|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 2.9333333333333336, |
|
"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": 276.8177795410156, |
|
"learning_rate": 9.453408280367092e-05, |
|
"loss": 9.734, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.8888888888888888, |
|
"grad_norm": 104.99998474121094, |
|
"learning_rate": 7.913801073293639e-05, |
|
"loss": 10.6814, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 1.3333333333333333, |
|
"grad_norm": 11.027587890625, |
|
"learning_rate": 5.724440921850196e-05, |
|
"loss": 7.7392, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 1.7777777777777777, |
|
"grad_norm": 28.372657775878906, |
|
"learning_rate": 3.37353658459787e-05, |
|
"loss": 7.0622, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 2.2222222222222223, |
|
"grad_norm": 3.4534733295440674, |
|
"learning_rate": 1.3853198044178739e-05, |
|
"loss": 6.9932, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 2.6666666666666665, |
|
"grad_norm": 3.3354361057281494, |
|
"learning_rate": 2.031460728048701e-06, |
|
"loss": 6.8446, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 2.9333333333333336, |
|
"step": 66, |
|
"total_flos": 2.4665386651326874e+17, |
|
"train_loss": 8.046322331284031, |
|
"train_runtime": 1610.0642, |
|
"train_samples_per_second": 0.335, |
|
"train_steps_per_second": 0.041 |
|
} |
|
], |
|
"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": false, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 2.4665386651326874e+17, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|