ryusangwon's picture
Model save
fcdc3bf verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.35765379113018597,
"eval_steps": 500,
"global_step": 500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 4.988078206962327e-05,
"loss": 1.7516,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 4.976156413924655e-05,
"loss": 1.7798,
"step": 20
},
{
"epoch": 0.02,
"learning_rate": 4.964234620886982e-05,
"loss": 1.7269,
"step": 30
},
{
"epoch": 0.03,
"learning_rate": 4.9523128278493086e-05,
"loss": 1.6977,
"step": 40
},
{
"epoch": 0.04,
"learning_rate": 4.940391034811636e-05,
"loss": 1.6931,
"step": 50
},
{
"epoch": 0.04,
"learning_rate": 4.928469241773963e-05,
"loss": 1.6307,
"step": 60
},
{
"epoch": 0.05,
"learning_rate": 4.91654744873629e-05,
"loss": 1.6882,
"step": 70
},
{
"epoch": 0.06,
"learning_rate": 4.904625655698618e-05,
"loss": 1.6711,
"step": 80
},
{
"epoch": 0.06,
"learning_rate": 4.8927038626609446e-05,
"loss": 1.6717,
"step": 90
},
{
"epoch": 0.07,
"learning_rate": 4.8807820696232716e-05,
"loss": 1.6882,
"step": 100
},
{
"epoch": 0.08,
"learning_rate": 4.868860276585599e-05,
"loss": 1.6379,
"step": 110
},
{
"epoch": 0.09,
"learning_rate": 4.856938483547926e-05,
"loss": 1.6351,
"step": 120
},
{
"epoch": 0.09,
"learning_rate": 4.845016690510253e-05,
"loss": 1.6685,
"step": 130
},
{
"epoch": 0.1,
"learning_rate": 4.8330948974725806e-05,
"loss": 1.632,
"step": 140
},
{
"epoch": 0.11,
"learning_rate": 4.8211731044349076e-05,
"loss": 1.6629,
"step": 150
},
{
"epoch": 0.11,
"learning_rate": 4.8092513113972345e-05,
"loss": 1.6639,
"step": 160
},
{
"epoch": 0.12,
"learning_rate": 4.7973295183595614e-05,
"loss": 1.5963,
"step": 170
},
{
"epoch": 0.13,
"learning_rate": 4.785407725321889e-05,
"loss": 1.6739,
"step": 180
},
{
"epoch": 0.14,
"learning_rate": 4.773485932284216e-05,
"loss": 1.6487,
"step": 190
},
{
"epoch": 0.14,
"learning_rate": 4.761564139246543e-05,
"loss": 1.6607,
"step": 200
},
{
"epoch": 0.15,
"learning_rate": 4.74964234620887e-05,
"loss": 1.6357,
"step": 210
},
{
"epoch": 0.16,
"learning_rate": 4.7377205531711974e-05,
"loss": 1.6406,
"step": 220
},
{
"epoch": 0.16,
"learning_rate": 4.7257987601335244e-05,
"loss": 1.6421,
"step": 230
},
{
"epoch": 0.17,
"learning_rate": 4.713876967095851e-05,
"loss": 1.6822,
"step": 240
},
{
"epoch": 0.18,
"learning_rate": 4.701955174058178e-05,
"loss": 1.6343,
"step": 250
},
{
"epoch": 0.19,
"learning_rate": 4.690033381020505e-05,
"loss": 1.6222,
"step": 260
},
{
"epoch": 0.19,
"learning_rate": 4.678111587982833e-05,
"loss": 1.6628,
"step": 270
},
{
"epoch": 0.2,
"learning_rate": 4.66618979494516e-05,
"loss": 1.6068,
"step": 280
},
{
"epoch": 0.21,
"learning_rate": 4.6542680019074866e-05,
"loss": 1.6533,
"step": 290
},
{
"epoch": 0.21,
"learning_rate": 4.642346208869814e-05,
"loss": 1.6371,
"step": 300
},
{
"epoch": 0.22,
"learning_rate": 4.630424415832141e-05,
"loss": 1.6491,
"step": 310
},
{
"epoch": 0.23,
"learning_rate": 4.618502622794468e-05,
"loss": 1.6218,
"step": 320
},
{
"epoch": 0.24,
"learning_rate": 4.606580829756796e-05,
"loss": 1.6676,
"step": 330
},
{
"epoch": 0.24,
"learning_rate": 4.5946590367191226e-05,
"loss": 1.5947,
"step": 340
},
{
"epoch": 0.25,
"learning_rate": 4.5827372436814496e-05,
"loss": 1.6307,
"step": 350
},
{
"epoch": 0.26,
"learning_rate": 4.570815450643777e-05,
"loss": 1.609,
"step": 360
},
{
"epoch": 0.26,
"learning_rate": 4.558893657606104e-05,
"loss": 1.6171,
"step": 370
},
{
"epoch": 0.27,
"learning_rate": 4.546971864568431e-05,
"loss": 1.6125,
"step": 380
},
{
"epoch": 0.28,
"learning_rate": 4.5350500715307586e-05,
"loss": 1.6325,
"step": 390
},
{
"epoch": 0.29,
"learning_rate": 4.5231282784930856e-05,
"loss": 1.626,
"step": 400
},
{
"epoch": 0.29,
"learning_rate": 4.5112064854554125e-05,
"loss": 1.5777,
"step": 410
},
{
"epoch": 0.3,
"learning_rate": 4.49928469241774e-05,
"loss": 1.6446,
"step": 420
},
{
"epoch": 0.31,
"learning_rate": 4.487362899380067e-05,
"loss": 1.6189,
"step": 430
},
{
"epoch": 0.31,
"learning_rate": 4.475441106342394e-05,
"loss": 1.6356,
"step": 440
},
{
"epoch": 0.32,
"learning_rate": 4.4635193133047216e-05,
"loss": 1.6001,
"step": 450
},
{
"epoch": 0.33,
"learning_rate": 4.4515975202670485e-05,
"loss": 1.6226,
"step": 460
},
{
"epoch": 0.34,
"learning_rate": 4.4396757272293754e-05,
"loss": 1.6109,
"step": 470
},
{
"epoch": 0.34,
"learning_rate": 4.4277539341917024e-05,
"loss": 1.6559,
"step": 480
},
{
"epoch": 0.35,
"learning_rate": 4.41583214115403e-05,
"loss": 1.6108,
"step": 490
},
{
"epoch": 0.36,
"learning_rate": 4.403910348116357e-05,
"loss": 1.6137,
"step": 500
}
],
"logging_steps": 10,
"max_steps": 4194,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"total_flos": 3.1601241096192e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}