abhinavp's picture
Training in progress, epoch 1, checkpoint
1bdd935 verified
{
"best_metric": 4.312550067901611,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/pp-mod-subj/lstm/0/checkpoints/checkpoint-305276",
"epoch": 1.0250002784396635,
"eval_steps": 10,
"global_step": 305276,
"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": 10.8212,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 7.5833,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 7.0572,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 6.9837,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 6.9532,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 6.8624,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 6.7187,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 6.6081,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 6.5231,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 6.4374,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 6.3822,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 6.3146,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989936862987376e-05,
"loss": 6.2475,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989098268236324e-05,
"loss": 6.1734,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988259673485272e-05,
"loss": 6.1072,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.98742107873422e-05,
"loss": 6.0606,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986582483983168e-05,
"loss": 6.0118,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985743889232116e-05,
"loss": 5.9605,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984905294481064e-05,
"loss": 5.9258,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984066699730012e-05,
"loss": 5.8818,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.8523,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.982391148108281e-05,
"loss": 5.8137,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.981552553357229e-05,
"loss": 5.7773,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.980713958606178e-05,
"loss": 5.7553,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 5.7238,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790384069844466e-05,
"loss": 5.6962,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9781998122333946e-05,
"loss": 5.6734,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773612174823426e-05,
"loss": 5.6524,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 5.619,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756856658606115e-05,
"loss": 5.605,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748470711095595e-05,
"loss": 5.579,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.974008476358507e-05,
"loss": 5.5615,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731715194878284e-05,
"loss": 5.5501,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.9723329247367764e-05,
"loss": 5.5333,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.9714943299857244e-05,
"loss": 5.5129,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.9706557352346724e-05,
"loss": 5.5041,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969818778363994e-05,
"loss": 5.4898,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968980183612942e-05,
"loss": 5.4715,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.96814158886189e-05,
"loss": 5.4539,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967302994110837e-05,
"loss": 5.4452,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966464399359785e-05,
"loss": 5.4191,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965625804608733e-05,
"loss": 5.4201,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964787209857681e-05,
"loss": 5.391,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963950252987002e-05,
"loss": 5.3906,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.96311165823595e-05,
"loss": 5.3845,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962273063484898e-05,
"loss": 5.3753,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.961434468733847e-05,
"loss": 5.3496,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.9605991497435414e-05,
"loss": 5.3482,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.9597605549924894e-05,
"loss": 5.3439,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.9589219602414374e-05,
"loss": 5.3209,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958083365490385e-05,
"loss": 5.3069,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957244770739333e-05,
"loss": 5.3047,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956406175988281e-05,
"loss": 5.3114,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.955567581237229e-05,
"loss": 5.2782,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.954728986486177e-05,
"loss": 5.2988,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.953890391735125e-05,
"loss": 5.2592,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530534348644456e-05,
"loss": 5.2698,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.9522148401133936e-05,
"loss": 5.2482,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951376245362342e-05,
"loss": 5.2445,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.95053765061129e-05,
"loss": 5.2362,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949699055860238e-05,
"loss": 5.2305,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948860461109186e-05,
"loss": 5.2104,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.948023504238507e-05,
"loss": 5.2179,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947184909487455e-05,
"loss": 5.2004,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946346314736403e-05,
"loss": 5.2091,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945507719985351e-05,
"loss": 5.19,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944670763114672e-05,
"loss": 5.1804,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.94383216836362e-05,
"loss": 5.1635,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942995211492941e-05,
"loss": 5.1712,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942156616741889e-05,
"loss": 5.165,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.941318021990837e-05,
"loss": 5.1462,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404794272397856e-05,
"loss": 5.1487,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396408324887336e-05,
"loss": 5.14,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388022377376816e-05,
"loss": 5.1364,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379636429866296e-05,
"loss": 5.1337,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371250482355776e-05,
"loss": 5.1279,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362880913648985e-05,
"loss": 5.114,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.9354494966138465e-05,
