242933038e-05, + "loss": 3.7537, + "step": 413696 + }, + { + "epoch": 0.01, + "learning_rate": 4.321855286062359e-05, + "loss": 3.7572, + "step": 414208 + }, + { + "epoch": 0.01, + "learning_rate": 4.321016691311307e-05, + "loss": 3.7657, + "step": 414720 + }, + { + "epoch": 0.01, + "learning_rate": 4.320178096560255e-05, + "loss": 3.7673, + "step": 415232 + }, + { + "epoch": 0.01, + "learning_rate": 4.319339501809203e-05, + "loss": 3.7567, + "step": 415744 + }, + { + "epoch": 0.01, + "learning_rate": 4.318502544938524e-05, + "loss": 3.7588, + "step": 416256 + }, + { + "epoch": 0.01, + "learning_rate": 4.317663950187472e-05, + "loss": 3.755, + "step": 416768 + }, + { + "epoch": 0.01, + "learning_rate": 4.31682535543642e-05, + "loss": 3.7647, + "step": 417280 + }, + { + "epoch": 0.01, + "learning_rate": 4.315986760685368e-05, + "loss": 3.7718, + "step": 417792 + }, + { + "epoch": 0.01, + "learning_rate": 4.315149803814689e-05, + "loss": 3.7666, + "step": 418304 + }, + { + "epoch": 0.01, + "learning_rate": 4.314311209063637e-05, + "loss": 3.7737, + "step": 418816 + }, + { + "epoch": 0.01, + "learning_rate": 4.313472614312585e-05, + "loss": 3.7681, + "step": 419328 + }, + { + "epoch": 0.01, + "learning_rate": 4.312634019561533e-05, + "loss": 3.7934, + "step": 419840 + }, + { + "epoch": 0.01, + "learning_rate": 4.3117970626908546e-05, + "loss": 3.7543, + "step": 420352 + }, + { + "epoch": 0.01, + "learning_rate": 4.3109584679398026e-05, + "loss": 3.7631, + "step": 420864 + }, + { + "epoch": 0.01, + "learning_rate": 4.3101198731887506e-05, + "loss": 3.774, + "step": 421376 + }, + { + "epoch": 0.01, + "learning_rate": 4.309281278437698e-05, + "loss": 3.7507, + "step": 421888 + }, + { + "epoch": 0.01, + "learning_rate": 4.3084443215670195e-05, + "loss": 3.7695, + "step": 422400 + }, + { + "epoch": 0.01, + "learning_rate": 4.3076057268159675e-05, + "loss": 3.7686, + "step": 422912 + }, + { + "epoch": 0.01, + "learning_rate": 4.3067671320649155e-05, + "loss": 3.768, + "step": 423424 + }, + { + "epoch": 0.01, + "learning_rate": 4.305928537313863e-05, + "loss": 3.7638, + "step": 423936 + }, + { + "epoch": 0.01, + "learning_rate": 4.3050915804431844e-05, + "loss": 3.7511, + "step": 424448 + }, + { + "epoch": 0.01, + "learning_rate": 4.3042529856921324e-05, + "loss": 3.762, + "step": 424960 + }, + { + "epoch": 0.01, + "learning_rate": 4.3034143909410804e-05, + "loss": 3.7527, + "step": 425472 + }, + { + "epoch": 0.01, + "learning_rate": 4.3025757961900284e-05, + "loss": 3.7645, + "step": 425984 + }, + { + "epoch": 0.01, + "learning_rate": 4.30173883931935e-05, + "loss": 3.7718, + "step": 426496 + }, + { + "epoch": 0.01, + "learning_rate": 4.300900244568298e-05, + "loss": 3.7502, + "step": 427008 + }, + { + "epoch": 0.02, + "learning_rate": 4.300061649817245e-05, + "loss": 3.7598, + "step": 427520 + }, + { + "epoch": 0.02, + "learning_rate": 4.299223055066193e-05, + "loss": 3.7526, + "step": 428032 + }, + { + "epoch": 0.02, + "learning_rate": 4.298386098195515e-05, + "loss": 3.7542, + "step": 428544 + }, + { + "epoch": 0.02, + "learning_rate": 4.297547503444463e-05, + "loss": 3.7572, + "step": 429056 + }, + { + "epoch": 0.02, + "learning_rate": 4.29670890869341e-05, + "loss": 3.7684, + "step": 429568 + }, + { + "epoch": 0.02, + "learning_rate": 4.295870313942358e-05, + "loss": 3.77, + "step": 430080 + }, + { + "epoch": 0.02, + "learning_rate": 4.29503335707168e-05, + "loss": 3.7545, + "step": 430592 + }, + { + "epoch": 0.02, + "learning_rate": 4.294194762320628e-05, + "loss": 3.7548, + "step": 431104 + }, + { + "epoch": 0.02, + "learning_rate": 4.293356167569576e-05, + "loss": 3.7629, + "step": 431616 + }, + { + "epoch": 0.02, + "learning_rate": 4.292517572818524e-05, + "loss": 3.7556, + "step": 432128 + }, + { + "epoch": 0.02, + "learning_rate": 4.2916806159478454e-05, + "loss": 3.7671, + "step": 432640 + }, + { + "epoch": 0.02, + "learning_rate": 4.290842021196793e-05, + "loss": 3.7508, + "step": 433152 + }, + { + "epoch": 0.02, + "learning_rate": 4.290003426445741e-05, + "loss": 3.7529, + "step": 433664 + }, + { + "epoch": 0.02, + "learning_rate": 4.289164831694689e-05, + "loss": 3.7605, + "step": 434176 + }, + { + "epoch": 0.02, + "learning_rate": 4.288326236943637e-05, + "loss": 3.7661, + "step": 434688 + }, + { + "epoch": 0.02, + "learning_rate": 4.2874892800729576e-05, + "loss": 3.7448, + "step": 435200 + }, + { + "epoch": 0.02, + "learning_rate": 4.2866506853219056e-05, + "loss": 3.7523, + "step": 435712 + }, + { + "epoch": 0.02, + "learning_rate": 4.285813728451227e-05, + "loss": 3.7602, + "step": 436224 + }, + { + "epoch": 0.02, + "learning_rate": 4.284975133700175e-05, + "loss": 3.7591, + "step": 436736 + }, + { + "epoch": 0.02, + "learning_rate": 4.2841365389491225e-05, + "loss": 3.7446, + "step": 437248 + }, + { + "epoch": 0.02, + "learning_rate": 4.283297944198071e-05, + "loss": 3.7633, + "step": 437760 + }, + { + "epoch": 0.02, + "learning_rate": 4.282459349447019e-05, + "loss": 3.7457, + "step": 438272 + }, + { + "epoch": 0.02, + "learning_rate": 4.281620754695967e-05, + "loss": 3.7619, + "step": 438784 + }, + { + "epoch": 0.02, + "learning_rate": 4.280782159944915e-05, + "loss": 3.7544, + "step": 439296 + }, + { + "epoch": 0.02, + "learning_rate": 4.279945203074236e-05, + "loss": 3.7499, + "step": 439808 + }, + { + "epoch": 0.02, + "learning_rate": 4.279106608323184e-05, + "loss": 3.7602, + "step": 440320 + }, + { + "epoch": 0.02, + "learning_rate": 4.278268013572132e-05, + "loss": 3.7692, + "step": 440832 + }, + { + "epoch": 0.02, + "learning_rate": 4.27742941882108e-05, + "loss": 3.7574, + "step": 441344 + }, + { + "epoch": 0.02, + "learning_rate": 4.276592461950401e-05, + "loss": 3.7549, + "step": 441856 + }, + { + "epoch": 0.02, + "learning_rate": 4.275753867199349e-05, + "loss": 3.7635, + "step": 442368 + }, + { + "epoch": 0.02, + "learning_rate": 4.274915272448297e-05, + "loss": 3.7569, + "step": 442880 + }, + { + "epoch": 0.02, + "learning_rate": 4.274076677697245e-05, + "loss": 3.7468, + "step": 443392 + }, + { + "epoch": 0.02, + "learning_rate": 4.273238082946193e-05, + "loss": 3.7535, + "step": 443904 + }, + { + "epoch": 0.02, + "learning_rate": 4.2724011260755145e-05, + "loss": 3.7484, + "step": 444416 + }, + { + "epoch": 0.02, + "learning_rate": 4.2715625313244625e-05, + "loss": 3.7549, + "step": 444928 + }, + { + "epoch": 0.02, + "learning_rate": 4.2707239365734105e-05, + "loss": 3.7535, + "step": 445440 + }, + { + "epoch": 0.02, + "learning_rate": 4.2698853418223585e-05, + "loss": 3.7509, + "step": 445952 + }, + { + "epoch": 0.02, + "learning_rate": 4.2690483849516794e-05, + "loss": 3.7479, + "step": 446464 + }, + { + "epoch": 0.02, + "learning_rate": 4.2682097902006274e-05, + "loss": 3.7418, + "step": 446976 + }, + { + "epoch": 0.02, + "learning_rate": 4.2673711954495754e-05, + "loss": 3.7533, + "step": 447488 + }, + { + "epoch": 0.02, + "learning_rate": 4.2665326006985234e-05, + "loss": 3.7606, + "step": 448000 + }, + { + "epoch": 0.02, + "learning_rate": 4.265695643827844e-05, + "loss": 3.7583, + "step": 448512 + }, + { + "epoch": 0.02, + "learning_rate": 4.264857049076792e-05, + "loss": 3.7604, + "step": 449024 + }, + { + "epoch": 0.02, + "learning_rate": 4.26401845432574e-05, + "loss": 3.7392, + "step": 449536 + }, + { + "epoch": 0.02, + "learning_rate": 4.263179859574688e-05, + "loss": 3.7613, + "step": 450048 + }, + { + "epoch": 0.02, + "learning_rate": 4.26234290270401e-05, + "loss": 3.7567, + "step": 450560 + }, + { + "epoch": 0.02, + "learning_rate": 4.261504307952958e-05, + "loss": 3.755, + "step": 451072 + }, + { + "epoch": 0.02, + "learning_rate": 4.260665713201906e-05, + "loss": 3.7508, + "step": 451584 + }, + { + "epoch": 0.02, + "learning_rate": 4.259827118450854e-05, + "loss": 3.7568, + "step": 452096 + }, + { + "epoch": 0.02, + "learning_rate": 4.258990161580175e-05, + "loss": 3.7463, + "step": 452608 + }, + { + "epoch": 0.02, + "learning_rate": 4.258151566829123e-05, + "loss": 3.7681, + "step": 453120 + }, + { + "epoch": 0.02, + "learning_rate": 4.257312972078071e-05, + "loss": 3.7357, + "step": 453632 + }, + { + "epoch": 0.02, + "learning_rate": 4.256474377327019e-05, + "loss": 3.7585, + "step": 454144 + }, + { + "epoch": 0.02, + "learning_rate": 4.255635782575967e-05, + "loss": 3.7423, + "step": 454656 + }, + { + "epoch": 0.02, + "learning_rate": 4.254798825705288e-05, + "loss": 3.7472, + "step": 455168 + }, + { + "epoch": 0.02, + "learning_rate": 4.253960230954236e-05, + "loss": 3.7552, + "step": 455680 + }, + { + "epoch": 0.02, + "learning_rate": 4.253121636203184e-05, + "loss": 3.7501, + "step": 456192 + }, + { + "epoch": 0.02, + "learning_rate": 4.252283041452132e-05, + "loss": 3.7601, + "step": 456704 + }, + { + "epoch": 0.02, + "learning_rate": 4.251446084581453e-05, + "loss": 3.7358, + "step": 457216 + }, + { + "epoch": 0.02, + "learning_rate": 4.250607489830401e-05, + "loss": 3.7538, + "step": 457728 + }, + { + "epoch": 0.03, + "eval_loss": 3.8698768615722656, + "eval_runtime": 302.5882, + "eval_samples_per_second": 1261.09, + "eval_steps_per_second": 39.41, + "step": 457920 + }, + { + "epoch": 1.0, + "learning_rate": 4.249768895079349e-05, + "loss": 3.7491, + "step": 458240 + }, + { + "epoch": 1.0, + "learning_rate": 4.248930300328297e-05, + "loss": 3.7393, + "step": 458752 + }, + { + "epoch": 1.0, + "learning_rate": 4.248093343457618e-05, + "loss": 3.7532, + "step": 459264 + }, + { + "epoch": 1.0, + "learning_rate": 4.247254748706566e-05, + "loss": 3.7465, + "step": 459776 + }, + { + "epoch": 1.0, + "learning_rate": 4.246416153955514e-05, + "loss": 3.7546, + "step": 460288 + }, + { + "epoch": 1.0, + "learning_rate": 4.245577559204462e-05, + "loss": 3.7427, + "step": 460800 + }, + { + "epoch": 1.0, + "learning_rate": 4.244740602333783e-05, + "loss": 3.7412, + "step": 461312 + }, + { + "epoch": 1.0, + "learning_rate": 4.243902007582731e-05, + "loss": 3.7441, + "step": 461824 + }, + { + "epoch": 1.0, + "learning_rate": 4.243063412831679e-05, + "loss": 3.746, + "step": 462336 + }, + { + "epoch": 1.0, + "learning_rate": 4.242224818080627e-05, + "loss": 3.7484, + "step": 462848 + }, + { + "epoch": 1.0, + "learning_rate": 4.2413878612099486e-05, + "loss": 3.7461, + "step": 463360 + }, + { + "epoch": 1.0, + "learning_rate": 4.2405492664588966e-05, + "loss": 3.7461, + "step": 463872 + }, + { + "epoch": 1.0, + "learning_rate": 4.2397123095882175e-05, + "loss": 3.7396, + "step": 464384 + }, + { + "epoch": 1.0, + "learning_rate": 4.2388737148371655e-05, + "loss": 3.7392, + "step": 464896 + }, + { + "epoch": 1.0, + "learning_rate": 4.2380351200861135e-05, + "loss": 3.7431, + "step": 465408 + }, + { + "epoch": 1.0, + "learning_rate": 4.2371965253350615e-05, + "loss": 3.7344, + "step": 465920 + }, + { + "epoch": 1.0, + "learning_rate": 4.2363579305840095e-05, + "loss": 3.7413, + "step": 466432 + }, + { + "epoch": 1.0, + "learning_rate": 4.2355193358329575e-05, + "loss": 3.7361, + "step": 466944 + }, + { + "epoch": 1.0, + "learning_rate": 4.2346807410819055e-05, + "loss": 3.7366, + "step": 467456 + }, + { + "epoch": 1.0, + "learning_rate": 4.233842146330853e-05, + "loss": 3.7543, + "step": 467968 + }, + { + "epoch": 1.0, + "learning_rate": 4.2330051894601744e-05, + "loss": 3.7463, + "step": 468480 + }, + { + "epoch": 1.0, + "learning_rate": 4.2321665947091224e-05, + "loss": 3.7508, + "step": 468992 + }, + { + "epoch": 1.0, + "learning_rate": 4.2313279999580704e-05, + "loss": 3.7428, + "step": 469504 + }, + { + "epoch": 1.0, + "learning_rate": 4.2304894052070184e-05, + "loss": 3.7472, + "step": 470016 + }, + { + "epoch": 1.0, + "learning_rate": 4.2296508104559664e-05, + "loss": 3.729, + "step": 470528 + }, + { + "epoch": 1.0, + "learning_rate": 4.228813853585288e-05, + "loss": 3.7499, + "step": 471040 + }, + { + "epoch": 1.0, + "learning_rate": 4.227975258834236e-05, + "loss": 3.7363, + "step": 471552 + }, + { + "epoch": 1.0, + "learning_rate": 4.227136664083183e-05, + "loss": 3.7313, + "step": 472064 + }, + { + "epoch": 1.0, + "learning_rate": 4.226299707212505e-05, + "loss": 3.7306, + "step": 472576 + }, + { + "epoch": 1.0, + "learning_rate": 4.225461112461453e-05, + "loss": 3.7349, + "step": 473088 + }, + { + "epoch": 1.01, + "learning_rate": 4.2246225177104e-05, + "loss": 3.7385, + "step": 473600 + }, + { + "epoch": 1.01, + "learning_rate": 4.223783922959348e-05, + "loss": 3.7504, + "step": 474112 + }, + { + "epoch": 1.01, + "learning_rate": 4.22294696608867e-05, + "loss": 3.7458, + "step": 474624 + }, + { + "epoch": 1.01, + "learning_rate": 4.222108371337618e-05, + "loss": 3.7397, + "step": 475136 + }, + { + "epoch": 1.01, + "learning_rate": 4.221269776586566e-05, + "loss": 3.7282, + "step": 475648 + }, + { + "epoch": 1.01, + "learning_rate": 4.220431181835514e-05, + "loss": 3.7418, + "step": 476160 + }, + { + "epoch": 1.01, + "learning_rate": 4.2195942249648353e-05, + "loss": 3.7389, + "step": 476672 + }, + { + "epoch": 1.01, + "learning_rate": 4.2187556302137833e-05, + "loss": 3.7318, + "step": 477184 + }, + { + "epoch": 1.01, + "learning_rate": 4.217917035462731e-05, + "loss": 3.729, + "step": 477696 + }, + { + "epoch": 1.01, + "learning_rate": 4.2170784407116787e-05, + "loss": 3.727, + "step": 478208 + }, + { + "epoch": 1.01, + "learning_rate": 4.216241483841e-05, + "loss": 3.7332, + "step": 478720 + }, + { + "epoch": 1.01, + "learning_rate": 4.2154028890899476e-05, + "loss": 3.7436, + "step": 479232 + }, + { + "epoch": 1.01, + "learning_rate": 4.2145642943388956e-05, + "loss": 3.7402, + "step": 479744 + }, + { + "epoch": 1.01, + "learning_rate": 4.2137256995878436e-05, + "loss": 3.7324, + "step": 480256 + }, + { + "epoch": 1.01, + "learning_rate": 4.2128871048367915e-05, + "loss": 3.7365, + "step": 480768 + }, + { + "epoch": 1.01, + "learning_rate": 4.212050147966113e-05, + "loss": 3.7284, + "step": 481280 + }, + { + "epoch": 1.01, + "learning_rate": 4.211211553215061e-05, + "loss": 3.74, + "step": 481792 + }, + { + "epoch": 1.01, + "learning_rate": 4.210372958464009e-05, + "loss": 3.7267, + "step": 482304 + }, + { + "epoch": 1.01, + "learning_rate": 4.209534363712957e-05, + "loss": 3.7169, + "step": 482816 + }, + { + "epoch": 1.01, + "learning_rate": 4.208697406842278e-05, + "loss": 3.7385, + "step": 483328 + }, + { + "epoch": 1.01, + "learning_rate": 4.207858812091226e-05, + "loss": 3.7331, + "step": 483840 + }, + { + "epoch": 1.01, + "learning_rate": 4.207020217340174e-05, + "loss": 3.7338, + "step": 484352 + }, + { + "epoch": 1.01, + "learning_rate": 4.206181622589122e-05, + "loss": 3.7257, + "step": 484864 + }, + { + "epoch": 1.01, + "learning_rate": 4.205344665718443e-05, + "loss": 3.7261, + "step": 485376 + }, + { + "epoch": 1.01, + "learning_rate": 4.204506070967391e-05, + "loss": 3.7201, + "step": 485888 + }, + { + "epoch": 1.01, + "learning_rate": 4.203667476216339e-05, + "loss": 3.7255, + "step": 486400 + }, + { + "epoch": 1.01, + "learning_rate": 4.202828881465287e-05, + "loss": 3.7212, + "step": 486912 + }, + { + "epoch": 1.01, + "learning_rate": 4.2019919245946085e-05, + "loss": 3.7287, + "step": 487424 + }, + { + "epoch": 1.01, + "learning_rate": 4.2011533298435565e-05, + "loss": 3.7319, + "step": 487936 + }, + { + "epoch": 1.01, + "learning_rate": 4.2003147350925045e-05, + "loss": 3.7251, + "step": 488448 + }, + { + "epoch": 1.01, + "learning_rate": 4.1994761403414525e-05, + "loss": 3.7245, + "step": 488960 + }, + { + "epoch": 1.01, + "learning_rate": 4.1986391834707734e-05, + "loss": 3.7418, + "step": 489472 + }, + { + "epoch": 1.01, + "learning_rate": 4.1978005887197214e-05, + "loss": 3.7117, + "step": 489984 + }, + { + "epoch": 1.01, + "learning_rate": 4.1969619939686694e-05, + "loss": 3.7168, + "step": 490496 + }, + { + "epoch": 1.01, + "learning_rate": 4.1961233992176174e-05, + "loss": 3.7272, + "step": 491008 + }, + { + "epoch": 1.01, + "learning_rate": 4.195286442346938e-05, + "loss": 3.7325, + "step": 491520 + }, + { + "epoch": 1.01, + "learning_rate": 4.194447847595886e-05, + "loss": 3.7159, + "step": 492032 + }, + { + "epoch": 1.01, + "learning_rate": 4.193609252844834e-05, + "loss": 3.7192, + "step": 492544 + }, + { + "epoch": 1.01, + "learning_rate": 4.192770658093782e-05, + "loss": 3.7171, + "step": 493056 + }, + { + "epoch": 1.01, + "learning_rate": 4.191933701223104e-05, + "loss": 3.7227, + "step": 493568 + }, + { + "epoch": 1.01, + "learning_rate": 4.191095106472052e-05, + "loss": 3.735, + "step": 494080 + }, + { + "epoch": 1.01, + "learning_rate": 4.190256511721e-05, + "loss": 3.7254, + "step": 494592 + }, + { + "epoch": 1.01, + "learning_rate": 4.189417916969948e-05, + "loss": 3.7311, + "step": 495104 + }, + { + "epoch": 1.01, + "learning_rate": 4.188580960099269e-05, + "loss": 3.7356, + "step": 495616 + }, + { + "epoch": 1.01, + "learning_rate": 4.187742365348217e-05, + "loss": 3.7487, + "step": 496128 + }, + { + "epoch": 1.01, + "learning_rate": 4.186903770597165e-05, + "loss": 3.7191, + "step": 496640 + }, + { + "epoch": 1.01, + "learning_rate": 4.186065175846113e-05, + "loss": 3.7274, + "step": 497152 + }, + { + "epoch": 1.01, + "learning_rate": 4.185228218975434e-05, + "loss": 3.7323, + "step": 497664 + }, + { + "epoch": 1.01, + "learning_rate": 4.1843896242243817e-05, + "loss": 3.7147, + "step": 498176 + }, + { + "epoch": 1.01, + "learning_rate": 4.1835510294733297e-05, + "loss": 3.7315, + "step": 498688 + }, + { + "epoch": 1.01, + "learning_rate": 4.1827124347222776e-05, + "loss": 3.7294, + "step": 499200 + }, + { + "epoch": 1.01, + "learning_rate": 4.181875477851599e-05, + "loss": 3.7297, + "step": 499712 + }, + { + "epoch": 1.01, + "learning_rate": 4.181036883100547e-05, + "loss": 3.7286, + "step": 500224 + }, + { + "epoch": 1.01, + "learning_rate": 4.180198288349495e-05, + "loss": 3.7131, + "step": 500736 + }, + { + "epoch": 1.01, + "learning_rate": 4.179359693598443e-05, + "loss": 3.7197, + "step": 501248 + }, + { + "epoch": 1.01, + "learning_rate": 4.178522736727764e-05, + "loss": 3.7182, + "step": 501760 + }, + { + "epoch": 1.01, + "learning_rate": 4.177684141976712e-05, + "loss": 3.7246, + "step": 502272 + }, + { + "epoch": 1.01, + "learning_rate": 4.17684554722566e-05, + "loss": 3.7318, + "step": 502784 + }, + { + "epoch": 1.01, + "learning_rate": 4.176006952474608e-05, + "loss": 3.7132, + "step": 503296 + }, + { + "epoch": 1.02, + "learning_rate": 4.175169995603929e-05, + "loss": 3.7229, + "step": 503808 + }, + { + "epoch": 1.02, + "learning_rate": 4.174331400852877e-05, + "loss": 3.7161, + "step": 504320 + }, + { + "epoch": 1.02, + "learning_rate": 4.173492806101825e-05, + "loss": 3.7125, + "step": 504832 + }, + { + "epoch": 1.02, + "learning_rate": 4.172654211350773e-05, + "loss": 3.7245, + "step": 505344 + }, + { + "epoch": 1.02, + "learning_rate": 4.1718172544800946e-05, + "loss": 3.7264, + "step": 505856 + }, + { + "epoch": 1.02, + "learning_rate": 4.1709786597290426e-05, + "loss": 3.7328, + "step": 506368 + }, + { + "epoch": 1.02, + "learning_rate": 4.1701400649779906e-05, + "loss": 3.721, + "step": 506880 + }, + { + "epoch": 1.02, + "learning_rate": 4.1693014702269386e-05, + "loss": 3.7149, + "step": 507392 + }, + { + "epoch": 1.02, + "learning_rate": 4.1684645133562595e-05, + "loss": 3.7241, + "step": 507904 + }, + { + "epoch": 1.02, + "learning_rate": 4.1676259186052075e-05, + "loss": 3.7207, + "step": 508416 + }, + { + "epoch": 1.02, + "learning_rate": 4.1667873238541555e-05, + "loss": 3.7283, + "step": 508928 + }, + { + "epoch": 1.02, + "learning_rate": 4.1659487291031035e-05, + "loss": 3.715, + "step": 509440 + }, + { + "epoch": 1.02, + "learning_rate": 4.1651117722324244e-05, + "loss": 3.7157, + "step": 509952 + }, + { + "epoch": 1.02, + "learning_rate": 4.1642731774813724e-05, + "loss": 3.7205, + "step": 510464 + }, + { + "epoch": 1.02, + "learning_rate": 4.1634345827303204e-05, + "loss": 3.7317, + "step": 510976 + }, + { + "epoch": 1.02, + "learning_rate": 4.1625959879792684e-05, + "loss": 3.7041, + "step": 511488 + }, + { + "epoch": 1.02, + "learning_rate": 4.16175903110859e-05, + "loss": 3.7176, + "step": 512000 + }, + { + "epoch": 1.02, + "learning_rate": 4.160920436357538e-05, + "loss": 3.7201, + "step": 512512 + }, + { + "epoch": 1.02, + "learning_rate": 4.160081841606486e-05, + "loss": 3.724, + "step": 513024 + }, + { + "epoch": 1.02, + "learning_rate": 4.159244884735807e-05, + "loss": 3.7054, + "step": 513536 + }, + { + "epoch": 1.02, + "learning_rate": 4.158406289984755e-05, + "loss": 3.722, + "step": 514048 + }, + { + "epoch": 1.02, + "learning_rate": 4.157567695233703e-05, + "loss": 3.7162, + "step": 514560 + }, + { + "epoch": 1.02, + "learning_rate": 4.156729100482651e-05, + "loss": 3.7202, + "step": 515072 + }, + { + "epoch": 1.02, + "learning_rate": 4.155890505731599e-05, + "loss": 3.7216, + "step": 515584 + }, + { + "epoch": 1.02, + "learning_rate": 4.155051910980547e-05, + "loss": 3.7144, + "step": 516096 + }, + { + "epoch": 1.02, + "learning_rate": 4.154213316229495e-05, + "loss": 3.7178, + "step": 516608 + }, + { + "epoch": 1.02, + "learning_rate": 4.153374721478443e-05, + "loss": 3.7327, + "step": 517120 + }, + { + "epoch": 1.02, + "learning_rate": 4.152537764607764e-05, + "loss": 3.72, + "step": 517632 + }, + { + "epoch": 1.02, + "learning_rate": 4.151699169856712e-05, + "loss": 3.7173, + "step": 518144 + }, + { + "epoch": 1.02, + "learning_rate": 4.15086057510566e-05, + "loss": 3.728, + "step": 518656 + }, + { + "epoch": 1.02, + "learning_rate": 4.1500219803546084e-05, + "loss": 3.7204, + "step": 519168 + }, + { + "epoch": 1.02, + "learning_rate": 4.149185023483929e-05, + "loss": 3.7065, + "step": 519680 + }, + { + "epoch": 1.02, + "learning_rate": 4.148346428732877e-05, + "loss": 3.7221, + "step": 520192 + }, + { + "epoch": 1.02, + "learning_rate": 4.147507833981825e-05, + "loss": 3.7105, + "step": 520704 + }, + { + "epoch": 1.02, + "learning_rate": 4.146669239230773e-05, + "loss": 3.7152, + "step": 521216 + }, + { + "epoch": 1.02, + "learning_rate": 4.145832282360094e-05, + "loss": 3.7161, + "step": 521728 + }, + { + "epoch": 1.02, + "learning_rate": 4.144993687609042e-05, + "loss": 3.716, + "step": 522240 + }, + { + "epoch": 1.02, + "learning_rate": 4.14415509285799e-05, + "loss": 3.7134, + "step": 522752 + }, + { + "epoch": 1.02, + "learning_rate": 4.143316498106938e-05, + "loss": 3.7086, + "step": 523264 + }, + { + "epoch": 1.02, + "learning_rate": 4.142479541236259e-05, + "loss": 3.7117, + "step": 523776 + }, + { + "epoch": 1.02, + "learning_rate": 4.141640946485207e-05, + "loss": 3.7282, + "step": 524288 + }, + { + "epoch": 1.02, + "learning_rate": 4.140802351734155e-05, + "loss": 3.719, + "step": 524800 + }, + { + "epoch": 1.02, + "learning_rate": 4.139963756983103e-05, + "loss": 3.724, + "step": 525312 + }, + { + "epoch": 1.02, + "learning_rate": 4.139126800112425e-05, + "loss": 3.7032, + "step": 525824 + }, + { + "epoch": 1.02, + "learning_rate": 4.138288205361373e-05, + "loss": 3.7292, + "step": 526336 + }, + { + "epoch": 1.02, + "learning_rate": 4.137449610610321e-05, + "loss": 3.7182, + "step": 526848 + }, + { + "epoch": 1.02, + "learning_rate": 4.136611015859268e-05, + "loss": 3.7203, + "step": 527360 + }, + { + "epoch": 1.02, + "learning_rate": 4.1357740589885896e-05, + "loss": 3.7141, + "step": 527872 + }, + { + "epoch": 1.02, + "learning_rate": 4.1349354642375376e-05, + "loss": 3.7196, + "step": 528384 + }, + { + "epoch": 1.02, + "learning_rate": 4.1340968694864856e-05, + "loss": 3.7103, + "step": 528896 + }, + { + "epoch": 1.02, + "learning_rate": 4.133258274735433e-05, + "loss": 3.7347, + "step": 529408 + }, + { + "epoch": 1.02, + "learning_rate": 4.1324213178647545e-05, + "loss": 3.6996, + "step": 529920 + }, + { + "epoch": 1.02, + "learning_rate": 4.1315827231137025e-05, + "loss": 3.7195, + "step": 530432 + }, + { + "epoch": 1.02, + "learning_rate": 4.1307441283626505e-05, + "loss": 3.7097, + "step": 530944 + }, + { + "epoch": 1.02, + "learning_rate": 4.1299055336115985e-05, + "loss": 3.7121, + "step": 531456 + }, + { + "epoch": 1.02, + "learning_rate": 4.12906857674092e-05, + "loss": 3.7142, + "step": 531968 + }, + { + "epoch": 1.02, + "learning_rate": 4.128229981989868e-05, + "loss": 3.7125, + "step": 532480 + }, + { + "epoch": 1.02, + "learning_rate": 4.1273913872388154e-05, + "loss": 3.7269, + "step": 532992 + }, + { + "epoch": 1.02, + "learning_rate": 4.1265527924877634e-05, + "loss": 3.7013, + "step": 533504 + }, + { + "epoch": 1.02, + "learning_rate": 4.125715835617085e-05, + "loss": 3.7193, + "step": 534016 + }, + { + "epoch": 1.03, + "eval_loss": 3.859912157058716, + "eval_runtime": 303.7577, + "eval_samples_per_second": 1256.235, + "eval_steps_per_second": 39.258, + "step": 534240 + }, + { + "epoch": 0.0, + "learning_rate": 4.124877240866032e-05, + "loss": 3.7149, + "step": 534528 + }, + { + "epoch": 0.0, + "learning_rate": 4.12403864611498e-05, + "loss": 3.7039, + "step": 535040 + }, + { + "epoch": 0.0, + "learning_rate": 4.123200051363928e-05, + "loss": 3.7154, + "step": 535552 + }, + { + "epoch": 0.0, + "learning_rate": 4.122361456612876e-05, + "loss": 3.7128, + "step": 536064 + }, + { + "epoch": 0.0, + "learning_rate": 4.121522861861824e-05, + "loss": 3.7187, + "step": 536576 + }, + { + "epoch": 0.0, + "learning_rate": 4.120684267110773e-05, + "loss": 3.7058, + "step": 537088 + }, + { + "epoch": 0.0, + "learning_rate": 4.119845672359721e-05, + "loss": 3.7111, + "step": 537600 + }, + { + "epoch": 0.0, + "learning_rate": 4.119007077608669e-05, + "loss": 3.7066, + "step": 538112 + }, + { + "epoch": 0.0, + "learning_rate": 4.11817012073799e-05, + "loss": 3.7151, + "step": 538624 + }, + { + "epoch": 0.0, + "learning_rate": 4.117331525986938e-05, + "loss": 3.7132, + "step": 539136 + }, + { + "epoch": 0.0, + "learning_rate": 4.116492931235886e-05, + "loss": 3.7133, + "step": 539648 + }, + { + "epoch": 0.0, + "learning_rate": 4.115654336484834e-05, + "loss": 3.7073, + "step": 540160 + }, + { + "epoch": 0.0, + "learning_rate": 4.1148190174945276e-05, + "loss": 3.7068, + "step": 540672 + }, + { + "epoch": 0.0, + "learning_rate": 4.1139804227434756e-05, + "loss": 3.705, + "step": 541184 + }, + { + "epoch": 0.0, + "learning_rate": 4.1131418279924236e-05, + "loss": 3.7099, + "step": 541696 + }, + { + "epoch": 0.0, + "learning_rate": 4.1123032332413716e-05, + "loss": 3.6973, + "step": 542208 + }, + { + "epoch": 0.0, + "learning_rate": 4.1114646384903196e-05, + "loss": 3.7043, + "step": 542720 + }, + { + "epoch": 0.0, + "learning_rate": 4.110626043739268e-05, + "loss": 3.6999, + "step": 543232 + }, + { + "epoch": 0.0, + "learning_rate": 4.109787448988216e-05, + "loss": 3.7037, + "step": 543744 + }, + { + "epoch": 0.0, + "learning_rate": 4.108948854237164e-05, + "loss": 3.7149, + "step": 544256 + }, + { + "epoch": 0.0, + "learning_rate": 4.108111897366485e-05, + "loss": 3.7154, + "step": 544768 + }, + { + "epoch": 0.0, + "learning_rate": 4.107273302615433e-05, + "loss": 3.7158, + "step": 545280 + }, + { + "epoch": 0.0, + "learning_rate": 4.106434707864381e-05, + "loss": 3.7094, + "step": 545792 + }, + { + "epoch": 0.0, + "learning_rate": 4.105596113113329e-05, + "loss": 3.7097, + "step": 546304 + }, + { + "epoch": 0.0, + "learning_rate": 4.10475915624265e-05, + "loss": 3.6965, + "step": 546816 + }, + { + "epoch": 0.0, + "learning_rate": 4.103920561491598e-05, + "loss": 3.7178, + "step": 547328 + }, + { + "epoch": 0.0, + "learning_rate": 4.103081966740546e-05, + "loss": 3.7012, + "step": 547840 + }, + { + "epoch": 0.0, + "learning_rate": 4.102243371989494e-05, + "loss": 3.6977, + "step": 548352 + }, + { + "epoch": 0.0, + "learning_rate": 4.101406415118815e-05, + "loss": 3.6974, + "step": 548864 + }, + { + "epoch": 0.0, + "learning_rate": 4.1005678203677637e-05, + "loss": 3.7026, + "step": 549376 + }, + { + "epoch": 0.01, + "learning_rate": 4.0997292256167117e-05, + "loss": 3.7027, + "step": 549888 + }, + { + "epoch": 0.01, + "learning_rate": 4.0988906308656597e-05, + "loss": 3.7162, + "step": 550400 + }, + { + "epoch": 0.01, + "learning_rate": 4.0980536739949806e-05, + "loss": 3.7136, + "step": 550912 + }, + { + "epoch": 0.01, + "learning_rate": 4.0972150792439286e-05, + "loss": 3.7026, + "step": 551424 + }, + { + "epoch": 0.01, + "learning_rate": 4.0963764844928766e-05, + "loss": 3.6969, + "step": 551936 + }, + { + "epoch": 0.01, + "learning_rate": 4.0955378897418245e-05, + "loss": 3.7098, + "step": 552448 + }, + { + "epoch": 0.01, + "learning_rate": 4.0947009328711455e-05, + "loss": 3.707, + "step": 552960 + }, + { + "epoch": 0.01, + "learning_rate": 4.0938623381200935e-05, + "loss": 3.6975, + "step": 553472 + }, + { + "epoch": 0.01, + "learning_rate": 4.0930237433690414e-05, + "loss": 3.6959, + "step": 553984 + }, + { + "epoch": 0.01, + "learning_rate": 4.0921867864983624e-05, + "loss": 3.6937, + "step": 554496 + }, + { + "epoch": 0.01, + "learning_rate": 4.0913481917473104e-05, + "loss": 3.6969, + "step": 555008 + }, + { + "epoch": 0.01, + "learning_rate": 4.0905095969962583e-05, + "loss": 3.7098, + "step": 555520 + }, + { + "epoch": 0.01, + "learning_rate": 4.089671002245207e-05, + "loss": 3.706, + "step": 556032 + }, + { + "epoch": 0.01, + "learning_rate": 4.088834045374528e-05, + "loss": 3.6977, + "step": 556544 + }, + { + "epoch": 0.01, + "learning_rate": 4.087995450623476e-05, + "loss": 3.7043, + "step": 557056 + }, + { + "epoch": 0.01, + "learning_rate": 4.087156855872424e-05, + "loss": 3.6946, + "step": 557568 + }, + { + "epoch": 0.01, + "learning_rate": 4.086318261121372e-05, + "loss": 3.7057, + "step": 558080 + }, + { + "epoch": 0.01, + "learning_rate": 4.085481304250693e-05, + "loss": 3.696, + "step": 558592 + }, + { + "epoch": 0.01, + "learning_rate": 4.084642709499641e-05, + "loss": 3.6797, + "step": 559104 + }, + { + "epoch": 0.01, + "learning_rate": 4.083804114748589e-05, + "loss": 3.7065, + "step": 559616 + }, + { + "epoch": 0.01, + "learning_rate": 4.082965519997537e-05, + "loss": 3.698, + "step": 560128 + }, + { + "epoch": 0.01, + "learning_rate": 4.082128563126858e-05, + "loss": 3.7027, + "step": 560640 + }, + { + "epoch": 0.01, + "learning_rate": 4.081289968375806e-05, + "loss": 3.6931, + "step": 561152 + }, + { + "epoch": 0.01, + "learning_rate": 4.080451373624754e-05, + "loss": 3.6909, + "step": 561664 + }, + { + "epoch": 0.01, + "learning_rate": 4.0796127788737024e-05, + "loss": 3.6887, + "step": 562176 + }, + { + "epoch": 0.01, + "learning_rate": 4.078775822003023e-05, + "loss": 3.6905, + "step": 562688 + }, + { + "epoch": 0.01, + "learning_rate": 4.077937227251971e-05, + "loss": 3.6937, + "step": 563200 + }, + { + "epoch": 0.01, + "learning_rate": 4.077098632500919e-05, + "loss": 3.6941, + "step": 563712 + }, + { + "epoch": 0.01, + "learning_rate": 4.076260037749867e-05, + "loss": 3.7039, + "step": 564224 + }, + { + "epoch": 0.01, + "learning_rate": 4.075423080879188e-05, + "loss": 3.688, + "step": 564736 + }, + { + "epoch": 0.01, + "learning_rate": 4.074584486128136e-05, + "loss": 3.6939, + "step": 565248 + }, + { + "epoch": 0.01, + "learning_rate": 4.073745891377084e-05, + "loss": 3.7063, + "step": 565760 + }, + { + "epoch": 0.01, + "learning_rate": 4.072907296626032e-05, + "loss": 3.6792, + "step": 566272 + }, + { + "epoch": 0.01, + "learning_rate": 4.072070339755353e-05, + "loss": 3.684, + "step": 566784 + }, + { + "epoch": 0.01, + "learning_rate": 4.071231745004301e-05, + "loss": 3.6989, + "step": 567296 + }, + { + "epoch": 0.01, + "learning_rate": 4.070393150253249e-05, + "loss": 3.6966, + "step": 567808 + }, + { + "epoch": 0.01, + "learning_rate": 4.069554555502198e-05, + "loss": 3.6843, + "step": 568320 + }, + { + "epoch": 0.01, + "learning_rate": 4.068717598631519e-05, + "loss": 3.6905, + "step": 568832 + }, + { + "epoch": 0.01, + "learning_rate": 4.0678790038804667e-05, + "loss": 3.6827, + "step": 569344 + }, + { + "epoch": 0.01, + "learning_rate": 4.0670404091294147e-05, + "loss": 3.6933, + "step": 569856 + }, + { + "epoch": 0.01, + "learning_rate": 4.0662018143783627e-05, + "loss": 3.6973, + "step": 570368 + }, + { + "epoch": 0.01, + "learning_rate": 4.0653648575076836e-05, + "loss": 3.6955, + "step": 570880 + }, + { + "epoch": 0.01, + "learning_rate": 4.0645262627566316e-05, + "loss": 3.6961, + "step": 571392 + }, + { + "epoch": 0.01, + "learning_rate": 4.0636876680055796e-05, + "loss": 3.7037, + "step": 571904 + }, + { + "epoch": 0.01, + "learning_rate": 4.0628490732545275e-05, + "loss": 3.7149, + "step": 572416 + }, + { + "epoch": 0.01, + "learning_rate": 4.0620121163838485e-05, + "loss": 3.688, + "step": 572928 + }, + { + "epoch": 0.01, + "learning_rate": 4.0611735216327965e-05, + "loss": 3.6958, + "step": 573440 + }, + { + "epoch": 0.01, + "learning_rate": 4.0603349268817444e-05, + "loss": 3.7011, + "step": 573952 + }, + { + "epoch": 0.01, + "learning_rate": 4.059496332130693e-05, + "loss": 3.6829, + "step": 574464 + }, + { + "epoch": 0.01, + "learning_rate": 4.058659375260014e-05, + "loss": 3.6947, + "step": 574976 + }, + { + "epoch": 0.01, + "learning_rate": 4.057820780508962e-05, + "loss": 3.6983, + "step": 575488 + }, + { + "epoch": 0.01, + "learning_rate": 4.05698218575791e-05, + "loss": 3.6975, + "step": 576000 + }, + { + "epoch": 0.01, + "learning_rate": 4.056143591006858e-05, + "loss": 3.6984, + "step": 576512 + }, + { + "epoch": 0.01, + "learning_rate": 4.055306634136179e-05, + "loss": 3.6816, + "step": 577024 + }, + { + "epoch": 0.01, + "learning_rate": 4.054468039385127e-05, + "loss": 3.6831, + "step": 577536 + }, + { + "epoch": 0.01, + "learning_rate": 4.053629444634075e-05, + "loss": 3.6881, + "step": 578048 + }, + { + "epoch": 0.01, + "learning_rate": 4.052790849883023e-05, + "loss": 3.6931, + "step": 578560 + }, + { + "epoch": 0.01, + "learning_rate": 4.051953893012344e-05, + "loss": 3.6952, + "step": 579072 + }, + { + "epoch": 0.01, + "learning_rate": 4.051115298261292e-05, + "loss": 3.685, + "step": 579584 + }, + { + "epoch": 0.02, + "learning_rate": 4.05027670351024e-05, + "loss": 3.6889, + "step": 580096 + }, + { + "epoch": 0.02, + "learning_rate": 4.049438108759188e-05, + "loss": 3.6857, + "step": 580608 + }, + { + "epoch": 0.02, + "learning_rate": 4.0486011518885094e-05, + "loss": 3.6812, + "step": 581120 + }, + { + "epoch": 0.02, + "learning_rate": 4.0477625571374574e-05, + "loss": 3.6913, + "step": 581632 + }, + { + "epoch": 0.02, + "learning_rate": 4.0469239623864054e-05, + "loss": 3.6951, + "step": 582144 + }, + { + "epoch": 0.02, + "learning_rate": 4.046085367635353e-05, + "loss": 3.6993, + "step": 582656 + }, + { + "epoch": 0.02, + "learning_rate": 4.045248410764674e-05, + "loss": 3.6911, + "step": 583168 + }, + { + "epoch": 0.02, + "learning_rate": 4.044409816013622e-05, + "loss": 3.682, + "step": 583680 + }, + { + "epoch": 0.02, + "learning_rate": 4.04357122126257e-05, + "loss": 3.6957, + "step": 584192 + }, + { + "epoch": 0.02, + "learning_rate": 4.0427326265115176e-05, + "loss": 3.6907, + "step": 584704 + }, + { + "epoch": 0.02, + "learning_rate": 4.041895669640839e-05, + "loss": 3.6915, + "step": 585216 + }, + { + "epoch": 0.02, + "learning_rate": 4.041057074889787e-05, + "loss": 3.6858, + "step": 585728 + }, + { + "epoch": 0.02, + "learning_rate": 4.040218480138735e-05, + "loss": 3.685, + "step": 586240 + }, + { + "epoch": 0.02, + "learning_rate": 4.039379885387683e-05, + "loss": 3.6856, + "step": 586752 + }, + { + "epoch": 0.02, + "learning_rate": 4.038542928517005e-05, + "loss": 3.7005, + "step": 587264 + }, + { + "epoch": 0.02, + "learning_rate": 4.037704333765953e-05, + "loss": 3.6755, + "step": 587776 + }, + { + "epoch": 0.02, + "learning_rate": 4.0368657390149e-05, + "loss": 3.6874, + "step": 588288 + }, + { + "epoch": 0.02, + "learning_rate": 4.036028782144222e-05, + "loss": 3.6849, + "step": 588800 + }, + { + "epoch": 0.02, + "learning_rate": 4.03519018739317e-05, + "loss": 3.6929, + "step": 589312 + }, + { + "epoch": 0.02, + "learning_rate": 4.0343532305224906e-05, + "loss": 3.6791, + "step": 589824 + }, + { + "epoch": 0.02, + "learning_rate": 4.0335146357714386e-05, + "loss": 3.6924, + "step": 590336 + }, + { + "epoch": 0.02, + "learning_rate": 4.0326760410203866e-05, + "loss": 3.6799, + "step": 590848 + }, + { + "epoch": 0.02, + "learning_rate": 4.0318374462693346e-05, + "loss": 3.6908, + "step": 591360 + }, + { + "epoch": 0.02, + "learning_rate": 4.0309988515182826e-05, + "loss": 3.6924, + "step": 591872 + }, + { + "epoch": 0.02, + "learning_rate": 4.0301602567672305e-05, + "loss": 3.6806, + "step": 592384 + }, + { + "epoch": 0.02, + "learning_rate": 4.0293216620161785e-05, + "loss": 3.6881, + "step": 592896 + }, + { + "epoch": 0.02, + "learning_rate": 4.0284830672651265e-05, + "loss": 3.7016, + "step": 593408 + }, + { + "epoch": 0.02, + "learning_rate": 4.0276461103944475e-05, + "loss": 3.6908, + "step": 593920 + }, + { + "epoch": 0.02, + "learning_rate": 4.0268075156433954e-05, + "loss": 3.687, + "step": 594432 + }, + { + "epoch": 0.02, + "learning_rate": 4.0259689208923434e-05, + "loss": 3.6933, + "step": 594944 + }, + { + "epoch": 0.02, + "learning_rate": 4.0251303261412914e-05, + "loss": 3.6935, + "step": 595456 + }, + { + "epoch": 0.02, + "learning_rate": 4.0242933692706123e-05, + "loss": 3.6772, + "step": 595968 + }, + { + "epoch": 0.02, + "learning_rate": 4.0234547745195603e-05, + "loss": 3.6923, + "step": 596480 + }, + { + "epoch": 0.02, + "learning_rate": 4.022616179768508e-05, + "loss": 3.6767, + "step": 596992 + }, + { + "epoch": 0.02, + "learning_rate": 4.021777585017456e-05, + "loss": 3.6866, + "step": 597504 + }, + { + "epoch": 0.02, + "learning_rate": 4.020940628146778e-05, + "loss": 3.6822, + "step": 598016 + }, + { + "epoch": 0.02, + "learning_rate": 4.020102033395726e-05, + "loss": 3.6858, + "step": 598528 + }, + { + "epoch": 0.02, + "learning_rate": 4.019263438644674e-05, + "loss": 3.6834, + "step": 599040 + }, + { + "epoch": 0.02, + "learning_rate": 4.018424843893622e-05, + "loss": 3.6808, + "step": 599552 + }, + { + "epoch": 0.02, + "learning_rate": 4.017587887022943e-05, + "loss": 3.6793, + "step": 600064 + }, + { + "epoch": 0.02, + "learning_rate": 4.016749292271891e-05, + "loss": 3.6964, + "step": 600576 + }, + { + "epoch": 0.02, + "learning_rate": 4.015910697520839e-05, + "loss": 3.6904, + "step": 601088 + }, + { + "epoch": 0.02, + "learning_rate": 4.015072102769787e-05, + "loss": 3.6932, + "step": 601600 + }, + { + "epoch": 0.02, + "learning_rate": 4.014235145899108e-05, + "loss": 3.672, + "step": 602112 + }, + { + "epoch": 0.02, + "learning_rate": 4.013396551148056e-05, + "loss": 3.7021, + "step": 602624 + }, + { + "epoch": 0.02, + "learning_rate": 4.012557956397004e-05, + "loss": 3.6835, + "step": 603136 + }, + { + "epoch": 0.02, + "learning_rate": 4.011719361645952e-05, + "loss": 3.6893, + "step": 603648 + }, + { + "epoch": 0.02, + "learning_rate": 4.010882404775273e-05, + "loss": 3.687, + "step": 604160 + }, + { + "epoch": 0.02, + "learning_rate": 4.010043810024221e-05, + "loss": 3.6855, + "step": 604672 + }, + { + "epoch": 0.02, + "learning_rate": 4.009205215273169e-05, + "loss": 3.6793, + "step": 605184 + }, + { + "epoch": 0.02, + "learning_rate": 4.008366620522117e-05, + "loss": 3.7021, + "step": 605696 + }, + { + "epoch": 0.02, + "learning_rate": 4.007529663651438e-05, + "loss": 3.6739, + "step": 606208 + }, + { + "epoch": 0.02, + "learning_rate": 4.006691068900386e-05, + "loss": 3.6902, + "step": 606720 + }, + { + "epoch": 0.02, + "learning_rate": 4.005852474149334e-05, + "loss": 3.6805, + "step": 607232 + }, + { + "epoch": 0.02, + "learning_rate": 4.005013879398282e-05, + "loss": 3.6829, + "step": 607744 + }, + { + "epoch": 0.02, + "learning_rate": 4.004176922527603e-05, + "loss": 3.6815, + "step": 608256 + }, + { + "epoch": 0.02, + "learning_rate": 4.003338327776551e-05, + "loss": 3.6833, + "step": 608768 + }, + { + "epoch": 0.02, + "learning_rate": 4.002499733025499e-05, + "loss": 3.694, + "step": 609280 + }, + { + "epoch": 0.02, + "learning_rate": 4.001661138274447e-05, + "loss": 3.6777, + "step": 609792 + }, + { + "epoch": 0.02, + "learning_rate": 4.0008241814037687e-05, + "loss": 3.6865, + "step": 610304 + }, + { + "epoch": 0.03, + "eval_loss": 3.8532724380493164, + "eval_runtime": 311.9124, + "eval_samples_per_second": 1223.392, + "eval_steps_per_second": 38.232, + "step": 610560 + }, + { + "epoch": 1.0, + "learning_rate": 3.9999855866527166e-05, + "loss": 3.6805, + "step": 610816 + }, + { + "epoch": 1.0, + "learning_rate": 3.9991469919016646e-05, + "loss": 3.6761, + "step": 611328 + }, + { + "epoch": 1.0, + "learning_rate": 3.9983083971506126e-05, + "loss": 3.6823, + "step": 611840 + }, + { + "epoch": 1.0, + "learning_rate": 3.9974714402799336e-05, + "loss": 3.6804, + "step": 612352 + }, + { + "epoch": 1.0, + "learning_rate": 3.9966328455288815e-05, + "loss": 3.6918, + "step": 612864 + }, + { + "epoch": 1.0, + "learning_rate": 3.9957942507778295e-05, + "loss": 3.6751, + "step": 613376 + }, + { + "epoch": 1.0, + "learning_rate": 3.9949556560267775e-05, + "loss": 3.6832, + "step": 613888 + }, + { + "epoch": 1.0, + "learning_rate": 3.9941186991560984e-05, + "loss": 3.6784, + "step": 614400 + }, + { + "epoch": 1.0, + "learning_rate": 3.9932801044050464e-05, + "loss": 3.6791, + "step": 614912 + }, + { + "epoch": 1.0, + "learning_rate": 3.9924415096539944e-05, + "loss": 3.6862, + "step": 615424 + }, + { + "epoch": 1.0, + "learning_rate": 3.991604552783316e-05, + "loss": 3.679, + "step": 615936 + }, + { + "epoch": 1.0, + "learning_rate": 3.990765958032264e-05, + "loss": 3.6772, + "step": 616448 + }, + { + "epoch": 1.0, + "learning_rate": 3.989929001161585e-05, + "loss": 3.6822, + "step": 616960 + }, + { + "epoch": 1.0, + "learning_rate": 3.989090406410533e-05, + "loss": 3.669, + "step": 617472 + }, + { + "epoch": 1.0, + "learning_rate": 3.988251811659481e-05, + "loss": 3.6781, + "step": 617984 + }, + { + "epoch": 1.0, + "learning_rate": 3.987413216908429e-05, + "loss": 3.6706, + "step": 618496 + }, + { + "epoch": 1.0, + "learning_rate": 3.986574622157377e-05, + "loss": 3.6781, + "step": 619008 + }, + { + "epoch": 1.0, + "learning_rate": 3.985736027406325e-05, + "loss": 3.6719, + "step": 619520 + }, + { + "epoch": 1.0, + "learning_rate": 3.984897432655273e-05, + "loss": 3.671, + "step": 620032 + }, + { + "epoch": 1.0, + "learning_rate": 3.984058837904221e-05, + "loss": 3.6867, + "step": 620544 + }, + { + "epoch": 1.0, + "learning_rate": 3.983221881033542e-05, + "loss": 3.6877, + "step": 621056 + }, + { + "epoch": 1.0, + "learning_rate": 3.982384924162863e-05, + "loss": 3.6877, + "step": 621568 + }, + { + "epoch": 1.0, + "learning_rate": 3.981546329411811e-05, + "loss": 3.6777, + "step": 622080 + }, + { + "epoch": 1.0, + "learning_rate": 3.9807077346607594e-05, + "loss": 3.6774, + "step": 622592 + }, + { + "epoch": 1.0, + "learning_rate": 3.9798691399097074e-05, + "loss": 3.6723, + "step": 623104 + }, + { + "epoch": 1.0, + "learning_rate": 3.9790305451586554e-05, + "loss": 3.6827, + "step": 623616 + }, + { + "epoch": 1.0, + "learning_rate": 3.9781919504076034e-05, + "loss": 3.6748, + "step": 624128 + }, + { + "epoch": 1.0, + "learning_rate": 3.9773533556565514e-05, + "loss": 3.6752, + "step": 624640 + }, + { + "epoch": 1.0, + "learning_rate": 3.9765147609054994e-05, + "loss": 3.6665, + "step": 625152 + }, + { + "epoch": 1.0, + "learning_rate": 3.97567780403482e-05, + "loss": 3.671, + "step": 625664 + }, + { + "epoch": 1.01, + "learning_rate": 3.974839209283768e-05, + "loss": 3.6696, + "step": 626176 + }, + { + "epoch": 1.01, + "learning_rate": 3.974000614532716e-05, + "loss": 3.6869, + "step": 626688 + }, + { + "epoch": 1.01, + "learning_rate": 3.973162019781664e-05, + "loss": 3.6837, + "step": 627200 + }, + { + "epoch": 1.01, + "learning_rate": 3.972325062910985e-05, + "loss": 3.674, + "step": 627712 + }, + { + "epoch": 1.01, + "learning_rate": 3.971486468159933e-05, + "loss": 3.6693, + "step": 628224 + }, + { + "epoch": 1.01, + "learning_rate": 3.970647873408881e-05, + "loss": 3.678, + "step": 628736 + }, + { + "epoch": 1.01, + "learning_rate": 3.969809278657829e-05, + "loss": 3.6762, + "step": 629248 + }, + { + "epoch": 1.01, + "learning_rate": 3.968972321787151e-05, + "loss": 3.6736, + "step": 629760 + }, + { + "epoch": 1.01, + "learning_rate": 3.968133727036099e-05, + "loss": 3.668, + "step": 630272 + }, + { + "epoch": 1.01, + "learning_rate": 3.967295132285047e-05, + "loss": 3.6638, + "step": 630784 + }, + { + "epoch": 1.01, + "learning_rate": 3.966456537533995e-05, + "loss": 3.6664, + "step": 631296 + }, + { + "epoch": 1.01, + "learning_rate": 3.9656195806633156e-05, + "loss": 3.6839, + "step": 631808 + }, + { + "epoch": 1.01, + "learning_rate": 3.9647809859122636e-05, + "loss": 3.6789, + "step": 632320 + }, + { + "epoch": 1.01, + "learning_rate": 3.9639423911612116e-05, + "loss": 3.6665, + "step": 632832 + }, + { + "epoch": 1.01, + "learning_rate": 3.9631037964101596e-05, + "loss": 3.6752, + "step": 633344 + }, + { + "epoch": 1.01, + "learning_rate": 3.9622668395394805e-05, + "loss": 3.6665, + "step": 633856 + }, + { + "epoch": 1.01, + "learning_rate": 3.9614282447884285e-05, + "loss": 3.676, + "step": 634368 + }, + { + "epoch": 1.01, + "learning_rate": 3.9605896500373765e-05, + "loss": 3.6678, + "step": 634880 + }, + { + "epoch": 1.01, + "learning_rate": 3.9597510552863245e-05, + "loss": 3.6476, + "step": 635392 + }, + { + "epoch": 1.01, + "learning_rate": 3.958914098415646e-05, + "loss": 3.6819, + "step": 635904 + }, + { + "epoch": 1.01, + "learning_rate": 3.958075503664594e-05, + "loss": 3.6673, + "step": 636416 + }, + { + "epoch": 1.01, + "learning_rate": 3.957236908913542e-05, + "loss": 3.6758, + "step": 636928 + }, + { + "epoch": 1.01, + "learning_rate": 3.956399952042863e-05, + "loss": 3.666, + "step": 637440 + }, + { + "epoch": 1.01, + "learning_rate": 3.955561357291811e-05, + "loss": 3.663, + "step": 637952 + }, + { + "epoch": 1.01, + "learning_rate": 3.954722762540759e-05, + "loss": 3.6569, + "step": 638464 + }, + { + "epoch": 1.01, + "learning_rate": 3.953884167789707e-05, + "loss": 3.6625, + "step": 638976 + }, + { + "epoch": 1.01, + "learning_rate": 3.953045573038655e-05, + "loss": 3.6648, + "step": 639488 + }, + { + "epoch": 1.01, + "learning_rate": 3.952206978287602e-05, + "loss": 3.6637, + "step": 640000 + }, + { + "epoch": 1.01, + "learning_rate": 3.95136838353655e-05, + "loss": 3.6751, + "step": 640512 + }, + { + "epoch": 1.01, + "learning_rate": 3.950529788785498e-05, + "loss": 3.6595, + "step": 641024 + }, + { + "epoch": 1.01, + "learning_rate": 3.94969283191482e-05, + "loss": 3.6666, + "step": 641536 + }, + { + "epoch": 1.01, + "learning_rate": 3.948854237163768e-05, + "loss": 3.6796, + "step": 642048 + }, + { + "epoch": 1.01, + "learning_rate": 3.948015642412716e-05, + "loss": 3.6522, + "step": 642560 + }, + { + "epoch": 1.01, + "learning_rate": 3.947177047661664e-05, + "loss": 3.6534, + "step": 643072 + }, + { + "epoch": 1.01, + "learning_rate": 3.946340090790985e-05, + "loss": 3.6675, + "step": 643584 + }, + { + "epoch": 1.01, + "learning_rate": 3.945501496039933e-05, + "loss": 3.6686, + "step": 644096 + }, + { + "epoch": 1.01, + "learning_rate": 3.944662901288881e-05, + "loss": 3.6566, + "step": 644608 + }, + { + "epoch": 1.01, + "learning_rate": 3.9438259444182024e-05, + "loss": 3.6605, + "step": 645120 + }, + { + "epoch": 1.01, + "learning_rate": 3.94298734966715e-05, + "loss": 3.6579, + "step": 645632 + }, + { + "epoch": 1.01, + "learning_rate": 3.942148754916098e-05, + "loss": 3.6626, + "step": 646144 + }, + { + "epoch": 1.01, + "learning_rate": 3.941310160165046e-05, + "loss": 3.6689, + "step": 646656 + }, + { + "epoch": 1.01, + "learning_rate": 3.940473203294367e-05, + "loss": 3.6657, + "step": 647168 + }, + { + "epoch": 1.01, + "learning_rate": 3.939634608543315e-05, + "loss": 3.6733, + "step": 647680 + }, + { + "epoch": 1.01, + "learning_rate": 3.938796013792263e-05, + "loss": 3.673, + "step": 648192 + }, + { + "epoch": 1.01, + "learning_rate": 3.937957419041211e-05, + "loss": 3.6877, + "step": 648704 + }, + { + "epoch": 1.01, + "learning_rate": 3.937120462170532e-05, + "loss": 3.6562, + "step": 649216 + }, + { + "epoch": 1.01, + "learning_rate": 3.93628186741948e-05, + "loss": 3.6722, + "step": 649728 + }, + { + "epoch": 1.01, + "learning_rate": 3.935443272668428e-05, + "loss": 3.6709, + "step": 650240 + }, + { + "epoch": 1.01, + "learning_rate": 3.934604677917376e-05, + "loss": 3.6568, + "step": 650752 + }, + { + "epoch": 1.01, + "learning_rate": 3.933767721046697e-05, + "loss": 3.6632, + "step": 651264 + }, + { + "epoch": 1.01, + "learning_rate": 3.932929126295645e-05, + "loss": 3.6752, + "step": 651776 + }, + { + "epoch": 1.01, + "learning_rate": 3.932090531544593e-05, + "loss": 3.6686, + "step": 652288 + }, + { + "epoch": 1.01, + "learning_rate": 3.931251936793541e-05, + "loss": 3.6725, + "step": 652800 + }, + { + "epoch": 1.01, + "learning_rate": 3.9304149799228626e-05, + "loss": 3.6524, + "step": 653312 + }, + { + "epoch": 1.01, + "learning_rate": 3.9295763851718106e-05, + "loss": 3.6536, + "step": 653824 + }, + { + "epoch": 1.01, + "learning_rate": 3.9287377904207586e-05, + "loss": 3.6607, + "step": 654336 + }, + { + "epoch": 1.01, + "learning_rate": 3.9278991956697066e-05, + "loss": 3.6678, + "step": 654848 + }, + { + "epoch": 1.01, + "learning_rate": 3.9270622387990275e-05, + "loss": 3.6671, + "step": 655360 + }, + { + "epoch": 1.01, + "learning_rate": 3.9262236440479755e-05, + "loss": 3.6606, + "step": 655872 + }, + { + "epoch": 1.02, + "learning_rate": 3.9253850492969235e-05, + "loss": 3.6547, + "step": 656384 + }, + { + "epoch": 1.02, + "learning_rate": 3.9245464545458715e-05, + "loss": 3.662, + "step": 656896 + }, + { + "epoch": 1.02, + "learning_rate": 3.9237094976751924e-05, + "loss": 3.6537, + "step": 657408 + }, + { + "epoch": 1.02, + "learning_rate": 3.9228709029241404e-05, + "loss": 3.664, + "step": 657920 + }, + { + "epoch": 1.02, + "learning_rate": 3.9220323081730884e-05, + "loss": 3.6705, + "step": 658432 + }, + { + "epoch": 1.02, + "learning_rate": 3.9211937134220364e-05, + "loss": 3.6696, + "step": 658944 + }, + { + "epoch": 1.02, + "learning_rate": 3.920356756551358e-05, + "loss": 3.6627, + "step": 659456 + }, + { + "epoch": 1.02, + "learning_rate": 3.919518161800306e-05, + "loss": 3.656, + "step": 659968 + }, + { + "epoch": 1.02, + "learning_rate": 3.918679567049254e-05, + "loss": 3.6673, + "step": 660480 + }, + { + "epoch": 1.02, + "learning_rate": 3.917840972298202e-05, + "loss": 3.6605, + "step": 660992 + }, + { + "epoch": 1.02, + "learning_rate": 3.917004015427523e-05, + "loss": 3.6664, + "step": 661504 + }, + { + "epoch": 1.02, + "learning_rate": 3.916165420676471e-05, + "loss": 3.6617, + "step": 662016 + }, + { + "epoch": 1.02, + "learning_rate": 3.915326825925419e-05, + "loss": 3.6545, + "step": 662528 + }, + { + "epoch": 1.02, + "learning_rate": 3.914488231174367e-05, + "loss": 3.6656, + "step": 663040 + }, + { + "epoch": 1.02, + "learning_rate": 3.913651274303688e-05, + "loss": 3.668, + "step": 663552 + }, + { + "epoch": 1.02, + "learning_rate": 3.912812679552636e-05, + "loss": 3.6468, + "step": 664064 + }, + { + "epoch": 1.02, + "learning_rate": 3.911974084801584e-05, + "loss": 3.6595, + "step": 664576 + }, + { + "epoch": 1.02, + "learning_rate": 3.911135490050532e-05, + "loss": 3.6535, + "step": 665088 + }, + { + "epoch": 1.02, + "learning_rate": 3.9102985331798534e-05, + "loss": 3.6728, + "step": 665600 + }, + { + "epoch": 1.02, + "learning_rate": 3.909461576309174e-05, + "loss": 3.6466, + "step": 666112 + }, + { + "epoch": 1.02, + "learning_rate": 3.908622981558122e-05, + "loss": 3.6673, + "step": 666624 + }, + { + "epoch": 1.02, + "learning_rate": 3.90778438680707e-05, + "loss": 3.6538, + "step": 667136 + }, + { + "epoch": 1.02, + "learning_rate": 3.906945792056018e-05, + "loss": 3.6626, + "step": 667648 + }, + { + "epoch": 1.02, + "learning_rate": 3.906107197304966e-05, + "loss": 3.6624, + "step": 668160 + }, + { + "epoch": 1.02, + "learning_rate": 3.905268602553914e-05, + "loss": 3.6548, + "step": 668672 + }, + { + "epoch": 1.02, + "learning_rate": 3.904430007802862e-05, + "loss": 3.6584, + "step": 669184 + }, + { + "epoch": 1.02, + "learning_rate": 3.90359141305181e-05, + "loss": 3.6754, + "step": 669696 + }, + { + "epoch": 1.02, + "learning_rate": 3.902754456181131e-05, + "loss": 3.6599, + "step": 670208 + }, + { + "epoch": 1.02, + "learning_rate": 3.901915861430079e-05, + "loss": 3.6632, + "step": 670720 + }, + { + "epoch": 1.02, + "learning_rate": 3.901077266679027e-05, + "loss": 3.6658, + "step": 671232 + }, + { + "epoch": 1.02, + "learning_rate": 3.900238671927975e-05, + "loss": 3.663, + "step": 671744 + }, + { + "epoch": 1.02, + "learning_rate": 3.899401715057297e-05, + "loss": 3.6577, + "step": 672256 + }, + { + "epoch": 1.02, + "learning_rate": 3.898563120306245e-05, + "loss": 3.6607, + "step": 672768 + }, + { + "epoch": 1.02, + "learning_rate": 3.897724525555193e-05, + "loss": 3.6476, + "step": 673280 + }, + { + "epoch": 1.02, + "learning_rate": 3.896885930804141e-05, + "loss": 3.6596, + "step": 673792 + }, + { + "epoch": 1.02, + "learning_rate": 3.8960506118138345e-05, + "loss": 3.6552, + "step": 674304 + }, + { + "epoch": 1.02, + "learning_rate": 3.8952120170627825e-05, + "loss": 3.6582, + "step": 674816 + }, + { + "epoch": 1.02, + "learning_rate": 3.8943734223117305e-05, + "loss": 3.6551, + "step": 675328 + }, + { + "epoch": 1.02, + "learning_rate": 3.8935348275606785e-05, + "loss": 3.6547, + "step": 675840 + }, + { + "epoch": 1.02, + "learning_rate": 3.8926962328096265e-05, + "loss": 3.6517, + "step": 676352 + }, + { + "epoch": 1.02, + "learning_rate": 3.8918576380585745e-05, + "loss": 3.6716, + "step": 676864 + }, + { + "epoch": 1.02, + "learning_rate": 3.8910206811878954e-05, + "loss": 3.6584, + "step": 677376 + }, + { + "epoch": 1.02, + "learning_rate": 3.890182086436844e-05, + "loss": 3.6709, + "step": 677888 + }, + { + "epoch": 1.02, + "learning_rate": 3.889343491685792e-05, + "loss": 3.6413, + "step": 678400 + }, + { + "epoch": 1.02, + "learning_rate": 3.88850489693474e-05, + "loss": 3.6743, + "step": 678912 + }, + { + "epoch": 1.02, + "learning_rate": 3.887666302183688e-05, + "loss": 3.6543, + "step": 679424 + }, + { + "epoch": 1.02, + "learning_rate": 3.886827707432636e-05, + "loss": 3.6653, + "step": 679936 + }, + { + "epoch": 1.02, + "learning_rate": 3.885989112681584e-05, + "loss": 3.6612, + "step": 680448 + }, + { + "epoch": 1.02, + "learning_rate": 3.885150517930532e-05, + "loss": 3.6571, + "step": 680960 + }, + { + "epoch": 1.02, + "learning_rate": 3.884313561059853e-05, + "loss": 3.6563, + "step": 681472 + }, + { + "epoch": 1.02, + "learning_rate": 3.883474966308801e-05, + "loss": 3.6767, + "step": 681984 + }, + { + "epoch": 1.02, + "learning_rate": 3.882636371557749e-05, + "loss": 3.6418, + "step": 682496 + }, + { + "epoch": 1.02, + "learning_rate": 3.881797776806697e-05, + "loss": 3.665, + "step": 683008 + }, + { + "epoch": 1.02, + "learning_rate": 3.880960819936018e-05, + "loss": 3.6567, + "step": 683520 + }, + { + "epoch": 1.02, + "learning_rate": 3.880122225184966e-05, + "loss": 3.6498, + "step": 684032 + }, + { + "epoch": 1.02, + "learning_rate": 3.879283630433914e-05, + "loss": 3.6564, + "step": 684544 + }, + { + "epoch": 1.02, + "learning_rate": 3.8784466735632355e-05, + "loss": 3.6566, + "step": 685056 + }, + { + "epoch": 1.02, + "learning_rate": 3.8776080788121834e-05, + "loss": 3.6676, + "step": 685568 + }, + { + "epoch": 1.02, + "learning_rate": 3.8767694840611314e-05, + "loss": 3.6548, + "step": 686080 + }, + { + "epoch": 1.02, + "learning_rate": 3.8759308893100794e-05, + "loss": 3.6568, + "step": 686592 + }, + { + "epoch": 1.03, + "eval_loss": 3.848642587661743, + "eval_runtime": 304.6815, + "eval_samples_per_second": 1252.426, + "eval_steps_per_second": 39.139, + "step": 686880 + }, + { + "epoch": 0.0, + "learning_rate": 3.8750922945590274e-05, + "loss": 3.6558, + "step": 687104 + }, + { + "epoch": 0.0, + "learning_rate": 3.8742536998079754e-05, + "loss": 3.6476, + "step": 687616 + }, + { + "epoch": 0.0, + "learning_rate": 3.873415105056923e-05, + "loss": 3.6548, + "step": 688128 + }, + { + "epoch": 0.0, + "learning_rate": 3.872576510305871e-05, + "loss": 3.6579, + "step": 688640 + }, + { + "epoch": 0.0, + "learning_rate": 3.871737915554819e-05, + "loss": 3.669, + "step": 689152 + }, + { + "epoch": 0.0, + "learning_rate": 3.870899320803767e-05, + "loss": 3.6462, + "step": 689664 + }, + { + "epoch": 0.0, + "learning_rate": 3.870060726052715e-05, + "loss": 3.6572, + "step": 690176 + }, + { + "epoch": 0.0, + "learning_rate": 3.869222131301663e-05, + "loss": 3.6512, + "step": 690688 + }, + { + "epoch": 0.0, + "learning_rate": 3.868385174430984e-05, + "loss": 3.6557, + "step": 691200 + }, + { + "epoch": 0.0, + "learning_rate": 3.867546579679932e-05, + "loss": 3.6614, + "step": 691712 + }, + { + "epoch": 0.0, + "learning_rate": 3.866709622809253e-05, + "loss": 3.6512, + "step": 692224 + }, + { + "epoch": 0.0, + "learning_rate": 3.865871028058201e-05, + "loss": 3.6518, + "step": 692736 + }, + { + "epoch": 0.0, + "learning_rate": 3.865032433307149e-05, + "loss": 3.662, + "step": 693248 + }, + { + "epoch": 0.0, + "learning_rate": 3.864193838556097e-05, + "loss": 3.6409, + "step": 693760 + }, + { + "epoch": 0.0, + "learning_rate": 3.863355243805045e-05, + "loss": 3.652, + "step": 694272 + }, + { + "epoch": 0.0, + "learning_rate": 3.862516649053993e-05, + "loss": 3.6433, + "step": 694784 + }, + { + "epoch": 0.0, + "learning_rate": 3.861678054302941e-05, + "loss": 3.652, + "step": 695296 + }, + { + "epoch": 0.0, + "learning_rate": 3.860839459551889e-05, + "loss": 3.6469, + "step": 695808 + }, + { + "epoch": 0.0, + "learning_rate": 3.86000250268121e-05, + "loss": 3.6456, + "step": 696320 + }, + { + "epoch": 0.0, + "learning_rate": 3.859165545810532e-05, + "loss": 3.66, + "step": 696832 + }, + { + "epoch": 0.0, + "learning_rate": 3.85832695105948e-05, + "loss": 3.6594, + "step": 697344 + }, + { + "epoch": 0.0, + "learning_rate": 3.857488356308428e-05, + "loss": 3.6634, + "step": 697856 + }, + { + "epoch": 0.0, + "learning_rate": 3.856649761557376e-05, + "loss": 3.6538, + "step": 698368 + }, + { + "epoch": 0.0, + "learning_rate": 3.855811166806324e-05, + "loss": 3.6508, + "step": 698880 + }, + { + "epoch": 0.0, + "learning_rate": 3.854972572055272e-05, + "loss": 3.6438, + "step": 699392 + }, + { + "epoch": 0.0, + "learning_rate": 3.8541339773042197e-05, + "loss": 3.6581, + "step": 699904 + }, + { + "epoch": 0.0, + "learning_rate": 3.8532953825531677e-05, + "loss": 3.6512, + "step": 700416 + }, + { + "epoch": 0.0, + "learning_rate": 3.8524584256824886e-05, + "loss": 3.6507, + "step": 700928 + }, + { + "epoch": 0.0, + "learning_rate": 3.8516198309314366e-05, + "loss": 3.6419, + "step": 701440 + }, + { + "epoch": 0.0, + "learning_rate": 3.8507812361803846e-05, + "loss": 3.6461, + "step": 701952 + }, + { + "epoch": 0.01, + "learning_rate": 3.8499442793097055e-05, + "loss": 3.642, + "step": 702464 + }, + { + "epoch": 0.01, + "learning_rate": 3.8491056845586535e-05, + "loss": 3.6591, + "step": 702976 + }, + { + "epoch": 0.01, + "learning_rate": 3.8482670898076015e-05, + "loss": 3.6614, + "step": 703488 + }, + { + "epoch": 0.01, + "learning_rate": 3.8474284950565495e-05, + "loss": 3.6466, + "step": 704000 + }, + { + "epoch": 0.01, + "learning_rate": 3.846591538185871e-05, + "loss": 3.6457, + "step": 704512 + }, + { + "epoch": 0.01, + "learning_rate": 3.845752943434819e-05, + "loss": 3.6479, + "step": 705024 + }, + { + "epoch": 0.01, + "learning_rate": 3.844914348683767e-05, + "loss": 3.6527, + "step": 705536 + }, + { + "epoch": 0.01, + "learning_rate": 3.844075753932715e-05, + "loss": 3.6469, + "step": 706048 + }, + { + "epoch": 0.01, + "learning_rate": 3.843238797062036e-05, + "loss": 3.642, + "step": 706560 + }, + { + "epoch": 0.01, + "learning_rate": 3.842400202310984e-05, + "loss": 3.6369, + "step": 707072 + }, + { + "epoch": 0.01, + "learning_rate": 3.841561607559932e-05, + "loss": 3.6441, + "step": 707584 + }, + { + "epoch": 0.01, + "learning_rate": 3.840724650689253e-05, + "loss": 3.6525, + "step": 708096 + }, + { + "epoch": 0.01, + "learning_rate": 3.839886055938201e-05, + "loss": 3.6538, + "step": 708608 + }, + { + "epoch": 0.01, + "learning_rate": 3.839047461187149e-05, + "loss": 3.6471, + "step": 709120 + }, + { + "epoch": 0.01, + "learning_rate": 3.838208866436097e-05, + "loss": 3.6462, + "step": 709632 + }, + { + "epoch": 0.01, + "learning_rate": 3.837370271685045e-05, + "loss": 3.6464, + "step": 710144 + }, + { + "epoch": 0.01, + "learning_rate": 3.8365316769339935e-05, + "loss": 3.6478, + "step": 710656 + }, + { + "epoch": 0.01, + "learning_rate": 3.8356930821829415e-05, + "loss": 3.6446, + "step": 711168 + }, + { + "epoch": 0.01, + "learning_rate": 3.834854487431889e-05, + "loss": 3.6214, + "step": 711680 + }, + { + "epoch": 0.01, + "learning_rate": 3.8340175305612104e-05, + "loss": 3.657, + "step": 712192 + }, + { + "epoch": 0.01, + "learning_rate": 3.8331789358101584e-05, + "loss": 3.6439, + "step": 712704 + }, + { + "epoch": 0.01, + "learning_rate": 3.832340341059106e-05, + "loss": 3.6524, + "step": 713216 + }, + { + "epoch": 0.01, + "learning_rate": 3.831503384188427e-05, + "loss": 3.6429, + "step": 713728 + }, + { + "epoch": 0.01, + "learning_rate": 3.830664789437375e-05, + "loss": 3.6374, + "step": 714240 + }, + { + "epoch": 0.01, + "learning_rate": 3.829826194686323e-05, + "loss": 3.6334, + "step": 714752 + }, + { + "epoch": 0.01, + "learning_rate": 3.8289875999352706e-05, + "loss": 3.6349, + "step": 715264 + }, + { + "epoch": 0.01, + "learning_rate": 3.828150643064592e-05, + "loss": 3.6444, + "step": 715776 + }, + { + "epoch": 0.01, + "learning_rate": 3.82731204831354e-05, + "loss": 3.6306, + "step": 716288 + }, + { + "epoch": 0.01, + "learning_rate": 3.826473453562489e-05, + "loss": 3.65, + "step": 716800 + }, + { + "epoch": 0.01, + "learning_rate": 3.825634858811436e-05, + "loss": 3.6387, + "step": 717312 + }, + { + "epoch": 0.01, + "learning_rate": 3.824797901940758e-05, + "loss": 3.6368, + "step": 717824 + }, + { + "epoch": 0.01, + "learning_rate": 3.823959307189706e-05, + "loss": 3.6571, + "step": 718336 + }, + { + "epoch": 0.01, + "learning_rate": 3.823120712438653e-05, + "loss": 3.6296, + "step": 718848 + }, + { + "epoch": 0.01, + "learning_rate": 3.822282117687601e-05, + "loss": 3.6292, + "step": 719360 + }, + { + "epoch": 0.01, + "learning_rate": 3.821443522936549e-05, + "loss": 3.6435, + "step": 719872 + }, + { + "epoch": 0.01, + "learning_rate": 3.820604928185497e-05, + "loss": 3.6442, + "step": 720384 + }, + { + "epoch": 0.01, + "learning_rate": 3.819766333434445e-05, + "loss": 3.6317, + "step": 720896 + }, + { + "epoch": 0.01, + "learning_rate": 3.818927738683393e-05, + "loss": 3.637, + "step": 721408 + }, + { + "epoch": 0.01, + "learning_rate": 3.818090781812714e-05, + "loss": 3.6266, + "step": 721920 + }, + { + "epoch": 0.01, + "learning_rate": 3.8172521870616626e-05, + "loss": 3.6422, + "step": 722432 + }, + { + "epoch": 0.01, + "learning_rate": 3.8164135923106106e-05, + "loss": 3.6446, + "step": 722944 + }, + { + "epoch": 0.01, + "learning_rate": 3.8155749975595586e-05, + "loss": 3.6454, + "step": 723456 + }, + { + "epoch": 0.01, + "learning_rate": 3.8147380406888795e-05, + "loss": 3.644, + "step": 723968 + }, + { + "epoch": 0.01, + "learning_rate": 3.8139010838182004e-05, + "loss": 3.6473, + "step": 724480 + }, + { + "epoch": 0.01, + "learning_rate": 3.8130624890671484e-05, + "loss": 3.6612, + "step": 724992 + }, + { + "epoch": 0.01, + "learning_rate": 3.8122238943160964e-05, + "loss": 3.6364, + "step": 725504 + }, + { + "epoch": 0.01, + "learning_rate": 3.8113852995650444e-05, + "loss": 3.65, + "step": 726016 + }, + { + "epoch": 0.01, + "learning_rate": 3.8105467048139924e-05, + "loss": 3.643, + "step": 726528 + }, + { + "epoch": 0.01, + "learning_rate": 3.8097081100629404e-05, + "loss": 3.6359, + "step": 727040 + }, + { + "epoch": 0.01, + "learning_rate": 3.8088695153118884e-05, + "loss": 3.6355, + "step": 727552 + }, + { + "epoch": 0.01, + "learning_rate": 3.8080309205608364e-05, + "loss": 3.6512, + "step": 728064 + }, + { + "epoch": 0.01, + "learning_rate": 3.807193963690158e-05, + "loss": 3.6433, + "step": 728576 + }, + { + "epoch": 0.01, + "learning_rate": 3.806355368939106e-05, + "loss": 3.6473, + "step": 729088 + }, + { + "epoch": 0.01, + "learning_rate": 3.805516774188054e-05, + "loss": 3.6299, + "step": 