|
{
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.16,
|
|
"eval_steps": 500,
|
|
"global_step": 100,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 0.032,
|
|
"grad_norm": 1.181923270225525,
|
|
"learning_rate": 4.522542485937369e-05,
|
|
"loss": 1.7744,
|
|
"step": 20
|
|
},
|
|
{
|
|
"epoch": 0.064,
|
|
"grad_norm": 1.2756545543670654,
|
|
"learning_rate": 3.272542485937369e-05,
|
|
"loss": 1.515,
|
|
"step": 40
|
|
},
|
|
{
|
|
"epoch": 0.096,
|
|
"grad_norm": 1.3430900573730469,
|
|
"learning_rate": 1.7274575140626318e-05,
|
|
"loss": 1.5067,
|
|
"step": 60
|
|
},
|
|
{
|
|
"epoch": 0.128,
|
|
"grad_norm": 1.454408884048462,
|
|
"learning_rate": 4.7745751406263165e-06,
|
|
"loss": 1.4885,
|
|
"step": 80
|
|
},
|
|
{
|
|
"epoch": 0.16,
|
|
"grad_norm": 1.6402275562286377,
|
|
"learning_rate": 0.0,
|
|
"loss": 1.4651,
|
|
"step": 100
|
|
}
|
|
],
|
|
"logging_steps": 20,
|
|
"max_steps": 100,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 1,
|
|
"save_steps": 100,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": true
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 3.581736838992691e+16,
|
|
"train_batch_size": 1,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|
|
|