{ "best_metric": 4.089334011077881, "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/npi-sim-ques/lstm/1/checkpoints/checkpoint-686880", "epoch": 0.025000606015738065, "eval_steps": 10, "global_step": 686880, "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": 10.8187, "step": 1 }, { "epoch": 0.0, "learning_rate": 4.999161405248948e-05, "loss": 7.5493, "step": 512 }, { "epoch": 0.0, "learning_rate": 4.998322810497896e-05, "loss": 7.0583, "step": 1024 }, { "epoch": 0.0, "learning_rate": 4.997484215746844e-05, "loss": 6.992, "step": 1536 }, { "epoch": 0.0, "learning_rate": 4.996645620995792e-05, "loss": 6.9458, "step": 2048 }, { "epoch": 0.0, "learning_rate": 4.99580702624474e-05, "loss": 6.8864, "step": 2560 }, { "epoch": 0.0, "learning_rate": 4.994970069374061e-05, "loss": 6.7227, "step": 3072 }, { "epoch": 0.0, "learning_rate": 4.994131474623009e-05, "loss": 6.6176, "step": 3584 }, { "epoch": 0.0, "learning_rate": 4.993294517752331e-05, "loss": 6.5241, "step": 4096 }, { "epoch": 0.0, "learning_rate": 4.992455923001279e-05, "loss": 6.449, "step": 4608 }, { "epoch": 0.0, "learning_rate": 4.991617328250227e-05, "loss": 6.3876, "step": 5120 }, { "epoch": 0.0, "learning_rate": 4.990778733499175e-05, "loss": 6.3439, "step": 5632 }, { "epoch": 0.0, "learning_rate": 4.989940138748123e-05, "loss": 6.2832, "step": 6144 }, { "epoch": 0.0, "learning_rate": 4.989101543997071e-05, "loss": 6.2131, "step": 6656 }, { "epoch": 0.0, "learning_rate": 4.988262949246018e-05, "loss": 6.1616, "step": 7168 }, { "epoch": 0.0, "learning_rate": 4.987424354494966e-05, "loss": 6.0988, "step": 7680 }, { "epoch": 0.0, "learning_rate": 4.986585759743914e-05, "loss": 6.0622, "step": 8192 }, { "epoch": 0.0, "learning_rate": 4.985747164992862e-05, "loss": 6.0039, "step": 8704 }, { "epoch": 0.0, "learning_rate": 4.98490857024181e-05, "loss": 5.9591, "step": 9216 }, { "epoch": 0.0, "learning_rate": 4.984069975490758e-05, "loss": 5.9277, "step": 9728 }, { "epoch": 0.0, "learning_rate": 4.983231380739706e-05, "loss": 5.8875, "step": 10240 }, { "epoch": 0.0, "learning_rate": 4.9823927859886547e-05, "loss": 5.8579, "step": 10752 }, { "epoch": 0.0, "learning_rate": 4.9815541912376026e-05, "loss": 5.8314, "step": 11264 }, { "epoch": 0.0, "learning_rate": 4.9807155964865506e-05, "loss": 5.7989, "step": 11776 }, { "epoch": 0.0, "learning_rate": 4.9798770017354986e-05, "loss": 5.7698, "step": 12288 }, { "epoch": 0.0, "learning_rate": 4.9790384069844466e-05, "loss": 5.7438, "step": 12800 }, { "epoch": 0.0, "learning_rate": 4.9781998122333946e-05, "loss": 5.714, "step": 13312 }, { "epoch": 0.0, "learning_rate": 4.9773612174823426e-05, "loss": 5.687, "step": 13824 }, { "epoch": 0.0, "learning_rate": 4.97652262273129e-05, "loss": 5.6592, "step": 14336 }, { "epoch": 0.0, "learning_rate": 4.9756856658606115e-05, "loss": 5.6469, "step": 14848 }, { "epoch": 0.01, "learning_rate": 4.9748470711095595e-05, "loss": 5.6244, "step": 15360 }, { "epoch": 0.01, "learning_rate": 4.974008476358507e-05, "loss": 5.6032, "step": 15872 }, { "epoch": 0.01, "learning_rate": 4.973169881607455e-05, "loss": 5.5808, "step": 16384 }, { "epoch": 0.01, "learning_rate": 4.972331286856403e-05, "loss": 5.5601, "step": 16896 }, { "epoch": 0.01, "learning_rate": 4.9714943299857244e-05, "loss": 5.5537, "step": 17408 }, { "epoch": 0.01, "learning_rate": 4.9706557352346724e-05, "loss": 5.5419, "step": 17920 }, { "epoch": 0.01, "learning_rate": 4.9698171404836204e-05, "loss": 5.5192, "step": 18432 }, { "epoch": 0.01, "learning_rate": 4.9689785457325684e-05, "loss": 5.4788, "step": 18944 }, { "epoch": 0.01, "learning_rate": 4.9681399509815164e-05, "loss": 5.4857, "step": 19456 }, { "epoch": 0.01, "learning_rate": 4.967302994110837e-05, "loss": 5.4502, "step": 19968 }, { "epoch": 0.01, "learning_rate": 4.966464399359785e-05, "loss": 5.4444, "step": 20480 }, { "epoch": 0.01, "learning_rate": 4.965625804608733e-05, "loss": 5.4355, "step": 20992 }, { "epoch": 0.01, "learning_rate": 4.964787209857681e-05, "loss": 5.4262, "step": 21504 }, { "epoch": 0.01, "learning_rate": 4.963950252987002e-05, "loss": 5.4044, "step": 22016 }, { "epoch": 0.01, "learning_rate": 4.96311165823595e-05, "loss": 5.3987, "step": 22528 }, { "epoch": 0.01, "learning_rate": 4.962273063484898e-05, "loss": 5.3924, "step": 23040 }, { "epoch": 0.01, "learning_rate": 4.961434468733847e-05, "loss": 5.38, "step": 23552 }, { "epoch": 0.01, "learning_rate": 4.960597511863168e-05, "loss": 5.3699, "step": 24064 }, { "epoch": 0.01, "learning_rate": 4.959758917112116e-05, "loss": 5.3495, "step": 24576 }, { "epoch": 0.01, "learning_rate": 4.958920322361064e-05, "loss": 5.338, "step": 25088 }, { "epoch": 0.01, "learning_rate": 4.958081727610012e-05, "loss": 5.3415, "step": 25600 }, { "epoch": 0.01, "learning_rate": 4.957244770739333e-05, "loss": 5.321, "step": 26112 }, { "epoch": 0.01, "learning_rate": 4.956406175988281e-05, "loss": 5.31, "step": 26624 }, { "epoch": 0.01, "learning_rate": 4.955567581237229e-05, "loss": 5.2912, "step": 27136 }, { "epoch": 0.01, "learning_rate": 4.9547306243665496e-05, "loss": 5.2959, "step": 27648 }, { "epoch": 0.01, "learning_rate": 4.953893667495871e-05, "loss": 5.2768, "step": 28160 }, { "epoch": 0.01, "learning_rate": 4.953055072744819e-05, "loss": 5.291, "step": 28672 }, { "epoch": 0.01, "learning_rate": 4.952216477993767e-05, "loss": 5.262, "step": 29184 }, { "epoch": 0.01, "learning_rate": 4.951377883242715e-05, "loss": 5.2594, "step": 29696 }, { "epoch": 0.01, "learning_rate": 4.950539288491663e-05, "loss": 5.2526, "step": 30208 }, { "epoch": 0.01, "learning_rate": 4.949700693740611e-05, "loss": 5.2299, "step": 30720 }, { "epoch": 0.01, "learning_rate": 4.948862098989559e-05, "loss": 5.2337, "step": 31232 }, { "epoch": 0.01, "learning_rate": 4.948023504238507e-05, "loss": 5.2199, "step": 31744 }, { "epoch": 0.01, "learning_rate": 4.947184909487455e-05, "loss": 5.2086, "step": 32256 }, { "epoch": 0.01, "learning_rate": 4.946346314736403e-05, "loss": 5.2037, "step": 32768 }, { "epoch": 0.01, "learning_rate": 4.945507719985351e-05, "loss": 5.2206, "step": 33280 }, { "epoch": 0.01, "learning_rate": 4.944669125234299e-05, "loss": 5.1949, "step": 33792 }, { "epoch": 0.01, "learning_rate": 4.943830530483247e-05, "loss": 5.1829, "step": 34304 }, { "epoch": 0.01, "learning_rate": 4.942991935732195e-05, "loss": 5.1633, "step": 34816 }, { "epoch": 0.01, "learning_rate": 4.942154978861516e-05, "loss": 5.1625, "step": 35328 }, { "epoch": 0.01, "learning_rate": 4.941316384110464e-05, "loss": 5.1757, "step": 35840 }, { "epoch": 0.01, "learning_rate": 4.940477789359412e-05, "loss": 5.1726, "step": 36352 }, { "epoch": 0.01, "learning_rate": 4.9396408324887336e-05, "loss": 5.1469, "step": 36864 }, { "epoch": 0.01, "learning_rate": 4.9388022377376816e-05, "loss": 5.1634, "step": 37376 }, { "epoch": 0.01, "learning_rate": 4.9379636429866296e-05, "loss": 5.1544, "step": 37888 }, { "epoch": 0.01, "learning_rate": 4.9371250482355776e-05, "loss": 5.1398, "step": 38400 }, { "epoch": 0.01, "learning_rate": 4.9362864534845256e-05, "loss": 5.1202, "step": 38912 }, { "epoch": 0.01, "learning_rate": 4.935447858733473e-05, "loss": 5.1245, "step": 39424 }, { "epoch": 0.01, "learning_rate": 4.934609263982421e-05, "loss": 5.1081, "step": 39936 }, { "epoch": 0.01, "learning_rate": 4.933770669231369e-05, "loss": 5.1055, "step": 40448 }, { "epoch": 0.01, "learning_rate": 4.932932074480317e-05, "loss": 5.106, "step": 40960 }, { "epoch": 0.01, "learning_rate": 4.932093479729265e-05, "loss": 5.0957, "step": 41472 }, { "epoch": 0.01, "learning_rate": 4.931254884978213e-05, "loss": 5.0998, "step": 41984 }, { "epoch": 0.01, "learning_rate": 4.930416290227161e-05, "loss": 5.0935, "step": 42496 }, { "epoch": 0.01, "learning_rate": 4.9295793333564825e-05, "loss": 5.0732, "step": 43008 }, { "epoch": 0.01, "learning_rate": 4.9287407386054305e-05, "loss": 5.0743, "step": 43520 }, { "epoch": 0.01, "learning_rate": 4.9279037817347514e-05, "loss": 5.0739, "step": 44032 }, { "epoch": 0.01, "learning_rate": 4.9270651869836994e-05, "loss": 5.0659, "step": 44544 }, { "epoch": 0.01, "learning_rate": 4.9262265922326474e-05, "loss": 5.0562, "step": 45056 }, { "epoch": 0.01, "learning_rate": 4.9253879974815954e-05, "loss": 5.053, "step": 45568 }, { "epoch": 0.02, "learning_rate": 4.924551040610916e-05, "loss": 5.0518, "step": 46080 }, { "epoch": 0.02, "learning_rate": 4.923712445859864e-05, "loss": 5.0373, "step": 46592 }, { "epoch": 0.02, "learning_rate": 4.922873851108812e-05, "loss": 5.042, "step": 47104 }, { "epoch": 0.02, "learning_rate": 4.92203525635776e-05, "loss": 5.027, "step": 47616 }, { "epoch": 0.02, "learning_rate": 4.921196661606708e-05, "loss": 5.0297, "step": 48128 }, { "epoch": 0.02, "learning_rate": 4.920359704736029e-05, "loss": 5.0237, "step": 48640 }, { "epoch": 0.02, "learning_rate": 4.919521109984978e-05, "loss": 5.016, "step": 49152 }, { "epoch": 0.02, "learning_rate": 4.918682515233926e-05, "loss": 4.9965, "step": 49664 }, { "epoch": 0.02, "learning_rate": 4.917843920482874e-05, "loss": 4.9961, "step": 50176 }, { "epoch": 0.02, "learning_rate": 4.917005325731822e-05, "loss": 4.9946, "step": 50688 }, { "epoch": 0.02, "learning_rate": 4.91616673098077e-05, "loss": 5.0079, "step": 51200 }, { "epoch": 0.02, "learning_rate": 4.915328136229718e-05, "loss": 4.9921, "step": 51712 }, { "epoch": 0.02, "learning_rate": 4.914491179359039e-05, "loss": 4.9802, "step": 52224 }, { "epoch": 0.02, "learning_rate": 4.913652584607987e-05, "loss": 4.9733, "step": 52736 }, { "epoch": 0.02, "learning_rate": 4.912813989856935e-05, "loss": 4.9772, "step": 53248 }, { "epoch": 0.02, "learning_rate": 4.911975395105883e-05, "loss": 4.952, "step": 53760 }, { "epoch": 0.02, "learning_rate": 4.9111384382352036e-05, "loss": 4.9546, "step": 54272 }, { "epoch": 0.02, "learning_rate": 4.9102998434841516e-05, "loss": 4.9518, "step": 54784 }, { "epoch": 0.02, "learning_rate": 4.9094612487330996e-05, "loss": 4.9547, "step": 55296 }, { "epoch": 0.02, "learning_rate": 4.9086226539820476e-05, "loss": 4.9435, "step": 55808 }, { "epoch": 0.02, "learning_rate": 4.907785697111369e-05, "loss": 4.9504, "step": 56320 }, { "epoch": 0.02, "learning_rate": 4.906947102360317e-05, "loss": 4.9285, "step": 56832 }, { "epoch": 0.02, "learning_rate": 4.906108507609265e-05, "loss": 4.9504, "step": 57344 }, { "epoch": 0.02, "learning_rate": 4.905269912858213e-05, "loss": 4.9293, "step": 57856 }, { "epoch": 0.02, "learning_rate": 4.904431318107161e-05, "loss": 4.9315, "step": 58368 }, { "epoch": 0.02, "learning_rate": 4.903594361236482e-05, "loss": 4.9331, "step": 58880 }, { "epoch": 0.02, "learning_rate": 4.90275576648543e-05, "loss": 4.9314, "step": 59392 }, { "epoch": 0.02, "learning_rate": 4.901918809614751e-05, "loss": 4.9181, "step": 59904 }, { "epoch": 0.02, "learning_rate": 4.901080214863699e-05, "loss": 4.9068, "step": 60416 }, { "epoch": 0.02, "learning_rate": 4.900241620112647e-05, "loss": 4.9131, "step": 60928 }, { "epoch": 0.02, "learning_rate": 4.899403025361595e-05, "loss": 4.9059, "step": 61440 }, { "epoch": 0.02, "learning_rate": 4.898564430610543e-05, "loss": 4.9077, "step": 61952 }, { "epoch": 0.02, "learning_rate": 4.897725835859491e-05, "loss": 4.9025, "step": 62464 }, { "epoch": 0.02, "learning_rate": 4.8968872411084396e-05, "loss": 4.8905, "step": 62976 }, { "epoch": 0.02, "learning_rate": 4.896048646357387e-05, "loss": 4.9021, "step": 63488 }, { "epoch": 0.02, "learning_rate": 4.895210051606335e-05, "loss": 4.8819, "step": 64000 }, { "epoch": 0.02, "learning_rate": 4.894371456855283e-05, "loss": 4.8761, "step": 64512 }, { "epoch": 0.02, "learning_rate": 4.893534499984604e-05, "loss": 4.8712, "step": 65024 }, { "epoch": 0.02, "learning_rate": 4.8926975431139254e-05, "loss": 4.8782, "step": 65536 }, { "epoch": 0.02, "learning_rate": 4.8918589483628734e-05, "loss": 4.8609, "step": 66048 }, { "epoch": 0.02, "learning_rate": 4.8910203536118214e-05, "loss": 4.8794, "step": 66560 }, { "epoch": 0.02, "learning_rate": 4.890181758860769e-05, "loss": 4.8709, "step": 67072 }, { "epoch": 0.02, "learning_rate": 4.889343164109717e-05, "loss": 4.8579, "step": 67584 }, { "epoch": 0.02, "learning_rate": 4.888504569358665e-05, "loss": 4.8485, "step": 68096 }, { "epoch": 0.02, "learning_rate": 4.8876659746076134e-05, "loss": 4.8518, "step": 68608 }, { "epoch": 0.02, "learning_rate": 4.8868273798565614e-05, "loss": 4.8498, "step": 69120 }, { "epoch": 0.02, "learning_rate": 4.8859887851055094e-05, "loss": 4.8513, "step": 69632 }, { "epoch": 0.02, "learning_rate": 4.88515182823483e-05, "loss": 4.8509, "step": 70144 }, { "epoch": 0.02, "learning_rate": 4.884313233483778e-05, "loss": 4.8472, "step": 70656 }, { "epoch": 0.02, "learning_rate": 4.883474638732726e-05, "loss": 4.8399, "step": 71168 }, { "epoch": 0.02, "learning_rate": 4.882636043981674e-05, "loss": 4.8332, "step": 71680 }, { "epoch": 0.02, "learning_rate": 4.881797449230622e-05, "loss": 4.8225, "step": 72192 }, { "epoch": 0.02, "learning_rate": 4.88095885447957e-05, "loss": 4.8209, "step": 72704 }, { "epoch": 0.02, "learning_rate": 4.880120259728518e-05, "loss": 4.8265, "step": 73216 }, { "epoch": 0.02, "learning_rate": 4.879281664977466e-05, "loss": 4.8073, "step": 73728 }, { "epoch": 0.02, "learning_rate": 4.878444708106787e-05, "loss": 4.8211, "step": 74240 }, { "epoch": 0.02, "learning_rate": 4.877607751236109e-05, "loss": 4.8199, "step": 74752 }, { "epoch": 0.02, "learning_rate": 4.876769156485057e-05, "loss": 4.8088, "step": 75264 }, { "epoch": 0.02, "learning_rate": 4.875930561734005e-05, "loss": 4.8132, "step": 75776 }, { "epoch": 0.02, "learning_rate": 4.875093604863326e-05, "loss": 4.808, "step": 76288 }, { "epoch": 0.03, "eval_loss": 4.764637470245361, "eval_runtime": 294.225, "eval_samples_per_second": 1296.936, "eval_steps_per_second": 40.53, "step": 76320 }, { "epoch": 1.0, "learning_rate": 4.874255010112274e-05, "loss": 4.7871, "step": 76800 }, { "epoch": 1.0, "learning_rate": 4.873416415361222e-05, "loss": 4.7939, "step": 77312 }, { "epoch": 1.0, "learning_rate": 4.8725794584905426e-05, "loss": 4.805, "step": 77824 }, { "epoch": 1.0, "learning_rate": 4.8717408637394906e-05, "loss": 4.7869, "step": 78336 }, { "epoch": 1.0, "learning_rate": 4.8709022689884386e-05, "loss": 4.792, "step": 78848 }, { "epoch": 1.0, "learning_rate": 4.8700636742373866e-05, "loss": 4.7811, "step": 79360 }, { "epoch": 1.0, "learning_rate": 4.8692250794863346e-05, "loss": 4.7826, "step": 79872 }, { "epoch": 1.0, "learning_rate": 4.8683881226156555e-05, "loss": 4.7698, "step": 80384 }, { "epoch": 1.0, "learning_rate": 4.867549527864604e-05, "loss": 4.7784, "step": 80896 }, { "epoch": 1.0, "learning_rate": 4.866710933113552e-05, "loss": 4.7662, "step": 81408 }, { "epoch": 1.0, "learning_rate": 4.8658723383625e-05, "loss": 4.7883, "step": 81920 }, { "epoch": 1.0, "learning_rate": 4.865033743611448e-05, "loss": 4.7789, "step": 82432 }, { "epoch": 1.0, "learning_rate": 4.864196786740769e-05, "loss": 4.7582, "step": 82944 }, { "epoch": 1.0, "learning_rate": 4.863358191989717e-05, "loss": 4.7553, "step": 83456 }, { "epoch": 1.0, "learning_rate": 4.862519597238665e-05, "loss": 4.7525, "step": 83968 }, { "epoch": 1.0, "learning_rate": 4.861681002487613e-05, "loss": 4.7542, "step": 84480 }, { "epoch": 1.0, "learning_rate": 4.860842407736561e-05, "loss": 4.7466, "step": 84992 }, { "epoch": 1.0, "learning_rate": 4.860003812985509e-05, "loss": 4.746, "step": 85504 }, { "epoch": 1.0, "learning_rate": 