|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.0003312629399585921, |
|
"eval_steps": 2, |
|
"global_step": 5, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 6.625258799171843e-05, |
|
"grad_norm": 2.1340200901031494, |
|
"learning_rate": 1e-05, |
|
"loss": 2.6955, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 6.625258799171843e-05, |
|
"eval_loss": 2.6818182468414307, |
|
"eval_runtime": 1129.5815, |
|
"eval_samples_per_second": 22.505, |
|
"eval_steps_per_second": 11.253, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.00013250517598343685, |
|
"grad_norm": 2.296602725982666, |
|
"learning_rate": 2e-05, |
|
"loss": 2.7052, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.00013250517598343685, |
|
"eval_loss": 2.647152900695801, |
|
"eval_runtime": 1087.1871, |
|
"eval_samples_per_second": 23.382, |
|
"eval_steps_per_second": 11.692, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.00019875776397515528, |
|
"grad_norm": 2.361423969268799, |
|
"learning_rate": 3e-05, |
|
"loss": 2.6662, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.0002650103519668737, |
|
"grad_norm": 2.1118416786193848, |
|
"learning_rate": 4e-05, |
|
"loss": 2.8258, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.0002650103519668737, |
|
"eval_loss": 2.5488884449005127, |
|
"eval_runtime": 1132.1276, |
|
"eval_samples_per_second": 22.454, |
|
"eval_steps_per_second": 11.228, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.0003312629399585921, |
|
"grad_norm": 2.3176746368408203, |
|
"learning_rate": 5e-05, |
|
"loss": 2.5634, |
|
"step": 5 |
|
} |
|
], |
|
"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": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 5637719677992960.0, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|