|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.00259665320253895, |
|
"eval_steps": 3, |
|
"global_step": 9, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.00028851702250432774, |
|
"grad_norm": NaN, |
|
"learning_rate": 2e-05, |
|
"loss": 0.0, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.00028851702250432774, |
|
"eval_loss": NaN, |
|
"eval_runtime": 44.6146, |
|
"eval_samples_per_second": 32.725, |
|
"eval_steps_per_second": 16.362, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0005770340450086555, |
|
"grad_norm": NaN, |
|
"learning_rate": 4e-05, |
|
"loss": 0.0, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.0008655510675129833, |
|
"grad_norm": NaN, |
|
"learning_rate": 6e-05, |
|
"loss": 0.0, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.0008655510675129833, |
|
"eval_loss": NaN, |
|
"eval_runtime": 43.2675, |
|
"eval_samples_per_second": 33.744, |
|
"eval_steps_per_second": 16.872, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.001154068090017311, |
|
"grad_norm": NaN, |
|
"learning_rate": 8e-05, |
|
"loss": 0.0, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.0014425851125216388, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.0017311021350259665, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.00012, |
|
"loss": 0.0, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.0017311021350259665, |
|
"eval_loss": NaN, |
|
"eval_runtime": 43.4516, |
|
"eval_samples_per_second": 33.601, |
|
"eval_steps_per_second": 16.8, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.002019619157530294, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.00014, |
|
"loss": 0.0, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.002308136180034622, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.00016, |
|
"loss": 0.0, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.00259665320253895, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.00018, |
|
"loss": 0.0, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.00259665320253895, |
|
"eval_loss": NaN, |
|
"eval_runtime": 43.2875, |
|
"eval_samples_per_second": 33.728, |
|
"eval_steps_per_second": 16.864, |
|
"step": 9 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 10, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 3, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 1577404619292672.0, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|