|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.0004321667083077297, |
|
"eval_steps": 2, |
|
"global_step": 4, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.00010804167707693242, |
|
"grad_norm": 0.7540108561515808, |
|
"learning_rate": 1e-05, |
|
"loss": 2.4735, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.00010804167707693242, |
|
"eval_loss": 2.4876058101654053, |
|
"eval_runtime": 861.0072, |
|
"eval_samples_per_second": 18.106, |
|
"eval_steps_per_second": 9.053, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.00021608335415386484, |
|
"grad_norm": 0.8363262414932251, |
|
"learning_rate": 2e-05, |
|
"loss": 2.35, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.00021608335415386484, |
|
"eval_loss": 2.474978446960449, |
|
"eval_runtime": 960.8052, |
|
"eval_samples_per_second": 16.225, |
|
"eval_steps_per_second": 8.113, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.0003241250312307973, |
|
"grad_norm": 0.7855400443077087, |
|
"learning_rate": 3e-05, |
|
"loss": 2.5276, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.0004321667083077297, |
|
"grad_norm": 0.6721187829971313, |
|
"learning_rate": 4e-05, |
|
"loss": 2.5383, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.0004321667083077297, |
|
"eval_loss": 2.45807147026062, |
|
"eval_runtime": 1219.4576, |
|
"eval_samples_per_second": 12.784, |
|
"eval_steps_per_second": 6.392, |
|
"step": 4 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 5, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 2, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 5779888275456000.0, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|