|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.9824561403508771, |
|
"eval_steps": 500, |
|
"global_step": 42, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.11695906432748537, |
|
"grad_norm": 1.7820518016815186, |
|
"learning_rate": 0.0002, |
|
"loss": 3.8601, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.23391812865497075, |
|
"grad_norm": 2.071708917617798, |
|
"learning_rate": 0.0002, |
|
"loss": 3.0122, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.3508771929824561, |
|
"grad_norm": 3.0540826320648193, |
|
"learning_rate": 0.0002, |
|
"loss": 2.3113, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.4678362573099415, |
|
"grad_norm": 2.741673707962036, |
|
"learning_rate": 0.0002, |
|
"loss": 1.862, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.5847953216374269, |
|
"grad_norm": 1.061865210533142, |
|
"learning_rate": 0.0002, |
|
"loss": 1.5215, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.7017543859649122, |
|
"grad_norm": 1.1919221878051758, |
|
"learning_rate": 0.0002, |
|
"loss": 1.3492, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.8187134502923976, |
|
"grad_norm": 1.1614408493041992, |
|
"learning_rate": 0.0002, |
|
"loss": 1.3886, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.935672514619883, |
|
"grad_norm": 1.2684136629104614, |
|
"learning_rate": 0.0002, |
|
"loss": 1.3099, |
|
"step": 40 |
|
} |
|
], |
|
"logging_steps": 5, |
|
"max_steps": 126, |
|
"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": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 1.867198522265088e+16, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|