729600 + }, + { + "epoch": 0.01, + "learning_rate": 3.804678179437002e-05, + "loss": 3.6305, + "step": 730112 + }, + { + "epoch": 0.01, + "learning_rate": 3.803841222566323e-05, + "loss": 3.6366, + "step": 730624 + }, + { + "epoch": 0.01, + "learning_rate": 3.803002627815271e-05, + "loss": 3.6425, + "step": 731136 + }, + { + "epoch": 0.01, + "learning_rate": 3.802164033064219e-05, + "loss": 3.6433, + "step": 731648 + }, + { + "epoch": 0.01, + "learning_rate": 3.801325438313167e-05, + "loss": 3.6389, + "step": 732160 + }, + { + "epoch": 0.02, + "learning_rate": 3.800488481442488e-05, + "loss": 3.6278, + "step": 732672 + }, + { + "epoch": 0.02, + "learning_rate": 3.799649886691436e-05, + "loss": 3.64, + "step": 733184 + }, + { + "epoch": 0.02, + "learning_rate": 3.798812929820757e-05, + "loss": 3.6304, + "step": 733696 + }, + { + "epoch": 0.02, + "learning_rate": 3.797974335069705e-05, + "loss": 3.6389, + "step": 734208 + }, + { + "epoch": 0.02, + "learning_rate": 3.7971357403186534e-05, + "loss": 3.6456, + "step": 734720 + }, + { + "epoch": 0.02, + "learning_rate": 3.7962971455676014e-05, + "loss": 3.6463, + "step": 735232 + }, + { + "epoch": 0.02, + "learning_rate": 3.7954585508165494e-05, + "loss": 3.6395, + "step": 735744 + }, + { + "epoch": 0.02, + "learning_rate": 3.7946199560654974e-05, + "loss": 3.6357, + "step": 736256 + }, + { + "epoch": 0.02, + "learning_rate": 3.7937813613144454e-05, + "loss": 3.6379, + "step": 736768 + }, + { + "epoch": 0.02, + "learning_rate": 3.7929427665633933e-05, + "loss": 3.6362, + "step": 737280 + }, + { + "epoch": 0.02, + "learning_rate": 3.792105809692714e-05, + "loss": 3.6447, + "step": 737792 + }, + { + "epoch": 0.02, + "learning_rate": 3.791267214941662e-05, + "loss": 3.6349, + "step": 738304 + }, + { + "epoch": 0.02, + "learning_rate": 3.79042862019061e-05, + "loss": 3.6339, + "step": 738816 + }, + { + "epoch": 0.02, + "learning_rate": 3.789590025439558e-05, + "loss": 3.6375, + "step": 739328 + }, + { + "epoch": 0.02, + "learning_rate": 3.788753068568879e-05, + "loss": 3.6453, + "step": 739840 + }, + { + "epoch": 0.02, + "learning_rate": 3.787914473817827e-05, + "loss": 3.6251, + "step": 740352 + }, + { + "epoch": 0.02, + "learning_rate": 3.787075879066775e-05, + "loss": 3.637, + "step": 740864 + }, + { + "epoch": 0.02, + "learning_rate": 3.786237284315723e-05, + "loss": 3.6291, + "step": 741376 + }, + { + "epoch": 0.02, + "learning_rate": 3.785400327445045e-05, + "loss": 3.646, + "step": 741888 + }, + { + "epoch": 0.02, + "learning_rate": 3.7845633705743656e-05, + "loss": 3.6257, + "step": 742400 + }, + { + "epoch": 0.02, + "learning_rate": 3.7837247758233136e-05, + "loss": 3.6404, + "step": 742912 + }, + { + "epoch": 0.02, + "learning_rate": 3.7828861810722616e-05, + "loss": 3.627, + "step": 743424 + }, + { + "epoch": 0.02, + "learning_rate": 3.7820475863212096e-05, + "loss": 3.6437, + "step": 743936 + }, + { + "epoch": 0.02, + "learning_rate": 3.7812089915701576e-05, + "loss": 3.6384, + "step": 744448 + }, + { + "epoch": 0.02, + "learning_rate": 3.7803703968191056e-05, + "loss": 3.6311, + "step": 744960 + }, + { + "epoch": 0.02, + "learning_rate": 3.7795334399484265e-05, + "loss": 3.6354, + "step": 745472 + }, + { + "epoch": 0.02, + "learning_rate": 3.7786948451973745e-05, + "loss": 3.6502, + "step": 745984 + }, + { + "epoch": 0.02, + "learning_rate": 3.7778562504463225e-05, + "loss": 3.6362, + "step": 746496 + }, + { + "epoch": 0.02, + "learning_rate": 3.7770176556952705e-05, + "loss": 3.6424, + "step": 747008 + }, + { + "epoch": 0.02, + "learning_rate": 3.7761790609442185e-05, + "loss": 3.637, + "step": 747520 + }, + { + "epoch": 0.02, + "learning_rate": 3.77534210407354e-05, + "loss": 3.6378, + "step": 748032 + }, + { + "epoch": 0.02, + "learning_rate": 3.774503509322488e-05, + "loss": 3.6388, + "step": 748544 + }, + { + "epoch": 0.02, + "learning_rate": 3.773664914571436e-05, + "loss": 3.6326, + "step": 749056 + }, + { + "epoch": 0.02, + "learning_rate": 3.772826319820384e-05, + "loss": 3.6265, + "step": 749568 + }, + { + "epoch": 0.02, + "learning_rate": 3.7719877250693314e-05, + "loss": 3.6368, + "step": 750080 + }, + { + "epoch": 0.02, + "learning_rate": 3.771150768198653e-05, + "loss": 3.6348, + "step": 750592 + }, + { + "epoch": 0.02, + "learning_rate": 3.770312173447601e-05, + "loss": 3.6341, + "step": 751104 + }, + { + "epoch": 0.02, + "learning_rate": 3.769473578696549e-05, + "loss": 3.6325, + "step": 751616 + }, + { + "epoch": 0.02, + "learning_rate": 3.768634983945496e-05, + "loss": 3.6326, + "step": 752128 + }, + { + "epoch": 0.02, + "learning_rate": 3.767796389194444e-05, + "loss": 3.6284, + "step": 752640 + }, + { + "epoch": 0.02, + "learning_rate": 3.766957794443392e-05, + "loss": 3.6464, + "step": 753152 + }, + { + "epoch": 0.02, + "learning_rate": 3.766120837572714e-05, + "loss": 3.6377, + "step": 753664 + }, + { + "epoch": 0.02, + "learning_rate": 3.765282242821662e-05, + "loss": 3.6461, + "step": 754176 + }, + { + "epoch": 0.02, + "learning_rate": 3.76444364807061e-05, + "loss": 3.6183, + "step": 754688 + }, + { + "epoch": 0.02, + "learning_rate": 3.763605053319558e-05, + "loss": 3.6469, + "step": 755200 + }, + { + "epoch": 0.02, + "learning_rate": 3.762766458568506e-05, + "loss": 3.637, + "step": 755712 + }, + { + "epoch": 0.02, + "learning_rate": 3.761929501697827e-05, + "loss": 3.6383, + "step": 756224 + }, + { + "epoch": 0.02, + "learning_rate": 3.761090906946775e-05, + "loss": 3.6344, + "step": 756736 + }, + { + "epoch": 0.02, + "learning_rate": 3.760252312195723e-05, + "loss": 3.6335, + "step": 757248 + }, + { + "epoch": 0.02, + "learning_rate": 3.759413717444671e-05, + "loss": 3.6357, + "step": 757760 + }, + { + "epoch": 0.02, + "learning_rate": 3.758575122693619e-05, + "loss": 3.6502, + "step": 758272 + }, + { + "epoch": 0.02, + "learning_rate": 3.757736527942567e-05, + "loss": 3.6231, + "step": 758784 + }, + { + "epoch": 0.02, + "learning_rate": 3.756897933191515e-05, + "loss": 3.6394, + "step": 759296 + }, + { + "epoch": 0.02, + "learning_rate": 3.7560609763208356e-05, + "loss": 3.6309, + "step": 759808 + }, + { + "epoch": 0.02, + "learning_rate": 3.755222381569784e-05, + "loss": 3.6275, + "step": 760320 + }, + { + "epoch": 0.02, + "learning_rate": 3.754383786818732e-05, + "loss": 3.6353, + "step": 760832 + }, + { + "epoch": 0.02, + "learning_rate": 3.753546829948053e-05, + "loss": 3.6327, + "step": 761344 + }, + { + "epoch": 0.02, + "learning_rate": 3.752708235197001e-05, + "loss": 3.6416, + "step": 761856 + }, + { + "epoch": 0.02, + "learning_rate": 3.751869640445949e-05, + "loss": 3.6376, + "step": 762368 + }, + { + "epoch": 0.02, + "learning_rate": 3.751031045694897e-05, + "loss": 3.6323, + "step": 762880 + }, + { + "epoch": 0.03, + "eval_loss": 3.8451194763183594, + "eval_runtime": 318.5135, + "eval_samples_per_second": 1198.037, + "eval_steps_per_second": 37.44, + "step": 763200 + }, + { + "epoch": 1.0, + "learning_rate": 3.750194088824218e-05, + "loss": 3.6286, + "step": 763392 + }, + { + "epoch": 1.0, + "learning_rate": 3.749355494073166e-05, + "loss": 3.6257, + "step": 763904 + }, + { + "epoch": 1.0, + "learning_rate": 3.748516899322114e-05, + "loss": 3.6305, + "step": 764416 + }, + { + "epoch": 1.0, + "learning_rate": 3.747678304571062e-05, + "loss": 3.6381, + "step": 764928 + }, + { + "epoch": 1.0, + "learning_rate": 3.74683970982001e-05, + "loss": 3.6454, + "step": 765440 + }, + { + "epoch": 1.0, + "learning_rate": 3.746001115068958e-05, + "loss": 3.6249, + "step": 765952 + }, + { + "epoch": 1.0, + "learning_rate": 3.745162520317906e-05, + "loss": 3.6309, + "step": 766464 + }, + { + "epoch": 1.0, + "learning_rate": 3.744323925566854e-05, + "loss": 3.631, + "step": 766976 + }, + { + "epoch": 1.0, + "learning_rate": 3.743486968696176e-05, + "loss": 3.6302, + "step": 767488 + }, + { + "epoch": 1.0, + "learning_rate": 3.742648373945124e-05, + "loss": 3.6356, + "step": 768000 + }, + { + "epoch": 1.0, + "learning_rate": 3.7418114170744446e-05, + "loss": 3.6294, + "step": 768512 + }, + { + "epoch": 1.0, + "learning_rate": 3.7409728223233926e-05, + "loss": 3.63, + "step": 769024 + }, + { + "epoch": 1.0, + "learning_rate": 3.7401342275723406e-05, + "loss": 3.6365, + "step": 769536 + }, + { + "epoch": 1.0, + "learning_rate": 3.7392956328212886e-05, + "loss": 3.6181, + "step": 770048 + }, + { + "epoch": 1.0, + "learning_rate": 3.7384570380702366e-05, + "loss": 3.6294, + "step": 770560 + }, + { + "epoch": 1.0, + "learning_rate": 3.7376184433191846e-05, + "loss": 3.6179, + "step": 771072 + }, + { + "epoch": 1.0, + "learning_rate": 3.736779848568132e-05, + "loss": 3.6311, + "step": 771584 + }, + { + "epoch": 1.0, + "learning_rate": 3.73594125381708e-05, + "loss": 3.6241, + "step": 772096 + }, + { + "epoch": 1.0, + "learning_rate": 3.7351042969464015e-05, + "loss": 3.6231, + "step": 772608 + }, + { + "epoch": 1.0, + "learning_rate": 3.734267340075723e-05, + "loss": 3.6362, + "step": 773120 + }, + { + "epoch": 1.0, + "learning_rate": 3.733428745324671e-05, + "loss": 3.6342, + "step": 773632 + }, + { + "epoch": 1.0, + "learning_rate": 3.732590150573619e-05, + "loss": 3.6374, + "step": 774144 + }, + { + "epoch": 1.0, + "learning_rate": 3.731751555822567e-05, + "loss": 3.6335, + "step": 774656 + }, + { + "epoch": 1.0, + "learning_rate": 3.730912961071515e-05, + "loss": 3.6274, + "step": 775168 + }, + { + "epoch": 1.0, + "learning_rate": 3.7300743663204624e-05, + "loss": 3.6267, + "step": 775680 + }, + { + "epoch": 1.0, + "learning_rate": 3.7292357715694103e-05, + "loss": 3.631, + "step": 776192 + }, + { + "epoch": 1.0, + "learning_rate": 3.7283971768183583e-05, + "loss": 3.6268, + "step": 776704 + }, + { + "epoch": 1.0, + "learning_rate": 3.727560219947679e-05, + "loss": 3.629, + "step": 777216 + }, + { + "epoch": 1.0, + "learning_rate": 3.726721625196627e-05, + "loss": 3.6193, + "step": 777728 + }, + { + "epoch": 1.0, + "learning_rate": 3.725883030445575e-05, + "loss": 3.6205, + "step": 778240 + }, + { + "epoch": 1.01, + "learning_rate": 3.7250477114552704e-05, + "loss": 3.6221, + "step": 778752 + }, + { + "epoch": 1.01, + "learning_rate": 3.7242091167042184e-05, + "loss": 3.6302, + "step": 779264 + }, + { + "epoch": 1.01, + "learning_rate": 3.7233705219531664e-05, + "loss": 3.6412, + "step": 779776 + }, + { + "epoch": 1.01, + "learning_rate": 3.7225319272021144e-05, + "loss": 3.6269, + "step": 780288 + }, + { + "epoch": 1.01, + "learning_rate": 3.7216933324510624e-05, + "loss": 3.624, + "step": 780800 + }, + { + "epoch": 1.01, + "learning_rate": 3.72085473770001e-05, + "loss": 3.6225, + "step": 781312 + }, + { + "epoch": 1.01, + "learning_rate": 3.720016142948958e-05, + "loss": 3.6338, + "step": 781824 + }, + { + "epoch": 1.01, + "learning_rate": 3.719177548197906e-05, + "loss": 3.6252, + "step": 782336 + }, + { + "epoch": 1.01, + "learning_rate": 3.7183405913272266e-05, + "loss": 3.6224, + "step": 782848 + }, + { + "epoch": 1.01, + "learning_rate": 3.7175019965761746e-05, + "loss": 3.6112, + "step": 783360 + }, + { + "epoch": 1.01, + "learning_rate": 3.7166634018251226e-05, + "loss": 3.6226, + "step": 783872 + }, + { + "epoch": 1.01, + "learning_rate": 3.715826444954444e-05, + "loss": 3.6243, + "step": 784384 + }, + { + "epoch": 1.01, + "learning_rate": 3.714987850203392e-05, + "loss": 3.6318, + "step": 784896 + }, + { + "epoch": 1.01, + "learning_rate": 3.71414925545234e-05, + "loss": 3.6256, + "step": 785408 + }, + { + "epoch": 1.01, + "learning_rate": 3.713310660701288e-05, + "loss": 3.6246, + "step": 785920 + }, + { + "epoch": 1.01, + "learning_rate": 3.712472065950236e-05, + "loss": 3.6227, + "step": 786432 + }, + { + "epoch": 1.01, + "learning_rate": 3.711633471199184e-05, + "loss": 3.626, + "step": 786944 + }, + { + "epoch": 1.01, + "learning_rate": 3.710794876448132e-05, + "loss": 3.6226, + "step": 787456 + }, + { + "epoch": 1.01, + "learning_rate": 3.709957919577453e-05, + "loss": 3.6002, + "step": 787968 + }, + { + "epoch": 1.01, + "learning_rate": 3.709119324826401e-05, + "loss": 3.6325, + "step": 788480 + }, + { + "epoch": 1.01, + "learning_rate": 3.708280730075349e-05, + "loss": 3.6214, + "step": 788992 + }, + { + "epoch": 1.01, + "learning_rate": 3.707442135324297e-05, + "loss": 3.6311, + "step": 789504 + }, + { + "epoch": 1.01, + "learning_rate": 3.706603540573245e-05, + "loss": 3.6199, + "step": 790016 + }, + { + "epoch": 1.01, + "learning_rate": 3.705764945822193e-05, + "loss": 3.6159, + "step": 790528 + }, + { + "epoch": 1.01, + "learning_rate": 3.704927988951514e-05, + "loss": 3.6119, + "step": 791040 + }, + { + "epoch": 1.01, + "learning_rate": 3.704089394200462e-05, + "loss": 3.6127, + "step": 791552 + }, + { + "epoch": 1.01, + "learning_rate": 3.7032507994494106e-05, + "loss": 3.6255, + "step": 792064 + }, + { + "epoch": 1.01, + "learning_rate": 3.7024122046983586e-05, + "loss": 3.605, + "step": 792576 + }, + { + "epoch": 1.01, + "learning_rate": 3.7015736099473066e-05, + "loss": 3.6305, + "step": 793088 + }, + { + "epoch": 1.01, + "learning_rate": 3.7007350151962546e-05, + "loss": 3.6149, + "step": 793600 + }, + { + "epoch": 1.01, + "learning_rate": 3.6998964204452026e-05, + "loss": 3.6106, + "step": 794112 + }, + { + "epoch": 1.01, + "learning_rate": 3.6990578256941506e-05, + "loss": 3.6365, + "step": 794624 + }, + { + "epoch": 1.01, + "learning_rate": 3.6982208688234715e-05, + "loss": 3.6107, + "step": 795136 + }, + { + "epoch": 1.01, + "learning_rate": 3.6973822740724195e-05, + "loss": 3.6069, + "step": 795648 + }, + { + "epoch": 1.01, + "learning_rate": 3.6965453172017404e-05, + "loss": 3.6208, + "step": 796160 + }, + { + "epoch": 1.01, + "learning_rate": 3.6957067224506884e-05, + "loss": 3.6202, + "step": 796672 + }, + { + "epoch": 1.01, + "learning_rate": 3.6948681276996364e-05, + "loss": 3.61, + "step": 797184 + }, + { + "epoch": 1.01, + "learning_rate": 3.6940295329485844e-05, + "loss": 3.6154, + "step": 797696 + }, + { + "epoch": 1.01, + "learning_rate": 3.6931909381975324e-05, + "loss": 3.6051, + "step": 798208 + }, + { + "epoch": 1.01, + "learning_rate": 3.6923523434464804e-05, + "loss": 3.6152, + "step": 798720 + }, + { + "epoch": 1.01, + "learning_rate": 3.6915137486954284e-05, + "loss": 3.6239, + "step": 799232 + }, + { + "epoch": 1.01, + "learning_rate": 3.6906751539443764e-05, + "loss": 3.6233, + "step": 799744 + }, + { + "epoch": 1.01, + "learning_rate": 3.689838197073698e-05, + "loss": 3.6225, + "step": 800256 + }, + { + "epoch": 1.01, + "learning_rate": 3.688999602322646e-05, + "loss": 3.6241, + "step": 800768 + }, + { + "epoch": 1.01, + "learning_rate": 3.688162645451967e-05, + "loss": 3.6389, + "step": 801280 + }, + { + "epoch": 1.01, + "learning_rate": 3.687324050700915e-05, + "loss": 3.619, + "step": 801792 + }, + { + "epoch": 1.01, + "learning_rate": 3.686485455949863e-05, + "loss": 3.6227, + "step": 802304 + }, + { + "epoch": 1.01, + "learning_rate": 3.68564686119881e-05, + "loss": 3.6193, + "step": 802816 + }, + { + "epoch": 1.01, + "learning_rate": 3.684808266447758e-05, + "loss": 3.6147, + "step": 803328 + }, + { + "epoch": 1.01, + "learning_rate": 3.683969671696706e-05, + "loss": 3.6126, + "step": 803840 + }, + { + "epoch": 1.01, + "learning_rate": 3.683131076945654e-05, + "loss": 3.6335, + "step": 804352 + }, + { + "epoch": 1.01, + "learning_rate": 3.682292482194603e-05, + "loss": 3.6219, + "step": 804864 + }, + { + "epoch": 1.01, + "learning_rate": 3.6814571632042974e-05, + "loss": 3.6281, + "step": 805376 + }, + { + "epoch": 1.01, + "learning_rate": 3.6806185684532454e-05, + "loss": 3.6043, + "step": 805888 + }, + { + "epoch": 1.01, + "learning_rate": 3.679779973702193e-05, + "loss": 3.6091, + "step": 806400 + }, + { + "epoch": 1.01, + "learning_rate": 3.678941378951141e-05, + "loss": 3.6148, + "step": 806912 + }, + { + "epoch": 1.01, + "learning_rate": 3.678102784200089e-05, + "loss": 3.619, + "step": 807424 + }, + { + "epoch": 1.01, + "learning_rate": 3.677264189449037e-05, + "loss": 3.6196, + "step": 807936 + }, + { + "epoch": 1.01, + "learning_rate": 3.676425594697985e-05, + "loss": 3.6208, + "step": 808448 + }, + { + "epoch": 1.01, + "learning_rate": 3.6755869999469327e-05, + "loss": 3.6065, + "step": 808960 + }, + { + "epoch": 1.02, + "learning_rate": 3.6747500430762536e-05, + "loss": 3.6158, + "step": 809472 + }, + { + "epoch": 1.02, + "learning_rate": 3.673913086205575e-05, + "loss": 3.6102, + "step": 809984 + }, + { + "epoch": 1.02, + "learning_rate": 3.673074491454523e-05, + "loss": 3.615, + "step": 810496 + }, + { + "epoch": 1.02, + "learning_rate": 3.672235896703471e-05, + "loss": 3.6234, + "step": 811008 + }, + { + "epoch": 1.02, + "learning_rate": 3.671397301952419e-05, + "loss": 3.6263, + "step": 811520 + }, + { + "epoch": 1.02, + "learning_rate": 3.670558707201367e-05, + "loss": 3.6164, + "step": 812032 + }, + { + "epoch": 1.02, + "learning_rate": 3.669720112450315e-05, + "loss": 3.6118, + "step": 812544 + }, + { + "epoch": 1.02, + "learning_rate": 3.668881517699263e-05, + "loss": 3.6193, + "step": 813056 + }, + { + "epoch": 1.02, + "learning_rate": 3.668042922948211e-05, + "loss": 3.6126, + "step": 813568 + }, + { + "epoch": 1.02, + "learning_rate": 3.667205966077532e-05, + "loss": 3.623, + "step": 814080 + }, + { + "epoch": 1.02, + "learning_rate": 3.666369009206853e-05, + "loss": 3.6127, + "step": 814592 + }, + { + "epoch": 1.02, + "learning_rate": 3.665530414455801e-05, + "loss": 3.6155, + "step": 815104 + }, + { + "epoch": 1.02, + "learning_rate": 3.664691819704749e-05, + "loss": 3.6155, + "step": 815616 + }, + { + "epoch": 1.02, + "learning_rate": 3.663853224953697e-05, + "loss": 3.6166, + "step": 816128 + }, + { + "epoch": 1.02, + "learning_rate": 3.663014630202645e-05, + "loss": 3.6132, + "step": 816640 + }, + { + "epoch": 1.02, + "learning_rate": 3.6621776733319665e-05, + "loss": 3.6141, + "step": 817152 + }, + { + "epoch": 1.02, + "learning_rate": 3.6613390785809145e-05, + "loss": 3.6047, + "step": 817664 + }, + { + "epoch": 1.02, + "learning_rate": 3.6605004838298625e-05, + "loss": 3.6264, + "step": 818176 + }, + { + "epoch": 1.02, + "learning_rate": 3.6596618890788105e-05, + "loss": 3.6125, + "step": 818688 + }, + { + "epoch": 1.02, + "learning_rate": 3.6588232943277585e-05, + "loss": 3.6115, + "step": 819200 + }, + { + "epoch": 1.02, + "learning_rate": 3.6579846995767065e-05, + "loss": 3.6037, + "step": 819712 + }, + { + "epoch": 1.02, + "learning_rate": 3.6571461048256545e-05, + "loss": 3.6213, + "step": 820224 + }, + { + "epoch": 1.02, + "learning_rate": 3.6563075100746025e-05, + "loss": 3.6218, + "step": 820736 + }, + { + "epoch": 1.02, + "learning_rate": 3.6554705532039234e-05, + "loss": 3.6093, + "step": 821248 + }, + { + "epoch": 1.02, + "learning_rate": 3.654633596333244e-05, + "loss": 3.6163, + "step": 821760 + }, + { + "epoch": 1.02, + "learning_rate": 3.653795001582192e-05, + "loss": 3.6282, + "step": 822272 + }, + { + "epoch": 1.02, + "learning_rate": 3.65295640683114e-05, + "loss": 3.6112, + "step": 822784 + }, + { + "epoch": 1.02, + "learning_rate": 3.652117812080089e-05, + "loss": 3.6224, + "step": 823296 + }, + { + "epoch": 1.02, + "learning_rate": 3.651279217329037e-05, + "loss": 3.6176, + "step": 823808 + }, + { + "epoch": 1.02, + "learning_rate": 3.650442260458358e-05, + "loss": 3.6166, + "step": 824320 + }, + { + "epoch": 1.02, + "learning_rate": 3.649603665707306e-05, + "loss": 3.6168, + "step": 824832 + }, + { + "epoch": 1.02, + "learning_rate": 3.648765070956254e-05, + "loss": 3.6081, + "step": 825344 + }, + { + "epoch": 1.02, + "learning_rate": 3.647926476205202e-05, + "loss": 3.6065, + "step": 825856 + }, + { + "epoch": 1.02, + "learning_rate": 3.64708788145415e-05, + "loss": 3.614, + "step": 826368 + }, + { + "epoch": 1.02, + "learning_rate": 3.646250924583471e-05, + "loss": 3.614, + "step": 826880 + }, + { + "epoch": 1.02, + "learning_rate": 3.645412329832419e-05, + "loss": 3.6162, + "step": 827392 + }, + { + "epoch": 1.02, + "learning_rate": 3.644573735081367e-05, + "loss": 3.6063, + "step": 827904 + }, + { + "epoch": 1.02, + "learning_rate": 3.643735140330315e-05, + "loss": 3.6127, + "step": 828416 + }, + { + "epoch": 1.02, + "learning_rate": 3.642896545579263e-05, + "loss": 3.6037, + "step": 828928 + }, + { + "epoch": 1.02, + "learning_rate": 3.642057950828211e-05, + "loss": 3.6254, + "step": 829440 + }, + { + "epoch": 1.02, + "learning_rate": 3.641220993957532e-05, + "loss": 3.6126, + "step": 829952 + }, + { + "epoch": 1.02, + "learning_rate": 3.64038239920648e-05, + "loss": 3.6266, + "step": 830464 + }, + { + "epoch": 1.02, + "learning_rate": 3.639543804455428e-05, + "loss": 3.6013, + "step": 830976 + }, + { + "epoch": 1.02, + "learning_rate": 3.638705209704376e-05, + "loss": 3.6224, + "step": 831488 + }, + { + "epoch": 1.02, + "learning_rate": 3.6378666149533236e-05, + "loss": 3.6173, + "step": 832000 + }, + { + "epoch": 1.02, + "learning_rate": 3.637029658082645e-05, + "loss": 3.6164, + "step": 832512 + }, + { + "epoch": 1.02, + "learning_rate": 3.636191063331593e-05, + "loss": 3.6146, + "step": 833024 + }, + { + "epoch": 1.02, + "learning_rate": 3.635352468580541e-05, + "loss": 3.6127, + "step": 833536 + }, + { + "epoch": 1.02, + "learning_rate": 3.6345138738294885e-05, + "loss": 3.6136, + "step": 834048 + }, + { + "epoch": 1.02, + "learning_rate": 3.63367691695881e-05, + "loss": 3.6292, + "step": 834560 + }, + { + "epoch": 1.02, + "learning_rate": 3.632838322207758e-05, + "loss": 3.6043, + "step": 835072 + }, + { + "epoch": 1.02, + "learning_rate": 3.631999727456706e-05, + "loss": 3.6168, + "step": 835584 + }, + { + "epoch": 1.02, + "learning_rate": 3.631161132705654e-05, + "loss": 3.6097, + "step": 836096 + }, + { + "epoch": 1.02, + "learning_rate": 3.630322537954602e-05, + "loss": 3.6087, + "step": 836608 + }, + { + "epoch": 1.02, + "learning_rate": 3.62948394320355e-05, + "loss": 3.6121, + "step": 837120 + }, + { + "epoch": 1.02, + "learning_rate": 3.628646986332871e-05, + "loss": 3.6099, + "step": 837632 + }, + { + "epoch": 1.02, + "learning_rate": 3.627808391581819e-05, + "loss": 3.6198, + "step": 838144 + }, + { + "epoch": 1.02, + "learning_rate": 3.626969796830767e-05, + "loss": 3.6162, + "step": 838656 + }, + { + "epoch": 1.02, + "learning_rate": 3.626131202079715e-05, + "loss": 3.612, + "step": 839168 + }, + { + "epoch": 1.03, + "eval_loss": 3.844451665878296, + "eval_runtime": 317.3761, + "eval_samples_per_second": 1202.331, + "eval_steps_per_second": 37.574, + "step": 839520 + }, + { + "epoch": 0.0, + "learning_rate": 3.625294245209036e-05, + "loss": 3.6109, + "step": 839680 + }, + { + "epoch": 0.0, + "learning_rate": 3.624455650457984e-05, + "loss": 3.6036, + "step": 840192 + }, + { + "epoch": 0.0, + "learning_rate": 3.623617055706932e-05, + "loss": 3.6125, + "step": 840704 + }, + { + "epoch": 0.0, + "learning_rate": 3.62277846095588e-05, + "loss": 3.6152, + "step": 841216 + }, + { + "epoch": 0.0, + "learning_rate": 3.621939866204828e-05, + "loss": 3.6221, + "step": 841728 + }, + { + "epoch": 0.0, + "learning_rate": 3.621101271453776e-05, + "loss": 3.6039, + "step": 842240 + }, + { + "epoch": 0.0, + "learning_rate": 3.6202643145830975e-05, + "loss": 3.6134, + "step": 842752 + }, + { + "epoch": 0.0, + "learning_rate": 3.6194257198320455e-05, + "loss": 3.6113, + "step": 843264 + }, + { + "epoch": 0.0, + "learning_rate": 3.6185871250809935e-05, + "loss": 3.6101, + "step": 843776 + }, + { + "epoch": 0.0, + "learning_rate": 3.6177485303299415e-05, + "loss": 3.6108, + "step": 844288 + }, + { + "epoch": 0.0, + "learning_rate": 3.6169115734592624e-05, + "loss": 3.6158, + "step": 844800 + }, + { + "epoch": 0.0, + "learning_rate": 3.6160729787082104e-05, + "loss": 3.6089, + "step": 845312 + }, + { + "epoch": 0.0, + "learning_rate": 3.6152343839571584e-05, + "loss": 3.6154, + "step": 845824 + }, + { + "epoch": 0.0, + "learning_rate": 3.6143957892061063e-05, + "loss": 3.5995, + "step": 846336 + }, + { + "epoch": 0.0, + "learning_rate": 3.6135571944550543e-05, + "loss": 3.6057, + "step": 846848 + }, + { + "epoch": 0.0, + "learning_rate": 3.612720237584375e-05, + "loss": 3.5967, + "step": 847360 + }, + { + "epoch": 0.0, + "learning_rate": 3.611881642833323e-05, + "loss": 3.6146, + "step": 847872 + }, + { + "epoch": 0.0, + "learning_rate": 3.611043048082271e-05, + "loss": 3.6035, + "step": 848384 + }, + { + "epoch": 0.0, + "learning_rate": 3.61020445333122e-05, + "loss": 3.6005, + "step": 848896 + }, + { + "epoch": 0.0, + "learning_rate": 3.609367496460541e-05, + "loss": 3.6138, + "step": 849408 + }, + { + "epoch": 0.0, + "learning_rate": 3.608528901709489e-05, + "loss": 3.6142, + "step": 849920 + }, + { + "epoch": 0.0, + "learning_rate": 3.607690306958437e-05, + "loss": 3.6135, + "step": 850432 + }, + { + "epoch": 0.0, + "learning_rate": 3.606851712207385e-05, + "loss": 3.6142, + "step": 850944 + }, + { + "epoch": 0.0, + "learning_rate": 3.606014755336706e-05, + "loss": 3.6068, + "step": 851456 + }, + { + "epoch": 0.0, + "learning_rate": 3.605176160585654e-05, + "loss": 3.608, + "step": 851968 + }, + { + "epoch": 0.0, + "learning_rate": 3.604337565834602e-05, + "loss": 3.6124, + "step": 852480 + }, + { + "epoch": 0.0, + "learning_rate": 3.60349897108355e-05, + "loss": 3.5998, + "step": 852992 + }, + { + "epoch": 0.0, + "learning_rate": 3.6026620142128706e-05, + "loss": 3.6115, + "step": 853504 + }, + { + "epoch": 0.0, + "learning_rate": 3.6018234194618186e-05, + "loss": 3.6011, + "step": 854016 + }, + { + "epoch": 0.0, + "learning_rate": 3.6009848247107666e-05, + "loss": 3.5975, + "step": 854528 + }, + { + "epoch": 0.01, + "learning_rate": 3.600146229959715e-05, + "loss": 3.6028, + "step": 855040 + }, + { + "epoch": 0.01, + "learning_rate": 3.599307635208663e-05, + "loss": 3.6132, + "step": 855552 + }, + { + "epoch": 0.01, + "learning_rate": 3.598470678337984e-05, + "loss": 3.6141, + "step": 856064 + }, + { + "epoch": 0.01, + "learning_rate": 3.597632083586932e-05, + "loss": 3.6156, + "step": 856576 + }, + { + "epoch": 0.01, + "learning_rate": 3.59679348883588e-05, + "loss": 3.601, + "step": 857088 + }, + { + "epoch": 0.01, + "learning_rate": 3.595954894084828e-05, + "loss": 3.6018, + "step": 857600 + }, + { + "epoch": 0.01, + "learning_rate": 3.595117937214149e-05, + "loss": 3.6142, + "step": 858112 + }, + { + "epoch": 0.01, + "learning_rate": 3.594279342463097e-05, + "loss": 3.6026, + "step": 858624 + }, + { + "epoch": 0.01, + "learning_rate": 3.593440747712045e-05, + "loss": 3.6028, + "step": 859136 + }, + { + "epoch": 0.01, + "learning_rate": 3.592602152960993e-05, + "loss": 3.5943, + "step": 859648 + }, + { + "epoch": 0.01, + "learning_rate": 3.591765196090314e-05, + "loss": 3.6011, + "step": 860160 + }, + { + "epoch": 0.01, + "learning_rate": 3.590926601339262e-05, + "loss": 3.6046, + "step": 860672 + }, + { + "epoch": 0.01, + "learning_rate": 3.5900880065882106e-05, + "loss": 3.6125, + "step": 861184 + }, + { + "epoch": 0.01, + "learning_rate": 3.5892494118371586e-05, + "loss": 3.6047, + "step": 861696 + }, + { + "epoch": 0.01, + "learning_rate": 3.5884124549664796e-05, + "loss": 3.6014, + "step": 862208 + }, + { + "epoch": 0.01, + "learning_rate": 3.5875738602154276e-05, + "loss": 3.606, + "step": 862720 + }, + { + "epoch": 0.01, + "learning_rate": 3.5867352654643755e-05, + "loss": 3.6031, + "step": 863232 + }, + { + "epoch": 0.01, + "learning_rate": 3.5858966707133235e-05, + "loss": 3.6044, + "step": 863744 + }, + { + "epoch": 0.01, + "learning_rate": 3.5850597138426445e-05, + "loss": 3.5833, + "step": 864256 + }, + { + "epoch": 0.01, + "learning_rate": 3.5842211190915924e-05, + "loss": 3.6083, + "step": 864768 + }, + { + "epoch": 0.01, + "learning_rate": 3.5833825243405404e-05, + "loss": 3.5995, + "step": 865280 + }, + { + "epoch": 0.01, + "learning_rate": 3.5825439295894884e-05, + "loss": 3.6111, + "step": 865792 + }, + { + "epoch": 0.01, + "learning_rate": 3.5817053348384364e-05, + "loss": 3.6005, + "step": 866304 + }, + { + "epoch": 0.01, + "learning_rate": 3.5808667400873844e-05, + "loss": 3.5934, + "step": 866816 + }, + { + "epoch": 0.01, + "learning_rate": 3.580029783216706e-05, + "loss": 3.5937, + "step": 867328 + }, + { + "epoch": 0.01, + "learning_rate": 3.579191188465654e-05, + "loss": 3.5923, + "step": 867840 + }, + { + "epoch": 0.01, + "learning_rate": 3.578352593714602e-05, + "loss": 3.6062, + "step": 868352 + }, + { + "epoch": 0.01, + "learning_rate": 3.577513998963549e-05, + "loss": 3.5843, + "step": 868864 + }, + { + "epoch": 0.01, + "learning_rate": 3.576675404212497e-05, + "loss": 3.6098, + "step": 869376 + }, + { + "epoch": 0.01, + "learning_rate": 3.575836809461445e-05, + "loss": 3.5971, + "step": 869888 + }, + { + "epoch": 0.01, + "learning_rate": 3.574998214710393e-05, + "loss": 3.5893, + "step": 870400 + }, + { + "epoch": 0.01, + "learning_rate": 3.574161257839714e-05, + "loss": 3.6166, + "step": 870912 + }, + { + "epoch": 0.01, + "learning_rate": 3.573322663088662e-05, + "loss": 3.591, + "step": 871424 + }, + { + "epoch": 0.01, + "learning_rate": 3.57248406833761e-05, + "loss": 3.5876, + "step": 871936 + }, + { + "epoch": 0.01, + "learning_rate": 3.571645473586558e-05, + "loss": 3.6024, + "step": 872448 + }, + { + "epoch": 0.01, + "learning_rate": 3.570806878835506e-05, + "loss": 3.6024, + "step": 872960 + }, + { + "epoch": 0.01, + "learning_rate": 3.569968284084454e-05, + "loss": 3.586, + "step": 873472 + }, + { + "epoch": 0.01, + "learning_rate": 3.569129689333402e-05, + "loss": 3.5997, + "step": 873984 + }, + { + "epoch": 0.01, + "learning_rate": 3.568292732462724e-05, + "loss": 3.5846, + "step": 874496 + }, + { + "epoch": 0.01, + "learning_rate": 3.567454137711672e-05, + "loss": 3.5951, + "step": 875008 + }, + { + "epoch": 0.01, + "learning_rate": 3.56661554296062e-05, + "loss": 3.6042, + "step": 875520 + }, + { + "epoch": 0.01, + "learning_rate": 3.565776948209568e-05, + "loss": 3.6023, + "step": 876032 + }, + { + "epoch": 0.01, + "learning_rate": 3.564938353458516e-05, + "loss": 3.6035, + "step": 876544 + }, + { + "epoch": 0.01, + "learning_rate": 3.564101396587837e-05, + "loss": 3.6049, + "step": 877056 + }, + { + "epoch": 0.01, + "learning_rate": 3.563262801836785e-05, + "loss": 3.6187, + "step": 877568 + }, + { + "epoch": 0.01, + "learning_rate": 3.562424207085733e-05, + "loss": 3.5987, + "step": 878080 + }, + { + "epoch": 0.01, + "learning_rate": 3.5615856123346807e-05, + "loss": 3.6065, + "step": 878592 + }, + { + "epoch": 0.01, + "learning_rate": 3.5607486554640016e-05, + "loss": 3.5963, + "step": 879104 + }, + { + "epoch": 0.01, + "learning_rate": 3.5599100607129496e-05, + "loss": 3.5957, + "step": 879616 + }, + { + "epoch": 0.01, + "learning_rate": 3.5590714659618976e-05, + "loss": 3.5954, + "step": 880128 + }, + { + "epoch": 0.01, + "learning_rate": 3.558232871210846e-05, + "loss": 3.609, + "step": 880640 + }, + { + "epoch": 0.01, + "learning_rate": 3.557394276459794e-05, + "loss": 3.6029, + "step": 881152 + }, + { + "epoch": 0.01, + "learning_rate": 3.556557319589115e-05, + "loss": 3.6087, + "step": 881664 + }, + { + "epoch": 0.01, + "learning_rate": 3.555718724838063e-05, + "loss": 3.5894, + "step": 882176 + }, + { + "epoch": 0.01, + "learning_rate": 3.554880130087011e-05, + "loss": 3.5886, + "step": 882688 + }, + { + "epoch": 0.01, + "learning_rate": 3.554041535335959e-05, + "loss": 3.596, + "step": 883200 + }, + { + "epoch": 0.01, + "learning_rate": 3.55320457846528e-05, + "loss": 3.5974, + "step": 883712 + }, + { + "epoch": 0.01, + "learning_rate": 3.552365983714228e-05, + "loss": 3.5984, + "step": 884224 + }, + { + "epoch": 0.01, + "learning_rate": 3.551527388963176e-05, + "loss": 3.6024, + "step": 884736 + }, + { + "epoch": 0.01, + "learning_rate": 3.550688794212124e-05, + "loss": 3.5901, + "step": 885248 + }, + { + "epoch": 0.02, + "learning_rate": 3.549850199461072e-05, + "loss": 3.5944, + "step": 885760 + }, + { + "epoch": 0.02, + "learning_rate": 3.549013242590393e-05, + "loss": 3.5903, + "step": 886272 + }, + { + "epoch": 0.02, + "learning_rate": 3.5481746478393416e-05, + "loss": 3.593, + "step": 886784 + }, + { + "epoch": 0.02, + "learning_rate": 3.5473360530882896e-05, + "loss": 3.6051, + "step": 887296 + }, + { + "epoch": 0.02, + "learning_rate": 3.5464974583372376e-05, + "loss": 3.6093, + "step": 887808 + }, + { + "epoch": 0.02, + "learning_rate": 3.5456588635861856e-05, + "loss": 3.6002, + "step": 888320 + }, + { + "epoch": 0.02, + "learning_rate": 3.5448219067155065e-05, + "loss": 3.5903, + "step": 888832 + }, + { + "epoch": 0.02, + "learning_rate": 3.5439833119644545e-05, + "loss": 3.5999, + "step": 889344 + }, + { + "epoch": 0.02, + "learning_rate": 3.5431447172134025e-05, + "loss": 3.5912, + "step": 889856 + }, + { + "epoch": 0.02, + "learning_rate": 3.54230612246235e-05, + "loss": 3.5998, + "step": 890368 + }, + { + "epoch": 0.02, + "learning_rate": 3.5414691655916714e-05, + "loss": 3.597, + "step": 890880 + }, + { + "epoch": 0.02, + "learning_rate": 3.5406305708406194e-05, + "loss": 3.5908, + "step": 891392 + }, + { + "epoch": 0.02, + "learning_rate": 3.5397919760895674e-05, + "loss": 3.5985, + "step": 891904 + }, + { + "epoch": 0.02, + "learning_rate": 3.5389533813385154e-05, + "loss": 3.5942, + "step": 892416 + }, + { + "epoch": 0.02, + "learning_rate": 3.5381147865874634e-05, + "loss": 3.5964, + "step": 892928 + }, + { + "epoch": 0.02, + "learning_rate": 3.537277829716785e-05, + "loss": 3.5913, + "step": 893440 + }, + { + "epoch": 0.02, + "learning_rate": 3.536439234965733e-05, + "loss": 3.5893, + "step": 893952 + }, + { + "epoch": 0.02, + "learning_rate": 3.53560064021468e-05, + "loss": 3.6041, + "step": 894464 + }, + { + "epoch": 0.02, + "learning_rate": 3.534762045463628e-05, + "loss": 3.5943, + "step": 894976 + }, + { + "epoch": 0.02, + "learning_rate": 3.533923450712576e-05, + "loss": 3.5905, + "step": 895488 + }, + { + "epoch": 0.02, + "learning_rate": 3.533086493841897e-05, + "loss": 3.5852, + "step": 896000 + }, + { + "epoch": 0.02, + "learning_rate": 3.532247899090845e-05, + "loss": 3.5962, + "step": 896512 + }, + { + "epoch": 0.02, + "learning_rate": 3.531409304339793e-05, + "loss": 3.6019, + "step": 897024 + }, + { + "epoch": 0.02, + "learning_rate": 3.530572347469115e-05, + "loss": 3.589, + "step": 897536 + }, + { + "epoch": 0.02, + "learning_rate": 3.529733752718062e-05, + "loss": 3.5986, + "step": 898048 + }, + { + "epoch": 0.02, + "learning_rate": 3.528895157967011e-05, + "loss": 3.6045, + "step": 898560 + }, + { + "epoch": 0.02, + "learning_rate": 3.528056563215959e-05, + "loss": 3.5984, + "step": 899072 + }, + { + "epoch": 0.02, + "learning_rate": 3.527217968464907e-05, + "loss": 3.5991, + "step": 899584 + }, + { + "epoch": 0.02, + "learning_rate": 3.5263810115942276e-05, + "loss": 3.5995, + "step": 900096 + }, + { + "epoch": 0.02, + "learning_rate": 3.5255424168431756e-05, + "loss": 3.5982, + "step": 900608 + }, + { + "epoch": 0.02, + "learning_rate": 3.5247038220921236e-05, + "loss": 3.5962, + "step": 901120 + }, + { + "epoch": 0.02, + "learning_rate": 3.5238652273410716e-05, + "loss": 3.5884, + "step": 901632 + }, + { + "epoch": 0.02, + "learning_rate": 3.5230282704703925e-05, + "loss": 3.5885, + "step": 902144 + }, + { + "epoch": 0.02, + "learning_rate": 3.5221896757193405e-05, + "loss": 3.5957, + "step": 902656 + }, + { + "epoch": 0.02, + "learning_rate": 3.5213510809682885e-05, + "loss": 3.5968, + "step": 903168 + }, + { + "epoch": 0.02, + "learning_rate": 3.5205124862172365e-05, + "loss": 3.5939, + "step": 903680 + }, + { + "epoch": 0.02, + "learning_rate": 3.5196755293465574e-05, + "loss": 3.5923, + "step": 904192 + }, + { + "epoch": 0.02, + "learning_rate": 3.518836934595506e-05, + "loss": 3.5873, + "step": 904704 + }, + { + "epoch": 0.02, + "learning_rate": 3.517998339844454e-05, + "loss": 3.5879, + "step": 905216 + }, + { + "epoch": 0.02, + "learning_rate": 3.517159745093402e-05, + "loss": 3.6073, + "step": 905728 + }, + { + "epoch": 0.02, + "learning_rate": 3.51632115034235e-05, + "loss": 3.5938, + "step": 906240 + }, + { + "epoch": 0.02, + "learning_rate": 3.515484193471671e-05, + "loss": 3.6099, + "step": 906752 + }, + { + "epoch": 0.02, + "learning_rate": 3.514645598720619e-05, + "loss": 3.5808, + "step": 907264 + }, + { + "epoch": 0.02, + "learning_rate": 3.513807003969567e-05, + "loss": 3.6039, + "step": 907776 + }, + { + "epoch": 0.02, + "learning_rate": 3.512968409218515e-05, + "loss": 3.601, + "step": 908288 + }, + { + "epoch": 0.02, + "learning_rate": 3.512131452347836e-05, + "loss": 3.5973, + "step": 908800 + }, + { + "epoch": 0.02, + "learning_rate": 3.511292857596784e-05, + "loss": 3.5896, + "step": 909312 + }, + { + "epoch": 0.02, + "learning_rate": 3.510454262845732e-05, + "loss": 3.5969, + "step": 909824 + }, + { + "epoch": 0.02, + "learning_rate": 3.50961566809468e-05, + "loss": 3.5956, + "step": 910336 + }, + { + "epoch": 0.02, + "learning_rate": 3.5087787112240015e-05, + "loss": 3.6042, + "step": 910848 + }, + { + "epoch": 0.02, + "learning_rate": 3.5079401164729495e-05, + "loss": 3.5898, + "step": 911360 + }, + { + "epoch": 0.02, + "learning_rate": 3.5071015217218975e-05, + "loss": 3.5917, + "step": 911872 + }, + { + "epoch": 0.02, + "learning_rate": 3.5062629269708455e-05, + "loss": 3.5944, + "step": 912384 + }, + { + "epoch": 0.02, + "learning_rate": 3.5054259701001664e-05, + "loss": 3.5901, + "step": 912896 + }, + { + "epoch": 0.02, + "learning_rate": 3.5045873753491144e-05, + "loss": 3.5897, + "step": 913408 + }, + { + "epoch": 0.02, + "learning_rate": 3.5037487805980624e-05, + "loss": 3.5964, + "step": 913920 + }, + { + "epoch": 0.02, + "learning_rate": 3.5029101858470104e-05, + "loss": 3.598, + "step": 914432 + }, + { + "epoch": 0.02, + "learning_rate": 3.5020715910959584e-05, + "loss": 3.5963, + "step": 914944 + }, + { + "epoch": 0.02, + "learning_rate": 3.501234634225279e-05, + "loss": 3.593, + "step": 915456 + }, + { + "epoch": 0.03, + "eval_loss": 3.8424384593963623, + "eval_runtime": 310.4058, + "eval_samples_per_second": 1229.329, + "eval_steps_per_second": 38.417, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.500396039474227e-05, + "loss": 3.6, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.499557444723175e-05, + "loss": 3.5817, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.498718849972123e-05, + "loss": 3.5958, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.497880255221071e-05, + "loss": 3.597, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.497043298350393e-05, + "loss": 3.5995, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.496204703599341e-05, + "loss": 3.5906, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.495366108848289e-05, + "loss": 3.5941, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.494527514097237e-05, + "loss": 3.5917, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.493688919346185e-05, + "loss": 3.5871, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.492851962475506e-05, + "loss": 3.5924, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.492013367724454e-05, + "loss": 3.5964, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.491174772973402e-05, + "loss": 3.5881, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.49033617822235e-05, + "loss": 3.6003, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.4894992213516706e-05, + "loss": 3.5748, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.4886606266006186e-05, + "loss": 3.5853, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.4878220318495666e-05, + "loss": 3.5814, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.4869834370985146e-05, + "loss": 3.5968, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.486144842347463e-05, + "loss": 3.5828, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.485307885476784e-05, + "loss": 3.582, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.484469290725732e-05, + "loss": 3.5932, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.48363069597468e-05, + "loss": 3.5954, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.482792101223628e-05, + "loss": 3.5975, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.4819535064725755e-05, + "loss": 3.5939, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.481116549601897e-05, + "loss": 3.5898, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.480277954850845e-05, + "loss": 3.5938, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.479439360099793e-05, + "loss": 3.5912, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.4786007653487404e-05, + "loss": 3.5832, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.477763808478062e-05, + "loss": 3.5925, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.47692521372701e-05, + "loss": 3.5828, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.476086618975958e-05, + "loss": 3.5769, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.475248024224906e-05, + "loss": 3.5867, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.4744110673542276e-05, + "loss": 3.5906, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.4735724726031756e-05, + "loss": 3.5946, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.472733877852123e-05, + "loss": 3.5952, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.471895283101071e-05, + "loss": 3.5847, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.471056688350019e-05, + "loss": 3.5817, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.4702197314793405e-05, + "loss": 3.5969, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.469381136728288e-05, + "loss": 3.5794, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.468542541977236e-05, + "loss": 3.5843, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.467703947226184e-05, + "loss": 3.5803, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.4668669903555053e-05, + "loss": 3.5804, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.4660283956044533e-05, + "loss": 3.585, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.465189800853401e-05, + "loss": 3.5935, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.464351206102349e-05, + "loss": 3.5853, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.46351424923167e-05, + "loss": 3.5838, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.462675654480618e-05, + "loss": 3.5868, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.461837059729566e-05, + "loss": 3.5843, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.460998464978514e-05, + "loss": 3.588, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.460161508107835e-05, + "loss": 3.5673, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.459322913356783e-05, + "loss": 3.5889, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.458484318605731e-05, + "loss": 3.5796, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.457645723854679e-05, + "loss": 3.5943, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.456808766984001e-05, + "loss": 3.5817, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.455970172232949e-05, + "loss": 3.5772, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.455131577481897e-05, + "loss": 3.5759, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.454292982730845e-05, + "loss": 3.5735, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.4534560258601656e-05, + "loss": 3.5867, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.4526174311091136e-05, + "loss": 3.5656, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.4517788363580616e-05, + "loss": 3.5925, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.4509402416070096e-05, + "loss": 3.581, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.4501032847363305e-05, + "loss": 3.5703, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.4492646899852785e-05, + "loss": 3.5995, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.4484260952342265e-05, + "loss": 3.5703, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.4475875004831745e-05, + "loss": 3.5702, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.446748905732123e-05, + "loss": 3.5817, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.445911948861444e-05, + "loss": 3.5827, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.445073354110392e-05, + "loss": 3.5707, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.44423475935934e-05, + "loss": 3.5815, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.443396164608288e-05, + "loss": 3.5645, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.442559207737609e-05, + "loss": 3.5796, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.441720612986557e-05, + "loss": 3.5857, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.440882018235505e-05, + "loss": 3.5862, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.440043423484453e-05, + "loss": 3.5823, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.439206466613774e-05, + "loss": 3.5862, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.438367871862722e-05, + "loss": 3.6013, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.43752927711167e-05, + "loss": 3.5788, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.4366906823606185e-05, + "loss": 3.5919, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.4358537254899394e-05, + "loss": 3.5788, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.4350151307388874e-05, + "loss": 3.58, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.4341765359878354e-05, + "loss": 3.5726, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.4333379412367834e-05, + "loss": 3.5918, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.4325009843661043e-05, + "loss": 3.5844, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.431662389615052e-05, + "loss": 3.5915, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.430823794864e-05, + "loss": 3.5714, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.429985200112948e-05, + "loss": 3.5684, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.429146605361896e-05, + "loss": 3.575, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.428309648491217e-05, + "loss": 3.5848, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.427471053740165e-05, + "loss": 3.579, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.426632458989113e-05, + "loss": 3.5832, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.425793864238062e-05, + "loss": 3.575, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.424956907367383e-05, + "loss": 3.5726, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.424118312616331e-05, + "loss": 3.5726, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.423279717865279e-05, + "loss": 3.5746, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.422441123114227e-05, + "loss": 3.5823, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.421604166243548e-05, + "loss": 3.5928, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.420765571492496e-05, + "loss": 3.5827, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.419926976741444e-05, + "loss": 3.5739, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.419088381990392e-05, + "loss": 3.5789, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.4182514251197126e-05, + "loss": 3.5752, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.4174128303686606e-05, + "loss": 3.583, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.4165742356176086e-05, + "loss": 3.5761, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.415735640866557e-05, + "loss": 3.5721, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.414898683995878e-05, + "loss": 3.5815, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.414060089244826e-05, + "loss": 3.5776, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.413221494493774e-05, + "loss": 3.5776, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.412382899742722e-05, + "loss": 3.5758, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.411545942872043e-05, + "loss": 3.5713, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.410707348120991e-05, + "loss": 3.5826, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.409868753369939e-05, + "loss": 3.5791, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.409030158618887e-05, + "loss": 3.5732, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.408193201748208e-05, + "loss": 3.5677, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.407354606997156e-05, + "loss": 3.5775, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.406516012246104e-05, + "loss": 3.5867, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.4056774174950526e-05, + "loss": 3.5738, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.4048404606243735e-05, + "loss": 3.5786, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.4040018658733215e-05, + "loss": 3.5881, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.4031632711222695e-05, + "loss": 3.5807, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.4023246763712175e-05, + "loss": 3.5819, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.4014877195005384e-05, + "loss": 3.5816, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.4006491247494864e-05, + "loss": 3.5812, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.3998105299984344e-05, + "loss": 3.5831, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.3989719352473824e-05, + "loss": 3.5656, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.3981333404963304e-05, + "loss": 3.5748, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.397296383625651e-05, + "loss": 3.5739, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.396457788874599e-05, + "loss": 3.5784, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.395619194123548e-05, + "loss": 3.579, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.394780599372496e-05, + "loss": 3.5732, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.393943642501817e-05, + "loss": 3.5665, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.393105047750765e-05, + "loss": 3.5694, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.392266452999713e-05, + "loss": 3.5891, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.39142785824866e-05, + "loss": 3.5784, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.390590901377982e-05, + "loss": 3.5888, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.38975230662693e-05, + "loss": 3.5682, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.388913711875878e-05, + "loss": 3.5815, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.388075117124825e-05, + "loss": 3.585, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.387238160254147e-05, + "loss": 3.579, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.386399565503095e-05, + "loss": 3.5705, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.3855609707520434e-05, + "loss": 3.5793, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.384722376000991e-05, + "loss": 3.5808, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.383885419130312e-05, + "loss": 3.5869, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.38304682437926e-05, + "loss": 3.5733, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.3822082296282076e-05, + "loss": 3.5735, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.3813696348771556e-05, + "loss": 3.5755, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.3805310401261036e-05, + "loss": 3.5761, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379694083255425e-05, + "loss": 3.5698, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.3788554885043725e-05, + "loss": 3.5826, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.3780168937533205e-05, + "loss": 3.5752, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.3771782990022685e-05, + "loss": 3.5833, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.37634134213159e-05, + "loss": 3.5738, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 3.8430490493774414, + "eval_runtime": 303.4616, + "eval_samples_per_second": 1257.461, + "eval_steps_per_second": 39.297, + "step": 992160 + }, + { + "epoch": 1.0, + "learning_rate": 3.375502747380538e-05, + "loss": 3.575, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.374664152629486e-05, + "loss": 3.5643, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.373825557878434e-05, + "loss": 3.5756, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.372988601007755e-05, + "loss": 3.5818, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.372150006256703e-05, + "loss": 3.5789, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.371311411505651e-05, + "loss": 3.5752, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.370472816754599e-05, + "loss": 3.5743, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.369634222003547e-05, + "loss": 3.5718, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.368797265132868e-05, + "loss": 3.5699, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.367958670381816e-05, + "loss": 3.5794, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.367120075630764e-05, + "loss": 3.5732, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.3662831187600854e-05, + "loss": 3.5762, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.3654445240090334e-05, + "loss": 3.5826, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.3646059292579814e-05, + "loss": 3.5607, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.3637673345069294e-05, + "loss": 3.5683, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.36293037763625e-05, + "loss": 3.5626, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.362091782885198e-05, + "loss": 3.5797, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.361253188134146e-05, + "loss": 3.5655, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.360414593383094e-05, + "loss": 3.5678, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.359577636512415e-05, + "loss": 3.5752, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.358739041761363e-05, + "loss": 3.582, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.357900447010311e-05, + "loss": 3.5774, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.357061852259259e-05, + "loss": 3.5781, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.356224895388581e-05, + "loss": 3.5704, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.355386300637529e-05, + "loss": 3.579, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.354547705886477e-05, + "loss": 3.5705, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.353709111135425e-05, + "loss": 3.5701, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.352870516384373e-05, + "loss": 3.5743, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.352033559513694e-05, + "loss": 3.5647, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.351194964762642e-05, + "loss": 3.5594, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.35035637001159e-05, + "loss": 3.5697, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.349517775260538e-05, + "loss": 3.5731, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.3486808183898586e-05, + "loss": 3.5802, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.3478422236388066e-05, + "loss": 3.5764, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.3470036288877546e-05, + "loss": 3.5675, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.346165034136703e-05, + "loss": 3.5663, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.345328077266024e-05, + "loss": 3.5817, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.344489482514972e-05, + "loss": 3.5574, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.34365088776392e-05, + "loss": 3.5714, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.342812293012868e-05, + "loss": 3.5637, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.341975336142189e-05, + "loss": 3.5587, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.341136741391137e-05, + "loss": 3.5686, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.340298146640085e-05, + "loss": 3.578, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.339459551889033e-05, + "loss": 3.5703, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.338622595018354e-05, + "loss": 3.566, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.337784000267302e-05, + "loss": 3.5685, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.33694540551625e-05, + "loss": 3.5656, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.336106810765198e-05, + "loss": 3.5728, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.3352698538945195e-05, + "loss": 3.5496, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.3344312591434675e-05, + "loss": 3.5716, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.3335926643924155e-05, + "loss": 3.5637, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.3327540696413635e-05, + "loss": 3.579, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.3319171127706844e-05, + "loss": 3.561, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.3310785180196324e-05, + "loss": 3.5658, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.3302399232685804e-05, + "loss": 3.5502, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.3294013285175284e-05, + "loss": 3.5591, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.328564371646849e-05, + "loss": 3.5713, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.327725776895797e-05, + "loss": 3.5492, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.326887182144745e-05, + "loss": 3.5743, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.326048587393693e-05, + "loss": 3.5646, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.325209992642642e-05, + "loss": 3.5589, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.324373035771963e-05, + "loss": 3.5781, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.323534441020911e-05, + "loss": 3.5523, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.322695846269859e-05, + "loss": 3.5541, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.321857251518807e-05, + "loss": 3.5621, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.321020294648128e-05, + "loss": 3.5718, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.320181699897076e-05, + "loss": 3.555, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.319343105146024e-05, + "loss": 3.5601, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.318506148275345e-05, + "loss": 3.5476, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.317667553524293e-05, + "loss": 3.5628, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.316828958773241e-05, + "loss": 3.5653, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.315990364022189e-05, + "loss": 3.572, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.315151769271137e-05, + "loss": 3.5658, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.314314812400458e-05, + "loss": 3.5691, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.313476217649406e-05, + "loss": 3.5813, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.312637622898354e-05, + "loss": 3.5663, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.311799028147302e-05, + "loss": 3.5684, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.310962071276623e-05, + "loss": 3.5659, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.310123476525571e-05, + "loss": 3.564, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.309284881774519e-05, + "loss": 3.5577, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.308446287023467e-05, + "loss": 3.5702, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.307609330152788e-05, + "loss": 3.5648, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.306770735401736e-05, + "loss": 3.5759, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.305932140650684e-05, + "loss": 3.5605, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.305093545899633e-05, + "loss": 3.5494, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.3042565890289536e-05, + "loss": 3.5565, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.3034179942779016e-05, + "loss": 3.5686, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.3025793995268496e-05, + "loss": 3.5576, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.3017408047757976e-05, + "loss": 3.568, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.3009038479051185e-05, + "loss": 3.5605, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.3000652531540665e-05, + "loss": 3.5551, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.2992266584030145e-05, + "loss": 3.5581, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.2983880636519625e-05, + "loss": 3.5603, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.2975511067812834e-05, + "loss": 3.5652, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.2967125120302314e-05, + "loss": 3.5724, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.2958739172791794e-05, + "loss": 3.5693, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.295035322528128e-05, + "loss": 3.553, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.294198365657449e-05, + "loss": 3.5633, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.293359770906397e-05, + "loss": 3.5589, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.292521176155345e-05, + "loss": 3.5674, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.291682581404292e-05, + "loss": 3.5657, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.290845624533614e-05, + "loss": 3.5541, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.290007029782562e-05, + "loss": 3.5633, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.28916843503151e-05, + "loss": 3.5618, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.288329840280457e-05, + "loss": 3.5621, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.287492883409779e-05, + "loss": 3.5602, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.286654288658727e-05, + "loss": 3.5553, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.285815693907675e-05, + "loss": 3.5666, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.284977099156623e-05, + "loss": 3.5638, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.2841401422859443e-05, + "loss": 3.5548, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.2833015475348923e-05, + "loss": 3.5505, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.2824629527838397e-05, + "loss": 3.5611, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.2816243580327877e-05, + "loss": 3.5716, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.280787401162109e-05, + "loss": 3.5567, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.279948806411057e-05, + "loss": 3.5617, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.2791102116600046e-05, + "loss": 3.5661, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.2782716169089526e-05, + "loss": 3.5702, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.277434660038274e-05, + "loss": 3.5624, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.276596065287222e-05, + "loss": 3.5628, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.27575747053617e-05, + "loss": 3.568, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.274918875785118e-05, + "loss": 3.5652, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.27408191891444e-05, + "loss": 3.5529, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.273243324163387e-05, + "loss": 3.5588, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.272404729412335e-05, + "loss": 3.552, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.271566134661283e-05, + "loss": 3.5647, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.2707291777906046e-05, + "loss": 3.5613, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.269890583039552e-05, + "loss": 3.5552, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.2690519882885e-05, + "loss": 3.5502, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.268213393537448e-05, + "loss": 3.558, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.2673764366667695e-05, + "loss": 3.5705, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.2665378419157175e-05, + "loss": 3.5626, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.2656992471646655e-05, + "loss": 3.5696, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.2648606524136135e-05, + "loss": 3.5541, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.2640236955429344e-05, + "loss": 3.5659, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.2631851007918824e-05, + "loss": 