4.859165218234457e-05, "loss": 4.7419, "step": 86016 }, { "epoch": 1.0, "learning_rate": 4.858326623483405e-05, "loss": 4.7528, "step": 86528 }, { "epoch": 1.0, "learning_rate": 4.857489666612726e-05, "loss": 4.744, "step": 87040 }, { "epoch": 1.0, "learning_rate": 4.856651071861674e-05, "loss": 4.7476, "step": 87552 }, { "epoch": 1.0, "learning_rate": 4.8558124771106226e-05, "loss": 4.7419, "step": 88064 }, { "epoch": 1.0, "learning_rate": 4.85497388235957e-05, "loss": 4.7492, "step": 88576 }, { "epoch": 1.0, "learning_rate": 4.854135287608518e-05, "loss": 4.7278, "step": 89088 }, { "epoch": 1.0, "learning_rate": 4.8532983307378395e-05, "loss": 4.7274, "step": 89600 }, { "epoch": 1.0, "learning_rate": 4.8524597359867875e-05, "loss": 4.7223, "step": 90112 }, { "epoch": 1.0, "learning_rate": 4.851621141235735e-05, "loss": 4.7195, "step": 90624 }, { "epoch": 1.0, "learning_rate": 4.850782546484683e-05, "loss": 4.7206, "step": 91136 }, { "epoch": 1.01, "learning_rate": 4.849943951733631e-05, "loss": 4.7178, "step": 91648 }, { "epoch": 1.01, "learning_rate": 4.849105356982579e-05, "loss": 4.7174, "step": 92160 }, { "epoch": 1.01, "learning_rate": 4.848266762231527e-05, "loss": 4.7153, "step": 92672 }, { "epoch": 1.01, "learning_rate": 4.847429805360848e-05, "loss": 4.7049, "step": 93184 }, { "epoch": 1.01, "learning_rate": 4.8465912106097964e-05, "loss": 4.7181, "step": 93696 }, { "epoch": 1.01, "learning_rate": 4.8457526158587444e-05, "loss": 4.7181, "step": 94208 }, { "epoch": 1.01, "learning_rate": 4.8449140211076924e-05, "loss": 4.7058, "step": 94720 }, { "epoch": 1.01, "learning_rate": 4.844077064237013e-05, "loss": 4.6868, "step": 95232 }, { "epoch": 1.01, "learning_rate": 4.843238469485961e-05, "loss": 4.702, "step": 95744 }, { "epoch": 1.01, "learning_rate": 4.842399874734909e-05, "loss": 4.6802, "step": 96256 }, { "epoch": 1.01, "learning_rate": 4.841561279983857e-05, "loss": 4.6907, "step": 96768 }, { "epoch": 1.01, "learning_rate": 4.840725960993552e-05, "loss": 4.6907, "step": 97280 }, { "epoch": 1.01, "learning_rate": 4.8398873662425e-05, "loss": 4.6931, "step": 97792 }, { "epoch": 1.01, "learning_rate": 4.839048771491447e-05, "loss": 4.6822, "step": 98304 }, { "epoch": 1.01, "learning_rate": 4.838210176740395e-05, "loss": 4.6872, "step": 98816 }, { "epoch": 1.01, "learning_rate": 4.837371581989343e-05, "loss": 4.689, "step": 99328 }, { "epoch": 1.01, "learning_rate": 4.836532987238292e-05, "loss": 4.6836, "step": 99840 }, { "epoch": 1.01, "learning_rate": 4.83569439248724e-05, "loss": 4.6844, "step": 100352 }, { "epoch": 1.01, "learning_rate": 4.834855797736188e-05, "loss": 4.667, "step": 100864 }, { "epoch": 1.01, "learning_rate": 4.834017202985136e-05, "loss": 4.6703, "step": 101376 }, { "epoch": 1.01, "learning_rate": 4.833178608234084e-05, "loss": 4.679, "step": 101888 }, { "epoch": 1.01, "learning_rate": 4.832340013483032e-05, "loss": 4.6658, "step": 102400 }, { "epoch": 1.01, "learning_rate": 4.8315030566123526e-05, "loss": 4.6668, "step": 102912 }, { "epoch": 1.01, "learning_rate": 4.8306644618613006e-05, "loss": 4.6505, "step": 103424 }, { "epoch": 1.01, "learning_rate": 4.8298258671102486e-05, "loss": 4.6623, "step": 103936 }, { "epoch": 1.01, "learning_rate": 4.8289872723591966e-05, "loss": 4.6506, "step": 104448 }, { "epoch": 1.01, "learning_rate": 4.8281503154885175e-05, "loss": 4.6687, "step": 104960 }, { "epoch": 1.01, "learning_rate": 4.8273117207374655e-05, "loss": 4.6517, "step": 105472 }, { "epoch": 1.01, "learning_rate": 4.8264731259864135e-05, "loss": 4.6568, "step": 105984 }, { "epoch": 1.01, "learning_rate": 4.8256345312353615e-05, "loss": 4.6571, "step": 106496 }, { "epoch": 1.01, "learning_rate": 4.8247959364843095e-05, "loss": 4.6343, "step": 107008 }, { "epoch": 1.01, "learning_rate": 4.823957341733258e-05, "loss": 4.6464, "step": 107520 }, { "epoch": 1.01, "learning_rate": 4.823120384862579e-05, "loss": 4.6447, "step": 108032 }, { "epoch": 1.01, "learning_rate": 4.822281790111527e-05, "loss": 4.6299, "step": 108544 }, { "epoch": 1.01, "learning_rate": 4.821443195360475e-05, "loss": 4.6341, "step": 109056 }, { "epoch": 1.01, "learning_rate": 4.820604600609423e-05, "loss": 4.6527, "step": 109568 }, { "epoch": 1.01, "learning_rate": 4.819766005858371e-05, "loss": 4.637, "step": 110080 }, { "epoch": 1.01, "learning_rate": 4.8189274111073184e-05, "loss": 4.6242, "step": 110592 }, { "epoch": 1.01, "learning_rate": 4.8180888163562664e-05, "loss": 4.6203, "step": 111104 }, { "epoch": 1.01, "learning_rate": 4.8172502216052144e-05, "loss": 4.6232, "step": 111616 }, { "epoch": 1.01, "learning_rate": 4.816413264734535e-05, "loss": 4.6403, "step": 112128 }, { "epoch": 1.01, "learning_rate": 4.815574669983483e-05, "loss": 4.6381, "step": 112640 }, { "epoch": 1.01, "learning_rate": 4.814736075232432e-05, "loss": 4.6237, "step": 113152 }, { "epoch": 1.01, "learning_rate": 4.8138991183617535e-05, "loss": 4.6389, "step": 113664 }, { "epoch": 1.01, "learning_rate": 4.813060523610701e-05, "loss": 4.636, "step": 114176 }, { "epoch": 1.01, "learning_rate": 4.8122235667400224e-05, "loss": 4.6286, "step": 114688 }, { "epoch": 1.01, "learning_rate": 4.8113849719889704e-05, "loss": 4.6132, "step": 115200 }, { "epoch": 1.01, "learning_rate": 4.8105463772379184e-05, "loss": 4.6252, "step": 115712 }, { "epoch": 1.01, "learning_rate": 4.809707782486866e-05, "loss": 4.6139, "step": 116224 }, { "epoch": 1.01, "learning_rate": 4.808869187735814e-05, "loss": 4.6099, "step": 116736 }, { "epoch": 1.01, "learning_rate": 4.808032230865135e-05, "loss": 4.6141, "step": 117248 }, { "epoch": 1.01, "learning_rate": 4.8071936361140827e-05, "loss": 4.608, "step": 117760 }, { "epoch": 1.01, "learning_rate": 4.8063550413630307e-05, "loss": 4.6219, "step": 118272 }, { "epoch": 1.01, "learning_rate": 4.8055164466119786e-05, "loss": 4.6099, "step": 118784 }, { "epoch": 1.01, "learning_rate": 4.804677851860927e-05, "loss": 4.6007, "step": 119296 }, { "epoch": 1.01, "learning_rate": 4.803839257109875e-05, "loss": 4.6081, "step": 119808 }, { "epoch": 1.01, "learning_rate": 4.803000662358823e-05, "loss": 4.6065, "step": 120320 }, { "epoch": 1.01, "learning_rate": 4.802162067607771e-05, "loss": 4.6029, "step": 120832 }, { "epoch": 1.01, "learning_rate": 4.801325110737092e-05, "loss": 4.5997, "step": 121344 }, { "epoch": 1.01, "learning_rate": 4.80048651598604e-05, "loss": 4.5946, "step": 121856 }, { "epoch": 1.02, "learning_rate": 4.799647921234988e-05, "loss": 4.6051, "step": 122368 }, { "epoch": 1.02, "learning_rate": 4.798809326483936e-05, "loss": 4.5901, "step": 122880 }, { "epoch": 1.02, "learning_rate": 4.797970731732884e-05, "loss": 4.5975, "step": 123392 }, { "epoch": 1.02, "learning_rate": 4.797133774862205e-05, "loss": 4.5829, "step": 123904 }, { "epoch": 1.02, "learning_rate": 4.796295180111153e-05, "loss": 4.5979, "step": 124416 }, { "epoch": 1.02, "learning_rate": 4.795456585360101e-05, "loss": 4.5939, "step": 124928 }, { "epoch": 1.02, "learning_rate": 4.794617990609049e-05, "loss": 4.5873, "step": 125440 }, { "epoch": 1.02, "learning_rate": 4.793779395857997e-05, "loss": 4.5725, "step": 125952 }, { "epoch": 1.02, "learning_rate": 4.792942438987319e-05, "loss": 4.5782, "step": 126464 }, { "epoch": 1.02, "learning_rate": 4.792103844236267e-05, "loss": 4.5811, "step": 126976 }, { "epoch": 1.02, "learning_rate": 4.791265249485215e-05, "loss": 4.5918, "step": 127488 }, { "epoch": 1.02, "learning_rate": 4.790426654734163e-05, "loss": 4.5843, "step": 128000 }, { "epoch": 1.02, "learning_rate": 4.7895896978634836e-05, "loss": 4.5735, "step": 128512 }, { "epoch": 1.02, "learning_rate": 4.7887511031124316e-05, "loss": 4.5704, "step": 129024 }, { "epoch": 1.02, "learning_rate": 4.7879125083613796e-05, "loss": 4.5776, "step": 129536 }, { "epoch": 1.02, "learning_rate": 4.7870739136103276e-05, "loss": 4.552, "step": 130048 }, { "epoch": 1.02, "learning_rate": 4.7862369567396485e-05, "loss": 4.5641, "step": 130560 }, { "epoch": 1.02, "learning_rate": 4.7853983619885965e-05, "loss": 4.5633, "step": 131072 }, { "epoch": 1.02, "learning_rate": 4.7845597672375445e-05, "loss": 4.5651, "step": 131584 }, { "epoch": 1.02, "learning_rate": 4.7837211724864925e-05, "loss": 4.5569, "step": 132096 }, { "epoch": 1.02, "learning_rate": 4.782882577735441e-05, "loss": 4.5671, "step": 132608 }, { "epoch": 1.02, "learning_rate": 4.782045620864762e-05, "loss": 4.5535, "step": 133120 }, { "epoch": 1.02, "learning_rate": 4.78120702611371e-05, "loss": 4.5729, "step": 133632 }, { "epoch": 1.02, "learning_rate": 4.780368431362658e-05, "loss": 4.5576, "step": 134144 }, { "epoch": 1.02, "learning_rate": 4.779529836611606e-05, "loss": 4.5559, "step": 134656 }, { "epoch": 1.02, "learning_rate": 4.778692879740927e-05, "loss": 4.573, "step": 135168 }, { "epoch": 1.02, "learning_rate": 4.777854284989875e-05, "loss": 4.5684, "step": 135680 }, { "epoch": 1.02, "learning_rate": 4.777017328119196e-05, "loss": 4.5553, "step": 136192 }, { "epoch": 1.02, "learning_rate": 4.776178733368144e-05, "loss": 4.5464, "step": 136704 }, { "epoch": 1.02, "learning_rate": 4.775340138617092e-05, "loss": 4.561, "step": 137216 }, { "epoch": 1.02, "learning_rate": 4.77450154386604e-05, "loss": 4.5491, "step": 137728 }, { "epoch": 1.02, "learning_rate": 4.773662949114988e-05, "loss": 4.5514, "step": 138240 }, { "epoch": 1.02, "learning_rate": 4.772824354363936e-05, "loss": 4.5584, "step": 138752 }, { "epoch": 1.02, "learning_rate": 4.7719857596128845e-05, "loss": 4.542, "step": 139264 }, { "epoch": 1.02, "learning_rate": 4.771147164861832e-05, "loss": 4.5575, "step": 139776 }, { "epoch": 1.02, "learning_rate": 4.7703102079911534e-05, "loss": 4.5387, "step": 140288 }, { "epoch": 1.02, "learning_rate": 4.7694716132401014e-05, "loss": 4.5417, "step": 140800 }, { "epoch": 1.02, "learning_rate": 4.7686330184890494e-05, "loss": 4.5326, "step": 141312 }, { "epoch": 1.02, "learning_rate": 4.767794423737997e-05, "loss": 4.5423, "step": 141824 }, { "epoch": 1.02, "learning_rate": 4.766955828986945e-05, "loss": 4.5324, "step": 142336 }, { "epoch": 1.02, "learning_rate": 4.766118872116266e-05, "loss": 4.5484, "step": 142848 }, { "epoch": 1.02, "learning_rate": 4.7652802773652136e-05, "loss": 4.5451, "step": 143360 }, { "epoch": 1.02, "learning_rate": 4.7644416826141616e-05, "loss": 4.5361, "step": 143872 }, { "epoch": 1.02, "learning_rate": 4.7636030878631096e-05, "loss": 4.5202, "step": 144384 }, { "epoch": 1.02, "learning_rate": 4.762764493112058e-05, "loss": 4.5371, "step": 144896 }, { "epoch": 1.02, "learning_rate": 4.761925898361006e-05, "loss": 4.5306, "step": 145408 }, { "epoch": 1.02, "learning_rate": 4.761087303609954e-05, "loss": 4.5378, "step": 145920 }, { "epoch": 1.02, "learning_rate": 4.760251984619649e-05, "loss": 4.5364, "step": 146432 }, { "epoch": 1.02, "learning_rate": 4.759413389868596e-05, "loss": 4.5319, "step": 146944 }, { "epoch": 1.02, "learning_rate": 4.758574795117544e-05, "loss": 4.5285, "step": 147456 }, { "epoch": 1.02, "learning_rate": 4.757736200366492e-05, "loss": 4.532, "step": 147968 }, { "epoch": 1.02, "learning_rate": 4.75689760561544e-05, "loss": 4.5171, "step": 148480 }, { "epoch": 1.02, "learning_rate": 4.756059010864388e-05, "loss": 4.5177, "step": 148992 }, { "epoch": 1.02, "learning_rate": 4.755222053993709e-05, "loss": 4.5236, "step": 149504 }, { "epoch": 1.02, "learning_rate": 4.754383459242657e-05, "loss": 4.5119, "step": 150016 }, { "epoch": 1.02, "learning_rate": 4.753544864491605e-05, "loss": 4.5206, "step": 150528 }, { "epoch": 1.02, "learning_rate": 4.7527062697405536e-05, "loss": 4.5295, "step": 151040 }, { "epoch": 1.02, "learning_rate": 4.7518676749895016e-05, "loss": 4.5145, "step": 151552 }, { "epoch": 1.02, "learning_rate": 4.7510290802384496e-05, "loss": 4.516, "step": 152064 }, { "epoch": 1.02, "learning_rate": 4.7501904854873976e-05, "loss": 4.517, "step": 152576 }, { "epoch": 1.03, "eval_loss": 4.481048583984375, "eval_runtime": 322.8212, "eval_samples_per_second": 1182.051, "eval_steps_per_second": 36.94, "step": 152640 }, { "epoch": 0.0, "learning_rate": 4.7493518907363456e-05, "loss": 4.5012, "step": 153088 }, { "epoch": 0.0, "learning_rate": 4.7485132959852936e-05, "loss": 4.506, "step": 153600 }, { "epoch": 0.0, "learning_rate": 4.7476747012342416e-05, "loss": 4.5171, "step": 154112 }, { "epoch": 0.0, "learning_rate": 4.7468361064831896e-05, "loss": 4.5079, "step": 154624 }, { "epoch": 0.0, "learning_rate": 4.7459975117321376e-05, "loss": 4.5129, "step": 155136 }, { "epoch": 0.0, "learning_rate": 4.745158916981085e-05, "loss": 4.4973, "step": 155648 }, { "epoch": 0.0, "learning_rate": 4.744320322230033e-05, "loss": 4.5099, "step": 156160 }, { "epoch": 0.0, "learning_rate": 4.743481727478981e-05, "loss": 4.4924, "step": 156672 }, { "epoch": 0.0, "learning_rate": 4.742643132727929e-05, "loss": 4.5049, "step": 157184 }, { "epoch": 0.0, "learning_rate": 4.741804537976877e-05, "loss": 4.4985, "step": 157696 }, { "epoch": 0.0, "learning_rate": 4.740965943225825e-05, "loss": 4.5115, "step": 158208 }, { "epoch": 0.0, "learning_rate": 4.7401273484747736e-05, "loss": 4.5128, "step": 158720 }, { "epoch": 0.0, "learning_rate": 4.7392903916040945e-05, "loss": 4.4882, "step": 159232 }, { "epoch": 0.0, "learning_rate": 4.7384517968530425e-05, "loss": 4.493, "step": 159744 }, { "epoch": 0.0, "learning_rate": 4.7376132021019905e-05, "loss": 4.494, "step": 160256 }, { "epoch": 0.0, "learning_rate": 4.7367746073509385e-05, "loss": 4.4876, "step": 160768 }, { "epoch": 0.0, "learning_rate": 4.7359360125998865e-05, "loss": 4.4885, "step": 161280 }, { "epoch": 0.0, "learning_rate": 4.7350974178488345e-05, "loss": 4.4862, "step": 161792 }, { "epoch": 0.0, "learning_rate": 4.7342588230977825e-05, "loss": 4.4835, "step": 162304 }, { "epoch": 0.0, "learning_rate": 4.7334202283467305e-05, "loss": 4.5034, "step": 162816 }, { "epoch": 0.0, "learning_rate": 4.7325832714760514e-05, "loss": 4.486, "step": 163328 }, { "epoch": 0.0, "learning_rate": 4.7317446767249994e-05, "loss": 4.4972, "step": 163840 }, { "epoch": 0.0, "learning_rate": 4.7309060819739474e-05, "loss": 4.4917, "step": 164352 }, { "epoch": 0.0, "learning_rate": 4.7300674872228953e-05, "loss": 4.4998, "step": 164864 }, { "epoch": 0.0, "learning_rate": 4.7292288924718433e-05, "loss": 4.4743, "step": 165376 }, { "epoch": 0.0, "learning_rate": 4.728390297720791e-05, "loss": 4.4834, "step": 165888 }, { "epoch": 0.0, "learning_rate": 4.727551702969739e-05, "loss": 4.4741, "step": 166400 }, { "epoch": 0.0, "learning_rate": 4.726713108218687e-05, "loss": 4.4808, "step": 166912 }, { "epoch": 0.0, "learning_rate": 4.725876151348009e-05, "loss": 4.4721, "step": 167424 }, { "epoch": 0.01, "learning_rate": 4.725037556596957e-05, "loss": 4.4755, "step": 167936 }, { "epoch": 0.01, "learning_rate": 4.724200599726278e-05, "loss": 4.4821, "step": 168448 }, { "epoch": 0.01, "learning_rate": 4.723362004975226e-05, "loss": 4.477, "step": 168960 }, { "epoch": 0.01, "learning_rate": 4.722523410224174e-05, "loss": 4.4654, "step": 169472 }, { "epoch": 0.01, "learning_rate": 4.721684815473121e-05, "loss": 4.4829, "step": 169984 }, { "epoch": 0.01, "learning_rate": 4.720847858602443e-05, "loss": 4.4782, "step": 170496 }, { "epoch": 0.01, "learning_rate": 4.720009263851391e-05, "loss": 4.4732, "step": 171008 }, { "epoch": 0.01, "learning_rate": 4.719170669100339e-05, "loss": 4.4585, "step": 171520 }, { "epoch": 0.01, "learning_rate": 4.718332074349287e-05, "loss": 4.4704, "step": 