Chef-Mistral-7B / checkpoint-500 /trainer_state.json
hazarsozer's picture
Upload folder using huggingface_hub
2d6f639 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.32362459546925565,
"eval_steps": 500,
"global_step": 500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.006472491909385114,
"grad_norm": 2.0135042667388916,
"learning_rate": 1.8e-05,
"loss": 1.5311,
"step": 10
},
{
"epoch": 0.012944983818770227,
"grad_norm": 1.0551478862762451,
"learning_rate": 3.8e-05,
"loss": 1.2229,
"step": 20
},
{
"epoch": 0.019417475728155338,
"grad_norm": 1.101570725440979,
"learning_rate": 5.8e-05,
"loss": 0.9845,
"step": 30
},
{
"epoch": 0.025889967637540454,
"grad_norm": 0.9952124357223511,
"learning_rate": 7.800000000000001e-05,
"loss": 0.8599,
"step": 40
},
{
"epoch": 0.032362459546925564,
"grad_norm": 0.8940704464912415,
"learning_rate": 9.8e-05,
"loss": 0.8401,
"step": 50
},
{
"epoch": 0.038834951456310676,
"grad_norm": 0.8487522602081299,
"learning_rate": 9.93979933110368e-05,
"loss": 0.776,
"step": 60
},
{
"epoch": 0.045307443365695796,
"grad_norm": 0.7864758968353271,
"learning_rate": 9.872909698996656e-05,
"loss": 0.8153,
"step": 70
},
{
"epoch": 0.05177993527508091,
"grad_norm": 0.7295967936515808,
"learning_rate": 9.806020066889633e-05,
"loss": 0.8251,
"step": 80
},
{
"epoch": 0.05825242718446602,
"grad_norm": 0.7075174450874329,
"learning_rate": 9.739130434782609e-05,
"loss": 0.749,
"step": 90
},
{
"epoch": 0.06472491909385113,
"grad_norm": 0.6422586441040039,
"learning_rate": 9.672240802675586e-05,
"loss": 0.7428,
"step": 100
},
{
"epoch": 0.07119741100323625,
"grad_norm": 0.6745761632919312,
"learning_rate": 9.605351170568563e-05,
"loss": 0.7806,
"step": 110
},
{
"epoch": 0.07766990291262135,
"grad_norm": 0.6769530177116394,
"learning_rate": 9.53846153846154e-05,
"loss": 0.796,
"step": 120
},
{
"epoch": 0.08414239482200647,
"grad_norm": 0.5150454044342041,
"learning_rate": 9.471571906354515e-05,
"loss": 0.7486,
"step": 130
},
{
"epoch": 0.09061488673139159,
"grad_norm": 0.6074182391166687,
"learning_rate": 9.404682274247491e-05,
"loss": 0.7783,
"step": 140
},
{
"epoch": 0.0970873786407767,
"grad_norm": 0.6745702624320984,
"learning_rate": 9.337792642140469e-05,
"loss": 0.7503,
"step": 150
},
{
"epoch": 0.10355987055016182,
"grad_norm": 0.6088436841964722,
"learning_rate": 9.270903010033445e-05,
"loss": 0.7771,
"step": 160
},
{
"epoch": 0.11003236245954692,
"grad_norm": 0.6351744532585144,
"learning_rate": 9.204013377926422e-05,
"loss": 0.7554,
"step": 170
},
{
"epoch": 0.11650485436893204,
"grad_norm": 0.5281522274017334,
"learning_rate": 9.137123745819398e-05,
"loss": 0.7635,
"step": 180
},
{
"epoch": 0.12297734627831715,
"grad_norm": 0.6833154559135437,
"learning_rate": 9.070234113712374e-05,
"loss": 0.753,
"step": 190
},
{
"epoch": 0.12944983818770225,
"grad_norm": 0.5272049307823181,
"learning_rate": 9.003344481605351e-05,
"loss": 0.7384,
"step": 200
},
{
"epoch": 0.13592233009708737,
"grad_norm": 0.6461851596832275,
"learning_rate": 8.936454849498329e-05,
"loss": 0.7548,
"step": 210
},
{
"epoch": 0.1423948220064725,
"grad_norm": 0.5979950428009033,
"learning_rate": 8.869565217391305e-05,
"loss": 0.7534,
"step": 220
},
{
"epoch": 0.1488673139158576,
"grad_norm": 0.6396514773368835,
"learning_rate": 8.802675585284281e-05,
"loss": 0.7436,
"step": 230
},
{
"epoch": 0.1553398058252427,
"grad_norm": 0.6104384064674377,
"learning_rate": 8.735785953177258e-05,
"loss": 0.7345,
"step": 240
},
{
"epoch": 0.16181229773462782,
"grad_norm": 0.5535375475883484,
"learning_rate": 8.668896321070234e-05,
