KLGR123's picture
commit message
5f1c52b
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.6701289998324678,
"eval_steps": 500,
"global_step": 1000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 4.99993842168232e-05,
"loss": 1.2211,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 4.9997536897627915e-05,
"loss": 1.0276,
"step": 20
},
{
"epoch": 0.02,
"learning_rate": 4.9994458133418e-05,
"loss": 0.8587,
"step": 30
},
{
"epoch": 0.03,
"learning_rate": 4.999014807586154e-05,
"loss": 0.7431,
"step": 40
},
{
"epoch": 0.03,
"learning_rate": 4.9984606937283405e-05,
"loss": 0.6841,
"step": 50
},
{
"epoch": 0.04,
"learning_rate": 4.9977834990654804e-05,
"loss": 0.6452,
"step": 60
},
{
"epoch": 0.05,
"learning_rate": 4.99698325695798e-05,
"loss": 0.6347,
"step": 70
},
{
"epoch": 0.05,
"learning_rate": 4.9960600068278876e-05,
"loss": 0.6109,
"step": 80
},
{
"epoch": 0.06,
"learning_rate": 4.995013794156957e-05,
"loss": 0.5911,
"step": 90
},
{
"epoch": 0.07,
"learning_rate": 4.993844670484401e-05,
"loss": 0.5803,
"step": 100
},
{
"epoch": 0.07,
"learning_rate": 4.992552693404354e-05,
"loss": 0.5902,
"step": 110
},
{
"epoch": 0.08,
"learning_rate": 4.991137926563036e-05,
"loss": 0.5745,
"step": 120
},
{
"epoch": 0.09,
"learning_rate": 4.9896004396556176e-05,
"loss": 0.5538,
"step": 130
},
{
"epoch": 0.09,
"learning_rate": 4.987940308422783e-05,
"loss": 0.5495,
"step": 140
},
{
"epoch": 0.1,
"learning_rate": 4.986157614647005e-05,
"loss": 0.5433,
"step": 150
},
{
"epoch": 0.11,
"learning_rate": 4.984252446148508e-05,
"loss": 0.548,
"step": 160
},
{
"epoch": 0.11,
"learning_rate": 4.98222489678095e-05,
"loss": 0.5361,
"step": 170
},
{
"epoch": 0.12,
"learning_rate": 4.980075066426796e-05,
"loss": 0.5331,
"step": 180
},
{
"epoch": 0.13,
"learning_rate": 4.977803060992393e-05,
"loss": 0.53,
"step": 190
},
{
"epoch": 0.13,
"learning_rate": 4.97540899240276e-05,
"loss": 0.5135,
"step": 200
},
{
"epoch": 0.14,
"learning_rate": 4.972892978596069e-05,
"loss": 0.5101,
"step": 210
},
{
"epoch": 0.15,
"learning_rate": 4.970255143517838e-05,
"loss": 0.5125,
"step": 220
},
{
"epoch": 0.15,
"learning_rate": 4.967495617114826e-05,
"loss": 0.4928,
"step": 230
},
{
"epoch": 0.16,
"learning_rate": 4.964614535328626e-05,
"loss": 0.4878,
"step": 240
},
{
"epoch": 0.17,
"learning_rate": 4.961612040088973e-05,
"loss": 0.5017,
"step": 250
},
{
"epoch": 0.17,
"learning_rate": 4.9584882793067534e-05,
"loss": 0.4863,
"step": 260
},
{
"epoch": 0.18,
"learning_rate": 4.955243406866713e-05,
"loss": 0.4847,
"step": 270
},
{
"epoch": 0.19,
"learning_rate": 4.951877582619881e-05,
"loss": 0.4868,
"step": 280
},
{
"epoch": 0.19,
"learning_rate": 4.948390972375694e-05,
"loss": 0.4748,
"step": 290
},
{
"epoch": 0.2,
"learning_rate": 4.944783747893825e-05,
"loss": 0.4764,
"step": 300
},
{
"epoch": 0.21,
"learning_rate": 4.941056086875727e-05,
"loss": 0.4712,
"step": 310
},
{
"epoch": 0.21,
"learning_rate": 4.937208172955876e-05,
"loss": 0.4642,
"step": 320
},
{
"epoch": 0.22,
"learning_rate": 4.9332401956927224e-05,
"loss": 0.4642,