172032 }, { "epoch": 0.01, "learning_rate": 4.717493479598235e-05, "loss": 4.4516, "step": 172544 }, { "epoch": 0.01, "learning_rate": 4.716654884847183e-05, "loss": 4.4665, "step": 173056 }, { "epoch": 0.01, "learning_rate": 4.715816290096131e-05, "loss": 4.4599, "step": 173568 }, { "epoch": 0.01, "learning_rate": 4.714977695345079e-05, "loss": 4.4678, "step": 174080 }, { "epoch": 0.01, "learning_rate": 4.714139100594027e-05, "loss": 4.4605, "step": 174592 }, { "epoch": 0.01, "learning_rate": 4.713300505842975e-05, "loss": 4.463, "step": 175104 }, { "epoch": 0.01, "learning_rate": 4.712461911091923e-05, "loss": 4.4665, "step": 175616 }, { "epoch": 0.01, "learning_rate": 4.711623316340871e-05, "loss": 4.4638, "step": 176128 }, { "epoch": 0.01, "learning_rate": 4.7107863594701916e-05, "loss": 4.4671, "step": 176640 }, { "epoch": 0.01, "learning_rate": 4.7099477647191396e-05, "loss": 4.4486, "step": 177152 }, { "epoch": 0.01, "learning_rate": 4.7091091699680876e-05, "loss": 4.4483, "step": 177664 }, { "epoch": 0.01, "learning_rate": 4.7082705752170356e-05, "loss": 4.4626, "step": 178176 }, { "epoch": 0.01, "learning_rate": 4.7074319804659836e-05, "loss": 4.4512, "step": 178688 }, { "epoch": 0.01, "learning_rate": 4.706593385714932e-05, "loss": 4.4501, "step": 179200 }, { "epoch": 0.01, "learning_rate": 4.70575479096388e-05, "loss": 4.4387, "step": 179712 }, { "epoch": 0.01, "learning_rate": 4.704917834093201e-05, "loss": 4.4512, "step": 180224 }, { "epoch": 0.01, "learning_rate": 4.704079239342149e-05, "loss": 4.4359, "step": 180736 }, { "epoch": 0.01, "learning_rate": 4.703240644591097e-05, "loss": 4.4558, "step": 181248 }, { "epoch": 0.01, "learning_rate": 4.702402049840045e-05, "loss": 4.4429, "step": 181760 }, { "epoch": 0.01, "learning_rate": 4.7015634550889924e-05, "loss": 4.4501, "step": 182272 }, { "epoch": 0.01, "learning_rate": 4.7007248603379404e-05, "loss": 4.4477, "step": 182784 }, { "epoch": 0.01, "learning_rate": 4.6998862655868884e-05, "loss": 4.4317, "step": 183296 }, { "epoch": 0.01, "learning_rate": 4.69904930871621e-05, "loss": 4.4395, "step": 183808 }, { "epoch": 0.01, "learning_rate": 4.6982107139651573e-05, "loss": 4.4408, "step": 184320 }, { "epoch": 0.01, "learning_rate": 4.697372119214106e-05, "loss": 4.4282, "step": 184832 }, { "epoch": 0.01, "learning_rate": 4.696533524463054e-05, "loss": 4.4389, "step": 185344 }, { "epoch": 0.01, "learning_rate": 4.695694929712002e-05, "loss": 4.4435, "step": 185856 }, { "epoch": 0.01, "learning_rate": 4.694857972841323e-05, "loss": 4.4384, "step": 186368 }, { "epoch": 0.01, "learning_rate": 4.694019378090271e-05, "loss": 4.4271, "step": 186880 }, { "epoch": 0.01, "learning_rate": 4.693180783339219e-05, "loss": 4.421, "step": 187392 }, { "epoch": 0.01, "learning_rate": 4.692342188588167e-05, "loss": 4.4256, "step": 187904 }, { "epoch": 0.01, "learning_rate": 4.691505231717488e-05, "loss": 4.4421, "step": 188416 }, { "epoch": 0.01, "learning_rate": 4.690666636966436e-05, "loss": 4.4457, "step": 188928 }, { "epoch": 0.01, "learning_rate": 4.689828042215384e-05, "loss": 4.4312, "step": 189440 }, { "epoch": 0.01, "learning_rate": 4.688989447464332e-05, "loss": 4.443, "step": 189952 }, { "epoch": 0.01, "learning_rate": 4.68815085271328e-05, "loss": 4.4433, "step": 190464 }, { "epoch": 0.01, "learning_rate": 4.687312257962228e-05, "loss": 4.4391, "step": 190976 }, { "epoch": 0.01, "learning_rate": 4.686473663211176e-05, "loss": 4.416, "step": 191488 }, { "epoch": 0.01, "learning_rate": 4.68563834422087e-05, "loss": 4.4371, "step": 192000 }, { "epoch": 0.01, "learning_rate": 4.684799749469818e-05, "loss": 4.429, "step": 192512 }, { "epoch": 0.01, "learning_rate": 4.683961154718766e-05, "loss": 4.418, "step": 193024 }, { "epoch": 0.01, "learning_rate": 4.683122559967714e-05, "loss": 4.4303, "step": 193536 }, { "epoch": 0.01, "learning_rate": 4.682283965216662e-05, "loss": 4.4208, "step": 194048 }, { "epoch": 0.01, "learning_rate": 4.68144537046561e-05, "loss": 4.4323, "step": 194560 }, { "epoch": 0.01, "learning_rate": 4.680606775714558e-05, "loss": 4.4274, "step": 195072 }, { "epoch": 0.01, "learning_rate": 4.679768180963506e-05, "loss": 4.4129, "step": 195584 }, { "epoch": 0.01, "learning_rate": 4.678929586212454e-05, "loss": 4.4241, "step": 196096 }, { "epoch": 0.01, "learning_rate": 4.678090991461402e-05, "loss": 4.4211, "step": 196608 }, { "epoch": 0.01, "learning_rate": 4.67725239671035e-05, "loss": 4.4229, "step": 197120 }, { "epoch": 0.01, "learning_rate": 4.676413801959298e-05, "loss": 4.418, "step": 197632 }, { "epoch": 0.01, "learning_rate": 4.675576845088619e-05, "loss": 4.4145, "step": 198144 }, { "epoch": 0.02, "learning_rate": 4.674738250337568e-05, "loss": 4.4222, "step": 198656 }, { "epoch": 0.02, "learning_rate": 4.673901293466889e-05, "loss": 4.4116, "step": 199168 }, { "epoch": 0.02, "learning_rate": 4.673062698715837e-05, "loss": 4.4181, "step": 199680 }, { "epoch": 0.02, "learning_rate": 4.672224103964785e-05, "loss": 4.4076, "step": 200192 }, { "epoch": 0.02, "learning_rate": 4.671385509213733e-05, "loss": 4.4229, "step": 200704 }, { "epoch": 0.02, "learning_rate": 4.670546914462681e-05, "loss": 4.4181, "step": 201216 }, { "epoch": 0.02, "learning_rate": 4.669708319711629e-05, "loss": 4.4098, "step": 201728 }, { "epoch": 0.02, "learning_rate": 4.668869724960576e-05, "loss": 4.4031, "step": 202240 }, { "epoch": 0.02, "learning_rate": 4.668031130209524e-05, "loss": 4.4088, "step": 202752 }, { "epoch": 0.02, "learning_rate": 4.667192535458472e-05, "loss": 4.4025, "step": 203264 }, { "epoch": 0.02, "learning_rate": 4.66635394070742e-05, "loss": 4.4225, "step": 203776 }, { "epoch": 0.02, "learning_rate": 4.665515345956368e-05, "loss": 4.4086, "step": 204288 }, { "epoch": 0.02, "learning_rate": 4.6646783890856896e-05, "loss": 4.4044, "step": 204800 }, { "epoch": 0.02, "learning_rate": 4.6638397943346376e-05, "loss": 4.3979, "step": 205312 }, { "epoch": 0.02, "learning_rate": 4.6630011995835856e-05, "loss": 4.4054, "step": 205824 }, { "epoch": 0.02, "learning_rate": 4.6621626048325336e-05, "loss": 4.3849, "step": 206336 }, { "epoch": 0.02, "learning_rate": 4.6613256479618545e-05, "loss": 4.396, "step": 206848 }, { "epoch": 0.02, "learning_rate": 4.6604870532108025e-05, "loss": 4.3961, "step": 207360 }, { "epoch": 0.02, "learning_rate": 4.6596484584597505e-05, "loss": 4.399, "step": 207872 }, { "epoch": 0.02, "learning_rate": 4.6588098637086985e-05, "loss": 4.3882, "step": 208384 }, { "epoch": 0.02, "learning_rate": 4.6579712689576465e-05, "loss": 4.4031, "step": 208896 }, { "epoch": 0.02, "learning_rate": 4.6571326742065945e-05, "loss": 4.3867, "step": 209408 }, { "epoch": 0.02, "learning_rate": 4.6562957173359154e-05, "loss": 4.4097, "step": 209920 }, { "epoch": 0.02, "learning_rate": 4.6554571225848634e-05, "loss": 4.3948, "step": 210432 }, { "epoch": 0.02, "learning_rate": 4.6546185278338114e-05, "loss": 4.3921, "step": 210944 }, { "epoch": 0.02, "learning_rate": 4.65377993308276e-05, "loss": 4.4108, "step": 211456 }, { "epoch": 0.02, "learning_rate": 4.652941338331708e-05, "loss": 4.4107, "step": 211968 }, { "epoch": 0.02, "learning_rate": 4.652104381461029e-05, "loss": 4.3957, "step": 212480 }, { "epoch": 0.02, "learning_rate": 4.651265786709977e-05, "loss": 4.3877, "step": 212992 }, { "epoch": 0.02, "learning_rate": 4.650427191958925e-05, "loss": 4.3955, "step": 213504 }, { "epoch": 0.02, "learning_rate": 4.649588597207873e-05, "loss": 4.3933, "step": 214016 }, { "epoch": 0.02, "learning_rate": 4.648750002456821e-05, "loss": 4.3889, "step": 214528 }, { "epoch": 0.02, "learning_rate": 4.647911407705769e-05, "loss": 4.4034, "step": 215040 }, { "epoch": 0.02, "learning_rate": 4.647072812954717e-05, "loss": 4.382, "step": 215552 }, { "epoch": 0.02, "learning_rate": 4.646235856084038e-05, "loss": 4.4004, "step": 216064 }, { "epoch": 0.02, "learning_rate": 4.645397261332986e-05, "loss": 4.3857, "step": 216576 }, { "epoch": 0.02, "learning_rate": 4.644558666581934e-05, "loss": 4.3882, "step": 217088 }, { "epoch": 0.02, "learning_rate": 4.643720071830882e-05, "loss": 4.3751, "step": 217600 }, { "epoch": 0.02, "learning_rate": 4.64288147707983e-05, "loss": 4.3915, "step": 218112 }, { "epoch": 0.02, "learning_rate": 4.642042882328778e-05, "loss": 4.3763, "step": 218624 }, { "epoch": 0.02, "learning_rate": 4.641204287577726e-05, "loss": 4.3968, "step": 219136 }, { "epoch": 0.02, "learning_rate": 4.6403673307070474e-05, "loss": 4.389, "step": 219648 }, { "epoch": 0.02, "learning_rate": 4.639528735955995e-05, "loss": 4.3863, "step": 220160 }, { "epoch": 0.02, "learning_rate": 4.638690141204943e-05, "loss": 4.3682, "step": 220672 }, { "epoch": 0.02, "learning_rate": 4.637851546453891e-05, "loss": 4.3883, "step": 221184 }, { "epoch": 0.02, "learning_rate": 4.637012951702839e-05, "loss": 4.385, "step": 221696 }, { "epoch": 0.02, "learning_rate": 4.636174356951787e-05, "loss": 4.3844, "step": 222208 }, { "epoch": 0.02, "learning_rate": 4.6353374000811076e-05, "loss": 4.3815, "step": 222720 }, { "epoch": 0.02, "learning_rate": 4.6344988053300556e-05, "loss": 4.3883, "step": 223232 }, { "epoch": 0.02, "learning_rate": 4.6336602105790036e-05, "loss": 4.382, "step": 223744 }, { "epoch": 0.02, "learning_rate": 4.632821615827952e-05, "loss": 4.387, "step": 224256 }, { "epoch": 0.02, "learning_rate": 4.6319830210769e-05, "loss": 4.3677, "step": 224768 }, { "epoch": 0.02, "learning_rate": 4.631144426325848e-05, "loss": 4.3726, "step": 225280 }, { "epoch": 0.02, "learning_rate": 4.630307469455169e-05, "loss": 4.377, "step": 225792 }, { "epoch": 0.02, "learning_rate": 4.62947051258449e-05, "loss": 4.3658, "step": 226304 }, { "epoch": 0.02, "learning_rate": 4.628631917833438e-05, "loss": 4.3761, "step": 226816 }, { "epoch": 0.02, "learning_rate": 4.627793323082386e-05, "loss": 4.385, "step": 227328 }, { "epoch": 0.02, "learning_rate": 4.626954728331334e-05, "loss": 4.3692, "step": 227840 }, { "epoch": 0.02, "learning_rate": 4.626116133580282e-05, "loss": 4.3698, "step": 228352 }, { "epoch": 0.02, "learning_rate": 4.62527753882923e-05, "loss": 4.3769, "step": 228864 }, { "epoch": 0.03, "eval_loss": 4.34541654586792, "eval_runtime": 300.3103, "eval_samples_per_second": 1270.656, "eval_steps_per_second": 39.709, "step": 228960 }, { "epoch": 1.0, "learning_rate": 4.624438944078178e-05, "loss": 4.3659, "step": 229376 }, { "epoch": 1.0, "learning_rate": 4.623600349327126e-05, "loss": 4.3627, "step": 229888 }, { "epoch": 1.0, "learning_rate": 4.6227633924564476e-05, "loss": 4.3757, "step": 230400 }, { "epoch": 1.0, "learning_rate": 4.6219247977053956e-05, "loss": 4.3619, "step": 230912 }, { "epoch": 1.0, "learning_rate": 4.6210862029543436e-05, "loss": 4.3752, "step": 231424 }, { "epoch": 1.0, "learning_rate": 4.6202476082032916e-05, "loss": 4.3574, "step": 231936 }, { "epoch": 1.0, "learning_rate": 4.6194090134522396e-05, "loss": 4.3706, "step": 232448 }, { "epoch": 1.0, "learning_rate": 4.6185720565815605e-05, "loss": 4.3532, "step": 232960 }, { "epoch": 1.0, "learning_rate": 4.6177334618305085e-05, "loss": 4.3681, "step": 233472 }, { "epoch": 1.0, "learning_rate": 4.6168948670794565e-05, "loss": 4.3576, "step": 233984 }, { "epoch": 1.0, "learning_rate": 4.6160562723284045e-05, "loss": 4.3751, "step": 234496 }, { "epoch": 1.0, "learning_rate": 4.6152193154577254e-05, "loss": 4.374, "step": 235008 }, { "epoch": 1.0, "learning_rate": 4.6143807207066734e-05, "loss": 4.3539, "step": 235520 }, { "epoch": 1.0, "learning_rate": 4.6135421259556214e-05, "loss": 4.3594, "step": 236032 }, { "epoch": 1.0, "learning_rate": 4.6127035312045694e-05, "loss": 4.3566, "step": 236544 }, { "epoch": 1.0, "learning_rate": 4.6118649364535174e-05, "loss": 4.358, "step": 237056 }, { "epoch": 1.0, "learning_rate": 4.6110263417024654e-05, "loss": 4.3508, "step": 237568 }, { "epoch": 1.0, "learning_rate": 4.610187746951414e-05, "loss": 4.3518, "step": 238080 }, { "epoch": 1.0, "learning_rate": 4.6093491522003614e-05, "loss": 4.3499, "step": 238592 }, { "epoch": 1.0, "learning_rate": 4.6085105574493094e-05, "loss": 4.3757, "step": 239104 }, { "epoch": 1.0, "learning_rate": 4.6076719626982574e-05, "loss": 4.3527, "step": 239616 }, { "epoch": 1.0, "learning_rate": 4.6068333679472054e-05, "loss": 4.3595, "step": 240128 }, { "epoch": 1.0, "learning_rate": 4.6059947731961534e-05, "loss": 4.3646, "step": 240640 }, { "epoch": 1.0, "learning_rate": 4.605159454205848e-05, "loss": 4.3665, "step": 241152 }, { "epoch": 1.0, "learning_rate": 4.604320859454796e-05, "loss": 4.344, "step": 241664 }, { "epoch": 1.0, "learning_rate": 4.603482264703743e-05, "loss": 4.3515, "step": 242176 }, { "epoch": 1.0, "learning_rate": 4.602643669952691e-05, "loss": 4.3452, "step": 242688 }, { "epoch": 1.0, "learning_rate": 4.601805075201639e-05, "loss": 4.3507, "step": 243200 }, { "epoch": 1.0, "learning_rate": 4.600966480450588e-05, "loss": 4.3443, "step": 243712 }, { "epoch": 1.01, "learning_rate": 4.600129523579909e-05, "loss": 4.3442, "step": 244224 }, { "epoch": 1.01, "learning_rate": 4.599290928828857e-05, "loss": 4.352, "step": 244736 }, { "epoch": 1.01, "learning_rate": 4.598452334077805e-05, "loss": 4.3499, "step": 245248 }, { "epoch": 1.01, "learning_rate": 4.5976153772071257e-05, "loss": 4.345, "step": 245760 }, { "epoch": 1.01, "learning_rate": 4.5967767824560737e-05, "loss": 4.3522, "step": 246272 }, { "epoch": 1.01, "learning_rate": 4.5959381877050217e-05, "loss": 4.3521, "step": 246784 }, { "epoch": 1.01, "learning_rate": 4.5950995929539696e-05, "loss": 4.3453, "step": 247296 }, { "epoch": 1.01, "learning_rate": 4.5942609982029176e-05, "loss": 4.3311, "step": 247808 }, { "epoch": 1.01, "learning_rate": 4.5934224034518656e-05, "loss": 4.3479, "step": 248320 }, { "epoch": 1.01, "learning_rate": 4.5925838087008136e-05, "loss": 4.3249, "step": 248832 }, { "epoch": 1.01, "learning_rate": 4.5917452139497616e-05, "loss": 4.3411, "step": 249344 }, { "epoch": 1.01, "learning_rate": 4.590908257079083e-05, "loss": 4.3352, "step": 249856 }, { "epoch": 1.01, "learning_rate": 4.590069662328031e-05, "loss": 4.3457, "step": 250368 }, { "epoch": 1.01, "learning_rate": 4.589231067576979e-05, "loss": 4.3434, "step": 250880 }, { "epoch": 1.01, "learning_rate": 4.588392472825927e-05, "loss": 4.3365, "step": 251392 }, { "epoch": 1.01, "learning_rate": 4.587553878074875e-05, "loss": 4.3433, "step": 251904 }, { "epoch": 1.01, "learning_rate": 4.586715283323823e-05, "loss": 4.3448, "step": 252416 }, { "epoch": 1.01, "learning_rate": 4.585878326453144e-05, "loss": 4.3449, "step": 252928 }, { "epoch": 1.01, "learning_rate": 4.585039731702092e-05, "loss": 4.3252, "step": 253440 }, { "epoch": 1.01, "learning_rate": 4.58420113695104e-05, "loss": 4.3275, "step": 253952 }, { "epoch": 1.01, "learning_rate": 4.583362542199988e-05, "loss": 4.3459, "step": 254464 }, { "epoch": 1.01, "learning_rate": 4.582523947448936e-05, "loss": 4.3264, "step": 254976 }, { "epoch": 1.01, "learning_rate": 4.581685352697884e-05, "loss": 4.3262, "step": 255488 }, { "epoch": 1.01, "learning_rate": 4.580846757946832e-05, "loss": 4.3229, "step": 256000 }, { "epoch": 1.01, "learning_rate": 4.580009801076153e-05, "loss": 4.3329, "step": 256512 }, { "epoch": 1.01, "learning_rate": 4.5791712063251017e-05, "loss": 4.3206, "step": 257024 }, { "epoch": 1.01, "learning_rate": 4.5783326115740497e-05, "loss": 4.3327, "step": 257536 }, { "epoch": 1.01, "learning_rate": 4.577494016822997e-05, "loss": 4.3263, "step": 258048 }, { "epoch": 1.01, "learning_rate": 4.576655422071945e-05, "loss": 4.3288, "step": 258560 }, { "epoch": 1.01, "learning_rate": 4.5758184652012666e-05, "loss": 4.3301, "step": 259072 }, { "epoch": 1.01, "learning_rate": 4.5749798704502146e-05, "loss": 4.3175, "step": 259584 }, { "epoch": 1.01, "learning_rate": 4.5741429135795355e-05, "loss": 4.3198, "step": 260096 }, { "epoch": 1.01, "learning_rate": 4.5733043188284835e-05, "loss": 4.3305, "step": 260608 }, { "epoch": 1.01, "learning_rate": 4.5724657240774315e-05, "loss": 4.3103, "step": 261120 }, { "epoch": 1.01, "learning_rate": 4.5716271293263794e-05, "loss": 4.3205, "step": 261632 }, { "epoch": 1.01, "learning_rate": 4.570788534575327e-05, "loss": 4.3273, "step": 262144 }, { "epoch": 1.01, "learning_rate": 4.5699499398242754e-05, "loss": 4.3286, "step": 262656 }, { "epoch": 1.01, "learning_rate": 4.5691113450732234e-05, "loss": 4.3111, "step": 263168 }, { "epoch": 1.01, "learning_rate": 4.5682727503221714e-05, "loss": 4.3077, "step": 263680 }, { "epoch": 1.01, "learning_rate": 4.5674357934514923e-05, "loss": 4.311, "step": 264192 }, { "epoch": 1.01, "learning_rate": 4.56659719870044e-05, "loss": 4.3271, "step": 264704 }, { "epoch": 1.01, "learning_rate": 4.565758603949388e-05, "loss": 4.3333, "step": 265216 }, { "epoch": 1.01, "learning_rate": 4.564920009198336e-05, "loss": 4.3191, "step": 265728 }, { "epoch": 1.01, "learning_rate": 4.564081414447284e-05, "loss": 4.3293, "step": 266240 }, { "epoch": 1.01, "learning_rate": 4.563242819696232e-05, "loss": 4.3314, "step": 266752 }, { "epoch": 1.01, "learning_rate": 4.562405862825553e-05, "loss": 4.3263, "step": 267264 }, { "epoch": 1.01, "learning_rate": 4.561568905954874e-05, "loss": 4.3081, "step": 267776 }, { "epoch": 1.01, "learning_rate": 4.560731949084196e-05, "loss": 4.3235, "step": 268288 }, { "epoch": 1.01, "learning_rate": 4.559893354333144e-05, "loss": 4.319, "step": 268800 }, { "epoch": 1.01, "learning_rate": 4.559054759582092e-05, "loss": 4.3094, "step": 269312 }, { "epoch": 1.01, "learning_rate": 4.55821616483104e-05, "loss": 4.317, "step": 269824 }, { "epoch": 1.01, "learning_rate": 4.557377570079988e-05, "loss": 4.3128, "step": 270336 }, { "epoch": 1.01, "learning_rate": 4.556538975328936e-05, "loss": 4.3193, "step": 270848 }, { "epoch": 1.01, "learning_rate": 4.555700380577884e-05, "loss": 4.3187, "step": 271360 }, { "epoch": 1.01, "learning_rate": 4.554861785826832e-05, "loss": 4.3071, "step": 271872 }, { "epoch": 1.01, "learning_rate": 4.55402319107578e-05, "loss": 4.3191, "step": 272384 }, { "epoch": 1.01, "learning_rate": 4.553184596324728e-05, "loss": 4.3101, "step": 272896 }, { "epoch": 1.01, "learning_rate": 4.552346001573676e-05, "loss": 4.3145, "step": 273408 }, { "epoch": 1.01, "learning_rate": 4.551507406822624e-05, "loss": 4.3114, "step": 273920 }, { "epoch": 1.01, "learning_rate": 4.5506704499519446e-05, "loss": 4.3066, "step": 274432 }, { "epoch": 1.02, "learning_rate": 4.5498318552008926e-05, "loss": 4.3163, "step": 274944 }, { "epoch": 1.02, "learning_rate": 4.5489932604498406e-05, "loss": 4.3094, "step": 275456 }, { "epoch": 1.02, "learning_rate": 4.5481546656987886e-05, "loss": 4.3058, "step": 275968 }, { "epoch": 1.02, "learning_rate": 4.547316070947737e-05, "loss": 4.3031, "step": 276480 }, { "epoch": 1.02, "learning_rate": 4.546479114077058e-05, "loss": 4.3189, "step": 276992 }, { "epoch": 1.02, "learning_rate": 4.545640519326006e-05, "loss": 4.3119, "step": 277504 }, { "epoch": 1.02, "learning_rate": 4.544801924574954e-05, "loss": 4.3034, "step": 278016 }, { "epoch": 1.02, "learning_rate": 4.543963329823902e-05, "loss": 4.2985, "step": 278528 }, { "epoch": 1.02, "learning_rate": 4.543126372953223e-05, "loss": 4.3037, "step": 279040 }, { "epoch": 1.02, "learning_rate": 4.542287778202171e-05, "loss": 4.2978, "step": 279552 }, { "epoch": 1.02, "learning_rate": 4.541449183451119e-05, "loss": 4.3201, "step": 280064 }, { "epoch": 1.02, "learning_rate": 4.540610588700067e-05, "loss": 4.3056, "step": 280576 }, { "epoch": 1.02, "learning_rate": 4.539771993949015e-05, "loss": 4.2997, "step": 281088 }, { "epoch": 1.02, "learning_rate": 4.538933399197963e-05, "loss": 4.297, "step": 281600 }, { "epoch": 1.02, "learning_rate": 4.538094804446911e-05, "loss": 4.3052, "step": 282112 }, { "epoch": 1.02, "learning_rate": 4.537256209695859e-05, "loss": 4.2777, "step": 282624 }, { "epoch": 1.02, "learning_rate": 4.5364192528251806e-05, "loss": 4.294, "step": 283136 }, { "epoch": 1.02, "learning_rate": 4.535580658074128e-05, "loss": 4.2931, "step": 283648 }, { "epoch": 1.02, "learning_rate": 4.534742063323076e-05, "loss": 4.3001, "step": 284160 }, { "epoch": 1.02, "learning_rate": 4.533903468572024e-05, "loss": 4.2868, "step": 284672 }, { "epoch": 1.02, "learning_rate": 4.533064873820972e-05, "loss": 4.3025, "step": 285184 }, { "epoch": 1.02, "learning_rate": 4.532227916950293e-05, "loss": 4.2861, "step": 285696 }, { "epoch": 1.02, "learning_rate": 4.5313909600796144e-05, "loss": 4.3035, "step": 286208 }, { "epoch": 1.02, "learning_rate": 4.5305523653285624e-05, "loss": 4.2982, "step": 286720 }, { "epoch": 1.02, "learning_rate": 4.5297137705775104e-05, "loss": 4.2904, "step": 287232 }, { "epoch": 1.02, "learning_rate": 4.528875175826458e-05, "loss": 4.3095, "step": 287744 }, { "epoch": 1.02, "learning_rate": 4.5280365810754064e-05, "loss": 4.3111, "step": 288256 }, { "epoch": 1.02, "learning_rate": 4.527199624204728e-05, "loss": 4.2979, "step": 288768 }, { "epoch": 1.02, "learning_rate": 4.526361029453675e-05, "loss": 4.2901, "step": 289280 }, { "epoch": 1.02, "learning_rate": 4.525522434702623e-05, "loss": 4.2973, "step": 289792 }, { "epoch": 1.02, "learning_rate": 4.524683839951571e-05, "loss": 4.291, "step": 290304 }, { "epoch": 1.02, "learning_rate": 4.523845245200519e-05, "loss": 4.2907, "step": 290816 }, { "epoch": 1.02, "learning_rate": 4.523006650449467e-05, "loss": 4.3076, "step": 291328 }, { "epoch": 1.02, "learning_rate": 4.522168055698415e-05, "loss": 4.2863, "step": 291840 }, { "epoch": 1.02, "learning_rate": 4.521329460947363e-05, "loss": 4.2999, "step": 292352 }, { "epoch": 1.02, "learning_rate": 4.520492504076684e-05, "loss": 4.2904, "step": 292864 }, { "epoch": 1.02, "learning_rate": 4.519653909325632e-05, "loss": 4.296, "step": 293376 }, { "epoch": 1.02, "learning_rate": 4.51881531457458e-05, "loss": 4.2731, "step": 293888 }, { "epoch": 1.02, "learning_rate": 4.517976719823528e-05, "loss": 4.2983, "step": 294400 }, { "epoch": 1.02, "learning_rate": 4.51713976295285e-05, "loss": 4.2826, "step": 294912 }, { "epoch": 1.02, "learning_rate": 4.516301168201798e-05, "loss": 4.2986, "step": 295424 }, { "epoch": 1.02, "learning_rate": 4.515462573450746e-05, "loss": 4.2914, "step": 295936 }, { "epoch": 1.02, "learning_rate": 4.514623978699694e-05, "loss": 4.2944, "step": 296448 }, { "epoch": 1.02, "learning_rate": 4.513785383948642e-05, "loss": 4.2735, "step": 296960 }, { "epoch": 1.02, "learning_rate": 4.51294678919759e-05, "loss": 4.2972, "step": 297472 }, { "epoch": 1.02, "learning_rate": 4.512108194446538e-05, "loss": 4.2877, "step": 297984 }, { "epoch": 1.02, "learning_rate": 4.511269599695486e-05, "loss": 4.2896, "step": 298496 }, { "epoch": 1.02, "learning_rate": 4.5104326428248066e-05, "loss": 4.2872, "step": 299008 }, { "epoch": 1.02, "learning_rate": 4.5095956859541275e-05, "loss": 4.2964, "step": 299520 }, { "epoch": 1.02, "learning_rate": 4.5087587290834485e-05, "loss": 4.291, "step": 300032 }, { "epoch": 1.02, "learning_rate": 4.507920134332397e-05, "loss": 4.2914, "step": 300544 }, { "epoch": 1.02, "learning_rate": 4.507081539581345e-05, "loss": 4.2756, "step": 301056 }, { "epoch": 1.02, "learning_rate": 4.506242944830293e-05, "loss": 4.2813, "step": 301568 }, { "epoch": 1.02, "learning_rate": 4.505404350079241e-05, "loss": 4.2825, "step": 302080 }, { "epoch": 1.02, "learning_rate": 4.504565755328189e-05, "loss": 4.2766, "step": 302592 }, { "epoch": 1.02, "learning_rate": 4.503727160577137e-05, "loss": 4.2838, "step": 303104 }, { "epoch": 1.02, "learning_rate": 4.502888565826085e-05, "loss": 4.2896, "step": 303616 }, { "epoch": 1.02, "learning_rate": 4.502049971075033e-05, "loss": 4.2803, "step": 304128 }, { "epoch": 1.02, "learning_rate": 4.501211376323981e-05, "loss": 4.2777, "step": 304640 }, { "epoch": 1.02, "learning_rate": 4.500372781572929e-05, "loss": 4.2883, "step": 305152 }, { "epoch": 1.03, "eval_loss": 4.261952877044678, "eval_runtime": 286.2862, "eval_samples_per_second": 1332.9, "eval_steps_per_second": 41.654, "step": 305280 }, { "epoch": 0.0, "learning_rate": 4.4995341868218764e-05, "loss": 4.2686, "step": 305664 }, { "epoch": 0.0, "learning_rate": 4.4986955920708244e-05, "loss": 4.2732, "step": 306176 }, { "epoch": 0.0, "learning_rate": 4.4978569973197724e-05, "loss": 4.2835, "step": 306688 }, { "epoch": 0.0, "learning_rate": 4.4970184025687204e-05, "loss": 4.2749, "step": 307200 }, { "epoch": 0.0, "learning_rate": 4.4961798078176684e-05, "loss": 4.2856, "step": 307712 }, { "epoch": 0.0, "learning_rate": 4.4953412130666164e-05, "loss": 4.2687, "step": 308224 }, { "epoch": 0.0, "learning_rate": 4.494502618315565e-05, "loss": 4.2778, "step": 308736 }, { "epoch": 0.0, "learning_rate": 4.493664023564513e-05, "loss": 4.2646, "step": 309248 }, { "epoch": 0.0, "learning_rate": 4.492825428813461e-05, "loss": 4.2821, "step": 309760 }, { "epoch": 0.0, "learning_rate": 4.491986834062409e-05, "loss": 4.271, "step": 310272 }, { "epoch": 0.0, "learning_rate": 4.491148239311357e-05, "loss": 4.2818, "step": 310784 }, { "epoch": 0.0, "learning_rate": 4.490309644560305e-05, "loss": 4.2874, "step": 311296 }, { "epoch": 0.0, "learning_rate": 4.489472687689626e-05, "loss": 4.2626, "step": 311808 }, { "epoch": 0.0, "learning_rate": 4.488634092938574e-05, "loss": 4.2746, "step": 312320 }, { "epoch": 0.0, "learning_rate": 4.487795498187522e-05, "loss": 4.2692, "step": 312832 }, { "epoch": 0.0, "learning_rate": 4.48695690343647e-05, "loss": 4.2698, "step": 313344 }, { "epoch": 0.0, "learning_rate": 4.486118308685418e-05, "loss": 4.2601, "step": 313856 }, { "epoch": 0.0, "learning_rate": 4.485279713934365e-05, "loss": 4.2684, "step": 314368 }, { "epoch": 0.0, "learning_rate": 4.484441119183313e-05, "loss": 4.2641, "step": 314880 }, { "epoch": 0.0, "learning_rate": 4.483602524432262e-05, "loss": 4.285, "step": 315392 }, { "epoch": 0.0, "learning_rate": 4.48276392968121e-05, "loss": 4.2653, "step": 315904 }, { "epoch": 0.0, "learning_rate": 4.481926972810531e-05, "loss": 4.2752, "step": 316416 }, { "epoch": 0.0, "learning_rate": 4.4810900159398524e-05, "loss": 4.2792, "step": 316928 }, { "epoch": 0.0, "learning_rate": 4.4802514211888004e-05, "loss": 4.2808, "step": 317440 }, { "epoch": 0.0, "learning_rate": 4.479412826437748e-05, "loss": 4.2576, "step": 317952 }, { "epoch": 0.0, "learning_rate": 4.478574231686696e-05, "loss": 4.2704, "step": 318464 }, { "epoch": 0.0, "learning_rate": 4.477735636935644e-05, "loss": 4.2582, "step": 318976 }, { "epoch": 0.0, "learning_rate": 4.476897042184592e-05, "loss": 4.2667, "step": 319488 }, { "epoch": 0.0, "learning_rate": 4.4760600853139126e-05, "loss": 4.2562, "step": 320000 }, { "epoch": 0.0, "learning_rate": 4.4752214905628606e-05, "loss": 4.2647, "step": 320512 }, { "epoch": 0.01, "learning_rate": 4.4743828958118086e-05, "loss": 4.2662, "step": 321024 }, { "epoch": 0.01, "learning_rate": 4.473544301060757e-05, "loss": 4.2676, "step": 321536 }, { "epoch": 0.01, "learning_rate": 4.472705706309705e-05, "loss": 4.26, "step": 322048 }, { "epoch": 0.01, "learning_rate": 4.471867111558653e-05, "loss": 4.271, "step": 322560 }, { "epoch": 0.01, "learning_rate": 4.471028516807601e-05, "loss": 4.2636, "step": 323072 }, { "epoch": 0.01, "learning_rate": 4.470189922056549e-05, "loss": 4.2657, "step": 323584 }, { "epoch": 0.01, "learning_rate": 4.469351327305497e-05, "loss": 4.2491, "step": 324096 }, { "epoch": 0.01, "learning_rate": 4.468512732554445e-05, "loss": 4.2616, "step": 324608 }, { "epoch": 0.01, "learning_rate": 4.467674137803393e-05, "loss": 4.248, "step": 325120 }, { "epoch": 0.01, "learning_rate": 4.466835543052341e-05, "loss": 4.2554, "step": 325632 }, { "epoch": 0.01, "learning_rate": 4.465998586181662e-05, "loss": 4.2529, "step": 326144 }, { "epoch": 0.01, "learning_rate": 4.465161629310983e-05, "loss": 4.2645, "step": 326656 }, { "epoch": 0.01, "learning_rate": 4.464323034559931e-05, "loss": 4.2606, "step": 327168 }, { "epoch": 0.01, "learning_rate": 4.463484439808879e-05, "loss": 4.2599, "step": 327680 }, { "epoch": 0.01, "learning_rate": 4.462645845057827e-05, "loss": 4.2615, "step": 328192 }, { "epoch": 0.01, "learning_rate": 4.461807250306775e-05, "loss": 4.2625, "step": 328704 }, { "epoch": 0.01, "learning_rate": 4.460968655555724e-05, "loss": 4.2603, "step": 329216 }, { "epoch": 0.01, "learning_rate": 4.460130060804672e-05, "loss": 4.2501, "step": 329728 }, { "epoch": 0.01, "learning_rate": 4.4592931039339926e-05, "loss": 4.242, "step": 330240 }, { "epoch": 0.01, "learning_rate": 4.4584545091829406e-05, "loss": 4.2638, "step": 330752 }, { "epoch": 0.01, "learning_rate": 4.4576159144318886e-05, "loss": 4.2506, "step": 331264 }, { "epoch": 0.01, "learning_rate": 4.4567773196808366e-05, "loss": 4.2445, "step": 331776 }, { "epoch": 0.01, "learning_rate": 4.455938724929784e-05, "loss": 4.247, "step": 332288 }, { "epoch": 0.01, "learning_rate": 4.4551017680591055e-05, "loss": 4.2543, "step": 332800 }, { "epoch": 0.01, "learning_rate": 4.4542631733080535e-05, "loss": 4.2415, "step": 333312 }, { "epoch": 0.01, "learning_rate": 4.453424578557001e-05, "loss": 4.2488, "step": 333824 }, { "epoch": 0.01, "learning_rate": 4.452585983805949e-05, "loss": 4.2477, "step": 334336 }, { "epoch": 0.01, "learning_rate": 4.4517473890548975e-05, "loss": 4.2456, "step": 334848 }, { "epoch": 0.01, "learning_rate": 4.4509087943038455e-05, "loss": 4.2593, "step": 335360 }, { "epoch": 0.01, "learning_rate": 4.4500718374331664e-05, "loss": 4.2377, "step": 335872 }, { "epoch": 0.01, "learning_rate": 4.4492332426821144e-05, "loss": 4.2414, "step": 336384 }, { "epoch": 0.01, "learning_rate": 4.4483946479310624e-05, "loss": 4.2526, "step": 336896 }, { "epoch": 0.01, "learning_rate": 4.4475560531800104e-05, "loss": 4.2365, "step": 337408 }, { "epoch": 0.01, "learning_rate": 4.4467174584289584e-05, "loss": 4.2439, "step": 337920 }, { "epoch": 0.01, "learning_rate": 4.4458788636779064e-05, "loss": 4.248, "step": 338432 }, { "epoch": 0.01, "learning_rate": 4.445041906807227e-05, "loss": 4.2522, "step": 338944 }, { "epoch": 0.01, "learning_rate": 4.444203312056175e-05, "loss": 4.2361, "step": 339456 }, { "epoch": 0.01, "learning_rate": 4.443364717305123e-05, "loss": 4.2314, "step": 339968 }, { "epoch": 0.01, "learning_rate": 4.442526122554071e-05, "loss": 4.2293, "step": 340480 }, { "epoch": 0.01, "learning_rate": 4.441687527803019e-05, "loss": 4.2469, "step": 340992 }, { "epoch": 0.01, "learning_rate": 4.440848933051967e-05, "loss": 4.2599, "step": 341504 }, { "epoch": 0.01, "learning_rate": 4.440010338300916e-05, "loss": 4.2422, "step": 342016 }, { "epoch": 0.01, "learning_rate": 4.439171743549864e-05, "loss": 4.2534, "step": 342528 }, { "epoch": 0.01, "learning_rate": 4.438333148798812e-05, "loss": 4.2527, "step": 343040 }, { "epoch": 0.01, "learning_rate": 4.437496191928133e-05, "loss": 4.2565, "step": 343552 }, { "epoch": 0.01, "learning_rate": 4.436660872937827e-05, "loss": 4.2327, "step": 344064 }, { "epoch": 