"loss": 5.0973,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.9346109018627945e-05,
"loss": 5.1051,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.9337723071117425e-05,
"loss": 5.0962,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.9329337123606905e-05,
"loss": 5.0985,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.932095117609638e-05,
"loss": 5.0895,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.931256522858586e-05,
"loss": 5.0805,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.9304195659879074e-05,
"loss": 5.0587,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.9295809712368554e-05,
"loss": 5.0656,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.9287423764858034e-05,
"loss": 5.067,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.9279037817347514e-05,
"loss": 5.0617,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.9270651869836994e-05,
"loss": 5.0511,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.9262265922326474e-05,
"loss": 5.0447,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925391273242342e-05,
"loss": 5.0329,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.92455267849129e-05,
"loss": 5.0276,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923714083740238e-05,
"loss": 5.0249,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922875488989185e-05,
"loss": 5.0319,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.922038532118507e-05,
"loss": 5.0224,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921199937367455e-05,
"loss": 4.9982,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920361342616403e-05,
"loss": 5.0003,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919522747865351e-05,
"loss": 5.0063,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918684153114299e-05,
"loss": 5.0023,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.917845558363247e-05,
"loss": 4.9909,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.917006963612195e-05,
"loss": 4.9903,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.916168368861143e-05,
"loss": 4.978,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.915329774110091e-05,
"loss": 4.9765,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914491179359039e-05,
"loss": 4.9828,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.913652584607987e-05,
"loss": 4.978,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.9128156277373076e-05,
"loss": 4.952,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.9119770329862556e-05,
"loss": 4.9629,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.9111384382352036e-05,
"loss": 4.9433,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.9102998434841516e-05,
"loss": 4.947,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.9094612487330996e-05,
"loss": 4.9444,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.9086226539820476e-05,
"loss": 4.9349,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907785697111369e-05,
"loss": 4.9321,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.906947102360317e-05,
"loss": 4.9225,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906108507609265e-05,
"loss": 4.922,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905269912858213e-05,
"loss": 4.9196,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904432955987534e-05,
"loss": 4.9309,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903594361236482e-05,
"loss": 4.907,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.90275576648543e-05,
"loss": 4.8897,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.901917171734378e-05,
"loss": 4.9012,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.901078576983326e-05,
"loss": 4.9114,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.900239982232274e-05,
"loss": 4.8947,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.899403025361595e-05,
"loss": 4.9021,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985660684909166e-05,
"loss": 4.8903,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977274737398646e-05,
"loss": 4.8903,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968888789888125e-05,
"loss": 4.8759,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960502842377605e-05,
"loss": 4.8793,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952116894867085e-05,
"loss": 4.874,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943730947356565e-05,
"loss": 4.8775,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.893534499984604e-05,
"loss": 4.8567,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.892695905233552e-05,
"loss": 4.8656,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.8918573104825e-05,
"loss": 4.8632,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.8910203536118214e-05,
"loss": 4.8488,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.890181758860769e-05,
"loss": 4.8573,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.889343164109717e-05,
"loss": 4.8501,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888504569358665e-05,
"loss": 4.8548,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.8876659746076134e-05,
"loss": 4.8508,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.8868273798565614e-05,
"loss": 4.8334,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.8859887851055094e-05,
"loss": 4.828,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.88515182823483e-05,
"loss": 4.828,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884314871364151e-05,
"loss": 4.833,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883476276613099e-05,
"loss": 4.8406,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882637681862047e-05,
"loss": 4.8283,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881799087110995e-05,
"loss": 4.8189,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.880960492359943e-05,
"loss": 4.8147,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880121897608891e-05,
"loss": 4.8139,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879283302857839e-05,
"loss": 4.81,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878444708106787e-05,
"loss": 4.8075,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877607751236109e-05,
"loss": 4.8196,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.87677079436543e-05,
"loss": 4.8047,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875932199614378e-05,
"loss": 4.7968,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.875093604863326e-05,
"loss": 4.7923,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.810235500335693,
"eval_runtime": 552.8952,
"eval_samples_per_second": 690.169,
"eval_steps_per_second": 21.568,
"step": 76319
},
{
"epoch": 1.0,
"learning_rate": 4.8742566479926466e-05,
"loss": 4.8064,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.8734180532415946e-05,
