|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.044444444444444446, |
|
"eval_steps": 4, |
|
"global_step": 5, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.008888888888888889, |
|
"grad_norm": 0.3842334449291229, |
|
"learning_rate": 0.0001, |
|
"loss": 1.6342, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.017777777777777778, |
|
"grad_norm": 0.3358556032180786, |
|
"learning_rate": 8.535533905932738e-05, |
|
"loss": 1.4708, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.02666666666666667, |
|
"grad_norm": 0.3367025852203369, |
|
"learning_rate": 5e-05, |
|
"loss": 1.4667, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.035555555555555556, |
|
"grad_norm": 0.3284144699573517, |
|
"learning_rate": 1.4644660940672627e-05, |
|
"loss": 1.5967, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.035555555555555556, |
|
"eval_accuracy": 0.5943584982531214, |
|
"eval_loss": 1.5761107206344604, |
|
"eval_runtime": 22.9023, |
|
"eval_samples_per_second": 4.366, |
|
"eval_steps_per_second": 4.366, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.044444444444444446, |
|
"grad_norm": 0.33207380771636963, |
|
"learning_rate": 0.0, |
|
"loss": 1.5693, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.044444444444444446, |
|
"step": 5, |
|
"total_flos": 335088840425472.0, |
|
"train_loss": 1.547522735595703, |
|
"train_runtime": 53.6437, |
|
"train_samples_per_second": 0.746, |
|
"train_steps_per_second": 0.093 |
|
} |
|
], |
|
"logging_steps": 1.0, |
|
"max_steps": 5, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 4, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 335088840425472.0, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|