3.5685, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.2623465060408304e-05, + "loss": 3.5637, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.2615079112897784e-05, + "loss": 3.5558, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.260670954419099e-05, + "loss": 3.5608, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.259832359668047e-05, + "loss": 3.5652, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.258993764916995e-05, + "loss": 3.5679, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.258155170165943e-05, + "loss": 3.5584, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.257318213295265e-05, + "loss": 3.5553, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.256479618544213e-05, + "loss": 3.564, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.255641023793161e-05, + "loss": 3.5582, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.254802429042109e-05, + "loss": 3.55, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.25396547217143e-05, + "loss": 3.5698, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.253126877420378e-05, + "loss": 3.5563, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.252288282669326e-05, + "loss": 3.572, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.251449687918274e-05, + "loss": 3.5506, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 3.843306303024292, + "eval_runtime": 302.8569, + "eval_samples_per_second": 1259.971, + "eval_steps_per_second": 39.375, + "step": 1068480 + }, + { + "epoch": 0.0, + "learning_rate": 3.250612731047595e-05, + "loss": 3.5732, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.249774136296543e-05, + "loss": 3.5492, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.2489355415454907e-05, + "loss": 3.5599, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.2480969467944387e-05, + "loss": 3.5645, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.24725998992376e-05, + "loss": 3.5634, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.246421395172708e-05, + "loss": 3.5616, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.245582800421656e-05, + "loss": 3.5552, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.244744205670604e-05, + "loss": 3.5573, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.243907248799925e-05, + "loss": 3.5531, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.243068654048873e-05, + "loss": 3.5608, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.242230059297821e-05, + "loss": 3.559, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.241391464546769e-05, + "loss": 3.5598, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.24055450767609e-05, + "loss": 3.5651, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.239715912925038e-05, + "loss": 3.544, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.238877318173986e-05, + "loss": 3.5508, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.238038723422934e-05, + "loss": 3.5439, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.237201766552255e-05, + "loss": 3.5659, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.2363631718012036e-05, + "loss": 3.5479, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.2355245770501516e-05, + "loss": 3.5507, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.2346859822990996e-05, + "loss": 3.5606, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.2338490254284205e-05, + "loss": 3.5636, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.2330104306773685e-05, + "loss": 3.5615, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.2321718359263165e-05, + "loss": 3.558, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.2313332411752645e-05, + "loss": 3.5581, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.2304962843045854e-05, + "loss": 3.5654, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.2296576895535334e-05, + "loss": 3.5523, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.2288190948024814e-05, + "loss": 3.5552, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.2279805000514294e-05, + "loss": 3.5588, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.22714354318075e-05, + "loss": 3.5452, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.226304948429699e-05, + "loss": 3.5422, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.225466353678647e-05, + "loss": 3.5523, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.224627758927595e-05, + "loss": 3.5541, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.223790802056916e-05, + "loss": 3.5656, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.222952207305864e-05, + "loss": 3.5601, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.222113612554812e-05, + "loss": 3.5506, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.22127501780376e-05, + "loss": 3.5523, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.220438060933081e-05, + "loss": 3.565, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.219599466182029e-05, + "loss": 3.543, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.218760871430977e-05, + "loss": 3.5556, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.217922276679925e-05, + "loss": 3.5418, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.217085319809246e-05, + "loss": 3.5458, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.216246725058194e-05, + "loss": 3.5527, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.215408130307142e-05, + "loss": 3.5685, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.21456953555609e-05, + "loss": 3.5495, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.213732578685411e-05, + "loss": 3.5501, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.212893983934359e-05, + "loss": 3.5539, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.212055389183307e-05, + "loss": 3.5508, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.211216794432255e-05, + "loss": 3.5529, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.210379837561576e-05, + "loss": 3.5339, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.209541242810524e-05, + "loss": 3.5567, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.208702648059472e-05, + "loss": 3.5508, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.20786405330842e-05, + "loss": 3.5612, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.207027096437741e-05, + "loss": 3.5433, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.20618850168669e-05, + "loss": 3.5442, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.205349906935638e-05, + "loss": 3.5434, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.204511312184586e-05, + "loss": 3.5374, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.2036743553139066e-05, + "loss": 3.5574, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.2028357605628546e-05, + "loss": 3.5343, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.2019971658118026e-05, + "loss": 3.5547, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.2011585710607506e-05, + "loss": 3.5493, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.2003216141900715e-05, + "loss": 3.5444, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.1994830194390195e-05, + "loss": 3.5623, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.1986444246879675e-05, + "loss": 3.5402, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.1978058299369155e-05, + "loss": 3.5391, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.1969688730662364e-05, + "loss": 3.5396, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.196130278315185e-05, + "loss": 3.5592, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.195291683564133e-05, + "loss": 3.5406, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.194453088813081e-05, + "loss": 3.5398, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.193616131942402e-05, + "loss": 3.5379, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.19277753719135e-05, + "loss": 3.5419, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.191938942440298e-05, + "loss": 3.5505, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.191100347689246e-05, + "loss": 3.5562, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.190263390818567e-05, + "loss": 3.5496, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.189424796067515e-05, + "loss": 3.5558, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.188586201316463e-05, + "loss": 3.5635, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.187747606565411e-05, + "loss": 3.5501, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.186910649694732e-05, + "loss": 3.5547, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.1860720549436804e-05, + "loss": 3.5507, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.1852334601926284e-05, + "loss": 3.5498, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.1843948654415764e-05, + "loss": 3.5431, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.183557908570897e-05, + "loss": 3.5541, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.182719313819845e-05, + "loss": 3.5516, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.181880719068793e-05, + "loss": 3.5586, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.181042124317741e-05, + "loss": 3.5473, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.180205167447062e-05, + "loss": 3.5321, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.17936657269601e-05, + "loss": 3.5393, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.178527977944958e-05, + "loss": 3.5511, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.177689383193906e-05, + "loss": 3.5414, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.176852426323227e-05, + "loss": 3.5533, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.176013831572176e-05, + "loss": 3.547, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.175175236821124e-05, + "loss": 3.5379, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.174336642070072e-05, + "loss": 3.5388, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.173499685199393e-05, + "loss": 3.5461, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.172661090448341e-05, + "loss": 3.5512, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.171822495697289e-05, + "loss": 3.5556, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.170983900946237e-05, + "loss": 3.5516, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.1701469440755576e-05, + "loss": 3.5383, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.1693083493245056e-05, + "loss": 3.5483, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.1684697545734536e-05, + "loss": 3.5482, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.1676311598224016e-05, + "loss": 3.5483, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.1667942029517225e-05, + "loss": 3.5513, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.165955608200671e-05, + "loss": 3.5372, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.165117013449619e-05, + "loss": 3.5469, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.1642784186985665e-05, + "loss": 3.5475, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.163441461827888e-05, + "loss": 3.5467, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.162602867076836e-05, + "loss": 3.5423, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.161764272325784e-05, + "loss": 3.5418, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.1609256775747314e-05, + "loss": 3.5493, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.160088720704053e-05, + "loss": 3.5513, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.159250125953001e-05, + "loss": 3.5375, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.158411531201949e-05, + "loss": 3.5355, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.157572936450896e-05, + "loss": 3.5398, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.156735979580218e-05, + "loss": 3.5578, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.155897384829166e-05, + "loss": 3.5434, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.155058790078114e-05, + "loss": 3.5443, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.154220195327062e-05, + "loss": 3.5516, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.1533832384563834e-05, + "loss": 3.5541, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.1525446437053314e-05, + "loss": 3.5464, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.151706048954279e-05, + "loss": 3.5492, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.150867454203227e-05, + "loss": 3.5517, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.150030497332548e-05, + "loss": 3.5468, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.149191902581496e-05, + "loss": 3.5366, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.1483533078304436e-05, + "loss": 3.5426, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.1475147130793916e-05, + "loss": 3.5406, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.146677756208713e-05, + "loss": 3.544, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.145839161457661e-05, + "loss": 3.5461, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.145000566706609e-05, + "loss": 3.5404, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.144161971955557e-05, + "loss": 3.5385, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.143325015084879e-05, + "loss": 3.5435, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.142486420333826e-05, + "loss": 3.5464, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.141647825582774e-05, + "loss": 3.5523, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.140809230831722e-05, + "loss": 3.5555, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.1399739118414166e-05, + "loss": 3.5375, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.1391353170903646e-05, + "loss": 3.5488, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.1382967223393126e-05, + "loss": 3.5497, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.1374581275882606e-05, + "loss": 3.5503, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.1366195328372086e-05, + "loss": 3.5415, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.1357809380861566e-05, + "loss": 3.5481, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.1349423433351046e-05, + "loss": 3.5487, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.1341037485840526e-05, + "loss": 3.5496, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.1332667917133735e-05, + "loss": 3.5408, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.1324281969623215e-05, + "loss": 3.5415, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.1315896022112695e-05, + "loss": 3.5467, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.1307510074602175e-05, + "loss": 3.5418, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.1299140505895384e-05, + "loss": 3.5348, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.1290754558384864e-05, + "loss": 3.5513, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.1282368610874344e-05, + "loss": 3.5419, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.1273982663363824e-05, + "loss": 3.5562, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.126561309465704e-05, + "loss": 3.5384, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 3.843520164489746, + "eval_runtime": 316.1942, + "eval_samples_per_second": 1206.825, + "eval_steps_per_second": 37.714, + "step": 1144800 + }, + { + "epoch": 1.0, + "learning_rate": 3.125722714714652e-05, + "loss": 3.5447, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.1248841199636e-05, + "loss": 3.5393, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.124045525212548e-05, + "loss": 3.5415, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.123208568341869e-05, + "loss": 3.5511, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.122369973590817e-05, + "loss": 3.544, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.121531378839765e-05, + "loss": 3.5478, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.120692784088713e-05, + "loss": 3.538, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.119855827218034e-05, + "loss": 3.5409, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.119017232466982e-05, + "loss": 3.54, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.11817863771593e-05, + "loss": 3.5459, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.117340042964878e-05, + "loss": 3.5414, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.116503086094199e-05, + "loss": 3.5474, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.115664491343147e-05, + "loss": 3.5508, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.114825896592095e-05, + "loss": 3.5284, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.113987301841043e-05, + "loss": 3.5334, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.113150344970364e-05, + "loss": 3.5327, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.112311750219312e-05, + "loss": 3.5474, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.11147315546826e-05, + "loss": 3.5394, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.110634560717208e-05, + "loss": 3.5347, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.109797603846529e-05, + "loss": 3.5406, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.108959009095477e-05, + "loss": 3.5461, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.108120414344425e-05, + "loss": 3.5473, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.107281819593373e-05, + "loss": 3.544, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.106444862722695e-05, + "loss": 3.5415, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.105606267971643e-05, + "loss": 3.5525, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.104767673220591e-05, + "loss": 3.5336, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.103929078469539e-05, + "loss": 3.5398, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.1030921215988596e-05, + "loss": 3.5443, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.1022535268478076e-05, + "loss": 3.5302, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.1014149320967556e-05, + "loss": 3.5304, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.1005763373457036e-05, + "loss": 3.534, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.0997393804750245e-05, + "loss": 3.5396, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.0989007857239725e-05, + "loss": 3.5506, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.0980621909729205e-05, + "loss": 3.5436, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.0972235962218685e-05, + "loss": 3.5387, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.09638663935119e-05, + "loss": 3.5353, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.095548044600138e-05, + "loss": 3.549, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.094709449849086e-05, + "loss": 3.5318, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.093870855098034e-05, + "loss": 3.5416, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.093033898227355e-05, + "loss": 3.529, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.092195303476303e-05, + "loss": 3.5308, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.091356708725251e-05, + "loss": 3.5355, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.090518113974199e-05, + "loss": 3.554, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.08968115710352e-05, + "loss": 3.5312, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.088842562352468e-05, + "loss": 3.5398, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.088003967601416e-05, + "loss": 3.5395, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.087165372850364e-05, + "loss": 3.5368, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.0863284159796854e-05, + "loss": 3.5384, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.0854898212286334e-05, + "loss": 3.5166, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.0846512264775814e-05, + "loss": 3.5408, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.0838126317265294e-05, + "loss": 3.5421, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.08297567485585e-05, + "loss": 3.5413, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.082137080104798e-05, + "loss": 3.5301, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.081298485353746e-05, + "loss": 3.5256, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.080459890602694e-05, + "loss": 3.531, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.079622933732015e-05, + "loss": 3.521, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.078784338980963e-05, + "loss": 3.5473, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.077945744229911e-05, + "loss": 3.5177, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.077107149478859e-05, + "loss": 3.5372, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.076270192608181e-05, + "loss": 3.5352, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.075431597857129e-05, + "loss": 3.5289, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.074593003106077e-05, + "loss": 3.5436, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.073756046235398e-05, + "loss": 3.5268, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.072917451484346e-05, + "loss": 3.5243, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.072078856733294e-05, + "loss": 3.5259, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.071240261982242e-05, + "loss": 3.5466, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.0704033051115626e-05, + "loss": 3.525, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.0695647103605106e-05, + "loss": 3.5244, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.0687261156094586e-05, + "loss": 3.524, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.0678875208584066e-05, + "loss": 3.5281, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.067050563987728e-05, + "loss": 3.536, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.066211969236676e-05, + "loss": 3.5417, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.065373374485624e-05, + "loss": 3.5297, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.064534779734572e-05, + "loss": 3.5416, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.063697822863893e-05, + "loss": 3.5487, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.062859228112841e-05, + "loss": 3.539, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.062020633361789e-05, + "loss": 3.5334, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.061182038610737e-05, + "loss": 3.5366, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.060345081740058e-05, + "loss": 3.5355, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.059506486989006e-05, + "loss": 3.5296, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.058667892237954e-05, + "loss": 3.533, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.057829297486902e-05, + "loss": 3.5414, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.056992340616223e-05, + "loss": 3.5431, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.0561537458651715e-05, + "loss": 3.5358, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.0553151511141195e-05, + "loss": 3.5161, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.0544765563630675e-05, + "loss": 3.5236, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.0536395994923884e-05, + "loss": 3.5361, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.0528010047413364e-05, + "loss": 3.5289, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.0519624099902844e-05, + "loss": 3.5395, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.0511238152392324e-05, + "loss": 3.5309, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.0502868583685533e-05, + "loss": 3.5247, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.0494482636175013e-05, + "loss": 3.5211, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.0486096688664497e-05, + "loss": 3.5335, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.0477710741153977e-05, + "loss": 3.5337, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.0469341172447186e-05, + "loss": 3.5394, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.0460955224936666e-05, + "loss": 3.5397, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.0452569277426146e-05, + "loss": 3.5204, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.0444183329915625e-05, + "loss": 3.5356, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.0435813761208838e-05, + "loss": 3.5319, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.0427427813698318e-05, + "loss": 3.5335, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.0419041866187798e-05, + "loss": 3.5351, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.0410655918677278e-05, + "loss": 3.5254, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.0402286349970487e-05, + "loss": 3.5286, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.0393900402459967e-05, + "loss": 3.5321, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.038551445494945e-05, + "loss": 3.5357, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.037712850743893e-05, + "loss": 3.5273, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.036875893873214e-05, + "loss": 3.5279, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.036037299122162e-05, + "loss": 3.5356, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.03519870437111e-05, + "loss": 3.5363, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.034360109620058e-05, + "loss": 3.5208, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.033523152749379e-05, + "loss": 3.5239, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.032684557998327e-05, + "loss": 3.5222, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.031845963247275e-05, + "loss": 3.5413, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.031007368496223e-05, + "loss": 3.5268, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.030170411625544e-05, + "loss": 3.5308, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.0293334547548653e-05, + "loss": 3.5373, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.0284948600038133e-05, + "loss": 3.5415, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.0276562652527613e-05, + "loss": 3.533, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.0268176705017093e-05, + "loss": 3.5334, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.0259790757506573e-05, + "loss": 3.5381, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.0251404809996053e-05, + "loss": 3.5296, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.024301886248553e-05, + "loss": 3.5232, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.0234649293778745e-05, + "loss": 3.5315, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.0226263346268225e-05, + "loss": 3.5231, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.0217877398757705e-05, + "loss": 3.5311, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.020949145124718e-05, + "loss": 3.528, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.0201121882540394e-05, + "loss": 3.5308, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.0192735935029874e-05, + "loss": 3.5251, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.018434998751935e-05, + "loss": 3.527, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.017596404000883e-05, + "loss": 3.5301, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.0167594471302047e-05, + "loss": 3.5383, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.0159208523791527e-05, + "loss": 3.5423, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.0150822576281003e-05, + "loss": 3.5292, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.0142436628770483e-05, + "loss": 3.5265, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.01340670600637e-05, + "loss": 3.5331, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.012568111255318e-05, + "loss": 3.5356, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.0117295165042652e-05, + "loss": 3.5305, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.0108909217532132e-05, + "loss": 3.5307, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.0100539648825348e-05, + "loss": 3.537, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.0092153701314825e-05, + "loss": 3.5306, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.0083767753804304e-05, + "loss": 3.5298, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.0075381806293784e-05, + "loss": 3.5254, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.0067012237587e-05, + "loss": 3.5312, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.0058626290076473e-05, + "loss": 3.5271, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.0050240342565953e-05, + "loss": 3.5188, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.0041854395055437e-05, + "loss": 3.5393, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.0033484826348653e-05, + "loss": 3.5301, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.0025098878838126e-05, + "loss": 3.5376, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.0016712931327606e-05, + "loss": 3.5253, + "step": 1220608 + }, + { + "epoch": 1.03, + "learning_rate": 3.0008326983817086e-05, + "loss": 3.5287, + "step": 1221120 + }, + { + "epoch": 1.03, + "eval_loss": 3.8439714908599854, + "eval_runtime": 302.4787, + "eval_samples_per_second": 1261.547, + "eval_steps_per_second": 39.424, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.9999941036306566e-05, + "loss": 3.5277, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.9991555088796046e-05, + "loss": 3.5223, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.998316914128553e-05, + "loss": 3.5369, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.9974799572578738e-05, + "loss": 3.5314, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.9966413625068218e-05, + "loss": 3.5339, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.9958027677557698e-05, + "loss": 3.5217, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.9949641730047178e-05, + "loss": 3.5285, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.994127216134039e-05, + "loss": 3.5201, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.993288621382987e-05, + "loss": 3.5319, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.992450026631935e-05, + "loss": 3.5276, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.991611431880883e-05, + "loss": 3.536, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.990774475010204e-05, + "loss": 3.5324, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.989935880259152e-05, + "loss": 3.5201, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.9890972855081e-05, + "loss": 3.5202, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.9882586907570483e-05, + "loss": 3.5147, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.9874217338863692e-05, + "loss": 3.5289, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.9865831391353172e-05, + "loss": 3.5236, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.985744544384265e-05, + "loss": 3.5261, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.984905949633213e-05, + "loss": 3.5232, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.9840689927625344e-05, + "loss": 3.5376, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.9832303980114824e-05, + "loss": 3.5274, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.9823918032604304e-05, + "loss": 3.5324, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.9815532085093784e-05, + "loss": 3.5305, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.9807162516386993e-05, + "loss": 3.5374, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.9798776568876473e-05, + "loss": 3.5208, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.9790390621365953e-05, + "loss": 3.5287, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.9782004673855436e-05, + "loss": 3.5249, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.9773618726344916e-05, + "loss": 3.5178, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.9765249157638125e-05, + "loss": 3.5156, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.9756863210127605e-05, + "loss": 3.5198, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.9748477262617085e-05, + "loss": 3.5258, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.9740107693910298e-05, + "loss": 3.5358, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.9731721746399778e-05, + "loss": 3.5274, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.9723335798889258e-05, + "loss": 3.5257, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.9714949851378738e-05, + "loss": 3.5211, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.9706580282671947e-05, + "loss": 3.5309, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.9698194335161427e-05, + "loss": 3.5183, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.9689808387650907e-05, + "loss": 3.5286, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.968142244014039e-05, + "loss": 3.5111, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.96730528714336e-05, + "loss": 3.5199, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.966466692392308e-05, + "loss": 3.5234, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.965628097641256e-05, + "loss": 3.5364, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.964789502890204e-05, + "loss": 3.5205, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.963952546019525e-05, + "loss": 3.524, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.963113951268473e-05, + "loss": 3.5262, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.962275356517421e-05, + "loss": 3.5197, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.961436761766369e-05, + "loss": 3.5298, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.96059980489569e-05, + "loss": 3.5012, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.959761210144638e-05, + "loss": 3.5234, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.958922615393586e-05, + "loss": 3.5254, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.9580840206425344e-05, + "loss": 3.5288, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.9572470637718553e-05, + "loss": 3.519, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.9564084690208033e-05, + "loss": 3.5075, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.9555698742697513e-05, + "loss": 3.5205, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.9547312795186993e-05, + "loss": 3.5041, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.9538943226480205e-05, + "loss": 3.5328, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.9530557278969685e-05, + "loss": 3.5042, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.9522171331459165e-05, + "loss": 3.5257, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.9513785383948645e-05, + "loss": 3.5171, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.9505415815241854e-05, + "loss": 3.5164, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.9497029867731334e-05, + "loss": 3.5287, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.9488643920220814e-05, + "loss": 3.5146, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.9480257972710297e-05, + "loss": 3.5095, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.9471888404003506e-05, + "loss": 3.5096, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.9463502456492986e-05, + "loss": 3.5311, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.9455116508982466e-05, + "loss": 3.5144, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.9446730561471946e-05, + "loss": 3.5132, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.943836099276516e-05, + "loss": 3.5081, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.942997504525464e-05, + "loss": 3.5119, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.942158909774412e-05, + "loss": 3.5245, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.94132031502336e-05, + "loss": 3.5287, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.9404833581526808e-05, + "loss": 3.5162, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.9396447634016288e-05, + "loss": 3.5268, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.9388061686505768e-05, + "loss": 3.5351, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.9379675738995248e-05, + "loss": 3.5255, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.937130617028846e-05, + "loss": 3.5157, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.936292022277794e-05, + "loss": 3.5251, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.935453427526742e-05, + "loss": 3.5217, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.93461483277569e-05, + "loss": 3.5165, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.9337778759050112e-05, + "loss": 3.5204, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.9329392811539592e-05, + "loss": 3.5238, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.9321006864029072e-05, + "loss": 3.528, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.9312620916518552e-05, + "loss": 3.5227, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.930425134781176e-05, + "loss": 3.5045, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.929586540030124e-05, + "loss": 3.5133, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.928747945279072e-05, + "loss": 3.517, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.92790935052802e-05, + "loss": 3.5219, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.9270723936573414e-05, + "loss": 3.5223, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.9262337989062894e-05, + "loss": 3.5175, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.9253952041552374e-05, + "loss": 3.5118, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.924556609404185e-05, + "loss": 3.5036, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.9237196525335063e-05, + "loss": 3.5176, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.9228810577824546e-05, + "loss": 3.5195, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.9220424630314026e-05, + "loss": 3.5242, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.92120386828035e-05, + "loss": 3.5249, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.9203669114096715e-05, + "loss": 3.5089, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.9195283166586195e-05, + "loss": 3.5193, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.9186897219075675e-05, + "loss": 3.5221, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.917851127156515e-05, + "loss": 3.5188, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.9170141702858367e-05, + "loss": 3.5214, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.9161755755347847e-05, + "loss": 3.5127, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.915336980783732e-05, + "loss": 3.513, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.91449838603268e-05, + "loss": 3.5199, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.9136614291620016e-05, + "loss": 3.5214, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.91282283441095e-05, + "loss": 3.5101, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.9119842396598973e-05, + "loss": 3.5125, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9111456449088453e-05, + "loss": 3.5245, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.910308688038167e-05, + "loss": 3.5176, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.9094700932871145e-05, + "loss": 3.5098, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.9086314985360625e-05, + "loss": 3.5117, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.9077929037850105e-05, + "loss": 3.5095, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.906955946914332e-05, + "loss": 3.531, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.9061173521632794e-05, + "loss": 3.5113, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.9052787574122274e-05, + "loss": 3.5186, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.9044401626611754e-05, + "loss": 3.5216, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.903603205790497e-05, + "loss": 3.5276, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.9027646110394447e-05, + "loss": 3.5143, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.9019260162883927e-05, + "loss": 3.5205, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.9010874215373407e-05, + "loss": 3.5277, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.9002504646666616e-05, + "loss": 3.5175, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.89941186991561e-05, + "loss": 3.5074, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.898573275164558e-05, + "loss": 3.5134, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.897734680413506e-05, + "loss": 3.5086, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.8968977235428268e-05, + "loss": 3.5149, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.8960591287917748e-05, + "loss": 3.5149, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.8952205340407228e-05, + "loss": 3.5188, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.8943819392896708e-05, + "loss": 3.5089, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.893544982418992e-05, + "loss": 3.5107, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.89270638766794e-05, + "loss": 3.5146, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.891867792916888e-05, + "loss": 3.5296, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.891029198165836e-05, + "loss": 3.5284, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.890192241295157e-05, + "loss": 3.5153, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.8893536465441053e-05, + "loss": 3.5112, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.8885150517930533e-05, + "loss": 3.5196, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.8876764570420013e-05, + "loss": 3.5242, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.886839500171322e-05, + "loss": 3.5174, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.88600090542027e-05, + "loss": 3.5154, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.885162310669218e-05, + "loss": 3.5234, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.884323715918166e-05, + "loss": 3.5167, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.8834867590474874e-05, + "loss": 3.5188, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.8826481642964354e-05, + "loss": 3.5131, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.8818095695453834e-05, + "loss": 3.5201, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.8809709747943314e-05, + "loss": 3.5138, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.8801340179236523e-05, + "loss": 3.5048, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.8792954231726006e-05, + "loss": 3.5226, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.8784568284215486e-05, + "loss": 3.5173, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.8776182336704966e-05, + "loss": 3.5246, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.8767812767998175e-05, + "loss": 3.5094, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.8759426820487655e-05, + "loss": 3.512, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 3.84628963470459, + "eval_runtime": 311.0057, + "eval_samples_per_second": 1226.958, + "eval_steps_per_second": 38.343, + "step": 1297440 + }, + { + "epoch": 1.0, + "learning_rate": 2.8751040872977135e-05, + "loss": 3.512, + "step": 1297920 + }, + { + "epoch": 1.0, + "learning_rate": 2.8742654925466615e-05, + "loss": 3.5118, + "step": 1298432 + }, + { + "epoch": 1.0, + "learning_rate": 2.8734285356759828e-05, + "loss": 3.5246, + "step": 1298944 + }, + { + "epoch": 1.0, + "learning_rate": 2.8725899409249308e-05, + "loss": 3.5135, + "step": 1299456 + }, + { + "epoch": 1.0, + "learning_rate": 2.8717513461738788e-05, + "loss": 3.5236, + "step": 1299968 + }, + { + "epoch": 1.0, + "learning_rate": 2.8709127514228268e-05, + "loss": 3.5082, + "step": 1300480 + }, + { + "epoch": 1.0, + "learning_rate": 2.8700757945521477e-05, + "loss": 3.5171, + "step": 1300992 + }, + { + "epoch": 1.0, + "learning_rate": 2.869237199801096e-05, + "loss": 3.5079, + "step": 1301504 + }, + { + "epoch": 1.0, + "learning_rate": 2.868398605050044e-05, + "loss": 3.5185, + "step": 1302016 + }, + { + "epoch": 1.0, + "learning_rate": 2.867560010298992e-05, + "loss": 3.516, + "step": 1302528 + }, + { + "epoch": 1.0, + "learning_rate": 2.866723053428313e-05, + "loss": 3.521, + "step": 1303040 + }, + { + "epoch": 1.0, + "learning_rate": 2.865884458677261e-05, + "loss": 3.5185, + "step": 1303552 + }, + { + "epoch": 1.0, + "learning_rate": 2.865045863926209e-05, + "loss": 3.5069, + "step": 1304064 + }, + { + "epoch": 1.0, + "learning_rate": 2.864207269175157e-05, + "loss": 3.5077, + "step": 1304576 + }, + { + "epoch": 1.0, + "learning_rate": 2.863370312304478e-05, + "loss": 3.5113, + "step": 1305088 + }, + { + "epoch": 1.0, + "learning_rate": 2.862531717553426e-05, + "loss": 3.5059, + "step": 1305600 + }, + { + "epoch": 1.0, + "learning_rate": 2.861693122802374e-05, + "loss": 3.5121, + "step": 1306112 + }, + { + "epoch": 1.0, + "learning_rate": 2.860854528051322e-05, + "loss": 3.5102, + "step": 1306624 + }, + { + "epoch": 1.0, + "learning_rate": 2.860017571180643e-05, + "loss": 3.5102, + "step": 1307136 + }, + { + "epoch": 1.0, + "learning_rate": 2.8591789764295914e-05, + "loss": 3.5239, + "step": 1307648 + }, + { + "epoch": 1.0, + "learning_rate": 2.8583403816785394e-05, + "loss": 3.5154, + "step": 1308160 + }, + { + "epoch": 1.0, + "learning_rate": 2.8575017869274874e-05, + "loss": 3.5192, + "step": 1308672 + }, + { + "epoch": 1.0, + "learning_rate": 2.8566648300568083e-05, + "loss": 3.5122, + "step": 1309184 + }, + { + "epoch": 1.0, + "learning_rate": 2.8558262353057563e-05, + "loss": 3.5264, + "step": 1309696 + }, + { + "epoch": 1.0, + "learning_rate": 2.8549876405547043e-05, + "loss": 3.5017, + "step": 1310208 + }, + { + "epoch": 1.0, + "learning_rate": 2.8541490458036523e-05, + "loss": 3.516, + "step": 1310720 + }, + { + "epoch": 1.0, + "learning_rate": 2.8533120889329735e-05, + "loss": 3.5105, + "step": 1311232 + }, + { + "epoch": 1.0, + "learning_rate": 2.8524734941819215e-05, + "loss": 3.5093, + "step": 1311744 + }, + { + "epoch": 1.0, + "learning_rate": 2.8516348994308695e-05, + "loss": 3.5016, + "step": 1312256 + }, + { + "epoch": 1.01, + "learning_rate": 2.8507963046798175e-05, + "loss": 3.5048, + "step": 1312768 + }, + { + "epoch": 1.01, + "learning_rate": 2.8499593478091384e-05, + "loss": 3.5155, + "step": 1313280 + }, + { + "epoch": 1.01, + "learning_rate": 2.8491207530580867e-05, + "loss": 3.5223, + "step": 1313792 + }, + { + "epoch": 1.01, + "learning_rate": 2.8482821583070347e-05, + "loss": 3.5104, + "step": 1314304 + }, + { + "epoch": 1.01, + "learning_rate": 2.8474435635559827e-05, + "loss": 3.5168, + "step": 1314816 + }, + { + "epoch": 1.01, + "learning_rate": 2.8466066066853036e-05, + "loss": 3.5067, + "step": 1315328 + }, + { + "epoch": 1.01, + "learning_rate": 2.8457680119342516e-05, + "loss": 3.5147, + "step": 1315840 + }, + { + "epoch": 1.01, + "learning_rate": 2.8449294171831996e-05, + "loss": 3.5067, + "step": 1316352 + }, + { + "epoch": 1.01, + "learning_rate": 2.8440908224321476e-05, + "loss": 3.5143, + "step": 1316864 + }, + { + "epoch": 1.01, + "learning_rate": 2.843253865561469e-05, + "loss": 3.4984, + "step": 1317376 + }, + { + "epoch": 1.01, + "learning_rate": 2.842415270810417e-05, + "loss": 3.5095, + "step": 1317888 + }, + { + "epoch": 1.01, + "learning_rate": 2.841576676059365e-05, + "loss": 3.5069, + "step": 1318400 + }, + { + "epoch": 1.01, + "learning_rate": 2.840738081308313e-05, + "loss": 3.5244, + "step": 1318912 + }, + { + "epoch": 1.01, + "learning_rate": 2.8399011244376338e-05, + "loss": 3.5039, + "step": 1319424 + }, + { + "epoch": 1.01, + "learning_rate": 2.839062529686582e-05, + "loss": 3.5125, + "step": 1319936 + }, + { + "epoch": 1.01, + "learning_rate": 2.83822393493553e-05, + "loss": 3.5135, + "step": 1320448 + }, + { + "epoch": 1.01, + "learning_rate": 2.837385340184478e-05, + "loss": 3.5037, + "step": 1320960 + }, + { + "epoch": 1.01, + "learning_rate": 2.836548383313799e-05, + "loss": 3.5153, + "step": 1321472 + }, + { + "epoch": 1.01, + "learning_rate": 2.835709788562747e-05, + "loss": 3.4901, + "step": 1321984 + }, + { + "epoch": 1.01, + "learning_rate": 2.834871193811695e-05, + "loss": 3.5078, + "step": 1322496 + }, + { + "epoch": 1.01, + "learning_rate": 2.834032599060643e-05, + "loss": 3.5144, + "step": 1323008 + }, + { + "epoch": 1.01, + "learning_rate": 2.8331956421899642e-05, + "loss": 3.5096, + "step": 1323520 + }, + { + "epoch": 1.01, + "learning_rate": 2.8323570474389122e-05, + "loss": 3.5055, + "step": 1324032 + }, + { + "epoch": 1.01, + "learning_rate": 2.8315184526878602e-05, + "loss": 3.4992, + "step": 1324544 + }, + { + "epoch": 1.01, + "learning_rate": 2.8306798579368082e-05, + "loss": 3.507, + "step": 1325056 + }, + { + "epoch": 1.01, + "learning_rate": 2.829842901066129e-05, + "loss": 3.4926, + "step": 1325568 + }, + { + "epoch": 1.01, + "learning_rate": 2.829004306315077e-05, + "loss": 3.515, + "step": 1326080 + }, + { + "epoch": 1.01, + "learning_rate": 2.8281657115640255e-05, + "loss": 3.4936, + "step": 1326592 + }, + { + "epoch": 1.01, + "learning_rate": 2.8273287546933464e-05, + "loss": 3.5068, + "step": 1327104 + }, + { + "epoch": 1.01, + "learning_rate": 2.8264901599422944e-05, + "loss": 3.5064, + "step": 1327616 + }, + { + "epoch": 1.01, + "learning_rate": 2.8256515651912424e-05, + "loss": 3.5042, + "step": 1328128 + }, + { + "epoch": 1.01, + "learning_rate": 2.8248129704401904e-05, + "loss": 3.5143, + "step": 1328640 + }, + { + "epoch": 1.01, + "learning_rate": 2.8239743756891384e-05, + "loss": 3.5044, + "step": 1329152 + }, + { + "epoch": 1.01, + "learning_rate": 2.8231374188184596e-05, + "loss": 3.4951, + "step": 1329664 + }, + { + "epoch": 1.01, + "learning_rate": 2.8222988240674076e-05, + "loss": 3.4951, + "step": 1330176 + }, + { + "epoch": 1.01, + "learning_rate": 2.8214602293163556e-05, + "loss": 3.519, + "step": 1330688 + }, + { + "epoch": 1.01, + "learning_rate": 2.8206232724456765e-05, + "loss": 3.4998, + "step": 1331200 + }, + { + "epoch": 1.01, + "learning_rate": 2.8197846776946245e-05, + "loss": 3.4994, + "step": 1331712 + }, + { + "epoch": 1.01, + "learning_rate": 2.8189460829435725e-05, + "loss": 3.4963, + "step": 1332224 + }, + { + "epoch": 1.01, + "learning_rate": 2.8181074881925208e-05, + "loss": 3.5004, + "step": 1332736 + }, + { + "epoch": 1.01, + "learning_rate": 2.8172705313218417e-05, + "loss": 3.5064, + "step": 1333248 + }, + { + "epoch": 1.01, + "learning_rate": 2.8164319365707897e-05, + "loss": 3.5134, + "step": 1333760 + }, + { + "epoch": 1.01, + "learning_rate": 2.8155933418197377e-05, + "loss": 3.5065, + "step": 1334272 + }, + { + "epoch": 1.01, + "learning_rate": 2.8147547470686857e-05, + "loss": 3.5176, + "step": 1334784 + }, + { + "epoch": 1.01, + "learning_rate": 2.813917790198007e-05, + "loss": 3.5151, + "step": 1335296 + }, + { + "epoch": 1.01, + "learning_rate": 2.813079195446955e-05, + "loss": 3.5158, + "step": 1335808 + }, + { + "epoch": 1.01, + "learning_rate": 2.812240600695903e-05, + "loss": 3.5025, + "step": 1336320 + }, + { + "epoch": 1.01, + "learning_rate": 2.811402005944851e-05, + "loss": 3.5128, + "step": 1336832 + }, + { + "epoch": 1.01, + "learning_rate": 2.810563411193799e-05, + "loss": 3.5073, + "step": 1337344 + }, + { + "epoch": 1.01, + "learning_rate": 2.80972645432312e-05, + "loss": 3.5062, + "step": 1337856 + }, + { + "epoch": 1.01, + "learning_rate": 2.808887859572068e-05, + "loss": 3.5074, + "step": 1338368 + }, + { + "epoch": 1.01, + "learning_rate": 2.8080492648210162e-05, + "loss": 3.5106, + "step": 1338880 + }, + { + "epoch": 1.01, + "learning_rate": 2.807212307950337e-05, + "loss": 3.5135, + "step": 1339392 + }, + { + "epoch": 1.01, + "learning_rate": 2.806373713199285e-05, + "loss": 3.5086, + "step": 1339904 + }, + { + "epoch": 1.01, + "learning_rate": 2.805535118448233e-05, + "loss": 3.4893, + "step": 1340416 + }, + { + "epoch": 1.01, + "learning_rate": 2.804696523697181e-05, + "loss": 3.4974, + "step": 1340928 + }, + { + "epoch": 1.01, + "learning_rate": 2.8038595668265023e-05, + "loss": 3.5043, + "step": 1341440 + }, + { + "epoch": 1.01, + "learning_rate": 2.8030209720754503e-05, + "loss": 3.5107, + "step": 1341952 + }, + { + "epoch": 1.01, + "learning_rate": 2.8021823773243983e-05, + "loss": 3.513, + "step": 1342464 + }, + { + "epoch": 1.01, + "learning_rate": 2.8013437825733463e-05, + "loss": 3.5026, + "step": 1342976 + }, + { + "epoch": 1.02, + "learning_rate": 2.8005068257026672e-05, + "loss": 3.504, + "step": 1343488 + }, + { + "epoch": 1.02, + "learning_rate": 2.7996682309516152e-05, + "loss": 3.4881, + "step": 1344000 + }, + { + "epoch": 1.02, + "learning_rate": 2.7988296362005632e-05, + "loss": 3.5035, + "step": 1344512 + }, + { + "epoch": 1.02, + "learning_rate": 2.7979910414495116e-05, + "loss": 3.5092, + "step": 1345024 + }, + { + "epoch": 1.02, + "learning_rate": 2.7971540845788325e-05, + "loss": 3.5091, + "step": 1345536 + }, + { + "epoch": 1.02, + "learning_rate": 2.7963154898277805e-05, + "loss": 3.5114, + "step": 1346048 + }, + { + "epoch": 1.02, + "learning_rate": 2.7954768950767285e-05, + "loss": 3.5004, + "step": 1346560 + }, + { + "epoch": 1.02, + "learning_rate": 2.7946383003256765e-05, + "loss": 3.5029, + "step": 1347072 + }, + { + "epoch": 1.02, + "learning_rate": 2.7938013434549977e-05, + "loss": 3.5107, + "step": 1347584 + }, + { + "epoch": 1.02, + "learning_rate": 2.7929627487039457e-05, + "loss": 3.508, + "step": 1348096 + }, + { + "epoch": 1.02, + "learning_rate": 2.7921241539528937e-05, + "loss": 3.5034, + "step": 1348608 + }, + { + "epoch": 1.02, + "learning_rate": 2.7912855592018417e-05, + "loss": 3.5003, + "step": 1349120 + }, + { + "epoch": 1.02, + "learning_rate": 2.7904486023311626e-05, + "loss": 3.4978, + "step": 1349632 + }, + { + "epoch": 1.02, + "learning_rate": 2.7896100075801106e-05, + "loss": 3.5082, + "step": 1350144 + }, + { + "epoch": 1.02, + "learning_rate": 2.7887714128290586e-05, + "loss": 3.511, + "step": 1350656 + }, + { + "epoch": 1.02, + "learning_rate": 2.7879328180780062e-05, + "loss": 3.4914, + "step": 1351168 + }, + { + "epoch": 1.02, + "learning_rate": 2.787095861207328e-05, + "loss": 3.5016, + "step": 1351680 + }, + { + "epoch": 1.02, + "learning_rate": 2.786257266456276e-05, + "loss": 3.5131, + "step": 1352192 + }, + { + "epoch": 1.02, + "learning_rate": 2.7854186717052238e-05, + "loss": 3.5061, + "step": 1352704 + }, + { + "epoch": 1.02, + "learning_rate": 2.7845800769541715e-05, + "loss": 3.4952, + "step": 1353216 + }, + { + "epoch": 1.02, + "learning_rate": 2.783743120083493e-05, + "loss": 3.4997, + "step": 1353728 + }, + { + "epoch": 1.02, + "learning_rate": 2.782904525332441e-05, + "loss": 3.4963, + "step": 1354240 + }, + { + "epoch": 1.02, + "learning_rate": 2.782065930581389e-05, + "loss": 3.5164, + "step": 1354752 + }, + { + "epoch": 1.02, + "learning_rate": 2.7812273358303364e-05, + "loss": 3.4986, + "step": 1355264 + }, + { + "epoch": 1.02, + "learning_rate": 2.780390378959658e-05, + "loss": 3.5068, + "step": 1355776 + }, + { + "epoch": 1.02, + "learning_rate": 2.7795534220889792e-05, + "loss": 3.5039, + "step": 1356288 + }, + { + "epoch": 1.02, + "learning_rate": 2.7787148273379272e-05, + "loss": 3.517, + "step": 1356800 + }, + { + "epoch": 1.02, + "learning_rate": 2.7778762325868752e-05, + "loss": 3.5001, + "step": 1357312 + }, + { + "epoch": 1.02, + "learning_rate": 2.7770376378358232e-05, + "loss": 3.5083, + "step": 1357824 + }, + { + "epoch": 1.02, + "learning_rate": 2.7761990430847712e-05, + "loss": 3.514, + "step": 1358336 + }, + { + "epoch": 1.02, + "learning_rate": 2.7753604483337185e-05, + "loss": 3.504, + "step": 1358848 + }, + { + "epoch": 1.02, + "learning_rate": 2.774521853582667e-05, + "loss": 3.4984, + "step": 1359360 + }, + { + "epoch": 1.02, + "learning_rate": 2.7736848967119884e-05, + "loss": 3.5021, + "step": 1359872 + }, + { + "epoch": 1.02, + "learning_rate": 2.7728463019609358e-05, + "loss": 3.4986, + "step": 1360384 + }, + { + "epoch": 1.02, + "learning_rate": 2.7720077072098838e-05, + "loss": 3.5013, + "step": 1360896 + }, + { + "epoch": 1.02, + "learning_rate": 2.7711691124588317e-05, + "loss": 3.5043, + "step": 1361408 + }, + { + "epoch": 1.02, + "learning_rate": 2.7703321555881533e-05, + "loss": 3.5035, + "step": 1361920 + }, + { + "epoch": 1.02, + "learning_rate": 2.769493560837101e-05, + "loss": 3.4956, + "step": 1362432 + }, + { + "epoch": 1.02, + "learning_rate": 2.768654966086049e-05, + "loss": 3.4978, + "step": 1362944 + }, + { + "epoch": 1.02, + "learning_rate": 2.767816371334997e-05, + "loss": 3.5014, + "step": 1363456 + }, + { + "epoch": 1.02, + "learning_rate": 2.7669794144643186e-05, + "loss": 3.5141, + "step": 1363968 + }, + { + "epoch": 1.02, + "learning_rate": 2.766140819713266e-05, + "loss": 3.5182, + "step": 1364480 + }, + { + "epoch": 1.02, + "learning_rate": 2.765302224962214e-05, + "loss": 3.5056, + "step": 1364992 + }, + { + "epoch": 1.02, + "learning_rate": 2.7644636302111622e-05, + "loss": 3.4946, + "step": 1365504 + }, + { + "epoch": 1.02, + "learning_rate": 2.763626673340483e-05, + "loss": 3.5089, + "step": 1366016 + }, + { + "epoch": 1.02, + "learning_rate": 2.762788078589431e-05, + "loss": 3.5077, + "step": 1366528 + }, + { + "epoch": 1.02, + "learning_rate": 2.761949483838379e-05, + "loss": 3.5079, + "step": 1367040 + }, + { + "epoch": 1.02, + "learning_rate": 2.761110889087327e-05, + "loss": 3.5012, + "step": 1367552 + }, + { + "epoch": 1.02, + "learning_rate": 2.7602739322166484e-05, + "loss": 3.5112, + "step": 1368064 + }, + { + "epoch": 1.02, + "learning_rate": 2.7594353374655964e-05, + "loss": 3.5007, + "step": 1368576 + }, + { + "epoch": 1.02, + "learning_rate": 2.7585967427145444e-05, + "loss": 3.5085, + "step": 1369088 + }, + { + "epoch": 1.02, + "learning_rate": 2.7577581479634923e-05, + "loss": 3.5023, + "step": 1369600 + }, + { + "epoch": 1.02, + "learning_rate": 2.7569211910928133e-05, + "loss": 3.5045, + "step": 1370112 + }, + { + "epoch": 1.02, + "learning_rate": 2.7560825963417613e-05, + "loss": 3.5016, + "step": 1370624 + }, + { + "epoch": 1.02, + "learning_rate": 2.7552440015907092e-05, + "loss": 3.4951, + "step": 1371136 + }, + { + "epoch": 1.02, + "learning_rate": 2.7544054068396576e-05, + "loss": 3.5111, + "step": 1371648 + }, + { + "epoch": 1.02, + "learning_rate": 2.7535684499689785e-05, + "loss": 3.5082, + "step": 1372160 + }, + { + "epoch": 1.02, + "learning_rate": 2.7527298552179265e-05, + "loss": 3.5106, + "step": 1372672 + }, + { + "epoch": 1.02, + "learning_rate": 2.7518912604668745e-05, + "loss": 3.4982, + "step": 1373184 + }, + { + "epoch": 1.02, + "learning_rate": 2.7510543035961954e-05, + "loss": 3.499, + "step": 1373696 + }, + { + "epoch": 1.03, + "eval_loss": 3.846364974975586, + "eval_runtime": 310.7137, + "eval_samples_per_second": 1228.111, + "eval_steps_per_second": 38.379, + "step": 1373760 + }, + { + "epoch": 0.0, + "learning_rate": 2.7502157088451437e-05, + "loss": 3.4992, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.7493771140940917e-05, + "loss": 3.4989, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.7485385193430397e-05, + "loss": 3.5099, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.7476999245919877e-05, + "loss": 3.5005, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.7468629677213086e-05, + "loss": 3.5127, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.7460243729702566e-05, + "loss": 3.4937, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.7451857782192046e-05, + "loss": 3.5046, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.744347183468153e-05, + "loss": 3.4937, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.743510226597474e-05, + "loss": 3.5058, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.742671631846422e-05, + "loss": 3.5034, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.74183303709537e-05, + "loss": 3.508, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.7409960802246908e-05, + "loss": 3.5016, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.740157485473639e-05, + "loss": 3.4929, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.739318890722587e-05, + "loss": 3.4962, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.738480295971535e-05, + "loss": 3.496, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.737641701220483e-05, + "loss": 3.4955, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.736804744349804e-05, + "loss": 3.4986, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.735966149598752e-05, + "loss": 3.4958, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.7351275548477e-05, + "loss": 3.4952, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.734288960096648e-05, + "loss": 3.5134, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.7334520032259692e-05, + "loss": 3.5027, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.7326134084749172e-05, + "loss": 3.5044, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.7317748137238652e-05, + "loss": 3.5024, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.730937856853186e-05, + "loss": 3.5109, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.730099262102134e-05, + "loss": 3.4888, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.7292606673510825e-05, + "loss": 3.5034, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.7284220726000305e-05, + "loss": 3.5022, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.7275851157293514e-05, + "loss": 3.4963, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.7267465209782994e-05, + "loss": 3.4873, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.7259079262272474e-05, + "loss": 3.4875, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.7250693314761953e-05, + "loss": 3.5032, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.7242323746055166e-05, + "loss": 3.5085, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.7233937798544646e-05, + "loss": 3.4993, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.7225551851034126e-05, + "loss": 3.5046, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.7217165903523606e-05, + "loss": 3.4932, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.7208796334816815e-05, + "loss": 3.5002, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.7200410387306295e-05, + "loss": 3.493, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.7192024439795778e-05, + "loss": 3.5052, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.7183638492285258e-05, + "loss": 3.4834, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.7175268923578467e-05, + "loss": 3.4948, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.7166882976067947e-05, + "loss": 3.4931, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.7158497028557427e-05, + "loss": 3.5123, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.7150111081046907e-05, + "loss": 3.4952, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.714174151234012e-05, + "loss": 3.4967, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.71333555648296e-05, + "loss": 3.5017, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.712496961731908e-05, + "loss": 3.4936, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.711658366980856e-05, + "loss": 3.5007, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.710821410110177e-05, + "loss": 3.4808, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.709982815359125e-05, + "loss": 3.4938, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.7091442206080732e-05, + "loss": 3.5015, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.7083056258570212e-05, + "loss": 3.4951, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.707468668986342e-05, + "loss": 3.493, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.70663007423529e-05, + "loss": 3.4881, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.705791479484238e-05, + "loss": 3.4952, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.704952884733186e-05, + "loss": 3.4802, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.7041159278625073e-05, + "loss": 