|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.028303555634176542, |
|
"eval_steps": 5, |
|
"global_step": 5, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0056607111268353084, |
|
"grad_norm": 0.24056661128997803, |
|
"learning_rate": 1e-05, |
|
"loss": 10.4071, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0056607111268353084, |
|
"eval_loss": 10.435810089111328, |
|
"eval_runtime": 7.8807, |
|
"eval_samples_per_second": 75.501, |
|
"eval_steps_per_second": 37.814, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.011321422253670617, |
|
"grad_norm": 0.2668295204639435, |
|
"learning_rate": 2e-05, |
|
"loss": 10.4373, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.016982133380505925, |
|
"grad_norm": 0.23038893938064575, |
|
"learning_rate": 3e-05, |
|
"loss": 10.4385, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.022642844507341234, |
|
"grad_norm": 0.2281711995601654, |
|
"learning_rate": 4e-05, |
|
"loss": 10.4232, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.028303555634176542, |
|
"grad_norm": 0.2743370532989502, |
|
"learning_rate": 5e-05, |
|
"loss": 10.4297, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.028303555634176542, |
|
"eval_loss": 10.434837341308594, |
|
"eval_runtime": 7.8713, |
|
"eval_samples_per_second": 75.591, |
|
"eval_steps_per_second": 37.859, |
|
"step": 5 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 20, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 5, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 4184195727360.0, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|