|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.0022531244499207886, |
|
"eval_steps": 2, |
|
"global_step": 4, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0005632811124801971, |
|
"grad_norm": 12.581334114074707, |
|
"learning_rate": 1e-05, |
|
"loss": 60.8259, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0005632811124801971, |
|
"eval_loss": 3.8450818061828613, |
|
"eval_runtime": 606.5788, |
|
"eval_samples_per_second": 4.929, |
|
"eval_steps_per_second": 2.465, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0011265622249603943, |
|
"grad_norm": 11.610177040100098, |
|
"learning_rate": 2e-05, |
|
"loss": 61.5924, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.0011265622249603943, |
|
"eval_loss": 3.8027493953704834, |
|
"eval_runtime": 624.7617, |
|
"eval_samples_per_second": 4.786, |
|
"eval_steps_per_second": 2.393, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.0016898433374405914, |
|
"grad_norm": 11.927529335021973, |
|
"learning_rate": 3e-05, |
|
"loss": 62.9045, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.0022531244499207886, |
|
"grad_norm": 13.698987007141113, |
|
"learning_rate": 4e-05, |
|
"loss": 62.3275, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.0022531244499207886, |
|
"eval_loss": 3.778285026550293, |
|
"eval_runtime": 644.7439, |
|
"eval_samples_per_second": 4.638, |
|
"eval_steps_per_second": 2.319, |
|
"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": 4764091532967936.0, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|