Files

63 lines
1.5 KiB
JSON
Raw Permalink Normal View History

{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 219,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.22857142857142856,
"grad_norm": 0.5800270859104945,
"learning_rate": 9.062434390028407e-06,
"loss": 0.43176979064941406,
"step": 50
},
{
"epoch": 0.45714285714285713,
"grad_norm": 0.6300431299118571,
"learning_rate": 6.029893093705492e-06,
"loss": 0.3713723754882812,
"step": 100
},
{
"epoch": 0.6857142857142857,
"grad_norm": 0.5245981286124752,
"learning_rate": 2.457344406753899e-06,
"loss": 0.3548485565185547,
"step": 150
},
{
"epoch": 0.9142857142857143,
"grad_norm": 0.4934821853352409,
"learning_rate": 2.179950786173879e-07,
"loss": 0.354989013671875,
"step": 200
}
],
"logging_steps": 50,
"max_steps": 219,
"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": true
},
"attributes": {}
}
},
"total_flos": 6278015877120.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}