base_model / trainer_state.json
VladShash's picture
Upload 14 files
05bd547 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 4467,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02238638907544213,
"grad_norm": 8.243054389953613,
"learning_rate": 4.993942787771599e-06,
"loss": 1.1762,
"step": 100
},
{
"epoch": 0.04477277815088426,
"grad_norm": 13.294663429260254,
"learning_rate": 4.975555846433033e-06,
"loss": 1.1404,
"step": 200
},
{
"epoch": 0.0671591672263264,
"grad_norm": 8.65041446685791,
"learning_rate": 4.9449294649220665e-06,
"loss": 1.0161,
"step": 300
},
{
"epoch": 0.08954555630176853,
"grad_norm": 10.313958168029785,
"learning_rate": 4.902215063682208e-06,
"loss": 0.9855,
"step": 400
},
{
"epoch": 0.11193194537721066,
"grad_norm": 10.495174407958984,
"learning_rate": 4.847623827752661e-06,
"loss": 0.9682,
"step": 500
},
{
"epoch": 0.1343183344526528,
"grad_norm": 12.217084884643555,
"learning_rate": 4.781425662644569e-06,
"loss": 0.988,
"step": 600
},
{
"epoch": 0.15670472352809492,
"grad_norm": 10.601492881774902,
"learning_rate": 4.703947859896326e-06,
"loss": 1.0177,
"step": 700
},
{
"epoch": 0.17909111260353705,
"grad_norm": 7.260547637939453,
"learning_rate": 4.615573478905602e-06,
"loss": 0.9601,
"step": 800
},
{
"epoch": 0.20147750167897918,
"grad_norm": 10.645676612854004,
"learning_rate": 4.5167394530384775e-06,
"loss": 0.9422,
"step": 900
},
{
"epoch": 0.2238638907544213,
"grad_norm": 10.681941986083984,
"learning_rate": 4.407934429379341e-06,
"loss": 1.0196,
"step": 1000
},
{
"epoch": 0.24625027982986344,
"grad_norm": 9.875200271606445,
"learning_rate": 4.28969635280205e-06,
"loss": 1.0191,
"step": 1100
},
{
"epoch": 0.2686366689053056,
"grad_norm": 10.363883018493652,
"learning_rate": 4.162609806307003e-06,
"loss": 0.9449,
"step": 1200
},
{
"epoch": 0.2910230579807477,
"grad_norm": 8.477913856506348,
"learning_rate": 4.027303120773824e-06,
"loss": 0.9039,
"step": 1300
},
{
"epoch": 0.31340944705618984,
"grad_norm": 9.964315414428711,
"learning_rate": 3.884445268419355e-06,
"loss": 1.0146,
"step": 1400
},
{
"epoch": 0.33579583613163194,
"grad_norm": 10.20909309387207,
"learning_rate": 3.734742555320098e-06,
"loss": 1.0387,
"step": 1500
},
{
"epoch": 0.3581822252070741,
"grad_norm": 12.675057411193848,
"learning_rate": 3.578935129351634e-06,
"loss": 1.0002,
"step": 1600
},
{
"epoch": 0.3805686142825162,
"grad_norm": 11.391951560974121,
"learning_rate": 3.4177933208102103e-06,
"loss": 0.9976,
"step": 1700
},
{
"epoch": 0.40295500335795836,
"grad_norm": 10.763954162597656,
"learning_rate": 3.2521138338088676e-06,
"loss": 0.9535,
"step": 1800
},
{
"epoch": 0.42534139243340047,
"grad_norm": 9.04262638092041,
"learning_rate": 3.0827158072783113e-06,
"loss": 1.0119,
"step": 1900
},
{
"epoch": 0.4477277815088426,
"grad_norm": 7.757719993591309,
"learning_rate": 2.9104367650473923e-06,
"loss": 0.9353,
"step": 2000
},
{
"epoch": 0.47011417058428473,
"grad_norm": 8.288910865783691,
"learning_rate": 2.7361284750264927e-06,
"loss": 1.0068,
"step": 2100
},
{
"epoch": 0.4925005596597269,
"grad_norm": 10.480790138244629,
"learning_rate": 2.5606527379664746e-06,
"loss": 0.9621,
"step": 2200
},
{
"epoch": 0.514886948735169,