0.01, "learning_rate": 4.4358222781867747e-05, "loss": 4.2479, "step": 344576 }, { "epoch": 0.01, "learning_rate": 4.4349836834357227e-05, "loss": 4.243, "step": 345088 }, { "epoch": 0.01, "learning_rate": 4.4341450886846707e-05, "loss": 4.2313, "step": 345600 }, { "epoch": 0.01, "learning_rate": 4.4333064939336186e-05, "loss": 4.2466, "step": 346112 }, { "epoch": 0.01, "learning_rate": 4.4324678991825666e-05, "loss": 4.2387, "step": 346624 }, { "epoch": 0.01, "learning_rate": 4.4316293044315146e-05, "loss": 4.2399, "step": 347136 }, { "epoch": 0.01, "learning_rate": 4.4307907096804626e-05, "loss": 4.2443, "step": 347648 }, { "epoch": 0.01, "learning_rate": 4.429952114929411e-05, "loss": 4.2363, "step": 348160 }, { "epoch": 0.01, "learning_rate": 4.429115158058732e-05, "loss": 4.2444, "step": 348672 }, { "epoch": 0.01, "learning_rate": 4.42827656330768e-05, "loss": 4.2351, "step": 349184 }, { "epoch": 0.01, "learning_rate": 4.427437968556628e-05, "loss": 4.2404, "step": 349696 }, { "epoch": 0.01, "learning_rate": 4.426599373805576e-05, "loss": 4.2323, "step": 350208 }, { "epoch": 0.01, "learning_rate": 4.425762416934897e-05, "loss": 4.236, "step": 350720 }, { "epoch": 0.02, "learning_rate": 4.424923822183845e-05, "loss": 4.2385, "step": 351232 }, { "epoch": 0.02, "learning_rate": 4.424085227432793e-05, "loss": 4.239, "step": 351744 }, { "epoch": 0.02, "learning_rate": 4.423246632681741e-05, "loss": 4.2317, "step": 352256 }, { "epoch": 0.02, "learning_rate": 4.422408037930689e-05, "loss": 4.23, "step": 352768 }, { "epoch": 0.02, "learning_rate": 4.421569443179637e-05, "loss": 4.2463, "step": 353280 }, { "epoch": 0.02, "learning_rate": 4.420732486308958e-05, "loss": 4.2397, "step": 353792 }, { "epoch": 0.02, "learning_rate": 4.419893891557907e-05, "loss": 4.2337, "step": 354304 }, { "epoch": 0.02, "learning_rate": 4.419055296806855e-05, "loss": 4.2247, "step": 354816 }, { "epoch": 0.02, "learning_rate": 4.418216702055803e-05, "loss": 4.2289, "step": 355328 }, { "epoch": 0.02, "learning_rate": 4.41737810730475e-05, "loss": 4.2288, "step": 355840 }, { "epoch": 0.02, "learning_rate": 4.416539512553698e-05, "loss": 4.244, "step": 356352 }, { "epoch": 0.02, "learning_rate": 4.415700917802646e-05, "loss": 4.2418, "step": 356864 }, { "epoch": 0.02, "learning_rate": 4.414862323051594e-05, "loss": 4.2286, "step": 357376 }, { "epoch": 0.02, "learning_rate": 4.414025366180915e-05, "loss": 4.2251, "step": 357888 }, { "epoch": 0.02, "learning_rate": 4.4131884093102365e-05, "loss": 4.236, "step": 358400 }, { "epoch": 0.02, "learning_rate": 4.4123498145591845e-05, "loss": 4.2033, "step": 358912 }, { "epoch": 0.02, "learning_rate": 4.411511219808132e-05, "loss": 4.2289, "step": 359424 }, { "epoch": 0.02, "learning_rate": 4.4106726250570805e-05, "loss": 4.2176, "step": 359936 }, { "epoch": 0.02, "learning_rate": 4.4098340303060284e-05, "loss": 4.2294, "step": 360448 }, { "epoch": 0.02, "learning_rate": 4.4089954355549764e-05, "loss": 4.2175, "step": 360960 }, { "epoch": 0.02, "learning_rate": 4.4081584786842974e-05, "loss": 4.2308, "step": 361472 }, { "epoch": 0.02, "learning_rate": 4.4073198839332453e-05, "loss": 4.2231, "step": 361984 }, { "epoch": 0.02, "learning_rate": 4.406482927062567e-05, "loss": 4.2267, "step": 362496 }, { "epoch": 0.02, "learning_rate": 4.405645970191888e-05, "loss": 4.2321, "step": 363008 }, { "epoch": 0.02, "learning_rate": 4.404807375440836e-05, "loss": 4.2185, "step": 363520 }, { "epoch": 0.02, "learning_rate": 4.403968780689784e-05, "loss": 4.2401, "step": 364032 }, { "epoch": 0.02, "learning_rate": 4.403130185938732e-05, "loss": 4.2443, "step": 364544 }, { "epoch": 0.02, "learning_rate": 4.402291591187679e-05, "loss": 4.2295, "step": 365056 }, { "epoch": 0.02, "learning_rate": 4.401452996436627e-05, "loss": 4.219, "step": 365568 }, { "epoch": 0.02, "learning_rate": 4.400614401685576e-05, "loss": 4.229, "step": 366080 }, { "epoch": 0.02, "learning_rate": 4.399775806934524e-05, "loss": 4.2246, "step": 366592 }, { "epoch": 0.02, "learning_rate": 4.398937212183472e-05, "loss": 4.2174, "step": 367104 }, { "epoch": 0.02, "learning_rate": 4.39809861743242e-05, "loss": 4.2403, "step": 367616 }, { "epoch": 0.02, "learning_rate": 4.397260022681368e-05, "loss": 4.2178, "step": 368128 }, { "epoch": 0.02, "learning_rate": 4.396421427930316e-05, "loss": 4.2289, "step": 368640 }, { "epoch": 0.02, "learning_rate": 4.395584471059637e-05, "loss": 4.2251, "step": 369152 }, { "epoch": 0.02, "learning_rate": 4.394745876308585e-05, "loss": 4.2268, "step": 369664 }, { "epoch": 0.02, "learning_rate": 4.393907281557533e-05, "loss": 4.2132, "step": 370176 }, { "epoch": 0.02, "learning_rate": 4.393068686806481e-05, "loss": 4.2225, "step": 370688 }, { "epoch": 0.02, "learning_rate": 4.392230092055429e-05, "loss": 4.2185, "step": 371200 }, { "epoch": 0.02, "learning_rate": 4.3913931351847496e-05, "loss": 4.2333, "step": 371712 }, { "epoch": 0.02, "learning_rate": 4.3905561783140705e-05, "loss": 4.2229, "step": 372224 }, { "epoch": 0.02, "learning_rate": 4.389717583563019e-05, "loss": 4.2245, "step": 372736 }, { "epoch": 0.02, "learning_rate": 4.388878988811967e-05, "loss": 4.2083, "step": 373248 }, { "epoch": 0.02, "learning_rate": 4.388040394060915e-05, "loss": 4.23, "step": 373760 }, { "epoch": 0.02, "learning_rate": 4.387201799309863e-05, "loss": 4.2212, "step": 374272 }, { "epoch": 0.02, "learning_rate": 4.386363204558811e-05, "loss": 4.2261, "step": 374784 }, { "epoch": 0.02, "learning_rate": 4.385524609807759e-05, "loss": 4.219, "step": 375296 }, { "epoch": 0.02, "learning_rate": 4.384686015056707e-05, "loss": 4.2289, "step": 375808 }, { "epoch": 0.02, "learning_rate": 4.383847420305655e-05, "loss": 4.2222, "step": 376320 }, { "epoch": 0.02, "learning_rate": 4.383008825554603e-05, "loss": 4.2291, "step": 376832 }, { "epoch": 0.02, "learning_rate": 4.382171868683924e-05, "loss": 4.2081, "step": 377344 }, { "epoch": 0.02, "learning_rate": 4.381333273932872e-05, "loss": 4.2189, "step": 377856 }, { "epoch": 0.02, "learning_rate": 4.38049467918182e-05, "loss": 4.2153, "step": 378368 }, { "epoch": 0.02, "learning_rate": 4.379656084430768e-05, "loss": 4.2108, "step": 378880 }, { "epoch": 0.02, "learning_rate": 4.378817489679716e-05, "loss": 4.2211, "step": 379392 }, { "epoch": 0.02, "learning_rate": 4.377978894928664e-05, "loss": 4.2217, "step": 379904 }, { "epoch": 0.02, "learning_rate": 4.377140300177612e-05, "loss": 4.2199, "step": 380416 }, { "epoch": 0.02, "learning_rate": 4.3763033433069336e-05, "loss": 4.2064, "step": 380928 }, { "epoch": 0.02, "learning_rate": 4.375464748555881e-05, "loss": 4.2251, "step": 381440 }, { "epoch": 0.03, "eval_loss": 4.205812454223633, "eval_runtime": 302.9187, "eval_samples_per_second": 1259.714, "eval_steps_per_second": 39.367, "step": 381600 }, { "epoch": 1.0, "learning_rate": 4.374626153804829e-05, "loss": 4.2122, "step": 381952 }, { "epoch": 1.0, "learning_rate": 4.373787559053777e-05, "loss": 4.2059, "step": 382464 }, { "epoch": 1.0, "learning_rate": 4.372948964302725e-05, "loss": 4.2211, "step": 382976 }, { "epoch": 1.0, "learning_rate": 4.372112007432046e-05, "loss": 4.2136, "step": 383488 }, { "epoch": 1.0, "learning_rate": 4.371273412680994e-05, "loss": 4.2155, "step": 384000 }, { "epoch": 1.0, "learning_rate": 4.370434817929942e-05, "loss": 4.2092, "step": 384512 }, { "epoch": 1.0, "learning_rate": 4.369597861059263e-05, "loss": 4.2104, "step": 385024 }, { "epoch": 1.0, "learning_rate": 4.3687592663082114e-05, "loss": 4.204, "step": 385536 }, { "epoch": 1.0, "learning_rate": 4.3679206715571594e-05, "loss": 4.2145, "step": 386048 }, { "epoch": 1.0, "learning_rate": 4.3670820768061074e-05, "loss": 4.2107, "step": 386560 }, { "epoch": 1.0, "learning_rate": 4.3662434820550554e-05, "loss": 4.2158, "step": 387072 }, { "epoch": 1.0, "learning_rate": 4.365406525184376e-05, "loss": 4.2216, "step": 387584 }, { "epoch": 1.0, "learning_rate": 4.364567930433324e-05, "loss": 4.2025, "step": 388096 }, { "epoch": 1.0, "learning_rate": 4.363729335682272e-05, "loss": 4.2133, "step": 388608 }, { "epoch": 1.0, "learning_rate": 4.36289074093122e-05, "loss": 4.2096, "step": 389120 }, { "epoch": 1.0, "learning_rate": 4.362052146180168e-05, "loss": 4.2042, "step": 389632 }, { "epoch": 1.0, "learning_rate": 4.361213551429116e-05, "loss": 4.1992, "step": 390144 }, { "epoch": 1.0, "learning_rate": 4.360374956678064e-05, "loss": 4.2064, "step": 390656 }, { "epoch": 1.0, "learning_rate": 4.359536361927012e-05, "loss": 4.2002, "step": 391168 }, { "epoch": 1.0, "learning_rate": 4.35869776717596e-05, "loss": 4.2205, "step": 391680 }, { "epoch": 1.0, "learning_rate": 4.357859172424908e-05, "loss": 4.2114, "step": 392192 }, { "epoch": 1.0, "learning_rate": 4.357020577673856e-05, "loss": 4.211, "step": 392704 }, { "epoch": 1.0, "learning_rate": 4.356181982922804e-05, "loss": 4.2183, "step": 393216 }, { "epoch": 1.0, "learning_rate": 4.355345026052126e-05, "loss": 4.2189, "step": 393728 }, { "epoch": 1.0, "learning_rate": 4.354506431301074e-05, "loss": 4.1947, "step": 394240 }, { "epoch": 1.0, "learning_rate": 4.353669474430395e-05, "loss": 4.2091, "step": 394752 }, { "epoch": 1.0, "learning_rate": 4.352830879679343e-05, "loss": 4.2012, "step": 395264 }, { "epoch": 1.0, "learning_rate": 4.351992284928291e-05, "loss": 4.2046, "step": 395776 }, { "epoch": 1.0, "learning_rate": 4.351153690177239e-05, "loss": 4.1977, "step": 396288 }, { "epoch": 1.0, "learning_rate": 4.350315095426187e-05, "loss": 4.1998, "step": 396800 }, { "epoch": 1.01, "learning_rate": 4.349476500675134e-05, "loss": 4.2086, "step": 397312 }, { "epoch": 1.01, "learning_rate": 4.348637905924082e-05, "loss": 4.2039, "step": 397824 }, { "epoch": 1.01, "learning_rate": 4.3478009490534036e-05, "loss": 4.2021, "step": 398336 }, { "epoch": 1.01, "learning_rate": 4.3469623543023516e-05, "loss": 4.2073, "step": 398848 }, { "epoch": 1.01, "learning_rate": 4.346125397431673e-05, "loss": 4.2053, "step": 399360 }, { "epoch": 1.01, "learning_rate": 4.345286802680621e-05, "loss": 4.2053, "step": 399872 }, { "epoch": 1.01, "learning_rate": 4.344448207929569e-05, "loss": 4.1936, "step": 400384 }, { "epoch": 1.01, "learning_rate": 4.3436096131785165e-05, "loss": 4.1942, "step": 400896 }, { "epoch": 1.01, "learning_rate": 4.3427710184274645e-05, "loss": 4.1933, "step": 401408 }, { "epoch": 1.01, "learning_rate": 4.341934061556786e-05, "loss": 4.1948, "step": 401920 }, { "epoch": 1.01, "learning_rate": 4.341095466805734e-05, "loss": 4.193, "step": 402432 }, { "epoch": 1.01, "learning_rate": 4.3402568720546814e-05, "loss": 4.2033, "step": 402944 }, { "epoch": 1.01, "learning_rate": 4.3394182773036294e-05, "loss": 4.2023, "step": 403456 }, { "epoch": 1.01, "learning_rate": 4.3385796825525774e-05, "loss": 4.2, "step": 403968 }, { "epoch": 1.01, "learning_rate": 4.3377410878015254e-05, "loss": 4.2077, "step": 404480 }, { "epoch": 1.01, "learning_rate": 4.3369024930504734e-05, "loss": 4.1992, "step": 404992 }, { "epoch": 1.01, "learning_rate": 4.3360638982994214e-05, "loss": 4.2038, "step": 405504 }, { "epoch": 1.01, "learning_rate": 4.33522530354837e-05, "loss": 4.1914, "step": 406016 }, { "epoch": 1.01, "learning_rate": 4.334386708797318e-05, "loss": 4.1806, "step": 406528 }, { "epoch": 1.01, "learning_rate": 4.333548114046266e-05, "loss": 4.2073, "step": 407040 }, { "epoch": 1.01, "learning_rate": 4.332709519295214e-05, "loss": 4.1906, "step": 407552 }, { "epoch": 1.01, "learning_rate": 4.331872562424535e-05, "loss": 4.1922, "step": 408064 }, { "epoch": 1.01, "learning_rate": 4.331033967673483e-05, "loss": 4.1877, "step": 408576 }, { "epoch": 1.01, "learning_rate": 4.330195372922431e-05, "loss": 4.1926, "step": 409088 }, { "epoch": 1.01, "learning_rate": 4.329358416051752e-05, "loss": 4.1844, "step": 409600 }, { "epoch": 1.01, "learning_rate": 4.3285198213007e-05, "loss": 4.1893, "step": 410112 }, { "epoch": 1.01, "learning_rate": 4.327681226549648e-05, "loss": 4.1905, "step": 410624 }, { "epoch": 1.01, "learning_rate": 4.326842631798596e-05, "loss": 4.1866, "step": 411136 }, { "epoch": 1.01, "learning_rate": 4.326004037047544e-05, "loss": 4.2005, "step": 411648 }, { "epoch": 1.01, "learning_rate": 4.3251670801768654e-05, "loss": 4.1812, "step": 412160 }, { "epoch": 1.01, "learning_rate": 4.3243284854258134e-05, "loss": 4.1843, "step": 412672 }, { "epoch": 1.01, "learning_rate": 4.3234898906747614e-05, "loss": 4.198, "step": 413184 }, { "epoch": 1.01, "learning_rate": 4.3226512959237094e-05, "loss": 4.1797, "step": 413696 }, { "epoch": 1.01, "learning_rate": 4.32181433905303e-05, "loss": 4.1853, "step": 414208 }, { "epoch": 1.01, "learning_rate": 4.320975744301978e-05, "loss": 4.1864, "step": 414720 }, { "epoch": 1.01, "learning_rate": 4.320138787431299e-05, "loss": 4.1966, "step": 415232 }, { "epoch": 1.01, "learning_rate": 4.319300192680247e-05, "loss": 4.179, "step": 415744 }, { "epoch": 1.01, "learning_rate": 4.318461597929195e-05, "loss": 4.1783, "step": 416256 }, { "epoch": 1.01, "learning_rate": 4.317623003178143e-05, "loss": 4.1683, "step": 416768 }, { "epoch": 1.01, "learning_rate": 4.316784408427091e-05, "loss": 4.1927, "step": 417280 }, { "epoch": 1.01, "learning_rate": 4.315945813676039e-05, "loss": 4.2014, "step": 417792 }, { "epoch": 1.01, "learning_rate": 4.315107218924987e-05, "loss": 4.188, "step": 418304 }, { "epoch": 1.01, "learning_rate": 4.314268624173935e-05, "loss": 4.1924, "step": 418816 }, { "epoch": 1.01, "learning_rate": 4.313430029422883e-05, "loss": 4.1967, "step": 419328 }, { "epoch": 1.01, "learning_rate": 4.312591434671831e-05, "loss": 4.2018, "step": 419840 }, { "epoch": 1.01, "learning_rate": 4.311756115681526e-05, "loss": 4.1771, "step": 420352 }, { "epoch": 1.01, "learning_rate": 4.310917520930474e-05, "loss": 4.1915, "step": 420864 }, { "epoch": 1.01, "learning_rate": 4.310078926179422e-05, "loss": 4.1881, "step": 421376 }, { "epoch": 1.01, "learning_rate": 4.30924033142837e-05, "loss": 4.1731, "step": 421888 }, { "epoch": 1.01, "learning_rate": 4.308401736677318e-05, "loss": 4.1901, "step": 422400 }, { "epoch": 1.01, "learning_rate": 4.307563141926265e-05, "loss": 4.1863, "step": 422912 }, { "epoch": 1.01, "learning_rate": 4.306724547175213e-05, "loss": 4.1857, "step": 423424 }, { "epoch": 1.01, "learning_rate": 4.305885952424161e-05, "loss": 4.1904, "step": 423936 }, { "epoch": 1.01, "learning_rate": 4.3050489955534826e-05, "loss": 4.1829, "step": 424448 }, { "epoch": 1.01, "learning_rate": 4.3042104008024306e-05, "loss": 4.1803, "step": 424960 }, { "epoch": 1.01, "learning_rate": 4.3033718060513786e-05, "loss": 4.1841, "step": 425472 }, { "epoch": 1.01, "learning_rate": 4.3025332113003266e-05, "loss": 4.1872, "step": 425984 }, { "epoch": 1.01, "learning_rate": 4.3016946165492746e-05, "loss": 4.1749, "step": 426496 }, { "epoch": 1.01, "learning_rate": 4.3008576596785955e-05, "loss": 4.1807, "step": 427008 }, { "epoch": 1.02, "learning_rate": 4.3000190649275435e-05, "loss": 4.1866, "step": 427520 }, { "epoch": 1.02, "learning_rate": 4.2991804701764915e-05, "loss": 4.1839, "step": 428032 }, { "epoch": 1.02, "learning_rate": 4.2983418754254395e-05, "loss": 4.1778, "step": 428544 }, { "epoch": 1.02, "learning_rate": 4.2975032806743874e-05, "loss": 4.1769, "step": 429056 }, { "epoch": 1.02, "learning_rate": 4.2966646859233354e-05, "loss": 4.1939, "step": 429568 }, { "epoch": 1.02, "learning_rate": 4.2958260911722834e-05, "loss": 4.1875, "step": 430080 }, { "epoch": 1.02, "learning_rate": 