Metis-RISE-72B / trainer_state.json
rubyla1's picture
Upload folder using huggingface_hub
c049790 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 1000000000,
"global_step": 333,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.09009009009009009,
"grad_norm": 1.1388429249940315,
"learning_rate": 1e-06,
"loss": 0.2794,
"step": 10
},
{
"epoch": 0.18018018018018017,
"grad_norm": 0.7379889069329842,
"learning_rate": 9.976368444410984e-07,
"loss": 0.25,
"step": 20
},
{
"epoch": 0.2702702702702703,
"grad_norm": 0.7102173931739229,
"learning_rate": 9.90569715781176e-07,
"loss": 0.2314,
"step": 30
},
{
"epoch": 0.36036036036036034,
"grad_norm": 0.6479325695726197,
"learning_rate": 9.788654169177453e-07,
"loss": 0.2083,
"step": 40
},
{
"epoch": 0.45045045045045046,
"grad_norm": 0.651257304866243,
"learning_rate": 9.626345841664951e-07,
"loss": 0.2005,
"step": 50
},
{
"epoch": 0.5405405405405406,
"grad_norm": 0.6216808244633711,
"learning_rate": 9.420306414579924e-07,
"loss": 0.1958,
"step": 60
},
{
"epoch": 0.6306306306306306,
"grad_norm": 0.5994250658408403,
"learning_rate": 9.172483500792244e-07,
"loss": 0.1904,
"step": 70
},
{
"epoch": 0.7207207207207207,
"grad_norm": 0.8078023363316856,
"learning_rate": 8.885219676687276e-07,
"loss": 0.1834,
"step": 80
},
{
"epoch": 0.8108108108108109,
"grad_norm": 0.6753114001644601,
"learning_rate": 8.561230338676239e-07,
"loss": 0.1844,
"step": 90
},
{
"epoch": 0.9009009009009009,
"grad_norm": 0.6635142899460188,
"learning_rate": 8.203578035579715e-07,
"loss": 0.1817,
"step": 100
},
{
"epoch": 0.990990990990991,
"grad_norm": 0.5961830092202408,
"learning_rate": 7.81564351951057e-07,
"loss": 0.184,
"step": 110
},
{
"epoch": 1.0810810810810811,
"grad_norm": 0.5110100942254465,
"learning_rate": 7.40109378890136e-07,
"loss": 0.1695,
"step": 120
},
{
"epoch": 1.1711711711711712,
"grad_norm": 0.5243157852701217,
"learning_rate": 6.963847425753402e-07,
"loss": 0.1613,
"step": 130
},
{
"epoch": 1.2612612612612613,
"grad_norm": 0.5476337775859051,
"learning_rate": 6.508037554761432e-07,
"loss": 0.1648,
"step": 140
},
{
"epoch": 1.3513513513513513,
"grad_norm": 0.5566351464797659,
"learning_rate": 6.037972774447193e-07,
"loss": 0.1582,
"step": 150
},
{
"epoch": 1.4414414414414414,
"grad_norm": 0.6330056010848006,
"learning_rate": 5.558096429605262e-07,
"loss": 0.1594,
"step": 160
},
{
"epoch": 1.5315315315315314,
"grad_norm": 0.576332699146444,
"learning_rate": 5.072944610043232e-07,
"loss": 0.1548,
"step": 170
},
{
"epoch": 1.6216216216216215,
"grad_norm": 0.553240344080441,
"learning_rate": 4.5871032726383385e-07,
"loss": 0.1543,
"step": 180
},
{
"epoch": 1.7117117117117115,
"grad_norm": 0.5447783047597399,
"learning_rate": 4.1051648920195136e-07,
"loss": 0.1524,
"step": 190
},
{
"epoch": 1.8018018018018018,
"grad_norm": 0.4974619958479327,
"learning_rate": 3.6316850496395855e-07,
"loss": 0.156,
"step": 200
},
{
"epoch": 1.8918918918918919,
"grad_norm": 0.5450685177163245,
"learning_rate": 3.1711393715847473e-07,
"loss": 0.1572,
"step": 210
},
{
"epoch": 1.981981981981982,
"grad_norm": 0.5552205648869585,
"learning_rate": 2.727881222171892e-07,
"loss": 0.157,
"step": 220
},
{
"epoch": 2.0720720720720722,
"grad_norm": 0.5485057468217042,
"learning_rate": 2.3061005532402738e-07,
"loss": 0.1439,
"step": 230
},
{
"epoch": 2.1621621621621623,
"grad_norm": 0.5550102284110532,
"learning_rate": 1.9097842981195832e-07,
"loss": 0.1411,
"step": 240
},
{
"epoch": 2.2522522522522523,
"grad_norm": 0.5267038237885973,
"learning_rate": 1.542678684655306e-07,
"loss": 0.1467,
"step": 250
},
{
"epoch": 2.3423423423423424,
"grad_norm": 0.5817516648231494,
"learning_rate": 1.2082538235320928e-07,
"loss": 0.1392,
"step": 260
},
{
"epoch": 2.4324324324324325,
"grad_norm": 0.5287607572042831,
"learning_rate": 9.096709066283353e-08,
"loss": 0.1396,
"step": 270
},
{
"epoch": 2.5225225225225225,
"grad_norm": 0.5959387033532365,
"learning_rate": 6.497523254635296e-08,
"loss": 0.1412,
"step": 280
},
{
"epoch": 2.6126126126126126,
"grad_norm": 0.5688306435076187,
"learning_rate": 4.30954992197442e-08,
"loss": 0.1408,
"step": 290
},
{
"epoch": 2.7027027027027026,
"grad_norm": 0.5097576755387367,
"learning_rate": 2.5534711536759403e-08,
"loss": 0.1427,
"step": 300
},
{
"epoch": 2.7927927927927927,
"grad_norm": 0.5454762489740467,
"learning_rate": 1.2458864989525697e-08,
"loss": 0.1394,
"step": 310
},
{
"epoch": 2.8828828828828827,
"grad_norm": 0.5420347142954879,
"learning_rate": 3.991560615864586e-09,
"loss": 0.1407,
"step": 320
},
{
"epoch": 2.972972972972973,
"grad_norm": 0.5676126641058691,
"learning_rate": 2.1283664537435908e-10,
"loss": 0.1416,
"step": 330
}
],
"logging_steps": 10,
"max_steps": 333,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 40,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 635986474172416.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}