3.497, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.7032773331114553e-05, + "loss": 3.481, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.7024387383604033e-05, + "loss": 3.4958, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.7016001436093513e-05, + "loss": 3.4964, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.7007631867386722e-05, + "loss": 3.4915, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.6999245919876202e-05, + "loss": 3.4966, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.6990859972365686e-05, + "loss": 3.4969, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.6982474024855166e-05, + "loss": 3.4781, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.6974104456148375e-05, + "loss": 3.4879, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.6965718508637855e-05, + "loss": 3.4987, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.6957332561127335e-05, + "loss": 3.4943, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.6948946613616814e-05, + "loss": 3.489, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.6940577044910027e-05, + "loss": 3.4808, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.6932191097399507e-05, + "loss": 3.4868, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.6923805149888987e-05, + "loss": 3.4964, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.6915419202378467e-05, + "loss": 3.4986, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.6907049633671676e-05, + "loss": 3.49, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.6898663686161156e-05, + "loss": 3.5051, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.689027773865064e-05, + "loss": 3.5049, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.688189179114012e-05, + "loss": 3.5076, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.6873522222433328e-05, + "loss": 3.4844, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.6865136274922808e-05, + "loss": 3.5049, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.6856750327412288e-05, + "loss": 3.4932, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.6848364379901768e-05, + "loss": 3.4911, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.683999481119498e-05, + "loss": 3.4963, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.683160886368446e-05, + "loss": 3.4987, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.682322291617394e-05, + "loss": 3.4992, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.681483696866342e-05, + "loss": 3.4993, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.680646739995663e-05, + "loss": 3.4764, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.679808145244611e-05, + "loss": 3.4857, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.6789695504935593e-05, + "loss": 3.4921, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.6781309557425073e-05, + "loss": 3.4993, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.6772939988718282e-05, + "loss": 3.5003, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.6764554041207762e-05, + "loss": 3.4873, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.6756168093697242e-05, + "loss": 3.4907, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.6747782146186722e-05, + "loss": 3.4765, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.6739412577479934e-05, + "loss": 3.4919, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.6731026629969414e-05, + "loss": 3.4922, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.6722640682458894e-05, + "loss": 3.4955, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.6714254734948374e-05, + "loss": 3.4971, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.6705885166241583e-05, + "loss": 3.4957, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.6697499218731063e-05, + "loss": 3.4867, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.6689113271220547e-05, + "loss": 3.4984, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.6680727323710027e-05, + "loss": 3.4939, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.6672357755003236e-05, + "loss": 3.493, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.6663971807492716e-05, + "loss": 3.4874, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.6655585859982196e-05, + "loss": 3.4862, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.6647199912471675e-05, + "loss": 3.4947, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.6638830343764888e-05, + "loss": 3.4993, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.6630444396254368e-05, + "loss": 3.4775, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.6622058448743848e-05, + "loss": 3.4901, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.6613672501233328e-05, + "loss": 3.5046, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.6605302932526537e-05, + "loss": 3.4918, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.6596916985016017e-05, + "loss": 3.4805, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.65885310375055e-05, + "loss": 3.4867, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.658014508999498e-05, + "loss": 3.4873, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.657177552128819e-05, + "loss": 3.5016, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.656338957377767e-05, + "loss": 3.4844, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.655500362626715e-05, + "loss": 3.495, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.654661767875663e-05, + "loss": 3.4936, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.653824811004984e-05, + "loss": 3.5006, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.652986216253932e-05, + "loss": 3.4884, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.65214762150288e-05, + "loss": 3.4993, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.6513090267518275e-05, + "loss": 3.501, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.650472069881149e-05, + "loss": 3.4903, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.649633475130097e-05, + "loss": 3.4851, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.648794880379045e-05, + "loss": 3.4887, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.6479562856279927e-05, + "loss": 3.4862, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.6471193287573143e-05, + "loss": 3.4912, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.6462807340062623e-05, + "loss": 3.4893, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.64544213925521e-05, + "loss": 3.4939, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.644603544504158e-05, + "loss": 3.4821, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.6437665876334795e-05, + "loss": 3.4835, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.6429279928824275e-05, + "loss": 3.4886, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.642089398131375e-05, + "loss": 3.5014, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.6412524412606964e-05, + "loss": 3.5054, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.6404138465096444e-05, + "loss": 3.4948, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.6395752517585924e-05, + "loss": 3.4834, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.63873665700754e-05, + "loss": 3.494, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.6378997001368617e-05, + "loss": 3.4972, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.6370611053858097e-05, + "loss": 3.4929, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.636222510634757e-05, + "loss": 3.4876, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.635383915883705e-05, + "loss": 3.4948, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.6345469590130266e-05, + "loss": 3.4901, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.633708364261975e-05, + "loss": 3.5003, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.6328697695109222e-05, + "loss": 3.4827, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.6320311747598702e-05, + "loss": 3.4956, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.6311942178891918e-05, + "loss": 3.4877, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.6303556231381398e-05, + "loss": 3.4806, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.6295170283870875e-05, + "loss": 3.4962, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.6286784336360354e-05, + "loss": 3.4965, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.627841476765357e-05, + "loss": 3.4947, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.6270028820143044e-05, + "loss": 3.4898, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.6261642872632523e-05, + "loss": 3.4808, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 3.8489468097686768, + "eval_runtime": 303.484, + "eval_samples_per_second": 1257.368, + "eval_steps_per_second": 39.294, + "step": 1450080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6253256925122003e-05, + "loss": 3.493, + "step": 1450496 + }, + { + "epoch": 1.0, + "learning_rate": 2.624488735641522e-05, + "loss": 3.4854, + "step": 1451008 + }, + { + "epoch": 1.0, + "learning_rate": 2.6236501408904696e-05, + "loss": 3.4957, + "step": 1451520 + }, + { + "epoch": 1.0, + "learning_rate": 2.6228115461394176e-05, + "loss": 3.487, + "step": 1452032 + }, + { + "epoch": 1.0, + "learning_rate": 2.6219729513883656e-05, + "loss": 3.5061, + "step": 1452544 + }, + { + "epoch": 1.0, + "learning_rate": 2.621135994517687e-05, + "loss": 3.4772, + "step": 1453056 + }, + { + "epoch": 1.0, + "learning_rate": 2.6202973997666348e-05, + "loss": 3.4935, + "step": 1453568 + }, + { + "epoch": 1.0, + "learning_rate": 2.6194588050155828e-05, + "loss": 3.4799, + "step": 1454080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6186202102645308e-05, + "loss": 3.4939, + "step": 1454592 + }, + { + "epoch": 1.0, + "learning_rate": 2.6177832533938517e-05, + "loss": 3.4916, + "step": 1455104 + }, + { + "epoch": 1.0, + "learning_rate": 2.6169446586427997e-05, + "loss": 3.4885, + "step": 1455616 + }, + { + "epoch": 1.0, + "learning_rate": 2.6161060638917477e-05, + "loss": 3.4952, + "step": 1456128 + }, + { + "epoch": 1.0, + "learning_rate": 2.6152674691406957e-05, + "loss": 3.4777, + "step": 1456640 + }, + { + "epoch": 1.0, + "learning_rate": 2.614430512270017e-05, + "loss": 3.4842, + "step": 1457152 + }, + { + "epoch": 1.0, + "learning_rate": 2.613591917518965e-05, + "loss": 3.4857, + "step": 1457664 + }, + { + "epoch": 1.0, + "learning_rate": 2.612753322767913e-05, + "loss": 3.4863, + "step": 1458176 + }, + { + "epoch": 1.0, + "learning_rate": 2.611914728016861e-05, + "loss": 3.4853, + "step": 1458688 + }, + { + "epoch": 1.0, + "learning_rate": 2.611077771146182e-05, + "loss": 3.4812, + "step": 1459200 + }, + { + "epoch": 1.0, + "learning_rate": 2.6102391763951302e-05, + "loss": 3.4858, + "step": 1459712 + }, + { + "epoch": 1.0, + "learning_rate": 2.6094005816440782e-05, + "loss": 3.5001, + "step": 1460224 + }, + { + "epoch": 1.0, + "learning_rate": 2.6085619868930262e-05, + "loss": 3.4905, + "step": 1460736 + }, + { + "epoch": 1.0, + "learning_rate": 2.607725030022347e-05, + "loss": 3.491, + "step": 1461248 + }, + { + "epoch": 1.0, + "learning_rate": 2.606886435271295e-05, + "loss": 3.4919, + "step": 1461760 + }, + { + "epoch": 1.0, + "learning_rate": 2.606047840520243e-05, + "loss": 3.4944, + "step": 1462272 + }, + { + "epoch": 1.0, + "learning_rate": 2.605209245769191e-05, + "loss": 3.4778, + "step": 1462784 + }, + { + "epoch": 1.0, + "learning_rate": 2.6043722888985123e-05, + "loss": 3.4973, + "step": 1463296 + }, + { + "epoch": 1.0, + "learning_rate": 2.6035336941474603e-05, + "loss": 3.4838, + "step": 1463808 + }, + { + "epoch": 1.0, + "learning_rate": 2.6026950993964083e-05, + "loss": 3.4838, + "step": 1464320 + }, + { + "epoch": 1.0, + "learning_rate": 2.6018565046453563e-05, + "loss": 3.473, + "step": 1464832 + }, + { + "epoch": 1.01, + "learning_rate": 2.6010195477746772e-05, + "loss": 3.4818, + "step": 1465344 + }, + { + "epoch": 1.01, + "learning_rate": 2.6001809530236256e-05, + "loss": 3.4891, + "step": 1465856 + }, + { + "epoch": 1.01, + "learning_rate": 2.5993423582725736e-05, + "loss": 3.4978, + "step": 1466368 + }, + { + "epoch": 1.01, + "learning_rate": 2.5985037635215215e-05, + "loss": 3.49, + "step": 1466880 + }, + { + "epoch": 1.01, + "learning_rate": 2.5976668066508425e-05, + "loss": 3.4906, + "step": 1467392 + }, + { + "epoch": 1.01, + "learning_rate": 2.5968282118997905e-05, + "loss": 3.4786, + "step": 1467904 + }, + { + "epoch": 1.01, + "learning_rate": 2.5959896171487384e-05, + "loss": 3.4902, + "step": 1468416 + }, + { + "epoch": 1.01, + "learning_rate": 2.5951510223976864e-05, + "loss": 3.4766, + "step": 1468928 + }, + { + "epoch": 1.01, + "learning_rate": 2.5943140655270077e-05, + "loss": 3.4954, + "step": 1469440 + }, + { + "epoch": 1.01, + "learning_rate": 2.5934754707759557e-05, + "loss": 3.4703, + "step": 1469952 + }, + { + "epoch": 1.01, + "learning_rate": 2.5926368760249037e-05, + "loss": 3.4811, + "step": 1470464 + }, + { + "epoch": 1.01, + "learning_rate": 2.5917982812738517e-05, + "loss": 3.4808, + "step": 1470976 + }, + { + "epoch": 1.01, + "learning_rate": 2.5909613244031726e-05, + "loss": 3.4995, + "step": 1471488 + }, + { + "epoch": 1.01, + "learning_rate": 2.590122729652121e-05, + "loss": 3.4847, + "step": 1472000 + }, + { + "epoch": 1.01, + "learning_rate": 2.589284134901069e-05, + "loss": 3.4854, + "step": 1472512 + }, + { + "epoch": 1.01, + "learning_rate": 2.588445540150017e-05, + "loss": 3.4877, + "step": 1473024 + }, + { + "epoch": 1.01, + "learning_rate": 2.5876085832793378e-05, + "loss": 3.4852, + "step": 1473536 + }, + { + "epoch": 1.01, + "learning_rate": 2.5867699885282858e-05, + "loss": 3.4883, + "step": 1474048 + }, + { + "epoch": 1.01, + "learning_rate": 2.5859313937772338e-05, + "loss": 3.4733, + "step": 1474560 + }, + { + "epoch": 1.01, + "learning_rate": 2.5850927990261818e-05, + "loss": 3.4752, + "step": 1475072 + }, + { + "epoch": 1.01, + "learning_rate": 2.584255842155503e-05, + "loss": 3.4894, + "step": 1475584 + }, + { + "epoch": 1.01, + "learning_rate": 2.583417247404451e-05, + "loss": 3.4826, + "step": 1476096 + }, + { + "epoch": 1.01, + "learning_rate": 2.582578652653399e-05, + "loss": 3.4832, + "step": 1476608 + }, + { + "epoch": 1.01, + "learning_rate": 2.581740057902347e-05, + "loss": 3.4788, + "step": 1477120 + }, + { + "epoch": 1.01, + "learning_rate": 2.580903101031668e-05, + "loss": 3.481, + "step": 1477632 + }, + { + "epoch": 1.01, + "learning_rate": 2.5800645062806163e-05, + "loss": 3.4664, + "step": 1478144 + }, + { + "epoch": 1.01, + "learning_rate": 2.5792259115295643e-05, + "loss": 3.4878, + "step": 1478656 + }, + { + "epoch": 1.01, + "learning_rate": 2.5783873167785123e-05, + "loss": 3.4691, + "step": 1479168 + }, + { + "epoch": 1.01, + "learning_rate": 2.5775503599078332e-05, + "loss": 3.4862, + "step": 1479680 + }, + { + "epoch": 1.01, + "learning_rate": 2.5767117651567812e-05, + "loss": 3.4803, + "step": 1480192 + }, + { + "epoch": 1.01, + "learning_rate": 2.5758731704057292e-05, + "loss": 3.4851, + "step": 1480704 + }, + { + "epoch": 1.01, + "learning_rate": 2.5750345756546772e-05, + "loss": 3.48, + "step": 1481216 + }, + { + "epoch": 1.01, + "learning_rate": 2.5741976187839984e-05, + "loss": 3.4876, + "step": 1481728 + }, + { + "epoch": 1.01, + "learning_rate": 2.5733590240329464e-05, + "loss": 3.4655, + "step": 1482240 + }, + { + "epoch": 1.01, + "learning_rate": 2.5725204292818944e-05, + "loss": 3.479, + "step": 1482752 + }, + { + "epoch": 1.01, + "learning_rate": 2.5716818345308424e-05, + "loss": 3.4851, + "step": 1483264 + }, + { + "epoch": 1.01, + "learning_rate": 2.5708448776601633e-05, + "loss": 3.4834, + "step": 1483776 + }, + { + "epoch": 1.01, + "learning_rate": 2.5700062829091117e-05, + "loss": 3.4735, + "step": 1484288 + }, + { + "epoch": 1.01, + "learning_rate": 2.5691676881580597e-05, + "loss": 3.4729, + "step": 1484800 + }, + { + "epoch": 1.01, + "learning_rate": 2.5683290934070076e-05, + "loss": 3.4733, + "step": 1485312 + }, + { + "epoch": 1.01, + "learning_rate": 2.5674921365363286e-05, + "loss": 3.4791, + "step": 1485824 + }, + { + "epoch": 1.01, + "learning_rate": 2.5666535417852766e-05, + "loss": 3.4868, + "step": 1486336 + }, + { + "epoch": 1.01, + "learning_rate": 2.5658149470342245e-05, + "loss": 3.4792, + "step": 1486848 + }, + { + "epoch": 1.01, + "learning_rate": 2.5649763522831725e-05, + "loss": 3.4941, + "step": 1487360 + }, + { + "epoch": 1.01, + "learning_rate": 2.5641393954124938e-05, + "loss": 3.4921, + "step": 1487872 + }, + { + "epoch": 1.01, + "learning_rate": 2.5633008006614418e-05, + "loss": 3.4984, + "step": 1488384 + }, + { + "epoch": 1.01, + "learning_rate": 2.5624622059103898e-05, + "loss": 3.4684, + "step": 1488896 + }, + { + "epoch": 1.01, + "learning_rate": 2.5616236111593378e-05, + "loss": 3.4877, + "step": 1489408 + }, + { + "epoch": 1.01, + "learning_rate": 2.5607866542886587e-05, + "loss": 3.4879, + "step": 1489920 + }, + { + "epoch": 1.01, + "learning_rate": 2.559948059537607e-05, + "loss": 3.4737, + "step": 1490432 + }, + { + "epoch": 1.01, + "learning_rate": 2.559109464786555e-05, + "loss": 3.4861, + "step": 1490944 + }, + { + "epoch": 1.01, + "learning_rate": 2.558270870035503e-05, + "loss": 3.4881, + "step": 1491456 + }, + { + "epoch": 1.01, + "learning_rate": 2.557433913164824e-05, + "loss": 3.4885, + "step": 1491968 + }, + { + "epoch": 1.01, + "learning_rate": 2.556595318413772e-05, + "loss": 3.48, + "step": 1492480 + }, + { + "epoch": 1.01, + "learning_rate": 2.55575672366272e-05, + "loss": 3.4707, + "step": 1492992 + }, + { + "epoch": 1.01, + "learning_rate": 2.554919766792041e-05, + "loss": 3.4715, + "step": 1493504 + }, + { + "epoch": 1.01, + "learning_rate": 2.554081172040989e-05, + "loss": 3.4801, + "step": 1494016 + }, + { + "epoch": 1.01, + "learning_rate": 2.553242577289937e-05, + "loss": 3.4866, + "step": 1494528 + }, + { + "epoch": 1.01, + "learning_rate": 2.552403982538885e-05, + "loss": 3.4906, + "step": 1495040 + }, + { + "epoch": 1.01, + "learning_rate": 2.551565387787833e-05, + "loss": 3.4732, + "step": 1495552 + }, + { + "epoch": 1.02, + "learning_rate": 2.550728430917154e-05, + "loss": 3.4786, + "step": 1496064 + }, + { + "epoch": 1.02, + "learning_rate": 2.549889836166102e-05, + "loss": 3.4651, + "step": 1496576 + }, + { + "epoch": 1.02, + "learning_rate": 2.5490512414150504e-05, + "loss": 3.477, + "step": 1497088 + }, + { + "epoch": 1.02, + "learning_rate": 2.5482142845443713e-05, + "loss": 3.4815, + "step": 1497600 + }, + { + "epoch": 1.02, + "learning_rate": 2.5473756897933193e-05, + "loss": 3.4822, + "step": 1498112 + }, + { + "epoch": 1.02, + "learning_rate": 2.5465370950422673e-05, + "loss": 3.487, + "step": 1498624 + }, + { + "epoch": 1.02, + "learning_rate": 2.5456985002912153e-05, + "loss": 3.4837, + "step": 1499136 + }, + { + "epoch": 1.02, + "learning_rate": 2.5448615434205365e-05, + "loss": 3.4749, + "step": 1499648 + }, + { + "epoch": 1.02, + "learning_rate": 2.5440229486694845e-05, + "loss": 3.4858, + "step": 1500160 + }, + { + "epoch": 1.02, + "learning_rate": 2.5431843539184325e-05, + "loss": 3.4821, + "step": 1500672 + }, + { + "epoch": 1.02, + "learning_rate": 2.5423457591673805e-05, + "loss": 3.4843, + "step": 1501184 + }, + { + "epoch": 1.02, + "learning_rate": 2.5415088022967014e-05, + "loss": 3.4704, + "step": 1501696 + }, + { + "epoch": 1.02, + "learning_rate": 2.5406702075456494e-05, + "loss": 3.4761, + "step": 1502208 + }, + { + "epoch": 1.02, + "learning_rate": 2.5398316127945974e-05, + "loss": 3.4812, + "step": 1502720 + }, + { + "epoch": 1.02, + "learning_rate": 2.5389930180435458e-05, + "loss": 3.4887, + "step": 1503232 + }, + { + "epoch": 1.02, + "learning_rate": 2.5381560611728667e-05, + "loss": 3.4684, + "step": 1503744 + }, + { + "epoch": 1.02, + "learning_rate": 2.5373174664218147e-05, + "loss": 3.4727, + "step": 1504256 + }, + { + "epoch": 1.02, + "learning_rate": 2.5364788716707627e-05, + "loss": 3.4899, + "step": 1504768 + }, + { + "epoch": 1.02, + "learning_rate": 2.5356402769197106e-05, + "loss": 3.4814, + "step": 1505280 + }, + { + "epoch": 1.02, + "learning_rate": 2.534803320049032e-05, + "loss": 3.4686, + "step": 1505792 + }, + { + "epoch": 1.02, + "learning_rate": 2.53396472529798e-05, + "loss": 3.4726, + "step": 1506304 + }, + { + "epoch": 1.02, + "learning_rate": 2.533126130546928e-05, + "loss": 3.4785, + "step": 1506816 + }, + { + "epoch": 1.02, + "learning_rate": 2.532287535795876e-05, + "loss": 3.4843, + "step": 1507328 + }, + { + "epoch": 1.02, + "learning_rate": 2.5314505789251968e-05, + "loss": 3.4748, + "step": 1507840 + }, + { + "epoch": 1.02, + "learning_rate": 2.5306119841741448e-05, + "loss": 3.4778, + "step": 1508352 + }, + { + "epoch": 1.02, + "learning_rate": 2.5297733894230928e-05, + "loss": 3.4845, + "step": 1508864 + }, + { + "epoch": 1.02, + "learning_rate": 2.528934794672041e-05, + "loss": 3.4887, + "step": 1509376 + }, + { + "epoch": 1.02, + "learning_rate": 2.528097837801362e-05, + "loss": 3.4829, + "step": 1509888 + }, + { + "epoch": 1.02, + "learning_rate": 2.52725924305031e-05, + "loss": 3.4786, + "step": 1510400 + }, + { + "epoch": 1.02, + "learning_rate": 2.526420648299258e-05, + "loss": 3.4932, + "step": 1510912 + }, + { + "epoch": 1.02, + "learning_rate": 2.525582053548206e-05, + "loss": 3.4783, + "step": 1511424 + }, + { + "epoch": 1.02, + "learning_rate": 2.5247450966775273e-05, + "loss": 3.4692, + "step": 1511936 + }, + { + "epoch": 1.02, + "learning_rate": 2.5239065019264753e-05, + "loss": 3.4776, + "step": 1512448 + }, + { + "epoch": 1.02, + "learning_rate": 2.5230679071754233e-05, + "loss": 3.4757, + "step": 1512960 + }, + { + "epoch": 1.02, + "learning_rate": 2.5222293124243712e-05, + "loss": 3.4804, + "step": 1513472 + }, + { + "epoch": 1.02, + "learning_rate": 2.521392355553692e-05, + "loss": 3.4732, + "step": 1513984 + }, + { + "epoch": 1.02, + "learning_rate": 2.52055376080264e-05, + "loss": 3.4837, + "step": 1514496 + }, + { + "epoch": 1.02, + "learning_rate": 2.519715166051588e-05, + "loss": 3.4716, + "step": 1515008 + }, + { + "epoch": 1.02, + "learning_rate": 2.5188765713005365e-05, + "loss": 3.4718, + "step": 1515520 + }, + { + "epoch": 1.02, + "learning_rate": 2.5180396144298574e-05, + "loss": 3.4748, + "step": 1516032 + }, + { + "epoch": 1.02, + "learning_rate": 2.5172010196788054e-05, + "loss": 3.4931, + "step": 1516544 + }, + { + "epoch": 1.02, + "learning_rate": 2.5163624249277534e-05, + "loss": 3.4874, + "step": 1517056 + }, + { + "epoch": 1.02, + "learning_rate": 2.5155238301767014e-05, + "loss": 3.487, + "step": 1517568 + }, + { + "epoch": 1.02, + "learning_rate": 2.5146868733060226e-05, + "loss": 3.4713, + "step": 1518080 + }, + { + "epoch": 1.02, + "learning_rate": 2.5138482785549706e-05, + "loss": 3.4855, + "step": 1518592 + }, + { + "epoch": 1.02, + "learning_rate": 2.5130096838039186e-05, + "loss": 3.4865, + "step": 1519104 + }, + { + "epoch": 1.02, + "learning_rate": 2.5121710890528666e-05, + "loss": 3.4793, + "step": 1519616 + }, + { + "epoch": 1.02, + "learning_rate": 2.5113341321821875e-05, + "loss": 3.4745, + "step": 1520128 + }, + { + "epoch": 1.02, + "learning_rate": 2.5104955374311355e-05, + "loss": 3.4847, + "step": 1520640 + }, + { + "epoch": 1.02, + "learning_rate": 2.5096569426800835e-05, + "loss": 3.4779, + "step": 1521152 + }, + { + "epoch": 1.02, + "learning_rate": 2.5088183479290312e-05, + "loss": 3.4889, + "step": 1521664 + }, + { + "epoch": 1.02, + "learning_rate": 2.5079813910583528e-05, + "loss": 3.4707, + "step": 1522176 + }, + { + "epoch": 1.02, + "learning_rate": 2.5071427963073008e-05, + "loss": 3.4854, + "step": 1522688 + }, + { + "epoch": 1.02, + "learning_rate": 2.5063042015562488e-05, + "loss": 3.4749, + "step": 1523200 + }, + { + "epoch": 1.02, + "learning_rate": 2.5054656068051964e-05, + "loss": 3.4738, + "step": 1523712 + }, + { + "epoch": 1.02, + "learning_rate": 2.504628649934518e-05, + "loss": 3.4796, + "step": 1524224 + }, + { + "epoch": 1.02, + "learning_rate": 2.503790055183466e-05, + "loss": 3.4885, + "step": 1524736 + }, + { + "epoch": 1.02, + "learning_rate": 2.502951460432414e-05, + "loss": 3.4824, + "step": 1525248 + }, + { + "epoch": 1.02, + "learning_rate": 2.5021128656813613e-05, + "loss": 3.4717, + "step": 1525760 + }, + { + "epoch": 1.02, + "learning_rate": 2.501275908810683e-05, + "loss": 3.4728, + "step": 1526272 + }, + { + "epoch": 1.03, + "eval_loss": 3.8487415313720703, + "eval_runtime": 303.2978, + "eval_samples_per_second": 1258.14, + "eval_steps_per_second": 39.318, + "step": 1526400 + }, + { + "epoch": 0.0, + "learning_rate": 2.500438951940004e-05, + "loss": 3.4751, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.499600357188952e-05, + "loss": 3.4764, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.4987617624378998e-05, + "loss": 3.4792, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.4979231676868478e-05, + "loss": 3.4771, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.497086210816169e-05, + "loss": 3.4898, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.496247616065117e-05, + "loss": 3.4724, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.495409021314065e-05, + "loss": 3.4791, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.494570426563013e-05, + "loss": 3.4653, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.4937334696923343e-05, + "loss": 3.4799, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.492894874941282e-05, + "loss": 3.4828, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.49205628019023e-05, + "loss": 3.4733, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.491217685439178e-05, + "loss": 3.4804, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.4903807285684995e-05, + "loss": 3.4657, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.489542133817447e-05, + "loss": 3.4726, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.488703539066395e-05, + "loss": 3.4742, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.487864944315343e-05, + "loss": 3.4702, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.487027987444664e-05, + "loss": 3.4754, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.486189392693612e-05, + "loss": 3.4695, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.4853507979425604e-05, + "loss": 3.4752, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.4845122031915084e-05, + "loss": 3.4854, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.4836752463208293e-05, + "loss": 3.4822, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.4828366515697773e-05, + "loss": 3.4782, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.4819980568187253e-05, + "loss": 3.4805, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.4811594620676733e-05, + "loss": 3.4824, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.4803225051969945e-05, + "loss": 3.4655, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.4794839104459425e-05, + "loss": 3.4843, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.4786453156948905e-05, + "loss": 3.4726, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.4778067209438385e-05, + "loss": 3.4681, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.4769697640731594e-05, + "loss": 3.462, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.4761311693221074e-05, + "loss": 3.4699, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.4752925745710558e-05, + "loss": 3.4743, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.4744556177003767e-05, + "loss": 3.4856, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.4736170229493247e-05, + "loss": 3.4761, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.4727784281982727e-05, + "loss": 3.4799, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.4719398334472207e-05, + "loss": 3.4654, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.471102876576542e-05, + "loss": 3.4768, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.47026428182549e-05, + "loss": 3.4721, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.469425687074438e-05, + "loss": 3.4771, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.468587092323386e-05, + "loss": 3.4584, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.4677501354527068e-05, + "loss": 3.4682, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.4669115407016548e-05, + "loss": 3.4712, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.4660729459506028e-05, + "loss": 3.4871, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.465234351199551e-05, + "loss": 3.4753, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.464397394328872e-05, + "loss": 3.4725, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.46355879957782e-05, + "loss": 3.4766, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.462720204826768e-05, + "loss": 3.4693, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.461881610075716e-05, + "loss": 3.4767, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.4610446532050373e-05, + "loss": 3.4621, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.4602060584539853e-05, + "loss": 3.4625, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.4593674637029333e-05, + "loss": 3.4772, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.4585288689518813e-05, + "loss": 3.469, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.4576919120812022e-05, + "loss": 3.4729, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.45685331733015e-05, + "loss": 3.4658, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.456014722579098e-05, + "loss": 3.4719, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.4551761278280465e-05, + "loss": 3.455, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.4543391709573674e-05, + "loss": 3.4694, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.4535005762063154e-05, + "loss": 3.4599, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.4526619814552634e-05, + "loss": 3.4701, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.4518233867042114e-05, + "loss": 3.4703, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.4509864298335326e-05, + "loss": 3.4711, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.4501478350824806e-05, + "loss": 3.4684, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.4493092403314286e-05, + "loss": 3.4801, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.4484706455803766e-05, + "loss": 3.4547, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.4476336887096975e-05, + "loss": 3.4604, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.4467950939586455e-05, + "loss": 3.4754, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.4459564992075935e-05, + "loss": 3.4686, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.445117904456542e-05, + "loss": 3.4637, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.4442809475858628e-05, + "loss": 3.4581, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.4434423528348108e-05, + "loss": 3.4622, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.4426037580837588e-05, + "loss": 3.4677, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.4417651633327064e-05, + "loss": 3.4747, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.440928206462028e-05, + "loss": 3.4683, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.440089611710976e-05, + "loss": 3.4809, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.439251016959924e-05, + "loss": 3.479, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.4384124222088717e-05, + "loss": 3.4905, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.437575465338193e-05, + "loss": 3.459, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.436736870587141e-05, + "loss": 3.4729, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.435898275836089e-05, + "loss": 3.4783, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.435059681085037e-05, + "loss": 3.4584, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.434222724214358e-05, + "loss": 3.4767, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.433384129463306e-05, + "loss": 3.4758, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.432547172592627e-05, + "loss": 3.4758, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.431708577841575e-05, + "loss": 3.4711, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.4308699830905234e-05, + "loss": 3.4575, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.4300313883394714e-05, + "loss": 3.4574, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.429192793588419e-05, + "loss": 3.4665, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.428354198837367e-05, + "loss": 3.4742, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.427515604086315e-05, + "loss": 3.4794, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.426677009335263e-05, + "loss": 3.4628, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.4258400524645843e-05, + "loss": 3.4685, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.4250014577135323e-05, + "loss": 3.4533, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.4241628629624803e-05, + "loss": 3.4646, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.4233242682114282e-05, + "loss": 3.4687, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.422487311340749e-05, + "loss": 3.4726, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.421648716589697e-05, + "loss": 3.477, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.420810121838645e-05, + "loss": 3.469, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.4199715270875935e-05, + "loss": 3.4677, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.4191345702169144e-05, + "loss": 3.4726, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.4182959754658624e-05, + "loss": 3.4675, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.4174573807148104e-05, + "loss": 3.4752, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.4166187859637584e-05, + "loss": 3.4588, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.4157801912127064e-05, + "loss": 3.465, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.4149432343420276e-05, + "loss": 3.4671, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.4141046395909756e-05, + "loss": 3.4765, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.4132660448399236e-05, + "loss": 3.456, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.4124274500888716e-05, + "loss": 3.4643, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.4115904932181925e-05, + "loss": 3.4754, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.4107518984671405e-05, + "loss": 3.4705, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.409913303716089e-05, + "loss": 3.455, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.4090763468454098e-05, + "loss": 3.4682, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.4082377520943578e-05, + "loss": 3.46, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.4073991573433058e-05, + "loss": 3.4784, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.4065605625922537e-05, + "loss": 3.462, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.405723605721575e-05, + "loss": 3.4615, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.404885010970523e-05, + "loss": 3.4729, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.404046416219471e-05, + "loss": 3.4818, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.403207821468419e-05, + "loss": 3.4696, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.40237086459774e-05, + "loss": 3.4689, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.401532269846688e-05, + "loss": 3.4758, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.400693675095636e-05, + "loss": 3.4686, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.3998550803445842e-05, + "loss": 3.4609, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.399018123473905e-05, + "loss": 3.4698, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.398179528722853e-05, + "loss": 3.4629, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.397340933971801e-05, + "loss": 3.4684, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.396502339220749e-05, + "loss": 3.4627, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.3956653823500704e-05, + "loss": 3.4709, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.3948267875990184e-05, + "loss": 3.4583, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.3939881928479664e-05, + "loss": 3.4592, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.393149598096914e-05, + "loss": 3.4659, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.3923126412262353e-05, + "loss": 3.4745, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.3914740464751833e-05, + "loss": 3.4765, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.3906354517241312e-05, + "loss": 3.4777, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.3897968569730792e-05, + "loss": 3.456, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.3889599001024005e-05, + "loss": 3.4747, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.3881213053513485e-05, + "loss": 3.4736, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.3872827106002965e-05, + "loss": 3.4721, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.386444115849244e-05, + "loss": 3.4604, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.3856071589785657e-05, + "loss": 3.4763, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.3847685642275137e-05, + "loss": 3.4623, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.3839299694764614e-05, + "loss": 3.4777, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.3830913747254094e-05, + "loss": 3.4552, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.3822544178547306e-05, + "loss": 3.4773, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.3814158231036786e-05, + "loss": 3.4588, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.3805772283526266e-05, + "loss": 3.4613, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.3797386336015746e-05, + "loss": 3.4712, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.378901676730896e-05, + "loss": 3.4725, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.3780630819798435e-05, + "loss": 3.4736, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.3772244872287915e-05, + "loss": 3.4554, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.3763858924777395e-05, + "loss": 3.4668, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 3.850640058517456, + "eval_runtime": 303.8817, + "eval_samples_per_second": 1255.722, + "eval_steps_per_second": 39.242, + "step": 1602720 + }, + { + "epoch": 1.0, + "learning_rate": 2.375548935607061e-05, + "loss": 3.4673, + "step": 1603072 + }, + { + "epoch": 1.0, + "learning_rate": 2.3747103408560088e-05, + "loss": 3.4641, + "step": 1603584 + }, + { + "epoch": 1.0, + "learning_rate": 2.3738717461049567e-05, + "loss": 3.4696, + "step": 1604096 + }, + { + "epoch": 1.0, + "learning_rate": 2.3730331513539047e-05, + "loss": 3.4665, + "step": 1604608 + }, + { + "epoch": 1.0, + "learning_rate": 2.372196194483226e-05, + "loss": 3.4788, + "step": 1605120 + }, + { + "epoch": 1.0, + "learning_rate": 2.3713575997321736e-05, + "loss": 3.4602, + "step": 1605632 + }, + { + "epoch": 1.0, + "learning_rate": 2.370519004981122e-05, + "loss": 3.4627, + "step": 1606144 + }, + { + "epoch": 1.0, + "learning_rate": 2.36968041023007e-05, + "loss": 3.4628, + "step": 1606656 + }, + { + "epoch": 1.0, + "learning_rate": 2.368843453359391e-05, + "loss": 3.4675, + "step": 1607168 + }, + { + "epoch": 1.0, + "learning_rate": 2.368004858608339e-05, + "loss": 3.4703, + "step": 1607680 + }, + { + "epoch": 1.0, + "learning_rate": 2.367166263857287e-05, + "loss": 3.4625, + "step": 1608192 + }, + { + "epoch": 1.0, + "learning_rate": 2.366327669106235e-05, + "loss": 3.4708, + "step": 1608704 + }, + { + "epoch": 1.0, + "learning_rate": 2.365490712235556e-05, + "loss": 3.4565, + "step": 1609216 + }, + { + "epoch": 1.0, + "learning_rate": 2.364652117484504e-05, + "loss": 3.4608, + "step": 1609728 + }, + { + "epoch": 1.0, + "learning_rate": 2.363813522733452e-05, + "loss": 3.4661, + "step": 1610240 + }, + { + "epoch": 1.0, + "learning_rate": 2.3629749279824e-05, + "loss": 3.4554, + "step": 1610752 + }, + { + "epoch": 1.0, + "learning_rate": 2.362137971111721e-05, + "loss": 3.4647, + "step": 1611264 + }, + { + "epoch": 1.0, + "learning_rate": 2.361299376360669e-05, + "loss": 3.4549, + "step": 1611776 + }, + { + "epoch": 1.0, + "learning_rate": 2.3604607816096173e-05, + "loss": 3.4592, + "step": 1612288 + }, + { + "epoch": 1.0, + "learning_rate": 2.3596221868585653e-05, + "loss": 3.4769, + "step": 1612800 + }, + { + "epoch": 1.0, + "learning_rate": 2.3587852299878863e-05, + "loss": 3.4662, + "step": 1613312 + }, + { + "epoch": 1.0, + "learning_rate": 2.3579466352368343e-05, + "loss": 3.4723, + "step": 1613824 + }, + { + "epoch": 1.0, + "learning_rate": 2.3571080404857822e-05, + "loss": 3.4658, + "step": 1614336 + }, + { + "epoch": 1.0, + "learning_rate": 2.3562694457347302e-05, + "loss": 3.4703, + "step": 1614848 + }, + { + "epoch": 1.0, + "learning_rate": 2.3554324888640515e-05, + "loss": 3.455, + "step": 1615360 + }, + { + "epoch": 1.0, + "learning_rate": 2.3545938941129995e-05, + "loss": 3.4739, + "step": 1615872 + }, + { + "epoch": 1.0, + "learning_rate": 2.3537552993619475e-05, + "loss": 3.4636, + "step": 1616384 + }, + { + "epoch": 1.0, + "learning_rate": 2.3529183424912684e-05, + "loss": 3.4533, + "step": 1616896 + }, + { + "epoch": 1.0, + "learning_rate": 2.3520797477402164e-05, + "loss": 3.4545, + "step": 1617408 + }, + { + "epoch": 1.0, + "learning_rate": 2.3512411529891644e-05, + "loss": 3.4563, + "step": 1617920 + }, + { + "epoch": 1.01, + "learning_rate": 2.3504025582381127e-05, + "loss": 3.4647, + "step": 1618432 + }, + { + "epoch": 1.01, + "learning_rate": 2.3495639634870607e-05, + "loss": 3.4711, + "step": 1618944 + }, + { + "epoch": 1.01, + "learning_rate": 2.3487270066163816e-05, + "loss": 3.4708, + "step": 1619456 + }, + { + "epoch": 1.01, + "learning_rate": 2.3478884118653296e-05, + "loss": 3.4671, + "step": 1619968 + }, + { + "epoch": 1.01, + "learning_rate": 2.3470498171142776e-05, + "loss": 3.456, + "step": 1620480 + }, + { + "epoch": 1.01, + "learning_rate": 2.346212860243599e-05, + "loss": 3.4656, + "step": 1620992 + }, + { + "epoch": 1.01, + "learning_rate": 2.345374265492547e-05, + "loss": 3.4613, + "step": 1621504 + }, + { + "epoch": 1.01, + "learning_rate": 2.344535670741495e-05, + "loss": 3.4654, + "step": 1622016 + }, + { + "epoch": 1.01, + "learning_rate": 2.343697075990443e-05, + "loss": 3.4526, + "step": 1622528 + }, + { + "epoch": 1.01, + "learning_rate": 2.3428601191197638e-05, + "loss": 3.454, + "step": 1623040 + }, + { + "epoch": 1.01, + "learning_rate": 2.3420215243687118e-05, + "loss": 3.4602, + "step": 1623552 + }, + { + "epoch": 1.01, + "learning_rate": 2.3411829296176597e-05, + "loss": 3.4743, + "step": 1624064 + }, + { + "epoch": 1.01, + "learning_rate": 2.340344334866608e-05, + "loss": 3.4645, + "step": 1624576 + }, + { + "epoch": 1.01, + "learning_rate": 2.339507377995929e-05, + "loss": 3.4591, + "step": 1625088 + }, + { + "epoch": 1.01, + "learning_rate": 2.338668783244877e-05, + "loss": 3.4679, + "step": 1625600 + }, + { + "epoch": 1.01, + "learning_rate": 2.337830188493825e-05, + "loss": 3.455, + "step": 1626112 + }, + { + "epoch": 1.01, + "learning_rate": 2.336991593742773e-05, + "loss": 3.4674, + "step": 1626624 + }, + { + "epoch": 1.01, + "learning_rate": 2.3361546368720942e-05, + "loss": 3.4525, + "step": 1627136 + }, + { + "epoch": 1.01, + "learning_rate": 2.3353160421210422e-05, + "loss": 3.4453, + "step": 1627648 + }, + { + "epoch": 1.01, + "learning_rate": 2.3344774473699902e-05, + "loss": 3.4678, + "step": 1628160 + }, + { + "epoch": 1.01, + "learning_rate": 2.3336388526189382e-05, + "loss": 3.459, + "step": 1628672 + }, + { + "epoch": 1.01, + "learning_rate": 2.332801895748259e-05, + "loss": 3.4592, + "step": 1629184 + }, + { + "epoch": 1.01, + "learning_rate": 2.331963300997207e-05, + "loss": 3.4591, + "step": 1629696 + }, + { + "epoch": 1.01, + "learning_rate": 2.331124706246155e-05, + "loss": 3.456, + "step": 1630208 + }, + { + "epoch": 1.01, + "learning_rate": 2.3302861114951034e-05, + "loss": 3.4467, + "step": 1630720 + }, + { + "epoch": 1.01, + "learning_rate": 2.3294491546244244e-05, + "loss": 3.4557, + "step": 1631232 + }, + { + "epoch": 1.01, + "learning_rate": 2.3286105598733724e-05, + "loss": 3.4514, + "step": 1631744 + }, + { + "epoch": 1.01, + "learning_rate": 2.3277719651223204e-05, + "loss": 3.4567, + "step": 1632256 + }, + { + "epoch": 1.01, + "learning_rate": 2.3269333703712683e-05, + "loss": 3.4601, + "step": 1632768 + }, + { + "epoch": 1.01, + "learning_rate": 2.3260964135005896e-05, + "loss": 3.4571, + "step": 1633280 + }, + { + "epoch": 1.01, + "learning_rate": 2.3252578187495376e-05, + "loss": 3.4571, + "step": 1633792 + }, + { + "epoch": 1.01, + "learning_rate": 2.3244192239984856e-05, + "loss": 3.4676, + "step": 1634304 + }, + { + "epoch": 1.01, + "learning_rate": 2.3235806292474336e-05, + "loss": 3.4457, + "step": 1634816 + }, + { + "epoch": 1.01, + "learning_rate": 2.3227436723767545e-05, + "loss": 3.4497, + "step": 1635328 + }, + { + "epoch": 1.01, + "learning_rate": 2.3219050776257025e-05, + "loss": 3.4583, + "step": 1635840 + }, + { + "epoch": 1.01, + "learning_rate": 2.3210664828746505e-05, + "loss": 3.4615, + "step": 1636352 + }, + { + "epoch": 1.01, + "learning_rate": 2.3202278881235985e-05, + "loss": 3.4487, + "step": 1636864 + }, + { + "epoch": 1.01, + "learning_rate": 2.3193909312529197e-05, + "loss": 3.4517, + "step": 1637376 + }, + { + "epoch": 1.01, + "learning_rate": 2.3185523365018677e-05, + "loss": 3.4492, + "step": 1637888 + }, + { + "epoch": 1.01, + "learning_rate": 2.3177137417508157e-05, + "loss": 3.4562, + "step": 1638400 + }, + { + "epoch": 1.01, + "learning_rate": 2.3168751469997634e-05, + "loss": 3.4624, + "step": 1638912 + }, + { + "epoch": 1.01, + "learning_rate": 2.316038190129085e-05, + "loss": 3.4592, + "step": 1639424 + }, + { + "epoch": 1.01, + "learning_rate": 2.315199595378033e-05, + "loss": 3.4693, + "step": 1639936 + }, + { + "epoch": 1.01, + "learning_rate": 2.3143610006269806e-05, + "loss": 3.4617, + "step": 1640448 + }, + { + "epoch": 1.01, + "learning_rate": 2.3135224058759286e-05, + "loss": 3.4846, + "step": 1640960 + }, + { + "epoch": 1.01, + "learning_rate": 2.31268544900525e-05, + "loss": 3.4476, + "step": 1641472 + }, + { + "epoch": 1.01, + "learning_rate": 2.311846854254198e-05, + "loss": 3.4587, + "step": 1641984 + }, + { + "epoch": 1.01, + "learning_rate": 2.311008259503146e-05, + "loss": 3.467, + "step": 1642496 + }, + { + "epoch": 1.01, + "learning_rate": 2.310169664752094e-05, + "loss": 3.4463, + "step": 1643008 + }, + { + "epoch": 1.01, + "learning_rate": 2.309332707881415e-05, + "loss": 3.4656, + "step": 1643520 + }, + { + "epoch": 1.01, + "learning_rate": 2.308494113130363e-05, + "loss": 3.4632, + "step": 1644032 + }, + { + "epoch": 1.01, + "learning_rate": 2.3076555183793107e-05, + "loss": 3.4615, + "step": 1644544 + }, + { + "epoch": 1.01, + "learning_rate": 2.3068169236282587e-05, + "loss": 3.4591, + "step": 1645056 + }, + { + "epoch": 1.01, + "learning_rate": 2.30597996675758e-05, + "loss": 3.4454, + "step": 1645568 + }, + { + "epoch": 1.01, + "learning_rate": 2.305141372006528e-05, + "loss": 3.4548, + "step": 1646080 + }, + { + "epoch": 1.01, + "learning_rate": 2.304302777255476e-05, + "loss": 3.4487, + "step": 1646592 + }, + { + "epoch": 1.01, + "learning_rate": 2.303464182504424e-05, + "loss": 3.4614, + "step": 1647104 + }, + { + "epoch": 1.01, + "learning_rate": 2.3026272256337452e-05, + "loss": 3.4681, + "step": 1647616 + }, + { + "epoch": 1.01, + "learning_rate": 2.301788630882693e-05, + "loss": 3.4481, + "step": 1648128 + }, + { + "epoch": 1.02, + "learning_rate": 2.3009500361316412e-05, + "loss": 3.4567, + "step": 1648640 + }, + { + "epoch": 1.02, + "learning_rate": 2.3001114413805892e-05, + "loss": 3.4461, + "step": 1649152 + }, + { + "epoch": 1.02, + "learning_rate": 2.2992744845099105e-05, + "loss": 3.4513, + "step": 1649664 + }, + { + "epoch": 1.02, + "learning_rate": 2.298435889758858e-05, + "loss": 3.454, + "step": 1650176 + }, + { + "epoch": 1.02, + "learning_rate": 2.297597295007806e-05, + "loss": 3.4658, + "step": 1650688 + }, + { + "epoch": 1.02, + "learning_rate": 2.296758700256754e-05, + "loss": 3.4684, + "step": 1651200 + }, + { + "epoch": 1.02, + "learning_rate": 2.2959217433860754e-05, + "loss": 3.4537, + "step": 1651712 + }, + { + "epoch": 1.02, + "learning_rate": 2.2950831486350234e-05, + "loss": 3.4524, + "step": 1652224 + }, + { + "epoch": 1.02, + "learning_rate": 2.2942445538839713e-05, + "loss": 3.4625, + "step": 1652736 + }, + { + "epoch": 1.02, + "learning_rate": 2.2934059591329193e-05, + "loss": 3.4537, + "step": 1653248 + }, + { + "epoch": 1.02, + "learning_rate": 2.2925690022622403e-05, + "loss": 3.4675, + "step": 1653760 + }, + { + "epoch": 1.02, + "learning_rate": 2.2917304075111882e-05, + "loss": 3.4493, + "step": 1654272 + }, + { + "epoch": 1.02, + "learning_rate": 2.2908918127601366e-05, + "loss": 3.4522, + "step": 1654784 + }, + { + "epoch": 1.02, + "learning_rate": 2.2900532180090846e-05, + "loss": 3.4567, + "step": 1655296 + }, + { + "epoch": 1.02, + "learning_rate": 2.2892162611384055e-05, + "loss": 3.4652, + "step": 1655808 + }, + { + "epoch": 1.02, + "learning_rate": 2.2883776663873535e-05, + "loss": 3.4457, + "step": 1656320 + }, + { + "epoch": 1.02, + "learning_rate": 2.2875390716363015e-05, + "loss": 3.4534, + "step": 1656832 + }, + { + "epoch": 1.02, + "learning_rate": 2.2867004768852495e-05, + "loss": 3.4596, + "step": 1657344 + }, + { + "epoch": 1.02, + "learning_rate": 2.2858635200145707e-05, + "loss": 3.4632, + "step": 1657856 + }, + { + "epoch": 1.02, + "learning_rate": 2.2850249252635187e-05, + "loss": 3.4414, + "step": 1658368 + }, + { + "epoch": 1.02, + "learning_rate": 2.2841863305124667e-05, + "loss": 3.4617, + "step": 1658880 + }, + { + "epoch": 1.02, + "learning_rate": 2.2833477357614147e-05, + "loss": 3.4483, + "step": 1659392 + }, + { + "epoch": 1.02, + "learning_rate": 2.2825107788907356e-05, + "loss": 3.4606, + "step": 1659904 + }, + { + "epoch": 1.02, + "learning_rate": 2.2816721841396836e-05, + "loss": 3.4534, + "step": 1660416 + }, + { + "epoch": 1.02, + "learning_rate": 2.280833589388632e-05, + "loss": 3.4525, + "step": 1660928 + }, + { + "epoch": 1.02, + "learning_rate": 2.27999499463758e-05, + "loss": 3.4615, + "step": 1661440 + }, + { + "epoch": 1.02, + "learning_rate": 2.279158037766901e-05, + "loss": 3.4694, + "step": 1661952 + }, + { + "epoch": 1.02, + "learning_rate": 2.278319443015849e-05, + "loss": 3.4577, + "step": 1662464 + }, + { + "epoch": 1.02, + "learning_rate": 2.277480848264797e-05, + "loss": 3.4578, + "step": 1662976 + }, + { + "epoch": 1.02, + "learning_rate": 2.276642253513745e-05, + "loss": 3.4627, + "step": 1663488 + }, + { + "epoch": 1.02, + "learning_rate": 2.275805296643066e-05, + "loss": 3.4567, + "step": 1664000 + }, + { + "epoch": 1.02, + "learning_rate": 2.274966701892014e-05, + "loss": 3.4492, + "step": 1664512 + }, + { + "epoch": 1.02, + "learning_rate": 2.274128107140962e-05, + "loss": 3.4547, + "step": 1665024 + }, + { + "epoch": 1.02, + "learning_rate": 2.27328951238991e-05, + "loss": 3.4513, + "step": 1665536 + }, + { + "epoch": 1.02, + "learning_rate": 2.272452555519231e-05, + "loss": 3.4566, + "step": 1666048 + }, + { + "epoch": 1.02, + "learning_rate": 2.271613960768179e-05, + "loss": 3.4561, + "step": 1666560 + }, + { + "epoch": 1.02, + "learning_rate": 2.2707753660171273e-05, + "loss": 3.4556, + "step": 1667072 + }, + { + "epoch": 1.02, + "learning_rate": 2.2699367712660753e-05, + "loss": 3.453, + "step": 1667584 + }, + { + "epoch": 1.02, + "learning_rate": 2.2690998143953962e-05, + "loss": 3.4459, + "step": 1668096 + }, + { + "epoch": 1.02, + "learning_rate": 2.2682612196443442e-05, + "loss": 3.4553, + "step": 1668608 + }, + { + "epoch": 1.02, + "learning_rate": 2.2674226248932922e-05, + "loss": 3.4623, + "step": 1669120 + }, + { + "epoch": 1.02, + "learning_rate": 2.2665840301422402e-05, + "loss": 3.4631, + "step": 1669632 + }, + { + "epoch": 1.02, + "learning_rate": 2.2657470732715615e-05, + "loss": 3.4671, + "step": 1670144 + }, + { + "epoch": 1.02, + "learning_rate": 2.2649084785205095e-05, + "loss": 3.4423, + "step": 1670656 + }, + { + "epoch": 1.02, + "learning_rate": 2.2640698837694574e-05, + "loss": 3.4676, + "step": 1671168 + }, + { + "epoch": 1.02, + "learning_rate": 2.2632312890184054e-05, + "loss": 3.4612, + "step": 1671680 + }, + { + "epoch": 1.02, + "learning_rate": 2.2623943321477264e-05, + "loss": 3.4582, + "step": 1672192 + }, + { + "epoch": 1.02, + "learning_rate": 2.2615557373966743e-05, + "loss": 3.4523, + "step": 1672704 + }, + { + "epoch": 1.02, + "learning_rate": 2.2607171426456223e-05, + "loss": 3.4614, + "step": 1673216 + }, + { + "epoch": 1.02, + "learning_rate": 2.2598785478945707e-05, + "loss": 3.4518, + "step": 1673728 + }, + { + "epoch": 1.02, + "learning_rate": 2.2590415910238916e-05, + "loss": 3.4706, + "step": 1674240 + }, + { + "epoch": 1.02, + "learning_rate": 2.2582029962728396e-05, + "loss": 3.443, + "step": 1674752 + }, + { + "epoch": 1.02, + "learning_rate": 2.2573644015217876e-05, + "loss": 3.4652, + "step": 1675264 + }, + { + "epoch": 1.02, + "learning_rate": 2.2565258067707352e-05, + "loss": 3.4489, + "step": 1675776 + }, + { + "epoch": 1.02, + "learning_rate": 2.2556888499000568e-05, + "loss": 3.4539, + "step": 1676288 + }, + { + "epoch": 1.02, + "learning_rate": 2.2548502551490048e-05, + "loss": 3.4573, + "step": 1676800 + }, + { + "epoch": 1.02, + "learning_rate": 2.2540116603979528e-05, + "loss": 3.4561, + "step": 1677312 + }, + { + "epoch": 1.02, + "learning_rate": 2.2531730656469005e-05, + "loss": 3.4689, + "step": 1677824 + }, + { + "epoch": 1.02, + "learning_rate": 2.2523361087762217e-05, + "loss": 3.4407, + "step": 1678336 + }, + { + "epoch": 1.02, + "learning_rate": 2.2514975140251697e-05, + "loss": 3.4605, + "step": 1678848 + }, + { + "epoch": 1.03, + "eval_loss": 3.8524880409240723, + "eval_runtime": 303.3278, + "eval_samples_per_second": 1258.015, + "eval_steps_per_second": 39.314, + "step": 1679040 + }, + { + "epoch": 0.0, + "learning_rate": 2.2506589192741177e-05, + "loss": 3.4551, + "step": 1679360 + }, + { + "epoch": 0.0, + "learning_rate": 2.2498203245230657e-05, + "loss": 3.4503, + "step": 1679872 + }, + { + "epoch": 0.0, + "learning_rate": 2.2489817297720137e-05, + "loss": 3.4593, + "step": 1680384 + }, + { + "epoch": 0.0, + "learning_rate": 2.2481431350209617e-05, + "loss": 3.4544, + "step": 1680896 + }, + { + "epoch": 0.0, + "learning_rate": 2.2473061781502826e-05, + "loss": 3.4639, + "step": 1681408 + }, + { + "epoch": 0.0, + "learning_rate": 2.2464675833992306e-05, + "loss": 3.4512, + "step": 1681920 + }, + { + "epoch": 0.0, + "learning_rate": 2.245628988648179e-05, + "loss": 3.4484, + "step": 1682432 + }, + { + "epoch": 0.0, + "learning_rate": 2.244790393897127e-05, + "loss": 3.4526, + "step": 1682944 + }, + { + "epoch": 0.0, + "learning_rate": 2.243953437026448e-05, + "loss": 3.4552, + "step": 1683456 + }, + { + "epoch": 0.0, + "learning_rate": 2.243114842275396e-05, + "loss": 3.4576, + "step": 1683968 + }, + { + "epoch": 0.0, + "learning_rate": 2.242276247524344e-05, + "loss": 3.4563, + "step": 1684480 + }, + { + "epoch": 0.0, + "learning_rate": 2.2414376527732918e-05, + "loss": 3.4541, + "step": 1684992 + }, + { + "epoch": 0.0, + "learning_rate": 2.240600695902613e-05, + "loss": 3.4508, + "step": 1685504 + }, + { + "epoch": 0.0, + "learning_rate": 2.239762101151561e-05, + "loss": 3.4486, + "step": 1686016 + }, + { + "epoch": 0.0, + "learning_rate": 2.238923506400509e-05, + "loss": 3.4535, + "step": 1686528 + }, + { + "epoch": 0.0, + "learning_rate": 2.238084911649457e-05, + "loss": 3.4458, + "step": 1687040 + }, + { + "epoch": 0.0, + "learning_rate": 2.237247954778778e-05, + "loss": 3.4513, + "step": 1687552 + }, + { + "epoch": 0.0, + "learning_rate": 2.236409360027726e-05, + "loss": 3.4462, + "step": 1688064 + }, + { + "epoch": 0.0, + "learning_rate": 2.2355707652766743e-05, + "loss": 3.4505, + "step": 1688576 + }, + { + "epoch": 0.0, + "learning_rate": 2.2347321705256223e-05, + "loss": 3.4643, + "step": 1689088 + }, + { + "epoch": 0.0, + "learning_rate": 2.2338952136549432e-05, + "loss": 3.4557, + "step": 1689600 + }, + { + "epoch": 0.0, + "learning_rate": 2.2330566189038912e-05, + "loss": 3.4624, + "step": 1690112 + }, + { + "epoch": 0.0, + "learning_rate": 2.2322180241528392e-05, + "loss": 3.4554, + "step": 1690624 + }, + { + "epoch": 0.0, + "learning_rate": 2.2313794294017872e-05, + "loss": 3.4605, + "step": 1691136 + }, + { + "epoch": 0.0, + "learning_rate": 2.2305424725311084e-05, + "loss": 3.4432, + "step": 1691648 + }, + { + "epoch": 0.0, + "learning_rate": 2.2297038777800564e-05, + "loss": 3.4623, + "step": 1692160 + }, + { + "epoch": 0.0, + "learning_rate": 2.2288652830290044e-05, + "loss": 3.4503, + "step": 1692672 + }, + { + "epoch": 0.0, + "learning_rate": 2.2280283261583253e-05, + "loss": 3.4444, + "step": 1693184 + }, + { + "epoch": 0.0, + "learning_rate": 2.2271897314072733e-05, + "loss": 3.4433, + "step": 1693696 + }, + { + "epoch": 0.0, + "learning_rate": 2.2263527745365946e-05, + "loss": 3.448, + "step": 1694208 + }, + { + "epoch": 0.01, + "learning_rate": 2.2255141797855426e-05, + "loss": 3.4526, + "step": 1694720 + }, + { + "epoch": 0.01, + "learning_rate": 2.2246755850344906e-05, + "loss": 3.459, + "step": 1695232 + }, + { + "epoch": 0.01, + "learning_rate": 2.2238369902834386e-05, + "loss": 3.4574, + "step": 1695744 + }, + { + "epoch": 0.01, + "learning_rate": 2.2229983955323866e-05, + "loss": 3.4571, + "step": 1696256 + }, + { + "epoch": 0.01, + "learning_rate": 2.2221598007813346e-05, + "loss": 3.4406, + "step": 1696768 + }, + { + "epoch": 0.01, + "learning_rate": 2.2213212060302826e-05, + "loss": 3.453, + "step": 1697280 + }, + { + "epoch": 0.01, + "learning_rate": 2.2204826112792306e-05, + "loss": 3.4527, + "step": 1697792 + }, + { + "epoch": 0.01, + "learning_rate": 2.2196456544085518e-05, + "loss": 3.4484, + "step": 1698304 + }, + { + "epoch": 0.01, + "learning_rate": 2.2188070596574998e-05, + "loss": 3.4433, + "step": 1698816 + }, + { + "epoch": 0.01, + "learning_rate": 2.2179684649064478e-05, + "loss": 3.4421, + "step": 1699328 + }, + { + "epoch": 0.01, + "learning_rate": 2.2171298701553955e-05, + "loss": 3.4509, + "step": 1699840 + }, + { + "epoch": 0.01, + "learning_rate": 2.2162929132847167e-05, + "loss": 3.4599, + "step": 1700352 + }, + { + "epoch": 0.01, + "learning_rate": 2.2154543185336647e-05, + "loss": 3.4552, + "step": 1700864 + }, + { + "epoch": 0.01, + "learning_rate": 2.214615723782613e-05, + "loss": 3.4485, + "step": 1701376 + }, + { + "epoch": 0.01, + "learning_rate": 2.2137771290315607e-05, + "loss": 3.4551, + "step": 1701888 + }, + { + "epoch": 0.01, + "learning_rate": 2.212940172160882e-05, + "loss": 3.4453, + "step": 1702400 + }, + { + "epoch": 0.01, + "learning_rate": 2.21210157740983e-05, + "loss": 3.4578, + "step": 1702912 + }, + { + "epoch": 0.01, + "learning_rate": 2.2112629826587776e-05, + "loss": 3.441, + "step": 1703424 + }, + { + "epoch": 0.01, + "learning_rate": 2.210424387907726e-05, + "loss": 3.4322, + "step": 1703936 + }, + { + "epoch": 0.01, + "learning_rate": 2.2095874310370472e-05, + "loss": 3.454, + "step": 1704448 + }, + { + "epoch": 0.01, + "learning_rate": 2.208748836285995e-05, + "loss": 3.4498, + "step": 1704960 + }, + { + "epoch": 0.01, + "learning_rate": 2.2079102415349428e-05, + "loss": 3.4521, + "step": 1705472 + }, + { + "epoch": 0.01, + "learning_rate": 2.2070716467838908e-05, + "loss": 3.4453, + "step": 1705984 + }, + { + "epoch": 0.01, + "learning_rate": 2.206234689913212e-05, + "loss": 3.4419, + "step": 1706496 + }, + { + "epoch": 0.01, + "learning_rate": 2.20539609516216e-05, + "loss": 3.4382, + "step": 1707008 + }, + { + "epoch": 0.01, + "learning_rate": 2.204557500411108e-05, + "loss": 3.4421, + "step": 1707520 + }, + { + "epoch": 0.01, + "learning_rate": 2.203718905660056e-05, + "loss": 3.4406, + "step": 1708032 + }, + { + "epoch": 0.01, + "learning_rate": 2.2028819487893773e-05, + "loss": 3.4496, + "step": 1708544 + }, + { + "epoch": 0.01, + "learning_rate": 2.202043354038325e-05, + "loss": 3.4471, + "step": 1709056 + }, + { + "epoch": 0.01, + "learning_rate": 2.201204759287273e-05, + "loss": 3.4463, + "step": 1709568 + }, + { + "epoch": 0.01, + "learning_rate": 2.2003661645362213e-05, + "loss": 3.4459, + "step": 1710080 + }, + { + "epoch": 0.01, + "learning_rate": 2.1995292076655425e-05, + "loss": 3.4624, + "step": 1710592 + }, + { + "epoch": 0.01, + "learning_rate": 2.1986906129144902e-05, + "loss": 3.4312, + "step": 1711104 + }, + { + "epoch": 0.01, + "learning_rate": 2.1978520181634382e-05, + "loss": 3.4362, + "step": 1711616 + }, + { + "epoch": 0.01, + "learning_rate": 2.1970134234123862e-05, + "loss": 3.4476, + "step": 1712128 + }, + { + "epoch": 0.01, + "learning_rate": 2.1961764665417074e-05, + "loss": 3.4511, + "step": 1712640 + }, + { + "epoch": 0.01, + "learning_rate": 2.1953378717906554e-05, + "loss": 3.4375, + "step": 1713152 + }, + { + "epoch": 0.01, + "learning_rate": 2.1944992770396034e-05, + "loss": 3.4381, + "step": 1713664 + }, + { + "epoch": 0.01, + "learning_rate": 2.1936606822885514e-05, + "loss": 3.439, + "step": 1714176 + }, + { + "epoch": 0.01, + "learning_rate": 2.1928237254178723e-05, + "loss": 3.4408, + "step": 1714688 + }, + { + "epoch": 0.01, + "learning_rate": 2.1919851306668203e-05, + "loss": 3.4547, + "step": 1715200 + }, + { + "epoch": 0.01, + "learning_rate": 2.1911465359157683e-05, + "loss": 3.4478, + "step": 1715712 + }, + { + "epoch": 0.01, + "learning_rate": 2.19030957904509e-05, + "loss": 3.453, + "step": 1716224 + }, + { + "epoch": 0.01, + "learning_rate": 2.1894709842940376e-05, + "loss": 3.4558, + "step": 1716736 + }, + { + "epoch": 0.01, + "learning_rate": 2.1886323895429856e-05, + "loss": 3.4685, + "step": 1717248 + }, + { + "epoch": 0.01, + "learning_rate": 2.1877937947919336e-05, + "loss": 3.4409, + "step": 1717760 + }, + { + "epoch": 0.01, + "learning_rate": 2.1869568379212545e-05, + "loss": 3.4499, + "step": 1718272 + }, + { + "epoch": 0.01, + "learning_rate": 2.1861182431702028e-05, + "loss": 3.4542, + "step": 1718784 + }, + { + "epoch": 0.01, + "learning_rate": 2.1852796484191508e-05, + "loss": 3.435, + "step": 1719296 + }, + { + "epoch": 0.01, + "learning_rate": 2.1844410536680988e-05, + "loss": 3.4544, + "step": 1719808 + }, + { + "epoch": 0.01, + "learning_rate": 2.1836040967974197e-05, + "loss": 3.4527, + "step": 1720320 + }, + { + "epoch": 0.01, + "learning_rate": 2.1827655020463677e-05, + "loss": 3.4514, + "step": 1720832 + }, + { + "epoch": 0.01, + "learning_rate": 2.1819269072953157e-05, + "loss": 3.4491, + "step": 1721344 + }, + { + "epoch": 0.01, + "learning_rate": 2.1810883125442637e-05, + "loss": 3.434, + "step": 1721856 + }, + { + "epoch": 0.01, + "learning_rate": 2.180251355673585e-05, + "loss": 3.4401, + "step": 1722368 + }, + { + "epoch": 0.01, + "learning_rate": 2.179412760922533e-05, + "loss": 3.4417, + "step": 1722880 + }, + { + "epoch": 0.01, + "learning_rate": 2.178574166171481e-05, + "loss": 3.4497, + "step": 1723392 + }, + { + "epoch": 0.01, + "learning_rate": 2.177735571420429e-05, + "loss": 3.4563, + "step": 1723904 + }, + { + "epoch": 0.01, + "learning_rate": 2.17689861454975e-05, + "loss": 3.4391, + "step": 1724416 + }, + { + "epoch": 0.02, + "learning_rate": 2.176060019798698e-05, + "loss": 3.4446, + "step": 1724928 + }, + { + "epoch": 0.02, + "learning_rate": 2.175221425047646e-05, + "loss": 3.4368, + "step": 1725440 + }, + { + "epoch": 0.02, + "learning_rate": 2.174382830296594e-05, + "loss": 3.4368, + "step": 1725952 + }, + { + "epoch": 0.02, + "learning_rate": 2.173545873425915e-05, + "loss": 3.4455, + "step": 1726464 + }, + { + "epoch": 0.02, + "learning_rate": 2.172707278674863e-05, + "loss": 3.4497, + "step": 1726976 + }, + { + "epoch": 0.02, + "learning_rate": 2.171868683923811e-05, + "loss": 3.4567, + "step": 1727488 + }, + { + "epoch": 0.02, + "learning_rate": 2.171030089172759e-05, + "loss": 3.4452, + "step": 1728000 + }, + { + "epoch": 0.02, + "learning_rate": 