|
{
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 5.0,
|
|
"eval_steps": 500,
|
|
"global_step": 1870,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 1.0,
|
|
"eval_loss": 0.703195333480835,
|
|
"eval_runtime": 211.7753,
|
|
"eval_samples_per_second": 3.532,
|
|
"eval_steps_per_second": 0.444,
|
|
"step": 374
|
|
},
|
|
{
|
|
"epoch": 1.3368983957219251,
|
|
"grad_norm": 0.5129834413528442,
|
|
"learning_rate": 1.4652406417112302e-05,
|
|
"loss": 2.9329,
|
|
"step": 500
|
|
},
|
|
{
|
|
"epoch": 2.0,
|
|
"eval_loss": 0.6699346303939819,
|
|
"eval_runtime": 210.8953,
|
|
"eval_samples_per_second": 3.547,
|
|
"eval_steps_per_second": 0.446,
|
|
"step": 748
|
|
},
|
|
{
|
|
"epoch": 2.6737967914438503,
|
|
"grad_norm": 0.537359356880188,
|
|
"learning_rate": 9.3048128342246e-06,
|
|
"loss": 0.6964,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"epoch": 3.0,
|
|
"eval_loss": 0.655941903591156,
|
|
"eval_runtime": 210.9443,
|
|
"eval_samples_per_second": 3.546,
|
|
"eval_steps_per_second": 0.446,
|
|
"step": 1122
|
|
},
|
|
{
|
|
"epoch": 4.0,
|
|
"eval_loss": 0.6526938676834106,
|
|
"eval_runtime": 211.2934,
|
|
"eval_samples_per_second": 3.54,
|
|
"eval_steps_per_second": 0.445,
|
|
"step": 1496
|
|
},
|
|
{
|
|
"epoch": 4.010695187165775,
|
|
"grad_norm": 0.4965839087963104,
|
|
"learning_rate": 3.957219251336899e-06,
|
|
"loss": 0.6599,
|
|
"step": 1500
|
|
}
|
|
],
|
|
"logging_steps": 500,
|
|
"max_steps": 1870,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 5,
|
|
"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": 1.087284373880832e+16,
|
|
"train_batch_size": 8,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|
|
|