|
{ |
|
"best_metric": 0.5, |
|
"best_model_checkpoint": "gemma-finetuned-spam/run-2/checkpoint-57", |
|
"epoch": 2.0, |
|
"eval_steps": 500, |
|
"global_step": 114, |
|
"is_hyper_param_search": true, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"eval_accuracy": 0.5, |
|
"eval_loss": 1.8851122856140137, |
|
"eval_runtime": 2.4925, |
|
"eval_samples_per_second": 20.061, |
|
"eval_steps_per_second": 10.03, |
|
"step": 57 |
|
}, |
|
{ |
|
"epoch": 1.7543859649122808, |
|
"grad_norm": 48.380149841308594, |
|
"learning_rate": 1.31634031080353e-06, |
|
"loss": 1.8582, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_accuracy": 0.5, |
|
"eval_loss": 1.693444848060608, |
|
"eval_runtime": 2.4568, |
|
"eval_samples_per_second": 20.351, |
|
"eval_steps_per_second": 10.176, |
|
"step": 114 |
|
} |
|
], |
|
"logging_steps": 100, |
|
"max_steps": 171, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 3, |
|
"save_steps": 100, |
|
"stateful_callbacks": { |
|
"EarlyStoppingCallback": { |
|
"args": { |
|
"early_stopping_patience": 1, |
|
"early_stopping_threshold": 0.0 |
|
}, |
|
"attributes": { |
|
"early_stopping_patience_counter": 1 |
|
} |
|
}, |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 4869057014661120.0, |
|
"train_batch_size": 8, |
|
"trial_name": null, |
|
"trial_params": { |
|
"learning_rate": 3.170340748554981e-06, |
|
"num_train_epochs": 3, |
|
"per_device_train_batch_size": 8, |
|
"seed": 25 |
|
} |
|
} |
|
|