4.2949874964212314e-05, "loss": 4.1835, "step": 430592 }, { "epoch": 1.02, "learning_rate": 4.294150539550553e-05, "loss": 4.1683, "step": 431104 }, { "epoch": 1.02, "learning_rate": 4.293311944799501e-05, "loss": 4.1767, "step": 431616 }, { "epoch": 1.02, "learning_rate": 4.292473350048449e-05, "loss": 4.1775, "step": 432128 }, { "epoch": 1.02, "learning_rate": 4.291634755297397e-05, "loss": 4.1857, "step": 432640 }, { "epoch": 1.02, "learning_rate": 4.290796160546345e-05, "loss": 4.1893, "step": 433152 }, { "epoch": 1.02, "learning_rate": 4.289959203675666e-05, "loss": 4.1743, "step": 433664 }, { "epoch": 1.02, "learning_rate": 4.289122246804987e-05, "loss": 4.1698, "step": 434176 }, { "epoch": 1.02, "learning_rate": 4.288283652053935e-05, "loss": 4.1812, "step": 434688 }, { "epoch": 1.02, "learning_rate": 4.287445057302883e-05, "loss": 4.1528, "step": 435200 }, { "epoch": 1.02, "learning_rate": 4.286606462551831e-05, "loss": 4.1753, "step": 435712 }, { "epoch": 1.02, "learning_rate": 4.285767867800779e-05, "loss": 4.1604, "step": 436224 }, { "epoch": 1.02, "learning_rate": 4.284929273049727e-05, "loss": 4.1801, "step": 436736 }, { "epoch": 1.02, "learning_rate": 4.284090678298675e-05, "loss": 4.1664, "step": 437248 }, { "epoch": 1.02, "learning_rate": 4.2832537214279964e-05, "loss": 4.1781, "step": 437760 }, { "epoch": 1.02, "learning_rate": 4.2824151266769444e-05, "loss": 4.1703, "step": 438272 }, { "epoch": 1.02, "learning_rate": 4.2815765319258924e-05, "loss": 4.1747, "step": 438784 }, { "epoch": 1.02, "learning_rate": 4.2807379371748404e-05, "loss": 4.1794, "step": 439296 }, { "epoch": 1.02, "learning_rate": 4.2798993424237884e-05, "loss": 4.1724, "step": 439808 }, { "epoch": 1.02, "learning_rate": 4.2790607476727364e-05, "loss": 4.1864, "step": 440320 }, { "epoch": 1.02, "learning_rate": 4.278222152921684e-05, "loss": 4.1893, "step": 440832 }, { "epoch": 1.02, "learning_rate": 4.277385196051005e-05, "loss": 4.1783, "step": 441344 }, { "epoch": 1.02, "learning_rate": 4.276546601299953e-05, "loss": 4.1684, "step": 441856 }, { "epoch": 1.02, "learning_rate": 4.275708006548901e-05, "loss": 4.1724, "step": 442368 }, { "epoch": 1.02, "learning_rate": 4.2748694117978486e-05, "loss": 4.1752, "step": 442880 }, { "epoch": 1.02, "learning_rate": 4.2740308170467966e-05, "loss": 4.162, "step": 443392 }, { "epoch": 1.02, "learning_rate": 4.2731922222957446e-05, "loss": 4.192, "step": 443904 }, { "epoch": 1.02, "learning_rate": 4.272353627544693e-05, "loss": 4.1636, "step": 444416 }, { "epoch": 1.02, "learning_rate": 4.271515032793641e-05, "loss": 4.1793, "step": 444928 }, { "epoch": 1.02, "learning_rate": 4.270678075922962e-05, "loss": 4.173, "step": 445440 }, { "epoch": 1.02, "learning_rate": 4.269841119052284e-05, "loss": 4.1746, "step": 445952 }, { "epoch": 1.02, "learning_rate": 4.269002524301231e-05, "loss": 4.1628, "step": 446464 }, { "epoch": 1.02, "learning_rate": 4.268163929550179e-05, "loss": 4.1738, "step": 446976 }, { "epoch": 1.02, "learning_rate": 4.267325334799127e-05, "loss": 4.1664, "step": 447488 }, { "epoch": 1.02, "learning_rate": 4.266486740048075e-05, "loss": 4.1825, "step": 448000 }, { "epoch": 1.02, "learning_rate": 4.265649783177396e-05, "loss": 4.1725, "step": 448512 }, { "epoch": 1.02, "learning_rate": 4.264811188426344e-05, "loss": 4.1748, "step": 449024 }, { "epoch": 1.02, "learning_rate": 4.263972593675292e-05, "loss": 4.157, "step": 449536 }, { "epoch": 1.02, "learning_rate": 4.26313399892424e-05, "loss": 4.1813, "step": 450048 }, { "epoch": 1.02, "learning_rate": 4.2622954041731886e-05, "loss": 4.1688, "step": 450560 }, { "epoch": 1.02, "learning_rate": 4.2614584473025095e-05, "loss": 4.1741, "step": 451072 }, { "epoch": 1.02, "learning_rate": 4.2606198525514575e-05, "loss": 4.1708, "step": 451584 }, { "epoch": 1.02, "learning_rate": 4.2597812578004055e-05, "loss": 4.1782, "step": 452096 }, { "epoch": 1.02, "learning_rate": 4.2589426630493535e-05, "loss": 4.1703, "step": 452608 }, { "epoch": 1.02, "learning_rate": 4.2581040682983015e-05, "loss": 4.1831, "step": 453120 }, { "epoch": 1.02, "learning_rate": 4.2572654735472495e-05, "loss": 4.1567, "step": 453632 }, { "epoch": 1.02, "learning_rate": 4.2564268787961975e-05, "loss": 4.1682, "step": 454144 }, { "epoch": 1.02, "learning_rate": 4.2555899219255184e-05, "loss": 4.1663, "step": 454656 }, { "epoch": 1.02, "learning_rate": 4.2547513271744664e-05, "loss": 4.1655, "step": 455168 }, { "epoch": 1.02, "learning_rate": 4.2539127324234144e-05, "loss": 4.165, "step": 455680 }, { "epoch": 1.02, "learning_rate": 4.2530741376723624e-05, "loss": 4.1704, "step": 456192 }, { "epoch": 1.02, "learning_rate": 4.2522355429213104e-05, "loss": 4.173, "step": 456704 }, { "epoch": 1.02, "learning_rate": 4.251398586050632e-05, "loss": 4.1578, "step": 457216 }, { "epoch": 1.02, "learning_rate": 4.25055999129958e-05, "loss": 4.1783, "step": 457728 }, { "epoch": 1.03, "eval_loss": 4.164219379425049, "eval_runtime": 301.2945, "eval_samples_per_second": 1266.505, "eval_steps_per_second": 39.579, "step": 457920 }, { "epoch": 0.0, "learning_rate": 4.249721396548528e-05, "loss": 4.1629, "step": 458240 }, { "epoch": 0.0, "learning_rate": 4.248882801797476e-05, "loss": 4.1533, "step": 458752 }, { "epoch": 0.0, "learning_rate": 4.248044207046424e-05, "loss": 4.1729, "step": 459264 }, { "epoch": 0.0, "learning_rate": 4.247205612295372e-05, "loss": 4.1627, "step": 459776 }, { "epoch": 0.0, "learning_rate": 4.24636701754432e-05, "loss": 4.1661, "step": 460288 }, { "epoch": 0.0, "learning_rate": 4.245528422793267e-05, "loss": 4.1606, "step": 460800 }, { "epoch": 0.0, "learning_rate": 4.244689828042215e-05, "loss": 4.1578, "step": 461312 }, { "epoch": 0.0, "learning_rate": 4.243851233291163e-05, "loss": 4.1586, "step": 461824 }, { "epoch": 0.0, "learning_rate": 4.243012638540111e-05, "loss": 4.165, "step": 462336 }, { "epoch": 0.0, "learning_rate": 4.242174043789059e-05, "loss": 4.1624, "step": 462848 }, { "epoch": 0.0, "learning_rate": 4.241335449038007e-05, "loss": 4.1706, "step": 463360 }, { "epoch": 0.0, "learning_rate": 4.240496854286955e-05, "loss": 4.173, "step": 463872 }, { "epoch": 0.0, "learning_rate": 4.239659897416277e-05, "loss": 4.157, "step": 464384 }, { "epoch": 0.0, "learning_rate": 4.238821302665225e-05, "loss": 4.1612, "step": 464896 }, { "epoch": 0.0, "learning_rate": 4.237982707914173e-05, "loss": 4.1634, "step": 465408 }, { "epoch": 0.0, "learning_rate": 4.237144113163121e-05, "loss": 4.1556, "step": 465920 }, { "epoch": 0.0, "learning_rate": 4.236305518412069e-05, "loss": 4.1508, "step": 466432 }, { "epoch": 0.0, "learning_rate": 4.235466923661017e-05, "loss": 4.1571, "step": 466944 }, { "epoch": 0.0, "learning_rate": 4.234628328909965e-05, "loss": 4.1547, "step": 467456 }, { "epoch": 0.0, "learning_rate": 4.233789734158913e-05, "loss": 4.1692, "step": 467968 }, { "epoch": 0.0, "learning_rate": 4.232951139407861e-05, "loss": 4.1646, "step": 468480 }, { "epoch": 0.0, "learning_rate": 4.232112544656809e-05, "loss": 4.166, "step": 468992 }, { "epoch": 0.0, "learning_rate": 4.23127558778613e-05, "loss": 4.1684, "step": 469504 }, { "epoch": 0.0, "learning_rate": 4.230436993035078e-05, "loss": 4.169, "step": 470016 }, { "epoch": 0.0, "learning_rate": 4.229598398284026e-05, "loss": 4.1501, "step": 470528 }, { "epoch": 0.0, "learning_rate": 4.228759803532974e-05, "loss": 4.1636, "step": 471040 }, { "epoch": 0.0, "learning_rate": 4.227921208781922e-05, "loss": 4.1486, "step": 471552 }, { "epoch": 0.0, "learning_rate": 4.22708261403087e-05, "loss": 4.1559, "step": 472064 }, { "epoch": 0.0, "learning_rate": 4.226244019279818e-05, "loss": 4.1552, "step": 472576 }, { "epoch": 0.0, "learning_rate": 4.2254070624091386e-05, "loss": 4.152, "step": 473088 }, { "epoch": 0.01, "learning_rate": 4.2245684676580866e-05, "loss": 4.1625, "step": 473600 }, { "epoch": 0.01, "learning_rate": 4.2237298729070346e-05, "loss": 4.1581, "step": 474112 }, { "epoch": 0.01, "learning_rate": 4.2228912781559826e-05, "loss": 4.1565, "step": 474624 }, { "epoch": 0.01, "learning_rate": 4.2220543212853035e-05, "loss": 4.1595, "step": 475136 }, { "epoch": 0.01, "learning_rate": 4.2212157265342515e-05, "loss": 4.1576, "step": 475648 }, { "epoch": 0.01, "learning_rate": 4.2203771317831995e-05, "loss": 4.1599, "step": 476160 }, { "epoch": 0.01, "learning_rate": 4.2195385370321475e-05, "loss": 4.1499, "step": 476672 }, { "epoch": 0.01, "learning_rate": 4.2186999422810955e-05, "loss": 4.1486, "step": 477184 }, { "epoch": 0.01, "learning_rate": 4.217861347530044e-05, "loss": 4.1442, "step": 477696 }, { "epoch": 0.01, "learning_rate": 4.217024390659365e-05, "loss": 4.1479, "step": 478208 }, { "epoch": 0.01, "learning_rate": 4.216185795908313e-05, "loss": 4.1495, "step": 478720 }, { "epoch": 0.01, "learning_rate": 4.215347201157261e-05, "loss": 4.1571, "step": 479232 }, { "epoch": 0.01, "learning_rate": 4.214508606406209e-05, "loss": 4.1545, "step": 479744 }, { "epoch": 0.01, "learning_rate": 4.213670011655157e-05, "loss": 4.1535, "step": 480256 }, { "epoch": 0.01, "learning_rate": 4.212831416904105e-05, "loss": 4.1611, "step": 480768 }, { "epoch": 0.01, "learning_rate": 4.211992822153053e-05, "loss": 4.1549, "step": 481280 }, { "epoch": 0.01, "learning_rate": 4.211155865282374e-05, "loss": 4.159, "step": 481792 }, { "epoch": 0.01, "learning_rate": 4.210317270531322e-05, "loss": 4.1443, "step": 482304 }, { "epoch": 0.01, "learning_rate": 4.20947867578027e-05, "loss": 4.1354, "step": 482816 }, { "epoch": 0.01, "learning_rate": 4.208640081029218e-05, "loss": 4.164, "step": 483328 }, { "epoch": 0.01, "learning_rate": 4.207801486278166e-05, "loss": 4.1463, "step": 483840 }, { "epoch": 0.01, "learning_rate": 4.206962891527114e-05, "loss": 4.1421, "step": 484352 }, { "epoch": 0.01, "learning_rate": 4.2061242967760626e-05, "loss": 4.148, "step": 484864 }, { "epoch": 0.01, "learning_rate": 4.2052873399053835e-05, "loss": 4.1427, "step": 485376 }, { "epoch": 0.01, "learning_rate": 4.2044487451543315e-05, "loss": 4.1434, "step": 485888 }, { "epoch": 0.01, "learning_rate": 4.2036101504032795e-05, "loss": 4.1398, "step": 486400 }, { "epoch": 0.01, "learning_rate": 4.2027731935326004e-05, "loss": 4.1472, "step": 486912 }, { "epoch": 0.01, "learning_rate": 4.2019345987815484e-05, "loss": 4.144, "step": 487424 }, { "epoch": 0.01, "learning_rate": 4.2010960040304964e-05, "loss": 4.158, "step": 487936 }, { "epoch": 0.01, "learning_rate": 4.2002574092794444e-05, "loss": 4.1361, "step": 488448 }, { "epoch": 0.01, "learning_rate": 4.1994188145283924e-05, "loss": 4.1364, "step": 488960 }, { "epoch": 0.01, "learning_rate": 4.19858021977734e-05, "loss": 4.1592, "step": 489472 }, { "epoch": 0.01, "learning_rate": 4.197741625026288e-05, "loss": 4.1303, "step": 489984 }, { "epoch": 0.01, "learning_rate": 4.1969030302752363e-05, "loss": 4.1392, "step": 490496 }, { "epoch": 0.01, "learning_rate": 4.1960644355241843e-05, "loss": 4.1446, "step": 491008 }, { "epoch": 0.01, "learning_rate": 4.1952258407731323e-05, "loss": 4.1545, "step": 491520 }, { "epoch": 0.01, "learning_rate": 4.194388883902453e-05, "loss": 4.1348, "step": 492032 }, { "epoch": 0.01, "learning_rate": 4.193550289151401e-05, "loss": 4.1357, "step": 492544 }, { "epoch": 0.01, "learning_rate": 4.192711694400349e-05, "loss": 4.126, "step": 493056 }, { "epoch": 0.01, "learning_rate": 4.19187473752967e-05, "loss": 4.1441, "step": 493568 }, { "epoch": 0.01, "learning_rate": 4.191036142778618e-05, "loss": 4.1588, "step": 494080 }, { "epoch": 0.01, "learning_rate": 4.190197548027566e-05, "loss": 4.1455, "step": 494592 }, { "epoch": 0.01, "learning_rate": 4.189358953276514e-05, "loss": 4.1441, "step": 495104 }, { "epoch": 0.01, "learning_rate": 4.188520358525462e-05, "loss": 4.1546, "step": 495616 }, { "epoch": 0.01, "learning_rate": 4.18768176377441e-05, "loss": 4.1581, "step": 496128 }, { "epoch": 0.01, "learning_rate": 4.186843169023358e-05, "loss": 4.1362, "step": 496640 }, { "epoch": 0.01, "learning_rate": 4.186004574272306e-05, "loss": 4.146, "step": 497152 }, { "epoch": 0.01, "learning_rate": 4.185165979521254e-05, "loss": 4.1461, "step": 497664 }, { "epoch": 0.01, "learning_rate": 4.184327384770203e-05, "loss": 4.1295, "step": 498176 }, { "epoch": 0.01, "learning_rate": 4.183488790019151e-05, "loss": 4.1444, "step": 498688 }, { "epoch": 0.01, "learning_rate": 4.182650195268099e-05, "loss": 4.144, "step": 499200 }, { "epoch": 0.01, "learning_rate": 4.18181323839742e-05, "loss": 4.1459, "step": 499712 }, { "epoch": 0.01, "learning_rate": 4.1809762815267406e-05, "loss": 4.1446, "step": 500224 }, { "epoch": 0.01, "learning_rate": 4.1801376867756886e-05, "loss": 4.1429, "step": 500736 }, { "epoch": 0.01, "learning_rate": 4.1792990920246366e-05, "loss": 4.1357, "step": 501248 }, { "epoch": 0.01, "learning_rate": 4.1784604972735846e-05, "loss": 4.1451, "step": 501760 }, { "epoch": 0.01, "learning_rate": 4.1776219025225326e-05, "loss": 4.1417, "step": 502272 }, { "epoch": 0.01, "learning_rate": 4.1767849456518535e-05, "loss": 4.1354, "step": 502784 }, { "epoch": 0.01, "learning_rate": 4.175947988781175e-05, "loss": 4.14, "step": 503296 }, { "epoch": 0.02, "learning_rate": 4.175109394030123e-05, "loss": 4.1374, "step": 503808 }, { "epoch": 0.02, "learning_rate": 4.174270799279071e-05, "loss": 4.1448, "step": 504320 }, { "epoch": 0.02, "learning_rate": 4.173432204528019e-05, "loss": 4.1375, "step": 504832 }, { "epoch": 0.02, "learning_rate": 4.172593609776967e-05, "loss": 4.1323, "step": 505344 }, { "epoch": 0.02, "learning_rate": 4.171755015025915e-05, "loss": 4.1524, "step": 505856 }, { "epoch": 0.02, "learning_rate": 4.170916420274863e-05, "loss": 4.1429, "step": 506368 }, { "epoch": 0.02, "learning_rate": 4.170077825523811e-05, "loss": 4.1404, "step": 506880 }, { "epoch": 0.02, "learning_rate": 4.169240868653132e-05, "loss": 4.1261, "step": 507392 }, { "epoch": 0.02, "learning_rate": 4.16840227390208e-05, "loss": 4.1368, "step": 507904 }, { "epoch": 0.02, "learning_rate": 4.167563679151028e-05, "loss": 4.1332, "step": 508416 }, { "epoch": 0.02, "learning_rate": 4.166725084399975e-05, "loss": 4.1399, "step": 508928 }, { "epoch": 0.02, "learning_rate": 4.165886489648923e-05, "loss": 4.1503, "step": 509440 }, { "epoch": 0.02, "learning_rate": 4.165047894897872e-05, "loss": 4.1317, "step": 509952 }, { "epoch": 0.02, "learning_rate": 4.16420930014682e-05, "loss": 4.1327, "step": 510464 }, { "epoch": 0.02, "learning_rate": 4.163370705395768e-05, "loss": 4.136, "step": 510976 }, { "epoch": 0.02, "learning_rate": 4.162533748525089e-05, "loss": 4.1125, "step": 511488 }, { "epoch": 0.02, "learning_rate": 4.1616967916544104e-05, "loss": 4.1368, "step": 512000 }, { "epoch": 0.02, "learning_rate": 4.1608581969033584e-05, "loss": 4.1171, "step": 512512 }, { "epoch": 0.02, "learning_rate": 4.160019602152306e-05, "loss": 4.1391, "step": 513024 }, { "epoch": 0.02, "learning_rate": 4.159181007401254e-05, "loss": 4.1253, "step": 513536 }, { "epoch": 0.02, "learning_rate": 4.158344050530575e-05, "loss": 4.1363, "step": 514048 }, { "epoch": 0.02, "learning_rate": 4.1575054557795226e-05, "loss": 4.1281, "step": 514560 }, { "epoch": 0.02, "learning_rate": 4.1566668610284706e-05, "loss": 4.1312, "step": 515072 }, { "epoch": 0.02, "learning_rate": 4.1558282662774186e-05, "loss": 4.1448, "step": 515584 }, { "epoch": 0.02, "learning_rate": 4.15499130940674e-05, "loss": 4.127, "step": 516096 }, { "epoch": 0.02, "learning_rate": 4.154152714655688e-05, "loss": 