2.1701931323020803e-05, + "loss": 3.4393, + "step": 1728512 + }, + { + "epoch": 0.02, + "learning_rate": 2.1693545375510283e-05, + "loss": 3.4506, + "step": 1729024 + }, + { + "epoch": 0.02, + "learning_rate": 2.1685159427999763e-05, + "loss": 3.4444, + "step": 1729536 + }, + { + "epoch": 0.02, + "learning_rate": 2.1676773480489243e-05, + "loss": 3.4528, + "step": 1730048 + }, + { + "epoch": 0.02, + "learning_rate": 2.1668403911782452e-05, + "loss": 3.4404, + "step": 1730560 + }, + { + "epoch": 0.02, + "learning_rate": 2.1660017964271932e-05, + "loss": 3.4397, + "step": 1731072 + }, + { + "epoch": 0.02, + "learning_rate": 2.1651632016761415e-05, + "loss": 3.4441, + "step": 1731584 + }, + { + "epoch": 0.02, + "learning_rate": 2.1643246069250895e-05, + "loss": 3.4554, + "step": 1732096 + }, + { + "epoch": 0.02, + "learning_rate": 2.1634876500544104e-05, + "loss": 3.432, + "step": 1732608 + }, + { + "epoch": 0.02, + "learning_rate": 2.1626490553033584e-05, + "loss": 3.4458, + "step": 1733120 + }, + { + "epoch": 0.02, + "learning_rate": 2.1618104605523064e-05, + "loss": 3.4467, + "step": 1733632 + }, + { + "epoch": 0.02, + "learning_rate": 2.1609718658012544e-05, + "loss": 3.4555, + "step": 1734144 + }, + { + "epoch": 0.02, + "learning_rate": 2.1601349089305757e-05, + "loss": 3.4293, + "step": 1734656 + }, + { + "epoch": 0.02, + "learning_rate": 2.1592963141795237e-05, + "loss": 3.446, + "step": 1735168 + }, + { + "epoch": 0.02, + "learning_rate": 2.1584577194284717e-05, + "loss": 3.4427, + "step": 1735680 + }, + { + "epoch": 0.02, + "learning_rate": 2.1576191246774197e-05, + "loss": 3.4457, + "step": 1736192 + }, + { + "epoch": 0.02, + "learning_rate": 2.1567821678067406e-05, + "loss": 3.4473, + "step": 1736704 + }, + { + "epoch": 0.02, + "learning_rate": 2.1559435730556886e-05, + "loss": 3.441, + "step": 1737216 + }, + { + "epoch": 0.02, + "learning_rate": 2.155104978304637e-05, + "loss": 3.4462, + "step": 1737728 + }, + { + "epoch": 0.02, + "learning_rate": 2.154266383553585e-05, + "loss": 3.4618, + "step": 1738240 + }, + { + "epoch": 0.02, + "learning_rate": 2.1534294266829058e-05, + "loss": 3.4482, + "step": 1738752 + }, + { + "epoch": 0.02, + "learning_rate": 2.1525908319318538e-05, + "loss": 3.4451, + "step": 1739264 + }, + { + "epoch": 0.02, + "learning_rate": 2.1517522371808018e-05, + "loss": 3.454, + "step": 1739776 + }, + { + "epoch": 0.02, + "learning_rate": 2.1509136424297498e-05, + "loss": 3.4475, + "step": 1740288 + }, + { + "epoch": 0.02, + "learning_rate": 2.150076685559071e-05, + "loss": 3.4355, + "step": 1740800 + }, + { + "epoch": 0.02, + "learning_rate": 2.149238090808019e-05, + "loss": 3.4485, + "step": 1741312 + }, + { + "epoch": 0.02, + "learning_rate": 2.148399496056967e-05, + "loss": 3.4423, + "step": 1741824 + }, + { + "epoch": 0.02, + "learning_rate": 2.1475609013059147e-05, + "loss": 3.4432, + "step": 1742336 + }, + { + "epoch": 0.02, + "learning_rate": 2.146723944435236e-05, + "loss": 3.4429, + "step": 1742848 + }, + { + "epoch": 0.02, + "learning_rate": 2.145885349684184e-05, + "loss": 3.4453, + "step": 1743360 + }, + { + "epoch": 0.02, + "learning_rate": 2.1450467549331323e-05, + "loss": 3.4431, + "step": 1743872 + }, + { + "epoch": 0.02, + "learning_rate": 2.14420816018208e-05, + "loss": 3.4376, + "step": 1744384 + }, + { + "epoch": 0.02, + "learning_rate": 2.1433712033114012e-05, + "loss": 3.4415, + "step": 1744896 + }, + { + "epoch": 0.02, + "learning_rate": 2.142532608560349e-05, + "loss": 3.4527, + "step": 1745408 + }, + { + "epoch": 0.02, + "learning_rate": 2.141694013809297e-05, + "loss": 3.4473, + "step": 1745920 + }, + { + "epoch": 0.02, + "learning_rate": 2.140855419058245e-05, + "loss": 3.4568, + "step": 1746432 + }, + { + "epoch": 0.02, + "learning_rate": 2.1400184621875664e-05, + "loss": 3.4321, + "step": 1746944 + }, + { + "epoch": 0.02, + "learning_rate": 2.1391798674365144e-05, + "loss": 3.4592, + "step": 1747456 + }, + { + "epoch": 0.02, + "learning_rate": 2.138341272685462e-05, + "loss": 3.447, + "step": 1747968 + }, + { + "epoch": 0.02, + "learning_rate": 2.13750267793441e-05, + "loss": 3.4501, + "step": 1748480 + }, + { + "epoch": 0.02, + "learning_rate": 2.1366657210637313e-05, + "loss": 3.4421, + "step": 1748992 + }, + { + "epoch": 0.02, + "learning_rate": 2.1358271263126793e-05, + "loss": 3.4513, + "step": 1749504 + }, + { + "epoch": 0.02, + "learning_rate": 2.1349885315616273e-05, + "loss": 3.4391, + "step": 1750016 + }, + { + "epoch": 0.02, + "learning_rate": 2.1341499368105753e-05, + "loss": 3.4623, + "step": 1750528 + }, + { + "epoch": 0.02, + "learning_rate": 2.1333129799398965e-05, + "loss": 3.4314, + "step": 1751040 + }, + { + "epoch": 0.02, + "learning_rate": 2.1324743851888445e-05, + "loss": 3.4503, + "step": 1751552 + }, + { + "epoch": 0.02, + "learning_rate": 2.1316357904377922e-05, + "loss": 3.4398, + "step": 1752064 + }, + { + "epoch": 0.02, + "learning_rate": 2.1307971956867405e-05, + "loss": 3.4444, + "step": 1752576 + }, + { + "epoch": 0.02, + "learning_rate": 2.1299602388160618e-05, + "loss": 3.4436, + "step": 1753088 + }, + { + "epoch": 0.02, + "learning_rate": 2.1291216440650094e-05, + "loss": 3.4429, + "step": 1753600 + }, + { + "epoch": 0.02, + "learning_rate": 2.1282830493139574e-05, + "loss": 3.459, + "step": 1754112 + }, + { + "epoch": 0.02, + "learning_rate": 2.1274444545629054e-05, + "loss": 3.4327, + "step": 1754624 + }, + { + "epoch": 0.02, + "learning_rate": 2.1266074976922267e-05, + "loss": 3.4498, + "step": 1755136 + }, + { + "epoch": 0.03, + "eval_loss": 3.853148937225342, + "eval_runtime": 304.4333, + "eval_samples_per_second": 1253.447, + "eval_steps_per_second": 39.171, + "step": 1755360 + }, + { + "epoch": 1.0, + "learning_rate": 2.1257689029411747e-05, + "loss": 3.4441, + "step": 1755648 + }, + { + "epoch": 1.0, + "learning_rate": 2.1249303081901227e-05, + "loss": 3.4391, + "step": 1756160 + }, + { + "epoch": 1.0, + "learning_rate": 2.124093351319444e-05, + "loss": 3.447, + "step": 1756672 + }, + { + "epoch": 1.0, + "learning_rate": 2.123254756568392e-05, + "loss": 3.4445, + "step": 1757184 + }, + { + "epoch": 1.0, + "learning_rate": 2.1224161618173396e-05, + "loss": 3.4513, + "step": 1757696 + }, + { + "epoch": 1.0, + "learning_rate": 2.1215775670662876e-05, + "loss": 3.4403, + "step": 1758208 + }, + { + "epoch": 1.0, + "learning_rate": 2.120740610195609e-05, + "loss": 3.441, + "step": 1758720 + }, + { + "epoch": 1.0, + "learning_rate": 2.1199020154445568e-05, + "loss": 3.439, + "step": 1759232 + }, + { + "epoch": 1.0, + "learning_rate": 2.1190634206935048e-05, + "loss": 3.4467, + "step": 1759744 + }, + { + "epoch": 1.0, + "learning_rate": 2.1182248259424528e-05, + "loss": 3.4477, + "step": 1760256 + }, + { + "epoch": 1.0, + "learning_rate": 2.117387869071774e-05, + "loss": 3.4472, + "step": 1760768 + }, + { + "epoch": 1.0, + "learning_rate": 2.1165492743207217e-05, + "loss": 3.4412, + "step": 1761280 + }, + { + "epoch": 1.0, + "learning_rate": 2.11571067956967e-05, + "loss": 3.4394, + "step": 1761792 + }, + { + "epoch": 1.0, + "learning_rate": 2.114872084818618e-05, + "loss": 3.4373, + "step": 1762304 + }, + { + "epoch": 1.0, + "learning_rate": 2.114035127947939e-05, + "loss": 3.4436, + "step": 1762816 + }, + { + "epoch": 1.0, + "learning_rate": 2.113196533196887e-05, + "loss": 3.4326, + "step": 1763328 + }, + { + "epoch": 1.0, + "learning_rate": 2.112357938445835e-05, + "loss": 3.441, + "step": 1763840 + }, + { + "epoch": 1.0, + "learning_rate": 2.111519343694783e-05, + "loss": 3.4359, + "step": 1764352 + }, + { + "epoch": 1.0, + "learning_rate": 2.1106823868241042e-05, + "loss": 3.4381, + "step": 1764864 + }, + { + "epoch": 1.0, + "learning_rate": 2.109843792073052e-05, + "loss": 3.45, + "step": 1765376 + }, + { + "epoch": 1.0, + "learning_rate": 2.109005197322e-05, + "loss": 3.4489, + "step": 1765888 + }, + { + "epoch": 1.0, + "learning_rate": 2.108166602570948e-05, + "loss": 3.45, + "step": 1766400 + }, + { + "epoch": 1.0, + "learning_rate": 2.107329645700269e-05, + "loss": 3.444, + "step": 1766912 + }, + { + "epoch": 1.0, + "learning_rate": 2.106491050949217e-05, + "loss": 3.4457, + "step": 1767424 + }, + { + "epoch": 1.0, + "learning_rate": 2.1056524561981654e-05, + "loss": 3.4322, + "step": 1767936 + }, + { + "epoch": 1.0, + "learning_rate": 2.1048138614471134e-05, + "loss": 3.4537, + "step": 1768448 + }, + { + "epoch": 1.0, + "learning_rate": 2.1039769045764343e-05, + "loss": 3.4385, + "step": 1768960 + }, + { + "epoch": 1.0, + "learning_rate": 2.1031383098253823e-05, + "loss": 3.4348, + "step": 1769472 + }, + { + "epoch": 1.0, + "learning_rate": 2.1022997150743303e-05, + "loss": 3.4342, + "step": 1769984 + }, + { + "epoch": 1.0, + "learning_rate": 2.1014611203232783e-05, + "loss": 3.438, + "step": 1770496 + }, + { + "epoch": 1.01, + "learning_rate": 2.1006241634525995e-05, + "loss": 3.441, + "step": 1771008 + }, + { + "epoch": 1.01, + "learning_rate": 2.0997855687015475e-05, + "loss": 3.4503, + "step": 1771520 + }, + { + "epoch": 1.01, + "learning_rate": 2.0989469739504955e-05, + "loss": 3.4489, + "step": 1772032 + }, + { + "epoch": 1.01, + "learning_rate": 2.0981083791994435e-05, + "loss": 3.4418, + "step": 1772544 + }, + { + "epoch": 1.01, + "learning_rate": 2.0972714223287644e-05, + "loss": 3.4305, + "step": 1773056 + }, + { + "epoch": 1.01, + "learning_rate": 2.0964328275777124e-05, + "loss": 3.4455, + "step": 1773568 + }, + { + "epoch": 1.01, + "learning_rate": 2.0955942328266608e-05, + "loss": 3.4433, + "step": 1774080 + }, + { + "epoch": 1.01, + "learning_rate": 2.0947556380756088e-05, + "loss": 3.4347, + "step": 1774592 + }, + { + "epoch": 1.01, + "learning_rate": 2.0939186812049297e-05, + "loss": 3.4333, + "step": 1775104 + }, + { + "epoch": 1.01, + "learning_rate": 2.0930800864538777e-05, + "loss": 3.43, + "step": 1775616 + }, + { + "epoch": 1.01, + "learning_rate": 2.0922414917028257e-05, + "loss": 3.4364, + "step": 1776128 + }, + { + "epoch": 1.01, + "learning_rate": 2.0914028969517737e-05, + "loss": 3.4513, + "step": 1776640 + }, + { + "epoch": 1.01, + "learning_rate": 2.090565940081095e-05, + "loss": 3.4426, + "step": 1777152 + }, + { + "epoch": 1.01, + "learning_rate": 2.089727345330043e-05, + "loss": 3.4356, + "step": 1777664 + }, + { + "epoch": 1.01, + "learning_rate": 2.088888750578991e-05, + "loss": 3.4446, + "step": 1778176 + }, + { + "epoch": 1.01, + "learning_rate": 2.088050155827939e-05, + "loss": 3.435, + "step": 1778688 + }, + { + "epoch": 1.01, + "learning_rate": 2.0872131989572598e-05, + "loss": 3.4457, + "step": 1779200 + }, + { + "epoch": 1.01, + "learning_rate": 2.0863746042062078e-05, + "loss": 3.4341, + "step": 1779712 + }, + { + "epoch": 1.01, + "learning_rate": 2.085536009455156e-05, + "loss": 3.42, + "step": 1780224 + }, + { + "epoch": 1.01, + "learning_rate": 2.084697414704104e-05, + "loss": 3.4452, + "step": 1780736 + }, + { + "epoch": 1.01, + "learning_rate": 2.083860457833425e-05, + "loss": 3.4368, + "step": 1781248 + }, + { + "epoch": 1.01, + "learning_rate": 2.083021863082373e-05, + "loss": 3.443, + "step": 1781760 + }, + { + "epoch": 1.01, + "learning_rate": 2.082183268331321e-05, + "loss": 3.4332, + "step": 1782272 + }, + { + "epoch": 1.01, + "learning_rate": 2.081344673580269e-05, + "loss": 3.4315, + "step": 1782784 + }, + { + "epoch": 1.01, + "learning_rate": 2.0805077167095903e-05, + "loss": 3.4278, + "step": 1783296 + }, + { + "epoch": 1.01, + "learning_rate": 2.0796691219585383e-05, + "loss": 3.4285, + "step": 1783808 + }, + { + "epoch": 1.01, + "learning_rate": 2.0788305272074863e-05, + "loss": 3.4334, + "step": 1784320 + }, + { + "epoch": 1.01, + "learning_rate": 2.0779919324564343e-05, + "loss": 3.4347, + "step": 1784832 + }, + { + "epoch": 1.01, + "learning_rate": 2.077154975585755e-05, + "loss": 3.4409, + "step": 1785344 + }, + { + "epoch": 1.01, + "learning_rate": 2.076316380834703e-05, + "loss": 3.4283, + "step": 1785856 + }, + { + "epoch": 1.01, + "learning_rate": 2.0754777860836515e-05, + "loss": 3.4383, + "step": 1786368 + }, + { + "epoch": 1.01, + "learning_rate": 2.074639191332599e-05, + "loss": 3.4472, + "step": 1786880 + }, + { + "epoch": 1.01, + "learning_rate": 2.0738022344619204e-05, + "loss": 3.422, + "step": 1787392 + }, + { + "epoch": 1.01, + "learning_rate": 2.0729636397108684e-05, + "loss": 3.4261, + "step": 1787904 + }, + { + "epoch": 1.01, + "learning_rate": 2.0721250449598164e-05, + "loss": 3.4404, + "step": 1788416 + }, + { + "epoch": 1.01, + "learning_rate": 2.071286450208764e-05, + "loss": 3.4377, + "step": 1788928 + }, + { + "epoch": 1.01, + "learning_rate": 2.0704494933380856e-05, + "loss": 3.4266, + "step": 1789440 + }, + { + "epoch": 1.01, + "learning_rate": 2.0696108985870336e-05, + "loss": 3.4302, + "step": 1789952 + }, + { + "epoch": 1.01, + "learning_rate": 2.0687723038359816e-05, + "loss": 3.4277, + "step": 1790464 + }, + { + "epoch": 1.01, + "learning_rate": 2.0679337090849293e-05, + "loss": 3.4337, + "step": 1790976 + }, + { + "epoch": 1.01, + "learning_rate": 2.0670967522142505e-05, + "loss": 3.4396, + "step": 1791488 + }, + { + "epoch": 1.01, + "learning_rate": 2.0662581574631985e-05, + "loss": 3.4382, + "step": 1792000 + }, + { + "epoch": 1.01, + "learning_rate": 2.0654195627121465e-05, + "loss": 3.4398, + "step": 1792512 + }, + { + "epoch": 1.01, + "learning_rate": 2.0645809679610945e-05, + "loss": 3.4465, + "step": 1793024 + }, + { + "epoch": 1.01, + "learning_rate": 2.0637440110904158e-05, + "loss": 3.4559, + "step": 1793536 + }, + { + "epoch": 1.01, + "learning_rate": 2.0629054163393638e-05, + "loss": 3.431, + "step": 1794048 + }, + { + "epoch": 1.01, + "learning_rate": 2.0620668215883114e-05, + "loss": 3.437, + "step": 1794560 + }, + { + "epoch": 1.01, + "learning_rate": 2.061229864717633e-05, + "loss": 3.4437, + "step": 1795072 + }, + { + "epoch": 1.01, + "learning_rate": 2.060391269966581e-05, + "loss": 3.4255, + "step": 1795584 + }, + { + "epoch": 1.01, + "learning_rate": 2.059552675215529e-05, + "loss": 3.4405, + "step": 1796096 + }, + { + "epoch": 1.01, + "learning_rate": 2.0587140804644767e-05, + "loss": 3.4423, + "step": 1796608 + }, + { + "epoch": 1.01, + "learning_rate": 2.057877123593798e-05, + "loss": 3.4395, + "step": 1797120 + }, + { + "epoch": 1.01, + "learning_rate": 2.057038528842746e-05, + "loss": 3.4424, + "step": 1797632 + }, + { + "epoch": 1.01, + "learning_rate": 2.056199934091694e-05, + "loss": 3.4242, + "step": 1798144 + }, + { + "epoch": 1.01, + "learning_rate": 2.055361339340642e-05, + "loss": 3.4256, + "step": 1798656 + }, + { + "epoch": 1.01, + "learning_rate": 2.054524382469963e-05, + "loss": 3.4319, + "step": 1799168 + }, + { + "epoch": 1.01, + "learning_rate": 2.053685787718911e-05, + "loss": 3.4375, + "step": 1799680 + }, + { + "epoch": 1.01, + "learning_rate": 2.0528471929678588e-05, + "loss": 3.4429, + "step": 1800192 + }, + { + "epoch": 1.01, + "learning_rate": 2.0520085982168068e-05, + "loss": 3.4318, + "step": 1800704 + }, + { + "epoch": 1.02, + "learning_rate": 2.0511716413461284e-05, + "loss": 3.4335, + "step": 1801216 + }, + { + "epoch": 1.02, + "learning_rate": 2.050333046595076e-05, + "loss": 3.4293, + "step": 1801728 + }, + { + "epoch": 1.02, + "learning_rate": 2.049494451844024e-05, + "loss": 3.4242, + "step": 1802240 + }, + { + "epoch": 1.02, + "learning_rate": 2.048655857092972e-05, + "loss": 3.4352, + "step": 1802752 + }, + { + "epoch": 1.02, + "learning_rate": 2.0478189002222933e-05, + "loss": 3.4394, + "step": 1803264 + }, + { + "epoch": 1.02, + "learning_rate": 2.046980305471241e-05, + "loss": 3.446, + "step": 1803776 + }, + { + "epoch": 1.02, + "learning_rate": 2.0461417107201893e-05, + "loss": 3.4386, + "step": 1804288 + }, + { + "epoch": 1.02, + "learning_rate": 2.0453031159691373e-05, + "loss": 3.4271, + "step": 1804800 + }, + { + "epoch": 1.02, + "learning_rate": 2.0444661590984585e-05, + "loss": 3.4419, + "step": 1805312 + }, + { + "epoch": 1.02, + "learning_rate": 2.043627564347406e-05, + "loss": 3.435, + "step": 1805824 + }, + { + "epoch": 1.02, + "learning_rate": 2.042788969596354e-05, + "loss": 3.4385, + "step": 1806336 + }, + { + "epoch": 1.02, + "learning_rate": 2.041950374845302e-05, + "loss": 3.4312, + "step": 1806848 + }, + { + "epoch": 1.02, + "learning_rate": 2.0411134179746234e-05, + "loss": 3.43, + "step": 1807360 + }, + { + "epoch": 1.02, + "learning_rate": 2.0402748232235714e-05, + "loss": 3.4311, + "step": 1807872 + }, + { + "epoch": 1.02, + "learning_rate": 2.0394362284725194e-05, + "loss": 3.4447, + "step": 1808384 + }, + { + "epoch": 1.02, + "learning_rate": 2.0385976337214674e-05, + "loss": 3.4225, + "step": 1808896 + }, + { + "epoch": 1.02, + "learning_rate": 2.0377606768507883e-05, + "loss": 3.4333, + "step": 1809408 + }, + { + "epoch": 1.02, + "learning_rate": 2.0369220820997363e-05, + "loss": 3.4316, + "step": 1809920 + }, + { + "epoch": 1.02, + "learning_rate": 2.0360834873486846e-05, + "loss": 3.4428, + "step": 1810432 + }, + { + "epoch": 1.02, + "learning_rate": 2.0352448925976326e-05, + "loss": 3.4258, + "step": 1810944 + }, + { + "epoch": 1.02, + "learning_rate": 2.0344079357269535e-05, + "loss": 3.4359, + "step": 1811456 + }, + { + "epoch": 1.02, + "learning_rate": 2.0335693409759015e-05, + "loss": 3.4288, + "step": 1811968 + }, + { + "epoch": 1.02, + "learning_rate": 2.0327307462248495e-05, + "loss": 3.4382, + "step": 1812480 + }, + { + "epoch": 1.02, + "learning_rate": 2.0318921514737975e-05, + "loss": 3.4402, + "step": 1812992 + }, + { + "epoch": 1.02, + "learning_rate": 2.0310551946031188e-05, + "loss": 3.4266, + "step": 1813504 + }, + { + "epoch": 1.02, + "learning_rate": 2.0302165998520668e-05, + "loss": 3.4362, + "step": 1814016 + }, + { + "epoch": 1.02, + "learning_rate": 2.0293780051010148e-05, + "loss": 3.4479, + "step": 1814528 + }, + { + "epoch": 1.02, + "learning_rate": 2.0285394103499628e-05, + "loss": 3.438, + "step": 1815040 + }, + { + "epoch": 1.02, + "learning_rate": 2.0277024534792837e-05, + "loss": 3.4319, + "step": 1815552 + }, + { + "epoch": 1.02, + "learning_rate": 2.0268638587282317e-05, + "loss": 3.4395, + "step": 1816064 + }, + { + "epoch": 1.02, + "learning_rate": 2.02602526397718e-05, + "loss": 3.4402, + "step": 1816576 + }, + { + "epoch": 1.02, + "learning_rate": 2.025186669226128e-05, + "loss": 3.4288, + "step": 1817088 + }, + { + "epoch": 1.02, + "learning_rate": 2.024349712355449e-05, + "loss": 3.4354, + "step": 1817600 + }, + { + "epoch": 1.02, + "learning_rate": 2.023511117604397e-05, + "loss": 3.4274, + "step": 1818112 + }, + { + "epoch": 1.02, + "learning_rate": 2.022672522853345e-05, + "loss": 3.436, + "step": 1818624 + }, + { + "epoch": 1.02, + "learning_rate": 2.021833928102293e-05, + "loss": 3.4284, + "step": 1819136 + }, + { + "epoch": 1.02, + "learning_rate": 2.020996971231614e-05, + "loss": 3.4353, + "step": 1819648 + }, + { + "epoch": 1.02, + "learning_rate": 2.020158376480562e-05, + "loss": 3.4317, + "step": 1820160 + }, + { + "epoch": 1.02, + "learning_rate": 2.01931978172951e-05, + "loss": 3.4288, + "step": 1820672 + }, + { + "epoch": 1.02, + "learning_rate": 2.018481186978458e-05, + "loss": 3.4281, + "step": 1821184 + }, + { + "epoch": 1.02, + "learning_rate": 2.017644230107779e-05, + "loss": 3.4446, + "step": 1821696 + }, + { + "epoch": 1.02, + "learning_rate": 2.016805635356727e-05, + "loss": 3.4407, + "step": 1822208 + }, + { + "epoch": 1.02, + "learning_rate": 2.0159670406056754e-05, + "loss": 3.4445, + "step": 1822720 + }, + { + "epoch": 1.02, + "learning_rate": 2.0151284458546234e-05, + "loss": 3.4228, + "step": 1823232 + }, + { + "epoch": 1.02, + "learning_rate": 2.0142914889839443e-05, + "loss": 3.4506, + "step": 1823744 + }, + { + "epoch": 1.02, + "learning_rate": 2.0134528942328923e-05, + "loss": 3.4333, + "step": 1824256 + }, + { + "epoch": 1.02, + "learning_rate": 2.0126142994818403e-05, + "loss": 3.4371, + "step": 1824768 + }, + { + "epoch": 1.02, + "learning_rate": 2.0117757047307883e-05, + "loss": 3.4354, + "step": 1825280 + }, + { + "epoch": 1.02, + "learning_rate": 2.0109387478601095e-05, + "loss": 3.4342, + "step": 1825792 + }, + { + "epoch": 1.02, + "learning_rate": 2.0101001531090575e-05, + "loss": 3.4294, + "step": 1826304 + }, + { + "epoch": 1.02, + "learning_rate": 2.0092615583580055e-05, + "loss": 3.45, + "step": 1826816 + }, + { + "epoch": 1.02, + "learning_rate": 2.0084229636069535e-05, + "loss": 3.4264, + "step": 1827328 + }, + { + "epoch": 1.02, + "learning_rate": 2.0075860067362744e-05, + "loss": 3.4408, + "step": 1827840 + }, + { + "epoch": 1.02, + "learning_rate": 2.0067474119852224e-05, + "loss": 3.4296, + "step": 1828352 + }, + { + "epoch": 1.02, + "learning_rate": 2.0059088172341707e-05, + "loss": 3.4347, + "step": 1828864 + }, + { + "epoch": 1.02, + "learning_rate": 2.0050718603634916e-05, + "loss": 3.4295, + "step": 1829376 + }, + { + "epoch": 1.02, + "learning_rate": 2.0042332656124396e-05, + "loss": 3.4338, + "step": 1829888 + }, + { + "epoch": 1.02, + "learning_rate": 2.0033946708613876e-05, + "loss": 3.4458, + "step": 1830400 + }, + { + "epoch": 1.02, + "learning_rate": 2.0025560761103356e-05, + "loss": 3.426, + "step": 1830912 + }, + { + "epoch": 1.02, + "learning_rate": 2.0017174813592833e-05, + "loss": 3.4355, + "step": 1831424 + }, + { + "epoch": 1.03, + "eval_loss": 3.854401111602783, + "eval_runtime": 305.263, + "eval_samples_per_second": 1250.04, + "eval_steps_per_second": 39.065, + "step": 1831680 + }, + { + "epoch": 0.0, + "learning_rate": 2.000880524488605e-05, + "loss": 3.4316, + "step": 1831936 + }, + { + "epoch": 0.0, + "learning_rate": 2.000041929737553e-05, + "loss": 3.4299, + "step": 1832448 + }, + { + "epoch": 0.0, + "learning_rate": 1.999203334986501e-05, + "loss": 3.4341, + "step": 1832960 + }, + { + "epoch": 0.0, + "learning_rate": 1.9983647402354485e-05, + "loss": 3.4316, + "step": 1833472 + }, + { + "epoch": 0.0, + "learning_rate": 1.9975277833647698e-05, + "loss": 3.446, + "step": 1833984 + }, + { + "epoch": 0.0, + "learning_rate": 1.9966891886137178e-05, + "loss": 3.4251, + "step": 1834496 + }, + { + "epoch": 0.0, + "learning_rate": 1.995850593862666e-05, + "loss": 3.434, + "step": 1835008 + }, + { + "epoch": 0.0, + "learning_rate": 1.9950119991116138e-05, + "loss": 3.4299, + "step": 1835520 + }, + { + "epoch": 0.0, + "learning_rate": 1.994175042240935e-05, + "loss": 3.4296, + "step": 1836032 + }, + { + "epoch": 0.0, + "learning_rate": 1.993336447489883e-05, + "loss": 3.441, + "step": 1836544 + }, + { + "epoch": 0.0, + "learning_rate": 1.9924978527388307e-05, + "loss": 3.4341, + "step": 1837056 + }, + { + "epoch": 0.0, + "learning_rate": 1.9916592579877786e-05, + "loss": 3.4283, + "step": 1837568 + }, + { + "epoch": 0.0, + "learning_rate": 1.9908223011171002e-05, + "loss": 3.4359, + "step": 1838080 + }, + { + "epoch": 0.0, + "learning_rate": 1.9899837063660482e-05, + "loss": 3.4206, + "step": 1838592 + }, + { + "epoch": 0.0, + "learning_rate": 1.989145111614996e-05, + "loss": 3.4318, + "step": 1839104 + }, + { + "epoch": 0.0, + "learning_rate": 1.988306516863944e-05, + "loss": 3.4244, + "step": 1839616 + }, + { + "epoch": 0.0, + "learning_rate": 1.987469559993265e-05, + "loss": 3.4311, + "step": 1840128 + }, + { + "epoch": 0.0, + "learning_rate": 1.986630965242213e-05, + "loss": 3.4254, + "step": 1840640 + }, + { + "epoch": 0.0, + "learning_rate": 1.985792370491161e-05, + "loss": 3.4239, + "step": 1841152 + }, + { + "epoch": 0.0, + "learning_rate": 1.984953775740109e-05, + "loss": 3.4401, + "step": 1841664 + }, + { + "epoch": 0.0, + "learning_rate": 1.9841168188694304e-05, + "loss": 3.4402, + "step": 1842176 + }, + { + "epoch": 0.0, + "learning_rate": 1.983278224118378e-05, + "loss": 3.4437, + "step": 1842688 + }, + { + "epoch": 0.0, + "learning_rate": 1.982439629367326e-05, + "loss": 3.4304, + "step": 1843200 + }, + { + "epoch": 0.0, + "learning_rate": 1.981601034616274e-05, + "loss": 3.433, + "step": 1843712 + }, + { + "epoch": 0.0, + "learning_rate": 1.9807640777455956e-05, + "loss": 3.4269, + "step": 1844224 + }, + { + "epoch": 0.0, + "learning_rate": 1.9799254829945433e-05, + "loss": 3.4384, + "step": 1844736 + }, + { + "epoch": 0.0, + "learning_rate": 1.9790868882434913e-05, + "loss": 3.4307, + "step": 1845248 + }, + { + "epoch": 0.0, + "learning_rate": 1.9782482934924393e-05, + "loss": 3.4301, + "step": 1845760 + }, + { + "epoch": 0.0, + "learning_rate": 1.97741133662176e-05, + "loss": 3.4198, + "step": 1846272 + }, + { + "epoch": 0.0, + "learning_rate": 1.9765727418707085e-05, + "loss": 3.4264, + "step": 1846784 + }, + { + "epoch": 0.01, + "learning_rate": 1.9757341471196565e-05, + "loss": 3.424, + "step": 1847296 + }, + { + "epoch": 0.01, + "learning_rate": 1.9748955523686045e-05, + "loss": 3.4392, + "step": 1847808 + }, + { + "epoch": 0.01, + "learning_rate": 1.9740585954979254e-05, + "loss": 3.4366, + "step": 1848320 + }, + { + "epoch": 0.01, + "learning_rate": 1.9732200007468734e-05, + "loss": 3.4303, + "step": 1848832 + }, + { + "epoch": 0.01, + "learning_rate": 1.9723814059958214e-05, + "loss": 3.4236, + "step": 1849344 + }, + { + "epoch": 0.01, + "learning_rate": 1.9715428112447694e-05, + "loss": 3.4325, + "step": 1849856 + }, + { + "epoch": 0.01, + "learning_rate": 1.9707058543740906e-05, + "loss": 3.4318, + "step": 1850368 + }, + { + "epoch": 0.01, + "learning_rate": 1.9698672596230386e-05, + "loss": 3.4275, + "step": 1850880 + }, + { + "epoch": 0.01, + "learning_rate": 1.9690286648719866e-05, + "loss": 3.4257, + "step": 1851392 + }, + { + "epoch": 0.01, + "learning_rate": 1.9681917080013075e-05, + "loss": 3.4172, + "step": 1851904 + }, + { + "epoch": 0.01, + "learning_rate": 1.9673531132502555e-05, + "loss": 3.4246, + "step": 1852416 + }, + { + "epoch": 0.01, + "learning_rate": 1.966514518499204e-05, + "loss": 3.441, + "step": 1852928 + }, + { + "epoch": 0.01, + "learning_rate": 1.965675923748152e-05, + "loss": 3.4374, + "step": 1853440 + }, + { + "epoch": 0.01, + "learning_rate": 1.9648389668774728e-05, + "loss": 3.427, + "step": 1853952 + }, + { + "epoch": 0.01, + "learning_rate": 1.9640003721264208e-05, + "loss": 3.4324, + "step": 1854464 + }, + { + "epoch": 0.01, + "learning_rate": 1.9631617773753688e-05, + "loss": 3.4261, + "step": 1854976 + }, + { + "epoch": 0.01, + "learning_rate": 1.9623231826243168e-05, + "loss": 3.434, + "step": 1855488 + }, + { + "epoch": 0.01, + "learning_rate": 1.961486225753638e-05, + "loss": 3.424, + "step": 1856000 + }, + { + "epoch": 0.01, + "learning_rate": 1.960647631002586e-05, + "loss": 3.4024, + "step": 1856512 + }, + { + "epoch": 0.01, + "learning_rate": 1.959809036251534e-05, + "loss": 3.4401, + "step": 1857024 + }, + { + "epoch": 0.01, + "learning_rate": 1.958970441500482e-05, + "loss": 3.4254, + "step": 1857536 + }, + { + "epoch": 0.01, + "learning_rate": 1.958133484629803e-05, + "loss": 3.434, + "step": 1858048 + }, + { + "epoch": 0.01, + "learning_rate": 1.957294889878751e-05, + "loss": 3.4242, + "step": 1858560 + }, + { + "epoch": 0.01, + "learning_rate": 1.9564562951276992e-05, + "loss": 3.4209, + "step": 1859072 + }, + { + "epoch": 0.01, + "learning_rate": 1.9556177003766472e-05, + "loss": 3.4126, + "step": 1859584 + }, + { + "epoch": 0.01, + "learning_rate": 1.954780743505968e-05, + "loss": 3.4207, + "step": 1860096 + }, + { + "epoch": 0.01, + "learning_rate": 1.953942148754916e-05, + "loss": 3.4224, + "step": 1860608 + }, + { + "epoch": 0.01, + "learning_rate": 1.953103554003864e-05, + "loss": 3.4205, + "step": 1861120 + }, + { + "epoch": 0.01, + "learning_rate": 1.952264959252812e-05, + "loss": 3.4338, + "step": 1861632 + }, + { + "epoch": 0.01, + "learning_rate": 1.9514280023821334e-05, + "loss": 3.418, + "step": 1862144 + }, + { + "epoch": 0.01, + "learning_rate": 1.9505894076310814e-05, + "loss": 3.4269, + "step": 1862656 + }, + { + "epoch": 0.01, + "learning_rate": 1.9497508128800294e-05, + "loss": 3.4387, + "step": 1863168 + }, + { + "epoch": 0.01, + "learning_rate": 1.9489122181289774e-05, + "loss": 3.411, + "step": 1863680 + }, + { + "epoch": 0.01, + "learning_rate": 1.9480752612582983e-05, + "loss": 3.4139, + "step": 1864192 + }, + { + "epoch": 0.01, + "learning_rate": 1.9472366665072463e-05, + "loss": 3.4279, + "step": 1864704 + }, + { + "epoch": 0.01, + "learning_rate": 1.9463980717561946e-05, + "loss": 3.428, + "step": 1865216 + }, + { + "epoch": 0.01, + "learning_rate": 1.9455594770051426e-05, + "loss": 3.4179, + "step": 1865728 + }, + { + "epoch": 0.01, + "learning_rate": 1.9447225201344635e-05, + "loss": 3.4182, + "step": 1866240 + }, + { + "epoch": 0.01, + "learning_rate": 1.9438839253834115e-05, + "loss": 3.4207, + "step": 1866752 + }, + { + "epoch": 0.01, + "learning_rate": 1.9430453306323595e-05, + "loss": 3.4212, + "step": 1867264 + }, + { + "epoch": 0.01, + "learning_rate": 1.9422067358813075e-05, + "loss": 3.4279, + "step": 1867776 + }, + { + "epoch": 0.01, + "learning_rate": 1.9413697790106287e-05, + "loss": 3.4254, + "step": 1868288 + }, + { + "epoch": 0.01, + "learning_rate": 1.9405311842595767e-05, + "loss": 3.4318, + "step": 1868800 + }, + { + "epoch": 0.01, + "learning_rate": 1.9396925895085247e-05, + "loss": 3.4347, + "step": 1869312 + }, + { + "epoch": 0.01, + "learning_rate": 1.9388539947574727e-05, + "loss": 3.4479, + "step": 1869824 + }, + { + "epoch": 0.01, + "learning_rate": 1.9380170378867936e-05, + "loss": 3.4183, + "step": 1870336 + }, + { + "epoch": 0.01, + "learning_rate": 1.9371784431357416e-05, + "loss": 3.4317, + "step": 1870848 + }, + { + "epoch": 0.01, + "learning_rate": 1.9363398483846896e-05, + "loss": 3.4315, + "step": 1871360 + }, + { + "epoch": 0.01, + "learning_rate": 1.935501253633638e-05, + "loss": 3.4172, + "step": 1871872 + }, + { + "epoch": 0.01, + "learning_rate": 1.934664296762959e-05, + "loss": 3.4269, + "step": 1872384 + }, + { + "epoch": 0.01, + "learning_rate": 1.933825702011907e-05, + "loss": 3.4354, + "step": 1872896 + }, + { + "epoch": 0.01, + "learning_rate": 1.932987107260855e-05, + "loss": 3.4294, + "step": 1873408 + }, + { + "epoch": 0.01, + "learning_rate": 1.932148512509803e-05, + "loss": 3.4321, + "step": 1873920 + }, + { + "epoch": 0.01, + "learning_rate": 1.931311555639124e-05, + "loss": 3.4128, + "step": 1874432 + }, + { + "epoch": 0.01, + "learning_rate": 1.930472960888072e-05, + "loss": 3.4165, + "step": 1874944 + }, + { + "epoch": 0.01, + "learning_rate": 1.92963436613702e-05, + "loss": 3.4214, + "step": 1875456 + }, + { + "epoch": 0.01, + "learning_rate": 1.9287957713859678e-05, + "loss": 3.4292, + "step": 1875968 + }, + { + "epoch": 0.01, + "learning_rate": 1.927958814515289e-05, + "loss": 3.4308, + "step": 1876480 + }, + { + "epoch": 0.01, + "learning_rate": 1.927120219764237e-05, + "loss": 3.4222, + "step": 1876992 + }, + { + "epoch": 0.02, + "learning_rate": 1.926281625013185e-05, + "loss": 3.4155, + "step": 1877504 + }, + { + "epoch": 0.02, + "learning_rate": 1.925443030262133e-05, + "loss": 3.4229, + "step": 1878016 + }, + { + "epoch": 0.02, + "learning_rate": 1.9246060733914542e-05, + "loss": 3.4132, + "step": 1878528 + }, + { + "epoch": 0.02, + "learning_rate": 1.9237674786404022e-05, + "loss": 3.4241, + "step": 1879040 + }, + { + "epoch": 0.02, + "learning_rate": 1.92292888388935e-05, + "loss": 3.4323, + "step": 1879552 + }, + { + "epoch": 0.02, + "learning_rate": 1.922090289138298e-05, + "loss": 3.4323, + "step": 1880064 + }, + { + "epoch": 0.02, + "learning_rate": 1.9212533322676195e-05, + "loss": 3.4253, + "step": 1880576 + }, + { + "epoch": 0.02, + "learning_rate": 1.9204147375165675e-05, + "loss": 3.4183, + "step": 1881088 + }, + { + "epoch": 0.02, + "learning_rate": 1.919576142765515e-05, + "loss": 3.4301, + "step": 1881600 + }, + { + "epoch": 0.02, + "learning_rate": 1.918737548014463e-05, + "loss": 3.4234, + "step": 1882112 + }, + { + "epoch": 0.02, + "learning_rate": 1.9179005911437844e-05, + "loss": 3.4275, + "step": 1882624 + }, + { + "epoch": 0.02, + "learning_rate": 1.9170619963927324e-05, + "loss": 3.4227, + "step": 1883136 + }, + { + "epoch": 0.02, + "learning_rate": 1.9162234016416804e-05, + "loss": 3.4173, + "step": 1883648 + }, + { + "epoch": 0.02, + "learning_rate": 1.9153848068906284e-05, + "loss": 3.4284, + "step": 1884160 + }, + { + "epoch": 0.02, + "learning_rate": 1.9145478500199496e-05, + "loss": 3.4305, + "step": 1884672 + }, + { + "epoch": 0.02, + "learning_rate": 1.9137092552688973e-05, + "loss": 3.4127, + "step": 1885184 + }, + { + "epoch": 0.02, + "learning_rate": 1.9128706605178453e-05, + "loss": 3.4238, + "step": 1885696 + }, + { + "epoch": 0.02, + "learning_rate": 1.9120337036471665e-05, + "loss": 3.4171, + "step": 1886208 + }, + { + "epoch": 0.02, + "learning_rate": 1.911195108896115e-05, + "loss": 3.4371, + "step": 1886720 + }, + { + "epoch": 0.02, + "learning_rate": 1.9103565141450625e-05, + "loss": 3.4106, + "step": 1887232 + }, + { + "epoch": 0.02, + "learning_rate": 1.9095179193940105e-05, + "loss": 3.4269, + "step": 1887744 + }, + { + "epoch": 0.02, + "learning_rate": 1.9086809625233317e-05, + "loss": 3.4164, + "step": 1888256 + }, + { + "epoch": 0.02, + "learning_rate": 1.9078423677722797e-05, + "loss": 3.4273, + "step": 1888768 + }, + { + "epoch": 0.02, + "learning_rate": 1.9070037730212277e-05, + "loss": 3.4268, + "step": 1889280 + }, + { + "epoch": 0.02, + "learning_rate": 1.9061651782701757e-05, + "loss": 3.4204, + "step": 1889792 + }, + { + "epoch": 0.02, + "learning_rate": 1.905328221399497e-05, + "loss": 3.4233, + "step": 1890304 + }, + { + "epoch": 0.02, + "learning_rate": 1.9044896266484446e-05, + "loss": 3.4394, + "step": 1890816 + }, + { + "epoch": 0.02, + "learning_rate": 1.9036510318973926e-05, + "loss": 3.4255, + "step": 1891328 + }, + { + "epoch": 0.02, + "learning_rate": 1.9028124371463406e-05, + "loss": 3.4265, + "step": 1891840 + }, + { + "epoch": 0.02, + "learning_rate": 1.901975480275662e-05, + "loss": 3.4276, + "step": 1892352 + }, + { + "epoch": 0.02, + "learning_rate": 1.90113688552461e-05, + "loss": 3.4266, + "step": 1892864 + }, + { + "epoch": 0.02, + "learning_rate": 1.900298290773558e-05, + "loss": 3.424, + "step": 1893376 + }, + { + "epoch": 0.02, + "learning_rate": 1.899459696022506e-05, + "loss": 3.4233, + "step": 1893888 + }, + { + "epoch": 0.02, + "learning_rate": 1.898622739151827e-05, + "loss": 3.4162, + "step": 1894400 + }, + { + "epoch": 0.02, + "learning_rate": 1.8977841444007748e-05, + "loss": 3.4236, + "step": 1894912 + }, + { + "epoch": 0.02, + "learning_rate": 1.896945549649723e-05, + "loss": 3.4174, + "step": 1895424 + }, + { + "epoch": 0.02, + "learning_rate": 1.896106954898671e-05, + "loss": 3.4247, + "step": 1895936 + }, + { + "epoch": 0.02, + "learning_rate": 1.895269998027992e-05, + "loss": 3.4214, + "step": 1896448 + }, + { + "epoch": 0.02, + "learning_rate": 1.89443140327694e-05, + "loss": 3.4211, + "step": 1896960 + }, + { + "epoch": 0.02, + "learning_rate": 1.893592808525888e-05, + "loss": 3.4175, + "step": 1897472 + }, + { + "epoch": 0.02, + "learning_rate": 1.892754213774836e-05, + "loss": 3.4372, + "step": 1897984 + }, + { + "epoch": 0.02, + "learning_rate": 1.8919172569041572e-05, + "loss": 3.4234, + "step": 1898496 + }, + { + "epoch": 0.02, + "learning_rate": 1.8910786621531052e-05, + "loss": 3.4371, + "step": 1899008 + }, + { + "epoch": 0.02, + "learning_rate": 1.8902400674020532e-05, + "loss": 3.4104, + "step": 1899520 + }, + { + "epoch": 0.02, + "learning_rate": 1.8894014726510012e-05, + "loss": 3.4402, + "step": 1900032 + }, + { + "epoch": 0.02, + "learning_rate": 1.888564515780322e-05, + "loss": 3.4198, + "step": 1900544 + }, + { + "epoch": 0.02, + "learning_rate": 1.88772592102927e-05, + "loss": 3.429, + "step": 1901056 + }, + { + "epoch": 0.02, + "learning_rate": 1.8868873262782185e-05, + "loss": 3.4238, + "step": 1901568 + }, + { + "epoch": 0.02, + "learning_rate": 1.8860487315271665e-05, + "loss": 3.4213, + "step": 1902080 + }, + { + "epoch": 0.02, + "learning_rate": 1.8852117746564874e-05, + "loss": 3.4222, + "step": 1902592 + }, + { + "epoch": 0.02, + "learning_rate": 1.8843731799054354e-05, + "loss": 3.4417, + "step": 1903104 + }, + { + "epoch": 0.02, + "learning_rate": 1.8835345851543834e-05, + "loss": 3.4096, + "step": 1903616 + }, + { + "epoch": 0.02, + "learning_rate": 1.8826959904033314e-05, + "loss": 3.4304, + "step": 1904128 + }, + { + "epoch": 0.02, + "learning_rate": 1.8818590335326526e-05, + "loss": 3.4222, + "step": 1904640 + }, + { + "epoch": 0.02, + "learning_rate": 1.8810204387816006e-05, + "loss": 3.4181, + "step": 1905152 + }, + { + "epoch": 0.02, + "learning_rate": 1.8801818440305486e-05, + "loss": 3.422, + "step": 1905664 + }, + { + "epoch": 0.02, + "learning_rate": 1.8793432492794966e-05, + "loss": 3.4218, + "step": 1906176 + }, + { + "epoch": 0.02, + "learning_rate": 1.8785062924088175e-05, + "loss": 3.4375, + "step": 1906688 + }, + { + "epoch": 0.02, + "learning_rate": 1.8776676976577655e-05, + "loss": 3.4196, + "step": 1907200 + }, + { + "epoch": 0.02, + "learning_rate": 1.8768291029067135e-05, + "loss": 3.4245, + "step": 1907712 + }, + { + "epoch": 0.03, + "eval_loss": 3.854795455932617, + "eval_runtime": 303.3299, + "eval_samples_per_second": 1258.006, + "eval_steps_per_second": 39.314, + "step": 1908000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8759905081556618e-05, + "loss": 3.4221, + "step": 1908224 + }, + { + "epoch": 0.0, + "learning_rate": 1.8751519134046098e-05, + "loss": 3.4183, + "step": 1908736 + }, + { + "epoch": 0.0, + "learning_rate": 1.8743133186535575e-05, + "loss": 3.423, + "step": 1909248 + }, + { + "epoch": 0.0, + "learning_rate": 1.8734747239025055e-05, + "loss": 3.4236, + "step": 1909760 + }, + { + "epoch": 0.0, + "learning_rate": 1.8726377670318267e-05, + "loss": 3.4367, + "step": 1910272 + }, + { + "epoch": 0.0, + "learning_rate": 1.8717991722807747e-05, + "loss": 3.4135, + "step": 1910784 + }, + { + "epoch": 0.0, + "learning_rate": 1.8709605775297227e-05, + "loss": 3.4231, + "step": 1911296 + }, + { + "epoch": 0.0, + "learning_rate": 1.8701219827786707e-05, + "loss": 3.4193, + "step": 1911808 + }, + { + "epoch": 0.0, + "learning_rate": 1.869285025907992e-05, + "loss": 3.4219, + "step": 1912320 + }, + { + "epoch": 0.0, + "learning_rate": 1.86844643115694e-05, + "loss": 3.4307, + "step": 1912832 + }, + { + "epoch": 0.0, + "learning_rate": 1.8676078364058876e-05, + "loss": 3.4204, + "step": 1913344 + }, + { + "epoch": 0.0, + "learning_rate": 1.8667692416548356e-05, + "loss": 3.4185, + "step": 1913856 + }, + { + "epoch": 0.0, + "learning_rate": 1.8659322847841572e-05, + "loss": 3.4285, + "step": 1914368 + }, + { + "epoch": 0.0, + "learning_rate": 1.865093690033105e-05, + "loss": 3.4085, + "step": 1914880 + }, + { + "epoch": 0.0, + "learning_rate": 1.864255095282053e-05, + "loss": 3.4186, + "step": 1915392 + }, + { + "epoch": 0.0, + "learning_rate": 1.863416500531001e-05, + "loss": 3.4124, + "step": 1915904 + }, + { + "epoch": 0.0, + "learning_rate": 1.862579543660322e-05, + "loss": 3.4211, + "step": 1916416 + }, + { + "epoch": 0.0, + "learning_rate": 1.86174094890927e-05, + "loss": 3.4142, + "step": 1916928 + }, + { + "epoch": 0.0, + "learning_rate": 1.860902354158218e-05, + "loss": 3.417, + "step": 1917440 + }, + { + "epoch": 0.0, + "learning_rate": 1.860063759407166e-05, + "loss": 3.4292, + "step": 1917952 + }, + { + "epoch": 0.0, + "learning_rate": 1.8592268025364873e-05, + "loss": 3.429, + "step": 1918464 + }, + { + "epoch": 0.0, + "learning_rate": 1.858388207785435e-05, + "loss": 3.4331, + "step": 1918976 + }, + { + "epoch": 0.0, + "learning_rate": 1.857549613034383e-05, + "loss": 3.4203, + "step": 1919488 + }, + { + "epoch": 0.0, + "learning_rate": 1.856711018283331e-05, + "loss": 3.4196, + "step": 1920000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8558740614126522e-05, + "loss": 3.4147, + "step": 1920512 + }, + { + "epoch": 0.0, + "learning_rate": 1.8550354666616002e-05, + "loss": 3.4279, + "step": 1921024 + }, + { + "epoch": 0.0, + "learning_rate": 1.8541968719105482e-05, + "loss": 3.4203, + "step": 1921536 + }, + { + "epoch": 0.0, + "learning_rate": 1.8533582771594962e-05, + "loss": 3.4202, + "step": 1922048 + }, + { + "epoch": 0.0, + "learning_rate": 1.852521320288817e-05, + "loss": 3.4118, + "step": 1922560 + }, + { + "epoch": 0.0, + "learning_rate": 1.8516827255377654e-05, + "loss": 3.4136, + "step": 1923072 + }, + { + "epoch": 0.01, + "learning_rate": 1.8508441307867134e-05, + "loss": 3.4119, + "step": 1923584 + }, + { + "epoch": 0.01, + "learning_rate": 1.8500055360356614e-05, + "loss": 3.4297, + "step": 1924096 + }, + { + "epoch": 0.01, + "learning_rate": 1.8491685791649823e-05, + "loss": 3.43, + "step": 1924608 + }, + { + "epoch": 0.01, + "learning_rate": 1.8483299844139303e-05, + "loss": 3.4204, + "step": 1925120 + }, + { + "epoch": 0.01, + "learning_rate": 1.8474913896628783e-05, + "loss": 3.4165, + "step": 1925632 + }, + { + "epoch": 0.01, + "learning_rate": 1.8466527949118263e-05, + "loss": 3.4171, + "step": 1926144 + }, + { + "epoch": 0.01, + "learning_rate": 1.8458158380411476e-05, + "loss": 3.4251, + "step": 1926656 + }, + { + "epoch": 0.01, + "learning_rate": 1.8449772432900956e-05, + "loss": 3.4184, + "step": 1927168 + }, + { + "epoch": 0.01, + "learning_rate": 1.8441386485390436e-05, + "loss": 3.4142, + "step": 1927680 + }, + { + "epoch": 0.01, + "learning_rate": 1.8433016916683645e-05, + "loss": 3.4059, + "step": 1928192 + }, + { + "epoch": 0.01, + "learning_rate": 1.8424630969173125e-05, + "loss": 3.4164, + "step": 1928704 + }, + { + "epoch": 0.01, + "learning_rate": 1.841626140046634e-05, + "loss": 3.4231, + "step": 1929216 + }, + { + "epoch": 0.01, + "learning_rate": 1.8407875452955817e-05, + "loss": 3.4266, + "step": 1929728 + }, + { + "epoch": 0.01, + "learning_rate": 1.8399489505445297e-05, + "loss": 3.4191, + "step": 1930240 + }, + { + "epoch": 0.01, + "learning_rate": 1.8391103557934777e-05, + "loss": 3.4197, + "step": 1930752 + }, + { + "epoch": 0.01, + "learning_rate": 1.8382717610424257e-05, + "loss": 3.4198, + "step": 1931264 + }, + { + "epoch": 0.01, + "learning_rate": 1.8374331662913737e-05, + "loss": 3.4197, + "step": 1931776 + }, + { + "epoch": 0.01, + "learning_rate": 1.8365945715403217e-05, + "loss": 3.4135, + "step": 1932288 + }, + { + "epoch": 0.01, + "learning_rate": 1.8357559767892697e-05, + "loss": 3.3931, + "step": 1932800 + }, + { + "epoch": 0.01, + "learning_rate": 1.834919019918591e-05, + "loss": 3.4267, + "step": 1933312 + }, + { + "epoch": 0.01, + "learning_rate": 1.834080425167539e-05, + "loss": 3.4158, + "step": 1933824 + }, + { + "epoch": 0.01, + "learning_rate": 1.833241830416487e-05, + "loss": 3.4268, + "step": 1934336 + }, + { + "epoch": 0.01, + "learning_rate": 1.832404873545808e-05, + "loss": 3.4136, + "step": 1934848 + }, + { + "epoch": 0.01, + "learning_rate": 1.831566278794756e-05, + "loss": 3.4094, + "step": 1935360 + }, + { + "epoch": 0.01, + "learning_rate": 1.8307276840437042e-05, + "loss": 3.405, + "step": 1935872 + }, + { + "epoch": 0.01, + "learning_rate": 1.8298890892926522e-05, + "loss": 3.4064, + "step": 1936384 + }, + { + "epoch": 0.01, + "learning_rate": 1.829052132421973e-05, + "loss": 3.4181, + "step": 1936896 + }, + { + "epoch": 0.01, + "learning_rate": 1.828213537670921e-05, + "loss": 3.404, + "step": 1937408 + }, + { + "epoch": 0.01, + "learning_rate": 1.827374942919869e-05, + "loss": 3.4245, + "step": 1937920 + }, + { + "epoch": 0.01, + "learning_rate": 1.826536348168817e-05, + "loss": 3.4116, + "step": 1938432 + }, + { + "epoch": 0.01, + "learning_rate": 1.8256993912981383e-05, + "loss": 3.413, + "step": 1938944 + }, + { + "epoch": 0.01, + "learning_rate": 1.8248607965470863e-05, + "loss": 3.4314, + "step": 1939456 + }, + { + "epoch": 0.01, + "learning_rate": 1.8240222017960343e-05, + "loss": 3.4029, + "step": 1939968 + }, + { + "epoch": 0.01, + "learning_rate": 1.8231836070449823e-05, + "loss": 3.4028, + "step": 1940480 + }, + { + "epoch": 0.01, + "learning_rate": 1.8223466501743032e-05, + "loss": 3.4193, + "step": 1940992 + }, + { + "epoch": 0.01, + "learning_rate": 1.8215080554232512e-05, + "loss": 3.4183, + "step": 1941504 + }, + { + "epoch": 0.01, + "learning_rate": 1.8206694606721995e-05, + "loss": 3.4059, + "step": 1942016 + }, + { + "epoch": 0.01, + "learning_rate": 1.8198308659211472e-05, + "loss": 3.4092, + "step": 1942528 + }, + { + "epoch": 0.01, + "learning_rate": 1.8189939090504684e-05, + "loss": 3.4035, + "step": 1943040 + }, + { + "epoch": 0.01, + "learning_rate": 1.8181553142994164e-05, + "loss": 3.4139, + "step": 1943552 + }, + { + "epoch": 0.01, + "learning_rate": 1.8173167195483644e-05, + "loss": 3.4157, + "step": 1944064 + }, + { + "epoch": 0.01, + "learning_rate": 1.8164781247973124e-05, + "loss": 3.4184, + "step": 1944576 + }, + { + "epoch": 0.01, + "learning_rate": 1.8156411679266337e-05, + "loss": 3.4209, + "step": 1945088 + }, + { + "epoch": 0.01, + "learning_rate": 1.8148025731755817e-05, + "loss": 3.4194, + "step": 1945600 + }, + { + "epoch": 0.01, + "learning_rate": 1.8139639784245297e-05, + "loss": 3.4361, + "step": 1946112 + }, + { + "epoch": 0.01, + "learning_rate": 1.8131253836734773e-05, + "loss": 3.4121, + "step": 1946624 + }, + { + "epoch": 0.01, + "learning_rate": 1.8122884268027986e-05, + "loss": 3.4257, + "step": 1947136 + }, + { + "epoch": 0.01, + "learning_rate": 1.8114498320517466e-05, + "loss": 3.4176, + "step": 1947648 + }, + { + "epoch": 0.01, + "learning_rate": 1.8106112373006946e-05, + "loss": 3.4101, + "step": 1948160 + }, + { + "epoch": 0.01, + "learning_rate": 1.8097726425496426e-05, + "loss": 3.4137, + "step": 1948672 + }, + { + "epoch": 0.01, + "learning_rate": 1.8089356856789638e-05, + "loss": 3.4267, + "step": 1949184 + }, + { + "epoch": 0.01, + "learning_rate": 1.8080970909279118e-05, + "loss": 3.4181, + "step": 1949696 + }, + { + "epoch": 0.01, + "learning_rate": 1.8072584961768595e-05, + "loss": 3.4214, + "step": 1950208 + }, + { + "epoch": 0.01, + "learning_rate": 1.8064199014258078e-05, + "loss": 3.4027, + "step": 1950720 + }, + { + "epoch": 0.01, + "learning_rate": 1.805582944555129e-05, + "loss": 3.4063, + "step": 1951232 + }, + { + "epoch": 0.01, + "learning_rate": 1.804744349804077e-05, + "loss": 3.4116, + "step": 1951744 + }, + { + "epoch": 0.01, + "learning_rate": 1.8039057550530247e-05, + "loss": 3.4167, + "step": 1952256 + }, + { + "epoch": 0.01, + "learning_rate": 1.8030671603019727e-05, + "loss": 3.4197, + "step": 1952768 + }, + { + "epoch": 0.01, + "learning_rate": 1.802230203431294e-05, + "loss": 3.4167, + "step": 1953280 + }, + { + "epoch": 0.02, + "learning_rate": 1.801391608680242e-05, + "loss": 3.4041, + "step": 1953792 + }, + { + "epoch": 0.02, + "learning_rate": 1.80055301392919e-05, + "loss": 3.416, + "step": 1954304 + }, + { + "epoch": 0.02, + "learning_rate": 1.799714419178138e-05, + "loss": 3.4067, + "step": 1954816 + }, + { + "epoch": 0.02, + "learning_rate": 1.7988774623074592e-05, + "loss": 3.4117, + "step": 1955328 + }, + { + "epoch": 0.02, + "learning_rate": 1.798038867556407e-05, + "loss": 3.4218, + "step": 1955840 + }, + { + "epoch": 0.02, + "learning_rate": 1.797200272805355e-05, + "loss": 3.4205, + "step": 1956352 + }, + { + "epoch": 0.02, + "learning_rate": 1.796361678054303e-05, + "loss": 3.416, + "step": 1956864 + }, + { + "epoch": 0.02, + "learning_rate": 1.7955247211836244e-05, + "loss": 3.4092, + "step": 1957376 + }, + { + "epoch": 0.02, + "learning_rate": 1.794686126432572e-05, + "loss": 3.415, + "step": 1957888 + }, + { + "epoch": 0.02, + "learning_rate": 1.79384753168152e-05, + "loss": 3.4115, + "step": 1958400 + }, + { + "epoch": 0.02, + "learning_rate": 1.793008936930468e-05, + "loss": 3.4207, + "step": 1958912 + }, + { + "epoch": 0.02, + "learning_rate": 1.7921719800597893e-05, + "loss": 3.41, + "step": 1959424 + }, + { + "epoch": 0.02, + "learning_rate": 1.7913333853087373e-05, + "loss": 3.4103, + "step": 1959936 + }, + { + "epoch": 0.02, + "learning_rate": 1.7904947905576853e-05, + "loss": 3.4135, + "step": 1960448 + }, + { + "epoch": 0.02, + "learning_rate": 1.7896578336870066e-05, + "loss": 3.4202, + "step": 1960960 + }, + { + "epoch": 0.02, + "learning_rate": 1.7888192389359542e-05, + "loss": 3.4048, + "step": 1961472 + }, + { + "epoch": 0.02, + "learning_rate": 1.7879806441849022e-05, + "loss": 3.4157, + "step": 1961984 + }, + { + "epoch": 0.02, + "learning_rate": 1.7871420494338502e-05, + "loss": 3.4064, + "step": 1962496 + }, + { + "epoch": 0.02, + "learning_rate": 1.7863050925631715e-05, + "loss": 3.4275, + "step": 1963008 + }, + { + "epoch": 0.02, + "learning_rate": 1.7854664978121194e-05, + "loss": 3.4025, + "step": 1963520 + }, + { + "epoch": 0.02, + "learning_rate": 1.7846279030610674e-05, + "loss": 3.4141, + "step": 1964032 + }, + { + "epoch": 0.02, + "learning_rate": 1.7837893083100154e-05, + "loss": 3.4066, + "step": 1964544 + }, + { + "epoch": 0.02, + "learning_rate": 1.7829523514393363e-05, + "loss": 3.4226, + "step": 1965056 + }, + { + "epoch": 0.02, + "learning_rate": 1.7821137566882843e-05, + "loss": 3.4134, + "step": 1965568 + }, + { + "epoch": 0.02, + "learning_rate": 1.7812751619372327e-05, + "loss": 3.408, + "step": 1966080 + }, + { + "epoch": 0.02, + "learning_rate": 1.7804365671861807e-05, + "loss": 3.4152, + "step": 1966592 + }, + { + "epoch": 0.02, + "learning_rate": 1.7795996103155016e-05, + "loss": 3.4272, + "step": 1967104 + }, + { + "epoch": 0.02, + "learning_rate": 1.7787610155644496e-05, + "loss": 3.4153, + "step": 1967616 + }, + { + "epoch": 0.02, + "learning_rate": 1.7779224208133976e-05, + "loss": 3.4187, + "step": 1968128 + }, + { + "epoch": 0.02, + "learning_rate": 1.7770838260623456e-05, + "loss": 3.4147, + "step": 1968640 + }, + { + "epoch": 0.02, + "learning_rate": 1.7762468691916668e-05, + "loss": 3.4142, + "step": 1969152 + }, + { + "epoch": 0.02, + "learning_rate": 1.7754082744406148e-05, + "loss": 3.4179, + "step": 1969664 + }, + { + "epoch": 0.02, + "learning_rate": 1.7745696796895628e-05, + "loss": 3.409, + "step": 1970176 + }, + { + "epoch": 0.02, + "learning_rate": 1.7737310849385108e-05, + "loss": 3.4064, + "step": 1970688 + }, + { + "epoch": 0.02, + "learning_rate": 1.7728941280678317e-05, + "loss": 3.4148, + "step": 1971200 + }, + { + "epoch": 0.02, + "learning_rate": 1.7720555333167797e-05, + "loss": 3.4099, + "step": 1971712 + }, + { + "epoch": 0.02, + "learning_rate": 1.771216938565728e-05, + "loss": 3.4146, + "step": 1972224 + }, + { + "epoch": 0.02, + "learning_rate": 1.770378343814676e-05, + "loss": 3.4115, + "step": 1972736 + }, + { + "epoch": 0.02, + "learning_rate": 1.769541386943997e-05, + "loss": 3.4102, + "step": 1973248 + }, + { + "epoch": 0.02, + "learning_rate": 1.768702792192945e-05, + "loss": 3.406, + "step": 1973760 + }, + { + "epoch": 0.02, + "learning_rate": 1.767864197441893e-05, + "loss": 3.4226, + "step": 1974272 + }, + { + "epoch": 0.02, + "learning_rate": 1.767025602690841e-05, + "loss": 3.4168, + "step": 1974784 + }, + { + "epoch": 0.02, + "learning_rate": 1.7661886458201622e-05, + "loss": 3.4266, + "step": 1975296 + }, + { + "epoch": 0.02, + "learning_rate": 1.7653500510691102e-05, + "loss": 3.3992, + "step": 1975808 + }, + { + "epoch": 0.02, + "learning_rate": 1.7645114563180582e-05, + "loss": 3.4281, + "step": 1976320 + }, + { + "epoch": 0.02, + "learning_rate": 1.7636728615670062e-05, + "loss": 3.4176, + "step": 1976832 + }, + { + "epoch": 0.02, + "learning_rate": 1.762835904696327e-05, + "loss": 3.4168, + "step": 1977344 + }, + { + "epoch": 0.02, + "learning_rate": 1.761997309945275e-05, + "loss": 3.4113, + "step": 1977856 + }, + { + "epoch": 0.02, + "learning_rate": 1.7611587151942234e-05, + "loss": 3.4111, + "step": 1978368 + }, + { + "epoch": 0.02, + "learning_rate": 1.7603201204431714e-05, + "loss": 3.4147, + "step": 1978880 + }, + { + "epoch": 0.02, + "learning_rate": 1.7594815256921194e-05, + "loss": 3.4287, + "step": 1979392 + }, + { + "epoch": 0.02, + "learning_rate": 1.758642930941067e-05, + "loss": 3.4019, + "step": 1979904 + }, + { + "epoch": 0.02, + "learning_rate": 1.757804336190015e-05, + "loss": 3.4205, + "step": 1980416 + }, + { + "epoch": 0.02, + "learning_rate": 1.7569673793193363e-05, + "loss": 3.4098, + "step": 1980928 + }, + { + "epoch": 0.02, + "learning_rate": 1.7561287845682843e-05, + "loss": 3.4079, + "step": 1981440 + }, + { + "epoch": 0.02, + "learning_rate": 1.7552901898172323e-05, + "loss": 3.4153, + "step": 1981952 + }, + { + "epoch": 0.02, + "learning_rate": 1.7544515950661803e-05, + "loss": 3.4109, + "step": 1982464 + }, + { + "epoch": 0.02, + "learning_rate": 1.7536146381955015e-05, + "loss": 3.4231, + "step": 1982976 + }, + { + "epoch": 0.02, + "learning_rate": 1.7527760434444492e-05, + "loss": 3.4142, + "step": 1983488 + }, + { + "epoch": 0.02, + "learning_rate": 1.7519374486933972e-05, + "loss": 3.4117, + "step": 1984000 + }, + { + "epoch": 0.03, + "eval_loss": 3.8569869995117188, + "eval_runtime": 303.6361, + "eval_samples_per_second": 1256.738, + "eval_steps_per_second": 39.274, + "step": 1984320 + }, + { + "epoch": 1.0, + "learning_rate": 1.7510988539423452e-05, + "loss": 3.4091, + "step": 1984512 + }, + { + "epoch": 1.0, + "learning_rate": 1.7502618970716668e-05, + "loss": 3.4087, + "step": 1985024 + }, + { + "epoch": 1.0, + "learning_rate": 1.7494233023206144e-05, + "loss": 3.412, + "step": 1985536 + }, + { + "epoch": 1.0, + "learning_rate": 1.7485847075695624e-05, + "loss": 3.4168, + "step": 1986048 + }, + { + "epoch": 1.0, + "learning_rate": 1.7477461128185104e-05, + "loss": 3.4252, + "step": 1986560 + }, + { + "epoch": 1.0, + "learning_rate": 1.7469091559478313e-05, + "loss": 3.4054, + "step": 1987072 + }, + { + "epoch": 1.0, + "learning_rate": 1.7460705611967797e-05, + "loss": 3.4113, + "step": 1987584 + }, + { + "epoch": 1.0, + "learning_rate": 1.7452319664457277e-05, + "loss": 3.4107, + "step": 1988096 + }, + { + "epoch": 1.0, + "learning_rate": 1.7443933716946757e-05, + "loss": 3.4104, + "step": 1988608 + }, + { + "epoch": 1.0, + "learning_rate": 1.7435564148239966e-05, + "loss": 3.4181, + "step": 1989120 + }, + { + "epoch": 1.0, + "learning_rate": 1.7427178200729446e-05, + "loss": 3.4117, + "step": 1989632 + }, + { + "epoch": 1.0, + "learning_rate": 1.7418792253218926e-05, + "loss": 3.4135, + "step": 1990144 + }, + { + "epoch": 1.0, + "learning_rate": 1.7410406305708406e-05, + "loss": 3.4159, + "step": 1990656 + }, + { + "epoch": 1.0, + "learning_rate": 1.7402036737001618e-05, + "loss": 3.3999, + "step": 1991168 + }, + { + "epoch": 1.0, + "learning_rate": 1.7393650789491098e-05, + "loss": 3.4115, + "step": 1991680 + }, + { + "epoch": 1.0, + "learning_rate": 1.7385264841980578e-05, + "loss": 3.3981, + "step": 1992192 + }, + { + "epoch": 1.0, + "learning_rate": 1.7376878894470058e-05, + "loss": 3.4118, + "step": 1992704 + }, + { + "epoch": 1.0, + "learning_rate": 1.7368509325763267e-05, + "loss": 3.407, + "step": 1993216 + }, + { + "epoch": 1.0, + "learning_rate": 1.736012337825275e-05, + "loss": 3.4052, + "step": 1993728 + }, + { + "epoch": 1.0, + "learning_rate": 1.735173743074223e-05, + "loss": 3.4189, + "step": 1994240 + }, + { + "epoch": 1.0, + "learning_rate": 1.734335148323171e-05, + "loss": 3.4144, + "step": 1994752 + }, + { + "epoch": 1.0, + "learning_rate": 1.733498191452492e-05, + "loss": 3.4196, + "step": 1995264 + }, + { + "epoch": 1.0, + "learning_rate": 1.73265959670144e-05, + "loss": 3.4133, + "step": 1995776 + }, + { + "epoch": 1.0, + "learning_rate": 1.731821001950388e-05, + "loss": 3.4107, + "step": 1996288 + }, + { + "epoch": 1.0, + "learning_rate": 1.730982407199336e-05, + "loss": 3.4098, + "step": 1996800 + }, + { + "epoch": 1.0, + "learning_rate": 1.730145450328657e-05, + "loss": 3.4139, + "step": 1997312 + }, + { + "epoch": 1.0, + "learning_rate": 1.729306855577605e-05, + "loss": 3.4086, + "step": 1997824 + }, + { + "epoch": 1.0, + "learning_rate": 1.728468260826553e-05, + "loss": 3.4119, + "step": 1998336 + }, + { + "epoch": 1.0, + "learning_rate": 1.727629666075501e-05, + "loss": 3.4036, + "step": 1998848 + }, + { + "epoch": 1.0, + "learning_rate": 1.726792709204822e-05, + "loss": 3.4025, + "step": 1999360 + }, + { + "epoch": 1.01, + "learning_rate": 1.7259541144537704e-05, + "loss": 3.4048, + "step": 1999872 + }, + { + "epoch": 1.01, + "learning_rate": 1.7251155197027184e-05, + "loss": 3.4123, + "step": 2000384 + }, + { + "epoch": 1.01, + "learning_rate": 1.7242769249516664e-05, + "loss": 3.4207, + "step": 2000896 + }, + { + "epoch": 1.01, + "learning_rate": 1.7234399680809873e-05, + "loss": 3.4106, + "step": 2001408 + }, + { + "epoch": 1.01, + "learning_rate": 1.7226013733299353e-05, + "loss": 3.4051, + "step": 2001920 + }, + { + "epoch": 1.01, + "learning_rate": 1.7217627785788833e-05, + "loss": 3.4045, + "step": 2002432 + }, + { + "epoch": 1.01, + "learning_rate": 1.7209241838278313e-05, + "loss": 3.4168, + "step": 2002944 + }, + { + "epoch": 1.01, + "learning_rate": 1.7200872269571525e-05, + "loss": 3.4093, + "step": 2003456 + }, + { + "epoch": 1.01, + "learning_rate": 1.7192486322061005e-05, + "loss": 3.4057, + "step": 2003968 + }, + { + "epoch": 1.01, + "learning_rate": 1.7184100374550485e-05, + "loss": 3.3947, + "step": 2004480 + }, + { + "epoch": 1.01, + "learning_rate": 1.7175714427039965e-05, + "loss": 3.4074, + "step": 2004992 + }, + { + "epoch": 1.01, + "learning_rate": 1.716736123713691e-05, + "loss": 3.4092, + "step": 2005504 + }, + { + "epoch": 1.01, + "learning_rate": 1.7158975289626387e-05, + "loss": 3.4182, + "step": 2006016 + }, + { + "epoch": 1.01, + "learning_rate": 1.7150589342115867e-05, + "loss": 3.4103, + "step": 2006528 + }, + { + "epoch": 1.01, + "learning_rate": 1.7142203394605347e-05, + "loss": 3.4075, + "step": 2007040 + }, + { + "epoch": 1.01, + "learning_rate": 1.7133817447094827e-05, + "loss": 3.4086, + "step": 2007552 + }, + { + "epoch": 1.01, + "learning_rate": 1.7125431499584307e-05, + "loss": 3.4106, + "step": 2008064 + }, + { + "epoch": 1.01, + "learning_rate": 1.7117045552073787e-05, + "loss": 3.4052, + "step": 2008576 + }, + { + "epoch": 1.01, + "learning_rate": 1.7108659604563267e-05, + "loss": 3.3827, + "step": 2009088 + }, + { + "epoch": 1.01, + "learning_rate": 1.710029003585648e-05, + "loss": 3.4171, + "step": 2009600 + }, + { + "epoch": 1.01, + "learning_rate": 1.709190408834596e-05, + "loss": 3.4054, + "step": 2010112 + }, + { + "epoch": 1.01, + "learning_rate": 1.708351814083544e-05, + "loss": 3.4155, + "step": 2010624 + }, + { + "epoch": 1.01, + "learning_rate": 1.7075132193324915e-05, + "loss": 3.4027, + "step": 2011136 + }, + { + "epoch": 1.01, + "learning_rate": 1.7066762624618128e-05, + "loss": 3.4002, + "step": 2011648 + }, + { + "epoch": 1.01, + "learning_rate": 1.705837667710761e-05, + "loss": 3.3941, + "step": 2012160 + }, + { + "epoch": 1.01, + "learning_rate": 1.704999072959709e-05, + "loss": 3.3957, + "step": 2012672 + }, + { + "epoch": 1.01, + "learning_rate": 1.70416211608903e-05, + "loss": 3.4097, + "step": 2013184 + }, + { + "epoch": 1.01, + "learning_rate": 1.703323521337978e-05, + "loss": 3.3907, + "step": 2013696 + }, + { + "epoch": 1.01, + "learning_rate": 1.702484926586926e-05, + "loss": 3.4143, + "step": 2014208 + }, + { + "epoch": 1.01, + "learning_rate": 1.7016463318358737e-05, + "loss": 3.3991, + "step": 2014720 + }, + { + "epoch": 1.01, + "learning_rate": 1.7008093749651953e-05, + "loss": 3.3996, + "step": 2015232 + }, + { + "epoch": 1.01, + "learning_rate": 1.6999707802141433e-05, + "loss": 3.4236, + "step": 2015744 + }, + { + "epoch": 1.01, + "learning_rate": 1.6991321854630913e-05, + "loss": 3.3956, + "step": 2016256 + }, + { + "epoch": 1.01, + "learning_rate": 1.698293590712039e-05, + "loss": 3.3915, + "step": 2016768 + }, + { + "epoch": 1.01, + "learning_rate": 1.69745663384136e-05, + "loss": 3.4089, + "step": 2017280 + }, + { + "epoch": 1.01, + "learning_rate": 1.696618039090308e-05, + "loss": 3.4059, + "step": 2017792 + }, + { + "epoch": 1.01, + "learning_rate": 1.6957794443392565e-05, + "loss": 3.3947, + "step": 2018304 + }, + { + "epoch": 1.01, + "learning_rate": 1.694940849588204e-05, + "loss": 3.3992, + "step": 2018816 + }, + { + "epoch": 1.01, + "learning_rate": 1.6941038927175254e-05, + "loss": 3.394, + "step": 2019328 + }, + { + "epoch": 1.01, + "learning_rate": 1.6932652979664734e-05, + "loss": 3.4021, + "step": 2019840 + }, + { + "epoch": 1.01, + "learning_rate": 1.692426703215421e-05, + "loss": 3.4079, + "step": 2020352 + }, + { + "epoch": 1.01, + "learning_rate": 1.691588108464369e-05, + "loss": 3.4094, + "step": 2020864 + }, + { + "epoch": 1.01, + "learning_rate": 1.6907511515936906e-05, + "loss": 3.4094, + "step": 2021376 + }, + { + "epoch": 1.01, + "learning_rate": 1.6899141947230115e-05, + "loss": 3.4113, + "step": 2021888 + }, + { + "epoch": 1.01, + "learning_rate": 1.6890755999719595e-05, + "loss": 3.4246, + "step": 2022400 + }, + { + "epoch": 1.01, + "learning_rate": 1.6882370052209075e-05, + "loss": 3.4044, + "step": 2022912 + }, + { + "epoch": 1.01, + "learning_rate": 1.6873984104698555e-05, + "loss": 3.4108, + "step": 2023424 + }, + { + "epoch": 1.01, + "learning_rate": 1.6865614535991768e-05, + "loss": 3.4053, + "step": 2023936 + }, + { + "epoch": 1.01, + "learning_rate": 1.6857228588481248e-05, + "loss": 3.4017, + "step": 2024448 + }, + { + "epoch": 1.01, + "learning_rate": 1.6848842640970728e-05, + "loss": 3.4005, + "step": 2024960 + }, + { + "epoch": 1.01, + "learning_rate": 1.6840456693460208e-05, + "loss": 3.4187, + "step": 2025472 + }, + { + "epoch": 1.01, + "learning_rate": 1.6832070745949684e-05, + "loss": 3.4085, + "step": 2025984 + }, + { + "epoch": 1.01, + "learning_rate": 1.6823684798439164e-05, + "loss": 3.4136, + "step": 2026496 + }, + { + "epoch": 1.01, + "learning_rate": 1.6815298850928644e-05, + "loss": 3.3884, + "step": 2027008 + }, + { + "epoch": 1.01, + "learning_rate": 1.6806912903418128e-05, + "loss": 3.3966, + "step": 2027520 + }, + { + "epoch": 1.01, + "learning_rate": 1.6798543334711337e-05, + "loss": 3.4024, + "step": 2028032 + }, + { + "epoch": 1.01, + "learning_rate": 1.6790157387200817e-05, + "loss": 3.407, + "step": 2028544 + }, + { + "epoch": 1.01, + "learning_rate": 1.6781771439690297e-05, + "loss": 3.4066, + "step": 2029056 + }, + { + "epoch": 1.01, + "learning_rate": 1.6773385492179776e-05, + "loss": 3.4089, + "step": 2029568 + }, + { + "epoch": 1.01, + "learning_rate": 1.676501592347299e-05, + "loss": 3.3919, + "step": 2030080 + }, + { + "epoch": 1.02, + "learning_rate": 1.675662997596247e-05, + "loss": 3.4033, + "step": 2030592 + }, + { + "epoch": 1.02, + "learning_rate": 1.674824402845195e-05, + "loss": 3.3963, + "step": 2031104 + }, + { + "epoch": 1.02, + "learning_rate": 1.673985808094143e-05, + "loss": 3.4003, + "step": 2031616 + }, + { + "epoch": 1.02, + "learning_rate": 1.6731488512234638e-05, + "loss": 3.4111, + "step": 2032128 + }, + { + "epoch": 1.02, + "learning_rate": 1.6723102564724118e-05, + "loss": 3.4117, + "step": 2032640 + }, + { + "epoch": 1.02, + "learning_rate": 1.6714716617213598e-05, + "loss": 3.4057, + "step": 2033152 + }, + { + "epoch": 1.02, + "learning_rate": 1.670633066970308e-05, + "loss": 3.3995, + "step": 2033664 + }, + { + "epoch": 1.02, + "learning_rate": 1.669796110099629e-05, + "loss": 3.408, + "step": 2034176 + }, + { + "epoch": 1.02, + "learning_rate": 1.668957515348577e-05, + "loss": 3.3996, + "step": 2034688 + }, + { + "epoch": 1.02, + "learning_rate": 1.668118920597525e-05, + "loss": 3.4102, + "step": 2035200 + }, + { + "epoch": 1.02, + "learning_rate": 1.667280325846473e-05, + "loss": 3.4003, + "step": 2035712 + }, + { + "epoch": 1.02, + "learning_rate": 1.6664433689757943e-05, + "loss": 3.4037, + "step": 2036224 + }, + { + "epoch": 1.02, + "learning_rate": 1.6656047742247423e-05, + "loss": 3.4035, + "step": 2036736 + }, + { + "epoch": 1.02, + "learning_rate": 1.6647661794736903e-05, + "loss": 3.4032, + "step": 2037248 + }, + { + "epoch": 1.02, + "learning_rate": 1.6639275847226383e-05, + "loss": 3.4014, + "step": 2037760 + }, + { + "epoch": 1.02, + "learning_rate": 1.663090627851959e-05, + "loss": 3.4043, + "step": 2038272 + }, + { + "epoch": 1.02, + "learning_rate": 1.662252033100907e-05, + "loss": 3.3939, + "step": 2038784 + }, + { + "epoch": 1.02, + "learning_rate": 1.661413438349855e-05, + "loss": 3.4145, + "step": 2039296 + }, + { + "epoch": 1.02, + "learning_rate": 1.6605748435988035e-05, + "loss": 3.4013, + "step": 2039808 + }, + { + "epoch": 1.02, + "learning_rate": 1.6597378867281244e-05, + "loss": 3.3988, + "step": 