"step": 330
},
{
"epoch": 0.23,
"learning_rate": 4.9291523505593604e-05,
"loss": 0.4709,
"step": 340
},
{
"epoch": 0.23,
"learning_rate": 4.9249448389338905e-05,
"loss": 0.461,
"step": 350
},
{
"epoch": 0.24,
"learning_rate": 4.920617868089501e-05,
"loss": 0.4677,
"step": 360
},
{
"epoch": 0.25,
"learning_rate": 4.9161716511842614e-05,
"loss": 0.4564,
"step": 370
},
{
"epoch": 0.25,
"learning_rate": 4.911606407250617e-05,
"loss": 0.4663,
"step": 380
},
{
"epoch": 0.26,
"learning_rate": 4.9069223611846014e-05,
"loss": 0.4682,
"step": 390
},
{
"epoch": 0.27,
"learning_rate": 4.9021197437347555e-05,
"loss": 0.4636,
"step": 400
},
{
"epoch": 0.27,
"learning_rate": 4.897198791490762e-05,
"loss": 0.4569,
"step": 410
},
{
"epoch": 0.28,
"learning_rate": 4.8921597468717887e-05,
"loss": 0.462,
"step": 420
},
{
"epoch": 0.29,
"learning_rate": 4.887002858114548e-05,
"loss": 0.4563,
"step": 430
},
{
"epoch": 0.29,
"learning_rate": 4.881728379261068e-05,
"loss": 0.4563,
"step": 440
},
{
"epoch": 0.3,
"learning_rate": 4.876336570146175e-05,
"loss": 0.4468,
"step": 450
},
{
"epoch": 0.31,
"learning_rate": 4.870827696384698e-05,
"loss": 0.4508,
"step": 460
},
{
"epoch": 0.31,
"learning_rate": 4.865202029358379e-05,
"loss": 0.4507,
"step": 470
},
{
"epoch": 0.32,
"learning_rate": 4.859459846202507e-05,
"loss": 0.4486,
"step": 480
},
{
"epoch": 0.33,
"learning_rate": 4.853601429792265e-05,
"loss": 0.4423,
"step": 490
},
{
"epoch": 0.34,
"learning_rate": 4.847627068728795e-05,
"loss": 0.4369,
"step": 500
},
{
"epoch": 0.34,
"learning_rate": 4.841537057324979e-05,
"loss": 0.4429,
"step": 510
},
{
"epoch": 0.35,
"learning_rate": 4.835331695590943e-05,
"loss": 0.4389,
"step": 520
},
{
"epoch": 0.36,
"learning_rate": 4.829011289219276e-05,
"loss": 0.44,
"step": 530
},
{
"epoch": 0.36,
"learning_rate": 4.82257614956997e-05,
"loss": 0.4476,
"step": 540
},
{
"epoch": 0.37,
"learning_rate": 4.816026593655085e-05,
"loss": 0.4367,
"step": 550
},
{
"epoch": 0.38,
"learning_rate": 4.809362944123129e-05,
"loss": 0.4357,
"step": 560
},
{
"epoch": 0.38,
"learning_rate": 4.802585529243164e-05,
"loss": 0.4492,
"step": 570
},
{
"epoch": 0.39,
"learning_rate": 4.795694682888635e-05,
"loss": 0.4403,
"step": 580
},
{
"epoch": 0.4,
"learning_rate": 4.7886907445209234e-05,
"loss": 0.4406,
"step": 590
},
{
"epoch": 0.4,
"learning_rate": 4.781574059172621e-05,
"loss": 0.4317,
"step": 600
},
{
"epoch": 0.41,
"learning_rate": 4.7743449774305386e-05,
"loss": 0.4379,
"step": 610
},
{
"epoch": 0.42,
"learning_rate": 4.7670038554184296e-05,
"loss": 0.4324,
"step": 620
},
{
"epoch": 0.42,
"learning_rate": 4.7595510547794465e-05,
"loss": 0.4329,
"step": 630
},
{
"epoch": 0.43,
"learning_rate": 4.751986942658332e-05,
"loss": 0.4259,
"step": 640
},
{
"epoch": 0.44,
"learning_rate": 4.744311891683325e-05,
"loss": 0.4256,
"step": 650
},
{
"epoch": 0.44,
"learning_rate": 4.736526279947807e-05,
"loss": 0.4289,
"step": 660
},
{
"epoch": 0.45,
"learning_rate": 4.728630490991676e-05,
"loss": 0.4353,
"step": 670
},
{
"epoch": 0.46,