"loss": 4.7989,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.8725794584905426e-05,
"loss": 4.7829,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.8717408637394906e-05,
"loss": 4.7851,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.8709022689884386e-05,
"loss": 4.7746,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.8700636742373866e-05,
"loss": 4.7713,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.8692250794863346e-05,
"loss": 4.768,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.8683864847352826e-05,
"loss": 4.7704,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.867549527864604e-05,
"loss": 4.766,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.866710933113552e-05,
"loss": 4.7674,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.8658723383625e-05,
"loss": 4.7656,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865033743611448e-05,
"loss": 4.7718,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.864195148860396e-05,
"loss": 4.7582,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.863358191989717e-05,
"loss": 4.7493,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.862519597238665e-05,
"loss": 4.7476,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.861681002487613e-05,
"loss": 4.7293,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.860842407736561e-05,
"loss": 4.742,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860005450865882e-05,
"loss": 4.7399,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.85916685611483e-05,
"loss": 4.7377,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.858328261363778e-05,
"loss": 4.7475,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.857489666612726e-05,
"loss": 4.735,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.856651071861674e-05,
"loss": 4.7337,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.8558124771106226e-05,
"loss": 4.736,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.85497388235957e-05,
"loss": 4.7317,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.8541369254888915e-05,
"loss": 4.7214,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.8532983307378395e-05,
"loss": 4.7209,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.8524597359867875e-05,
"loss": 4.7255,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.851621141235735e-05,
"loss": 4.7128,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.850782546484683e-05,
"loss": 4.7133,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.849943951733631e-05,
"loss": 4.6998,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.849105356982579e-05,
"loss": 4.703,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.848266762231527e-05,
"loss": 4.7132,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847429805360848e-05,
"loss": 4.7053,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.846594486370543e-05,
"loss": 4.7041,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845755891619491e-05,
"loss": 4.7007,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844917296868439e-05,
"loss": 4.704,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.844078702117387e-05,
"loss": 4.6991,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843240107366335e-05,
"loss": 4.6963,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842401512615282e-05,
"loss": 4.697,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.84156291786423e-05,
"loss": 4.6842,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840724323113178e-05,
"loss": 4.6882,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.839885728362126e-05,
"loss": 4.6749,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839047133611074e-05,
"loss": 4.6808,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.838210176740395e-05,
"loss": 4.6897,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.837371581989343e-05,
"loss": 4.6873,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.836532987238292e-05,
"loss": 4.673,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.83569439248724e-05,
"loss": 4.6754,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.834855797736188e-05,
"loss": 4.6796,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.834017202985136e-05,
"loss": 4.6585,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.833178608234084e-05,
"loss": 4.6583,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.832340013483032e-05,
"loss": 4.6611,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.8315030566123526e-05,
"loss": 4.6742,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.8306644618613006e-05,
"loss": 4.6483,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.8298258671102486e-05,
"loss": 4.6754,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.8289872723591966e-05,
"loss": 4.6436,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.8281503154885175e-05,
"loss": 4.6568,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.8273133586178384e-05,
"loss": 4.6493,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.826474763866787e-05,
"loss": 4.6525,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.825636169115735e-05,
"loss": 4.6438,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.824797574364683e-05,
"loss": 4.6482,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.823958979613631e-05,
"loss": 4.6368,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.823120384862579e-05,
"loss": 4.6451,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.8222834279919e-05,
"loss": 4.6366,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.821444833240848e-05,
"loss": 4.6434,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.820606238489796e-05,
"loss": 4.635,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.819767643738744e-05,
"loss": 4.6322,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.818929048987692e-05,
"loss": 4.6151,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.81809045423664e-05,
"loss": 4.6404,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.817253497365961e-05,
"loss": 4.6284,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.816414902614909e-05,
"loss": 4.6173,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.815576307863857e-05,
"loss": 4.6271,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.814737713112805e-05,
"loss": 4.6216,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.8139007562421265e-05,
"loss": 4.623,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.8130621614910745e-05,
"loss": 4.6289,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.8122235667400224e-05,
"loss": 4.6274,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.8113849719889704e-05,
"loss": 4.6135,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.8105463772379184e-05,
"loss": 4.6047,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.809707782486866e-05,
