|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.0010922247252372176, |
|
"eval_steps": 2, |
|
"global_step": 4, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0002730561813093044, |
|
"grad_norm": 0.07088964432477951, |
|
"learning_rate": 1e-05, |
|
"loss": 1.2514, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0002730561813093044, |
|
"eval_loss": 1.3034921884536743, |
|
"eval_runtime": 264.474, |
|
"eval_samples_per_second": 23.322, |
|
"eval_steps_per_second": 11.661, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0005461123626186088, |
|
"grad_norm": 0.07327114045619965, |
|
"learning_rate": 2e-05, |
|
"loss": 1.2596, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.0005461123626186088, |
|
"eval_loss": 1.3020037412643433, |
|
"eval_runtime": 264.1456, |
|
"eval_samples_per_second": 23.351, |
|
"eval_steps_per_second": 11.675, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.0008191685439279131, |
|
"grad_norm": 0.06202254816889763, |
|
"learning_rate": 3e-05, |
|
"loss": 1.2409, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.0010922247252372176, |
|
"grad_norm": 0.07336132228374481, |
|
"learning_rate": 4e-05, |
|
"loss": 1.2299, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.0010922247252372176, |
|
"eval_loss": 1.3011958599090576, |
|
"eval_runtime": 416.4721, |
|
"eval_samples_per_second": 14.81, |
|
"eval_steps_per_second": 7.405, |
|
"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": 556347552694272.0, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|