multitoken_ft_v2 / checkpoint-11110 /trainer_state.json
Goldenwert's picture
Upload folder using huggingface_hub
cddc00e verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 11110,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0450070323488045,
"grad_norm": 57.50090789794922,
"learning_rate": 4.7754275427542756e-05,
"loss": 4.3526,
"step": 500
},
{
"epoch": 0.090014064697609,
"grad_norm": 33.234798431396484,
"learning_rate": 4.55040504050405e-05,
"loss": 1.6131,
"step": 1000
},
{
"epoch": 0.1350210970464135,
"grad_norm": 40.48593521118164,
"learning_rate": 4.325382538253826e-05,
"loss": 1.3157,
"step": 1500
},
{
"epoch": 0.180028129395218,
"grad_norm": 34.0600700378418,
"learning_rate": 4.1003600360036004e-05,
"loss": 1.1683,
"step": 2000
},
{
"epoch": 0.2250351617440225,
"grad_norm": 11.524826049804688,
"learning_rate": 3.875337533753375e-05,
"loss": 1.0973,
"step": 2500
},
{
"epoch": 0.270042194092827,
"grad_norm": 35.38045120239258,
"learning_rate": 3.6503150315031505e-05,
"loss": 1.0251,
"step": 3000
},
{
"epoch": 0.3150492264416315,
"grad_norm": 13.695218086242676,
"learning_rate": 3.425292529252925e-05,
"loss": 0.958,
"step": 3500
},
{
"epoch": 0.360056258790436,
"grad_norm": 14.775146484375,
"learning_rate": 3.2002700270027e-05,
"loss": 0.9002,
"step": 4000
},
{
"epoch": 0.4050632911392405,
"grad_norm": 9.160333633422852,
"learning_rate": 2.9752475247524754e-05,
"loss": 0.8585,
"step": 4500
},
{
"epoch": 0.450070323488045,
"grad_norm": 7.049114227294922,
"learning_rate": 2.75022502250225e-05,
"loss": 0.8319,
"step": 5000
},
{
"epoch": 0.49507735583684953,
"grad_norm": 7.8238115310668945,
"learning_rate": 2.525202520252025e-05,
"loss": 0.8034,
"step": 5500
},
{
"epoch": 0.540084388185654,
"grad_norm": 5.348775863647461,
"learning_rate": 2.3001800180018002e-05,
"loss": 0.7809,
"step": 6000
},
{
"epoch": 0.5850914205344585,
"grad_norm": 8.474061012268066,
"learning_rate": 2.0751575157515752e-05,
"loss": 0.763,
"step": 6500
},
{
"epoch": 0.630098452883263,
"grad_norm": 7.072192192077637,
"learning_rate": 1.85013501350135e-05,
"loss": 0.7535,
"step": 7000
},
{
"epoch": 0.6751054852320675,
"grad_norm": 7.099096775054932,
"learning_rate": 1.625112511251125e-05,
"loss": 0.7386,
"step": 7500
},
{
"epoch": 0.720112517580872,
"grad_norm": 6.223616600036621,
"learning_rate": 1.4000900090009e-05,
"loss": 0.73,
"step": 8000
},
{
"epoch": 0.7651195499296765,
"grad_norm": 4.832330703735352,
"learning_rate": 1.1750675067506751e-05,
"loss": 0.7213,
"step": 8500
},
{
"epoch": 0.810126582278481,
"grad_norm": 3.9546172618865967,
"learning_rate": 9.500450045004502e-06,
"loss": 0.7076,
"step": 9000
},
{
"epoch": 0.8551336146272855,
"grad_norm": 3.895390510559082,
"learning_rate": 7.250225022502251e-06,
"loss": 0.7049,
"step": 9500
},
{
"epoch": 0.90014064697609,
"grad_norm": 4.706455230712891,
"learning_rate": 5e-06,
"loss": 0.705,
"step": 10000
},
{
"epoch": 0.9451476793248945,
"grad_norm": 3.554635524749756,
"learning_rate": 2.7497749774977497e-06,
"loss": 0.7032,
"step": 10500
},
{
"epoch": 0.9901547116736991,
"grad_norm": 3.6398956775665283,
"learning_rate": 4.995499549954995e-07,
"loss": 0.6962,
"step": 11000
}
],
"logging_steps": 500,
"max_steps": 11110,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 99999999,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 0.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}