4.1451, "step": 516608 }, { "epoch": 0.02, "learning_rate": 4.153314119904636e-05, "loss": 4.1481, "step": 517120 }, { "epoch": 0.02, "learning_rate": 4.152475525153584e-05, "loss": 4.1361, "step": 517632 }, { "epoch": 0.02, "learning_rate": 4.151636930402532e-05, "loss": 4.135, "step": 518144 }, { "epoch": 0.02, "learning_rate": 4.15079833565148e-05, "loss": 4.1257, "step": 518656 }, { "epoch": 0.02, "learning_rate": 4.149959740900428e-05, "loss": 4.1359, "step": 519168 }, { "epoch": 0.02, "learning_rate": 4.149121146149376e-05, "loss": 4.1296, "step": 519680 }, { "epoch": 0.02, "learning_rate": 4.148284189278697e-05, "loss": 4.149, "step": 520192 }, { "epoch": 0.02, "learning_rate": 4.147445594527645e-05, "loss": 4.1191, "step": 520704 }, { "epoch": 0.02, "learning_rate": 4.146606999776593e-05, "loss": 4.1393, "step": 521216 }, { "epoch": 0.02, "learning_rate": 4.145770042905914e-05, "loss": 4.1369, "step": 521728 }, { "epoch": 0.02, "learning_rate": 4.144931448154863e-05, "loss": 4.1336, "step": 522240 }, { "epoch": 0.02, "learning_rate": 4.144092853403811e-05, "loss": 4.1219, "step": 522752 }, { "epoch": 0.02, "learning_rate": 4.1432558965331316e-05, "loss": 4.136, "step": 523264 }, { "epoch": 0.02, "learning_rate": 4.1424173017820796e-05, "loss": 4.1235, "step": 523776 }, { "epoch": 0.02, "learning_rate": 4.1415787070310276e-05, "loss": 4.1471, "step": 524288 }, { "epoch": 0.02, "learning_rate": 4.1407401122799756e-05, "loss": 4.1296, "step": 524800 }, { "epoch": 0.02, "learning_rate": 4.1399015175289236e-05, "loss": 4.1347, "step": 525312 }, { "epoch": 0.02, "learning_rate": 4.1390629227778716e-05, "loss": 4.1181, "step": 525824 }, { "epoch": 0.02, "learning_rate": 4.1382243280268195e-05, "loss": 4.1438, "step": 526336 }, { "epoch": 0.02, "learning_rate": 4.1373857332757675e-05, "loss": 4.1321, "step": 526848 }, { "epoch": 0.02, "learning_rate": 4.1365471385247155e-05, "loss": 4.1358, "step": 527360 }, { "epoch": 0.02, "learning_rate": 4.1357085437736635e-05, "loss": 4.1309, "step": 527872 }, { "epoch": 0.02, "learning_rate": 4.1348699490226115e-05, "loss": 4.1335, "step": 528384 }, { "epoch": 0.02, "learning_rate": 4.1340313542715595e-05, "loss": 4.1351, "step": 528896 }, { "epoch": 0.02, "learning_rate": 4.1331943974008804e-05, "loss": 4.1481, "step": 529408 }, { "epoch": 0.02, "learning_rate": 4.132355802649829e-05, "loss": 4.1149, "step": 529920 }, { "epoch": 0.02, "learning_rate": 4.131517207898777e-05, "loss": 4.1287, "step": 530432 }, { "epoch": 0.02, "learning_rate": 4.130681888908471e-05, "loss": 4.1261, "step": 530944 }, { "epoch": 0.02, "learning_rate": 4.129843294157419e-05, "loss": 4.1279, "step": 531456 }, { "epoch": 0.02, "learning_rate": 4.129004699406367e-05, "loss": 4.1241, "step": 531968 }, { "epoch": 0.02, "learning_rate": 4.128166104655315e-05, "loss": 4.1321, "step": 532480 }, { "epoch": 0.02, "learning_rate": 4.127327509904263e-05, "loss": 4.1316, "step": 532992 }, { "epoch": 0.02, "learning_rate": 4.126488915153211e-05, "loss": 4.1213, "step": 533504 }, { "epoch": 0.02, "learning_rate": 4.125650320402159e-05, "loss": 4.1398, "step": 534016 }, { "epoch": 0.03, "eval_loss": 4.132750988006592, "eval_runtime": 300.9059, "eval_samples_per_second": 1268.141, "eval_steps_per_second": 39.63, "step": 534240 }, { "epoch": 1.0, "learning_rate": 4.124811725651106e-05, "loss": 4.1232, "step": 534528 }, { "epoch": 1.0, "learning_rate": 4.123973130900054e-05, "loss": 4.1166, "step": 535040 }, { "epoch": 1.0, "learning_rate": 4.123134536149003e-05, "loss": 4.1352, "step": 535552 }, { "epoch": 1.0, "learning_rate": 4.122295941397951e-05, "loss": 4.1205, "step": 536064 }, { "epoch": 1.0, "learning_rate": 4.121457346646899e-05, "loss": 4.1281, "step": 536576 }, { "epoch": 1.0, "learning_rate": 4.12062038977622e-05, "loss": 4.1223, "step": 537088 }, { "epoch": 1.0, "learning_rate": 4.119781795025168e-05, "loss": 4.1224, "step": 537600 }, { "epoch": 1.0, "learning_rate": 4.118943200274116e-05, "loss": 4.1187, "step": 538112 }, { "epoch": 1.0, "learning_rate": 4.118104605523064e-05, "loss": 4.1293, "step": 538624 }, { "epoch": 1.0, "learning_rate": 4.117269286532758e-05, "loss": 4.1205, "step": 539136 }, { "epoch": 1.0, "learning_rate": 4.116430691781706e-05, "loss": 4.1342, "step": 539648 }, { "epoch": 1.0, "learning_rate": 4.115593734911027e-05, "loss": 4.1337, "step": 540160 }, { "epoch": 1.0, "learning_rate": 4.114756778040348e-05, "loss": 4.1235, "step": 540672 }, { "epoch": 1.0, "learning_rate": 4.113918183289297e-05, "loss": 4.1235, "step": 541184 }, { "epoch": 1.0, "learning_rate": 4.113079588538245e-05, "loss": 4.1214, "step": 541696 }, { "epoch": 1.0, "learning_rate": 4.112240993787193e-05, "loss": 4.1153, "step": 542208 }, { "epoch": 1.0, "learning_rate": 4.111402399036141e-05, "loss": 4.1146, "step": 542720 }, { "epoch": 1.0, "learning_rate": 4.110563804285089e-05, "loss": 4.1203, "step": 543232 }, { "epoch": 1.0, "learning_rate": 4.109725209534036e-05, "loss": 4.1208, "step": 543744 }, { "epoch": 1.0, "learning_rate": 4.108886614782984e-05, "loss": 4.1263, "step": 544256 }, { "epoch": 1.0, "learning_rate": 4.108048020031932e-05, "loss": 4.1331, "step": 544768 }, { "epoch": 1.0, "learning_rate": 4.10720942528088e-05, "loss": 4.1269, "step": 545280 }, { "epoch": 1.0, "learning_rate": 4.106370830529828e-05, "loss": 4.1282, "step": 545792 }, { "epoch": 1.0, "learning_rate": 4.105532235778776e-05, "loss": 4.1316, "step": 546304 }, { "epoch": 1.0, "learning_rate": 4.104693641027724e-05, "loss": 4.1107, "step": 546816 }, { "epoch": 1.0, "learning_rate": 4.103856684157045e-05, "loss": 4.1278, "step": 547328 }, { "epoch": 1.0, "learning_rate": 4.1030180894059936e-05, "loss": 4.1153, "step": 547840 }, { "epoch": 1.0, "learning_rate": 4.1021794946549416e-05, "loss": 4.1187, "step": 548352 }, { "epoch": 1.0, "learning_rate": 4.1013408999038896e-05, "loss": 4.1153, "step": 548864 }, { "epoch": 1.0, "learning_rate": 4.1005023051528376e-05, "loss": 4.1189, "step": 549376 }, { "epoch": 1.01, "learning_rate": 4.0996637104017856e-05, "loss": 4.1198, "step": 549888 }, { "epoch": 1.01, "learning_rate": 4.0988251156507336e-05, "loss": 4.123, "step": 550400 }, { "epoch": 1.01, "learning_rate": 4.0979865208996816e-05, "loss": 4.1207, "step": 550912 }, { "epoch": 1.01, "learning_rate": 4.0971495640290025e-05, "loss": 4.1267, "step": 551424 }, { "epoch": 1.01, "learning_rate": 4.0963126071583234e-05, "loss": 4.1146, "step": 551936 }, { "epoch": 1.01, "learning_rate": 4.0954740124072714e-05, "loss": 4.1246, "step": 552448 }, { "epoch": 1.01, "learning_rate": 4.0946354176562194e-05, "loss": 4.1205, "step": 552960 }, { "epoch": 1.01, "learning_rate": 4.0937968229051674e-05, "loss": 4.1034, "step": 553472 }, { "epoch": 1.01, "learning_rate": 4.0929582281541154e-05, "loss": 4.1082, "step": 553984 }, { "epoch": 1.01, "learning_rate": 4.092121271283437e-05, "loss": 4.1093, "step": 554496 }, { "epoch": 1.01, "learning_rate": 4.091282676532385e-05, "loss": 4.1162, "step": 555008 }, { "epoch": 1.01, "learning_rate": 4.090444081781333e-05, "loss": 4.12, "step": 555520 }, { "epoch": 1.01, "learning_rate": 4.089605487030281e-05, "loss": 4.1172, "step": 556032 }, { "epoch": 1.01, "learning_rate": 4.088766892279229e-05, "loss": 4.1149, "step": 556544 }, { "epoch": 1.01, "learning_rate": 4.08792993540855e-05, "loss": 4.1272, "step": 557056 }, { "epoch": 1.01, "learning_rate": 4.087091340657498e-05, "loss": 4.1171, "step": 557568 }, { "epoch": 1.01, "learning_rate": 4.086252745906446e-05, "loss": 4.1244, "step": 558080 }, { "epoch": 1.01, "learning_rate": 4.085414151155394e-05, "loss": 4.1112, "step": 558592 }, { "epoch": 1.01, "learning_rate": 4.084577194284715e-05, "loss": 4.0925, "step": 559104 }, { "epoch": 1.01, "learning_rate": 4.083740237414036e-05, "loss": 4.1298, "step": 559616 }, { "epoch": 1.01, "learning_rate": 4.0829016426629844e-05, "loss": 4.1099, "step": 560128 }, { "epoch": 1.01, "learning_rate": 4.0820630479119323e-05, "loss": 4.1117, "step": 560640 }, { "epoch": 1.01, "learning_rate": 4.0812244531608803e-05, "loss": 4.1086, "step": 561152 }, { "epoch": 1.01, "learning_rate": 4.0803858584098283e-05, "loss": 4.1084, "step": 561664 }, { "epoch": 1.01, "learning_rate": 4.079547263658776e-05, "loss": 4.1083, "step": 562176 }, { "epoch": 1.01, "learning_rate": 4.078708668907724e-05, "loss": 4.1012, "step": 562688 }, { "epoch": 1.01, "learning_rate": 4.077870074156672e-05, "loss": 4.1113, "step": 563200 }, { "epoch": 1.01, "learning_rate": 4.0770314794056196e-05, "loss": 4.1061, "step": 563712 }, { "epoch": 1.01, "learning_rate": 4.0761928846545676e-05, "loss": 4.1236, "step": 564224 }, { "epoch": 1.01, "learning_rate": 4.075355927783889e-05, "loss": 4.1023, "step": 564736 }, { "epoch": 1.01, "learning_rate": 4.074517333032837e-05, "loss": 4.1012, "step": 565248 }, { "epoch": 1.01, "learning_rate": 4.0736787382817845e-05, "loss": 4.122, "step": 565760 }, { "epoch": 1.01, "learning_rate": 4.0728401435307325e-05, "loss": 4.0953, "step": 566272 }, { "epoch": 1.01, "learning_rate": 4.072001548779681e-05, "loss": 4.1029, "step": 566784 }, { "epoch": 1.01, "learning_rate": 4.071162954028629e-05, "loss": 4.1121, "step": 567296 }, { "epoch": 1.01, "learning_rate": 4.070324359277577e-05, "loss": 4.1199, "step": 567808 }, { "epoch": 1.01, "learning_rate": 4.069485764526525e-05, "loss": 4.1009, "step": 568320 }, { "epoch": 1.01, "learning_rate": 4.068647169775473e-05, "loss": 4.1, "step": 568832 }, { "epoch": 1.01, "learning_rate": 4.067808575024421e-05, "loss": 4.0935, "step": 569344 }, { "epoch": 1.01, "learning_rate": 4.066969980273369e-05, "loss": 4.1085, "step": 569856 }, { "epoch": 1.01, "learning_rate": 4.066131385522317e-05, "loss": 4.1233, "step": 570368 }, { "epoch": 1.01, "learning_rate": 4.065294428651638e-05, "loss": 4.1078, "step": 570880 }, { "epoch": 1.01, "learning_rate": 4.064457471780959e-05, "loss": 4.1096, "step": 571392 }, { "epoch": 1.01, "learning_rate": 4.063618877029907e-05, "loss": 4.12, "step": 571904 }, { "epoch": 1.01, "learning_rate": 4.062780282278855e-05, "loss": 4.1247, "step": 572416 }, { "epoch": 1.01, "learning_rate": 4.061941687527803e-05, "loss": 4.0979, "step": 572928 }, { "epoch": 1.01, "learning_rate": 4.0611047306571246e-05, "loss": 4.1153, "step": 573440 }, { "epoch": 1.01, "learning_rate": 4.0602661359060726e-05, "loss": 4.1067, "step": 573952 }, { "epoch": 1.01, "learning_rate": 4.0594275411550206e-05, "loss": 4.1027, "step": 574464 }, { "epoch": 1.01, "learning_rate": 4.0585889464039686e-05, "loss": 4.1032, "step": 574976 }, { "epoch": 1.01, "learning_rate": 4.0577503516529166e-05, "loss": 4.1136, "step": 575488 }, { "epoch": 1.01, "learning_rate": 4.0569117569018645e-05, "loss": 4.1097, "step": 576000 }, { "epoch": 1.01, "learning_rate": 4.0560731621508125e-05, "loss": 4.115, "step": 576512 }, { "epoch": 1.01, "learning_rate": 4.0552345673997605e-05, "loss": 4.1058, "step": 577024 }, { "epoch": 1.01, "learning_rate": 4.0543992484094544e-05, "loss": 4.0993, "step": 577536 }, { "epoch": 1.01, "learning_rate": 4.0535606536584024e-05, "loss": 4.1108, "step": 578048 }, { "epoch": 1.01, "learning_rate": 4.0527220589073504e-05, "loss": 4.1072, "step": 578560 }, { "epoch": 1.01, "learning_rate": 4.0518834641562984e-05, "loss": 4.1027, "step": 579072 }, { "epoch": 1.01, "learning_rate": 4.05104650728562e-05, "loss": 4.1079, "step": 579584 }, { "epoch": 1.02, "learning_rate": 4.050207912534568e-05, "loss": 4.1047, "step": 580096 }, { "epoch": 1.02, "learning_rate": 4.049369317783516e-05, "loss": 4.111, "step": 580608 }, { "epoch": 1.02, "learning_rate": 4.048530723032464e-05, "loss": 4.1055, "step": 581120 }, { "epoch": 1.02, "learning_rate": 4.047692128281412e-05, "loss": 4.096, "step": 581632 }, { "epoch": 1.02, "learning_rate": 4.04685353353036e-05, "loss": 4.1164, "step": 582144 }, { "epoch": 1.02, "learning_rate": 4.046014938779308e-05, "loss": 4.1112, "step": 582656 }, { "epoch": 1.02, "learning_rate": 4.045176344028256e-05, "loss": 4.1075, "step": 583168 }, { "epoch": 1.02, "learning_rate": 4.044337749277203e-05, "loss": 4.0958, "step": 583680 }, { "epoch": 1.02, "learning_rate": 4.043499154526151e-05, "loss": 4.1005, "step": 584192 }, { "epoch": 1.02, "learning_rate": 4.042662197655473e-05, "loss": 4.0988, "step": 584704 }, { "epoch": 1.02, "learning_rate": 4.041823602904421e-05, "loss": 4.1087, "step": 585216 }, { "epoch": 1.02, "learning_rate": 4.040985008153368e-05, "loss": 4.1142, "step": 585728 }, { "epoch": 1.02, "learning_rate": 4.040146413402317e-05, "loss": 4.1016, "step": 586240 }, { "epoch": 1.02, "learning_rate": 4.039307818651265e-05, "loss": 4.1005, "step": 586752 }, { "epoch": 1.02, "learning_rate": 4.038469223900213e-05, "loss": 4.0979, "step": 587264 }, { "epoch": 1.02, "learning_rate": 4.037632267029534e-05, "loss": 4.0857, "step": 587776 }, { "epoch": 1.02, "learning_rate": 4.036793672278482e-05, "loss": 4.0981, "step": 588288 }, { "epoch": 1.02, "learning_rate": 4.03595507752743e-05, "loss": 4.0852, "step": 588800 }, { "epoch": 1.02, "learning_rate": 4.035116482776378e-05, "loss": 4.1066, "step": 589312 }, { "epoch": 1.02, "learning_rate": 4.034277888025326e-05, "loss": 4.0914, "step": 589824 }, { "epoch": 1.02, "learning_rate": 4.0334409311546466e-05, "loss": 4.1007, "step": 590336 }, { "epoch": 1.02, "learning_rate": 4.0326023364035946e-05, "loss": 4.0949, "step": 590848 }, { "epoch": 1.02, "learning_rate": 4.0317637416525426e-05, "loss": 4.1009, "step": 591360 }, { "epoch": 1.02, "learning_rate": 4.0309251469014906e-05, "loss": 4.1074, "step": 591872 }, { "epoch": 1.02, "learning_rate": 4.030088190030812e-05, "loss": 4.0974, "step": 592384 }, { "epoch": 1.02, "learning_rate": 4.02924959527976e-05, "loss": 4.1122, "step": 592896 }, { "epoch": 1.02, "learning_rate": 4.028412638409081e-05, "loss": 4.1136, "step": 593408 }, { "epoch": 1.02, "learning_rate": 4.027574043658029e-05, "loss": 4.1035, "step": 593920 }, { "epoch": 1.02, "learning_rate": 4.026735448906977e-05, "loss": 4.1052, "step": 594432 }, { "epoch": 1.02, "learning_rate": 4.025896854155925e-05, "loss": 4.0902, "step": 594944 }, { "epoch": 1.02, "learning_rate": 4.025058259404873e-05, "loss": 4.1033, "step": 595456 }, { "epoch": 1.02, "learning_rate": 4.024219664653821e-05, "loss": 4.0988, "step": 595968 }, { "epoch": 1.02, "learning_rate": 4.023381069902769e-05, "loss": 4.1094, "step": 596480 }, { "epoch": 1.02, "learning_rate": 4.022542475151717e-05, "loss": 4.0914, "step": 596992 }, { "epoch": 1.02, "learning_rate": 4.021703880400665e-05, "loss": 4.1073, "step": 597504 }, { "epoch": 1.02, "learning_rate": 4.020865285649613e-05, "loss": 4.106, "step": 598016 }, { "epoch": 1.02, "learning_rate": 4.020026690898561e-05, "loss": 4.1018, "step": 598528 }, { "epoch": 1.02, "learning_rate": 4.019188096147509e-05, "loss": 4.0859, "step": 599040 }, { "epoch": 1.02, "learning_rate": 4.0183527771572035e-05, "loss": 4.1043, "step": 599552 }, { "epoch": 1.02, "learning_rate": 4.0175141824061515e-05, "loss": 4.0918, "step": 600064 }, { "epoch": 1.02, "learning_rate": 4.0166755876550995e-05, "loss": 4.1111, "step": 600576 }, { "epoch": 1.02, "learning_rate": 4.0158369929040475e-05, "loss": 4.1007, "step": 601088 }, { "epoch": 1.02, "learning_rate": 4.015001673913741e-05, "loss": 4.0998, "step": 601600 }, { "epoch": 1.02, "learning_rate": 4.014163079162689e-05, "loss": 4.0844, "step": 602112 }, { "epoch": 1.02, "learning_rate": 4.013324484411637e-05, "loss": 