|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.006683375104427736, |
|
"eval_steps": 3, |
|
"global_step": 10, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0006683375104427736, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0, |
|
"loss": 5.8583, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0006683375104427736, |
|
"eval_loss": 6.567427635192871, |
|
"eval_runtime": 12.5721, |
|
"eval_samples_per_second": 25.135, |
|
"eval_steps_per_second": 25.135, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0013366750208855473, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0, |
|
"loss": 6.9726, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.0020050125313283208, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0, |
|
"loss": 7.0245, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.0020050125313283208, |
|
"eval_loss": 6.567427635192871, |
|
"eval_runtime": 12.4056, |
|
"eval_samples_per_second": 25.472, |
|
"eval_steps_per_second": 25.472, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.0026733500417710945, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0, |
|
"loss": 6.3121, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.003341687552213868, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0, |
|
"loss": 6.5075, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.0040100250626566416, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0, |
|
"loss": 6.479, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.0040100250626566416, |
|
"eval_loss": 6.567427635192871, |
|
"eval_runtime": 12.9457, |
|
"eval_samples_per_second": 24.41, |
|
"eval_steps_per_second": 24.41, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.004678362573099415, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0, |
|
"loss": 5.702, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.005346700083542189, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0, |
|
"loss": 5.4896, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.006015037593984963, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0, |
|
"loss": 5.3384, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.006015037593984963, |
|
"eval_loss": 6.567427635192871, |
|
"eval_runtime": 12.5182, |
|
"eval_samples_per_second": 25.243, |
|
"eval_steps_per_second": 25.243, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.006683375104427736, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0, |
|
"loss": 6.3319, |
|
"step": 10 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 10, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 3, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 255791978250240.0, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|