|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.896, |
|
"eval_steps": 30, |
|
"global_step": 7, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.128, |
|
"grad_norm": 1.7210274934768677, |
|
"learning_rate": 2.5714285714285714e-05, |
|
"loss": 10.176, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.256, |
|
"grad_norm": 1.5320605039596558, |
|
"learning_rate": 2.1428571428571428e-05, |
|
"loss": 10.1016, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.384, |
|
"grad_norm": 1.8677138090133667, |
|
"learning_rate": 1.7142857142857142e-05, |
|
"loss": 10.1503, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.512, |
|
"grad_norm": 1.860098123550415, |
|
"learning_rate": 1.2857142857142857e-05, |
|
"loss": 10.0642, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"grad_norm": 1.9219690561294556, |
|
"learning_rate": 8.571428571428571e-06, |
|
"loss": 10.0105, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.768, |
|
"grad_norm": 2.151355743408203, |
|
"learning_rate": 4.2857142857142855e-06, |
|
"loss": 10.1061, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.896, |
|
"grad_norm": 2.104682445526123, |
|
"learning_rate": 0.0, |
|
"loss": 10.1254, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.896, |
|
"step": 7, |
|
"total_flos": 94839606729324.0, |
|
"train_loss": 10.104869842529297, |
|
"train_runtime": 2106.6171, |
|
"train_samples_per_second": 0.059, |
|
"train_steps_per_second": 0.003 |
|
} |
|
], |
|
"logging_steps": 1.0, |
|
"max_steps": 7, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 500, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": false, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 94839606729324.0, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|