|
{ |
|
"best_global_step": null, |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 2.977777777777778, |
|
"eval_steps": 500, |
|
"global_step": 66, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.4444444444444444, |
|
"grad_norm": 2.2113311290740967, |
|
"learning_rate": 4.996456739191905e-05, |
|
"loss": 1.9772, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.8888888888888888, |
|
"grad_norm": 0.5997061133384705, |
|
"learning_rate": 4.5832847977062874e-05, |
|
"loss": 1.1074, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 1.3555555555555556, |
|
"grad_norm": 0.2707456648349762, |
|
"learning_rate": 3.593268301147139e-05, |
|
"loss": 1.0178, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 1.8, |
|
"grad_norm": 0.24949735403060913, |
|
"learning_rate": 2.300534736117292e-05, |
|
"loss": 0.9034, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 2.2666666666666666, |
|
"grad_norm": 0.23965899646282196, |
|
"learning_rate": 1.063031474463983e-05, |
|
"loss": 0.9639, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 2.7111111111111112, |
|
"grad_norm": 0.3781649172306061, |
|
"learning_rate": 2.2341306786271695e-06, |
|
"loss": 0.8663, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 2.977777777777778, |
|
"step": 66, |
|
"total_flos": 2.191733634052915e+16, |
|
"train_loss": 1.115423397584395, |
|
"train_runtime": 175.9178, |
|
"train_samples_per_second": 6.088, |
|
"train_steps_per_second": 0.375 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 66, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 3, |
|
"save_steps": 500, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 2.191733634052915e+16, |
|
"train_batch_size": 4, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|