|
{ |
|
"best_global_step": null, |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.04325259515570934, |
|
"eval_steps": 500, |
|
"global_step": 50, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.00865051903114187, |
|
"grad_norm": 0.6758226156234741, |
|
"learning_rate": 5.142857142857142e-06, |
|
"loss": 2.4878, |
|
"mean_token_accuracy": 0.5207233637571335, |
|
"num_tokens": 20480.0, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.01730103806228374, |
|
"grad_norm": 0.527189314365387, |
|
"learning_rate": 1.0857142857142858e-05, |
|
"loss": 2.2677, |
|
"mean_token_accuracy": 0.5652981504797936, |
|
"num_tokens": 40960.0, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.025951557093425604, |
|
"grad_norm": 0.5320698022842407, |
|
"learning_rate": 1.6571428571428574e-05, |
|
"loss": 2.3177, |
|
"mean_token_accuracy": 0.5567937418818474, |
|
"num_tokens": 61440.0, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.03460207612456748, |
|
"grad_norm": 0.4314405918121338, |
|
"learning_rate": 1.9999371690018227e-05, |
|
"loss": 2.1426, |
|
"mean_token_accuracy": 0.571554248034954, |
|
"num_tokens": 81920.0, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.04325259515570934, |
|
"grad_norm": 0.413466215133667, |
|
"learning_rate": 1.9992304109437157e-05, |
|
"loss": 2.2219, |
|
"mean_token_accuracy": 0.5544477015733719, |
|
"num_tokens": 102400.0, |
|
"step": 50 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 1156, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 50, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 1749313545830400.0, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|