|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.00020433966360582879, |
|
"eval_steps": 2, |
|
"global_step": 4, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 5.1084915901457196e-05, |
|
"grad_norm": 3.2880730628967285, |
|
"learning_rate": 1e-05, |
|
"loss": 2.5327, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 5.1084915901457196e-05, |
|
"eval_loss": 2.525873899459839, |
|
"eval_runtime": 1259.9592, |
|
"eval_samples_per_second": 26.167, |
|
"eval_steps_per_second": 13.084, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.00010216983180291439, |
|
"grad_norm": 2.686666488647461, |
|
"learning_rate": 2e-05, |
|
"loss": 2.5567, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.00010216983180291439, |
|
"eval_loss": 2.491791009902954, |
|
"eval_runtime": 975.455, |
|
"eval_samples_per_second": 33.799, |
|
"eval_steps_per_second": 16.9, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.00015325474770437158, |
|
"grad_norm": 2.3463869094848633, |
|
"learning_rate": 3e-05, |
|
"loss": 2.4839, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.00020433966360582879, |
|
"grad_norm": 2.5627706050872803, |
|
"learning_rate": 4e-05, |
|
"loss": 2.2932, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.00020433966360582879, |
|
"eval_loss": 2.3392558097839355, |
|
"eval_runtime": 976.0151, |
|
"eval_samples_per_second": 33.779, |
|
"eval_steps_per_second": 16.89, |
|
"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": 3283829787721728.0, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|