"loss": 0.7293,
"step": 250
},
{
"epoch": 0.16828478964401294,
"grad_norm": 0.5984886884689331,
"learning_rate": 8.602006688963212e-05,
"loss": 0.7173,
"step": 260
},
{
"epoch": 0.17475728155339806,
"grad_norm": 0.517716646194458,
"learning_rate": 8.535117056856188e-05,
"loss": 0.7694,
"step": 270
},
{
"epoch": 0.18122977346278318,
"grad_norm": 0.5802426934242249,
"learning_rate": 8.468227424749165e-05,
"loss": 0.7505,
"step": 280
},
{
"epoch": 0.18770226537216828,
"grad_norm": 0.5289272665977478,
"learning_rate": 8.401337792642141e-05,
"loss": 0.7678,
"step": 290
},
{
"epoch": 0.1941747572815534,
"grad_norm": 0.5293733477592468,
"learning_rate": 8.334448160535117e-05,
"loss": 0.7242,
"step": 300
},
{
"epoch": 0.20064724919093851,
"grad_norm": 0.566146969795227,
"learning_rate": 8.267558528428094e-05,
"loss": 0.7248,
"step": 310
},
{
"epoch": 0.20711974110032363,
"grad_norm": 0.5496853590011597,
"learning_rate": 8.200668896321071e-05,
"loss": 0.7588,
"step": 320
},
{
"epoch": 0.21359223300970873,
"grad_norm": 0.5420507192611694,
"learning_rate": 8.133779264214048e-05,
"loss": 0.7673,
"step": 330
},
{
"epoch": 0.22006472491909385,
"grad_norm": 0.582582950592041,
"learning_rate": 8.066889632107024e-05,
"loss": 0.7341,
"step": 340
},
{
"epoch": 0.22653721682847897,
"grad_norm": 0.5332103371620178,
"learning_rate": 8e-05,
"loss": 0.7518,
"step": 350
},
{
"epoch": 0.23300970873786409,
"grad_norm": 0.5132858157157898,
"learning_rate": 7.933110367892977e-05,
"loss": 0.752,
"step": 360
},
{
"epoch": 0.23948220064724918,
"grad_norm": 0.5356752276420593,
"learning_rate": 7.866220735785953e-05,
"loss": 0.7432,
"step": 370
},
{
"epoch": 0.2459546925566343,
"grad_norm": 0.5592623353004456,
"learning_rate": 7.79933110367893e-05,
"loss": 0.7396,
"step": 380
},
{
"epoch": 0.2524271844660194,
"grad_norm": 0.5103404521942139,
"learning_rate": 7.732441471571906e-05,
"loss": 0.7253,
"step": 390
},
{
"epoch": 0.2588996763754045,
"grad_norm": 0.5380160212516785,
"learning_rate": 7.665551839464883e-05,
"loss": 0.7464,
"step": 400
},
{
"epoch": 0.26537216828478966,
"grad_norm": 0.5373779535293579,
"learning_rate": 7.598662207357859e-05,
"loss": 0.7377,
"step": 410
},
{
"epoch": 0.27184466019417475,
"grad_norm": 0.523170530796051,
"learning_rate": 7.531772575250837e-05,
"loss": 0.7413,
"step": 420
},
{
"epoch": 0.2783171521035599,
"grad_norm": 0.5368985533714294,
"learning_rate": 7.464882943143813e-05,
"loss": 0.7227,
"step": 430
},
{
"epoch": 0.284789644012945,
"grad_norm": 0.587778627872467,
"learning_rate": 7.39799331103679e-05,
"loss": 0.7289,
"step": 440
},
{
"epoch": 0.2912621359223301,
"grad_norm": 0.5471896529197693,
"learning_rate": 7.331103678929766e-05,
"loss": 0.7301,
"step": 450
},
{
"epoch": 0.2977346278317152,
"grad_norm": 0.5446394085884094,
"learning_rate": 7.264214046822742e-05,
"loss": 0.7325,
"step": 460
},
{
"epoch": 0.3042071197411003,
"grad_norm": 0.5761464238166809,
"learning_rate": 7.197324414715719e-05,
"loss": 0.7583,
"step": 470
},
{
"epoch": 0.3106796116504854,
"grad_norm": 0.5082632899284363,
"learning_rate": 7.130434782608696e-05,
"loss": 0.7382,
"step": 480
},
{
"epoch": 0.31715210355987056,
"grad_norm": 0.5441333651542664,
"learning_rate": 7.063545150501673e-05,
"loss": 0.7411,
"step": 490
},
{
"epoch": 0.32362459546925565,
"grad_norm": 0.5039440393447876,
"learning_rate": 6.996655518394649e-05,
"loss": 0.7332,
"step": 500
}
],
"logging_steps": 10,
"max_steps": 1545,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.803063236717445e+17,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}