|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 25.0, |
|
"eval_steps": 500, |
|
"global_step": 3050, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 4.098360655737705, |
|
"grad_norm": 1.2930060625076294, |
|
"learning_rate": 0.00046757131025753886, |
|
"loss": 0.6295, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 8.19672131147541, |
|
"grad_norm": 1.416014313697815, |
|
"learning_rate": 0.00037869820037745775, |
|
"loss": 0.2831, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 12.295081967213115, |
|
"grad_norm": 0.8189792037010193, |
|
"learning_rate": 0.0002564369784137472, |
|
"loss": 0.1604, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 16.39344262295082, |
|
"grad_norm": 2.0649912357330322, |
|
"learning_rate": 0.0001325058142431701, |
|
"loss": 0.1006, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 20.491803278688526, |
|
"grad_norm": 1.0378129482269287, |
|
"learning_rate": 3.905611004420359e-05, |
|
"loss": 0.0709, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 24.59016393442623, |
|
"grad_norm": 0.8734142184257507, |
|
"learning_rate": 3.314775287923677e-07, |
|
"loss": 0.0612, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 25.0, |
|
"step": 3050, |
|
"total_flos": 2757779000721408.0, |
|
"train_loss": 0.21498731050334993, |
|
"train_runtime": 248.6198, |
|
"train_samples_per_second": 392.366, |
|
"train_steps_per_second": 12.268 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 3050, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 25, |
|
"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": 2757779000721408.0, |
|
"train_batch_size": 32, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|