"loss": 4.6119,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.8088708256161873e-05,
"loss": 4.6131,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808032230865135e-05,
"loss": 4.6206,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.8071936361140827e-05,
"loss": 4.6123,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.8063550413630307e-05,
"loss": 4.6078,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.8055164466119786e-05,
"loss": 4.5875,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.8046794897413e-05,
"loss": 4.599,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803840894990248e-05,
"loss": 4.6039,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.803002300239196e-05,
"loss": 4.6011,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.802163705488144e-05,
"loss": 4.6059,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.801326748617466e-05,
"loss": 4.5966,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.800488153866413e-05,
"loss": 4.5867,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.799649559115361e-05,
"loss": 4.5921,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.798812602244683e-05,
"loss": 4.5863,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.79797400749363e-05,
"loss": 4.5929,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.797135412742578e-05,
"loss": 4.5947,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.796296817991526e-05,
"loss": 4.5717,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.795458223240474e-05,
"loss": 4.5739,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.794619628489423e-05,
"loss": 4.5843,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.7937826716187436e-05,
"loss": 4.5896,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.7929440768676916e-05,
"loss": 4.5759,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.7921054821166396e-05,
"loss": 4.5821,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.7912668873655876e-05,
"loss": 4.5747,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.7904282926145356e-05,
"loss": 4.5727,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.7895896978634836e-05,
"loss": 4.5819,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.7887511031124316e-05,
"loss": 4.5783,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.7879125083613796e-05,
"loss": 4.56,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.7870739136103276e-05,
"loss": 4.5745,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.7862353188592756e-05,
"loss": 4.5556,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.7853967241082236e-05,
"loss": 4.5593,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.7845581293571715e-05,
"loss": 4.5654,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.7837211724864925e-05,
"loss": 4.5552,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.782884215615814e-05,
"loss": 4.5559,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.782045620864762e-05,
"loss": 4.5508,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.78120702611371e-05,
"loss": 4.5517,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.780370069243031e-05,
"loss": 4.5506,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.779531474491979e-05,
"loss": 4.5659,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.778692879740927e-05,
"loss": 4.547,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.777854284989875e-05,
"loss": 4.5376,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.777015690238823e-05,
"loss": 4.5441,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.776177095487771e-05,
"loss": 4.552,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775340138617092e-05,
"loss": 4.5468,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.77450154386604e-05,
"loss": 4.5502,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773662949114988e-05,
"loss": 4.5462,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.772824354363936e-05,
"loss": 4.5486,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.7719857596128845e-05,
"loss": 4.539,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.771147164861832e-05,
"loss": 4.5351,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.77030857011078e-05,
"loss": 4.5392,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.769469975359728e-05,
"loss": 4.5443,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.768631380608676e-05,
"loss": 4.5291,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.767792785857624e-05,
"loss": 4.5335,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766954191106572e-05,
"loss": 4.5462,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766117234235893e-05,
"loss": 4.5204,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765278639484841e-05,
"loss": 4.5349,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764440044733789e-05,
"loss": 4.5302,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.7636030878631096e-05,
"loss": 4.5409,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762764493112058e-05,
"loss": 4.5333,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761925898361006e-05,
"loss": 4.5209,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.761087303609954e-05,
"loss": 4.5195,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.760248708858902e-05,
"loss": 4.5187,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.75941011410785e-05,
"loss": 4.5281,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.758571519356798e-05,
"loss": 4.535,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.757732924605746e-05,
"loss": 4.5289,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.756895967735067e-05,
"loss": 4.5147,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.756057372984015e-05,
"loss": 4.5162,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.755218778232963e-05,
"loss": 4.518,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.754381821362284e-05,
"loss": 4.5166,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.753543226611232e-05,
"loss": 4.5138,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.75270463186018e-05,
"loss": 4.5307,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.751866037109128e-05,
"loss": 4.5096,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.751027442358077e-05,
"loss": 4.5127,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.750188847607025e-05,
"loss": 4.5063,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.530740261077881,
"eval_runtime": 587.9687,
"eval_samples_per_second": 648.999,
"eval_steps_per_second": 20.282,
"step": 152638
},
{
"epoch": 0.0,
"learning_rate": 4.749350252855973e-05,
"loss": 4.522,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.748511658104921e-05,