2040320 + }, + { + "epoch": 1.02, + "learning_rate": 1.6588992919770724e-05, + "loss": 3.3929, + "step": 2040832 + }, + { + "epoch": 1.02, + "learning_rate": 1.6580606972260204e-05, + "loss": 3.4088, + "step": 2041344 + }, + { + "epoch": 1.02, + "learning_rate": 1.6572221024749684e-05, + "loss": 3.4083, + "step": 2041856 + }, + { + "epoch": 1.02, + "learning_rate": 1.6563851456042896e-05, + "loss": 3.3999, + "step": 2042368 + }, + { + "epoch": 1.02, + "learning_rate": 1.6555465508532376e-05, + "loss": 3.406, + "step": 2042880 + }, + { + "epoch": 1.02, + "learning_rate": 1.6547079561021856e-05, + "loss": 3.4174, + "step": 2043392 + }, + { + "epoch": 1.02, + "learning_rate": 1.6538693613511336e-05, + "loss": 3.3997, + "step": 2043904 + }, + { + "epoch": 1.02, + "learning_rate": 1.6530324044804545e-05, + "loss": 3.4096, + "step": 2044416 + }, + { + "epoch": 1.02, + "learning_rate": 1.6521938097294025e-05, + "loss": 3.4044, + "step": 2044928 + }, + { + "epoch": 1.02, + "learning_rate": 1.6513552149783505e-05, + "loss": 3.4048, + "step": 2045440 + }, + { + "epoch": 1.02, + "learning_rate": 1.6505182581076718e-05, + "loss": 3.4071, + "step": 2045952 + }, + { + "epoch": 1.02, + "learning_rate": 1.6496796633566198e-05, + "loss": 3.3982, + "step": 2046464 + }, + { + "epoch": 1.02, + "learning_rate": 1.6488410686055678e-05, + "loss": 3.3995, + "step": 2046976 + }, + { + "epoch": 1.02, + "learning_rate": 1.6480024738545158e-05, + "loss": 3.4033, + "step": 2047488 + }, + { + "epoch": 1.02, + "learning_rate": 1.6471655169838367e-05, + "loss": 3.4024, + "step": 2048000 + }, + { + "epoch": 1.02, + "learning_rate": 1.646326922232785e-05, + "loss": 3.4073, + "step": 2048512 + }, + { + "epoch": 1.02, + "learning_rate": 1.645488327481733e-05, + "loss": 3.3978, + "step": 2049024 + }, + { + "epoch": 1.02, + "learning_rate": 1.644649732730681e-05, + "loss": 3.4009, + "step": 2049536 + }, + { + "epoch": 1.02, + "learning_rate": 1.643812775860002e-05, + "loss": 3.394, + "step": 2050048 + }, + { + "epoch": 1.02, + "learning_rate": 1.64297418110895e-05, + "loss": 3.4148, + "step": 2050560 + }, + { + "epoch": 1.02, + "learning_rate": 1.642135586357898e-05, + "loss": 3.4027, + "step": 2051072 + }, + { + "epoch": 1.02, + "learning_rate": 1.641296991606846e-05, + "loss": 3.4188, + "step": 2051584 + }, + { + "epoch": 1.02, + "learning_rate": 1.640460034736167e-05, + "loss": 3.3904, + "step": 2052096 + }, + { + "epoch": 1.02, + "learning_rate": 1.639621439985115e-05, + "loss": 3.4124, + "step": 2052608 + }, + { + "epoch": 1.02, + "learning_rate": 1.638782845234063e-05, + "loss": 3.4073, + "step": 2053120 + }, + { + "epoch": 1.02, + "learning_rate": 1.637945888363384e-05, + "loss": 3.4056, + "step": 2053632 + }, + { + "epoch": 1.02, + "learning_rate": 1.637107293612332e-05, + "loss": 3.4031, + "step": 2054144 + }, + { + "epoch": 1.02, + "learning_rate": 1.6362686988612804e-05, + "loss": 3.4007, + "step": 2054656 + }, + { + "epoch": 1.02, + "learning_rate": 1.6354301041102284e-05, + "loss": 3.4031, + "step": 2055168 + }, + { + "epoch": 1.02, + "learning_rate": 1.634591509359176e-05, + "loss": 3.419, + "step": 2055680 + }, + { + "epoch": 1.02, + "learning_rate": 1.633752914608124e-05, + "loss": 3.395, + "step": 2056192 + }, + { + "epoch": 1.02, + "learning_rate": 1.632914319857072e-05, + "loss": 3.4076, + "step": 2056704 + }, + { + "epoch": 1.02, + "learning_rate": 1.6320773629863933e-05, + "loss": 3.4002, + "step": 2057216 + }, + { + "epoch": 1.02, + "learning_rate": 1.6312387682353413e-05, + "loss": 3.3998, + "step": 2057728 + }, + { + "epoch": 1.02, + "learning_rate": 1.6304001734842892e-05, + "loss": 3.4026, + "step": 2058240 + }, + { + "epoch": 1.02, + "learning_rate": 1.6295615787332372e-05, + "loss": 3.3999, + "step": 2058752 + }, + { + "epoch": 1.02, + "learning_rate": 1.628724621862558e-05, + "loss": 3.4114, + "step": 2059264 + }, + { + "epoch": 1.02, + "learning_rate": 1.627886027111506e-05, + "loss": 3.4058, + "step": 2059776 + }, + { + "epoch": 1.02, + "learning_rate": 1.627047432360454e-05, + "loss": 3.401, + "step": 2060288 + }, + { + "epoch": 1.03, + "eval_loss": 3.8574743270874023, + "eval_runtime": 303.5164, + "eval_samples_per_second": 1257.234, + "eval_steps_per_second": 39.289, + "step": 2060640 + }, + { + "epoch": 0.0, + "learning_rate": 1.626208837609402e-05, + "loss": 3.4021, + "step": 2060800 + }, + { + "epoch": 0.0, + "learning_rate": 1.6253702428583505e-05, + "loss": 3.397, + "step": 2061312 + }, + { + "epoch": 0.0, + "learning_rate": 1.6245316481072985e-05, + "loss": 3.4045, + "step": 2061824 + }, + { + "epoch": 0.0, + "learning_rate": 1.6236930533562465e-05, + "loss": 3.4058, + "step": 2062336 + }, + { + "epoch": 0.0, + "learning_rate": 1.6228560964855674e-05, + "loss": 3.414, + "step": 2062848 + }, + { + "epoch": 0.0, + "learning_rate": 1.6220175017345154e-05, + "loss": 3.3944, + "step": 2063360 + }, + { + "epoch": 0.0, + "learning_rate": 1.6211789069834634e-05, + "loss": 3.4041, + "step": 2063872 + }, + { + "epoch": 0.0, + "learning_rate": 1.6203403122324114e-05, + "loss": 3.3994, + "step": 2064384 + }, + { + "epoch": 0.0, + "learning_rate": 1.6195033553617326e-05, + "loss": 3.4002, + "step": 2064896 + }, + { + "epoch": 0.0, + "learning_rate": 1.6186663984910535e-05, + "loss": 3.4022, + "step": 2065408 + }, + { + "epoch": 0.0, + "learning_rate": 1.6178278037400015e-05, + "loss": 3.4082, + "step": 2065920 + }, + { + "epoch": 0.0, + "learning_rate": 1.6169892089889495e-05, + "loss": 3.4015, + "step": 2066432 + }, + { + "epoch": 0.0, + "learning_rate": 1.6161506142378975e-05, + "loss": 3.4035, + "step": 2066944 + }, + { + "epoch": 0.0, + "learning_rate": 1.615312019486846e-05, + "loss": 3.3921, + "step": 2067456 + }, + { + "epoch": 0.0, + "learning_rate": 1.614473424735794e-05, + "loss": 3.3974, + "step": 2067968 + }, + { + "epoch": 0.0, + "learning_rate": 1.6136348299847415e-05, + "loss": 3.3875, + "step": 2068480 + }, + { + "epoch": 0.0, + "learning_rate": 1.6127962352336895e-05, + "loss": 3.4063, + "step": 2068992 + }, + { + "epoch": 0.0, + "learning_rate": 1.6119592783630107e-05, + "loss": 3.3954, + "step": 2069504 + }, + { + "epoch": 0.0, + "learning_rate": 1.6111206836119587e-05, + "loss": 3.3944, + "step": 2070016 + }, + { + "epoch": 0.0, + "learning_rate": 1.6102820888609067e-05, + "loss": 3.4076, + "step": 2070528 + }, + { + "epoch": 0.0, + "learning_rate": 1.6094434941098547e-05, + "loss": 3.4067, + "step": 2071040 + }, + { + "epoch": 0.0, + "learning_rate": 1.608606537239176e-05, + "loss": 3.4054, + "step": 2071552 + }, + { + "epoch": 0.0, + "learning_rate": 1.6077679424881236e-05, + "loss": 3.4066, + "step": 2072064 + }, + { + "epoch": 0.0, + "learning_rate": 1.6069293477370716e-05, + "loss": 3.3994, + "step": 2072576 + }, + { + "epoch": 0.0, + "learning_rate": 1.6060907529860196e-05, + "loss": 3.4022, + "step": 2073088 + }, + { + "epoch": 0.0, + "learning_rate": 1.6052537961153412e-05, + "loss": 3.406, + "step": 2073600 + }, + { + "epoch": 0.0, + "learning_rate": 1.604415201364289e-05, + "loss": 3.3939, + "step": 2074112 + }, + { + "epoch": 0.0, + "learning_rate": 1.603576606613237e-05, + "loss": 3.4031, + "step": 2074624 + }, + { + "epoch": 0.0, + "learning_rate": 1.602738011862185e-05, + "loss": 3.3941, + "step": 2075136 + }, + { + "epoch": 0.0, + "learning_rate": 1.601901054991506e-05, + "loss": 3.3897, + "step": 2075648 + }, + { + "epoch": 0.01, + "learning_rate": 1.6010624602404538e-05, + "loss": 3.3956, + "step": 2076160 + }, + { + "epoch": 0.01, + "learning_rate": 1.600223865489402e-05, + "loss": 3.4056, + "step": 2076672 + }, + { + "epoch": 0.01, + "learning_rate": 1.59938527073835e-05, + "loss": 3.4045, + "step": 2077184 + }, + { + "epoch": 0.01, + "learning_rate": 1.598548313867671e-05, + "loss": 3.4066, + "step": 2077696 + }, + { + "epoch": 0.01, + "learning_rate": 1.597709719116619e-05, + "loss": 3.3955, + "step": 2078208 + }, + { + "epoch": 0.01, + "learning_rate": 1.596871124365567e-05, + "loss": 3.3921, + "step": 2078720 + }, + { + "epoch": 0.01, + "learning_rate": 1.596032529614515e-05, + "loss": 3.4076, + "step": 2079232 + }, + { + "epoch": 0.01, + "learning_rate": 1.5951955727438362e-05, + "loss": 3.3975, + "step": 2079744 + }, + { + "epoch": 0.01, + "learning_rate": 1.5943569779927842e-05, + "loss": 3.3977, + "step": 2080256 + }, + { + "epoch": 0.01, + "learning_rate": 1.5935183832417322e-05, + "loss": 3.3883, + "step": 2080768 + }, + { + "epoch": 0.01, + "learning_rate": 1.5926797884906802e-05, + "loss": 3.3946, + "step": 2081280 + }, + { + "epoch": 0.01, + "learning_rate": 1.5918444695003744e-05, + "loss": 3.3992, + "step": 2081792 + }, + { + "epoch": 0.01, + "learning_rate": 1.5910058747493227e-05, + "loss": 3.4086, + "step": 2082304 + }, + { + "epoch": 0.01, + "learning_rate": 1.5901672799982707e-05, + "loss": 3.4012, + "step": 2082816 + }, + { + "epoch": 0.01, + "learning_rate": 1.5893286852472184e-05, + "loss": 3.3982, + "step": 2083328 + }, + { + "epoch": 0.01, + "learning_rate": 1.5884900904961664e-05, + "loss": 3.4014, + "step": 2083840 + }, + { + "epoch": 0.01, + "learning_rate": 1.5876514957451144e-05, + "loss": 3.3973, + "step": 2084352 + }, + { + "epoch": 0.01, + "learning_rate": 1.5868129009940624e-05, + "loss": 3.3959, + "step": 2084864 + }, + { + "epoch": 0.01, + "learning_rate": 1.5859743062430104e-05, + "loss": 3.3772, + "step": 2085376 + }, + { + "epoch": 0.01, + "learning_rate": 1.5851373493723316e-05, + "loss": 3.4036, + "step": 2085888 + }, + { + "epoch": 0.01, + "learning_rate": 1.5842987546212796e-05, + "loss": 3.3937, + "step": 2086400 + }, + { + "epoch": 0.01, + "learning_rate": 1.5834601598702276e-05, + "loss": 3.4055, + "step": 2086912 + }, + { + "epoch": 0.01, + "learning_rate": 1.5826215651191756e-05, + "loss": 3.394, + "step": 2087424 + }, + { + "epoch": 0.01, + "learning_rate": 1.5817846082484965e-05, + "loss": 3.3888, + "step": 2087936 + }, + { + "epoch": 0.01, + "learning_rate": 1.5809460134974445e-05, + "loss": 3.3875, + "step": 2088448 + }, + { + "epoch": 0.01, + "learning_rate": 1.5801074187463928e-05, + "loss": 3.3844, + "step": 2088960 + }, + { + "epoch": 0.01, + "learning_rate": 1.5792688239953408e-05, + "loss": 3.4012, + "step": 2089472 + }, + { + "epoch": 0.01, + "learning_rate": 1.5784318671246617e-05, + "loss": 3.3795, + "step": 2089984 + }, + { + "epoch": 0.01, + "learning_rate": 1.5775932723736097e-05, + "loss": 3.4055, + "step": 2090496 + }, + { + "epoch": 0.01, + "learning_rate": 1.5767546776225577e-05, + "loss": 3.3929, + "step": 2091008 + }, + { + "epoch": 0.01, + "learning_rate": 1.575917720751879e-05, + "loss": 3.39, + "step": 2091520 + }, + { + "epoch": 0.01, + "learning_rate": 1.575079126000827e-05, + "loss": 3.4112, + "step": 2092032 + }, + { + "epoch": 0.01, + "learning_rate": 1.574240531249775e-05, + "loss": 3.3888, + "step": 2092544 + }, + { + "epoch": 0.01, + "learning_rate": 1.573401936498723e-05, + "loss": 3.3845, + "step": 2093056 + }, + { + "epoch": 0.01, + "learning_rate": 1.572564979628044e-05, + "loss": 3.396, + "step": 2093568 + }, + { + "epoch": 0.01, + "learning_rate": 1.571726384876992e-05, + "loss": 3.3978, + "step": 2094080 + }, + { + "epoch": 0.01, + "learning_rate": 1.57088779012594e-05, + "loss": 3.3829, + "step": 2094592 + }, + { + "epoch": 0.01, + "learning_rate": 1.5700491953748882e-05, + "loss": 3.3934, + "step": 2095104 + }, + { + "epoch": 0.01, + "learning_rate": 1.569212238504209e-05, + "loss": 3.3838, + "step": 2095616 + }, + { + "epoch": 0.01, + "learning_rate": 1.568373643753157e-05, + "loss": 3.3913, + "step": 2096128 + }, + { + "epoch": 0.01, + "learning_rate": 1.567535049002105e-05, + "loss": 3.3998, + "step": 2096640 + }, + { + "epoch": 0.01, + "learning_rate": 1.566696454251053e-05, + "loss": 3.399, + "step": 2097152 + }, + { + "epoch": 0.01, + "learning_rate": 1.5658594973803743e-05, + "loss": 3.4002, + "step": 2097664 + }, + { + "epoch": 0.01, + "learning_rate": 1.5650225405096952e-05, + "loss": 3.4013, + "step": 2098176 + }, + { + "epoch": 0.01, + "learning_rate": 1.5641839457586432e-05, + "loss": 3.4137, + "step": 2098688 + }, + { + "epoch": 0.01, + "learning_rate": 1.5633453510075912e-05, + "loss": 3.3958, + "step": 2099200 + }, + { + "epoch": 0.01, + "learning_rate": 1.5625067562565392e-05, + "loss": 3.404, + "step": 2099712 + }, + { + "epoch": 0.01, + "learning_rate": 1.5616697993858605e-05, + "loss": 3.3953, + "step": 2100224 + }, + { + "epoch": 0.01, + "learning_rate": 1.5608312046348085e-05, + "loss": 3.3921, + "step": 2100736 + }, + { + "epoch": 0.01, + "learning_rate": 1.5599926098837565e-05, + "loss": 3.3933, + "step": 2101248 + }, + { + "epoch": 0.01, + "learning_rate": 1.5591540151327045e-05, + "loss": 3.4059, + "step": 2101760 + }, + { + "epoch": 0.01, + "learning_rate": 1.5583154203816525e-05, + "loss": 3.4006, + "step": 2102272 + }, + { + "epoch": 0.01, + "learning_rate": 1.5574768256306005e-05, + "loss": 3.4027, + "step": 2102784 + }, + { + "epoch": 0.01, + "learning_rate": 1.5566382308795485e-05, + "loss": 3.3837, + "step": 2103296 + }, + { + "epoch": 0.01, + "learning_rate": 1.555799636128496e-05, + "loss": 3.3873, + "step": 2103808 + }, + { + "epoch": 0.01, + "learning_rate": 1.5549626792578177e-05, + "loss": 3.3919, + "step": 2104320 + }, + { + "epoch": 0.01, + "learning_rate": 1.5541240845067657e-05, + "loss": 3.3932, + "step": 2104832 + }, + { + "epoch": 0.01, + "learning_rate": 1.5532854897557134e-05, + "loss": 3.3958, + "step": 2105344 + }, + { + "epoch": 0.01, + "learning_rate": 1.5524468950046613e-05, + "loss": 3.3994, + "step": 2105856 + }, + { + "epoch": 0.01, + "learning_rate": 1.5516099381339826e-05, + "loss": 3.388, + "step": 2106368 + }, + { + "epoch": 0.02, + "learning_rate": 1.5507713433829306e-05, + "loss": 3.391, + "step": 2106880 + }, + { + "epoch": 0.02, + "learning_rate": 1.5499327486318786e-05, + "loss": 3.3866, + "step": 2107392 + }, + { + "epoch": 0.02, + "learning_rate": 1.5490941538808266e-05, + "loss": 3.3891, + "step": 2107904 + }, + { + "epoch": 0.02, + "learning_rate": 1.548257197010148e-05, + "loss": 3.4019, + "step": 2108416 + }, + { + "epoch": 0.02, + "learning_rate": 1.5474186022590958e-05, + "loss": 3.4046, + "step": 2108928 + }, + { + "epoch": 0.02, + "learning_rate": 1.5465800075080435e-05, + "loss": 3.3983, + "step": 2109440 + }, + { + "epoch": 0.02, + "learning_rate": 1.5457414127569915e-05, + "loss": 3.3865, + "step": 2109952 + }, + { + "epoch": 0.02, + "learning_rate": 1.544904455886313e-05, + "loss": 3.3992, + "step": 2110464 + }, + { + "epoch": 0.02, + "learning_rate": 1.5440658611352607e-05, + "loss": 3.3896, + "step": 2110976 + }, + { + "epoch": 0.02, + "learning_rate": 1.5432272663842087e-05, + "loss": 3.399, + "step": 2111488 + }, + { + "epoch": 0.02, + "learning_rate": 1.5423886716331567e-05, + "loss": 3.3933, + "step": 2112000 + }, + { + "epoch": 0.02, + "learning_rate": 1.541551714762478e-05, + "loss": 3.3913, + "step": 2112512 + }, + { + "epoch": 0.02, + "learning_rate": 1.540713120011426e-05, + "loss": 3.3969, + "step": 2113024 + }, + { + "epoch": 0.02, + "learning_rate": 1.539874525260374e-05, + "loss": 3.391, + "step": 2113536 + }, + { + "epoch": 0.02, + "learning_rate": 1.539035930509322e-05, + "loss": 3.3937, + "step": 2114048 + }, + { + "epoch": 0.02, + "learning_rate": 1.5381989736386432e-05, + "loss": 3.3899, + "step": 2114560 + }, + { + "epoch": 0.02, + "learning_rate": 1.537360378887591e-05, + "loss": 3.3867, + "step": 2115072 + }, + { + "epoch": 0.02, + "learning_rate": 1.536521784136539e-05, + "loss": 3.4037, + "step": 2115584 + }, + { + "epoch": 0.02, + "learning_rate": 1.535683189385487e-05, + "loss": 3.3938, + "step": 2116096 + }, + { + "epoch": 0.02, + "learning_rate": 1.534846232514808e-05, + "loss": 3.387, + "step": 2116608 + }, + { + "epoch": 0.02, + "learning_rate": 1.534007637763756e-05, + "loss": 3.386, + "step": 2117120 + }, + { + "epoch": 0.02, + "learning_rate": 1.533169043012704e-05, + "loss": 3.3936, + "step": 2117632 + }, + { + "epoch": 0.02, + "learning_rate": 1.532330448261652e-05, + "loss": 3.4014, + "step": 2118144 + }, + { + "epoch": 0.02, + "learning_rate": 1.531493491390973e-05, + "loss": 3.3866, + "step": 2118656 + }, + { + "epoch": 0.02, + "learning_rate": 1.5306548966399213e-05, + "loss": 3.3967, + "step": 2119168 + }, + { + "epoch": 0.02, + "learning_rate": 1.5298179397692426e-05, + "loss": 3.4064, + "step": 2119680 + }, + { + "epoch": 0.02, + "learning_rate": 1.5289793450181902e-05, + "loss": 3.3967, + "step": 2120192 + }, + { + "epoch": 0.02, + "learning_rate": 1.5281407502671382e-05, + "loss": 3.3952, + "step": 2120704 + }, + { + "epoch": 0.02, + "learning_rate": 1.5273021555160862e-05, + "loss": 3.4003, + "step": 2121216 + }, + { + "epoch": 0.02, + "learning_rate": 1.5264635607650342e-05, + "loss": 3.3964, + "step": 2121728 + }, + { + "epoch": 0.02, + "learning_rate": 1.5256249660139824e-05, + "loss": 3.3956, + "step": 2122240 + }, + { + "epoch": 0.02, + "learning_rate": 1.5247863712629304e-05, + "loss": 3.3866, + "step": 2122752 + }, + { + "epoch": 0.02, + "learning_rate": 1.5239477765118784e-05, + "loss": 3.3883, + "step": 2123264 + }, + { + "epoch": 0.02, + "learning_rate": 1.5231108196411995e-05, + "loss": 3.3918, + "step": 2123776 + }, + { + "epoch": 0.02, + "learning_rate": 1.5222722248901474e-05, + "loss": 3.3938, + "step": 2124288 + }, + { + "epoch": 0.02, + "learning_rate": 1.5214336301390954e-05, + "loss": 3.393, + "step": 2124800 + }, + { + "epoch": 0.02, + "learning_rate": 1.5205966732684165e-05, + "loss": 3.3934, + "step": 2125312 + }, + { + "epoch": 0.02, + "learning_rate": 1.5197580785173645e-05, + "loss": 3.3853, + "step": 2125824 + }, + { + "epoch": 0.02, + "learning_rate": 1.5189194837663127e-05, + "loss": 3.3845, + "step": 2126336 + }, + { + "epoch": 0.02, + "learning_rate": 1.5180808890152607e-05, + "loss": 3.4045, + "step": 2126848 + }, + { + "epoch": 0.02, + "learning_rate": 1.5172422942642083e-05, + "loss": 3.3937, + "step": 2127360 + }, + { + "epoch": 0.02, + "learning_rate": 1.5164036995131565e-05, + "loss": 3.4098, + "step": 2127872 + }, + { + "epoch": 0.02, + "learning_rate": 1.5155651047621045e-05, + "loss": 3.3812, + "step": 2128384 + }, + { + "epoch": 0.02, + "learning_rate": 1.5147265100110525e-05, + "loss": 3.4027, + "step": 2128896 + }, + { + "epoch": 0.02, + "learning_rate": 1.5138895531403736e-05, + "loss": 3.3995, + "step": 2129408 + }, + { + "epoch": 0.02, + "learning_rate": 1.5130525962696948e-05, + "loss": 3.3968, + "step": 2129920 + }, + { + "epoch": 0.02, + "learning_rate": 1.5122140015186428e-05, + "loss": 3.3893, + "step": 2130432 + }, + { + "epoch": 0.02, + "learning_rate": 1.5113754067675908e-05, + "loss": 3.3954, + "step": 2130944 + }, + { + "epoch": 0.02, + "learning_rate": 1.5105368120165386e-05, + "loss": 3.3937, + "step": 2131456 + }, + { + "epoch": 0.02, + "learning_rate": 1.5096982172654866e-05, + "loss": 3.4032, + "step": 2131968 + }, + { + "epoch": 0.02, + "learning_rate": 1.5088596225144346e-05, + "loss": 3.3888, + "step": 2132480 + }, + { + "epoch": 0.02, + "learning_rate": 1.5080210277633828e-05, + "loss": 3.393, + "step": 2132992 + }, + { + "epoch": 0.02, + "learning_rate": 1.5071824330123308e-05, + "loss": 3.3946, + "step": 2133504 + }, + { + "epoch": 0.02, + "learning_rate": 1.5063454761416517e-05, + "loss": 3.3904, + "step": 2134016 + }, + { + "epoch": 0.02, + "learning_rate": 1.5055068813905999e-05, + "loss": 3.3904, + "step": 2134528 + }, + { + "epoch": 0.02, + "learning_rate": 1.5046682866395479e-05, + "loss": 3.3956, + "step": 2135040 + }, + { + "epoch": 0.02, + "learning_rate": 1.503831329768869e-05, + "loss": 3.399, + "step": 2135552 + }, + { + "epoch": 0.02, + "learning_rate": 1.502992735017817e-05, + "loss": 3.3952, + "step": 2136064 + }, + { + "epoch": 0.02, + "learning_rate": 1.502154140266765e-05, + "loss": 3.393, + "step": 2136576 + }, + { + "epoch": 0.03, + "eval_loss": 3.8583056926727295, + "eval_runtime": 303.5184, + "eval_samples_per_second": 1257.225, + "eval_steps_per_second": 39.289, + "step": 2136960 + }, + { + "epoch": 1.0, + "learning_rate": 1.501315545515713e-05, + "loss": 3.3908, + "step": 2137088 + }, + { + "epoch": 1.0, + "learning_rate": 1.500478588645034e-05, + "loss": 3.3836, + "step": 2137600 + }, + { + "epoch": 1.0, + "learning_rate": 1.499639993893982e-05, + "loss": 3.3973, + "step": 2138112 + }, + { + "epoch": 1.0, + "learning_rate": 1.49880139914293e-05, + "loss": 3.3967, + "step": 2138624 + }, + { + "epoch": 1.0, + "learning_rate": 1.4979628043918782e-05, + "loss": 3.3979, + "step": 2139136 + }, + { + "epoch": 1.0, + "learning_rate": 1.497125847521199e-05, + "loss": 3.3918, + "step": 2139648 + }, + { + "epoch": 1.0, + "learning_rate": 1.496287252770147e-05, + "loss": 3.3948, + "step": 2140160 + }, + { + "epoch": 1.0, + "learning_rate": 1.4954486580190952e-05, + "loss": 3.3895, + "step": 2140672 + }, + { + "epoch": 1.0, + "learning_rate": 1.4946100632680432e-05, + "loss": 3.3862, + "step": 2141184 + }, + { + "epoch": 1.0, + "learning_rate": 1.4937731063973643e-05, + "loss": 3.3941, + "step": 2141696 + }, + { + "epoch": 1.0, + "learning_rate": 1.4929345116463123e-05, + "loss": 3.4008, + "step": 2142208 + }, + { + "epoch": 1.0, + "learning_rate": 1.4920959168952603e-05, + "loss": 3.3906, + "step": 2142720 + }, + { + "epoch": 1.0, + "learning_rate": 1.4912573221442083e-05, + "loss": 3.3972, + "step": 2143232 + }, + { + "epoch": 1.0, + "learning_rate": 1.4904203652735294e-05, + "loss": 3.3778, + "step": 2143744 + }, + { + "epoch": 1.0, + "learning_rate": 1.4895817705224774e-05, + "loss": 3.3853, + "step": 2144256 + }, + { + "epoch": 1.0, + "learning_rate": 1.4887431757714254e-05, + "loss": 3.3813, + "step": 2144768 + }, + { + "epoch": 1.0, + "learning_rate": 1.4879045810203735e-05, + "loss": 3.3977, + "step": 2145280 + }, + { + "epoch": 1.0, + "learning_rate": 1.4870676241496944e-05, + "loss": 3.3869, + "step": 2145792 + }, + { + "epoch": 1.0, + "learning_rate": 1.4862290293986424e-05, + "loss": 3.384, + "step": 2146304 + }, + { + "epoch": 1.0, + "learning_rate": 1.4853904346475906e-05, + "loss": 3.3957, + "step": 2146816 + }, + { + "epoch": 1.0, + "learning_rate": 1.4845518398965386e-05, + "loss": 3.3977, + "step": 2147328 + }, + { + "epoch": 1.0, + "learning_rate": 1.4837148830258597e-05, + "loss": 3.3998, + "step": 2147840 + }, + { + "epoch": 1.0, + "learning_rate": 1.4828762882748077e-05, + "loss": 3.395, + "step": 2148352 + }, + { + "epoch": 1.0, + "learning_rate": 1.4820376935237557e-05, + "loss": 3.3903, + "step": 2148864 + }, + { + "epoch": 1.0, + "learning_rate": 1.4811990987727037e-05, + "loss": 3.3961, + "step": 2149376 + }, + { + "epoch": 1.0, + "learning_rate": 1.4803621419020247e-05, + "loss": 3.396, + "step": 2149888 + }, + { + "epoch": 1.0, + "learning_rate": 1.4795235471509727e-05, + "loss": 3.3842, + "step": 2150400 + }, + { + "epoch": 1.0, + "learning_rate": 1.4786849523999207e-05, + "loss": 3.3946, + "step": 2150912 + }, + { + "epoch": 1.0, + "learning_rate": 1.4778463576488686e-05, + "loss": 3.3834, + "step": 2151424 + }, + { + "epoch": 1.0, + "learning_rate": 1.4770094007781898e-05, + "loss": 3.3809, + "step": 2151936 + }, + { + "epoch": 1.01, + "learning_rate": 1.4761708060271378e-05, + "loss": 3.3886, + "step": 2152448 + }, + { + "epoch": 1.01, + "learning_rate": 1.475332211276086e-05, + "loss": 3.3924, + "step": 2152960 + }, + { + "epoch": 1.01, + "learning_rate": 1.4744936165250336e-05, + "loss": 3.3964, + "step": 2153472 + }, + { + "epoch": 1.01, + "learning_rate": 1.473656659654355e-05, + "loss": 3.3984, + "step": 2153984 + }, + { + "epoch": 1.01, + "learning_rate": 1.472818064903303e-05, + "loss": 3.3865, + "step": 2154496 + }, + { + "epoch": 1.01, + "learning_rate": 1.471979470152251e-05, + "loss": 3.3819, + "step": 2155008 + }, + { + "epoch": 1.01, + "learning_rate": 1.4711408754011987e-05, + "loss": 3.3976, + "step": 2155520 + }, + { + "epoch": 1.01, + "learning_rate": 1.4703039185305201e-05, + "loss": 3.3849, + "step": 2156032 + }, + { + "epoch": 1.01, + "learning_rate": 1.4694653237794681e-05, + "loss": 3.3869, + "step": 2156544 + }, + { + "epoch": 1.01, + "learning_rate": 1.468626729028416e-05, + "loss": 3.3812, + "step": 2157056 + }, + { + "epoch": 1.01, + "learning_rate": 1.467788134277364e-05, + "loss": 3.3827, + "step": 2157568 + }, + { + "epoch": 1.01, + "learning_rate": 1.4669528152870583e-05, + "loss": 3.389, + "step": 2158080 + }, + { + "epoch": 1.01, + "learning_rate": 1.4661142205360062e-05, + "loss": 3.3981, + "step": 2158592 + }, + { + "epoch": 1.01, + "learning_rate": 1.4652756257849542e-05, + "loss": 3.3899, + "step": 2159104 + }, + { + "epoch": 1.01, + "learning_rate": 1.4644370310339022e-05, + "loss": 3.3862, + "step": 2159616 + }, + { + "epoch": 1.01, + "learning_rate": 1.4635984362828502e-05, + "loss": 3.3912, + "step": 2160128 + }, + { + "epoch": 1.01, + "learning_rate": 1.462759841531798e-05, + "loss": 3.388, + "step": 2160640 + }, + { + "epoch": 1.01, + "learning_rate": 1.461921246780746e-05, + "loss": 3.3882, + "step": 2161152 + }, + { + "epoch": 1.01, + "learning_rate": 1.461082652029694e-05, + "loss": 3.3675, + "step": 2161664 + }, + { + "epoch": 1.01, + "learning_rate": 1.4602456951590155e-05, + "loss": 3.3934, + "step": 2162176 + }, + { + "epoch": 1.01, + "learning_rate": 1.4594071004079631e-05, + "loss": 3.383, + "step": 2162688 + }, + { + "epoch": 1.01, + "learning_rate": 1.4585701435372845e-05, + "loss": 3.398, + "step": 2163200 + }, + { + "epoch": 1.01, + "learning_rate": 1.4577315487862325e-05, + "loss": 3.3828, + "step": 2163712 + }, + { + "epoch": 1.01, + "learning_rate": 1.4568929540351805e-05, + "loss": 3.382, + "step": 2164224 + }, + { + "epoch": 1.01, + "learning_rate": 1.4560543592841284e-05, + "loss": 3.3778, + "step": 2164736 + }, + { + "epoch": 1.01, + "learning_rate": 1.4552157645330764e-05, + "loss": 3.3754, + "step": 2165248 + }, + { + "epoch": 1.01, + "learning_rate": 1.4543771697820244e-05, + "loss": 3.3902, + "step": 2165760 + }, + { + "epoch": 1.01, + "learning_rate": 1.4535385750309723e-05, + "loss": 3.3712, + "step": 2166272 + }, + { + "epoch": 1.01, + "learning_rate": 1.4526999802799205e-05, + "loss": 3.3965, + "step": 2166784 + }, + { + "epoch": 1.01, + "learning_rate": 1.4518630234092414e-05, + "loss": 3.3821, + "step": 2167296 + }, + { + "epoch": 1.01, + "learning_rate": 1.4510244286581894e-05, + "loss": 3.3764, + "step": 2167808 + }, + { + "epoch": 1.01, + "learning_rate": 1.4501858339071376e-05, + "loss": 3.4032, + "step": 2168320 + }, + { + "epoch": 1.01, + "learning_rate": 1.4493472391560856e-05, + "loss": 3.3754, + "step": 2168832 + }, + { + "epoch": 1.01, + "learning_rate": 1.4485102822854067e-05, + "loss": 3.3741, + "step": 2169344 + }, + { + "epoch": 1.01, + "learning_rate": 1.4476716875343547e-05, + "loss": 3.3873, + "step": 2169856 + }, + { + "epoch": 1.01, + "learning_rate": 1.4468330927833027e-05, + "loss": 3.3889, + "step": 2170368 + }, + { + "epoch": 1.01, + "learning_rate": 1.4459944980322506e-05, + "loss": 3.3755, + "step": 2170880 + }, + { + "epoch": 1.01, + "learning_rate": 1.4451575411615717e-05, + "loss": 3.3855, + "step": 2171392 + }, + { + "epoch": 1.01, + "learning_rate": 1.4443189464105197e-05, + "loss": 3.3709, + "step": 2171904 + }, + { + "epoch": 1.01, + "learning_rate": 1.4434819895398408e-05, + "loss": 3.3833, + "step": 2172416 + }, + { + "epoch": 1.01, + "learning_rate": 1.4426433947887888e-05, + "loss": 3.388, + "step": 2172928 + }, + { + "epoch": 1.01, + "learning_rate": 1.4418048000377368e-05, + "loss": 3.3902, + "step": 2173440 + }, + { + "epoch": 1.01, + "learning_rate": 1.4409662052866848e-05, + "loss": 3.3877, + "step": 2173952 + }, + { + "epoch": 1.01, + "learning_rate": 1.440127610535633e-05, + "loss": 3.3895, + "step": 2174464 + }, + { + "epoch": 1.01, + "learning_rate": 1.439289015784581e-05, + "loss": 3.4064, + "step": 2174976 + }, + { + "epoch": 1.01, + "learning_rate": 1.4384504210335286e-05, + "loss": 3.3844, + "step": 2175488 + }, + { + "epoch": 1.01, + "learning_rate": 1.4376118262824768e-05, + "loss": 3.3968, + "step": 2176000 + }, + { + "epoch": 1.01, + "learning_rate": 1.436776507292171e-05, + "loss": 3.384, + "step": 2176512 + }, + { + "epoch": 1.01, + "learning_rate": 1.4359379125411191e-05, + "loss": 3.3843, + "step": 2177024 + }, + { + "epoch": 1.01, + "learning_rate": 1.4350993177900671e-05, + "loss": 3.3787, + "step": 2177536 + }, + { + "epoch": 1.01, + "learning_rate": 1.4342607230390151e-05, + "loss": 3.3958, + "step": 2178048 + }, + { + "epoch": 1.01, + "learning_rate": 1.433422128287963e-05, + "loss": 3.3875, + "step": 2178560 + }, + { + "epoch": 1.01, + "learning_rate": 1.4325835335369109e-05, + "loss": 3.3958, + "step": 2179072 + }, + { + "epoch": 1.01, + "learning_rate": 1.4317449387858589e-05, + "loss": 3.3742, + "step": 2179584 + }, + { + "epoch": 1.01, + "learning_rate": 1.4309063440348069e-05, + "loss": 3.3747, + "step": 2180096 + }, + { + "epoch": 1.01, + "learning_rate": 1.4300693871641283e-05, + "loss": 3.3802, + "step": 2180608 + }, + { + "epoch": 1.01, + "learning_rate": 1.429230792413076e-05, + "loss": 3.3907, + "step": 2181120 + }, + { + "epoch": 1.01, + "learning_rate": 1.428392197662024e-05, + "loss": 3.385, + "step": 2181632 + }, + { + "epoch": 1.01, + "learning_rate": 1.4275552407913454e-05, + "loss": 3.3895, + "step": 2182144 + }, + { + "epoch": 1.01, + "learning_rate": 1.4267166460402934e-05, + "loss": 3.3797, + "step": 2182656 + }, + { + "epoch": 1.02, + "learning_rate": 1.425878051289241e-05, + "loss": 3.3788, + "step": 2183168 + }, + { + "epoch": 1.02, + "learning_rate": 1.4250394565381892e-05, + "loss": 3.3766, + "step": 2183680 + }, + { + "epoch": 1.02, + "learning_rate": 1.4242024996675105e-05, + "loss": 3.3797, + "step": 2184192 + }, + { + "epoch": 1.02, + "learning_rate": 1.4233639049164583e-05, + "loss": 3.3885, + "step": 2184704 + }, + { + "epoch": 1.02, + "learning_rate": 1.4225253101654063e-05, + "loss": 3.398, + "step": 2185216 + }, + { + "epoch": 1.02, + "learning_rate": 1.4216867154143543e-05, + "loss": 3.3895, + "step": 2185728 + }, + { + "epoch": 1.02, + "learning_rate": 1.4208497585436755e-05, + "loss": 3.3796, + "step": 2186240 + }, + { + "epoch": 1.02, + "learning_rate": 1.4200111637926233e-05, + "loss": 3.3851, + "step": 2186752 + }, + { + "epoch": 1.02, + "learning_rate": 1.4191725690415713e-05, + "loss": 3.3814, + "step": 2187264 + }, + { + "epoch": 1.02, + "learning_rate": 1.4183339742905193e-05, + "loss": 3.3898, + "step": 2187776 + }, + { + "epoch": 1.02, + "learning_rate": 1.4174970174198408e-05, + "loss": 3.3807, + "step": 2188288 + }, + { + "epoch": 1.02, + "learning_rate": 1.4166584226687884e-05, + "loss": 3.3793, + "step": 2188800 + }, + { + "epoch": 1.02, + "learning_rate": 1.4158198279177364e-05, + "loss": 3.3878, + "step": 2189312 + }, + { + "epoch": 1.02, + "learning_rate": 1.4149812331666846e-05, + "loss": 3.3842, + "step": 2189824 + }, + { + "epoch": 1.02, + "learning_rate": 1.4141442762960055e-05, + "loss": 3.3839, + "step": 2190336 + }, + { + "epoch": 1.02, + "learning_rate": 1.4133056815449536e-05, + "loss": 3.3813, + "step": 2190848 + }, + { + "epoch": 1.02, + "learning_rate": 1.4124670867939016e-05, + "loss": 3.3772, + "step": 2191360 + }, + { + "epoch": 1.02, + "learning_rate": 1.4116284920428496e-05, + "loss": 3.3894, + "step": 2191872 + }, + { + "epoch": 1.02, + "learning_rate": 1.4107898972917976e-05, + "loss": 3.3859, + "step": 2192384 + }, + { + "epoch": 1.02, + "learning_rate": 1.4099513025407456e-05, + "loss": 3.3776, + "step": 2192896 + }, + { + "epoch": 1.02, + "learning_rate": 1.4091127077896938e-05, + "loss": 3.3729, + "step": 2193408 + }, + { + "epoch": 1.02, + "learning_rate": 1.4082757509190147e-05, + "loss": 3.3839, + "step": 2193920 + }, + { + "epoch": 1.02, + "learning_rate": 1.4074371561679629e-05, + "loss": 3.3945, + "step": 2194432 + }, + { + "epoch": 1.02, + "learning_rate": 1.4065985614169109e-05, + "loss": 3.3804, + "step": 2194944 + }, + { + "epoch": 1.02, + "learning_rate": 1.4057599666658585e-05, + "loss": 3.3844, + "step": 2195456 + }, + { + "epoch": 1.02, + "learning_rate": 1.40492300979518e-05, + "loss": 3.3951, + "step": 2195968 + }, + { + "epoch": 1.02, + "learning_rate": 1.404084415044128e-05, + "loss": 3.3886, + "step": 2196480 + }, + { + "epoch": 1.02, + "learning_rate": 1.403245820293076e-05, + "loss": 3.3854, + "step": 2196992 + }, + { + "epoch": 1.02, + "learning_rate": 1.4024072255420238e-05, + "loss": 3.3893, + "step": 2197504 + }, + { + "epoch": 1.02, + "learning_rate": 1.401570268671345e-05, + "loss": 3.3886, + "step": 2198016 + }, + { + "epoch": 1.02, + "learning_rate": 1.400731673920293e-05, + "loss": 3.3907, + "step": 2198528 + }, + { + "epoch": 1.02, + "learning_rate": 1.399893079169241e-05, + "loss": 3.375, + "step": 2199040 + }, + { + "epoch": 1.02, + "learning_rate": 1.3990544844181888e-05, + "loss": 3.3823, + "step": 2199552 + }, + { + "epoch": 1.02, + "learning_rate": 1.3982158896671368e-05, + "loss": 3.3802, + "step": 2200064 + }, + { + "epoch": 1.02, + "learning_rate": 1.3973772949160848e-05, + "loss": 3.385, + "step": 2200576 + }, + { + "epoch": 1.02, + "learning_rate": 1.396538700165033e-05, + "loss": 3.3869, + "step": 2201088 + }, + { + "epoch": 1.02, + "learning_rate": 1.3957017432943539e-05, + "loss": 3.382, + "step": 2201600 + }, + { + "epoch": 1.02, + "learning_rate": 1.3948631485433019e-05, + "loss": 3.3721, + "step": 2202112 + }, + { + "epoch": 1.02, + "learning_rate": 1.39402455379225e-05, + "loss": 3.3773, + "step": 2202624 + }, + { + "epoch": 1.02, + "learning_rate": 1.393185959041198e-05, + "loss": 3.3947, + "step": 2203136 + }, + { + "epoch": 1.02, + "learning_rate": 1.392347364290146e-05, + "loss": 3.3874, + "step": 2203648 + }, + { + "epoch": 1.02, + "learning_rate": 1.391508769539094e-05, + "loss": 3.3964, + "step": 2204160 + }, + { + "epoch": 1.02, + "learning_rate": 1.3906701747880419e-05, + "loss": 3.3762, + "step": 2204672 + }, + { + "epoch": 1.02, + "learning_rate": 1.3898315800369899e-05, + "loss": 3.3899, + "step": 2205184 + }, + { + "epoch": 1.02, + "learning_rate": 1.3889946231663111e-05, + "loss": 3.3939, + "step": 2205696 + }, + { + "epoch": 1.02, + "learning_rate": 1.3881576662956322e-05, + "loss": 3.3839, + "step": 2206208 + }, + { + "epoch": 1.02, + "learning_rate": 1.3873190715445802e-05, + "loss": 3.3762, + "step": 2206720 + }, + { + "epoch": 1.02, + "learning_rate": 1.3864804767935283e-05, + "loss": 3.3853, + "step": 2207232 + }, + { + "epoch": 1.02, + "learning_rate": 1.3856418820424763e-05, + "loss": 3.3875, + "step": 2207744 + }, + { + "epoch": 1.02, + "learning_rate": 1.384803287291424e-05, + "loss": 3.394, + "step": 2208256 + }, + { + "epoch": 1.02, + "learning_rate": 1.3839646925403722e-05, + "loss": 3.3809, + "step": 2208768 + }, + { + "epoch": 1.02, + "learning_rate": 1.3831260977893202e-05, + "loss": 3.3798, + "step": 2209280 + }, + { + "epoch": 1.02, + "learning_rate": 1.3822875030382682e-05, + "loss": 3.3851, + "step": 2209792 + }, + { + "epoch": 1.02, + "learning_rate": 1.3814505461675892e-05, + "loss": 3.3852, + "step": 2210304 + }, + { + "epoch": 1.02, + "learning_rate": 1.3806119514165372e-05, + "loss": 3.3776, + "step": 2210816 + }, + { + "epoch": 1.02, + "learning_rate": 1.3797733566654852e-05, + "loss": 3.389, + "step": 2211328 + }, + { + "epoch": 1.02, + "learning_rate": 1.3789347619144332e-05, + "loss": 3.384, + "step": 2211840 + }, + { + "epoch": 1.02, + "learning_rate": 1.3780978050437543e-05, + "loss": 3.3906, + "step": 2212352 + }, + { + "epoch": 1.02, + "learning_rate": 1.3772592102927023e-05, + "loss": 3.3814, + "step": 2212864 + }, + { + "epoch": 1.03, + "eval_loss": 3.860208511352539, + "eval_runtime": 301.8797, + "eval_samples_per_second": 1264.05, + "eval_steps_per_second": 39.502, + "step": 2213280 + }, + { + "epoch": 0.0, + "learning_rate": 1.3764206155416503e-05, + "loss": 3.3916, + "step": 2213376 + }, + { + "epoch": 0.0, + "learning_rate": 1.3755820207905985e-05, + "loss": 3.3724, + "step": 2213888 + }, + { + "epoch": 0.0, + "learning_rate": 1.3747434260395464e-05, + "loss": 3.3864, + "step": 2214400 + }, + { + "epoch": 0.0, + "learning_rate": 1.3739048312884944e-05, + "loss": 3.3885, + "step": 2214912 + }, + { + "epoch": 0.0, + "learning_rate": 1.3730678744178155e-05, + "loss": 3.3855, + "step": 2215424 + }, + { + "epoch": 0.0, + "learning_rate": 1.3722292796667635e-05, + "loss": 3.3828, + "step": 2215936 + }, + { + "epoch": 0.0, + "learning_rate": 1.3713906849157115e-05, + "loss": 3.3818, + "step": 2216448 + }, + { + "epoch": 0.0, + "learning_rate": 1.3705520901646595e-05, + "loss": 3.3802, + "step": 2216960 + }, + { + "epoch": 0.0, + "learning_rate": 1.3697151332939806e-05, + "loss": 3.3788, + "step": 2217472 + }, + { + "epoch": 0.0, + "learning_rate": 1.3688765385429286e-05, + "loss": 3.3898, + "step": 2217984 + }, + { + "epoch": 0.0, + "learning_rate": 1.3680379437918766e-05, + "loss": 3.3835, + "step": 2218496 + }, + { + "epoch": 0.0, + "learning_rate": 1.3671993490408247e-05, + "loss": 3.3851, + "step": 2219008 + }, + { + "epoch": 0.0, + "learning_rate": 1.3663623921701457e-05, + "loss": 3.3875, + "step": 2219520 + }, + { + "epoch": 0.0, + "learning_rate": 1.3655237974190938e-05, + "loss": 3.3686, + "step": 2220032 + }, + { + "epoch": 0.0, + "learning_rate": 1.3646852026680418e-05, + "loss": 3.3779, + "step": 2220544 + }, + { + "epoch": 0.0, + "learning_rate": 1.3638466079169895e-05, + "loss": 3.3693, + "step": 2221056 + }, + { + "epoch": 0.0, + "learning_rate": 1.3630096510463109e-05, + "loss": 3.3894, + "step": 2221568 + }, + { + "epoch": 0.0, + "learning_rate": 1.3621710562952589e-05, + "loss": 3.3753, + "step": 2222080 + }, + { + "epoch": 0.0, + "learning_rate": 1.3613324615442069e-05, + "loss": 3.3734, + "step": 2222592 + }, + { + "epoch": 0.0, + "learning_rate": 1.3604938667931547e-05, + "loss": 3.3807, + "step": 2223104 + }, + { + "epoch": 0.0, + "learning_rate": 1.359656909922476e-05, + "loss": 3.3893, + "step": 2223616 + }, + { + "epoch": 0.0, + "learning_rate": 1.358818315171424e-05, + "loss": 3.387, + "step": 2224128 + }, + { + "epoch": 0.0, + "learning_rate": 1.357979720420372e-05, + "loss": 3.3872, + "step": 2224640 + }, + { + "epoch": 0.0, + "learning_rate": 1.3571411256693198e-05, + "loss": 3.3788, + "step": 2225152 + }, + { + "epoch": 0.0, + "learning_rate": 1.356304168798641e-05, + "loss": 3.3888, + "step": 2225664 + }, + { + "epoch": 0.0, + "learning_rate": 1.3554655740475892e-05, + "loss": 3.3815, + "step": 2226176 + }, + { + "epoch": 0.0, + "learning_rate": 1.3546269792965368e-05, + "loss": 3.3778, + "step": 2226688 + }, + { + "epoch": 0.0, + "learning_rate": 1.3537883845454848e-05, + "loss": 3.3845, + "step": 2227200 + }, + { + "epoch": 0.0, + "learning_rate": 1.3529514276748063e-05, + "loss": 3.3745, + "step": 2227712 + }, + { + "epoch": 0.0, + "learning_rate": 1.3521128329237543e-05, + "loss": 3.3694, + "step": 2228224 + }, + { + "epoch": 0.01, + "learning_rate": 1.3512742381727019e-05, + "loss": 3.3775, + "step": 2228736 + }, + { + "epoch": 0.01, + "learning_rate": 1.35043564342165e-05, + "loss": 3.3813, + "step": 2229248 + }, + { + "epoch": 0.01, + "learning_rate": 1.3495986865509713e-05, + "loss": 3.3875, + "step": 2229760 + }, + { + "epoch": 0.01, + "learning_rate": 1.3487600917999193e-05, + "loss": 3.3854, + "step": 2230272 + }, + { + "epoch": 0.01, + "learning_rate": 1.3479214970488671e-05, + "loss": 3.3762, + "step": 2230784 + }, + { + "epoch": 0.01, + "learning_rate": 1.3470829022978151e-05, + "loss": 3.3739, + "step": 2231296 + }, + { + "epoch": 0.01, + "learning_rate": 1.3462459454271364e-05, + "loss": 3.3932, + "step": 2231808 + }, + { + "epoch": 0.01, + "learning_rate": 1.3454073506760842e-05, + "loss": 3.3685, + "step": 2232320 + }, + { + "epoch": 0.01, + "learning_rate": 1.3445687559250322e-05, + "loss": 3.3812, + "step": 2232832 + }, + { + "epoch": 0.01, + "learning_rate": 1.3437301611739802e-05, + "loss": 3.3725, + "step": 2233344 + }, + { + "epoch": 0.01, + "learning_rate": 1.3428932043033016e-05, + "loss": 3.371, + "step": 2233856 + }, + { + "epoch": 0.01, + "learning_rate": 1.3420562474326225e-05, + "loss": 3.3808, + "step": 2234368 + }, + { + "epoch": 0.01, + "learning_rate": 1.3412176526815707e-05, + "loss": 3.3895, + "step": 2234880 + }, + { + "epoch": 0.01, + "learning_rate": 1.3403790579305187e-05, + "loss": 3.3799, + "step": 2235392 + }, + { + "epoch": 0.01, + "learning_rate": 1.3395404631794664e-05, + "loss": 3.3794, + "step": 2235904 + }, + { + "epoch": 0.01, + "learning_rate": 1.3387018684284145e-05, + "loss": 3.3792, + "step": 2236416 + }, + { + "epoch": 0.01, + "learning_rate": 1.3378632736773625e-05, + "loss": 3.3756, + "step": 2236928 + }, + { + "epoch": 0.01, + "learning_rate": 1.3370246789263105e-05, + "loss": 3.3807, + "step": 2237440 + }, + { + "epoch": 0.01, + "learning_rate": 1.3361860841752585e-05, + "loss": 3.3566, + "step": 2237952 + }, + { + "epoch": 0.01, + "learning_rate": 1.3353491273045796e-05, + "loss": 3.3807, + "step": 2238464 + }, + { + "epoch": 0.01, + "learning_rate": 1.3345105325535276e-05, + "loss": 3.3748, + "step": 2238976 + }, + { + "epoch": 0.01, + "learning_rate": 1.3336735756828488e-05, + "loss": 3.3902, + "step": 2239488 + }, + { + "epoch": 0.01, + "learning_rate": 1.3328349809317967e-05, + "loss": 3.3701, + "step": 2240000 + }, + { + "epoch": 0.01, + "learning_rate": 1.3319963861807446e-05, + "loss": 3.3754, + "step": 2240512 + }, + { + "epoch": 0.01, + "learning_rate": 1.3311577914296926e-05, + "loss": 3.3601, + "step": 2241024 + }, + { + "epoch": 0.01, + "learning_rate": 1.3303191966786408e-05, + "loss": 3.3685, + "step": 2241536 + }, + { + "epoch": 0.01, + "learning_rate": 1.3294806019275888e-05, + "loss": 3.3806, + "step": 2242048 + }, + { + "epoch": 0.01, + "learning_rate": 1.3286420071765368e-05, + "loss": 3.3584, + "step": 2242560 + }, + { + "epoch": 0.01, + "learning_rate": 1.3278034124254846e-05, + "loss": 3.3857, + "step": 2243072 + }, + { + "epoch": 0.01, + "learning_rate": 1.3269664555548059e-05, + "loss": 3.3742, + "step": 2243584 + }, + { + "epoch": 0.01, + "learning_rate": 1.3261278608037539e-05, + "loss": 3.3709, + "step": 2244096 + }, + { + "epoch": 0.01, + "learning_rate": 1.325290903933075e-05, + "loss": 3.3902, + "step": 2244608 + }, + { + "epoch": 0.01, + "learning_rate": 1.324452309182023e-05, + "loss": 3.3651, + "step": 2245120 + }, + { + "epoch": 0.01, + "learning_rate": 1.323613714430971e-05, + "loss": 3.3666, + "step": 2245632 + }, + { + "epoch": 0.01, + "learning_rate": 1.322775119679919e-05, + "loss": 3.3722, + "step": 2246144 + }, + { + "epoch": 0.01, + "learning_rate": 1.3219365249288671e-05, + "loss": 3.3857, + "step": 2246656 + }, + { + "epoch": 0.01, + "learning_rate": 1.3210979301778148e-05, + "loss": 3.3652, + "step": 2247168 + }, + { + "epoch": 0.01, + "learning_rate": 1.3202593354267628e-05, + "loss": 3.3716, + "step": 2247680 + }, + { + "epoch": 0.01, + "learning_rate": 1.319420740675711e-05, + "loss": 3.3618, + "step": 2248192 + }, + { + "epoch": 0.01, + "learning_rate": 1.318585421685405e-05, + "loss": 3.3735, + "step": 2248704 + }, + { + "epoch": 0.01, + "learning_rate": 1.3177468269343532e-05, + "loss": 3.3778, + "step": 2249216 + }, + { + "epoch": 0.01, + "learning_rate": 1.3169082321833012e-05, + "loss": 3.3844, + "step": 2249728 + }, + { + "epoch": 0.01, + "learning_rate": 1.3160696374322492e-05, + "loss": 3.3784, + "step": 2250240 + }, + { + "epoch": 0.01, + "learning_rate": 1.315231042681197e-05, + "loss": 3.3809, + "step": 2250752 + }, + { + "epoch": 0.01, + "learning_rate": 1.314392447930145e-05, + "loss": 3.3927, + "step": 2251264 + }, + { + "epoch": 0.01, + "learning_rate": 1.313553853179093e-05, + "loss": 3.378, + "step": 2251776 + }, + { + "epoch": 0.01, + "learning_rate": 1.312715258428041e-05, + "loss": 3.3824, + "step": 2252288 + }, + { + "epoch": 0.01, + "learning_rate": 1.3118783015573621e-05, + "loss": 3.3778, + "step": 2252800 + }, + { + "epoch": 0.01, + "learning_rate": 1.3110413446866834e-05, + "loss": 3.3756, + "step": 2253312 + }, + { + "epoch": 0.01, + "learning_rate": 1.3102027499356315e-05, + "loss": 3.37, + "step": 2253824 + }, + { + "epoch": 0.01, + "learning_rate": 1.3093641551845792e-05, + "loss": 3.3813, + "step": 2254336 + }, + { + "epoch": 0.01, + "learning_rate": 1.3085255604335272e-05, + "loss": 3.3759, + "step": 2254848 + }, + { + "epoch": 0.01, + "learning_rate": 1.3076869656824754e-05, + "loss": 3.3874, + "step": 2255360 + }, + { + "epoch": 0.01, + "learning_rate": 1.3068483709314234e-05, + "loss": 3.3694, + "step": 2255872 + }, + { + "epoch": 0.01, + "learning_rate": 1.3060097761803713e-05, + "loss": 3.3638, + "step": 2256384 + }, + { + "epoch": 0.01, + "learning_rate": 1.3051728193096924e-05, + "loss": 3.3691, + "step": 2256896 + }, + { + "epoch": 0.01, + "learning_rate": 1.3043342245586404e-05, + "loss": 3.3794, + "step": 2257408 + }, + { + "epoch": 0.01, + "learning_rate": 1.3034956298075884e-05, + "loss": 3.3703, + "step": 2257920 + }, + { + "epoch": 0.01, + "learning_rate": 1.3026570350565364e-05, + "loss": 3.3815, + "step": 2258432 + }, + { + "epoch": 0.01, + "learning_rate": 1.3018200781858575e-05, + "loss": 3.3713, + "step": 2258944 + }, + { + "epoch": 0.02, + "learning_rate": 1.3009814834348055e-05, + "loss": 3.3664, + "step": 2259456 + }, + { + "epoch": 0.02, + "learning_rate": 1.3001428886837535e-05, + "loss": 3.3692, + "step": 2259968 + }, + { + "epoch": 0.02, + "learning_rate": 1.2993042939327017e-05, + "loss": 3.3722, + "step": 2260480 + }, + { + "epoch": 0.02, + "learning_rate": 1.2984673370620226e-05, + "loss": 3.3777, + "step": 2260992 + }, + { + "epoch": 0.02, + "learning_rate": 1.2976287423109707e-05, + "loss": 3.3831, + "step": 2261504 + }, + { + "epoch": 0.02, + "learning_rate": 1.2967901475599187e-05, + "loss": 3.3835, + "step": 2262016 + }, + { + "epoch": 0.02, + "learning_rate": 1.2959515528088667e-05, + "loss": 3.3643, + "step": 2262528 + }, + { + "epoch": 0.02, + "learning_rate": 1.2951145959381878e-05, + "loss": 3.3788, + "step": 2263040 + }, + { + "epoch": 0.02, + "learning_rate": 1.2942760011871358e-05, + "loss": 3.3692, + "step": 2263552 + }, + { + "epoch": 0.02, + "learning_rate": 1.2934374064360838e-05, + "loss": 3.3805, + "step": 2264064 + }, + { + "epoch": 0.02, + "learning_rate": 1.2925988116850318e-05, + "loss": 3.3748, + "step": 2264576 + }, + { + "epoch": 0.02, + "learning_rate": 1.2917618548143529e-05, + "loss": 3.3674, + "step": 2265088 + }, + { + "epoch": 0.02, + "learning_rate": 1.2909232600633009e-05, + "loss": 3.3753, + "step": 2265600 + }, + { + "epoch": 0.02, + "learning_rate": 1.290086303192622e-05, + "loss": 3.373, + "step": 2266112 + }, + { + "epoch": 0.02, + "learning_rate": 1.28924770844157e-05, + "loss": 3.3748, + "step": 2266624 + }, + { + "epoch": 0.02, + "learning_rate": 1.288409113690518e-05, + "loss": 3.3732, + "step": 2267136 + }, + { + "epoch": 0.02, + "learning_rate": 1.2875705189394661e-05, + "loss": 3.3689, + "step": 2267648 + }, + { + "epoch": 0.02, + "learning_rate": 1.2867319241884141e-05, + "loss": 3.3792, + "step": 2268160 + }, + { + "epoch": 0.02, + "learning_rate": 1.285893329437362e-05, + "loss": 3.3777, + "step": 2268672 + }, + { + "epoch": 0.02, + "learning_rate": 1.2850547346863097e-05, + "loss": 3.367, + "step": 2269184 + }, + { + "epoch": 0.02, + "learning_rate": 1.2842161399352579e-05, + "loss": 3.3642, + "step": 2269696 + }, + { + "epoch": 0.02, + "learning_rate": 1.2833791830645792e-05, + "loss": 3.3709, + "step": 2270208 + }, + { + "epoch": 0.02, + "learning_rate": 1.2825405883135271e-05, + "loss": 3.3857, + "step": 2270720 + }, + { + "epoch": 0.02, + "learning_rate": 1.281701993562475e-05, + "loss": 3.3686, + "step": 2271232 + }, + { + "epoch": 0.02, + "learning_rate": 1.280863398811423e-05, + "loss": 3.3761, + "step": 2271744 + }, + { + "epoch": 0.02, + "learning_rate": 1.2800264419407442e-05, + "loss": 3.3781, + "step": 2272256 + }, + { + "epoch": 0.02, + "learning_rate": 1.279187847189692e-05, + "loss": 3.386, + "step": 2272768 + }, + { + "epoch": 0.02, + "learning_rate": 1.27834925243864e-05, + "loss": 3.3752, + "step": 2273280 + }, + { + "epoch": 0.02, + "learning_rate": 1.277510657687588e-05, + "loss": 3.3764, + "step": 2273792 + }, + { + "epoch": 0.02, + "learning_rate": 1.2766737008169095e-05, + "loss": 3.3809, + "step": 2274304 + }, + { + "epoch": 0.02, + "learning_rate": 1.2758351060658571e-05, + "loss": 3.3783, + "step": 2274816 + }, + { + "epoch": 0.02, + "learning_rate": 1.2749965113148051e-05, + "loss": 3.3656, + "step": 2275328 + }, + { + "epoch": 0.02, + "learning_rate": 1.2741579165637533e-05, + "loss": 3.3732, + "step": 2275840 + }, + { + "epoch": 0.02, + "learning_rate": 1.2733209596930742e-05, + "loss": 3.3639, + "step": 2276352 + }, + { + "epoch": 0.02, + "learning_rate": 1.2724823649420223e-05, + "loss": 3.3795, + "step": 2276864 + }, + { + "epoch": 0.02, + "learning_rate": 1.2716437701909703e-05, + "loss": 3.3744, + "step": 2277376 + }, + { + "epoch": 0.02, + "learning_rate": 1.2708068133202916e-05, + "loss": 3.3724, + "step": 2277888 + }, + { + "epoch": 0.02, + "learning_rate": 1.2699682185692394e-05, + "loss": 3.3618, + "step": 2278400 + }, + { + "epoch": 0.02, + "learning_rate": 1.2691296238181874e-05, + "loss": 3.371, + "step": 2278912 + }, + { + "epoch": 0.02, + "learning_rate": 1.2682910290671354e-05, + "loss": 3.3838, + "step": 2279424 + }, + { + "epoch": 0.02, + "learning_rate": 1.2674524343160834e-05, + "loss": 3.377, + "step": 2279936 + }, + { + "epoch": 0.02, + "learning_rate": 1.2666138395650316e-05, + "loss": 3.3858, + "step": 2280448 + }, + { + "epoch": 0.02, + "learning_rate": 1.2657752448139796e-05, + "loss": 3.3668, + "step": 2280960 + }, + { + "epoch": 0.02, + "learning_rate": 1.2649366500629276e-05, + "loss": 3.3796, + "step": 2281472 + }, + { + "epoch": 0.02, + "learning_rate": 1.2640996931922486e-05, + "loss": 3.3837, + "step": 2281984 + }, + { + "epoch": 0.02, + "learning_rate": 1.2632627363215695e-05, + "loss": 3.3761, + "step": 2282496 + }, + { + "epoch": 0.02, + "learning_rate": 1.2624241415705177e-05, + "loss": 3.3665, + "step": 2283008 + }, + { + "epoch": 0.02, + "learning_rate": 1.2615855468194657e-05, + "loss": 3.3767, + "step": 2283520 + }, + { + "epoch": 0.02, + "learning_rate": 1.2607469520684137e-05, + "loss": 3.3802, + "step": 2284032 + }, + { + "epoch": 0.02, + "learning_rate": 1.2599083573173617e-05, + "loss": 3.3808, + "step": 2284544 + }, + { + "epoch": 0.02, + "learning_rate": 1.2590697625663097e-05, + "loss": 3.3709, + "step": 2285056 + }, + { + "epoch": 0.02, + "learning_rate": 1.2582311678152575e-05, + "loss": 3.3688, + "step": 2285568 + }, + { + "epoch": 0.02, + "learning_rate": 1.2573942109445788e-05, + "loss": 3.3764, + "step": 2286080 + }, + { + "epoch": 0.02, + "learning_rate": 1.256555616193527e-05, + "loss": 3.3741, + "step": 2286592 + }, + { + "epoch": 0.02, + "learning_rate": 1.255717021442475e-05, + "loss": 3.3649, + "step": 2287104 + }, + { + "epoch": 0.02, + "learning_rate": 1.2548784266914226e-05, + "loss": 3.382, + "step": 2287616 + }, + { + "epoch": 0.02, + "learning_rate": 1.2540398319403708e-05, + "loss": 3.3734, + "step": 2288128 + }, + { + "epoch": 0.02, + "learning_rate": 1.2532012371893187e-05, + "loss": 3.3865, + "step": 2288640 + }, + { + "epoch": 0.02, + "learning_rate": 1.2523626424382667e-05, + "loss": 3.3636, + "step": 2289152 + }, + { + "epoch": 0.03, + "eval_loss": 3.8604750633239746, + "eval_runtime": 304.2083, + "eval_samples_per_second": 1254.374, + "eval_steps_per_second": 39.2, + "step": 2289600 + }, + { + "epoch": 1.0, + "learning_rate": 1.2515240476872147e-05, + "loss": 3.3766, + "step": 2289664 + }, + { + "epoch": 1.0, + "learning_rate": 1.2506870908165358e-05, + "loss": 3.3657, + "step": 2290176 + }, + { + "epoch": 1.0, + "learning_rate": 1.2498484960654838e-05, + "loss": 3.3756, + "step": 2290688 + }, + { + "epoch": 1.0, + "learning_rate": 1.2490099013144318e-05, + "loss": 3.3802, + "step": 2291200 + }, + { + "epoch": 1.0, + "learning_rate": 1.2481713065633798e-05, + "loss": 3.3773, + "step": 2291712 + }, + { + "epoch": 1.0, + "learning_rate": 1.2473343496927009e-05, + "loss": 3.3745, + "step": 2292224 + }, + { + "epoch": 1.0, + "learning_rate": 1.2464957549416489e-05, + "loss": 3.3699, + "step": 2292736 + }, + { + "epoch": 1.0, + "learning_rate": 1.245657160190597e-05, + "loss": 3.3706, + "step": 2293248 + }, + { + "epoch": 1.0, + "learning_rate": 1.2448185654395449e-05, + "loss": 3.3686, + "step": 2293760 + }, + { + "epoch": 1.0, + "learning_rate": 1.243981608568866e-05, + "loss": 3.3772, + "step": 2294272 + }, + { + "epoch": 1.0, + "learning_rate": 1.2431430138178141e-05, + "loss": 3.3753, + "step": 2294784 + }, + { + "epoch": 1.0, + "learning_rate": 1.2423044190667621e-05, + "loss": 3.3741, + "step": 2295296 + }, + { + "epoch": 1.0, + "learning_rate": 1.24146582431571e-05, + "loss": 3.3772, + "step": 2295808 + }, + { + "epoch": 1.0, + "learning_rate": 1.2406288674450312e-05, + "loss": 3.3607, + "step": 2296320 + }, + { + "epoch": 1.0, + "learning_rate": 1.2397902726939792e-05, + "loss": 3.3664, + "step": 2296832 + }, + { + "epoch": 1.0, + "learning_rate": 1.238951677942927e-05, + "loss": 3.3592, + "step": 2297344 + }, + { + "epoch": 1.0, + "learning_rate": 1.2381130831918752e-05, + "loss": 3.3807, + "step": 2297856 + }, + { + "epoch": 1.0, + "learning_rate": 1.2372761263211963e-05, + "loss": 3.3644, + "step": 2298368 + }, + { + "epoch": 1.0, + "learning_rate": 1.2364375315701442e-05, + "loss": 3.3658, + "step": 2298880 + }, + { + "epoch": 1.0, + "learning_rate": 1.2356005746994653e-05, + "loss": 3.376, + "step": 2299392 + }, + { + "epoch": 1.0, + "learning_rate": 1.2347619799484133e-05, + "loss": 3.3773, + "step": 2299904 + }, + { + "epoch": 1.0, + "learning_rate": 1.2339233851973613e-05, + "loss": 3.3776, + "step": 2300416 + }, + { + "epoch": 1.0, + "learning_rate": 1.2330847904463095e-05, + "loss": 3.3728, + "step": 2300928 + }, + { + "epoch": 1.0, + "learning_rate": 1.2322461956952573e-05, + "loss": 3.3718, + "step": 2301440 + }, + { + "epoch": 1.0, + "learning_rate": 1.2314076009442053e-05, + "loss": 3.3818, + "step": 2301952 + }, + { + "epoch": 1.0, + "learning_rate": 1.2305690061931533e-05, + "loss": 3.3683, + "step": 2302464 + }, + { + "epoch": 1.0, + "learning_rate": 1.2297304114421013e-05, + "loss": 3.3697, + "step": 2302976 + }, + { + "epoch": 1.0, + "learning_rate": 1.2288934545714224e-05, + "loss": 3.3774, + "step": 2303488 + }, + { + "epoch": 1.0, + "learning_rate": 1.2280548598203705e-05, + "loss": 3.3627, + "step": 2304000 + }, + { + "epoch": 1.0, + "learning_rate": 1.2272162650693185e-05, + "loss": 3.3596, + "step": 2304512 + }, + { + "epoch": 1.01, + "learning_rate": 1.2263776703182664e-05, + "loss": 3.3667, + "step": 2305024 + }, + { + "epoch": 1.01, + "learning_rate": 1.2255407134475876e-05, + "loss": 3.3713, + "step": 2305536 + }, + { + "epoch": 1.01, + "learning_rate": 1.2247021186965356e-05, + "loss": 3.3808, + "step": 2306048 + }, + { + "epoch": 1.01, + "learning_rate": 1.2238635239454834e-05, + "loss": 3.3758, + "step": 2306560 + }, + { + "epoch": 1.01, + "learning_rate": 1.2230249291944316e-05, + "loss": 3.3673, + "step": 2307072 + }, + { + "epoch": 1.01, + "learning_rate": 1.2221879723237527e-05, + "loss": 3.366, + "step": 2307584 + }, + { + "epoch": 1.01, + "learning_rate": 1.2213493775727007e-05, + "loss": 3.3801, + "step": 2308096 + }, + { + "epoch": 1.01, + "learning_rate": 1.2205107828216487e-05, + "loss": 3.3619, + "step": 2308608 + }, + { + "epoch": 1.01, + "learning_rate": 1.2196721880705967e-05, + "loss": 3.3745, + "step": 2309120 + }, + { + "epoch": 1.01, + "learning_rate": 1.2188352311999177e-05, + "loss": 3.3601, + "step": 2309632 + }, + { + "epoch": 1.01, + "learning_rate": 1.2179966364488659e-05, + "loss": 3.362, + "step": 2310144 + }, + { + "epoch": 1.01, + "learning_rate": 1.2171596795781868e-05, + "loss": 3.37, + "step": 2310656 + }, + { + "epoch": 1.01, + "learning_rate": 1.2163210848271348e-05, + "loss": 3.3861, + "step": 2311168 + }, + { + "epoch": 1.01, + "learning_rate": 1.215482490076083e-05, + "loss": 3.3681, + "step": 2311680 + }, + { + "epoch": 1.01, + "learning_rate": 1.2146438953250308e-05, + "loss": 3.3687, + "step": 2312192 + }, + { + "epoch": 1.01, + "learning_rate": 1.2138053005739788e-05, + "loss": 3.3718, + "step": 2312704 + }, + { + "epoch": 1.01, + "learning_rate": 1.2129667058229268e-05, + "loss": 3.3679, + "step": 2313216 + }, + { + "epoch": 1.01, + "learning_rate": 1.2121281110718748e-05, + "loss": 3.3691, + "step": 2313728 + }, + { + "epoch": 1.01, + "learning_rate": 1.2112895163208228e-05, + "loss": 3.3501, + "step": 2314240 + }, + { + "epoch": 1.01, + "learning_rate": 1.210452559450144e-05, + "loss": 3.371, + "step": 2314752 + }, + { + "epoch": 1.01, + "learning_rate": 1.209613964699092e-05, + "loss": 3.3678, + "step": 2315264 + }, + { + "epoch": 1.01, + "learning_rate": 1.2087753699480399e-05, + "loss": 3.376, + "step": 2315776 + }, + { + "epoch": 1.01, + "learning_rate": 1.2079367751969878e-05, + "loss": 3.3588, + "step": 2316288 + }, + { + "epoch": 1.01, + "learning_rate": 1.2070998183263091e-05, + "loss": 3.3616, + "step": 2316800 + }, + { + "epoch": 1.01, + "learning_rate": 1.2062628614556302e-05, + "loss": 3.3596, + "step": 2317312 + }, + { + "epoch": 1.01, + "learning_rate": 1.2054242667045782e-05, + "loss": 3.3529, + "step": 2317824 + }, + { + "epoch": 1.01, + "learning_rate": 1.2045856719535262e-05, + "loss": 3.3749, + "step": 2318336 + }, + { + "epoch": 1.01, + "learning_rate": 1.2037470772024742e-05, + "loss": 3.3527, + "step": 2318848 + }, + { + "epoch": 1.01, + "learning_rate": 1.2029084824514222e-05, + "loss": 3.3727, + "step": 2319360 + }, + { + "epoch": 1.01, + "learning_rate": 1.2020698877003702e-05, + "loss": 3.3657, + "step": 2319872 + }, + { + "epoch": 1.01, + "learning_rate": 1.2012312929493181e-05, + "loss": 3.364, + "step": 2320384 + }, + { + "epoch": 1.01, + "learning_rate": 1.2003943360786394e-05, + "loss": 3.3804, + "step": 2320896 + }, + { + "epoch": 1.01, + "learning_rate": 1.1995557413275872e-05, + "loss": 3.3595, + "step": 2321408 + }, + { + "epoch": 1.01, + "learning_rate": 1.1987171465765352e-05, + "loss": 3.3578, + "step": 2321920 + }, + { + "epoch": 1.01, + "learning_rate": 1.1978785518254832e-05, + "loss": 3.3594, + "step": 2322432 + }, + { + "epoch": 1.01, + "learning_rate": 1.1970399570744312e-05, + "loss": 3.378, + "step": 2322944 + }, + { + "epoch": 1.01, + "learning_rate": 1.1962013623233792e-05, + "loss": 3.3578, + "step": 2323456 + }, + { + "epoch": 1.01, + "learning_rate": 1.1953627675723272e-05, + "loss": 3.3569, + "step": 2323968 + }, + { + "epoch": 1.01, + "learning_rate": 1.1945241728212752e-05, + "loss": 3.3579, + "step": 2324480 + }, + { + "epoch": 1.01, + "learning_rate": 1.1936888538309694e-05, + "loss": 3.3615, + "step": 2324992 + }, + { + "epoch": 1.01, + "learning_rate": 1.1928502590799175e-05, + "loss": 3.37, + "step": 2325504 + }, + { + "epoch": 1.01, + "learning_rate": 1.1920116643288655e-05, + "loss": 3.3735, + "step": 2326016 + }, + { + "epoch": 1.01, + "learning_rate": 1.1911730695778135e-05, + "loss": 3.3673, + "step": 2326528 + }, + { + "epoch": 1.01, + "learning_rate": 1.1903361127071346e-05, + "loss": 3.3742, + "step": 2327040 + }, + { + "epoch": 1.01, + "learning_rate": 1.1894975179560826e-05, + "loss": 3.3809, + "step": 2327552 + }, + { + "epoch": 1.01, + "learning_rate": 1.1886589232050306e-05, + "loss": 3.3682, + "step": 2328064 + }, + { + "epoch": 1.01, + "learning_rate": 1.1878203284539786e-05, + "loss": 3.3713, + "step": 2328576 + }, + { + "epoch": 1.01, + "learning_rate": 1.1869817337029266e-05, + "loss": 3.3692, + "step": 2329088 + }, + { + "epoch": 1.01, + "learning_rate": 1.1861447768322477e-05, + "loss": 3.3693, + "step": 2329600 + }, + { + "epoch": 1.01, + "learning_rate": 1.1853061820811957e-05, + "loss": 3.3632, + "step": 2330112 + }, + { + "epoch": 1.01, + "learning_rate": 1.1844675873301436e-05, + "loss": 3.3721, + "step": 2330624 + }, + { + "epoch": 1.01, + "learning_rate": 1.1836289925790916e-05, + "loss": 3.3686, + "step": 2331136 + }, + { + "epoch": 1.01, + "learning_rate": 1.1827903978280396e-05, + "loss": 3.3766, + "step": 2331648 + }, + { + "epoch": 1.01, + "learning_rate": 1.1819518030769876e-05, + "loss": 3.3642, + "step": 2332160 + }, + { + "epoch": 1.01, + "learning_rate": 1.1811132083259356e-05, + "loss": 3.3506, + "step": 2332672 + }, + { + "epoch": 1.01, + "learning_rate": 1.1802762514552567e-05, + "loss": 3.3575, + "step": 2333184 + }, + { + "epoch": 1.01, + "learning_rate": 1.1794376567042049e-05, + "loss": 3.3701, + "step": 2333696 + }, + { + "epoch": 1.01, + "learning_rate": 1.1785990619531527e-05, + "loss": 3.3616, + "step": 2334208 + }, + { + "epoch": 1.01, + "learning_rate": 1.1777604672021007e-05, + "loss": 3.3723, + "step": 2334720 + }, + { + "epoch": 1.01, + "learning_rate": 1.176923510331422e-05, + "loss": 3.3672, + "step": 2335232 + }, + { + "epoch": 1.02, + "learning_rate": 1.17608491558037e-05, + "loss": 3.3572, + "step": 2335744 + }, + { + "epoch": 1.02, + "learning_rate": 1.1752463208293178e-05, + "loss": 3.3547, + "step": 2336256 + }, + { + "epoch": 1.02, + "learning_rate": 1.174407726078266e-05, + "loss": 3.3646, + "step": 2336768 + }, + { + "epoch": 1.02, + "learning_rate": 1.173570769207587e-05, + "loss": 3.3691, + "step": 2337280 + }, + { + "epoch": 1.02, + "learning_rate": 1.1727321744565348e-05, + "loss": 3.3759, + "step": 2337792 + }, + { + "epoch": 1.02, + "learning_rate": 1.171893579705483e-05, + "loss": 3.3684, + "step": 2338304 + }, + { + "epoch": 1.02, + "learning_rate": 1.171054984954431e-05, + "loss": 3.3567, + "step": 2338816 + }, + { + "epoch": 1.02, + "learning_rate": 1.170218028083752e-05, + "loss": 3.3685, + "step": 2339328 + }, + { + "epoch": 1.02, + "learning_rate": 1.1693794333327e-05, + "loss": 3.3669, + "step": 2339840 + }, + { + "epoch": 1.02, + "learning_rate": 1.168540838581648e-05, + "loss": 3.3675, + "step": 2340352 + }, + { + "epoch": 1.02, + "learning_rate": 1.167702243830596e-05, + "loss": 3.3674, + "step": 2340864 + }, + { + "epoch": 1.02, + "learning_rate": 1.1668652869599173e-05, + "loss": 3.3559, + "step": 2341376 + }, + { + "epoch": 1.02, + "learning_rate": 1.1660266922088651e-05, + "loss": 3.3647, + "step": 2341888 + }, + { + "epoch": 1.02, + "learning_rate": 1.1651880974578131e-05, + "loss": 3.3651, + "step": 2342400 + }, + { + "epoch": 1.02, + "learning_rate": 1.1643495027067613e-05, + "loss": 3.3667, + "step": 2342912 + }, + { + "epoch": 1.02, + "learning_rate": 1.1635125458360822e-05, + "loss": 3.3628, + "step": 2343424 + }, + { + "epoch": 1.02, + "learning_rate": 1.1626739510850302e-05, + "loss": 3.3617, + "step": 2343936 + }, + { + "epoch": 1.02, + "learning_rate": 1.1618369942143515e-05, + "loss": 3.3689, + "step": 2344448 + }, + { + "epoch": 1.02, + "learning_rate": 1.1609983994632994e-05, + "loss": 3.3711, + "step": 2344960 + }, + { + "epoch": 1.02, + "learning_rate": 1.1601598047122474e-05, + "loss": 3.3551, + "step": 2345472 + }, + { + "epoch": 1.02, + "learning_rate": 1.1593212099611954e-05, + "loss": 3.3535, + "step": 2345984 + }, + { + "epoch": 1.02, + "learning_rate": 1.1584826152101434e-05, + "loss": 3.3591, + "step": 2346496 + }, + { + "epoch": 1.02, + "learning_rate": 1.1576440204590913e-05, + "loss": 3.3765, + "step": 2347008 + }, + { + "epoch": 1.02, + "learning_rate": 1.1568054257080394e-05, + "loss": 3.3625, + "step": 2347520 + }, + { + "epoch": 1.02, + "learning_rate": 1.1559684688373605e-05, + "loss": 3.3655, + "step": 2348032 + }, + { + "epoch": 1.02, + "learning_rate": 1.1551298740863085e-05, + "loss": 3.3701, + "step": 2348544 + }, + { + "epoch": 1.02, + "learning_rate": 1.1542912793352565e-05, + "loss": 3.3741, + "step": 2349056 + }, + { + "epoch": 1.02, + "learning_rate": 1.1534526845842045e-05, + "loss": 3.364, + "step": 2349568 + }, + { + "epoch": 1.02, + "learning_rate": 1.1526140898331525e-05, + "loss": 3.37, + "step": 2350080 + }, + { + "epoch": 1.02, + "learning_rate": 1.1517754950821003e-05, + "loss": 3.3697, + "step": 2350592 + }, + { + "epoch": 1.02, + "learning_rate": 1.1509369003310485e-05, + "loss": 3.366, + "step": 2351104 + }, + { + "epoch": 1.02, + "learning_rate": 1.1500983055799965e-05, + "loss": 3.3546, + "step": 2351616 + }, + { + "epoch": 1.02, + "learning_rate": 