|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.004957243772462511, |
|
"eval_steps": 5, |
|
"global_step": 5, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0009914487544925021, |
|
"grad_norm": 0.604952871799469, |
|
"learning_rate": 1e-05, |
|
"loss": 3.1854, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0009914487544925021, |
|
"eval_loss": 3.30363392829895, |
|
"eval_runtime": 78.7969, |
|
"eval_samples_per_second": 21.562, |
|
"eval_steps_per_second": 10.787, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0019828975089850043, |
|
"grad_norm": 0.5781750679016113, |
|
"learning_rate": 2e-05, |
|
"loss": 3.1779, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.0029743462634775064, |
|
"grad_norm": 0.7077589631080627, |
|
"learning_rate": 3e-05, |
|
"loss": 3.4209, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.0039657950179700086, |
|
"grad_norm": 0.6238883137702942, |
|
"learning_rate": 4e-05, |
|
"loss": 3.2321, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.004957243772462511, |
|
"grad_norm": 0.6038368344306946, |
|
"learning_rate": 5e-05, |
|
"loss": 3.2133, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.004957243772462511, |
|
"eval_loss": 3.2816126346588135, |
|
"eval_runtime": 7.5553, |
|
"eval_samples_per_second": 224.876, |
|
"eval_steps_per_second": 112.504, |
|
"step": 5 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 20, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 5, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 72871882260480.0, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|