|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.015356265356265357, |
|
"eval_steps": 25, |
|
"global_step": 25, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0006142506142506142, |
|
"eval_loss": 3.9348061084747314, |
|
"eval_runtime": 105.8239, |
|
"eval_samples_per_second": 1.71, |
|
"eval_steps_per_second": 1.71, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.003071253071253071, |
|
"grad_norm": 2.589426040649414, |
|
"learning_rate": 5e-05, |
|
"loss": 3.7832, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.006142506142506142, |
|
"grad_norm": 5.146238803863525, |
|
"learning_rate": 0.0001, |
|
"loss": 4.0256, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.009213759213759214, |
|
"grad_norm": 4.875488758087158, |
|
"learning_rate": 9.619397662556435e-05, |
|
"loss": 3.8025, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.012285012285012284, |
|
"grad_norm": 5.637850761413574, |
|
"learning_rate": 8.535533905932738e-05, |
|
"loss": 3.4333, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.015356265356265357, |
|
"grad_norm": 6.818943500518799, |
|
"learning_rate": 6.91341716182545e-05, |
|
"loss": 2.7664, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.015356265356265357, |
|
"eval_loss": 3.3277134895324707, |
|
"eval_runtime": 106.2761, |
|
"eval_samples_per_second": 1.703, |
|
"eval_steps_per_second": 1.703, |
|
"step": 25 |
|
} |
|
], |
|
"logging_steps": 5, |
|
"max_steps": 50, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 25, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 4132166959104000.0, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|