1.1492613487093176e-05, + "loss": 3.364, + "step": 2352128 + }, + { + "epoch": 1.02, + "learning_rate": 1.1484227539582655e-05, + "loss": 3.3609, + "step": 2352640 + }, + { + "epoch": 1.02, + "learning_rate": 1.1475841592072135e-05, + "loss": 3.3645, + "step": 2353152 + }, + { + "epoch": 1.02, + "learning_rate": 1.1467455644561615e-05, + "loss": 3.3652, + "step": 2353664 + }, + { + "epoch": 1.02, + "learning_rate": 1.1459086075854826e-05, + "loss": 3.3619, + "step": 2354176 + }, + { + "epoch": 1.02, + "learning_rate": 1.1450700128344306e-05, + "loss": 3.358, + "step": 2354688 + }, + { + "epoch": 1.02, + "learning_rate": 1.1442314180833786e-05, + "loss": 3.3626, + "step": 2355200 + }, + { + "epoch": 1.02, + "learning_rate": 1.1433928233323268e-05, + "loss": 3.3662, + "step": 2355712 + }, + { + "epoch": 1.02, + "learning_rate": 1.1425558664616477e-05, + "loss": 3.3734, + "step": 2356224 + }, + { + "epoch": 1.02, + "learning_rate": 1.1417172717105957e-05, + "loss": 3.3771, + "step": 2356736 + }, + { + "epoch": 1.02, + "learning_rate": 1.1408786769595438e-05, + "loss": 3.3573, + "step": 2357248 + }, + { + "epoch": 1.02, + "learning_rate": 1.1400400822084917e-05, + "loss": 3.3689, + "step": 2357760 + }, + { + "epoch": 1.02, + "learning_rate": 1.139203125337813e-05, + "loss": 3.3725, + "step": 2358272 + }, + { + "epoch": 1.02, + "learning_rate": 1.138366168467134e-05, + "loss": 3.3676, + "step": 2358784 + }, + { + "epoch": 1.02, + "learning_rate": 1.137527573716082e-05, + "loss": 3.3607, + "step": 2359296 + }, + { + "epoch": 1.02, + "learning_rate": 1.13668897896503e-05, + "loss": 3.3695, + "step": 2359808 + }, + { + "epoch": 1.02, + "learning_rate": 1.135850384213978e-05, + "loss": 3.3698, + "step": 2360320 + }, + { + "epoch": 1.02, + "learning_rate": 1.135011789462926e-05, + "loss": 3.3689, + "step": 2360832 + }, + { + "epoch": 1.02, + "learning_rate": 1.134173194711874e-05, + "loss": 3.3627, + "step": 2361344 + }, + { + "epoch": 1.02, + "learning_rate": 1.133334599960822e-05, + "loss": 3.3617, + "step": 2361856 + }, + { + "epoch": 1.02, + "learning_rate": 1.132497643090143e-05, + "loss": 3.3655, + "step": 2362368 + }, + { + "epoch": 1.02, + "learning_rate": 1.131659048339091e-05, + "loss": 3.3613, + "step": 2362880 + }, + { + "epoch": 1.02, + "learning_rate": 1.130820453588039e-05, + "loss": 3.3541, + "step": 2363392 + }, + { + "epoch": 1.02, + "learning_rate": 1.129981858836987e-05, + "loss": 3.3712, + "step": 2363904 + }, + { + "epoch": 1.02, + "learning_rate": 1.129143264085935e-05, + "loss": 3.3643, + "step": 2364416 + }, + { + "epoch": 1.02, + "learning_rate": 1.128304669334883e-05, + "loss": 3.3772, + "step": 2364928 + }, + { + "epoch": 1.02, + "learning_rate": 1.127466074583831e-05, + "loss": 3.3563, + "step": 2365440 + }, + { + "epoch": 1.03, + "eval_loss": 3.861903667449951, + "eval_runtime": 306.2884, + "eval_samples_per_second": 1245.855, + "eval_steps_per_second": 38.934, + "step": 2365920 + }, + { + "epoch": 0.0, + "learning_rate": 1.126627479832779e-05, + "loss": 3.3623, + "step": 2365952 + }, + { + "epoch": 0.0, + "learning_rate": 1.125788885081727e-05, + "loss": 3.3587, + "step": 2366464 + }, + { + "epoch": 0.0, + "learning_rate": 1.124950290330675e-05, + "loss": 3.3633, + "step": 2366976 + }, + { + "epoch": 0.0, + "learning_rate": 1.124111695579623e-05, + "loss": 3.3708, + "step": 2367488 + }, + { + "epoch": 0.0, + "learning_rate": 1.1232747387089441e-05, + "loss": 3.3659, + "step": 2368000 + }, + { + "epoch": 0.0, + "learning_rate": 1.1224361439578922e-05, + "loss": 3.3692, + "step": 2368512 + }, + { + "epoch": 0.0, + "learning_rate": 1.12159754920684e-05, + "loss": 3.3593, + "step": 2369024 + }, + { + "epoch": 0.0, + "learning_rate": 1.120758954455788e-05, + "loss": 3.3624, + "step": 2369536 + }, + { + "epoch": 0.0, + "learning_rate": 1.1199219975851093e-05, + "loss": 3.361, + "step": 2370048 + }, + { + "epoch": 0.0, + "learning_rate": 1.1190834028340571e-05, + "loss": 3.3669, + "step": 2370560 + }, + { + "epoch": 0.0, + "learning_rate": 1.1182448080830051e-05, + "loss": 3.3645, + "step": 2371072 + }, + { + "epoch": 0.0, + "learning_rate": 1.1174062133319533e-05, + "loss": 3.3689, + "step": 2371584 + }, + { + "epoch": 0.0, + "learning_rate": 1.1165692564612744e-05, + "loss": 3.3689, + "step": 2372096 + }, + { + "epoch": 0.0, + "learning_rate": 1.1157306617102222e-05, + "loss": 3.3523, + "step": 2372608 + }, + { + "epoch": 0.0, + "learning_rate": 1.1148920669591704e-05, + "loss": 3.3534, + "step": 2373120 + }, + { + "epoch": 0.0, + "learning_rate": 1.1140534722081184e-05, + "loss": 3.3539, + "step": 2373632 + }, + { + "epoch": 0.0, + "learning_rate": 1.1132165153374395e-05, + "loss": 3.3668, + "step": 2374144 + }, + { + "epoch": 0.0, + "learning_rate": 1.1123779205863874e-05, + "loss": 3.361, + "step": 2374656 + }, + { + "epoch": 0.0, + "learning_rate": 1.1115393258353354e-05, + "loss": 3.3568, + "step": 2375168 + }, + { + "epoch": 0.0, + "learning_rate": 1.1107007310842834e-05, + "loss": 3.3625, + "step": 2375680 + }, + { + "epoch": 0.0, + "learning_rate": 1.1098637742136045e-05, + "loss": 3.3694, + "step": 2376192 + }, + { + "epoch": 0.0, + "learning_rate": 1.1090251794625525e-05, + "loss": 3.3692, + "step": 2376704 + }, + { + "epoch": 0.0, + "learning_rate": 1.1081865847115005e-05, + "loss": 3.3636, + "step": 2377216 + }, + { + "epoch": 0.0, + "learning_rate": 1.1073479899604485e-05, + "loss": 3.3613, + "step": 2377728 + }, + { + "epoch": 0.0, + "learning_rate": 1.1065110330897696e-05, + "loss": 3.3756, + "step": 2378240 + }, + { + "epoch": 0.0, + "learning_rate": 1.1056724383387176e-05, + "loss": 3.3546, + "step": 2378752 + }, + { + "epoch": 0.0, + "learning_rate": 1.1048338435876657e-05, + "loss": 3.3621, + "step": 2379264 + }, + { + "epoch": 0.0, + "learning_rate": 1.1039952488366136e-05, + "loss": 3.3669, + "step": 2379776 + }, + { + "epoch": 0.0, + "learning_rate": 1.1031582919659346e-05, + "loss": 3.3527, + "step": 2380288 + }, + { + "epoch": 0.0, + "learning_rate": 1.1023196972148828e-05, + "loss": 3.3538, + "step": 2380800 + }, + { + "epoch": 0.01, + "learning_rate": 1.1014811024638308e-05, + "loss": 3.3553, + "step": 2381312 + }, + { + "epoch": 0.01, + "learning_rate": 1.1006425077127786e-05, + "loss": 3.3632, + "step": 2381824 + }, + { + "epoch": 0.01, + "learning_rate": 1.0998055508420999e-05, + "loss": 3.3701, + "step": 2382336 + }, + { + "epoch": 0.01, + "learning_rate": 1.0989669560910479e-05, + "loss": 3.3645, + "step": 2382848 + }, + { + "epoch": 0.01, + "learning_rate": 1.0981283613399959e-05, + "loss": 3.3624, + "step": 2383360 + }, + { + "epoch": 0.01, + "learning_rate": 1.0972897665889439e-05, + "loss": 3.3556, + "step": 2383872 + }, + { + "epoch": 0.01, + "learning_rate": 1.096452809718265e-05, + "loss": 3.3691, + "step": 2384384 + }, + { + "epoch": 0.01, + "learning_rate": 1.095614214967213e-05, + "loss": 3.3525, + "step": 2384896 + }, + { + "epoch": 0.01, + "learning_rate": 1.094775620216161e-05, + "loss": 3.3649, + "step": 2385408 + }, + { + "epoch": 0.01, + "learning_rate": 1.093937025465109e-05, + "loss": 3.3522, + "step": 2385920 + }, + { + "epoch": 0.01, + "learning_rate": 1.09310006859443e-05, + "loss": 3.3536, + "step": 2386432 + }, + { + "epoch": 0.01, + "learning_rate": 1.0922631117237513e-05, + "loss": 3.3592, + "step": 2386944 + }, + { + "epoch": 0.01, + "learning_rate": 1.0914245169726991e-05, + "loss": 3.378, + "step": 2387456 + }, + { + "epoch": 0.01, + "learning_rate": 1.0905859222216473e-05, + "loss": 3.3543, + "step": 2387968 + }, + { + "epoch": 0.01, + "learning_rate": 1.0897473274705953e-05, + "loss": 3.3636, + "step": 2388480 + }, + { + "epoch": 0.01, + "learning_rate": 1.088908732719543e-05, + "loss": 3.3632, + "step": 2388992 + }, + { + "epoch": 0.01, + "learning_rate": 1.088070137968491e-05, + "loss": 3.359, + "step": 2389504 + }, + { + "epoch": 0.01, + "learning_rate": 1.0872315432174392e-05, + "loss": 3.3618, + "step": 2390016 + }, + { + "epoch": 0.01, + "learning_rate": 1.0863929484663872e-05, + "loss": 3.3361, + "step": 2390528 + }, + { + "epoch": 0.01, + "learning_rate": 1.0855559915957081e-05, + "loss": 3.3598, + "step": 2391040 + }, + { + "epoch": 0.01, + "learning_rate": 1.0847173968446563e-05, + "loss": 3.3636, + "step": 2391552 + }, + { + "epoch": 0.01, + "learning_rate": 1.0838788020936043e-05, + "loss": 3.3637, + "step": 2392064 + }, + { + "epoch": 0.01, + "learning_rate": 1.0830402073425521e-05, + "loss": 3.3528, + "step": 2392576 + }, + { + "epoch": 0.01, + "learning_rate": 1.0822032504718734e-05, + "loss": 3.3491, + "step": 2393088 + }, + { + "epoch": 0.01, + "learning_rate": 1.0813662936011945e-05, + "loss": 3.3535, + "step": 2393600 + }, + { + "epoch": 0.01, + "learning_rate": 1.0805276988501426e-05, + "loss": 3.3427, + "step": 2394112 + }, + { + "epoch": 0.01, + "learning_rate": 1.0796891040990904e-05, + "loss": 3.3664, + "step": 2394624 + }, + { + "epoch": 0.01, + "learning_rate": 1.0788505093480384e-05, + "loss": 3.3407, + "step": 2395136 + }, + { + "epoch": 0.01, + "learning_rate": 1.0780119145969864e-05, + "loss": 3.3601, + "step": 2395648 + }, + { + "epoch": 0.01, + "learning_rate": 1.0771733198459346e-05, + "loss": 3.3559, + "step": 2396160 + }, + { + "epoch": 0.01, + "learning_rate": 1.0763347250948824e-05, + "loss": 3.3543, + "step": 2396672 + }, + { + "epoch": 0.01, + "learning_rate": 1.0754977682242035e-05, + "loss": 3.3686, + "step": 2397184 + }, + { + "epoch": 0.01, + "learning_rate": 1.0746591734731517e-05, + "loss": 3.3509, + "step": 2397696 + }, + { + "epoch": 0.01, + "learning_rate": 1.0738205787220995e-05, + "loss": 3.3494, + "step": 2398208 + }, + { + "epoch": 0.01, + "learning_rate": 1.0729819839710475e-05, + "loss": 3.3489, + "step": 2398720 + }, + { + "epoch": 0.01, + "learning_rate": 1.0721433892199955e-05, + "loss": 3.37, + "step": 2399232 + }, + { + "epoch": 0.01, + "learning_rate": 1.0713047944689437e-05, + "loss": 3.3484, + "step": 2399744 + }, + { + "epoch": 0.01, + "learning_rate": 1.0704661997178915e-05, + "loss": 3.3482, + "step": 2400256 + }, + { + "epoch": 0.01, + "learning_rate": 1.0696276049668395e-05, + "loss": 3.3481, + "step": 2400768 + }, + { + "epoch": 0.01, + "learning_rate": 1.0687922859765338e-05, + "loss": 3.3535, + "step": 2401280 + }, + { + "epoch": 0.01, + "learning_rate": 1.0679536912254818e-05, + "loss": 3.3593, + "step": 2401792 + }, + { + "epoch": 0.01, + "learning_rate": 1.0671150964744298e-05, + "loss": 3.3648, + "step": 2402304 + }, + { + "epoch": 0.01, + "learning_rate": 1.0662765017233778e-05, + "loss": 3.353, + "step": 2402816 + }, + { + "epoch": 0.01, + "learning_rate": 1.0654379069723258e-05, + "loss": 3.3665, + "step": 2403328 + }, + { + "epoch": 0.01, + "learning_rate": 1.0645993122212738e-05, + "loss": 3.3704, + "step": 2403840 + }, + { + "epoch": 0.01, + "learning_rate": 1.0637607174702218e-05, + "loss": 3.364, + "step": 2404352 + }, + { + "epoch": 0.01, + "learning_rate": 1.0629221227191698e-05, + "loss": 3.3567, + "step": 2404864 + }, + { + "epoch": 0.01, + "learning_rate": 1.0620851658484909e-05, + "loss": 3.3617, + "step": 2405376 + }, + { + "epoch": 0.01, + "learning_rate": 1.061248208977812e-05, + "loss": 3.359, + "step": 2405888 + }, + { + "epoch": 0.01, + "learning_rate": 1.06040961422676e-05, + "loss": 3.3554, + "step": 2406400 + }, + { + "epoch": 0.01, + "learning_rate": 1.0595710194757081e-05, + "loss": 3.3568, + "step": 2406912 + }, + { + "epoch": 0.01, + "learning_rate": 1.058732424724656e-05, + "loss": 3.3659, + "step": 2407424 + }, + { + "epoch": 0.01, + "learning_rate": 1.057893829973604e-05, + "loss": 3.365, + "step": 2407936 + }, + { + "epoch": 0.01, + "learning_rate": 1.0570552352225519e-05, + "loss": 3.3592, + "step": 2408448 + }, + { + "epoch": 0.01, + "learning_rate": 1.0562166404715e-05, + "loss": 3.3378, + "step": 2408960 + }, + { + "epoch": 0.01, + "learning_rate": 1.055379683600821e-05, + "loss": 3.3481, + "step": 2409472 + }, + { + "epoch": 0.01, + "learning_rate": 1.0545410888497692e-05, + "loss": 3.3595, + "step": 2409984 + }, + { + "epoch": 0.01, + "learning_rate": 1.0537024940987172e-05, + "loss": 3.3544, + "step": 2410496 + }, + { + "epoch": 0.01, + "learning_rate": 1.052863899347665e-05, + "loss": 3.3628, + "step": 2411008 + }, + { + "epoch": 0.01, + "learning_rate": 1.0520269424769862e-05, + "loss": 3.3552, + "step": 2411520 + }, + { + "epoch": 0.02, + "learning_rate": 1.0511883477259342e-05, + "loss": 3.3477, + "step": 2412032 + }, + { + "epoch": 0.02, + "learning_rate": 1.0503497529748822e-05, + "loss": 3.3416, + "step": 2412544 + }, + { + "epoch": 0.02, + "learning_rate": 1.04951115822383e-05, + "loss": 3.3566, + "step": 2413056 + }, + { + "epoch": 0.02, + "learning_rate": 1.0486742013531513e-05, + "loss": 3.3579, + "step": 2413568 + }, + { + "epoch": 0.02, + "learning_rate": 1.0478356066020993e-05, + "loss": 3.3644, + "step": 2414080 + }, + { + "epoch": 0.02, + "learning_rate": 1.0469970118510473e-05, + "loss": 3.363, + "step": 2414592 + }, + { + "epoch": 0.02, + "learning_rate": 1.0461584170999953e-05, + "loss": 3.344, + "step": 2415104 + }, + { + "epoch": 0.02, + "learning_rate": 1.0453214602293164e-05, + "loss": 3.3587, + "step": 2415616 + }, + { + "epoch": 0.02, + "learning_rate": 1.0444828654782644e-05, + "loss": 3.3568, + "step": 2416128 + }, + { + "epoch": 0.02, + "learning_rate": 1.0436442707272123e-05, + "loss": 3.3565, + "step": 2416640 + }, + { + "epoch": 0.02, + "learning_rate": 1.0428056759761603e-05, + "loss": 3.3584, + "step": 2417152 + }, + { + "epoch": 0.02, + "learning_rate": 1.0419687191054816e-05, + "loss": 3.3494, + "step": 2417664 + }, + { + "epoch": 0.02, + "learning_rate": 1.0411301243544296e-05, + "loss": 3.3501, + "step": 2418176 + }, + { + "epoch": 0.02, + "learning_rate": 1.0402915296033774e-05, + "loss": 3.3585, + "step": 2418688 + }, + { + "epoch": 0.02, + "learning_rate": 1.0394529348523254e-05, + "loss": 3.3589, + "step": 2419200 + }, + { + "epoch": 0.02, + "learning_rate": 1.0386159779816467e-05, + "loss": 3.3519, + "step": 2419712 + }, + { + "epoch": 0.02, + "learning_rate": 1.0377773832305947e-05, + "loss": 3.3523, + "step": 2420224 + }, + { + "epoch": 0.02, + "learning_rate": 1.0369404263599157e-05, + "loss": 3.3612, + "step": 2420736 + }, + { + "epoch": 0.02, + "learning_rate": 1.0361018316088637e-05, + "loss": 3.3616, + "step": 2421248 + }, + { + "epoch": 0.02, + "learning_rate": 1.0352632368578117e-05, + "loss": 3.3443, + "step": 2421760 + }, + { + "epoch": 0.02, + "learning_rate": 1.0344246421067597e-05, + "loss": 3.3476, + "step": 2422272 + }, + { + "epoch": 0.02, + "learning_rate": 1.0335860473557077e-05, + "loss": 3.3478, + "step": 2422784 + }, + { + "epoch": 0.02, + "learning_rate": 1.0327474526046557e-05, + "loss": 3.3668, + "step": 2423296 + }, + { + "epoch": 0.02, + "learning_rate": 1.0319088578536037e-05, + "loss": 3.3528, + "step": 2423808 + }, + { + "epoch": 0.02, + "learning_rate": 1.0310719009829248e-05, + "loss": 3.3546, + "step": 2424320 + }, + { + "epoch": 0.02, + "learning_rate": 1.0302333062318728e-05, + "loss": 3.3623, + "step": 2424832 + }, + { + "epoch": 0.02, + "learning_rate": 1.0293947114808208e-05, + "loss": 3.3651, + "step": 2425344 + }, + { + "epoch": 0.02, + "learning_rate": 1.0285561167297688e-05, + "loss": 3.3554, + "step": 2425856 + }, + { + "epoch": 0.02, + "learning_rate": 1.0277175219787168e-05, + "loss": 3.3594, + "step": 2426368 + }, + { + "epoch": 0.02, + "learning_rate": 1.0268805651080378e-05, + "loss": 3.3626, + "step": 2426880 + }, + { + "epoch": 0.02, + "learning_rate": 1.026041970356986e-05, + "loss": 3.3538, + "step": 2427392 + }, + { + "epoch": 0.02, + "learning_rate": 1.0252033756059338e-05, + "loss": 3.3485, + "step": 2427904 + }, + { + "epoch": 0.02, + "learning_rate": 1.0243647808548818e-05, + "loss": 3.3547, + "step": 2428416 + }, + { + "epoch": 0.02, + "learning_rate": 1.02352618610383e-05, + "loss": 3.3486, + "step": 2428928 + }, + { + "epoch": 0.02, + "learning_rate": 1.0226875913527778e-05, + "loss": 3.3562, + "step": 2429440 + }, + { + "epoch": 0.02, + "learning_rate": 1.0218489966017258e-05, + "loss": 3.3509, + "step": 2429952 + }, + { + "epoch": 0.02, + "learning_rate": 1.0210104018506738e-05, + "loss": 3.3593, + "step": 2430464 + }, + { + "epoch": 0.02, + "learning_rate": 1.020173444979995e-05, + "loss": 3.3509, + "step": 2430976 + }, + { + "epoch": 0.02, + "learning_rate": 1.0193348502289429e-05, + "loss": 3.352, + "step": 2431488 + }, + { + "epoch": 0.02, + "learning_rate": 1.0184962554778909e-05, + "loss": 3.3555, + "step": 2432000 + }, + { + "epoch": 0.02, + "learning_rate": 1.0176592986072121e-05, + "loss": 3.3636, + "step": 2432512 + }, + { + "epoch": 0.02, + "learning_rate": 1.01682070385616e-05, + "loss": 3.3694, + "step": 2433024 + }, + { + "epoch": 0.02, + "learning_rate": 1.0159821091051081e-05, + "loss": 3.3532, + "step": 2433536 + }, + { + "epoch": 0.02, + "learning_rate": 1.0151435143540561e-05, + "loss": 3.3523, + "step": 2434048 + }, + { + "epoch": 0.02, + "learning_rate": 1.0143049196030041e-05, + "loss": 3.3606, + "step": 2434560 + }, + { + "epoch": 0.02, + "learning_rate": 1.0134679627323252e-05, + "loss": 3.3601, + "step": 2435072 + }, + { + "epoch": 0.02, + "learning_rate": 1.0126293679812732e-05, + "loss": 3.3554, + "step": 2435584 + }, + { + "epoch": 0.02, + "learning_rate": 1.0117907732302212e-05, + "loss": 3.3573, + "step": 2436096 + }, + { + "epoch": 0.02, + "learning_rate": 1.010952178479169e-05, + "loss": 3.3611, + "step": 2436608 + }, + { + "epoch": 0.02, + "learning_rate": 1.0101135837281172e-05, + "loss": 3.3545, + "step": 2437120 + }, + { + "epoch": 0.02, + "learning_rate": 1.0092749889770652e-05, + "loss": 3.3578, + "step": 2437632 + }, + { + "epoch": 0.02, + "learning_rate": 1.0084363942260132e-05, + "loss": 3.3528, + "step": 2438144 + }, + { + "epoch": 0.02, + "learning_rate": 1.0075977994749612e-05, + "loss": 3.3557, + "step": 2438656 + }, + { + "epoch": 0.02, + "learning_rate": 1.0067608426042822e-05, + "loss": 3.353, + "step": 2439168 + }, + { + "epoch": 0.02, + "learning_rate": 1.0059222478532302e-05, + "loss": 3.3463, + "step": 2439680 + }, + { + "epoch": 0.02, + "learning_rate": 1.0050836531021782e-05, + "loss": 3.3632, + "step": 2440192 + }, + { + "epoch": 0.02, + "learning_rate": 1.0042450583511262e-05, + "loss": 3.3557, + "step": 2440704 + }, + { + "epoch": 0.02, + "learning_rate": 1.0034081014804473e-05, + "loss": 3.3639, + "step": 2441216 + }, + { + "epoch": 0.02, + "learning_rate": 1.0025695067293955e-05, + "loss": 3.3481, + "step": 2441728 + }, + { + "epoch": 0.03, + "learning_rate": 1.0017309119783433e-05, + "loss": 3.3539, + "step": 2442240 + }, + { + "epoch": 0.03, + "eval_loss": 3.86250901222229, + "eval_runtime": 315.4573, + "eval_samples_per_second": 1209.644, + "eval_steps_per_second": 37.802, + "step": 2442240 + }, + { + "epoch": 1.0, + "learning_rate": 1.0008923172272913e-05, + "loss": 3.3517, + "step": 2442752 + }, + { + "epoch": 1.0, + "learning_rate": 1.0000553603566125e-05, + "loss": 3.3496, + "step": 2443264 + }, + { + "epoch": 1.0, + "learning_rate": 9.992167656055605e-06, + "loss": 3.3632, + "step": 2443776 + }, + { + "epoch": 1.0, + "learning_rate": 9.983781708545084e-06, + "loss": 3.3555, + "step": 2444288 + }, + { + "epoch": 1.0, + "learning_rate": 9.975395761034564e-06, + "loss": 3.3601, + "step": 2444800 + }, + { + "epoch": 1.0, + "learning_rate": 9.967026192327776e-06, + "loss": 3.3488, + "step": 2445312 + }, + { + "epoch": 1.0, + "learning_rate": 9.958640244817254e-06, + "loss": 3.3548, + "step": 2445824 + }, + { + "epoch": 1.0, + "learning_rate": 9.950254297306736e-06, + "loss": 3.3482, + "step": 2446336 + }, + { + "epoch": 1.0, + "learning_rate": 9.941884728599947e-06, + "loss": 3.3604, + "step": 2446848 + }, + { + "epoch": 1.0, + "learning_rate": 9.933498781089427e-06, + "loss": 3.3553, + "step": 2447360 + }, + { + "epoch": 1.0, + "learning_rate": 9.925112833578907e-06, + "loss": 3.3635, + "step": 2447872 + }, + { + "epoch": 1.0, + "learning_rate": 9.916726886068387e-06, + "loss": 3.3588, + "step": 2448384 + }, + { + "epoch": 1.0, + "learning_rate": 9.908357317361597e-06, + "loss": 3.3479, + "step": 2448896 + }, + { + "epoch": 1.0, + "learning_rate": 9.899971369851079e-06, + "loss": 3.3457, + "step": 2449408 + }, + { + "epoch": 1.0, + "learning_rate": 9.891585422340557e-06, + "loss": 3.3415, + "step": 2449920 + }, + { + "epoch": 1.0, + "learning_rate": 9.883199474830037e-06, + "loss": 3.3572, + "step": 2450432 + }, + { + "epoch": 1.0, + "learning_rate": 9.87482990612325e-06, + "loss": 3.3493, + "step": 2450944 + }, + { + "epoch": 1.0, + "learning_rate": 9.866443958612728e-06, + "loss": 3.3509, + "step": 2451456 + }, + { + "epoch": 1.0, + "learning_rate": 9.858058011102208e-06, + "loss": 3.3483, + "step": 2451968 + }, + { + "epoch": 1.0, + "learning_rate": 9.84967206359169e-06, + "loss": 3.364, + "step": 2452480 + }, + { + "epoch": 1.0, + "learning_rate": 9.8413024948849e-06, + "loss": 3.3548, + "step": 2452992 + }, + { + "epoch": 1.0, + "learning_rate": 9.832916547374379e-06, + "loss": 3.3567, + "step": 2453504 + }, + { + "epoch": 1.0, + "learning_rate": 9.82453059986386e-06, + "loss": 3.3565, + "step": 2454016 + }, + { + "epoch": 1.0, + "learning_rate": 9.81614465235334e-06, + "loss": 3.3634, + "step": 2454528 + }, + { + "epoch": 1.0, + "learning_rate": 9.807775083646551e-06, + "loss": 3.3464, + "step": 2455040 + }, + { + "epoch": 1.0, + "learning_rate": 9.799389136136031e-06, + "loss": 3.3556, + "step": 2455552 + }, + { + "epoch": 1.0, + "learning_rate": 9.791003188625511e-06, + "loss": 3.3512, + "step": 2456064 + }, + { + "epoch": 1.0, + "learning_rate": 9.782617241114991e-06, + "loss": 3.3462, + "step": 2456576 + }, + { + "epoch": 1.0, + "learning_rate": 9.774247672408202e-06, + "loss": 3.3427, + "step": 2457088 + }, + { + "epoch": 1.01, + "learning_rate": 9.765861724897682e-06, + "loss": 3.3459, + "step": 2457600 + }, + { + "epoch": 1.01, + "learning_rate": 9.757475777387162e-06, + "loss": 3.3537, + "step": 2458112 + }, + { + "epoch": 1.01, + "learning_rate": 9.749089829876643e-06, + "loss": 3.3605, + "step": 2458624 + }, + { + "epoch": 1.01, + "learning_rate": 9.740720261169852e-06, + "loss": 3.355, + "step": 2459136 + }, + { + "epoch": 1.01, + "learning_rate": 9.732334313659332e-06, + "loss": 3.3529, + "step": 2459648 + }, + { + "epoch": 1.01, + "learning_rate": 9.723948366148814e-06, + "loss": 3.3485, + "step": 2460160 + }, + { + "epoch": 1.01, + "learning_rate": 9.715562418638292e-06, + "loss": 3.3564, + "step": 2460672 + }, + { + "epoch": 1.01, + "learning_rate": 9.707192849931505e-06, + "loss": 3.3461, + "step": 2461184 + }, + { + "epoch": 1.01, + "learning_rate": 9.698806902420985e-06, + "loss": 3.3568, + "step": 2461696 + }, + { + "epoch": 1.01, + "learning_rate": 9.690420954910465e-06, + "loss": 3.3379, + "step": 2462208 + }, + { + "epoch": 1.01, + "learning_rate": 9.682035007399943e-06, + "loss": 3.3478, + "step": 2462720 + }, + { + "epoch": 1.01, + "learning_rate": 9.673681817496886e-06, + "loss": 3.3501, + "step": 2463232 + }, + { + "epoch": 1.01, + "learning_rate": 9.665295869986366e-06, + "loss": 3.3665, + "step": 2463744 + }, + { + "epoch": 1.01, + "learning_rate": 9.656909922475848e-06, + "loss": 3.3483, + "step": 2464256 + }, + { + "epoch": 1.01, + "learning_rate": 9.648523974965326e-06, + "loss": 3.3527, + "step": 2464768 + }, + { + "epoch": 1.01, + "learning_rate": 9.640138027454806e-06, + "loss": 3.3539, + "step": 2465280 + }, + { + "epoch": 1.01, + "learning_rate": 9.631752079944286e-06, + "loss": 3.3452, + "step": 2465792 + }, + { + "epoch": 1.01, + "learning_rate": 9.623366132433766e-06, + "loss": 3.3557, + "step": 2466304 + }, + { + "epoch": 1.01, + "learning_rate": 9.614980184923246e-06, + "loss": 3.3257, + "step": 2466816 + }, + { + "epoch": 1.01, + "learning_rate": 9.606610616216458e-06, + "loss": 3.3498, + "step": 2467328 + }, + { + "epoch": 1.01, + "learning_rate": 9.598224668705938e-06, + "loss": 3.3547, + "step": 2467840 + }, + { + "epoch": 1.01, + "learning_rate": 9.589838721195417e-06, + "loss": 3.3569, + "step": 2468352 + }, + { + "epoch": 1.01, + "learning_rate": 9.581452773684897e-06, + "loss": 3.3462, + "step": 2468864 + }, + { + "epoch": 1.01, + "learning_rate": 9.573083204978109e-06, + "loss": 3.3368, + "step": 2469376 + }, + { + "epoch": 1.01, + "learning_rate": 9.564697257467587e-06, + "loss": 3.3474, + "step": 2469888 + }, + { + "epoch": 1.01, + "learning_rate": 9.556311309957067e-06, + "loss": 3.3322, + "step": 2470400 + }, + { + "epoch": 1.01, + "learning_rate": 9.547925362446549e-06, + "loss": 3.3602, + "step": 2470912 + }, + { + "epoch": 1.01, + "learning_rate": 9.53955579373976e-06, + "loss": 3.3318, + "step": 2471424 + }, + { + "epoch": 1.01, + "learning_rate": 9.53116984622924e-06, + "loss": 3.3538, + "step": 2471936 + }, + { + "epoch": 1.01, + "learning_rate": 9.52278389871872e-06, + "loss": 3.3468, + "step": 2472448 + }, + { + "epoch": 1.01, + "learning_rate": 9.5143979512082e-06, + "loss": 3.3459, + "step": 2472960 + }, + { + "epoch": 1.01, + "learning_rate": 9.506044761305143e-06, + "loss": 3.3582, + "step": 2473472 + }, + { + "epoch": 1.01, + "learning_rate": 9.497658813794621e-06, + "loss": 3.3433, + "step": 2473984 + }, + { + "epoch": 1.01, + "learning_rate": 9.489272866284101e-06, + "loss": 3.3377, + "step": 2474496 + }, + { + "epoch": 1.01, + "learning_rate": 9.480886918773583e-06, + "loss": 3.3384, + "step": 2475008 + }, + { + "epoch": 1.01, + "learning_rate": 9.472500971263061e-06, + "loss": 3.3576, + "step": 2475520 + }, + { + "epoch": 1.01, + "learning_rate": 9.464115023752541e-06, + "loss": 3.3439, + "step": 2476032 + }, + { + "epoch": 1.01, + "learning_rate": 9.455729076242021e-06, + "loss": 3.3404, + "step": 2476544 + }, + { + "epoch": 1.01, + "learning_rate": 9.447343128731503e-06, + "loss": 3.3375, + "step": 2477056 + }, + { + "epoch": 1.01, + "learning_rate": 9.438989938828444e-06, + "loss": 3.3429, + "step": 2477568 + }, + { + "epoch": 1.01, + "learning_rate": 9.430603991317924e-06, + "loss": 3.3523, + "step": 2478080 + }, + { + "epoch": 1.01, + "learning_rate": 9.422218043807404e-06, + "loss": 3.3559, + "step": 2478592 + }, + { + "epoch": 1.01, + "learning_rate": 9.413832096296884e-06, + "loss": 3.3442, + "step": 2479104 + }, + { + "epoch": 1.01, + "learning_rate": 9.405446148786364e-06, + "loss": 3.3566, + "step": 2479616 + }, + { + "epoch": 1.01, + "learning_rate": 9.397060201275844e-06, + "loss": 3.3634, + "step": 2480128 + }, + { + "epoch": 1.01, + "learning_rate": 9.388674253765324e-06, + "loss": 3.3555, + "step": 2480640 + }, + { + "epoch": 1.01, + "learning_rate": 9.380288306254802e-06, + "loss": 3.3451, + "step": 2481152 + }, + { + "epoch": 1.01, + "learning_rate": 9.371935116351746e-06, + "loss": 3.3535, + "step": 2481664 + }, + { + "epoch": 1.01, + "learning_rate": 9.363549168841226e-06, + "loss": 3.3499, + "step": 2482176 + }, + { + "epoch": 1.01, + "learning_rate": 9.355163221330707e-06, + "loss": 3.3449, + "step": 2482688 + }, + { + "epoch": 1.01, + "learning_rate": 9.346777273820185e-06, + "loss": 3.3499, + "step": 2483200 + }, + { + "epoch": 1.01, + "learning_rate": 9.338391326309665e-06, + "loss": 3.3499, + "step": 2483712 + }, + { + "epoch": 1.01, + "learning_rate": 9.330005378799147e-06, + "loss": 3.3555, + "step": 2484224 + }, + { + "epoch": 1.01, + "learning_rate": 9.321619431288625e-06, + "loss": 3.3489, + "step": 2484736 + }, + { + "epoch": 1.01, + "learning_rate": 9.313233483778105e-06, + "loss": 3.331, + "step": 2485248 + }, + { + "epoch": 1.01, + "learning_rate": 9.304863915071318e-06, + "loss": 3.3419, + "step": 2485760 + }, + { + "epoch": 1.01, + "learning_rate": 9.296477967560798e-06, + "loss": 3.3476, + "step": 2486272 + }, + { + "epoch": 1.01, + "learning_rate": 9.288092020050276e-06, + "loss": 3.3503, + "step": 2486784 + }, + { + "epoch": 1.01, + "learning_rate": 9.279706072539756e-06, + "loss": 3.3518, + "step": 2487296 + }, + { + "epoch": 1.01, + "learning_rate": 9.271336503832968e-06, + "loss": 3.3475, + "step": 2487808 + }, + { + "epoch": 1.02, + "learning_rate": 9.262950556322448e-06, + "loss": 3.3419, + "step": 2488320 + }, + { + "epoch": 1.02, + "learning_rate": 9.254564608811928e-06, + "loss": 3.3305, + "step": 2488832 + }, + { + "epoch": 1.02, + "learning_rate": 9.246178661301408e-06, + "loss": 3.3485, + "step": 2489344 + }, + { + "epoch": 1.02, + "learning_rate": 9.237809092594619e-06, + "loss": 3.3473, + "step": 2489856 + }, + { + "epoch": 1.02, + "learning_rate": 9.229423145084099e-06, + "loss": 3.3516, + "step": 2490368 + }, + { + "epoch": 1.02, + "learning_rate": 9.221037197573579e-06, + "loss": 3.3544, + "step": 2490880 + }, + { + "epoch": 1.02, + "learning_rate": 9.212651250063059e-06, + "loss": 3.3385, + "step": 2491392 + }, + { + "epoch": 1.02, + "learning_rate": 9.204281681356271e-06, + "loss": 3.3491, + "step": 2491904 + }, + { + "epoch": 1.02, + "learning_rate": 9.19589573384575e-06, + "loss": 3.3501, + "step": 2492416 + }, + { + "epoch": 1.02, + "learning_rate": 9.18750978633523e-06, + "loss": 3.3466, + "step": 2492928 + }, + { + "epoch": 1.02, + "learning_rate": 9.179140217628442e-06, + "loss": 3.3493, + "step": 2493440 + }, + { + "epoch": 1.02, + "learning_rate": 9.170754270117922e-06, + "loss": 3.3427, + "step": 2493952 + }, + { + "epoch": 1.02, + "learning_rate": 9.1623683226074e-06, + "loss": 3.3402, + "step": 2494464 + }, + { + "epoch": 1.02, + "learning_rate": 9.153982375096882e-06, + "loss": 3.3499, + "step": 2494976 + }, + { + "epoch": 1.02, + "learning_rate": 9.145612806390093e-06, + "loss": 3.3496, + "step": 2495488 + }, + { + "epoch": 1.02, + "learning_rate": 9.137226858879571e-06, + "loss": 3.3426, + "step": 2496000 + }, + { + "epoch": 1.02, + "learning_rate": 9.128840911369053e-06, + "loss": 3.3417, + "step": 2496512 + }, + { + "epoch": 1.02, + "learning_rate": 9.120454963858533e-06, + "loss": 3.3565, + "step": 2497024 + }, + { + "epoch": 1.02, + "learning_rate": 9.112085395151743e-06, + "loss": 3.3478, + "step": 2497536 + }, + { + "epoch": 1.02, + "learning_rate": 9.103699447641223e-06, + "loss": 3.3389, + "step": 2498048 + }, + { + "epoch": 1.02, + "learning_rate": 9.095313500130703e-06, + "loss": 3.3397, + "step": 2498560 + }, + { + "epoch": 1.02, + "learning_rate": 9.086927552620183e-06, + "loss": 3.338, + "step": 2499072 + }, + { + "epoch": 1.02, + "learning_rate": 9.078541605109663e-06, + "loss": 3.3594, + "step": 2499584 + }, + { + "epoch": 1.02, + "learning_rate": 9.070155657599143e-06, + "loss": 3.3403, + "step": 2500096 + }, + { + "epoch": 1.02, + "learning_rate": 9.061769710088623e-06, + "loss": 3.3487, + "step": 2500608 + }, + { + "epoch": 1.02, + "learning_rate": 9.053400141381834e-06, + "loss": 3.3522, + "step": 2501120 + }, + { + "epoch": 1.02, + "learning_rate": 9.045014193871314e-06, + "loss": 3.3576, + "step": 2501632 + }, + { + "epoch": 1.02, + "learning_rate": 9.036628246360794e-06, + "loss": 3.3423, + "step": 2502144 + }, + { + "epoch": 1.02, + "learning_rate": 9.028242298850274e-06, + "loss": 3.348, + "step": 2502656 + }, + { + "epoch": 1.02, + "learning_rate": 9.019872730143486e-06, + "loss": 3.3568, + "step": 2503168 + }, + { + "epoch": 1.02, + "learning_rate": 9.011486782632965e-06, + "loss": 3.3452, + "step": 2503680 + }, + { + "epoch": 1.02, + "learning_rate": 9.003100835122445e-06, + "loss": 3.3377, + "step": 2504192 + }, + { + "epoch": 1.02, + "learning_rate": 8.994714887611926e-06, + "loss": 3.3434, + "step": 2504704 + }, + { + "epoch": 1.02, + "learning_rate": 8.986328940101404e-06, + "loss": 3.3401, + "step": 2505216 + }, + { + "epoch": 1.02, + "learning_rate": 8.977942992590884e-06, + "loss": 3.3431, + "step": 2505728 + }, + { + "epoch": 1.02, + "learning_rate": 8.969557045080364e-06, + "loss": 3.3468, + "step": 2506240 + }, + { + "epoch": 1.02, + "learning_rate": 8.961187476373575e-06, + "loss": 3.3509, + "step": 2506752 + }, + { + "epoch": 1.02, + "learning_rate": 8.952801528863055e-06, + "loss": 3.3377, + "step": 2507264 + }, + { + "epoch": 1.02, + "learning_rate": 8.944415581352537e-06, + "loss": 3.3402, + "step": 2507776 + }, + { + "epoch": 1.02, + "learning_rate": 8.936029633842017e-06, + "loss": 3.3442, + "step": 2508288 + }, + { + "epoch": 1.02, + "learning_rate": 8.927643686331495e-06, + "loss": 3.3599, + "step": 2508800 + }, + { + "epoch": 1.02, + "learning_rate": 8.919257738820975e-06, + "loss": 3.362, + "step": 2509312 + }, + { + "epoch": 1.02, + "learning_rate": 8.910871791310457e-06, + "loss": 3.3439, + "step": 2509824 + }, + { + "epoch": 1.02, + "learning_rate": 8.902485843799935e-06, + "loss": 3.3429, + "step": 2510336 + }, + { + "epoch": 1.02, + "learning_rate": 8.894116275093146e-06, + "loss": 3.35, + "step": 2510848 + }, + { + "epoch": 1.02, + "learning_rate": 8.885746706386358e-06, + "loss": 3.3519, + "step": 2511360 + }, + { + "epoch": 1.02, + "learning_rate": 8.877360758875838e-06, + "loss": 3.3471, + "step": 2511872 + }, + { + "epoch": 1.02, + "learning_rate": 8.868974811365318e-06, + "loss": 3.3455, + "step": 2512384 + }, + { + "epoch": 1.02, + "learning_rate": 8.860588863854798e-06, + "loss": 3.3536, + "step": 2512896 + }, + { + "epoch": 1.02, + "learning_rate": 8.852202916344278e-06, + "loss": 3.3439, + "step": 2513408 + }, + { + "epoch": 1.02, + "learning_rate": 8.843816968833756e-06, + "loss": 3.3492, + "step": 2513920 + }, + { + "epoch": 1.02, + "learning_rate": 8.835431021323238e-06, + "loss": 3.3427, + "step": 2514432 + }, + { + "epoch": 1.02, + "learning_rate": 8.827045073812718e-06, + "loss": 3.3489, + "step": 2514944 + }, + { + "epoch": 1.02, + "learning_rate": 8.818675505105929e-06, + "loss": 3.3435, + "step": 2515456 + }, + { + "epoch": 1.02, + "learning_rate": 8.810289557595409e-06, + "loss": 3.3346, + "step": 2515968 + }, + { + "epoch": 1.02, + "learning_rate": 8.801903610084889e-06, + "loss": 3.353, + "step": 2516480 + }, + { + "epoch": 1.02, + "learning_rate": 8.793517662574368e-06, + "loss": 3.3482, + "step": 2516992 + }, + { + "epoch": 1.02, + "learning_rate": 8.785148093867581e-06, + "loss": 3.3559, + "step": 2517504 + }, + { + "epoch": 1.02, + "learning_rate": 8.77676214635706e-06, + "loss": 3.3418, + "step": 2518016 + }, + { + "epoch": 1.02, + "learning_rate": 8.76837619884654e-06, + "loss": 3.3429, + "step": 2518528 + }, + { + "epoch": 1.03, + "eval_loss": 3.8624041080474854, + "eval_runtime": 318.873, + "eval_samples_per_second": 1196.686, + "eval_steps_per_second": 37.397, + "step": 2518560 + }, + { + "epoch": 0.0, + "learning_rate": 8.759990251336019e-06, + "loss": 3.3405, + "step": 2519040 + }, + { + "epoch": 0.0, + "learning_rate": 8.751604303825499e-06, + "loss": 3.3449, + "step": 2519552 + }, + { + "epoch": 0.0, + "learning_rate": 8.743218356314979e-06, + "loss": 3.3539, + "step": 2520064 + }, + { + "epoch": 0.0, + "learning_rate": 8.734848787608192e-06, + "loss": 3.3438, + "step": 2520576 + }, + { + "epoch": 0.0, + "learning_rate": 8.726462840097671e-06, + "loss": 3.3532, + "step": 2521088 + }, + { + "epoch": 0.0, + "learning_rate": 8.71807689258715e-06, + "loss": 3.3395, + "step": 2521600 + }, + { + "epoch": 0.0, + "learning_rate": 8.70969094507663e-06, + "loss": 3.3473, + "step": 2522112 + }, + { + "epoch": 0.0, + "learning_rate": 8.701321376369842e-06, + "loss": 3.3394, + "step": 2522624 + }, + { + "epoch": 0.0, + "learning_rate": 8.69293542885932e-06, + "loss": 3.3476, + "step": 2523136 + }, + { + "epoch": 0.0, + "learning_rate": 8.684549481348802e-06, + "loss": 3.3489, + "step": 2523648 + }, + { + "epoch": 0.0, + "learning_rate": 8.676163533838282e-06, + "loss": 3.3507, + "step": 2524160 + }, + { + "epoch": 0.0, + "learning_rate": 8.667793965131493e-06, + "loss": 3.3487, + "step": 2524672 + }, + { + "epoch": 0.0, + "learning_rate": 8.659408017620973e-06, + "loss": 3.3369, + "step": 2525184 + }, + { + "epoch": 0.0, + "learning_rate": 8.651022070110453e-06, + "loss": 3.3393, + "step": 2525696 + }, + { + "epoch": 0.0, + "learning_rate": 8.642636122599933e-06, + "loss": 3.3383, + "step": 2526208 + }, + { + "epoch": 0.0, + "learning_rate": 8.634266553893145e-06, + "loss": 3.3386, + "step": 2526720 + }, + { + "epoch": 0.0, + "learning_rate": 8.625880606382623e-06, + "loss": 3.3423, + "step": 2527232 + }, + { + "epoch": 0.0, + "learning_rate": 8.617494658872103e-06, + "loss": 3.3414, + "step": 2527744 + }, + { + "epoch": 0.0, + "learning_rate": 8.609108711361583e-06, + "loss": 3.3399, + "step": 2528256 + }, + { + "epoch": 0.0, + "learning_rate": 8.600739142654794e-06, + "loss": 3.3564, + "step": 2528768 + }, + { + "epoch": 0.0, + "learning_rate": 8.592353195144274e-06, + "loss": 3.3455, + "step": 2529280 + }, + { + "epoch": 0.0, + "learning_rate": 8.583967247633754e-06, + "loss": 3.3506, + "step": 2529792 + }, + { + "epoch": 0.0, + "learning_rate": 8.575581300123236e-06, + "loss": 3.3427, + "step": 2530304 + }, + { + "epoch": 0.0, + "learning_rate": 8.567211731416445e-06, + "loss": 3.3593, + "step": 2530816 + }, + { + "epoch": 0.0, + "learning_rate": 8.558825783905926e-06, + "loss": 3.3319, + "step": 2531328 + }, + { + "epoch": 0.0, + "learning_rate": 8.550439836395406e-06, + "loss": 3.3498, + "step": 2531840 + }, + { + "epoch": 0.0, + "learning_rate": 8.542053888884885e-06, + "loss": 3.3402, + "step": 2532352 + }, + { + "epoch": 0.0, + "learning_rate": 8.533684320178097e-06, + "loss": 3.3439, + "step": 2532864 + }, + { + "epoch": 0.0, + "learning_rate": 8.525298372667577e-06, + "loss": 3.3343, + "step": 2533376 + }, + { + "epoch": 0.01, + "learning_rate": 8.516912425157057e-06, + "loss": 3.3331, + "step": 2533888 + }, + { + "epoch": 0.01, + "learning_rate": 8.508526477646537e-06, + "loss": 3.3453, + "step": 2534400 + }, + { + "epoch": 0.01, + "learning_rate": 8.500156908939748e-06, + "loss": 3.3532, + "step": 2534912 + }, + { + "epoch": 0.01, + "learning_rate": 8.491770961429228e-06, + "loss": 3.3412, + "step": 2535424 + }, + { + "epoch": 0.01, + "learning_rate": 8.483385013918708e-06, + "loss": 3.3498, + "step": 2535936 + }, + { + "epoch": 0.01, + "learning_rate": 8.474999066408188e-06, + "loss": 3.3359, + "step": 2536448 + }, + { + "epoch": 0.01, + "learning_rate": 8.466629497701398e-06, + "loss": 3.3452, + "step": 2536960 + }, + { + "epoch": 0.01, + "learning_rate": 8.45824355019088e-06, + "loss": 3.3394, + "step": 2537472 + }, + { + "epoch": 0.01, + "learning_rate": 8.449857602680358e-06, + "loss": 3.3475, + "step": 2537984 + }, + { + "epoch": 0.01, + "learning_rate": 8.441471655169838e-06, + "loss": 3.3311, + "step": 2538496 + }, + { + "epoch": 0.01, + "learning_rate": 8.43310208646305e-06, + "loss": 3.3393, + "step": 2539008 + }, + { + "epoch": 0.01, + "learning_rate": 8.424732517756262e-06, + "loss": 3.3391, + "step": 2539520 + }, + { + "epoch": 0.01, + "learning_rate": 8.416346570245742e-06, + "loss": 3.3576, + "step": 2540032 + }, + { + "epoch": 0.01, + "learning_rate": 8.407960622735222e-06, + "loss": 3.3375, + "step": 2540544 + }, + { + "epoch": 0.01, + "learning_rate": 8.399574675224701e-06, + "loss": 3.3454, + "step": 2541056 + }, + { + "epoch": 0.01, + "learning_rate": 8.391188727714181e-06, + "loss": 3.3462, + "step": 2541568 + }, + { + "epoch": 0.01, + "learning_rate": 8.382802780203661e-06, + "loss": 3.3365, + "step": 2542080 + }, + { + "epoch": 0.01, + "learning_rate": 8.374416832693141e-06, + "loss": 3.3469, + "step": 2542592 + }, + { + "epoch": 0.01, + "learning_rate": 8.366030885182621e-06, + "loss": 3.3197, + "step": 2543104 + }, + { + "epoch": 0.01, + "learning_rate": 8.357661316475832e-06, + "loss": 3.3403, + "step": 2543616 + }, + { + "epoch": 0.01, + "learning_rate": 8.349275368965312e-06, + "loss": 3.346, + "step": 2544128 + }, + { + "epoch": 0.01, + "learning_rate": 8.340889421454792e-06, + "loss": 3.3421, + "step": 2544640 + }, + { + "epoch": 0.01, + "learning_rate": 8.332503473944272e-06, + "loss": 3.3381, + "step": 2545152 + }, + { + "epoch": 0.01, + "learning_rate": 8.324133905237483e-06, + "loss": 3.3332, + "step": 2545664 + }, + { + "epoch": 0.01, + "learning_rate": 8.315747957726963e-06, + "loss": 3.3386, + "step": 2546176 + }, + { + "epoch": 0.01, + "learning_rate": 8.307362010216443e-06, + "loss": 3.324, + "step": 2546688 + }, + { + "epoch": 0.01, + "learning_rate": 8.298976062705923e-06, + "loss": 3.3458, + "step": 2547200 + }, + { + "epoch": 0.01, + "learning_rate": 8.290606493999133e-06, + "loss": 3.3278, + "step": 2547712 + }, + { + "epoch": 0.01, + "learning_rate": 8.282220546488615e-06, + "loss": 3.341, + "step": 2548224 + }, + { + "epoch": 0.01, + "learning_rate": 8.273834598978095e-06, + "loss": 3.3376, + "step": 2548736 + }, + { + "epoch": 0.01, + "learning_rate": 8.265448651467573e-06, + "loss": 3.3382, + "step": 2549248 + }, + { + "epoch": 0.01, + "learning_rate": 8.257095461564517e-06, + "loss": 3.3484, + "step": 2549760 + }, + { + "epoch": 0.01, + "learning_rate": 8.248709514053997e-06, + "loss": 3.3385, + "step": 2550272 + }, + { + "epoch": 0.01, + "learning_rate": 8.240323566543477e-06, + "loss": 3.3271, + "step": 2550784 + }, + { + "epoch": 0.01, + "learning_rate": 8.231937619032956e-06, + "loss": 3.3246, + "step": 2551296 + }, + { + "epoch": 0.01, + "learning_rate": 8.223551671522436e-06, + "loss": 3.3506, + "step": 2551808 + }, + { + "epoch": 0.01, + "learning_rate": 8.215165724011916e-06, + "loss": 3.3345, + "step": 2552320 + }, + { + "epoch": 0.01, + "learning_rate": 8.206779776501396e-06, + "loss": 3.3307, + "step": 2552832 + }, + { + "epoch": 0.01, + "learning_rate": 8.198410207794607e-06, + "loss": 3.3301, + "step": 2553344 + }, + { + "epoch": 0.01, + "learning_rate": 8.190024260284087e-06, + "loss": 3.3353, + "step": 2553856 + }, + { + "epoch": 0.01, + "learning_rate": 8.181638312773569e-06, + "loss": 3.3402, + "step": 2554368 + }, + { + "epoch": 0.01, + "learning_rate": 8.173252365263047e-06, + "loss": 3.3434, + "step": 2554880 + }, + { + "epoch": 0.01, + "learning_rate": 8.164866417752527e-06, + "loss": 3.3392, + "step": 2555392 + }, + { + "epoch": 0.01, + "learning_rate": 8.15649684904574e-06, + "loss": 3.3483, + "step": 2555904 + }, + { + "epoch": 0.01, + "learning_rate": 8.148110901535218e-06, + "loss": 3.3504, + "step": 2556416 + }, + { + "epoch": 0.01, + "learning_rate": 8.139724954024698e-06, + "loss": 3.3496, + "step": 2556928 + }, + { + "epoch": 0.01, + "learning_rate": 8.131339006514178e-06, + "loss": 3.3352, + "step": 2557440 + }, + { + "epoch": 0.01, + "learning_rate": 8.12295305900366e-06, + "loss": 3.345, + "step": 2557952 + }, + { + "epoch": 0.01, + "learning_rate": 8.114567111493138e-06, + "loss": 3.3393, + "step": 2558464 + }, + { + "epoch": 0.01, + "learning_rate": 8.106181163982617e-06, + "loss": 3.339, + "step": 2558976 + }, + { + "epoch": 0.01, + "learning_rate": 8.097795216472097e-06, + "loss": 3.3405, + "step": 2559488 + }, + { + "epoch": 0.01, + "learning_rate": 8.089425647765308e-06, + "loss": 3.3433, + "step": 2560000 + }, + { + "epoch": 0.01, + "learning_rate": 8.081039700254788e-06, + "loss": 3.3445, + "step": 2560512 + }, + { + "epoch": 0.01, + "learning_rate": 8.07265375274427e-06, + "loss": 3.3416, + "step": 2561024 + }, + { + "epoch": 0.01, + "learning_rate": 8.06428418403748e-06, + "loss": 3.3227, + "step": 2561536 + }, + { + "epoch": 0.01, + "learning_rate": 8.05589823652696e-06, + "loss": 3.3319, + "step": 2562048 + }, + { + "epoch": 0.01, + "learning_rate": 8.04751228901644e-06, + "loss": 3.3398, + "step": 2562560 + }, + { + "epoch": 0.01, + "learning_rate": 8.03912634150592e-06, + "loss": 3.3438, + "step": 2563072 + }, + { + "epoch": 0.01, + "learning_rate": 8.030740393995399e-06, + "loss": 3.3441, + "step": 2563584 + }, + { + "epoch": 0.01, + "learning_rate": 8.02235444648488e-06, + "loss": 3.3372, + "step": 2564096 + }, + { + "epoch": 0.02, + "learning_rate": 8.01396849897436e-06, + "loss": 3.3369, + "step": 2564608 + }, + { + "epoch": 0.02, + "learning_rate": 8.00558255146384e-06, + "loss": 3.319, + "step": 2565120 + }, + { + "epoch": 0.02, + "learning_rate": 7.997212982757051e-06, + "loss": 3.3345, + "step": 2565632 + }, + { + "epoch": 0.02, + "learning_rate": 7.988843414050262e-06, + "loss": 3.3403, + "step": 2566144 + }, + { + "epoch": 0.02, + "learning_rate": 7.980457466539742e-06, + "loss": 3.3416, + "step": 2566656 + }, + { + "epoch": 0.02, + "learning_rate": 7.972071519029223e-06, + "loss": 3.3434, + "step": 2567168 + }, + { + "epoch": 0.02, + "learning_rate": 7.963685571518702e-06, + "loss": 3.334, + "step": 2567680 + }, + { + "epoch": 0.02, + "learning_rate": 7.955299624008182e-06, + "loss": 3.3378, + "step": 2568192 + }, + { + "epoch": 0.02, + "learning_rate": 7.946913676497662e-06, + "loss": 3.3437, + "step": 2568704 + }, + { + "epoch": 0.02, + "learning_rate": 7.938527728987142e-06, + "loss": 3.3397, + "step": 2569216 + }, + { + "epoch": 0.02, + "learning_rate": 7.930141781476622e-06, + "loss": 3.3357, + "step": 2569728 + }, + { + "epoch": 0.02, + "learning_rate": 7.921772212769834e-06, + "loss": 3.3365, + "step": 2570240 + }, + { + "epoch": 0.02, + "learning_rate": 7.913386265259314e-06, + "loss": 3.3313, + "step": 2570752 + }, + { + "epoch": 0.02, + "learning_rate": 7.905000317748792e-06, + "loss": 3.3411, + "step": 2571264 + }, + { + "epoch": 0.02, + "learning_rate": 7.896630749042005e-06, + "loss": 3.3449, + "step": 2571776 + }, + { + "epoch": 0.02, + "learning_rate": 7.888244801531485e-06, + "loss": 3.3238, + "step": 2572288 + }, + { + "epoch": 0.02, + "learning_rate": 7.879858854020963e-06, + "loss": 3.3358, + "step": 2572800 + }, + { + "epoch": 0.02, + "learning_rate": 7.871472906510443e-06, + "loss": 3.3474, + "step": 2573312 + }, + { + "epoch": 0.02, + "learning_rate": 7.863103337803655e-06, + "loss": 3.3399, + "step": 2573824 + }, + { + "epoch": 0.02, + "learning_rate": 7.854717390293135e-06, + "loss": 3.3267, + "step": 2574336 + }, + { + "epoch": 0.02, + "learning_rate": 7.846331442782615e-06, + "loss": 3.3317, + "step": 2574848 + }, + { + "epoch": 0.02, + "learning_rate": 7.837945495272095e-06, + "loss": 3.3292, + "step": 2575360 + }, + { + "epoch": 0.02, + "learning_rate": 7.829559547761575e-06, + "loss": 3.3507, + "step": 2575872 + }, + { + "epoch": 0.02, + "learning_rate": 7.821173600251053e-06, + "loss": 3.3314, + "step": 2576384 + }, + { + "epoch": 0.02, + "learning_rate": 7.812804031544266e-06, + "loss": 3.3391, + "step": 2576896 + }, + { + "epoch": 0.02, + "learning_rate": 7.804418084033746e-06, + "loss": 3.3385, + "step": 2577408 + }, + { + "epoch": 0.02, + "learning_rate": 7.796032136523226e-06, + "loss": 3.3506, + "step": 2577920 + }, + { + "epoch": 0.02, + "learning_rate": 7.787646189012706e-06, + "loss": 3.3342, + "step": 2578432 + }, + { + "epoch": 0.02, + "learning_rate": 7.779260241502186e-06, + "loss": 3.3432, + "step": 2578944 + }, + { + "epoch": 0.02, + "learning_rate": 7.770890672795397e-06, + "loss": 3.3468, + "step": 2579456 + }, + { + "epoch": 0.02, + "learning_rate": 7.762504725284877e-06, + "loss": 3.3345, + "step": 2579968 + }, + { + "epoch": 0.02, + "learning_rate": 7.754118777774357e-06, + "loss": 3.3326, + "step": 2580480 + }, + { + "epoch": 0.02, + "learning_rate": 7.745732830263836e-06, + "loss": 3.3352, + "step": 2580992 + }, + { + "epoch": 0.02, + "learning_rate": 7.737346882753316e-06, + "loss": 3.3309, + "step": 2581504 + }, + { + "epoch": 0.02, + "learning_rate": 7.728960935242796e-06, + "loss": 3.3342, + "step": 2582016 + }, + { + "epoch": 0.02, + "learning_rate": 7.720574987732276e-06, + "loss": 3.3384, + "step": 2582528 + }, + { + "epoch": 0.02, + "learning_rate": 7.712189040221756e-06, + "loss": 3.3388, + "step": 2583040 + }, + { + "epoch": 0.02, + "learning_rate": 7.703819471514967e-06, + "loss": 3.3282, + "step": 2583552 + }, + { + "epoch": 0.02, + "learning_rate": 7.695433524004447e-06, + "loss": 3.3314, + "step": 2584064 + }, + { + "epoch": 0.02, + "learning_rate": 7.687047576493927e-06, + "loss": 3.3342, + "step": 2584576 + }, + { + "epoch": 0.02, + "learning_rate": 7.678661628983409e-06, + "loss": 3.3504, + "step": 2585088 + }, + { + "epoch": 0.02, + "learning_rate": 7.670292060276618e-06, + "loss": 3.3536, + "step": 2585600 + }, + { + "epoch": 0.02, + "learning_rate": 7.661906112766098e-06, + "loss": 3.3383, + "step": 2586112 + }, + { + "epoch": 0.02, + "learning_rate": 7.65352016525558e-06, + "loss": 3.3291, + "step": 2586624 + }, + { + "epoch": 0.02, + "learning_rate": 7.645134217745058e-06, + "loss": 3.3434, + "step": 2587136 + }, + { + "epoch": 0.02, + "learning_rate": 7.636781027842001e-06, + "loss": 3.3397, + "step": 2587648 + }, + { + "epoch": 0.02, + "learning_rate": 7.628395080331481e-06, + "loss": 3.3407, + "step": 2588160 + }, + { + "epoch": 0.02, + "learning_rate": 7.620009132820962e-06, + "loss": 3.3355, + "step": 2588672 + }, + { + "epoch": 0.02, + "learning_rate": 7.61162318531044e-06, + "loss": 3.3447, + "step": 2589184 + }, + { + "epoch": 0.02, + "learning_rate": 7.603237237799921e-06, + "loss": 3.3333, + "step": 2589696 + }, + { + "epoch": 0.02, + "learning_rate": 7.594851290289401e-06, + "loss": 3.3423, + "step": 2590208 + }, + { + "epoch": 0.02, + "learning_rate": 7.5864653427788815e-06, + "loss": 3.3365, + "step": 2590720 + }, + { + "epoch": 0.02, + "learning_rate": 7.57807939526836e-06, + "loss": 3.3369, + "step": 2591232 + }, + { + "epoch": 0.02, + "learning_rate": 7.569709826561571e-06, + "loss": 3.3367, + "step": 2591744 + }, + { + "epoch": 0.02, + "learning_rate": 7.561323879051052e-06, + "loss": 3.328, + "step": 2592256 + }, + { + "epoch": 0.02, + "learning_rate": 7.552937931540531e-06, + "loss": 3.3428, + "step": 2592768 + }, + { + "epoch": 0.02, + "learning_rate": 7.544551984030011e-06, + "loss": 3.343, + "step": 2593280 + }, + { + "epoch": 0.02, + "learning_rate": 7.536182415323223e-06, + "loss": 3.3451, + "step": 2593792 + }, + { + "epoch": 0.02, + "learning_rate": 7.527796467812704e-06, + "loss": 3.3312, + "step": 2594304 + }, + { + "epoch": 0.02, + "learning_rate": 7.519410520302182e-06, + "loss": 3.3318, + "step": 2594816 + }, + { + "epoch": 0.03, + "eval_loss": 3.8638410568237305, + "eval_runtime": 326.8892, + "eval_samples_per_second": 1167.341, + "eval_steps_per_second": 36.48, + "step": 2594880 + }, + { + "epoch": 1.0, + "learning_rate": 7.511024572791663e-06, + "loss": 3.3352, + "step": 2595328 + }, + { + "epoch": 1.0, + "learning_rate": 7.502655004084874e-06, + "loss": 3.3357, + "step": 2595840 + }, + { + "epoch": 1.0, + "learning_rate": 7.494269056574354e-06, + "loss": 3.3418, + "step": 2596352 + }, + { + "epoch": 1.0, + "learning_rate": 7.4858831090638335e-06, + "loss": 3.3333, + "step": 2596864 + }, + { + "epoch": 1.0, + "learning_rate": 7.4774971615533134e-06, + "loss": 3.3467, + "step": 2597376 + }, + { + "epoch": 1.0, + "learning_rate": 7.469127592846525e-06, + "loss": 3.33, + "step": 2597888 + }, + { + "epoch": 1.0, + "learning_rate": 7.460741645336004e-06, + "loss": 3.3375, + "step": 2598400 + }, + { + "epoch": 1.0, + "learning_rate": 7.452355697825485e-06, + "loss": 3.3297, + "step": 2598912 + }, + { + "epoch": 1.0, + "learning_rate": 7.443969750314965e-06, + "loss": 3.3426, + "step": 2599424 + }, + { + "epoch": 1.0, + "learning_rate": 7.4356001816081766e-06, + "loss": 3.3388, + "step": 2599936 + }, + { + "epoch": 1.0, + "learning_rate": 7.427214234097656e-06, + "loss": 3.3424, + "step": 2600448 + }, + { + "epoch": 1.0, + "learning_rate": 7.418828286587136e-06, + "loss": 3.3394, + "step": 2600960 + }, + { + "epoch": 1.0, + "learning_rate": 7.4104423390766164e-06, + "loss": 3.3259, + "step": 2601472 + }, + { + "epoch": 1.0, + "learning_rate": 7.402072770369828e-06, + "loss": 3.3296, + "step": 2601984 + }, + { + "epoch": 1.0, + "learning_rate": 7.393686822859306e-06, + "loss": 3.3303, + "step": 2602496 + }, + { + "epoch": 1.0, + "learning_rate": 7.385300875348787e-06, + "loss": 3.3325, + "step": 2603008 + }, + { + "epoch": 1.0, + "learning_rate": 7.376931306641999e-06, + "loss": 3.3327, + "step": 2603520 + }, + { + "epoch": 1.0, + "learning_rate": 7.368545359131478e-06, + "loss": 3.3312, + "step": 2604032 + }, + { + "epoch": 1.0, + "learning_rate": 7.360159411620958e-06, + "loss": 3.3322, + "step": 2604544 + }, + { + "epoch": 1.0, + "learning_rate": 7.351773464110439e-06, + "loss": 3.3504, + "step": 2605056 + }, + { + "epoch": 1.0, + "learning_rate": 7.34340389540365e-06, + "loss": 3.3388, + "step": 2605568 + }, + { + "epoch": 1.0, + "learning_rate": 7.3350179478931285e-06, + "loss": 3.3389, + "step": 2606080 + }, + { + "epoch": 1.0, + "learning_rate": 7.326632000382609e-06, + "loss": 3.3382, + "step": 2606592 + }, + { + "epoch": 1.0, + "learning_rate": 7.318246052872089e-06, + "loss": 3.3431, + "step": 2607104 + }, + { + "epoch": 1.0, + "learning_rate": 7.309876484165301e-06, + "loss": 3.3252, + "step": 2607616 + }, + { + "epoch": 1.0, + "learning_rate": 7.30149053665478e-06, + "loss": 3.338, + "step": 2608128 + }, + { + "epoch": 1.0, + "learning_rate": 7.29310458914426e-06, + "loss": 3.3371, + "step": 2608640 + }, + { + "epoch": 1.0, + "learning_rate": 7.284718641633741e-06, + "loss": 3.3331, + "step": 2609152 + }, + { + "epoch": 1.0, + "learning_rate": 7.276349072926951e-06, + "loss": 3.3247, + "step": 2609664 + }, + { + "epoch": 1.01, + "learning_rate": 7.2679631254164316e-06, + "loss": 3.3233, + "step": 2610176 + }, + { + "epoch": 1.01, + "learning_rate": 7.2595771779059115e-06, + "loss": 3.3368, + "step": 2610688 + }, + { + "epoch": 1.01, + "learning_rate": 7.251191230395392e-06, + "loss": 3.3445, + "step": 2611200 + }, + { + "epoch": 1.01, + "learning_rate": 7.242821661688602e-06, + "loss": 3.3347, + "step": 2611712 + }, + { + "epoch": 1.01, + "learning_rate": 7.234435714178082e-06, + "loss": 3.3408, + "step": 2612224 + }, + { + "epoch": 1.01, + "learning_rate": 7.226049766667563e-06, + "loss": 3.3273, + "step": 2612736 + }, + { + "epoch": 1.01, + "learning_rate": 7.217663819157042e-06, + "loss": 3.3346, + "step": 2613248 + }, + { + "epoch": 1.01, + "learning_rate": 7.209294250450254e-06, + "loss": 3.3282, + "step": 2613760 + }, + { + "epoch": 1.01, + "learning_rate": 7.200908302939734e-06, + "loss": 3.3415, + "step": 2614272 + }, + { + "epoch": 1.01, + "learning_rate": 7.192522355429214e-06, + "loss": 3.3182, + "step": 2614784 + }, + { + "epoch": 1.01, + "learning_rate": 7.184136407918693e-06, + "loss": 3.3317, + "step": 2615296 + }, + { + "epoch": 1.01, + "learning_rate": 7.175783218015636e-06, + "loss": 3.3294, + "step": 2615808 + }, + { + "epoch": 1.01, + "learning_rate": 7.167397270505116e-06, + "loss": 3.3477, + "step": 2616320 + }, + { + "epoch": 1.01, + "learning_rate": 7.159011322994597e-06, + "loss": 3.3316, + "step": 2616832 + }, + { + "epoch": 1.01, + "learning_rate": 7.150625375484075e-06, + "loss": 3.3337, + "step": 2617344 + }, + { + "epoch": 1.01, + "learning_rate": 7.142239427973556e-06, + "loss": 3.3386, + "step": 2617856 + }, + { + "epoch": 1.01, + "learning_rate": 7.133853480463036e-06, + "loss": 3.328, + "step": 2618368 + }, + { + "epoch": 1.01, + "learning_rate": 7.125467532952515e-06, + "loss": 3.3355, + "step": 2618880 + }, + { + "epoch": 1.01, + "learning_rate": 7.117081585441995e-06, + "loss": 3.3142, + "step": 2619392 + }, + { + "epoch": 1.01, + "learning_rate": 7.108712016735207e-06, + "loss": 3.3289, + "step": 2619904 + }, + { + "epoch": 1.01, + "learning_rate": 7.100326069224687e-06, + "loss": 3.3375, + "step": 2620416 + }, + { + "epoch": 1.01, + "learning_rate": 7.0919401217141665e-06, + "loss": 3.3317, + "step": 2620928 + }, + { + "epoch": 1.01, + "learning_rate": 7.0835541742036464e-06, + "loss": 3.331, + "step": 2621440 + }, + { + "epoch": 1.01, + "learning_rate": 7.075184605496858e-06, + "loss": 3.3254, + "step": 2621952 + }, + { + "epoch": 1.01, + "learning_rate": 7.066798657986337e-06, + "loss": 3.3311, + "step": 2622464 + }, + { + "epoch": 1.01, + "learning_rate": 7.058412710475817e-06, + "loss": 3.3154, + "step": 2622976 + }, + { + "epoch": 1.01, + "learning_rate": 7.050026762965298e-06, + "loss": 3.331, + "step": 2623488 + }, + { + "epoch": 1.01, + "learning_rate": 7.04165719425851e-06, + "loss": 3.3179, + "step": 2624000 + }, + { + "epoch": 1.01, + "learning_rate": 7.033271246747989e-06, + "loss": 3.3355, + "step": 2624512 + }, + { + "epoch": 1.01, + "learning_rate": 7.024885299237469e-06, + "loss": 3.3308, + "step": 2625024 + }, + { + "epoch": 1.01, + "learning_rate": 7.016499351726949e-06, + "loss": 3.3286, + "step": 2625536 + }, + { + "epoch": 1.01, + "learning_rate": 7.008146161823892e-06, + "loss": 3.3349, + "step": 2626048 + }, + { + "epoch": 1.01, + "learning_rate": 6.999760214313371e-06, + "loss": 3.3342, + "step": 2626560 + }, + { + "epoch": 1.01, + "learning_rate": 6.991374266802851e-06, + "loss": 3.3165, + "step": 2627072 + }, + { + "epoch": 1.01, + "learning_rate": 6.982988319292332e-06, + "loss": 3.3229, + "step": 2627584 + }, + { + "epoch": 1.01, + "learning_rate": 6.97460237178181e-06, + "loss": 3.3326, + "step": 2628096 + }, + { + "epoch": 1.01, + "learning_rate": 6.966216424271291e-06, + "loss": 3.3307, + "step": 2628608 + }, + { + "epoch": 1.01, + "learning_rate": 6.957830476760771e-06, + "loss": 3.3241, + "step": 2629120 + }, + { + "epoch": 1.01, + "learning_rate": 6.949444529250252e-06, + "loss": 3.3178, + "step": 2629632 + }, + { + "epoch": 1.01, + "learning_rate": 6.941091339347193e-06, + "loss": 3.3227, + "step": 2630144 + }, + { + "epoch": 1.01, + "learning_rate": 6.932705391836673e-06, + "loss": 3.3344, + "step": 2630656 + }, + { + "epoch": 1.01, + "learning_rate": 6.924319444326154e-06, + "loss": 3.3322, + "step": 2631168 + }, + { + "epoch": 1.01, + "learning_rate": 6.915933496815634e-06, + "loss": 3.3268, + "step": 2631680 + }, + { + "epoch": 1.01, + "learning_rate": 6.907547549305113e-06, + "loss": 3.3432, + "step": 2632192 + }, + { + "epoch": 1.01, + "learning_rate": 6.899161601794593e-06, + "loss": 3.3414, + "step": 2632704 + }, + { + "epoch": 1.01, + "learning_rate": 6.890775654284074e-06, + "loss": 3.3429, + "step": 2633216 + }, + { + "epoch": 1.01, + "learning_rate": 6.882389706773552e-06, + "loss": 3.3202, + "step": 2633728 + }, + { + "epoch": 1.01, + "learning_rate": 6.874036516870495e-06, + "loss": 3.3396, + "step": 2634240 + }, + { + "epoch": 1.01, + "learning_rate": 6.865650569359975e-06, + "loss": 3.3285, + "step": 2634752 + }, + { + "epoch": 1.01, + "learning_rate": 6.857264621849456e-06, + "loss": 3.3283, + "step": 2635264 + }, + { + "epoch": 1.01, + "learning_rate": 6.848878674338935e-06, + "loss": 3.3332, + "step": 2635776 + }, + { + "epoch": 1.01, + "learning_rate": 6.840492726828415e-06, + "loss": 3.3353, + "step": 2636288 + }, + { + "epoch": 1.01, + "learning_rate": 6.832106779317895e-06, + "loss": 3.3337, + "step": 2636800 + }, + { + "epoch": 1.01, + "learning_rate": 6.823720831807374e-06, + "loss": 3.3349, + "step": 2637312 + }, + { + "epoch": 1.01, + "learning_rate": 6.815334884296855e-06, + "loss": 3.3138, + "step": 2637824 + }, + { + "epoch": 1.01, + "learning_rate": 6.8069816943937976e-06, + "loss": 3.3223, + "step": 2638336 + }, + { + "epoch": 1.01, + "learning_rate": 6.798595746883278e-06, + "loss": 3.33, + "step": 2638848 + }, + { + "epoch": 1.01, + "learning_rate": 6.790209799372757e-06, + "loss": 3.3351, + "step": 2639360 + }, + { + "epoch": 1.01, + "learning_rate": 6.7818238518622374e-06, + "loss": 3.3374, + "step": 2639872 + }, + { + "epoch": 1.01, + "learning_rate": 6.773437904351717e-06, + "loss": 3.3269, + "step": 2640384 + }, + { + "epoch": 1.02, + "learning_rate": 6.765051956841198e-06, + "loss": 3.3276, + "step": 2640896 + }, + { + "epoch": 1.02, + "learning_rate": 6.756666009330677e-06, + "loss": 3.3129, + "step": 2641408 + }, + { + "epoch": 1.02, + "learning_rate": 6.748280061820157e-06, + "loss": 3.3268, + "step": 2641920 + }, + { + "epoch": 1.02, + "learning_rate": 6.739910493113369e-06, + "loss": 3.3311, + "step": 2642432 + }, + { + "epoch": 1.02, + "learning_rate": 6.731524545602848e-06, + "loss": 3.332, + "step": 2642944 + }, + { + "epoch": 1.02, + "learning_rate": 6.723138598092328e-06, + "loss": 3.3306, + "step": 2643456 + }, + { + "epoch": 1.02, + "learning_rate": 6.714752650581809e-06, + "loss": 3.3318, + "step": 2643968 + }, + { + "epoch": 1.02, + "learning_rate": 6.70638308187502e-06, + "loss": 3.3252, + "step": 2644480 + }, + { + "epoch": 1.02, + "learning_rate": 6.697997134364499e-06, + "loss": 3.3366, + "step": 2644992 + }, + { + "epoch": 1.02, + "learning_rate": 6.6896111868539795e-06, + "loss": 3.3313, + "step": 2645504 + }, + { + "epoch": 1.02, + "learning_rate": 6.681225239343459e-06, + "loss": 3.3295, + "step": 2646016 + }, + { + "epoch": 1.02, + "learning_rate": 6.672855670636671e-06, + "loss": 3.3235, + "step": 2646528 + }, + { + "epoch": 1.02, + "learning_rate": 6.66446972312615e-06, + "loss": 3.3245, + "step": 2647040 + }, + { + "epoch": 1.02, + "learning_rate": 6.65608377561563e-06, + "loss": 3.3295, + "step": 2647552 + }, + { + "epoch": 1.02, + "learning_rate": 6.647714206908842e-06, + "loss": 3.3357, + "step": 2648064 + }, + { + "epoch": 1.02, + "learning_rate": 6.639328259398321e-06, + "loss": 3.3154, + "step": 2648576 + }, + { + "epoch": 1.02, + "learning_rate": 6.630942311887802e-06, + "loss": 3.3255, + "step": 2649088 + }, + { + "epoch": 1.02, + "learning_rate": 6.622556364377282e-06, + "loss": 3.3399, + "step": 2649600 + }, + { + "epoch": 1.02, + "learning_rate": 6.614186795670493e-06, + "loss": 3.3314, + "step": 2650112 + }, + { + "epoch": 1.02, + "learning_rate": 6.605800848159972e-06, + "loss": 3.3167, + "step": 2650624 + }, + { + "epoch": 1.02, + "learning_rate": 6.597414900649452e-06, + "loss": 3.3248, + "step": 2651136 + }, + { + "epoch": 1.02, + "learning_rate": 6.589028953138933e-06, + "loss": 3.3224, + "step": 2651648 + }, + { + "epoch": 1.02, + "learning_rate": 6.580643005628412e-06, + "loss": 3.3383, + "step": 2652160 + }, + { + "epoch": 1.02, + "learning_rate": 6.572257058117892e-06, + "loss": 3.3219, + "step": 2652672 + }, + { + "epoch": 1.02, + "learning_rate": 6.563871110607372e-06, + "loss": 3.3324, + "step": 2653184 + }, + { + "epoch": 1.02, + "learning_rate": 6.555501541900584e-06, + "loss": 3.332, + "step": 2653696 + }, + { + "epoch": 1.02, + "learning_rate": 6.547115594390063e-06, + "loss": 3.3377, + "step": 2654208 + }, + { + "epoch": 1.02, + "learning_rate": 6.538729646879544e-06, + "loss": 3.3262, + "step": 2654720 + }, + { + "epoch": 1.02, + "learning_rate": 6.530343699369024e-06, + "loss": 3.3348, + "step": 2655232 + }, + { + "epoch": 1.02, + "learning_rate": 6.521974130662235e-06, + "loss": 3.3395, + "step": 2655744 + }, + { + "epoch": 1.02, + "learning_rate": 6.513588183151714e-06, + "loss": 3.3276, + "step": 2656256 + }, + { + "epoch": 1.02, + "learning_rate": 6.505202235641194e-06, + "loss": 3.3222, + "step": 2656768 + }, + { + "epoch": 1.02, + "learning_rate": 6.496816288130675e-06, + "loss": 3.3263, + "step": 2657280 + }, + { + "epoch": 1.02, + "learning_rate": 6.488430340620153e-06, + "loss": 3.3244, + "step": 2657792 + }, + { + "epoch": 1.02, + "learning_rate": 6.480044393109634e-06, + "loss": 3.3274, + "step": 2658304 + }, + { + "epoch": 1.02, + "learning_rate": 6.471658445599114e-06, + "loss": 3.3279, + "step": 2658816 + }, + { + "epoch": 1.02, + "learning_rate": 6.463288876892325e-06, + "loss": 3.3328, + "step": 2659328 + }, + { + "epoch": 1.02, + "learning_rate": 6.454902929381805e-06, + "loss": 3.3183, + "step": 2659840 + }, + { + "epoch": 1.02, + "learning_rate": 6.446516981871286e-06, + "loss": 3.3208, + "step": 2660352 + }, + { + "epoch": 1.02, + "learning_rate": 6.438131034360766e-06, + "loss": 3.3254, + "step": 2660864 + }, + { + "epoch": 1.02, + "learning_rate": 6.429761465653976e-06, + "loss": 3.3393, + "step": 2661376 + }, + { + "epoch": 1.02, + "learning_rate": 6.4213755181434564e-06, + "loss": 3.3436, + "step": 2661888 + }, + { + "epoch": 1.02, + "learning_rate": 6.412989570632936e-06, + "loss": 3.3327, + "step": 2662400 + }, + { + "epoch": 1.02, + "learning_rate": 6.4046036231224155e-06, + "loss": 3.3211, + "step": 2662912 + }, + { + "epoch": 1.02, + "learning_rate": 6.3962176756118954e-06, + "loss": 3.3325, + "step": 2663424 + }, + { + "epoch": 1.02, + "learning_rate": 6.387848106905107e-06, + "loss": 3.3356, + "step": 2663936 + }, + { + "epoch": 1.02, + "learning_rate": 6.379462159394588e-06, + "loss": 3.3299, + "step": 2664448 + }, + { + "epoch": 1.02, + "learning_rate": 6.371076211884067e-06, + "loss": 3.3261, + "step": 2664960 + }, + { + "epoch": 