"learning_rate": 4.7206249137824535e-05,
"loss": 0.4413,
"step": 680
},
{
"epoch": 0.46,
"learning_rate": 4.7125099426961185e-05,
"loss": 0.4302,
"step": 690
},
{
"epoch": 0.47,
"learning_rate": 4.704285977497687e-05,
"loss": 0.4365,
"step": 700
},
{
"epoch": 0.48,
"learning_rate": 4.6959534233215116e-05,
"loss": 0.4238,
"step": 710
},
{
"epoch": 0.48,
"learning_rate": 4.687512690651328e-05,
"loss": 0.4284,
"step": 720
},
{
"epoch": 0.49,
"learning_rate": 4.678964195300028e-05,
"loss": 0.4193,
"step": 730
},
{
"epoch": 0.5,
"learning_rate": 4.670308358389184e-05,
"loss": 0.4256,
"step": 740
},
{
"epoch": 0.5,
"learning_rate": 4.6615456063282944e-05,
"loss": 0.4288,
"step": 750
},
{
"epoch": 0.51,
"learning_rate": 4.652676370793784e-05,
"loss": 0.4335,
"step": 760
},
{
"epoch": 0.52,
"learning_rate": 4.643701088707736e-05,
"loss": 0.4271,
"step": 770
},
{
"epoch": 0.52,
"learning_rate": 4.634620202216366e-05,
"loss": 0.4304,
"step": 780
},
{
"epoch": 0.53,
"learning_rate": 4.625434158668246e-05,
"loss": 0.4249,
"step": 790
},
{
"epoch": 0.54,
"learning_rate": 4.6161434105922616e-05,
"loss": 0.4322,
"step": 800
},
{
"epoch": 0.54,
"learning_rate": 4.6067484156753234e-05,
"loss": 0.4229,
"step": 810
},
{
"epoch": 0.55,
"learning_rate": 4.597249636739815e-05,
"loss": 0.4252,
"step": 820
},
{
"epoch": 0.56,
"learning_rate": 4.5876475417207974e-05,
"loss": 0.413,
"step": 830
},
{
"epoch": 0.56,
"learning_rate": 4.577942603642959e-05,
"loss": 0.4186,
"step": 840
},
{
"epoch": 0.57,
"learning_rate": 4.568135300597306e-05,
"loss": 0.4233,
"step": 850
},
{
"epoch": 0.58,
"learning_rate": 4.5582261157176164e-05,
"loss": 0.4177,
"step": 860
},
{
"epoch": 0.58,
"learning_rate": 4.5482155371566384e-05,
"loss": 0.4236,
"step": 870
},
{
"epoch": 0.59,
"learning_rate": 4.538104058062042e-05,
"loss": 0.4228,
"step": 880
},
{
"epoch": 0.6,
"learning_rate": 4.5278921765521234e-05,
"loss": 0.4181,
"step": 890
},
{
"epoch": 0.6,
"learning_rate": 4.51758039569127e-05,
"loss": 0.4261,
"step": 900
},
{
"epoch": 0.61,
"learning_rate": 4.5071692234651764e-05,
"loss": 0.4217,
"step": 910
},
{
"epoch": 0.62,
"learning_rate": 4.4966591727558184e-05,
"loss": 0.4191,
"step": 920
},
{
"epoch": 0.62,
"learning_rate": 4.48605076131619e-05,
"loss": 0.4247,
"step": 930
},
{
"epoch": 0.63,
"learning_rate": 4.475344511744794e-05,
"loss": 0.4236,
"step": 940
},
{
"epoch": 0.64,
"learning_rate": 4.464540951459902e-05,
"loss": 0.4172,
"step": 950
},
{
"epoch": 0.64,
"learning_rate": 4.4536406126735664e-05,
"loss": 0.4209,
"step": 960
},
{
"epoch": 0.65,
"learning_rate": 4.442644032365407e-05,
"loss": 0.4179,
"step": 970
},
{
"epoch": 0.66,
"learning_rate": 4.431551752256155e-05,
"loss": 0.4166,
"step": 980
},
{
"epoch": 0.66,
"learning_rate": 4.420364318780973e-05,
"loss": 0.4173,
"step": 990
},
{
"epoch": 0.67,
"learning_rate": 4.4090822830625236e-05,
"loss": 0.4166,
"step": 1000
}
],
"logging_steps": 10,
"max_steps": 4476,
"num_train_epochs": 3,
"save_steps": 200,
"total_flos": 9.097203781942116e+18,
"trial_name": null,
"trial_params": null
}