"loss": 4.5171,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.747673063353868e-05,
"loss": 4.5035,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.746834468602816e-05,
"loss": 4.5042,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.745995873851764e-05,
"loss": 4.4969,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.745157279100712e-05,
"loss": 4.4991,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.74431868434966e-05,
"loss": 4.4972,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.743480089598608e-05,
"loss": 4.4973,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.742641494847556e-05,
"loss": 4.4959,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.741804537976877e-05,
"loss": 4.5006,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.740965943225825e-05,
"loss": 4.5014,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.7401273484747736e-05,
"loss": 4.5065,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.7392887537237216e-05,
"loss": 4.4941,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.7384501589726696e-05,
"loss": 4.4843,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.7376115642216176e-05,
"loss": 4.4911,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.7367729694705656e-05,
"loss": 4.47,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.7359343747195135e-05,
"loss": 4.4869,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.7350957799684615e-05,
"loss": 4.4835,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.7342571852174095e-05,
"loss": 4.4828,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.733418590466357e-05,
"loss": 4.4979,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.732579995715305e-05,
"loss": 4.4854,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.731741400964253e-05,
"loss": 4.4853,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.730902806213201e-05,
"loss": 4.4879,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.730064211462149e-05,
"loss": 4.4815,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.729225616711097e-05,
"loss": 4.4794,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.7283886598404184e-05,
"loss": 4.4756,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.7275500650893664e-05,
"loss": 4.4805,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.726713108218687e-05,
"loss": 4.4708,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.725874513467635e-05,
"loss": 4.4751,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.725035918716583e-05,
"loss": 4.4601,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.724197323965531e-05,
"loss": 4.468,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.723358729214479e-05,
"loss": 4.4786,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.722520134463427e-05,
"loss": 4.4658,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.721681539712375e-05,
"loss": 4.4717,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.720842944961323e-05,
"loss": 4.4676,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.720007625971017e-05,
"loss": 4.4696,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.719169031219965e-05,
"loss": 4.4722,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.718332074349287e-05,
"loss": 4.4701,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.717493479598235e-05,
"loss": 4.4688,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.716654884847183e-05,
"loss": 4.4568,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.715816290096131e-05,
"loss": 4.4651,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.714977695345079e-05,
"loss": 4.4513,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.714139100594027e-05,
"loss": 4.466,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.713300505842975e-05,
"loss": 4.4636,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.712461911091923e-05,
"loss": 4.4667,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.7116249542212436e-05,
"loss": 4.4515,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.7107863594701916e-05,
"loss": 4.4538,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.7099477647191396e-05,
"loss": 4.4628,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.7091091699680876e-05,
"loss": 4.4426,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.7082705752170356e-05,
"loss": 4.4466,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.707433618346357e-05,
"loss": 4.4435,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.706595023595305e-05,
"loss": 4.4636,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.705756428844253e-05,
"loss": 4.4391,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704917834093201e-05,
"loss": 4.4653,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.704080877222522e-05,
"loss": 4.435,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.70324228247147e-05,
"loss": 4.4435,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.702403687720418e-05,
"loss": 4.446,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.701565092969366e-05,
"loss": 4.4457,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.700726498218314e-05,
"loss": 4.4407,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.699887903467262e-05,
"loss": 4.4506,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.69904930871621e-05,
"loss": 4.4256,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.698212351845531e-05,
"loss": 4.4424,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.697373757094479e-05,
"loss": 4.4342,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.6965351623434276e-05,
"loss": 4.4449,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.6956965675923756e-05,
"loss": 4.4329,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.694857972841323e-05,
"loss": 4.4342,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.6940210159706445e-05,
"loss": 4.417,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.6931824212195925e-05,
"loss": 4.4441,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.69234382646854e-05,
"loss": 4.434,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.691505231717488e-05,
"loss": 4.4253,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.690666636966436e-05,
"loss": 4.4313,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.689828042215384e-05,
"loss": 4.4304,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.688989447464332e-05,
"loss": 4.4287,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.68815085271328e-05,
"loss": 4.4382,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.6873138958426014e-05,
"loss": 4.4371,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.686476938971923e-05,
"loss": 4.4265,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.68563834422087e-05,
"loss": 4.4175,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.684799749469818e-05,
