abhinavp's picture
Training in progress, epoch 1, checkpoint
e45829a verified
{
"best_metric": 4.530740261077881,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/pp-mod-subj/lstm/0/checkpoints/checkpoint-152638",
"epoch": 1.0250002784396635,
"eval_steps": 10,
"global_step": 152638,
"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
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 5.873792269349571e+16,
"trial_name": null,
"trial_params": null
}