1.02, + "learning_rate": 6.362690264373547e-06, + "loss": 3.3337, + "step": 2665472 + }, + { + "epoch": 1.02, + "learning_rate": 6.354304316863027e-06, + "loss": 3.3271, + "step": 2665984 + }, + { + "epoch": 1.02, + "learning_rate": 6.345918369352506e-06, + "loss": 3.339, + "step": 2666496 + }, + { + "epoch": 1.02, + "learning_rate": 6.337532421841987e-06, + "loss": 3.3242, + "step": 2667008 + }, + { + "epoch": 1.02, + "learning_rate": 6.329146474331467e-06, + "loss": 3.3319, + "step": 2667520 + }, + { + "epoch": 1.02, + "learning_rate": 6.320776905624678e-06, + "loss": 3.3265, + "step": 2668032 + }, + { + "epoch": 1.02, + "learning_rate": 6.3123909581141575e-06, + "loss": 3.3172, + "step": 2668544 + }, + { + "epoch": 1.02, + "learning_rate": 6.3040050106036375e-06, + "loss": 3.3328, + "step": 2669056 + }, + { + "epoch": 1.02, + "learning_rate": 6.295619063093118e-06, + "loss": 3.3354, + "step": 2669568 + }, + { + "epoch": 1.02, + "learning_rate": 6.28724949438633e-06, + "loss": 3.334, + "step": 2670080 + }, + { + "epoch": 1.02, + "learning_rate": 6.278863546875809e-06, + "loss": 3.326, + "step": 2670592 + }, + { + "epoch": 1.02, + "learning_rate": 6.270477599365289e-06, + "loss": 3.3196, + "step": 2671104 + }, + { + "epoch": 1.03, + "eval_loss": 3.863429069519043, + "eval_runtime": 312.4442, + "eval_samples_per_second": 1221.309, + "eval_steps_per_second": 38.167, + "step": 2671200 + }, + { + "epoch": 0.0, + "learning_rate": 6.262091651854769e-06, + "loss": 3.3266, + "step": 2671616 + }, + { + "epoch": 0.0, + "learning_rate": 6.253705704344248e-06, + "loss": 3.3263, + "step": 2672128 + }, + { + "epoch": 0.0, + "learning_rate": 6.245319756833729e-06, + "loss": 3.3324, + "step": 2672640 + }, + { + "epoch": 0.0, + "learning_rate": 6.236933809323209e-06, + "loss": 3.3226, + "step": 2673152 + }, + { + "epoch": 0.0, + "learning_rate": 6.22856424061642e-06, + "loss": 3.3434, + "step": 2673664 + }, + { + "epoch": 0.0, + "learning_rate": 6.2201782931059e-06, + "loss": 3.3183, + "step": 2674176 + }, + { + "epoch": 0.0, + "learning_rate": 6.2117923455953795e-06, + "loss": 3.3304, + "step": 2674688 + }, + { + "epoch": 0.0, + "learning_rate": 6.2034063980848595e-06, + "loss": 3.3191, + "step": 2675200 + }, + { + "epoch": 0.0, + "learning_rate": 6.195036829378071e-06, + "loss": 3.3341, + "step": 2675712 + }, + { + "epoch": 0.0, + "learning_rate": 6.18665088186755e-06, + "loss": 3.3312, + "step": 2676224 + }, + { + "epoch": 0.0, + "learning_rate": 6.178264934357031e-06, + "loss": 3.3273, + "step": 2676736 + }, + { + "epoch": 0.0, + "learning_rate": 6.169895365650242e-06, + "loss": 3.3324, + "step": 2677248 + }, + { + "epoch": 0.0, + "learning_rate": 6.161509418139723e-06, + "loss": 3.3154, + "step": 2677760 + }, + { + "epoch": 0.0, + "learning_rate": 6.153123470629202e-06, + "loss": 3.322, + "step": 2678272 + }, + { + "epoch": 0.0, + "learning_rate": 6.144737523118682e-06, + "loss": 3.3241, + "step": 2678784 + }, + { + "epoch": 0.0, + "learning_rate": 6.136351575608162e-06, + "loss": 3.3261, + "step": 2679296 + }, + { + "epoch": 0.0, + "learning_rate": 6.127965628097642e-06, + "loss": 3.3252, + "step": 2679808 + }, + { + "epoch": 0.0, + "learning_rate": 6.1195796805871215e-06, + "loss": 3.3209, + "step": 2680320 + }, + { + "epoch": 0.0, + "learning_rate": 6.1111937330766015e-06, + "loss": 3.3245, + "step": 2680832 + }, + { + "epoch": 0.0, + "learning_rate": 6.102824164369813e-06, + "loss": 3.3395, + "step": 2681344 + }, + { + "epoch": 0.0, + "learning_rate": 6.094438216859292e-06, + "loss": 3.3299, + "step": 2681856 + }, + { + "epoch": 0.0, + "learning_rate": 6.086052269348772e-06, + "loss": 3.3289, + "step": 2682368 + }, + { + "epoch": 0.0, + "learning_rate": 6.077666321838252e-06, + "loss": 3.3295, + "step": 2682880 + }, + { + "epoch": 0.0, + "learning_rate": 6.069296753131464e-06, + "loss": 3.3328, + "step": 2683392 + }, + { + "epoch": 0.0, + "learning_rate": 6.060910805620944e-06, + "loss": 3.3163, + "step": 2683904 + }, + { + "epoch": 0.0, + "learning_rate": 6.052524858110424e-06, + "loss": 3.3359, + "step": 2684416 + }, + { + "epoch": 0.0, + "learning_rate": 6.044138910599904e-06, + "loss": 3.3234, + "step": 2684928 + }, + { + "epoch": 0.0, + "learning_rate": 6.0357693418931144e-06, + "loss": 3.3208, + "step": 2685440 + }, + { + "epoch": 0.0, + "learning_rate": 6.027383394382595e-06, + "loss": 3.3141, + "step": 2685952 + }, + { + "epoch": 0.01, + "learning_rate": 6.018997446872074e-06, + "loss": 3.3202, + "step": 2686464 + }, + { + "epoch": 0.01, + "learning_rate": 6.010611499361554e-06, + "loss": 3.3263, + "step": 2686976 + }, + { + "epoch": 0.01, + "learning_rate": 6.002241930654766e-06, + "loss": 3.3346, + "step": 2687488 + }, + { + "epoch": 0.01, + "learning_rate": 5.993855983144246e-06, + "loss": 3.3297, + "step": 2688000 + }, + { + "epoch": 0.01, + "learning_rate": 5.985470035633726e-06, + "loss": 3.33, + "step": 2688512 + }, + { + "epoch": 0.01, + "learning_rate": 5.977084088123206e-06, + "loss": 3.3165, + "step": 2689024 + }, + { + "epoch": 0.01, + "learning_rate": 5.9687145194164175e-06, + "loss": 3.3285, + "step": 2689536 + }, + { + "epoch": 0.01, + "learning_rate": 5.9603285719058966e-06, + "loss": 3.3159, + "step": 2690048 + }, + { + "epoch": 0.01, + "learning_rate": 5.951942624395377e-06, + "loss": 3.3343, + "step": 2690560 + }, + { + "epoch": 0.01, + "learning_rate": 5.9435566768848565e-06, + "loss": 3.3095, + "step": 2691072 + }, + { + "epoch": 0.01, + "learning_rate": 5.935187108178068e-06, + "loss": 3.3203, + "step": 2691584 + }, + { + "epoch": 0.01, + "learning_rate": 5.926817539471279e-06, + "loss": 3.3194, + "step": 2692096 + }, + { + "epoch": 0.01, + "learning_rate": 5.91843159196076e-06, + "loss": 3.3371, + "step": 2692608 + }, + { + "epoch": 0.01, + "learning_rate": 5.910045644450239e-06, + "loss": 3.3244, + "step": 2693120 + }, + { + "epoch": 0.01, + "learning_rate": 5.901659696939719e-06, + "loss": 3.3237, + "step": 2693632 + }, + { + "epoch": 0.01, + "learning_rate": 5.893273749429199e-06, + "loss": 3.3285, + "step": 2694144 + }, + { + "epoch": 0.01, + "learning_rate": 5.884887801918679e-06, + "loss": 3.3235, + "step": 2694656 + }, + { + "epoch": 0.01, + "learning_rate": 5.876501854408159e-06, + "loss": 3.3267, + "step": 2695168 + }, + { + "epoch": 0.01, + "learning_rate": 5.868115906897639e-06, + "loss": 3.3118, + "step": 2695680 + }, + { + "epoch": 0.01, + "learning_rate": 5.85974633819085e-06, + "loss": 3.3147, + "step": 2696192 + }, + { + "epoch": 0.01, + "learning_rate": 5.85136039068033e-06, + "loss": 3.3305, + "step": 2696704 + }, + { + "epoch": 0.01, + "learning_rate": 5.842974443169809e-06, + "loss": 3.3221, + "step": 2697216 + }, + { + "epoch": 0.01, + "learning_rate": 5.83458849565929e-06, + "loss": 3.3215, + "step": 2697728 + }, + { + "epoch": 0.01, + "learning_rate": 5.826218926952501e-06, + "loss": 3.3184, + "step": 2698240 + }, + { + "epoch": 0.01, + "learning_rate": 5.817832979441981e-06, + "loss": 3.3211, + "step": 2698752 + }, + { + "epoch": 0.01, + "learning_rate": 5.809447031931461e-06, + "loss": 3.307, + "step": 2699264 + }, + { + "epoch": 0.01, + "learning_rate": 5.801061084420941e-06, + "loss": 3.3269, + "step": 2699776 + }, + { + "epoch": 0.01, + "learning_rate": 5.792691515714152e-06, + "loss": 3.3096, + "step": 2700288 + }, + { + "epoch": 0.01, + "learning_rate": 5.784305568203632e-06, + "loss": 3.3257, + "step": 2700800 + }, + { + "epoch": 0.01, + "learning_rate": 5.775919620693112e-06, + "loss": 3.3187, + "step": 2701312 + }, + { + "epoch": 0.01, + "learning_rate": 5.767533673182591e-06, + "loss": 3.3257, + "step": 2701824 + }, + { + "epoch": 0.01, + "learning_rate": 5.759180483279535e-06, + "loss": 3.3203, + "step": 2702336 + }, + { + "epoch": 0.01, + "learning_rate": 5.750794535769015e-06, + "loss": 3.3277, + "step": 2702848 + }, + { + "epoch": 0.01, + "learning_rate": 5.742408588258495e-06, + "loss": 3.3047, + "step": 2703360 + }, + { + "epoch": 0.01, + "learning_rate": 5.734022640747974e-06, + "loss": 3.3172, + "step": 2703872 + }, + { + "epoch": 0.01, + "learning_rate": 5.7256366932374546e-06, + "loss": 3.3238, + "step": 2704384 + }, + { + "epoch": 0.01, + "learning_rate": 5.717250745726934e-06, + "loss": 3.3228, + "step": 2704896 + }, + { + "epoch": 0.01, + "learning_rate": 5.7088647982164145e-06, + "loss": 3.3119, + "step": 2705408 + }, + { + "epoch": 0.01, + "learning_rate": 5.7004788507058936e-06, + "loss": 3.3122, + "step": 2705920 + }, + { + "epoch": 0.01, + "learning_rate": 5.692125660802837e-06, + "loss": 3.3147, + "step": 2706432 + }, + { + "epoch": 0.01, + "learning_rate": 5.683739713292317e-06, + "loss": 3.3204, + "step": 2706944 + }, + { + "epoch": 0.01, + "learning_rate": 5.675353765781797e-06, + "loss": 3.3252, + "step": 2707456 + }, + { + "epoch": 0.01, + "learning_rate": 5.666967818271277e-06, + "loss": 3.3174, + "step": 2707968 + }, + { + "epoch": 0.01, + "learning_rate": 5.658581870760756e-06, + "loss": 3.3346, + "step": 2708480 + }, + { + "epoch": 0.01, + "learning_rate": 5.650195923250237e-06, + "loss": 3.3331, + "step": 2708992 + }, + { + "epoch": 0.01, + "learning_rate": 5.641809975739716e-06, + "loss": 3.3384, + "step": 2709504 + }, + { + "epoch": 0.01, + "learning_rate": 5.633424028229197e-06, + "loss": 3.3086, + "step": 2710016 + }, + { + "epoch": 0.01, + "learning_rate": 5.625070838326139e-06, + "loss": 3.3275, + "step": 2710528 + }, + { + "epoch": 0.01, + "learning_rate": 5.616684890815619e-06, + "loss": 3.3267, + "step": 2711040 + }, + { + "epoch": 0.01, + "learning_rate": 5.608298943305099e-06, + "loss": 3.3155, + "step": 2711552 + }, + { + "epoch": 0.01, + "learning_rate": 5.599912995794579e-06, + "loss": 3.3268, + "step": 2712064 + }, + { + "epoch": 0.01, + "learning_rate": 5.591527048284059e-06, + "loss": 3.3299, + "step": 2712576 + }, + { + "epoch": 0.01, + "learning_rate": 5.583141100773538e-06, + "loss": 3.3284, + "step": 2713088 + }, + { + "epoch": 0.01, + "learning_rate": 5.574755153263019e-06, + "loss": 3.3189, + "step": 2713600 + }, + { + "epoch": 0.01, + "learning_rate": 5.566369205752498e-06, + "loss": 3.3088, + "step": 2714112 + }, + { + "epoch": 0.01, + "learning_rate": 5.5579996370457095e-06, + "loss": 3.312, + "step": 2714624 + }, + { + "epoch": 0.01, + "learning_rate": 5.5496136895351895e-06, + "loss": 3.321, + "step": 2715136 + }, + { + "epoch": 0.01, + "learning_rate": 5.5412277420246694e-06, + "loss": 3.3267, + "step": 2715648 + }, + { + "epoch": 0.01, + "learning_rate": 5.532841794514149e-06, + "loss": 3.3297, + "step": 2716160 + }, + { + "epoch": 0.01, + "learning_rate": 5.52447222580736e-06, + "loss": 3.315, + "step": 2716672 + }, + { + "epoch": 0.02, + "learning_rate": 5.516086278296841e-06, + "loss": 3.3182, + "step": 2717184 + }, + { + "epoch": 0.02, + "learning_rate": 5.50770033078632e-06, + "loss": 3.3073, + "step": 2717696 + }, + { + "epoch": 0.02, + "learning_rate": 5.499314383275801e-06, + "loss": 3.3172, + "step": 2718208 + }, + { + "epoch": 0.02, + "learning_rate": 5.490944814569012e-06, + "loss": 3.3195, + "step": 2718720 + }, + { + "epoch": 0.02, + "learning_rate": 5.482558867058492e-06, + "loss": 3.3208, + "step": 2719232 + }, + { + "epoch": 0.02, + "learning_rate": 5.474172919547972e-06, + "loss": 3.3282, + "step": 2719744 + }, + { + "epoch": 0.02, + "learning_rate": 5.465786972037451e-06, + "loss": 3.3236, + "step": 2720256 + }, + { + "epoch": 0.02, + "learning_rate": 5.457417403330662e-06, + "loss": 3.3142, + "step": 2720768 + }, + { + "epoch": 0.02, + "learning_rate": 5.449031455820142e-06, + "loss": 3.3281, + "step": 2721280 + }, + { + "epoch": 0.02, + "learning_rate": 5.440645508309622e-06, + "loss": 3.3214, + "step": 2721792 + }, + { + "epoch": 0.02, + "learning_rate": 5.432259560799102e-06, + "loss": 3.3223, + "step": 2722304 + }, + { + "epoch": 0.02, + "learning_rate": 5.423889992092314e-06, + "loss": 3.3103, + "step": 2722816 + }, + { + "epoch": 0.02, + "learning_rate": 5.415504044581794e-06, + "loss": 3.3166, + "step": 2723328 + }, + { + "epoch": 0.02, + "learning_rate": 5.407118097071274e-06, + "loss": 3.3217, + "step": 2723840 + }, + { + "epoch": 0.02, + "learning_rate": 5.3987485283644846e-06, + "loss": 3.3301, + "step": 2724352 + }, + { + "epoch": 0.02, + "learning_rate": 5.390362580853965e-06, + "loss": 3.3106, + "step": 2724864 + }, + { + "epoch": 0.02, + "learning_rate": 5.3819766333434445e-06, + "loss": 3.3147, + "step": 2725376 + }, + { + "epoch": 0.02, + "learning_rate": 5.3735906858329244e-06, + "loss": 3.3332, + "step": 2725888 + }, + { + "epoch": 0.02, + "learning_rate": 5.365221117126136e-06, + "loss": 3.323, + "step": 2726400 + }, + { + "epoch": 0.02, + "learning_rate": 5.356835169615616e-06, + "loss": 3.308, + "step": 2726912 + }, + { + "epoch": 0.02, + "learning_rate": 5.348449222105096e-06, + "loss": 3.3145, + "step": 2727424 + }, + { + "epoch": 0.02, + "learning_rate": 5.340063274594576e-06, + "loss": 3.3196, + "step": 2727936 + }, + { + "epoch": 0.02, + "learning_rate": 5.331677327084056e-06, + "loss": 3.3251, + "step": 2728448 + }, + { + "epoch": 0.02, + "learning_rate": 5.323291379573536e-06, + "loss": 3.3163, + "step": 2728960 + }, + { + "epoch": 0.02, + "learning_rate": 5.314905432063015e-06, + "loss": 3.317, + "step": 2729472 + }, + { + "epoch": 0.02, + "learning_rate": 5.306535863356227e-06, + "loss": 3.3235, + "step": 2729984 + }, + { + "epoch": 0.02, + "learning_rate": 5.2981499158457065e-06, + "loss": 3.3314, + "step": 2730496 + }, + { + "epoch": 0.02, + "learning_rate": 5.2897639683351865e-06, + "loss": 3.3223, + "step": 2731008 + }, + { + "epoch": 0.02, + "learning_rate": 5.2813780208246665e-06, + "loss": 3.3186, + "step": 2731520 + }, + { + "epoch": 0.02, + "learning_rate": 5.273008452117878e-06, + "loss": 3.3331, + "step": 2732032 + }, + { + "epoch": 0.02, + "learning_rate": 5.264622504607357e-06, + "loss": 3.3188, + "step": 2732544 + }, + { + "epoch": 0.02, + "learning_rate": 5.256236557096838e-06, + "loss": 3.3116, + "step": 2733056 + }, + { + "epoch": 0.02, + "learning_rate": 5.247850609586317e-06, + "loss": 3.3175, + "step": 2733568 + }, + { + "epoch": 0.02, + "learning_rate": 5.239464662075797e-06, + "loss": 3.3171, + "step": 2734080 + }, + { + "epoch": 0.02, + "learning_rate": 5.231078714565278e-06, + "loss": 3.3186, + "step": 2734592 + }, + { + "epoch": 0.02, + "learning_rate": 5.222692767054757e-06, + "loss": 3.3145, + "step": 2735104 + }, + { + "epoch": 0.02, + "learning_rate": 5.214306819544238e-06, + "loss": 3.3268, + "step": 2735616 + }, + { + "epoch": 0.02, + "learning_rate": 5.2059372508374486e-06, + "loss": 3.3108, + "step": 2736128 + }, + { + "epoch": 0.02, + "learning_rate": 5.1975513033269285e-06, + "loss": 3.3117, + "step": 2736640 + }, + { + "epoch": 0.02, + "learning_rate": 5.1891653558164085e-06, + "loss": 3.314, + "step": 2737152 + }, + { + "epoch": 0.02, + "learning_rate": 5.180779408305888e-06, + "loss": 3.3332, + "step": 2737664 + }, + { + "epoch": 0.02, + "learning_rate": 5.172393460795368e-06, + "loss": 3.3293, + "step": 2738176 + }, + { + "epoch": 0.02, + "learning_rate": 5.1640075132848475e-06, + "loss": 3.3275, + "step": 2738688 + }, + { + "epoch": 0.02, + "learning_rate": 5.155621565774328e-06, + "loss": 3.3129, + "step": 2739200 + }, + { + "epoch": 0.02, + "learning_rate": 5.147251997067539e-06, + "loss": 3.3259, + "step": 2739712 + }, + { + "epoch": 0.02, + "learning_rate": 5.138882428360751e-06, + "loss": 3.3283, + "step": 2740224 + }, + { + "epoch": 0.02, + "learning_rate": 5.130496480850231e-06, + "loss": 3.3197, + "step": 2740736 + }, + { + "epoch": 0.02, + "learning_rate": 5.122110533339711e-06, + "loss": 3.3166, + "step": 2741248 + }, + { + "epoch": 0.02, + "learning_rate": 5.113724585829191e-06, + "loss": 3.3256, + "step": 2741760 + }, + { + "epoch": 0.02, + "learning_rate": 5.10533863831867e-06, + "loss": 3.3179, + "step": 2742272 + }, + { + "epoch": 0.02, + "learning_rate": 5.0969526908081505e-06, + "loss": 3.3314, + "step": 2742784 + }, + { + "epoch": 0.02, + "learning_rate": 5.08856674329763e-06, + "loss": 3.314, + "step": 2743296 + }, + { + "epoch": 0.02, + "learning_rate": 5.0801807957871104e-06, + "loss": 3.3256, + "step": 2743808 + }, + { + "epoch": 0.02, + "learning_rate": 5.071811227080321e-06, + "loss": 3.3164, + "step": 2744320 + }, + { + "epoch": 0.02, + "learning_rate": 5.063425279569801e-06, + "loss": 3.3156, + "step": 2744832 + }, + { + "epoch": 0.02, + "learning_rate": 5.055039332059281e-06, + "loss": 3.3211, + "step": 2745344 + }, + { + "epoch": 0.02, + "learning_rate": 5.046653384548761e-06, + "loss": 3.328, + "step": 2745856 + }, + { + "epoch": 0.02, + "learning_rate": 5.038267437038241e-06, + "loss": 3.3236, + "step": 2746368 + }, + { + "epoch": 0.02, + "learning_rate": 5.029881489527721e-06, + "loss": 3.3126, + "step": 2746880 + }, + { + "epoch": 0.02, + "learning_rate": 5.021495542017201e-06, + "loss": 3.315, + "step": 2747392 + }, + { + "epoch": 0.03, + "eval_loss": 3.863173723220825, + "eval_runtime": 302.7962, + "eval_samples_per_second": 1260.224, + "eval_steps_per_second": 39.383, + "step": 2747520 + }, + { + "epoch": 1.0, + "learning_rate": 5.013125973310412e-06, + "loss": 3.3204, + "step": 2747904 + }, + { + "epoch": 1.0, + "learning_rate": 5.0047400257998925e-06, + "loss": 3.3203, + "step": 2748416 + }, + { + "epoch": 1.0, + "learning_rate": 4.996354078289372e-06, + "loss": 3.3206, + "step": 2748928 + }, + { + "epoch": 1.0, + "learning_rate": 4.987968130778852e-06, + "loss": 3.3205, + "step": 2749440 + }, + { + "epoch": 1.0, + "learning_rate": 4.979598562072063e-06, + "loss": 3.3323, + "step": 2749952 + }, + { + "epoch": 1.0, + "learning_rate": 4.971212614561542e-06, + "loss": 3.3151, + "step": 2750464 + }, + { + "epoch": 1.0, + "learning_rate": 4.962826667051023e-06, + "loss": 3.3196, + "step": 2750976 + }, + { + "epoch": 1.0, + "learning_rate": 4.954440719540502e-06, + "loss": 3.3071, + "step": 2751488 + }, + { + "epoch": 1.0, + "learning_rate": 4.946071150833714e-06, + "loss": 3.3244, + "step": 2752000 + }, + { + "epoch": 1.0, + "learning_rate": 4.937685203323194e-06, + "loss": 3.3257, + "step": 2752512 + }, + { + "epoch": 1.0, + "learning_rate": 4.929299255812674e-06, + "loss": 3.3181, + "step": 2753024 + }, + { + "epoch": 1.0, + "learning_rate": 4.9209296871058855e-06, + "loss": 3.321, + "step": 2753536 + }, + { + "epoch": 1.0, + "learning_rate": 4.9125437395953646e-06, + "loss": 3.3058, + "step": 2754048 + }, + { + "epoch": 1.0, + "learning_rate": 4.904157792084845e-06, + "loss": 3.315, + "step": 2754560 + }, + { + "epoch": 1.0, + "learning_rate": 4.8957718445743245e-06, + "loss": 3.3157, + "step": 2755072 + }, + { + "epoch": 1.0, + "learning_rate": 4.887385897063805e-06, + "loss": 3.315, + "step": 2755584 + }, + { + "epoch": 1.0, + "learning_rate": 4.878999949553284e-06, + "loss": 3.3169, + "step": 2756096 + }, + { + "epoch": 1.0, + "learning_rate": 4.870614002042764e-06, + "loss": 3.3119, + "step": 2756608 + }, + { + "epoch": 1.0, + "learning_rate": 4.862228054532244e-06, + "loss": 3.3177, + "step": 2757120 + }, + { + "epoch": 1.0, + "learning_rate": 4.853858485825456e-06, + "loss": 3.3287, + "step": 2757632 + }, + { + "epoch": 1.0, + "learning_rate": 4.845472538314936e-06, + "loss": 3.3234, + "step": 2758144 + }, + { + "epoch": 1.0, + "learning_rate": 4.837086590804416e-06, + "loss": 3.3203, + "step": 2758656 + }, + { + "epoch": 1.0, + "learning_rate": 4.828700643293896e-06, + "loss": 3.3203, + "step": 2759168 + }, + { + "epoch": 1.0, + "learning_rate": 4.820331074587107e-06, + "loss": 3.325, + "step": 2759680 + }, + { + "epoch": 1.0, + "learning_rate": 4.811945127076587e-06, + "loss": 3.308, + "step": 2760192 + }, + { + "epoch": 1.0, + "learning_rate": 4.8035591795660665e-06, + "loss": 3.3257, + "step": 2760704 + }, + { + "epoch": 1.0, + "learning_rate": 4.7951732320555465e-06, + "loss": 3.3162, + "step": 2761216 + }, + { + "epoch": 1.0, + "learning_rate": 4.786803663348758e-06, + "loss": 3.3135, + "step": 2761728 + }, + { + "epoch": 1.0, + "learning_rate": 4.778417715838237e-06, + "loss": 3.3066, + "step": 2762240 + }, + { + "epoch": 1.0, + "learning_rate": 4.770031768327718e-06, + "loss": 3.3149, + "step": 2762752 + }, + { + "epoch": 1.01, + "learning_rate": 4.761645820817198e-06, + "loss": 3.3177, + "step": 2763264 + }, + { + "epoch": 1.01, + "learning_rate": 4.75327625211041e-06, + "loss": 3.3273, + "step": 2763776 + }, + { + "epoch": 1.01, + "learning_rate": 4.744890304599889e-06, + "loss": 3.3205, + "step": 2764288 + }, + { + "epoch": 1.01, + "learning_rate": 4.7365043570893695e-06, + "loss": 3.3213, + "step": 2764800 + }, + { + "epoch": 1.01, + "learning_rate": 4.728118409578849e-06, + "loss": 3.3078, + "step": 2765312 + }, + { + "epoch": 1.01, + "learning_rate": 4.71974884087206e-06, + "loss": 3.3188, + "step": 2765824 + }, + { + "epoch": 1.01, + "learning_rate": 4.71136289336154e-06, + "loss": 3.3136, + "step": 2766336 + }, + { + "epoch": 1.01, + "learning_rate": 4.702976945851019e-06, + "loss": 3.3239, + "step": 2766848 + }, + { + "epoch": 1.01, + "learning_rate": 4.6945909983405e-06, + "loss": 3.3036, + "step": 2767360 + }, + { + "epoch": 1.01, + "learning_rate": 4.686221429633711e-06, + "loss": 3.3109, + "step": 2767872 + }, + { + "epoch": 1.01, + "learning_rate": 4.6778518609269226e-06, + "loss": 3.3124, + "step": 2768384 + }, + { + "epoch": 1.01, + "learning_rate": 4.6694659134164025e-06, + "loss": 3.3318, + "step": 2768896 + }, + { + "epoch": 1.01, + "learning_rate": 4.6610799659058825e-06, + "loss": 3.3188, + "step": 2769408 + }, + { + "epoch": 1.01, + "learning_rate": 4.652694018395362e-06, + "loss": 3.315, + "step": 2769920 + }, + { + "epoch": 1.01, + "learning_rate": 4.644308070884842e-06, + "loss": 3.3211, + "step": 2770432 + }, + { + "epoch": 1.01, + "learning_rate": 4.635922123374322e-06, + "loss": 3.3138, + "step": 2770944 + }, + { + "epoch": 1.01, + "learning_rate": 4.6275361758638014e-06, + "loss": 3.3173, + "step": 2771456 + }, + { + "epoch": 1.01, + "learning_rate": 4.619150228353282e-06, + "loss": 3.3058, + "step": 2771968 + }, + { + "epoch": 1.01, + "learning_rate": 4.610780659646493e-06, + "loss": 3.3036, + "step": 2772480 + }, + { + "epoch": 1.01, + "learning_rate": 4.602394712135973e-06, + "loss": 3.321, + "step": 2772992 + }, + { + "epoch": 1.01, + "learning_rate": 4.594008764625453e-06, + "loss": 3.3122, + "step": 2773504 + }, + { + "epoch": 1.01, + "learning_rate": 4.585622817114933e-06, + "loss": 3.3152, + "step": 2774016 + }, + { + "epoch": 1.01, + "learning_rate": 4.5772532484081445e-06, + "loss": 3.3097, + "step": 2774528 + }, + { + "epoch": 1.01, + "learning_rate": 4.568883679701356e-06, + "loss": 3.3133, + "step": 2775040 + }, + { + "epoch": 1.01, + "learning_rate": 4.560497732190835e-06, + "loss": 3.2979, + "step": 2775552 + }, + { + "epoch": 1.01, + "learning_rate": 4.552111784680316e-06, + "loss": 3.3118, + "step": 2776064 + }, + { + "epoch": 1.01, + "learning_rate": 4.543725837169795e-06, + "loss": 3.3049, + "step": 2776576 + }, + { + "epoch": 1.01, + "learning_rate": 4.535339889659275e-06, + "loss": 3.3148, + "step": 2777088 + }, + { + "epoch": 1.01, + "learning_rate": 4.526953942148755e-06, + "loss": 3.3153, + "step": 2777600 + }, + { + "epoch": 1.01, + "learning_rate": 4.518567994638235e-06, + "loss": 3.3138, + "step": 2778112 + }, + { + "epoch": 1.01, + "learning_rate": 4.510198425931447e-06, + "loss": 3.3142, + "step": 2778624 + }, + { + "epoch": 1.01, + "learning_rate": 4.501812478420926e-06, + "loss": 3.3228, + "step": 2779136 + }, + { + "epoch": 1.01, + "learning_rate": 4.493426530910407e-06, + "loss": 3.2996, + "step": 2779648 + }, + { + "epoch": 1.01, + "learning_rate": 4.485040583399886e-06, + "loss": 3.3052, + "step": 2780160 + }, + { + "epoch": 1.01, + "learning_rate": 4.476654635889366e-06, + "loss": 3.3178, + "step": 2780672 + }, + { + "epoch": 1.01, + "learning_rate": 4.468268688378846e-06, + "loss": 3.3122, + "step": 2781184 + }, + { + "epoch": 1.01, + "learning_rate": 4.459882740868326e-06, + "loss": 3.3066, + "step": 2781696 + }, + { + "epoch": 1.01, + "learning_rate": 4.451513172161537e-06, + "loss": 3.3012, + "step": 2782208 + }, + { + "epoch": 1.01, + "learning_rate": 4.443127224651017e-06, + "loss": 3.3054, + "step": 2782720 + }, + { + "epoch": 1.01, + "learning_rate": 4.434741277140497e-06, + "loss": 3.3108, + "step": 2783232 + }, + { + "epoch": 1.01, + "learning_rate": 4.426355329629977e-06, + "loss": 3.3185, + "step": 2783744 + }, + { + "epoch": 1.01, + "learning_rate": 4.417969382119456e-06, + "loss": 3.312, + "step": 2784256 + }, + { + "epoch": 1.01, + "learning_rate": 4.409583434608937e-06, + "loss": 3.3234, + "step": 2784768 + }, + { + "epoch": 1.01, + "learning_rate": 4.401197487098416e-06, + "loss": 3.3209, + "step": 2785280 + }, + { + "epoch": 1.01, + "learning_rate": 4.392811539587897e-06, + "loss": 3.3316, + "step": 2785792 + }, + { + "epoch": 1.01, + "learning_rate": 4.384441970881108e-06, + "loss": 3.3025, + "step": 2786304 + }, + { + "epoch": 1.01, + "learning_rate": 4.376072402174319e-06, + "loss": 3.3159, + "step": 2786816 + }, + { + "epoch": 1.01, + "learning_rate": 4.367686454663799e-06, + "loss": 3.3205, + "step": 2787328 + }, + { + "epoch": 1.01, + "learning_rate": 4.359300507153279e-06, + "loss": 3.3015, + "step": 2787840 + }, + { + "epoch": 1.01, + "learning_rate": 4.350914559642759e-06, + "loss": 3.3216, + "step": 2788352 + }, + { + "epoch": 1.01, + "learning_rate": 4.342528612132238e-06, + "loss": 3.3196, + "step": 2788864 + }, + { + "epoch": 1.01, + "learning_rate": 4.334142664621719e-06, + "loss": 3.319, + "step": 2789376 + }, + { + "epoch": 1.01, + "learning_rate": 4.325756717111198e-06, + "loss": 3.3122, + "step": 2789888 + }, + { + "epoch": 1.01, + "learning_rate": 4.317370769600679e-06, + "loss": 3.3017, + "step": 2790400 + }, + { + "epoch": 1.01, + "learning_rate": 4.30900120089389e-06, + "loss": 3.305, + "step": 2790912 + }, + { + "epoch": 1.01, + "learning_rate": 4.300615253383369e-06, + "loss": 3.3138, + "step": 2791424 + }, + { + "epoch": 1.01, + "learning_rate": 4.29222930587285e-06, + "loss": 3.3161, + "step": 2791936 + }, + { + "epoch": 1.01, + "learning_rate": 4.28384335836233e-06, + "loss": 3.3227, + "step": 2792448 + }, + { + "epoch": 1.01, + "learning_rate": 4.275473789655541e-06, + "loss": 3.3082, + "step": 2792960 + }, + { + "epoch": 1.02, + "learning_rate": 4.2670878421450204e-06, + "loss": 3.31, + "step": 2793472 + }, + { + "epoch": 1.02, + "learning_rate": 4.258701894634501e-06, + "loss": 3.2987, + "step": 2793984 + }, + { + "epoch": 1.02, + "learning_rate": 4.250332325927712e-06, + "loss": 3.3081, + "step": 2794496 + }, + { + "epoch": 1.02, + "learning_rate": 4.241946378417192e-06, + "loss": 3.313, + "step": 2795008 + }, + { + "epoch": 1.02, + "learning_rate": 4.233560430906672e-06, + "loss": 3.315, + "step": 2795520 + }, + { + "epoch": 1.02, + "learning_rate": 4.225174483396151e-06, + "loss": 3.3199, + "step": 2796032 + }, + { + "epoch": 1.02, + "learning_rate": 4.216788535885632e-06, + "loss": 3.3132, + "step": 2796544 + }, + { + "epoch": 1.02, + "learning_rate": 4.208402588375111e-06, + "loss": 3.31, + "step": 2797056 + }, + { + "epoch": 1.02, + "learning_rate": 4.200016640864592e-06, + "loss": 3.3146, + "step": 2797568 + }, + { + "epoch": 1.02, + "learning_rate": 4.191630693354071e-06, + "loss": 3.3104, + "step": 2798080 + }, + { + "epoch": 1.02, + "learning_rate": 4.1832611246472825e-06, + "loss": 3.319, + "step": 2798592 + }, + { + "epoch": 1.02, + "learning_rate": 4.1748751771367625e-06, + "loss": 3.3022, + "step": 2799104 + }, + { + "epoch": 1.02, + "learning_rate": 4.166489229626242e-06, + "loss": 3.3097, + "step": 2799616 + }, + { + "epoch": 1.02, + "learning_rate": 4.158103282115722e-06, + "loss": 3.309, + "step": 2800128 + }, + { + "epoch": 1.02, + "learning_rate": 4.149733713408933e-06, + "loss": 3.3211, + "step": 2800640 + }, + { + "epoch": 1.02, + "learning_rate": 4.141347765898414e-06, + "loss": 3.3017, + "step": 2801152 + }, + { + "epoch": 1.02, + "learning_rate": 4.132961818387893e-06, + "loss": 3.3105, + "step": 2801664 + }, + { + "epoch": 1.02, + "learning_rate": 4.124575870877374e-06, + "loss": 3.3197, + "step": 2802176 + }, + { + "epoch": 1.02, + "learning_rate": 4.116206302170585e-06, + "loss": 3.3159, + "step": 2802688 + }, + { + "epoch": 1.02, + "learning_rate": 4.107820354660065e-06, + "loss": 3.2982, + "step": 2803200 + }, + { + "epoch": 1.02, + "learning_rate": 4.099434407149545e-06, + "loss": 3.3116, + "step": 2803712 + }, + { + "epoch": 1.02, + "learning_rate": 4.0910484596390245e-06, + "loss": 3.3043, + "step": 2804224 + }, + { + "epoch": 1.02, + "learning_rate": 4.0826625121285045e-06, + "loss": 3.3217, + "step": 2804736 + }, + { + "epoch": 1.02, + "learning_rate": 4.0742765646179844e-06, + "loss": 3.307, + "step": 2805248 + }, + { + "epoch": 1.02, + "learning_rate": 4.065890617107464e-06, + "loss": 3.3085, + "step": 2805760 + }, + { + "epoch": 1.02, + "learning_rate": 4.057521048400675e-06, + "loss": 3.3182, + "step": 2806272 + }, + { + "epoch": 1.02, + "learning_rate": 4.049135100890156e-06, + "loss": 3.3265, + "step": 2806784 + }, + { + "epoch": 1.02, + "learning_rate": 4.040749153379635e-06, + "loss": 3.3137, + "step": 2807296 + }, + { + "epoch": 1.02, + "learning_rate": 4.032363205869115e-06, + "loss": 3.3114, + "step": 2807808 + }, + { + "epoch": 1.02, + "learning_rate": 4.023993637162327e-06, + "loss": 3.3184, + "step": 2808320 + }, + { + "epoch": 1.02, + "learning_rate": 4.015607689651806e-06, + "loss": 3.3106, + "step": 2808832 + }, + { + "epoch": 1.02, + "learning_rate": 4.007221742141287e-06, + "loss": 3.3054, + "step": 2809344 + }, + { + "epoch": 1.02, + "learning_rate": 3.998835794630766e-06, + "loss": 3.315, + "step": 2809856 + }, + { + "epoch": 1.02, + "learning_rate": 3.9904498471202465e-06, + "loss": 3.3069, + "step": 2810368 + }, + { + "epoch": 1.02, + "learning_rate": 3.9820638996097265e-06, + "loss": 3.3112, + "step": 2810880 + }, + { + "epoch": 1.02, + "learning_rate": 3.973677952099206e-06, + "loss": 3.307, + "step": 2811392 + }, + { + "epoch": 1.02, + "learning_rate": 3.965292004588686e-06, + "loss": 3.3174, + "step": 2811904 + }, + { + "epoch": 1.02, + "learning_rate": 3.956922435881897e-06, + "loss": 3.3044, + "step": 2812416 + }, + { + "epoch": 1.02, + "learning_rate": 3.948536488371377e-06, + "loss": 3.3045, + "step": 2812928 + }, + { + "epoch": 1.02, + "learning_rate": 3.940150540860857e-06, + "loss": 3.3114, + "step": 2813440 + }, + { + "epoch": 1.02, + "learning_rate": 3.931764593350337e-06, + "loss": 3.3169, + "step": 2813952 + }, + { + "epoch": 1.02, + "learning_rate": 3.923395024643548e-06, + "loss": 3.3227, + "step": 2814464 + }, + { + "epoch": 1.02, + "learning_rate": 3.915009077133029e-06, + "loss": 3.3206, + "step": 2814976 + }, + { + "epoch": 1.02, + "learning_rate": 3.906623129622508e-06, + "loss": 3.3038, + "step": 2815488 + }, + { + "epoch": 1.02, + "learning_rate": 3.898237182111988e-06, + "loss": 3.3207, + "step": 2816000 + }, + { + "epoch": 1.02, + "learning_rate": 3.889867613405199e-06, + "loss": 3.3187, + "step": 2816512 + }, + { + "epoch": 1.02, + "learning_rate": 3.881481665894679e-06, + "loss": 3.3152, + "step": 2817024 + }, + { + "epoch": 1.02, + "learning_rate": 3.873095718384159e-06, + "loss": 3.3056, + "step": 2817536 + }, + { + "epoch": 1.02, + "learning_rate": 3.864709770873639e-06, + "loss": 3.3219, + "step": 2818048 + }, + { + "epoch": 1.02, + "learning_rate": 3.856323823363119e-06, + "loss": 3.3048, + "step": 2818560 + }, + { + "epoch": 1.02, + "learning_rate": 3.847937875852599e-06, + "loss": 3.3262, + "step": 2819072 + }, + { + "epoch": 1.02, + "learning_rate": 3.839551928342078e-06, + "loss": 3.3005, + "step": 2819584 + }, + { + "epoch": 1.02, + "learning_rate": 3.831165980831559e-06, + "loss": 3.3197, + "step": 2820096 + }, + { + "epoch": 1.02, + "learning_rate": 3.82279641212477e-06, + "loss": 3.303, + "step": 2820608 + }, + { + "epoch": 1.02, + "learning_rate": 3.81441046461425e-06, + "loss": 3.3072, + "step": 2821120 + }, + { + "epoch": 1.02, + "learning_rate": 3.8060245171037297e-06, + "loss": 3.3145, + "step": 2821632 + }, + { + "epoch": 1.02, + "learning_rate": 3.79763856959321e-06, + "loss": 3.3168, + "step": 2822144 + }, + { + "epoch": 1.02, + "learning_rate": 3.7892526220826896e-06, + "loss": 3.3195, + "step": 2822656 + }, + { + "epoch": 1.02, + "learning_rate": 3.780866674572169e-06, + "loss": 3.2995, + "step": 2823168 + }, + { + "epoch": 1.02, + "learning_rate": 3.7724807270616496e-06, + "loss": 3.3121, + "step": 2823680 + }, + { + "epoch": 1.03, + "eval_loss": 3.863150119781494, + "eval_runtime": 302.4785, + "eval_samples_per_second": 1261.548, + "eval_steps_per_second": 39.424, + "step": 2823840 + }, + { + "epoch": 0.0, + "learning_rate": 3.764094779551129e-06, + "loss": 3.3116, + "step": 2824192 + }, + { + "epoch": 0.0, + "learning_rate": 3.7557088320406095e-06, + "loss": 3.3114, + "step": 2824704 + }, + { + "epoch": 0.0, + "learning_rate": 3.747322884530089e-06, + "loss": 3.3135, + "step": 2825216 + }, + { + "epoch": 0.0, + "learning_rate": 3.7389369370195685e-06, + "loss": 3.3089, + "step": 2825728 + }, + { + "epoch": 0.0, + "learning_rate": 3.73056736831278e-06, + "loss": 3.3238, + "step": 2826240 + }, + { + "epoch": 0.0, + "learning_rate": 3.72218142080226e-06, + "loss": 3.3077, + "step": 2826752 + }, + { + "epoch": 0.0, + "learning_rate": 3.7137954732917405e-06, + "loss": 3.3066, + "step": 2827264 + }, + { + "epoch": 0.0, + "learning_rate": 3.70540952578122e-06, + "loss": 3.3077, + "step": 2827776 + }, + { + "epoch": 0.0, + "learning_rate": 3.6970399570744317e-06, + "loss": 3.3138, + "step": 2828288 + }, + { + "epoch": 0.0, + "learning_rate": 3.688654009563911e-06, + "loss": 3.3165, + "step": 2828800 + }, + { + "epoch": 0.0, + "learning_rate": 3.6802680620533907e-06, + "loss": 3.3085, + "step": 2829312 + }, + { + "epoch": 0.0, + "learning_rate": 3.6718984933466024e-06, + "loss": 3.3165, + "step": 2829824 + }, + { + "epoch": 0.0, + "learning_rate": 3.663512545836082e-06, + "loss": 3.3017, + "step": 2830336 + }, + { + "epoch": 0.0, + "learning_rate": 3.6551265983255623e-06, + "loss": 3.306, + "step": 2830848 + }, + { + "epoch": 0.0, + "learning_rate": 3.646740650815042e-06, + "loss": 3.3104, + "step": 2831360 + }, + { + "epoch": 0.0, + "learning_rate": 3.638354703304522e-06, + "loss": 3.3027, + "step": 2831872 + }, + { + "epoch": 0.0, + "learning_rate": 3.629968755794002e-06, + "loss": 3.3118, + "step": 2832384 + }, + { + "epoch": 0.0, + "learning_rate": 3.6215828082834817e-06, + "loss": 3.3031, + "step": 2832896 + }, + { + "epoch": 0.0, + "learning_rate": 3.613196860772962e-06, + "loss": 3.3076, + "step": 2833408 + }, + { + "epoch": 0.0, + "learning_rate": 3.604827292066173e-06, + "loss": 3.3249, + "step": 2833920 + }, + { + "epoch": 0.0, + "learning_rate": 3.5964413445556532e-06, + "loss": 3.3129, + "step": 2834432 + }, + { + "epoch": 0.0, + "learning_rate": 3.5880553970451328e-06, + "loss": 3.3217, + "step": 2834944 + }, + { + "epoch": 0.0, + "learning_rate": 3.579669449534613e-06, + "loss": 3.3096, + "step": 2835456 + }, + { + "epoch": 0.0, + "learning_rate": 3.571299880827824e-06, + "loss": 3.3167, + "step": 2835968 + }, + { + "epoch": 0.0, + "learning_rate": 3.5629139333173043e-06, + "loss": 3.3005, + "step": 2836480 + }, + { + "epoch": 0.0, + "learning_rate": 3.554527985806784e-06, + "loss": 3.3188, + "step": 2836992 + }, + { + "epoch": 0.0, + "learning_rate": 3.546142038296264e-06, + "loss": 3.3083, + "step": 2837504 + }, + { + "epoch": 0.0, + "learning_rate": 3.5377724695894754e-06, + "loss": 3.3022, + "step": 2838016 + }, + { + "epoch": 0.0, + "learning_rate": 3.529386522078955e-06, + "loss": 3.3006, + "step": 2838528 + }, + { + "epoch": 0.0, + "learning_rate": 3.5210005745684353e-06, + "loss": 3.3039, + "step": 2839040 + }, + { + "epoch": 0.01, + "learning_rate": 3.512614627057915e-06, + "loss": 3.3104, + "step": 2839552 + }, + { + "epoch": 0.01, + "learning_rate": 3.5042450583511265e-06, + "loss": 3.317, + "step": 2840064 + }, + { + "epoch": 0.01, + "learning_rate": 3.495859110840606e-06, + "loss": 3.316, + "step": 2840576 + }, + { + "epoch": 0.01, + "learning_rate": 3.4874731633300864e-06, + "loss": 3.3125, + "step": 2841088 + }, + { + "epoch": 0.01, + "learning_rate": 3.479087215819566e-06, + "loss": 3.3006, + "step": 2841600 + }, + { + "epoch": 0.01, + "learning_rate": 3.4707176471127776e-06, + "loss": 3.3083, + "step": 2842112 + }, + { + "epoch": 0.01, + "learning_rate": 3.462331699602257e-06, + "loss": 3.3052, + "step": 2842624 + }, + { + "epoch": 0.01, + "learning_rate": 3.453945752091737e-06, + "loss": 3.3121, + "step": 2843136 + }, + { + "epoch": 0.01, + "learning_rate": 3.445559804581217e-06, + "loss": 3.2997, + "step": 2843648 + }, + { + "epoch": 0.01, + "learning_rate": 3.4371902358744283e-06, + "loss": 3.3001, + "step": 2844160 + }, + { + "epoch": 0.01, + "learning_rate": 3.42882066716764e-06, + "loss": 3.3055, + "step": 2844672 + }, + { + "epoch": 0.01, + "learning_rate": 3.4204347196571194e-06, + "loss": 3.3203, + "step": 2845184 + }, + { + "epoch": 0.01, + "learning_rate": 3.4120487721466e-06, + "loss": 3.3102, + "step": 2845696 + }, + { + "epoch": 0.01, + "learning_rate": 3.4036628246360793e-06, + "loss": 3.3063, + "step": 2846208 + }, + { + "epoch": 0.01, + "learning_rate": 3.3952768771255597e-06, + "loss": 3.3148, + "step": 2846720 + }, + { + "epoch": 0.01, + "learning_rate": 3.3868909296150392e-06, + "loss": 3.304, + "step": 2847232 + }, + { + "epoch": 0.01, + "learning_rate": 3.3785049821045188e-06, + "loss": 3.3131, + "step": 2847744 + }, + { + "epoch": 0.01, + "learning_rate": 3.370119034593999e-06, + "loss": 3.2978, + "step": 2848256 + }, + { + "epoch": 0.01, + "learning_rate": 3.3617494658872104e-06, + "loss": 3.2929, + "step": 2848768 + }, + { + "epoch": 0.01, + "learning_rate": 3.3533635183766903e-06, + "loss": 3.3135, + "step": 2849280 + }, + { + "epoch": 0.01, + "learning_rate": 3.3449775708661703e-06, + "loss": 3.3071, + "step": 2849792 + }, + { + "epoch": 0.01, + "learning_rate": 3.3365916233556507e-06, + "loss": 3.3059, + "step": 2850304 + }, + { + "epoch": 0.01, + "learning_rate": 3.3282220546488615e-06, + "loss": 3.3057, + "step": 2850816 + }, + { + "epoch": 0.01, + "learning_rate": 3.319852485942073e-06, + "loss": 3.3012, + "step": 2851328 + }, + { + "epoch": 0.01, + "learning_rate": 3.3114665384315526e-06, + "loss": 3.292, + "step": 2851840 + }, + { + "epoch": 0.01, + "learning_rate": 3.303080590921033e-06, + "loss": 3.3007, + "step": 2852352 + }, + { + "epoch": 0.01, + "learning_rate": 3.2946946434105125e-06, + "loss": 3.2983, + "step": 2852864 + }, + { + "epoch": 0.01, + "learning_rate": 3.286308695899992e-06, + "loss": 3.3047, + "step": 2853376 + }, + { + "epoch": 0.01, + "learning_rate": 3.2779227483894724e-06, + "loss": 3.3078, + "step": 2853888 + }, + { + "epoch": 0.01, + "learning_rate": 3.269536800878952e-06, + "loss": 3.3042, + "step": 2854400 + }, + { + "epoch": 0.01, + "learning_rate": 3.2611508533684324e-06, + "loss": 3.3056, + "step": 2854912 + }, + { + "epoch": 0.01, + "learning_rate": 3.2527812846616436e-06, + "loss": 3.3154, + "step": 2855424 + }, + { + "epoch": 0.01, + "learning_rate": 3.244395337151124e-06, + "loss": 3.2936, + "step": 2855936 + }, + { + "epoch": 0.01, + "learning_rate": 3.2360093896406035e-06, + "loss": 3.2972, + "step": 2856448 + }, + { + "epoch": 0.01, + "learning_rate": 3.227623442130083e-06, + "loss": 3.3055, + "step": 2856960 + }, + { + "epoch": 0.01, + "learning_rate": 3.2192538734232947e-06, + "loss": 3.3068, + "step": 2857472 + }, + { + "epoch": 0.01, + "learning_rate": 3.210867925912774e-06, + "loss": 3.2953, + "step": 2857984 + }, + { + "epoch": 0.01, + "learning_rate": 3.2024819784022546e-06, + "loss": 3.299, + "step": 2858496 + }, + { + "epoch": 0.01, + "learning_rate": 3.1941124096954654e-06, + "loss": 3.2964, + "step": 2859008 + }, + { + "epoch": 0.01, + "learning_rate": 3.1857264621849457e-06, + "loss": 3.3022, + "step": 2859520 + }, + { + "epoch": 0.01, + "learning_rate": 3.1773405146744253e-06, + "loss": 3.31, + "step": 2860032 + }, + { + "epoch": 0.01, + "learning_rate": 3.1689545671639056e-06, + "loss": 3.3034, + "step": 2860544 + }, + { + "epoch": 0.01, + "learning_rate": 3.1605686196533856e-06, + "loss": 3.3186, + "step": 2861056 + }, + { + "epoch": 0.01, + "learning_rate": 3.152182672142865e-06, + "loss": 3.309, + "step": 2861568 + }, + { + "epoch": 0.01, + "learning_rate": 3.1437967246323455e-06, + "loss": 3.3289, + "step": 2862080 + }, + { + "epoch": 0.01, + "learning_rate": 3.135410777121825e-06, + "loss": 3.2953, + "step": 2862592 + }, + { + "epoch": 0.01, + "learning_rate": 3.127057587218768e-06, + "loss": 3.307, + "step": 2863104 + }, + { + "epoch": 0.01, + "learning_rate": 3.118671639708248e-06, + "loss": 3.3138, + "step": 2863616 + }, + { + "epoch": 0.01, + "learning_rate": 3.1102856921977274e-06, + "loss": 3.2943, + "step": 2864128 + }, + { + "epoch": 0.01, + "learning_rate": 3.1018997446872074e-06, + "loss": 3.3141, + "step": 2864640 + }, + { + "epoch": 0.01, + "learning_rate": 3.0935137971766873e-06, + "loss": 3.3095, + "step": 2865152 + }, + { + "epoch": 0.01, + "learning_rate": 3.0851278496661673e-06, + "loss": 3.3096, + "step": 2865664 + }, + { + "epoch": 0.01, + "learning_rate": 3.0767419021556473e-06, + "loss": 3.3046, + "step": 2866176 + }, + { + "epoch": 0.01, + "learning_rate": 3.068355954645127e-06, + "loss": 3.2906, + "step": 2866688 + }, + { + "epoch": 0.01, + "learning_rate": 3.059986385938339e-06, + "loss": 3.3035, + "step": 2867200 + }, + { + "epoch": 0.01, + "learning_rate": 3.0516004384278184e-06, + "loss": 3.2984, + "step": 2867712 + }, + { + "epoch": 0.01, + "learning_rate": 3.0432144909172983e-06, + "loss": 3.3081, + "step": 2868224 + }, + { + "epoch": 0.01, + "learning_rate": 3.0348285434067783e-06, + "loss": 3.3151, + "step": 2868736 + }, + { + "epoch": 0.01, + "learning_rate": 3.0264589746999895e-06, + "loss": 3.296, + "step": 2869248 + }, + { + "epoch": 0.02, + "learning_rate": 3.0180730271894695e-06, + "loss": 3.3039, + "step": 2869760 + }, + { + "epoch": 0.02, + "learning_rate": 3.0096870796789494e-06, + "loss": 3.2931, + "step": 2870272 + }, + { + "epoch": 0.02, + "learning_rate": 3.0013011321684294e-06, + "loss": 3.2963, + "step": 2870784 + }, + { + "epoch": 0.02, + "learning_rate": 2.9929315634616406e-06, + "loss": 3.3014, + "step": 2871296 + }, + { + "epoch": 0.02, + "learning_rate": 2.9845619947548522e-06, + "loss": 3.3121, + "step": 2871808 + }, + { + "epoch": 0.02, + "learning_rate": 2.976176047244332e-06, + "loss": 3.3155, + "step": 2872320 + }, + { + "epoch": 0.02, + "learning_rate": 2.967790099733812e-06, + "loss": 3.3007, + "step": 2872832 + }, + { + "epoch": 0.02, + "learning_rate": 2.9594041522232917e-06, + "loss": 3.3007, + "step": 2873344 + }, + { + "epoch": 0.02, + "learning_rate": 2.9510182047127716e-06, + "loss": 3.3113, + "step": 2873856 + }, + { + "epoch": 0.02, + "learning_rate": 2.9426322572022516e-06, + "loss": 3.2987, + "step": 2874368 + }, + { + "epoch": 0.02, + "learning_rate": 2.9342463096917315e-06, + "loss": 3.3123, + "step": 2874880 + }, + { + "epoch": 0.02, + "learning_rate": 2.9258767409849427e-06, + "loss": 3.2954, + "step": 2875392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9174907934744227e-06, + "loss": 3.3007, + "step": 2875904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9091048459639022e-06, + "loss": 3.3035, + "step": 2876416 + }, + { + "epoch": 0.02, + "learning_rate": 2.900735277257114e-06, + "loss": 3.3132, + "step": 2876928 + }, + { + "epoch": 0.02, + "learning_rate": 2.892349329746594e-06, + "loss": 3.2932, + "step": 2877440 + }, + { + "epoch": 0.02, + "learning_rate": 2.8839633822360738e-06, + "loss": 3.3019, + "step": 2877952 + }, + { + "epoch": 0.02, + "learning_rate": 2.8755774347255537e-06, + "loss": 3.3076, + "step": 2878464 + }, + { + "epoch": 0.02, + "learning_rate": 2.867207866018765e-06, + "loss": 3.3113, + "step": 2878976 + }, + { + "epoch": 0.02, + "learning_rate": 2.858821918508245e-06, + "loss": 3.2884, + "step": 2879488 + }, + { + "epoch": 0.02, + "learning_rate": 2.850435970997725e-06, + "loss": 3.3079, + "step": 2880000 + }, + { + "epoch": 0.02, + "learning_rate": 2.842050023487205e-06, + "loss": 3.2955, + "step": 2880512 + }, + { + "epoch": 0.02, + "learning_rate": 2.8336640759766844e-06, + "loss": 3.3077, + "step": 2881024 + }, + { + "epoch": 0.02, + "learning_rate": 2.8252781284661643e-06, + "loss": 3.3027, + "step": 2881536 + }, + { + "epoch": 0.02, + "learning_rate": 2.8168921809556443e-06, + "loss": 3.299, + "step": 2882048 + }, + { + "epoch": 0.02, + "learning_rate": 2.8085226122488555e-06, + "loss": 3.3097, + "step": 2882560 + }, + { + "epoch": 0.02, + "learning_rate": 2.8001366647383354e-06, + "loss": 3.3177, + "step": 2883072 + }, + { + "epoch": 0.02, + "learning_rate": 2.791750717227816e-06, + "loss": 3.3044, + "step": 2883584 + }, + { + "epoch": 0.02, + "learning_rate": 2.7833647697172958e-06, + "loss": 3.3031, + "step": 2884096 + }, + { + "epoch": 0.02, + "learning_rate": 2.7749788222067753e-06, + "loss": 3.3086, + "step": 2884608 + }, + { + "epoch": 0.02, + "learning_rate": 2.766609253499987e-06, + "loss": 3.3034, + "step": 2885120 + }, + { + "epoch": 0.02, + "learning_rate": 2.7582233059894665e-06, + "loss": 3.2961, + "step": 2885632 + }, + { + "epoch": 0.02, + "learning_rate": 2.7498373584789464e-06, + "loss": 3.3035, + "step": 2886144 + }, + { + "epoch": 0.02, + "learning_rate": 2.7414514109684264e-06, + "loss": 3.3014, + "step": 2886656 + }, + { + "epoch": 0.02, + "learning_rate": 2.7330654634579063e-06, + "loss": 3.3028, + "step": 2887168 + }, + { + "epoch": 0.02, + "learning_rate": 2.7246795159473863e-06, + "loss": 3.3048, + "step": 2887680 + }, + { + "epoch": 0.02, + "learning_rate": 2.716293568436866e-06, + "loss": 3.3035, + "step": 2888192 + }, + { + "epoch": 0.02, + "learning_rate": 2.7079239997300775e-06, + "loss": 3.3003, + "step": 2888704 + }, + { + "epoch": 0.02, + "learning_rate": 2.6995380522195574e-06, + "loss": 3.2938, + "step": 2889216 + }, + { + "epoch": 0.02, + "learning_rate": 2.6911521047090374e-06, + "loss": 3.3038, + "step": 2889728 + }, + { + "epoch": 0.02, + "learning_rate": 2.6827661571985173e-06, + "loss": 3.3108, + "step": 2890240 + }, + { + "epoch": 0.02, + "learning_rate": 2.6743965884917285e-06, + "loss": 3.3116, + "step": 2890752 + }, + { + "epoch": 0.02, + "learning_rate": 2.6660106409812085e-06, + "loss": 3.3147, + "step": 2891264 + }, + { + "epoch": 0.02, + "learning_rate": 2.6576246934706885e-06, + "loss": 3.2912, + "step": 2891776 + }, + { + "epoch": 0.02, + "learning_rate": 2.6492387459601684e-06, + "loss": 3.3152, + "step": 2892288 + }, + { + "epoch": 0.02, + "learning_rate": 2.640885556057111e-06, + "loss": 3.3093, + "step": 2892800 + }, + { + "epoch": 0.02, + "learning_rate": 2.632499608546591e-06, + "loss": 3.3035, + "step": 2893312 + }, + { + "epoch": 0.02, + "learning_rate": 2.624113661036071e-06, + "loss": 3.2998, + "step": 2893824 + }, + { + "epoch": 0.02, + "learning_rate": 2.6157277135255508e-06, + "loss": 3.3092, + "step": 2894336 + }, + { + "epoch": 0.02, + "learning_rate": 2.6073417660150307e-06, + "loss": 3.2986, + "step": 2894848 + }, + { + "epoch": 0.02, + "learning_rate": 2.5989558185045107e-06, + "loss": 3.3185, + "step": 2895360 + }, + { + "epoch": 0.02, + "learning_rate": 2.5905698709939906e-06, + "loss": 3.2924, + "step": 2895872 + }, + { + "epoch": 0.02, + "learning_rate": 2.5821839234834706e-06, + "loss": 3.3121, + "step": 2896384 + }, + { + "epoch": 0.02, + "learning_rate": 2.5738143547766818e-06, + "loss": 3.2938, + "step": 2896896 + }, + { + "epoch": 0.02, + "learning_rate": 2.5654284072661617e-06, + "loss": 3.3033, + "step": 2897408 + }, + { + "epoch": 0.02, + "learning_rate": 2.5570424597556413e-06, + "loss": 3.306, + "step": 2897920 + }, + { + "epoch": 0.02, + "learning_rate": 2.5486565122451212e-06, + "loss": 3.3048, + "step": 2898432 + }, + { + "epoch": 0.02, + "learning_rate": 2.5402869435383324e-06, + "loss": 3.3168, + "step": 2898944 + }, + { + "epoch": 0.02, + "learning_rate": 2.5319009960278124e-06, + "loss": 3.2868, + "step": 2899456 + }, + { + "epoch": 0.02, + "learning_rate": 2.5235150485172924e-06, + "loss": 3.3058, + "step": 2899968 + }, + { + "epoch": 0.03, + "eval_loss": 3.862410068511963, + "eval_runtime": 301.9782, + "eval_samples_per_second": 1263.638, + "eval_steps_per_second": 39.49, + "step": 2900160 + }, + { + "epoch": 1.0, + "learning_rate": 2.5151291010067723e-06, + "loss": 3.3047, + "step": 2900480 + }, + { + "epoch": 1.0, + "learning_rate": 2.506759532299984e-06, + "loss": 3.3025, + "step": 2900992 + }, + { + "epoch": 1.0, + "learning_rate": 2.498373584789464e-06, + "loss": 3.3075, + "step": 2901504 + }, + { + "epoch": 1.0, + "learning_rate": 2.489987637278944e-06, + "loss": 3.3044, + "step": 2902016 + }, + { + "epoch": 1.0, + "learning_rate": 2.4816016897684234e-06, + "loss": 3.3133, + "step": 2902528 + }, + { + "epoch": 1.0, + "learning_rate": 2.473232121061635e-06, + "loss": 3.3003, + "step": 2903040 + }, + { + "epoch": 1.0, + "learning_rate": 2.4648461735511146e-06, + "loss": 3.2973, + "step": 2903552 + }, + { + "epoch": 1.0, + "learning_rate": 2.4564602260405945e-06, + "loss": 3.3001, + "step": 2904064 + }, + { + "epoch": 1.0, + "learning_rate": 2.4480742785300745e-06, + "loss": 3.3067, + "step": 2904576 + }, + { + "epoch": 1.0, + "learning_rate": 2.4397047098232857e-06, + "loss": 3.3092, + "step": 2905088 + }, + { + "epoch": 1.0, + "learning_rate": 2.4313187623127656e-06, + "loss": 3.3052, + "step": 2905600 + }, + { + "epoch": 1.0, + "learning_rate": 2.4229491936059773e-06, + "loss": 3.3039, + "step": 2906112 + }, + { + "epoch": 1.0, + "learning_rate": 2.4145632460954572e-06, + "loss": 3.2978, + "step": 2906624 + }, + { + "epoch": 1.0, + "learning_rate": 2.406177298584937e-06, + "loss": 3.2953, + "step": 2907136 + }, + { + "epoch": 1.0, + "learning_rate": 2.397791351074417e-06, + "loss": 3.303, + "step": 2907648 + }, + { + "epoch": 1.0, + "learning_rate": 2.3894054035638967e-06, + "loss": 3.2931, + "step": 2908160 + }, + { + "epoch": 1.0, + "learning_rate": 2.3810194560533766e-06, + "loss": 3.3036, + "step": 2908672 + }, + { + "epoch": 1.0, + "learning_rate": 2.3726335085428566e-06, + "loss": 3.2962, + "step": 2909184 + }, + { + "epoch": 1.0, + "learning_rate": 2.3642475610323365e-06, + "loss": 3.2996, + "step": 2909696 + }, + { + "epoch": 1.0, + "learning_rate": 2.3558779923255478e-06, + "loss": 3.3138, + "step": 2910208 + }, + { + "epoch": 1.0, + "learning_rate": 2.3474920448150277e-06, + "loss": 3.3063, + "step": 2910720 + }, + { + "epoch": 1.0, + "learning_rate": 2.339122476108239e-06, + "loss": 3.3119, + "step": 2911232 + }, + { + "epoch": 1.0, + "learning_rate": 2.3307365285977193e-06, + "loss": 3.304, + "step": 2911744 + }, + { + "epoch": 1.0, + "learning_rate": 2.3223505810871993e-06, + "loss": 3.3087, + "step": 2912256 + }, + { + "epoch": 1.0, + "learning_rate": 2.313964633576679e-06, + "loss": 3.2925, + "step": 2912768 + }, + { + "epoch": 1.0, + "learning_rate": 2.3055786860661588e-06, + "loss": 3.3142, + "step": 2913280 + }, + { + "epoch": 1.0, + "learning_rate": 2.2971927385556387e-06, + "loss": 3.2997, + "step": 2913792 + }, + { + "epoch": 1.0, + "learning_rate": 2.2888067910451187e-06, + "loss": 3.2954, + "step": 2914304 + }, + { + "epoch": 1.0, + "learning_rate": 2.280420843534598e-06, + "loss": 3.2945, + "step": 2914816 + }, + { + "epoch": 1.0, + "learning_rate": 2.27205127482781e-06, + "loss": 3.2976, + "step": 2915328 + }, + { + "epoch": 1.01, + "learning_rate": 2.2636653273172894e-06, + "loss": 3.3014, + "step": 2915840 + }, + { + "epoch": 1.01, + "learning_rate": 2.2552793798067693e-06, + "loss": 3.3098, + "step": 2916352 + }, + { + "epoch": 1.01, + "learning_rate": 2.2468934322962493e-06, + "loss": 3.3073, + "step": 2916864 + }, + { + "epoch": 1.01, + "learning_rate": 2.238523863589461e-06, + "loss": 3.3051, + "step": 2917376 + }, + { + "epoch": 1.01, + "learning_rate": 2.230137916078941e-06, + "loss": 3.2901, + "step": 2917888 + }, + { + "epoch": 1.01, + "learning_rate": 2.221751968568421e-06, + "loss": 3.3041, + "step": 2918400 + }, + { + "epoch": 1.01, + "learning_rate": 2.2133660210579008e-06, + "loss": 3.3013, + "step": 2918912 + }, + { + "epoch": 1.01, + "learning_rate": 2.204996452351112e-06, + "loss": 3.2992, + "step": 2919424 + }, + { + "epoch": 1.01, + "learning_rate": 2.196610504840592e-06, + "loss": 3.2957, + "step": 2919936 + }, + { + "epoch": 1.01, + "learning_rate": 2.1882245573300715e-06, + "loss": 3.2896, + "step": 2920448 + }, + { + "epoch": 1.01, + "learning_rate": 2.1798386098195514e-06, + "loss": 3.2983, + "step": 2920960 + }, + { + "epoch": 1.01, + "learning_rate": 2.1714854199164943e-06, + "loss": 3.3112, + "step": 2921472 + }, + { + "epoch": 1.01, + "learning_rate": 2.1630994724059743e-06, + "loss": 3.3056, + "step": 2921984 + }, + { + "epoch": 1.01, + "learning_rate": 2.1547135248954542e-06, + "loss": 3.2997, + "step": 2922496 + }, + { + "epoch": 1.01, + "learning_rate": 2.146327577384934e-06, + "loss": 3.3055, + "step": 2923008 + }, + { + "epoch": 1.01, + "learning_rate": 2.137941629874414e-06, + "loss": 3.2964, + "step": 2923520 + }, + { + "epoch": 1.01, + "learning_rate": 2.129555682363894e-06, + "loss": 3.3057, + "step": 2924032 + }, + { + "epoch": 1.01, + "learning_rate": 2.121169734853374e-06, + "loss": 3.2886, + "step": 2924544 + }, + { + "epoch": 1.01, + "learning_rate": 2.1128001661465853e-06, + "loss": 3.2811, + "step": 2925056 + }, + { + "epoch": 1.01, + "learning_rate": 2.1044142186360652e-06, + "loss": 3.3057, + "step": 2925568 + }, + { + "epoch": 1.01, + "learning_rate": 2.0960282711255448e-06, + "loss": 3.2998, + "step": 2926080 + }, + { + "epoch": 1.01, + "learning_rate": 2.0876423236150247e-06, + "loss": 3.3014, + "step": 2926592 + }, + { + "epoch": 1.01, + "learning_rate": 2.079272754908236e-06, + "loss": 3.296, + "step": 2927104 + }, + { + "epoch": 1.01, + "learning_rate": 2.070886807397716e-06, + "loss": 3.2922, + "step": 2927616 + }, + { + "epoch": 1.01, + "learning_rate": 2.062500859887196e-06, + "loss": 3.2878, + "step": 2928128 + }, + { + "epoch": 1.01, + "learning_rate": 2.054114912376676e-06, + "loss": 3.2924, + "step": 2928640 + }, + { + "epoch": 1.01, + "learning_rate": 2.0457453436698874e-06, + "loss": 3.2905, + "step": 2929152 + }, + { + "epoch": 1.01, + "learning_rate": 2.0373593961593674e-06, + "loss": 3.3008, + "step": 2929664 + }, + { + "epoch": 1.01, + "learning_rate": 2.0289734486488474e-06, + "loss": 3.2962, + "step": 2930176 + }, + { + "epoch": 1.01, + "learning_rate": 2.020587501138327e-06, + "loss": 3.2958, + "step": 2930688 + }, + { + "epoch": 1.01, + "learning_rate": 2.0122343112352698e-06, + "loss": 3.2949, + "step": 2931200 + }, + { + "epoch": 1.01, + "learning_rate": 2.0038483637247497e-06, + "loss": 3.3135, + "step": 2931712 + }, + { + "epoch": 1.01, + "learning_rate": 1.9954624162142297e-06, + "loss": 3.2828, + "step": 2932224 + }, + { + "epoch": 1.01, + "learning_rate": 1.9870764687037092e-06, + "loss": 3.2868, + "step": 2932736 + }, + { + "epoch": 1.01, + "learning_rate": 1.978690521193189e-06, + "loss": 3.2976, + "step": 2933248 + }, + { + "epoch": 1.01, + "learning_rate": 1.970304573682669e-06, + "loss": 3.3012, + "step": 2933760 + }, + { + "epoch": 1.01, + "learning_rate": 1.961918626172149e-06, + "loss": 3.2883, + "step": 2934272 + }, + { + "epoch": 1.01, + "learning_rate": 1.953532678661629e-06, + "loss": 3.2888, + "step": 2934784 + }, + { + "epoch": 1.01, + "learning_rate": 1.945179488758572e-06, + "loss": 3.2897, + "step": 2935296 + }, + { + "epoch": 1.01, + "learning_rate": 1.936793541248052e-06, + "loss": 3.293, + "step": 2935808 + }, + { + "epoch": 1.01, + "learning_rate": 1.928407593737532e-06, + "loss": 3.3055, + "step": 2936320 + }, + { + "epoch": 1.01, + "learning_rate": 1.9200216462270114e-06, + "loss": 3.2961, + "step": 2936832 + }, + { + "epoch": 1.01, + "learning_rate": 1.9116356987164913e-06, + "loss": 3.3044, + "step": 2937344 + }, + { + "epoch": 1.01, + "learning_rate": 1.9032497512059713e-06, + "loss": 3.3053, + "step": 2937856 + }, + { + "epoch": 1.01, + "learning_rate": 1.8948638036954513e-06, + "loss": 3.3198, + "step": 2938368 + }, + { + "epoch": 1.01, + "learning_rate": 1.8864778561849314e-06, + "loss": 3.2921, + "step": 2938880 + }, + { + "epoch": 1.01, + "learning_rate": 1.878124666281874e-06, + "loss": 3.3011, + "step": 2939392 + }, + { + "epoch": 1.01, + "learning_rate": 1.8697387187713539e-06, + "loss": 3.3037, + "step": 2939904 + }, + { + "epoch": 1.01, + "learning_rate": 1.8613527712608338e-06, + "loss": 3.2862, + "step": 2940416 + }, + { + "epoch": 1.01, + "learning_rate": 1.8529668237503138e-06, + "loss": 3.3052, + "step": 2940928 + }, + { + "epoch": 1.01, + "learning_rate": 1.8445808762397935e-06, + "loss": 3.3014, + "step": 2941440 + }, + { + "epoch": 1.01, + "learning_rate": 1.8361949287292735e-06, + "loss": 3.301, + "step": 2941952 + }, + { + "epoch": 1.01, + "learning_rate": 1.8278089812187534e-06, + "loss": 3.3012, + "step": 2942464 + }, + { + "epoch": 1.01, + "learning_rate": 1.8194230337082334e-06, + "loss": 3.2829, + "step": 2942976 + }, + { + "epoch": 1.01, + "learning_rate": 1.8110534650014446e-06, + "loss": 3.2926, + "step": 2943488 + }, + { + "epoch": 1.01, + "learning_rate": 1.8026675174909248e-06, + "loss": 3.2928, + "step": 2944000 + }, + { + "epoch": 1.01, + "learning_rate": 1.794297948784136e-06, + "loss": 3.3, + "step": 2944512 + }, + { + "epoch": 1.01, + "learning_rate": 1.785912001273616e-06, + "loss": 3.3065, + "step": 2945024 + }, + { + "epoch": 1.01, + "learning_rate": 1.7775260537630959e-06, + "loss": 3.2904, + "step": 2945536 + }, + { + "epoch": 1.02, + "learning_rate": 1.7691401062525754e-06, + "loss": 3.2968, + "step": 2946048 + }, + { + "epoch": 1.02, + "learning_rate": 1.7607541587420556e-06, + "loss": 3.2877, + "step": 2946560 + }, + { + "epoch": 1.02, + "learning_rate": 1.7523682112315355e-06, + "loss": 3.2868, + "step": 2947072 + }, + { + "epoch": 1.02, + "learning_rate": 1.7439822637210155e-06, + "loss": 3.296, + "step": 2947584 + }, + { + "epoch": 1.02, + "learning_rate": 1.7355963162104955e-06, + "loss": 3.3013, + "step": 2948096 + }, + { + "epoch": 1.02, + "learning_rate": 1.7272267475037067e-06, + "loss": 3.3061, + "step": 2948608 + }, + { + "epoch": 1.02, + "learning_rate": 1.7188407999931866e-06, + "loss": 3.2973, + "step": 2949120 + }, + { + "epoch": 1.02, + "learning_rate": 1.7104548524826664e-06, + "loss": 3.2916, + "step": 2949632 + }, + { + "epoch": 1.02, + "learning_rate": 1.7020689049721463e-06, + "loss": 3.301, + "step": 2950144 + }, + { + "epoch": 1.02, + "learning_rate": 1.6936993362653575e-06, + "loss": 3.2936, + "step": 2950656 + }, + { + "epoch": 1.02, + "learning_rate": 1.6853133887548375e-06, + "loss": 3.3028, + "step": 2951168 + }, + { + "epoch": 1.02, + "learning_rate": 1.6769274412443174e-06, + "loss": 3.2911, + "step": 2951680 + }, + { + "epoch": 1.02, + "learning_rate": 1.6685578725375289e-06, + "loss": 3.2913, + "step": 2952192 + }, + { + "epoch": 1.02, + "learning_rate": 1.6601719250270088e-06, + "loss": 3.2959, + "step": 2952704 + }, + { + "epoch": 1.02, + "learning_rate": 1.65180235632022e-06, + "loss": 3.3072, + "step": 2953216 + }, + { + "epoch": 1.02, + "learning_rate": 1.6434164088097e-06, + "loss": 3.2806, + "step": 2953728 + }, + { + "epoch": 1.02, + "learning_rate": 1.63503046129918e-06, + "loss": 3.2966, + "step": 2954240 + }, + { + "epoch": 1.02, + "learning_rate": 1.6266445137886597e-06, + "loss": 3.2977, + "step": 2954752 + }, + { + "epoch": 1.02, + "learning_rate": 1.6182749450818713e-06, + "loss": 3.306, + "step": 2955264 + }, + { + "epoch": 1.02, + "learning_rate": 1.6098889975713509e-06, + "loss": 3.2806, + "step": 2955776 + }, + { + "epoch": 1.02, + "learning_rate": 1.6015030500608308e-06, + "loss": 3.2979, + "step": 2956288 + }, + { + "epoch": 1.02, + "learning_rate": 1.5931171025503108e-06, + "loss": 3.2947, + "step": 2956800 + }, + { + "epoch": 1.02, + "learning_rate": 1.5847311550397907e-06, + "loss": 3.2971, + "step": 2957312 + }, + { + "epoch": 1.02, + "learning_rate": 1.5763452075292707e-06, + "loss": 3.3011, + "step": 2957824 + }, + { + "epoch": 1.02, + "learning_rate": 1.5679592600187504e-06, + "loss": 3.2932, + "step": 2958336 + }, + { + "epoch": 1.02, + "learning_rate": 1.5595896913119619e-06, + "loss": 3.2974, + "step": 2958848 + }, + { + "epoch": 1.02, + "learning_rate": 1.5512037438014418e-06, + "loss": 3.3116, + "step": 2959360 + }, + { + "epoch": 1.02, + "learning_rate": 1.5428177962909216e-06, + "loss": 3.2987, + "step": 2959872 + }, + { + "epoch": 1.02, + "learning_rate": 1.5344318487804015e-06, + "loss": 3.2937, + "step": 2960384 + }, + { + "epoch": 1.02, + "learning_rate": 1.5260459012698815e-06, + "loss": 3.3048, + "step": 2960896 + }, + { + "epoch": 1.02, + "learning_rate": 1.517676332563093e-06, + "loss": 3.2971, + "step": 2961408 + }, + { + "epoch": 1.02, + "learning_rate": 1.5092903850525729e-06, + "loss": 3.2854, + "step": 2961920 + }, + { + "epoch": 1.02, + "learning_rate": 1.5009044375420526e-06, + "loss": 3.2985, + "step": 2962432 + }, + { + "epoch": 1.02, + "learning_rate": 1.4925184900315326e-06, + "loss": 3.2918, + "step": 2962944 + }, + { + "epoch": 1.02, + "learning_rate": 1.4841325425210123e-06, + "loss": 3.2933, + "step": 2963456 + }, + { + "epoch": 1.02, + "learning_rate": 1.4757465950104922e-06, + "loss": 3.2946, + "step": 2963968 + }, + { + "epoch": 1.02, + "learning_rate": 1.4673606474999722e-06, + "loss": 3.2969, + "step": 2964480 + }, + { + "epoch": 1.02, + "learning_rate": 1.4589910787931836e-06, + "loss": 3.2948, + "step": 2964992 + }, + { + "epoch": 1.02, + "learning_rate": 1.4506051312826636e-06, + "loss": 3.2883, + "step": 2965504 + }, + { + "epoch": 1.02, + "learning_rate": 1.4422191837721433e-06, + "loss": 3.2936, + "step": 2966016 + }, + { + "epoch": 1.02, + "learning_rate": 1.4338332362616233e-06, + "loss": 3.3042, + "step": 2966528 + }, + { + "epoch": 1.02, + "learning_rate": 1.4254636675548347e-06, + "loss": 3.2992, + "step": 2967040 + }, + { + "epoch": 1.02, + "learning_rate": 1.4170777200443147e-06, + "loss": 3.309, + "step": 2967552 + }, + { + "epoch": 1.02, + "learning_rate": 1.4086917725337944e-06, + "loss": 3.2853, + "step": 2968064 + }, + { + "epoch": 1.02, + "learning_rate": 1.4003058250232744e-06, + "loss": 3.311, + "step": 2968576 + }, + { + "epoch": 1.02, + "learning_rate": 1.3919362563164856e-06, + "loss": 3.2993, + "step": 2969088 + }, + { + "epoch": 1.02, + "learning_rate": 1.3835503088059657e-06, + "loss": 3.299, + "step": 2969600 + }, + { + "epoch": 1.02, + "learning_rate": 1.3751643612954455e-06, + "loss": 3.2921, + "step": 2970112 + }, + { + "epoch": 1.02, + "learning_rate": 1.3667784137849254e-06, + "loss": 3.3028, + "step": 2970624 + }, + { + "epoch": 1.02, + "learning_rate": 1.3583924662744054e-06, + "loss": 3.29, + "step": 2971136 + }, + { + "epoch": 1.02, + "learning_rate": 1.3500065187638851e-06, + "loss": 3.3152, + "step": 2971648 + }, + { + "epoch": 1.02, + "learning_rate": 1.341620571253365e-06, + "loss": 3.2852, + "step": 2972160 + }, + { + "epoch": 1.02, + "learning_rate": 1.3332346237428448e-06, + "loss": 3.3006, + "step": 2972672 + }, + { + "epoch": 1.02, + "learning_rate": 1.3248650550360565e-06, + "loss": 3.2914, + "step": 2973184 + }, + { + "epoch": 1.02, + "learning_rate": 1.3164791075255362e-06, + "loss": 3.2971, + "step": 2973696 + }, + { + "epoch": 1.02, + "learning_rate": 1.3080931600150162e-06, + "loss": 3.2947, + "step": 2974208 + }, + { + "epoch": 1.02, + "learning_rate": 1.2997072125044961e-06, + "loss": 3.2939, + "step": 2974720 + }, + { + "epoch": 1.02, + "learning_rate": 1.2913376437977074e-06, + "loss": 3.3118, + "step": 2975232 + }, + { + "epoch": 1.02, + "learning_rate": 1.2829516962871873e-06, + "loss": 3.2822, + "step": 2975744 + }, + { + "epoch": 1.02, + "learning_rate": 1.2745657487766673e-06, + "loss": 3.3017, + "step": 2976256 + }, + { + "epoch": 1.03, + "eval_loss": 3.8610048294067383, + "eval_runtime": 312.8772, + "eval_samples_per_second": 1219.619, + "eval_steps_per_second": 38.114, + "step": 2976480 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 2.072198558287743e+18, + "trial_name": null, + "trial_params": null +}