|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 10.0, |
|
"eval_steps": 500, |
|
"global_step": 10, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"grad_norm": 17.570717480629625, |
|
"learning_rate": 1e-05, |
|
"loss": 1.1064, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 1.116378664970398, |
|
"eval_runtime": 2.7633, |
|
"eval_samples_per_second": 8.685, |
|
"eval_steps_per_second": 0.724, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_loss": 1.234288215637207, |
|
"eval_runtime": 2.7167, |
|
"eval_samples_per_second": 8.834, |
|
"eval_steps_per_second": 0.736, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_loss": 0.9905319213867188, |
|
"eval_runtime": 2.7356, |
|
"eval_samples_per_second": 8.773, |
|
"eval_steps_per_second": 0.731, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"eval_loss": 0.712308406829834, |
|
"eval_runtime": 2.7104, |
|
"eval_samples_per_second": 8.855, |
|
"eval_steps_per_second": 0.738, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"grad_norm": 22.309413100632455, |
|
"learning_rate": 5.8682408883346535e-06, |
|
"loss": 1.0149, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"eval_loss": 0.5842603445053101, |
|
"eval_runtime": 2.7186, |
|
"eval_samples_per_second": 8.828, |
|
"eval_steps_per_second": 0.736, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 6.0, |
|
"eval_loss": 0.43497833609580994, |
|
"eval_runtime": 2.7203, |
|
"eval_samples_per_second": 8.823, |
|
"eval_steps_per_second": 0.735, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 7.0, |
|
"eval_loss": 0.349648118019104, |
|
"eval_runtime": 2.7121, |
|
"eval_samples_per_second": 8.849, |
|
"eval_steps_per_second": 0.737, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 8.0, |
|
"eval_loss": 0.298780232667923, |
|
"eval_runtime": 2.7204, |
|
"eval_samples_per_second": 8.822, |
|
"eval_steps_per_second": 0.735, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 9.0, |
|
"eval_loss": 0.26783373951911926, |
|
"eval_runtime": 2.7269, |
|
"eval_samples_per_second": 8.801, |
|
"eval_steps_per_second": 0.733, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"grad_norm": 3.99720130224049, |
|
"learning_rate": 0.0, |
|
"loss": 0.3844, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"step": 10, |
|
"total_flos": 2093796556800.0, |
|
"train_loss": 0.0, |
|
"train_runtime": 1.6028, |
|
"train_samples_per_second": 149.735, |
|
"train_steps_per_second": 6.239 |
|
} |
|
], |
|
"logging_steps": 5, |
|
"max_steps": 10, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 10, |
|
"save_steps": 100, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 2093796556800.0, |
|
"train_batch_size": 8, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|