|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.0008428238814146799, |
|
"eval_steps": 2, |
|
"global_step": 5, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.00016856477628293597, |
|
"grad_norm": NaN, |
|
"learning_rate": 1e-05, |
|
"loss": 0.0, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.00016856477628293597, |
|
"eval_loss": NaN, |
|
"eval_runtime": 378.2651, |
|
"eval_samples_per_second": 26.415, |
|
"eval_steps_per_second": 13.208, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.00033712955256587194, |
|
"grad_norm": NaN, |
|
"learning_rate": 2e-05, |
|
"loss": 274.9339, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.00033712955256587194, |
|
"eval_loss": NaN, |
|
"eval_runtime": 294.5395, |
|
"eval_samples_per_second": 33.924, |
|
"eval_steps_per_second": 16.962, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.0005056943288488079, |
|
"grad_norm": NaN, |
|
"learning_rate": 3e-05, |
|
"loss": 0.0, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.0006742591051317439, |
|
"grad_norm": NaN, |
|
"learning_rate": 4e-05, |
|
"loss": 37.1486, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.0006742591051317439, |
|
"eval_loss": NaN, |
|
"eval_runtime": 366.7163, |
|
"eval_samples_per_second": 27.247, |
|
"eval_steps_per_second": 13.624, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.0008428238814146799, |
|
"grad_norm": NaN, |
|
"learning_rate": 5e-05, |
|
"loss": 12.0458, |
|
"step": 5 |
|
} |
|
], |
|
"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": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 5082742379249664.0, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|