"loss": 4.4224,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.683961154718766e-05,
"loss": 4.4291,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.683122559967714e-05,
"loss": 4.4324,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.682283965216662e-05,
"loss": 4.4253,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.68144537046561e-05,
"loss": 4.4272,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.680606775714558e-05,
"loss": 4.4052,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.679769818843879e-05,
"loss": 4.4169,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.6789328619732e-05,
"loss": 4.415,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.678094267222148e-05,
"loss": 4.4199,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.677255672471097e-05,
"loss": 4.427,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.676417077720045e-05,
"loss": 4.4174,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.675578482968993e-05,
"loss": 4.4057,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.674739888217941e-05,
"loss": 4.416,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.6739029313472616e-05,
"loss": 4.4084,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.6730643365962096e-05,
"loss": 4.4158,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.6722257418451576e-05,
"loss": 4.4149,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.6713871470941056e-05,
"loss": 4.3973,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.6705485523430536e-05,
"loss": 4.4005,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.6697115954723745e-05,
"loss": 4.4073,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.6688730007213225e-05,
"loss": 4.4142,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.6680344059702705e-05,
"loss": 4.4053,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.6671958112192185e-05,
"loss": 4.4133,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.6663572164681665e-05,
"loss": 4.4,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.6655186217171145e-05,
"loss": 4.4021,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664681664846436e-05,
"loss": 4.4096,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663843070095384e-05,
"loss": 4.4077,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.663004475344332e-05,
"loss": 4.3933,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.66216588059328e-05,
"loss": 4.41,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.661327285842228e-05,
"loss": 4.3849,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.660488691091176e-05,
"loss": 4.3895,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.6596500963401234e-05,
"loss": 4.403,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.6588115015890714e-05,
"loss": 4.3871,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.657974544718393e-05,
"loss": 4.3981,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.657135949967341e-05,
"loss": 4.3872,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.656297355216288e-05,
"loss": 4.3864,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.655458760465237e-05,
"loss": 4.3857,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.654620165714185e-05,
"loss": 4.4062,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.653781570963133e-05,
"loss": 4.3855,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.652944614092454e-05,
"loss": 4.3807,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.652106019341402e-05,
"loss": 4.3785,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.65126742459035e-05,
"loss": 4.388,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.650428829839298e-05,
"loss": 4.3934,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.649591872968619e-05,
"loss": 4.3904,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.648753278217567e-05,
"loss": 4.3865,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.647914683466515e-05,
"loss": 4.3892,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.647076088715463e-05,
"loss": 4.3829,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.646237493964411e-05,
"loss": 4.3845,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.645398899213359e-05,
"loss": 4.3823,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.644560304462307e-05,
"loss": 4.3867,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.6437217097112554e-05,
"loss": 4.3766,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.642884752840576e-05,
"loss": 4.3788,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.642046158089524e-05,
"loss": 4.3918,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.641209201218845e-05,
"loss": 4.368,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.640370606467793e-05,
"loss": 4.3769,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.639532011716741e-05,
"loss": 4.3787,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.638693416965689e-05,
"loss": 4.3915,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.637854822214637e-05,
"loss": 4.3809,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.637016227463585e-05,
"loss": 4.3763,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.636177632712533e-05,
"loss": 4.3662,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.635339037961481e-05,
"loss": 4.3688,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.634500443210429e-05,
"loss": 4.3784,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.633661848459377e-05,
"loss": 4.3859,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.632823253708325e-05,
"loss": 4.3803,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.631984658957273e-05,
"loss": 4.37,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.631147702086595e-05,
"loss": 4.3667,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.630309107335542e-05,
"loss": 4.3788,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.62947051258449e-05,
"loss": 4.3685,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.628631917833438e-05,
"loss": 4.3711,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.6277949609627597e-05,
"loss": 4.3831,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626956366211707e-05,
"loss": 4.3659,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.626117771460655e-05,
"loss": 4.3702,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625279176709603e-05,
"loss": 4.365,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 4.396077632904053,
"eval_runtime": 542.5284,
"eval_samples_per_second": 703.357,
"eval_steps_per_second": 21.98,
"step": 228957
},
{
"epoch": 1.0,
"learning_rate": 4.6244422198389246e-05,
"loss": 4.3755,
"step": 229376
},
{
"epoch": 1.0,
"learning_rate": 4.623605262968246e-05,
"loss": 4.3765,
"step": 229888
},
{
"epoch": 1.0,