4.1149, "step": 602624 }, { "epoch": 1.02, "learning_rate": 4.012485889660585e-05, "loss": 4.0973, "step": 603136 }, { "epoch": 1.02, "learning_rate": 4.011647294909533e-05, "loss": 4.1038, "step": 603648 }, { "epoch": 1.02, "learning_rate": 4.010808700158481e-05, "loss": 4.0983, "step": 604160 }, { "epoch": 1.02, "learning_rate": 4.009970105407429e-05, "loss": 4.0995, "step": 604672 }, { "epoch": 1.02, "learning_rate": 4.009131510656377e-05, "loss": 4.1032, "step": 605184 }, { "epoch": 1.02, "learning_rate": 4.008292915905325e-05, "loss": 4.1127, "step": 605696 }, { "epoch": 1.02, "learning_rate": 4.007455959034647e-05, "loss": 4.0845, "step": 606208 }, { "epoch": 1.02, "learning_rate": 4.006617364283595e-05, "loss": 4.0982, "step": 606720 }, { "epoch": 1.02, "learning_rate": 4.005778769532543e-05, "loss": 4.0947, "step": 607232 }, { "epoch": 1.02, "learning_rate": 4.004940174781491e-05, "loss": 4.0927, "step": 607744 }, { "epoch": 1.02, "learning_rate": 4.004103217910812e-05, "loss": 4.0935, "step": 608256 }, { "epoch": 1.02, "learning_rate": 4.003266261040133e-05, "loss": 4.1003, "step": 608768 }, { "epoch": 1.02, "learning_rate": 4.002427666289081e-05, "loss": 4.1011, "step": 609280 }, { "epoch": 1.02, "learning_rate": 4.001589071538029e-05, "loss": 4.0887, "step": 609792 }, { "epoch": 1.02, "learning_rate": 4.000750476786977e-05, "loss": 4.1063, "step": 610304 }, { "epoch": 1.03, "eval_loss": 4.1089982986450195, "eval_runtime": 299.6682, "eval_samples_per_second": 1273.379, "eval_steps_per_second": 39.794, "step": 610560 }, { "epoch": 0.0, "learning_rate": 3.999911882035925e-05, "loss": 4.0878, "step": 610816 }, { "epoch": 0.0, "learning_rate": 3.999073287284873e-05, "loss": 4.0881, "step": 611328 }, { "epoch": 0.0, "learning_rate": 3.9982346925338207e-05, "loss": 4.0999, "step": 611840 }, { "epoch": 0.0, "learning_rate": 3.997396097782769e-05, "loss": 4.0882, "step": 612352 }, { "epoch": 0.0, "learning_rate": 3.9965575030317167e-05, "loss": 4.0996, "step": 612864 }, { "epoch": 0.0, "learning_rate": 3.9957189082806646e-05, "loss": 4.0856, "step": 613376 }, { "epoch": 0.0, "learning_rate": 3.9948803135296126e-05, "loss": 4.0993, "step": 613888 }, { "epoch": 0.0, "learning_rate": 3.9940417187785606e-05, "loss": 4.0837, "step": 614400 }, { "epoch": 0.0, "learning_rate": 3.9932031240275086e-05, "loss": 4.0964, "step": 614912 }, { "epoch": 0.0, "learning_rate": 3.9923645292764566e-05, "loss": 4.0926, "step": 615424 }, { "epoch": 0.0, "learning_rate": 3.9915259345254046e-05, "loss": 4.0971, "step": 615936 }, { "epoch": 0.0, "learning_rate": 3.9906873397743526e-05, "loss": 4.1036, "step": 616448 }, { "epoch": 0.0, "learning_rate": 3.9898503829036735e-05, "loss": 4.0918, "step": 616960 }, { "epoch": 0.0, "learning_rate": 3.9890117881526215e-05, "loss": 4.093, "step": 617472 }, { "epoch": 0.0, "learning_rate": 3.9881731934015695e-05, "loss": 4.093, "step": 617984 }, { "epoch": 0.0, "learning_rate": 3.9873345986505175e-05, "loss": 4.0827, "step": 618496 }, { "epoch": 0.0, "learning_rate": 3.986496003899466e-05, "loss": 4.0831, "step": 619008 }, { "epoch": 0.0, "learning_rate": 3.985659047028787e-05, "loss": 4.0892, "step": 619520 }, { "epoch": 0.0, "learning_rate": 3.984820452277735e-05, "loss": 4.0909, "step": 620032 }, { "epoch": 0.0, "learning_rate": 3.983981857526683e-05, "loss": 4.0913, "step": 620544 }, { "epoch": 0.0, "learning_rate": 3.983143262775631e-05, "loss": 4.1015, "step": 621056 }, { "epoch": 0.0, "learning_rate": 3.982304668024579e-05, "loss": 4.097, "step": 621568 }, { "epoch": 0.0, "learning_rate": 3.981466073273527e-05, "loss": 4.0996, "step": 622080 }, { "epoch": 0.0, "learning_rate": 3.980627478522475e-05, "loss": 4.0999, "step": 622592 }, { "epoch": 0.0, "learning_rate": 3.979790521651796e-05, "loss": 4.0842, "step": 623104 }, { "epoch": 0.0, "learning_rate": 3.978951926900744e-05, "loss": 4.0945, "step": 623616 }, { "epoch": 0.0, "learning_rate": 3.978113332149692e-05, "loss": 4.0839, "step": 624128 }, { "epoch": 0.0, "learning_rate": 3.97727473739864e-05, "loss": 4.0889, "step": 624640 }, { "epoch": 0.0, "learning_rate": 3.9764377805279616e-05, "loss": 4.0891, "step": 625152 }, { "epoch": 0.0, "learning_rate": 3.9755991857769096e-05, "loss": 4.0859, "step": 625664 }, { "epoch": 0.01, "learning_rate": 3.9747605910258575e-05, "loss": 4.0892, "step": 626176 }, { "epoch": 0.01, "learning_rate": 3.9739219962748055e-05, "loss": 4.0911, "step": 626688 }, { "epoch": 0.01, "learning_rate": 3.973083401523753e-05, "loss": 4.0896, "step": 627200 }, { "epoch": 0.01, "learning_rate": 3.972244806772701e-05, "loss": 4.0956, "step": 627712 }, { "epoch": 0.01, "learning_rate": 3.971406212021649e-05, "loss": 4.0836, "step": 628224 }, { "epoch": 0.01, "learning_rate": 3.970567617270597e-05, "loss": 4.0952, "step": 628736 }, { "epoch": 0.01, "learning_rate": 3.969730660399918e-05, "loss": 4.0883, "step": 629248 }, { "epoch": 0.01, "learning_rate": 3.968892065648866e-05, "loss": 4.0742, "step": 629760 }, { "epoch": 0.01, "learning_rate": 3.968053470897814e-05, "loss": 4.0819, "step": 630272 }, { "epoch": 0.01, "learning_rate": 3.967214876146762e-05, "loss": 4.0768, "step": 630784 }, { "epoch": 0.01, "learning_rate": 3.96637628139571e-05, "loss": 4.0854, "step": 631296 }, { "epoch": 0.01, "learning_rate": 3.9655376866446584e-05, "loss": 4.0892, "step": 631808 }, { "epoch": 0.01, "learning_rate": 3.964700729773979e-05, "loss": 4.0858, "step": 632320 }, { "epoch": 0.01, "learning_rate": 3.963862135022927e-05, "loss": 4.085, "step": 632832 }, { "epoch": 0.01, "learning_rate": 3.963023540271875e-05, "loss": 4.0933, "step": 633344 }, { "epoch": 0.01, "learning_rate": 3.962184945520823e-05, "loss": 4.0891, "step": 633856 }, { "epoch": 0.01, "learning_rate": 3.961346350769771e-05, "loss": 4.0928, "step": 634368 }, { "epoch": 0.01, "learning_rate": 3.960509393899092e-05, "loss": 4.0843, "step": 634880 }, { "epoch": 0.01, "learning_rate": 3.95967079914804e-05, "loss": 4.0564, "step": 635392 }, { "epoch": 0.01, "learning_rate": 3.958832204396988e-05, "loss": 4.1052, "step": 635904 }, { "epoch": 0.01, "learning_rate": 3.957993609645936e-05, "loss": 4.0783, "step": 636416 }, { "epoch": 0.01, "learning_rate": 3.957155014894884e-05, "loss": 4.0838, "step": 636928 }, { "epoch": 0.01, "learning_rate": 3.956316420143832e-05, "loss": 4.0789, "step": 637440 }, { "epoch": 0.01, "learning_rate": 3.955479463273154e-05, "loss": 4.0776, "step": 637952 }, { "epoch": 0.01, "learning_rate": 3.954640868522102e-05, "loss": 4.0745, "step": 638464 }, { "epoch": 0.01, "learning_rate": 3.95380227377105e-05, "loss": 4.071, "step": 638976 }, { "epoch": 0.01, "learning_rate": 3.952963679019998e-05, "loss": 4.0814, "step": 639488 }, { "epoch": 0.01, "learning_rate": 3.952125084268946e-05, "loss": 4.0755, "step": 640000 }, { "epoch": 0.01, "learning_rate": 3.951286489517894e-05, "loss": 4.0961, "step": 640512 }, { "epoch": 0.01, "learning_rate": 3.950449532647215e-05, "loss": 4.077, "step": 641024 }, { "epoch": 0.01, "learning_rate": 3.9496125757765356e-05, "loss": 4.0697, "step": 641536 }, { "epoch": 0.01, "learning_rate": 3.9487739810254836e-05, "loss": 4.0912, "step": 642048 }, { "epoch": 0.01, "learning_rate": 3.9479353862744316e-05, "loss": 4.069, "step": 642560 }, { "epoch": 0.01, "learning_rate": 3.9470967915233796e-05, "loss": 4.0723, "step": 643072 }, { "epoch": 0.01, "learning_rate": 3.9462581967723276e-05, "loss": 4.0857, "step": 643584 }, { "epoch": 0.01, "learning_rate": 3.9454196020212756e-05, "loss": 4.0861, "step": 644096 }, { "epoch": 0.01, "learning_rate": 3.9445810072702235e-05, "loss": 4.0732, "step": 644608 }, { "epoch": 0.01, "learning_rate": 3.9437424125191715e-05, "loss": 4.0715, "step": 645120 }, { "epoch": 0.01, "learning_rate": 3.9429038177681195e-05, "loss": 4.0626, "step": 645632 }, { "epoch": 0.01, "learning_rate": 3.9420652230170675e-05, "loss": 4.0785, "step": 646144 }, { "epoch": 0.01, "learning_rate": 3.9412266282660155e-05, "loss": 4.0946, "step": 646656 }, { "epoch": 0.01, "learning_rate": 3.9403880335149635e-05, "loss": 4.0782, "step": 647168 }, { "epoch": 0.01, "learning_rate": 3.9395510766442844e-05, "loss": 4.0838, "step": 647680 }, { "epoch": 0.01, "learning_rate": 3.9387124818932324e-05, "loss": 4.0867, "step": 648192 }, { "epoch": 0.01, "learning_rate": 3.9378738871421804e-05, "loss": 4.0944, "step": 648704 }, { "epoch": 0.01, "learning_rate": 3.937036930271501e-05, "loss": 4.0722, "step": 649216 }, { "epoch": 0.01, "learning_rate": 3.936198335520449e-05, "loss": 4.085, "step": 649728 }, { "epoch": 0.01, "learning_rate": 3.935359740769397e-05, "loss": 4.0759, "step": 650240 }, { "epoch": 0.01, "learning_rate": 3.934521146018345e-05, "loss": 4.0771, "step": 650752 }, { "epoch": 0.01, "learning_rate": 3.933682551267294e-05, "loss": 4.0752, "step": 651264 }, { "epoch": 0.01, "learning_rate": 3.932843956516242e-05, "loss": 4.084, "step": 651776 }, { "epoch": 0.01, "learning_rate": 3.93200536176519e-05, "loss": 4.0797, "step": 652288 }, { "epoch": 0.01, "learning_rate": 3.931168404894511e-05, "loss": 4.0895, "step": 652800 }, { "epoch": 0.01, "learning_rate": 3.930329810143459e-05, "loss": 4.0727, "step": 653312 }, { "epoch": 0.01, "learning_rate": 3.92949285327278e-05, "loss": 4.0725, "step": 653824 }, { "epoch": 0.01, "learning_rate": 3.928654258521728e-05, "loss": 4.0836, "step": 654336 }, { "epoch": 0.01, "learning_rate": 3.927815663770676e-05, "loss": 4.0777, "step": 654848 }, { "epoch": 0.01, "learning_rate": 3.926977069019624e-05, "loss": 4.0676, "step": 655360 }, { "epoch": 0.01, "learning_rate": 3.926140112148945e-05, "loss": 4.0802, "step": 655872 }, { "epoch": 0.02, "learning_rate": 3.925301517397893e-05, "loss": 4.0783, "step": 656384 }, { "epoch": 0.02, "learning_rate": 3.924462922646841e-05, "loss": 4.0841, "step": 656896 }, { "epoch": 0.02, "learning_rate": 3.9236243278957894e-05, "loss": 4.0752, "step": 657408 }, { "epoch": 0.02, "learning_rate": 3.9227857331447374e-05, "loss": 4.0659, "step": 657920 }, { "epoch": 0.02, "learning_rate": 3.9219471383936854e-05, "loss": 4.0899, "step": 658432 }, { "epoch": 0.02, "learning_rate": 3.9211085436426334e-05, "loss": 4.0811, "step": 658944 }, { "epoch": 0.02, "learning_rate": 3.9202699488915813e-05, "loss": 4.0767, "step": 659456 }, { "epoch": 0.02, "learning_rate": 3.9194313541405293e-05, "loss": 4.0691, "step": 659968 }, { "epoch": 0.02, "learning_rate": 3.918592759389477e-05, "loss": 4.0706, "step": 660480 }, { "epoch": 0.02, "learning_rate": 3.917754164638425e-05, "loss": 4.0687, "step": 660992 }, { "epoch": 0.02, "learning_rate": 3.916917207767746e-05, "loss": 4.0807, "step": 661504 }, { "epoch": 0.02, "learning_rate": 3.916078613016694e-05, "loss": 4.0869, "step": 662016 }, { "epoch": 0.02, "learning_rate": 3.915240018265642e-05, "loss": 4.0762, "step": 662528 }, { "epoch": 0.02, "learning_rate": 3.9144014235145896e-05, "loss": 4.0715, "step": 663040 }, { "epoch": 0.02, "learning_rate": 3.9135628287635375e-05, "loss": 4.0637, "step": 663552 }, { "epoch": 0.02, "learning_rate": 3.912725871892859e-05, "loss": 4.0642, "step": 664064 }, { "epoch": 0.02, "learning_rate": 3.911887277141808e-05, "loss": 4.0682, "step": 664576 }, { "epoch": 0.02, "learning_rate": 3.911048682390755e-05, "loss": 4.0586, "step": 665088 }, { "epoch": 0.02, "learning_rate": 3.910210087639703e-05, "loss": 4.0786, "step": 665600 }, { "epoch": 0.02, "learning_rate": 3.909371492888651e-05, "loss": 4.0658, "step": 666112 }, { "epoch": 0.02, "learning_rate": 3.908534536017973e-05, "loss": 4.0698, "step": 666624 }, { "epoch": 0.02, "learning_rate": 3.90769594126692e-05, "loss": 4.0653, "step": 667136 }, { "epoch": 0.02, "learning_rate": 3.906857346515868e-05, "loss": 4.0752, "step": 667648 }, { "epoch": 0.02, "learning_rate": 3.906018751764816e-05, "loss": 4.0795, "step": 668160 }, { "epoch": 0.02, "learning_rate": 3.905180157013764e-05, "loss": 4.0684, "step": 668672 }, { "epoch": 0.02, "learning_rate": 3.904341562262712e-05, "loss": 4.0867, "step": 669184 }, { "epoch": 0.02, "learning_rate": 3.903504605392033e-05, "loss": 4.0877, "step": 669696 }, { "epoch": 0.02, "learning_rate": 3.9026660106409816e-05, "loss": 4.074, "step": 670208 }, { "epoch": 0.02, "learning_rate": 3.9018274158899296e-05, "loss": 4.0773, "step": 670720 }, { "epoch": 0.02, "learning_rate": 3.9009888211388776e-05, "loss": 4.0631, "step": 671232 }, { "epoch": 0.02, "learning_rate": 3.9001502263878256e-05, "loss": 4.0691, "step": 671744 }, { "epoch": 0.02, "learning_rate": 3.89931490739752e-05, "loss": 4.0783, "step": 672256 }, { "epoch": 0.02, "learning_rate": 3.8984763126464674e-05, "loss": 4.0781, "step": 672768 }, { "epoch": 0.02, "learning_rate": 3.8976377178954154e-05, "loss": 4.063, "step": 673280 }, { "epoch": 0.02, "learning_rate": 3.8967991231443634e-05, "loss": 4.0805, "step": 673792 }, { "epoch": 0.02, "learning_rate": 3.8959605283933114e-05, "loss": 4.0809, "step": 674304 }, { "epoch": 0.02, "learning_rate": 3.8951219336422594e-05, "loss": 4.0751, "step": 674816 }, { "epoch": 0.02, "learning_rate": 3.8942833388912074e-05, "loss": 4.0597, "step": 675328 }, { "epoch": 0.02, "learning_rate": 3.8934447441401554e-05, "loss": 4.0736, "step": 675840 }, { "epoch": 0.02, "learning_rate": 3.892607787269476e-05, "loss": 4.0637, "step": 676352 }, { "epoch": 0.02, "learning_rate": 3.891769192518425e-05, "loss": 4.0837, "step": 676864 }, { "epoch": 0.02, "learning_rate": 3.890930597767373e-05, "loss": 4.072, "step": 677376 }, { "epoch": 0.02, "learning_rate": 3.890092003016321e-05, "loss": 4.0767, "step": 677888 }, { "epoch": 0.02, "learning_rate": 3.889253408265269e-05, "loss": 4.0572, "step": 678400 }, { "epoch": 0.02, "learning_rate": 3.888414813514217e-05, "loss": 4.0873, "step": 678912 }, { "epoch": 0.02, "learning_rate": 3.887576218763165e-05, "loss": 4.0669, "step": 679424 }, { "epoch": 0.02, "learning_rate": 3.886737624012113e-05, "loss": 4.0796, "step": 679936 }, { "epoch": 0.02, "learning_rate": 3.885899029261061e-05, "loss": 4.0748, "step": 680448 }, { "epoch": 0.02, "learning_rate": 3.885060434510009e-05, "loss": 4.0691, "step": 680960 }, { "epoch": 0.02, "learning_rate": 3.884221839758956e-05, "loss": 4.0756, "step": 681472 }, { "epoch": 0.02, "learning_rate": 3.883383245007904e-05, "loss": 4.0859, "step": 681984 }, { "epoch": 0.02, "learning_rate": 3.882546288137226e-05, "loss": 4.0578, "step": 682496 }, { "epoch": 0.02, "learning_rate": 3.881707693386173e-05, "loss": 4.0748, "step": 683008 }, { "epoch": 0.02, "learning_rate": 3.880869098635122e-05, "loss": 4.0661, "step": 683520 }, { "epoch": 0.02, "learning_rate": 3.88003050388407e-05, "loss": 4.0667, "step": 684032 }, { "epoch": 0.02, "learning_rate": 3.8791935470133914e-05, "loss": 4.0664, "step": 684544 }, { "epoch": 0.02, "learning_rate": 3.878354952262339e-05, "loss": 4.0717, "step": 685056 }, { "epoch": 0.02, "learning_rate": 3.877516357511287e-05, "loss": 4.0721, "step": 685568 }, { "epoch": 0.02, "learning_rate": 3.876679400640608e-05, "loss": 4.069, "step": 686080 }, { "epoch": 0.02, "learning_rate": 3.8758408058895556e-05, "loss": 4.0768, "step": 686592 }, { "epoch": 0.03, "eval_loss": 4.089334011077881, "eval_runtime": 305.5375, "eval_samples_per_second": 1248.917, "eval_steps_per_second": 39.03, "step": 686880 } ], "logging_steps": 512, "max_steps": 3052726, "num_train_epochs": 9223372036854775807, "save_steps": 10, "total_flos": 2.8575914566039667e+17, "trial_name": null, "trial_params": null }