"grad_norm": 12.541658401489258,
"learning_rate": 2.384877126614103e-06,
"loss": 0.9756,
"step": 2300
},
{
"epoch": 0.5372733378106112,
"grad_norm": 13.887962341308594,
"learning_rate": 2.20967069633002e-06,
"loss": 0.9665,
"step": 2400
},
{
"epoch": 0.5596597268860533,
"grad_norm": 11.765827178955078,
"learning_rate": 2.035899688376515e-06,
"loss": 0.9511,
"step": 2500
},
{
"epoch": 0.5820461159614954,
"grad_norm": 11.959718704223633,
"learning_rate": 1.8644232471185239e-06,
"loss": 0.9713,
"step": 2600
},
{
"epoch": 0.6044325050369376,
"grad_norm": 8.351862907409668,
"learning_rate": 1.6960891723125235e-06,
"loss": 1.0633,
"step": 2700
},
{
"epoch": 0.6268188941123797,
"grad_norm": 7.508358478546143,
"learning_rate": 1.5317297274845156e-06,
"loss": 0.895,
"step": 2800
},
{
"epoch": 0.6492052831878218,
"grad_norm": 12.4747314453125,
"learning_rate": 1.372157525120959e-06,
"loss": 0.9394,
"step": 2900
},
{
"epoch": 0.6715916722632639,
"grad_norm": 12.205965042114258,
"learning_rate": 1.2181615090167711e-06,
"loss": 0.9485,
"step": 3000
},
{
"epoch": 0.6939780613387061,
"grad_norm": 6.783346652984619,
"learning_rate": 1.0705030536441147e-06,
"loss": 0.8932,
"step": 3100
},
{
"epoch": 0.7163644504141482,
"grad_norm": 9.786669731140137,
"learning_rate": 9.299121998271918e-07,
"loss": 0.9629,
"step": 3200
},
{
"epoch": 0.7387508394895903,
"grad_norm": 8.05592155456543,
"learning_rate": 7.970840453342679e-07,
"loss": 0.9799,
"step": 3300
},
{
"epoch": 0.7611372285650324,
"grad_norm": 11.015290260314941,
"learning_rate": 6.726753082323087e-07,
"loss": 0.8752,
"step": 3400
},
{
"epoch": 0.7835236176404746,
"grad_norm": 8.78658390045166,
"learning_rate": 5.573010799953652e-07,
"loss": 0.8905,
"step": 3500
},
{
"epoch": 0.8059100067159167,
"grad_norm": 11.667632102966309,
"learning_rate": 4.515317844197653e-07,
"loss": 0.9166,
"step": 3600
},
{
"epoch": 0.8282963957913588,
"grad_norm": 8.403421401977539,
"learning_rate": 3.5589035738156305e-07,
"loss": 0.9322,
"step": 3700
},
{
"epoch": 0.8506827848668009,
"grad_norm": 11.51596450805664,
"learning_rate": 2.708496613798717e-07,
"loss": 0.909,
"step": 3800
},
{
"epoch": 0.8730691739422431,
"grad_norm": 6.4879045486450195,
"learning_rate": 1.9683014764887682e-07,
"loss": 0.9552,
"step": 3900
},
{
"epoch": 0.8954555630176853,
"grad_norm": 11.149494171142578,
"learning_rate": 1.3419777739733408e-07,
"loss": 0.9242,
"step": 4000
},
{
"epoch": 0.9178419520931274,
"grad_norm": 8.041584014892578,
"learning_rate": 8.326221245317373e-08,
"loss": 0.9278,
"step": 4100
},
{
"epoch": 0.9402283411685695,
"grad_norm": 9.19898796081543,
"learning_rate": 4.427528425888977e-08,
"loss": 0.8939,
"step": 4200
},
{
"epoch": 0.9626147302440117,
"grad_norm": 9.239889144897461,
"learning_rate": 1.7429748787176626e-08,
"loss": 0.9563,
"step": 4300
},
{
"epoch": 0.9850011193194538,
"grad_norm": 6.8510565757751465,
"learning_rate": 2.8583335326598516e-09,
"loss": 0.961,
"step": 4400
}
],
"logging_steps": 100,
"max_steps": 4467,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 100000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 2.417341778362368e+16,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}