"learning_rate": 4.622766668217194e-05,
"loss": 4.3623,
"step": 230400
},
{
"epoch": 1.0,
"learning_rate": 4.621928073466142e-05,
"loss": 4.3622,
"step": 230912
},
{
"epoch": 1.0,
"learning_rate": 4.6210894787150895e-05,
"loss": 4.3602,
"step": 231424
},
{
"epoch": 1.0,
"learning_rate": 4.6202508839640374e-05,
"loss": 4.3561,
"step": 231936
},
{
"epoch": 1.0,
"learning_rate": 4.619413927093359e-05,
"loss": 4.3598,
"step": 232448
},
{
"epoch": 1.0,
"learning_rate": 4.618575332342307e-05,
"loss": 4.3564,
"step": 232960
},
{
"epoch": 1.0,
"learning_rate": 4.6177367375912543e-05,
"loss": 4.3584,
"step": 233472
},
{
"epoch": 1.0,
"learning_rate": 4.616899780720576e-05,
"loss": 4.3672,
"step": 233984
},
{
"epoch": 1.0,
"learning_rate": 4.616061185969524e-05,
"loss": 4.3623,
"step": 234496
},
{
"epoch": 1.0,
"learning_rate": 4.615222591218472e-05,
"loss": 4.365,
"step": 235008
},
{
"epoch": 1.0,
"learning_rate": 4.61438399646742e-05,
"loss": 4.3591,
"step": 235520
},
{
"epoch": 1.0,
"learning_rate": 4.613545401716368e-05,
"loss": 4.352,
"step": 236032
},
{
"epoch": 1.0,
"learning_rate": 4.612706806965316e-05,
"loss": 4.3534,
"step": 236544
},
{
"epoch": 1.0,
"learning_rate": 4.611868212214264e-05,
"loss": 4.3371,
"step": 237056
},
{
"epoch": 1.0,
"learning_rate": 4.611029617463212e-05,
"loss": 4.3493,
"step": 237568
},
{
"epoch": 1.0,
"learning_rate": 4.61019102271216e-05,
"loss": 4.3495,
"step": 238080
},
{
"epoch": 1.0,
"learning_rate": 4.609352427961108e-05,
"loss": 4.3494,
"step": 238592
},
{
"epoch": 1.0,
"learning_rate": 4.608513833210056e-05,
"loss": 4.3631,
"step": 239104
},
{
"epoch": 1.0,
"learning_rate": 4.607675238459004e-05,
"loss": 4.3533,
"step": 239616
},
{
"epoch": 1.0,
"learning_rate": 4.606838281588325e-05,
"loss": 4.3557,
"step": 240128
},
{
"epoch": 1.0,
"learning_rate": 4.606001324717646e-05,
"loss": 4.3519,
"step": 240640
},
{
"epoch": 1.0,
"learning_rate": 4.605162729966594e-05,
"loss": 4.3478,
"step": 241152
},
{
"epoch": 1.0,
"learning_rate": 4.604324135215542e-05,
"loss": 4.347,
"step": 241664
},
{
"epoch": 1.0,
"learning_rate": 4.60348554046449e-05,
"loss": 4.3505,
"step": 242176
},
{
"epoch": 1.0,
"learning_rate": 4.602646945713438e-05,
"loss": 4.3468,
"step": 242688
},
{
"epoch": 1.0,
"learning_rate": 4.601809988842759e-05,
"loss": 4.3421,
"step": 243200
},
{
"epoch": 1.0,
"learning_rate": 4.60097303197208e-05,
"loss": 4.3435,
"step": 243712
},
{
"epoch": 1.01,
"learning_rate": 4.600134437221028e-05,
"loss": 4.333,
"step": 244224
},
{
"epoch": 1.01,
"learning_rate": 4.599295842469976e-05,
"loss": 4.3419,
"step": 244736
},
{
"epoch": 1.01,
"learning_rate": 4.598457247718924e-05,
"loss": 4.3485,
"step": 245248
},
{
"epoch": 1.01,
"learning_rate": 4.597618652967872e-05,
"loss": 4.3429,
"step": 245760
},
{
"epoch": 1.01,
"learning_rate": 4.59678005821682e-05,
"loss": 4.3427,
"step": 246272
},
{
"epoch": 1.01,
"learning_rate": 4.595941463465768e-05,
"loss": 4.3401,
"step": 246784
},
{
"epoch": 1.01,
"learning_rate": 4.595102868714716e-05,
"loss": 4.3455,
"step": 247296
},
{
"epoch": 1.01,
"learning_rate": 4.594264273963664e-05,
"loss": 4.3423,
"step": 247808
},
{
"epoch": 1.01,
"learning_rate": 4.593425679212612e-05,
"loss": 4.3506,
"step": 248320
},
{
"epoch": 1.01,
"learning_rate": 4.592588722341933e-05,
"loss": 4.3405,
"step": 248832
},
{
"epoch": 1.01,
"learning_rate": 4.591750127590882e-05,
"loss": 4.3335,
"step": 249344
},
{
"epoch": 1.01,
"learning_rate": 4.59091153283983e-05,
"loss": 4.3399,
"step": 249856
},
{
"epoch": 1.01,
"learning_rate": 4.590072938088778e-05,
"loss": 4.3233,
"step": 250368
},
{
"epoch": 1.01,
"learning_rate": 4.589234343337726e-05,
"loss": 4.3439,
"step": 250880
},
{
"epoch": 1.01,
"learning_rate": 4.588395748586673e-05,
"loss": 4.3425,
"step": 251392
},
{
"epoch": 1.01,
"learning_rate": 4.5875587917159946e-05,
"loss": 4.3412,
"step": 251904
},
{
"epoch": 1.01,
"learning_rate": 4.5867201969649426e-05,
"loss": 4.3304,
"step": 252416
},
{
"epoch": 1.01,
"learning_rate": 4.5858816022138906e-05,
"loss": 4.3311,
"step": 252928
},
{
"epoch": 1.01,
"learning_rate": 4.585043007462838e-05,
"loss": 4.3427,
"step": 253440
},
{
"epoch": 1.01,
"learning_rate": 4.584204412711786e-05,
"loss": 4.32,
"step": 253952
},
{
"epoch": 1.01,
"learning_rate": 4.583365817960734e-05,
"loss": 4.3265,
"step": 254464
},
{
"epoch": 1.01,
"learning_rate": 4.582527223209682e-05,
"loss": 4.3256,
"step": 254976
},
{
"epoch": 1.01,
"learning_rate": 4.58168862845863e-05,
"loss": 4.3417,
"step": 255488
},
{
"epoch": 1.01,
"learning_rate": 4.5808516715879515e-05,
"loss": 4.3155,
"step": 256000
},
{
"epoch": 1.01,
"learning_rate": 4.5800130768368995e-05,
"loss": 4.3465,
"step": 256512
},
{
"epoch": 1.01,
"learning_rate": 4.5791761199662204e-05,
"loss": 4.318,
"step": 257024
},
{
"epoch": 1.01,
"learning_rate": 4.5783375252151684e-05,
"loss": 4.3191,
"step": 257536
},
{
"epoch": 1.01,
"learning_rate": 4.5774989304641164e-05,
"loss": 4.3321,
"step": 258048
},
{
"epoch": 1.01,
"learning_rate": 4.5766603357130644e-05,
"loss": 4.3194,
"step": 258560
},
{
"epoch": 1.01,
"learning_rate": 4.5758217409620124e-05,
"loss": 4.3317,
"step": 259072
},
{
"epoch": 1.01,
"learning_rate": 4.5749831462109604e-05,
"loss": 4.3333,
"step": 259584
},
{
"epoch": 1.01,
"learning_rate": 4.5741445514599084e-05,
"loss": 4.3132,
"step": 260096
},
{
"epoch": 1.01,
"learning_rate": 4.5733059567088564e-05,
"loss": 4.3205,
"step": 260608
},
{
"epoch": 1.01,
"learning_rate": 4.5724673619578044e-05,
"loss": 4.3232,
"step": 261120
},
{
"epoch": 1.01,
"learning_rate": 4.571630405087125e-05,
"loss": 4.3278,
"step": 261632
},
{
"epoch": 1.01,
"learning_rate": 4.570791810336074e-05,
"loss": 4.316,
"step": 262144
},
{
"epoch": 1.01,
"learning_rate": 4.569953215585022e-05,
"loss": 4.3201,
"step": 262656
},
{
"epoch": 1.01,
"learning_rate": 4.56911462083397e-05,
"loss": 4.3017,
"step": 263168
},
{
"epoch": 1.01,
"learning_rate": 4.568276026082918e-05,
"loss": 4.3306,
"step": 263680
},
{
"epoch": 1.01,
"learning_rate": 4.567439069212239e-05,
"loss": 4.3176,
"step": 264192
},
{
"epoch": 1.01,
"learning_rate": 4.566600474461187e-05,
"loss": 4.3104,
"step": 264704
},
{
"epoch": 1.01,
"learning_rate": 4.565761879710135e-05,
"loss": 4.3186,
"step": 265216
},
{
"epoch": 1.01,
"learning_rate": 4.564923284959083e-05,
"loss": 4.3178,
"step": 265728
},
{
"epoch": 1.01,
"learning_rate": 4.564086328088404e-05,
"loss": 4.3171,
"step": 266240
},
{
"epoch": 1.01,
"learning_rate": 4.563247733337352e-05,
"loss": 4.3219,
"step": 266752
},
{
"epoch": 1.01,
"learning_rate": 4.5624091385863e-05,
"loss": 4.328,
"step": 267264
},
{
"epoch": 1.01,
"learning_rate": 4.5615721817156206e-05,
"loss": 4.3149,
"step": 267776
},
{
"epoch": 1.01,
"learning_rate": 4.560733586964569e-05,
"loss": 4.3097,
"step": 268288
},
{
"epoch": 1.01,
