|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.001471264367816092, |
|
"eval_steps": 2, |
|
"global_step": 5, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0002942528735632184, |
|
"grad_norm": NaN, |
|
"learning_rate": 1e-05, |
|
"loss": 2950.9355, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0002942528735632184, |
|
"eval_loss": NaN, |
|
"eval_runtime": 397.2054, |
|
"eval_samples_per_second": 14.411, |
|
"eval_steps_per_second": 7.205, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0005885057471264368, |
|
"grad_norm": NaN, |
|
"learning_rate": 2e-05, |
|
"loss": 4.9036, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.0005885057471264368, |
|
"eval_loss": NaN, |
|
"eval_runtime": 269.0869, |
|
"eval_samples_per_second": 21.272, |
|
"eval_steps_per_second": 10.636, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.0008827586206896551, |
|
"grad_norm": NaN, |
|
"learning_rate": 3e-05, |
|
"loss": 152.525, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.0011770114942528736, |
|
"grad_norm": NaN, |
|
"learning_rate": 4e-05, |
|
"loss": 262.7611, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.0011770114942528736, |
|
"eval_loss": NaN, |
|
"eval_runtime": 364.5475, |
|
"eval_samples_per_second": 15.702, |
|
"eval_steps_per_second": 7.851, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.001471264367816092, |
|
"grad_norm": NaN, |
|
"learning_rate": 5e-05, |
|
"loss": 157.4376, |
|
"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": 7324871593820160.0, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|