|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 3.0, |
|
"eval_steps": 500, |
|
"global_step": 33, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.9090909090909091, |
|
"grad_norm": 2.6606567665052214, |
|
"learning_rate": 5e-06, |
|
"loss": 0.8806, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 0.806667685508728, |
|
"eval_runtime": 8.0665, |
|
"eval_samples_per_second": 36.571, |
|
"eval_steps_per_second": 0.62, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 1.8181818181818183, |
|
"grad_norm": 1.0920052502671431, |
|
"learning_rate": 5e-06, |
|
"loss": 0.7689, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_loss": 0.7631939053535461, |
|
"eval_runtime": 7.7967, |
|
"eval_samples_per_second": 37.837, |
|
"eval_steps_per_second": 0.641, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 2.7272727272727275, |
|
"grad_norm": 1.200611383191004, |
|
"learning_rate": 5e-06, |
|
"loss": 0.7125, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_loss": 0.7436400055885315, |
|
"eval_runtime": 6.7975, |
|
"eval_samples_per_second": 43.399, |
|
"eval_steps_per_second": 0.736, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"step": 33, |
|
"total_flos": 55066849443840.0, |
|
"train_loss": 0.7791701663624157, |
|
"train_runtime": 1261.7876, |
|
"train_samples_per_second": 13.284, |
|
"train_steps_per_second": 0.026 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 33, |
|
"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": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 55066849443840.0, |
|
"train_batch_size": 8, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|