"learning_rate": 4.559894992213517e-05,
"loss": 4.3124,
"step": 268800
},
{
"epoch": 1.01,
"learning_rate": 4.559056397462465e-05,
"loss": 4.3135,
"step": 269312
},
{
"epoch": 1.01,
"learning_rate": 4.558217802711413e-05,
"loss": 4.325,
"step": 269824
},
{
"epoch": 1.01,
"learning_rate": 4.557380845840734e-05,
"loss": 4.3174,
"step": 270336
},
{
"epoch": 1.01,
"learning_rate": 4.556542251089682e-05,
"loss": 4.3116,
"step": 270848
},
{
"epoch": 1.01,
"learning_rate": 4.55570365633863e-05,
"loss": 4.3003,
"step": 271360
},
{
"epoch": 1.01,
"learning_rate": 4.554865061587578e-05,
"loss": 4.307,
"step": 271872
},
{
"epoch": 1.01,
"learning_rate": 4.554026466836526e-05,
"loss": 4.3075,
"step": 272384
},
{
"epoch": 1.01,
"learning_rate": 4.553189509965847e-05,
"loss": 4.3119,
"step": 272896
},
{
"epoch": 1.01,
"learning_rate": 4.552350915214795e-05,
"loss": 4.312,
"step": 273408
},
{
"epoch": 1.01,
"learning_rate": 4.551512320463743e-05,
"loss": 4.3103,
"step": 273920
},
{
"epoch": 1.01,
"learning_rate": 4.550673725712691e-05,
"loss": 4.3019,
"step": 274432
},
{
"epoch": 1.02,
"learning_rate": 4.549835130961639e-05,
"loss": 4.3121,
"step": 274944
},
{
"epoch": 1.02,
"learning_rate": 4.548996536210587e-05,
"loss": 4.3028,
"step": 275456
},
{
"epoch": 1.02,
"learning_rate": 4.548157941459535e-05,
"loss": 4.3048,
"step": 275968
},
{
"epoch": 1.02,
"learning_rate": 4.547319346708483e-05,
"loss": 4.3085,
"step": 276480
},
{
"epoch": 1.02,
"learning_rate": 4.546482389837804e-05,
"loss": 4.2943,
"step": 276992
},
{
"epoch": 1.02,
"learning_rate": 4.545643795086752e-05,
"loss": 4.293,
"step": 277504
},
{
"epoch": 1.02,
"learning_rate": 4.5448052003357e-05,
"loss": 4.3089,
"step": 278016
},
{
"epoch": 1.02,
"learning_rate": 4.543966605584648e-05,
"loss": 4.3018,
"step": 278528
},
{
"epoch": 1.02,
"learning_rate": 4.543128010833596e-05,
"loss": 4.3075,
"step": 279040
},
{
"epoch": 1.02,
"learning_rate": 4.542289416082544e-05,
"loss": 4.3057,
"step": 279552
},
{
"epoch": 1.02,
"learning_rate": 4.541450821331492e-05,
"loss": 4.2974,
"step": 280064
},
{
"epoch": 1.02,
"learning_rate": 4.54061222658044e-05,
"loss": 4.2974,
"step": 280576
},
{
"epoch": 1.02,
"learning_rate": 4.539773631829388e-05,
"loss": 4.3064,
"step": 281088
},
{
"epoch": 1.02,
"learning_rate": 4.5389366749587095e-05,
"loss": 4.3058,
"step": 281600
},
{
"epoch": 1.02,
"learning_rate": 4.5380997180880304e-05,
"loss": 4.2891,
"step": 282112
},
{
"epoch": 1.02,
"learning_rate": 4.5372611233369784e-05,
"loss": 4.3072,
"step": 282624
},
{
"epoch": 1.02,
"learning_rate": 4.5364225285859264e-05,
"loss": 4.2809,
"step": 283136
},
{
"epoch": 1.02,
"learning_rate": 4.5355839338348744e-05,
"loss": 4.2901,
"step": 283648
},
{
"epoch": 1.02,
"learning_rate": 4.5347453390838224e-05,
"loss": 4.3013,
"step": 284160
},
{
"epoch": 1.02,
"learning_rate": 4.533908382213143e-05,
"loss": 4.2847,
"step": 284672
},
{
"epoch": 1.02,
"learning_rate": 4.533069787462091e-05,
"loss": 4.2987,
"step": 285184
},
{
"epoch": 1.02,
"learning_rate": 4.532231192711039e-05,
"loss": 4.2833,
"step": 285696
},
{
"epoch": 1.02,
"learning_rate": 4.531392597959987e-05,
"loss": 4.2822,
"step": 286208
},
{
"epoch": 1.02,
"learning_rate": 4.530554003208935e-05,
"loss": 4.2845,
"step": 286720
},
{
"epoch": 1.02,
"learning_rate": 4.529715408457883e-05,
"loss": 4.3069,
"step": 287232
},
{
"epoch": 1.02,
"learning_rate": 4.528876813706831e-05,
"loss": 4.2905,
"step": 287744
},
{
"epoch": 1.02,
"learning_rate": 4.528038218955779e-05,
"loss": 4.2798,
"step": 288256
},
{
"epoch": 1.02,
"learning_rate": 4.527201262085101e-05,
"loss": 4.2804,
"step": 288768
},
{
"epoch": 1.02,
"learning_rate": 4.526362667334049e-05,
"loss": 4.2896,
"step": 289280
},
{
"epoch": 1.02,
"learning_rate": 4.525524072582997e-05,
"loss": 4.2945,
"step": 289792
},
{
"epoch": 1.02,
"learning_rate": 4.524685477831945e-05,
"loss": 4.294,
"step": 290304
},
{
"epoch": 1.02,
"learning_rate": 4.523848520961266e-05,
"loss": 4.2845,
"step": 290816
},
{
"epoch": 1.02,
"learning_rate": 4.523009926210214e-05,
"loss": 4.2954,
"step": 291328
},
{
"epoch": 1.02,
"learning_rate": 4.522171331459162e-05,
"loss": 4.2849,
"step": 291840
},
{
"epoch": 1.02,
"learning_rate": 4.52133273670811e-05,
"loss": 4.2873,
"step": 292352
},
{
"epoch": 1.02,
"learning_rate": 4.520494141957057e-05,
"loss": 4.2846,
"step": 292864
},
{
"epoch": 1.02,
"learning_rate": 4.519657185086379e-05,
"loss": 4.289,
"step": 293376
},
{
"epoch": 1.02,
"learning_rate": 4.518818590335327e-05,
"loss": 4.2802,
"step": 293888
},
{
"epoch": 1.02,
"learning_rate": 4.517979995584275e-05,
"loss": 4.2825,
"step": 294400
},
{
"epoch": 1.02,
"learning_rate": 4.517141400833223e-05,
"loss": 4.2937,
"step": 294912
},
{
"epoch": 1.02,
"learning_rate": 4.516304443962544e-05,
"loss": 4.274,
"step": 295424
},
{
"epoch": 1.02,
"learning_rate": 4.515465849211492e-05,
"loss": 4.2833,
"step": 295936
},
{
"epoch": 1.02,
"learning_rate": 4.51462725446044e-05,
"loss": 4.2867,
"step": 296448
},
{
"epoch": 1.02,
"learning_rate": 4.5137886597093876e-05,
"loss": 4.2923,
"step": 296960
},
{
"epoch": 1.02,
"learning_rate": 4.5129500649583356e-05,
"loss": 4.285,
"step": 297472
},
{
"epoch": 1.02,
"learning_rate": 4.512113108087657e-05,
"loss": 4.2832,
"step": 297984
},
{
"epoch": 1.02,
"learning_rate": 4.5112745133366045e-05,
"loss": 4.2724,
"step": 298496
},
{
"epoch": 1.02,
"learning_rate": 4.5104359185855525e-05,
"loss": 4.275,
"step": 299008
},
{
"epoch": 1.02,
"learning_rate": 4.5095973238345005e-05,
"loss": 4.2859,
"step": 299520
},
{
"epoch": 1.02,
"learning_rate": 4.5087587290834485e-05,
"loss": 4.2906,
"step": 300032
},
{
"epoch": 1.02,
"learning_rate": 4.507920134332397e-05,
"loss": 4.2893,
"step": 300544
},
{
"epoch": 1.02,
"learning_rate": 4.507081539581345e-05,
"loss": 4.2774,
"step": 301056
},
{
"epoch": 1.02,
"learning_rate": 4.506242944830293e-05,
"loss": 4.2719,
"step": 301568
},
{
"epoch": 1.02,
"learning_rate": 4.505405987959614e-05,
"loss": 4.284,
"step": 302080
},
{
"epoch": 1.02,
"learning_rate": 4.504567393208562e-05,
"loss": 4.2761,
"step": 302592
},
{
"epoch": 1.02,
"learning_rate": 4.503730436337883e-05,
"loss": 4.2799,
"step": 303104
},
{
"epoch": 1.02,
"learning_rate": 4.502891841586831e-05,
"loss": 4.2903,
"step": 303616
},
{
"epoch": 1.02,
"learning_rate": 4.502053246835779e-05,
"loss": 4.2789,
"step": 304128
},
{
"epoch": 1.02,
"learning_rate": 4.501214652084727e-05,
"loss": 4.2772,
"step": 304640
},
{
"epoch": 1.02,
"learning_rate": 4.500376057333675e-05,
"loss": 4.2747,
"step": 305152
},
{
"epoch": 1.03,
"eval_loss": 4.312550067901611,
"eval_runtime": 539.9506,
"eval_samples_per_second": 706.715,
"eval_steps_per_second": 22.085,
"step": 305276
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 1.1747584538699142e+17,
"trial_name": null,
"trial_params": null
}