|
{ |
|
"best_metric": 0.9300746034490112, |
|
"best_model_checkpoint": "model_checkpoints/fine-tuned_snips/deberta-v3-small/checkpoint-430", |
|
"epoch": 5.0, |
|
"eval_steps": 500, |
|
"global_step": 430, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"grad_norm": 70.6190185546875, |
|
"learning_rate": 4.0232558139534885e-05, |
|
"loss": 1.5849, |
|
"step": 86 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_accuracy": 0.6188034188034188, |
|
"eval_f1": 0.5633655833196575, |
|
"eval_loss": 1.0251919031143188, |
|
"eval_runtime": 41.3418, |
|
"eval_samples_per_second": 14.15, |
|
"eval_steps_per_second": 3.556, |
|
"step": 86 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"grad_norm": 51.66825485229492, |
|
"learning_rate": 3.0348837209302327e-05, |
|
"loss": 0.5988, |
|
"step": 172 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_accuracy": 0.8666666666666667, |
|
"eval_f1": 0.8606784405256506, |
|
"eval_loss": 0.4364546239376068, |
|
"eval_runtime": 41.2466, |
|
"eval_samples_per_second": 14.183, |
|
"eval_steps_per_second": 3.564, |
|
"step": 172 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"grad_norm": 3.9022738933563232, |
|
"learning_rate": 2.0348837209302328e-05, |
|
"loss": 0.2244, |
|
"step": 258 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_accuracy": 0.9042735042735043, |
|
"eval_f1": 0.9039006924540784, |
|
"eval_loss": 0.34247514605522156, |
|
"eval_runtime": 41.3132, |
|
"eval_samples_per_second": 14.16, |
|
"eval_steps_per_second": 3.558, |
|
"step": 258 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"grad_norm": 97.98139953613281, |
|
"learning_rate": 1.0348837209302325e-05, |
|
"loss": 0.1027, |
|
"step": 344 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"eval_accuracy": 0.9247863247863248, |
|
"eval_f1": 0.9252074264620417, |
|
"eval_loss": 0.34157708287239075, |
|
"eval_runtime": 41.2872, |
|
"eval_samples_per_second": 14.169, |
|
"eval_steps_per_second": 3.56, |
|
"step": 344 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"grad_norm": 86.72257232666016, |
|
"learning_rate": 4.651162790697675e-07, |
|
"loss": 0.0402, |
|
"step": 430 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"eval_accuracy": 0.9299145299145299, |
|
"eval_f1": 0.9300746034490112, |
|
"eval_loss": 0.3602432310581207, |
|
"eval_runtime": 41.4693, |
|
"eval_samples_per_second": 14.107, |
|
"eval_steps_per_second": 3.545, |
|
"step": 430 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 430, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 5, |
|
"save_steps": 500, |
|
"stateful_callbacks": { |
|
"EarlyStoppingCallback": { |
|
"args": { |
|
"early_stopping_patience": 2, |
|
"early_stopping_threshold": 0.01 |
|
}, |
|
"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": 455413506240000.0, |
|
"train_batch_size": 4, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|