|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.0011350536490201295, |
|
"eval_steps": 2, |
|
"global_step": 4, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0002837634122550324, |
|
"grad_norm": 58.883934020996094, |
|
"learning_rate": 1e-05, |
|
"loss": 101.3309, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0002837634122550324, |
|
"eval_loss": 5.771067142486572, |
|
"eval_runtime": 1086.1671, |
|
"eval_samples_per_second": 5.465, |
|
"eval_steps_per_second": 2.733, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0005675268245100648, |
|
"grad_norm": 48.294700622558594, |
|
"learning_rate": 2e-05, |
|
"loss": 73.711, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.0005675268245100648, |
|
"eval_loss": 5.677567005157471, |
|
"eval_runtime": 1770.5338, |
|
"eval_samples_per_second": 3.353, |
|
"eval_steps_per_second": 1.676, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.0008512902367650971, |
|
"grad_norm": 50.551979064941406, |
|
"learning_rate": 3e-05, |
|
"loss": 68.4265, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.0011350536490201295, |
|
"grad_norm": 50.849205017089844, |
|
"learning_rate": 4e-05, |
|
"loss": 87.0254, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.0011350536490201295, |
|
"eval_loss": 5.592475891113281, |
|
"eval_runtime": 992.8782, |
|
"eval_samples_per_second": 5.979, |
|
"eval_steps_per_second": 2.989, |
|
"step": 4 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 5, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 2, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 2605973017460736.0, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|