| { | |
| "best_metric": 0.6007231820008035, | |
| "best_model_checkpoint": "model/checkpoint-7504", | |
| "epoch": 4.0, | |
| "eval_steps": 50, | |
| "global_step": 7504, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.232726588845253, | |
| "learning_rate": 9.084300622945162e-06, | |
| "loss": 0.0817, | |
| "step": 1876 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8464818763326226, | |
| "eval_f1_macro": 0.4624149659863946, | |
| "eval_f1_weighted": 0.8011493190026544, | |
| "eval_loss": 0.06743289530277252, | |
| "eval_precision_macro": 0.7010764171889492, | |
| "eval_precision_weighted": 0.8229165574281427, | |
| "eval_recall_macro": 0.44028979481565683, | |
| "eval_recall_weighted": 0.8464818763326226, | |
| "eval_runtime": 5.0821, | |
| "eval_samples_per_second": 184.568, | |
| "eval_steps_per_second": 46.24, | |
| "step": 1876 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.18798664212226868, | |
| "learning_rate": 6.593041210714562e-06, | |
| "loss": 0.0588, | |
| "step": 3752 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8251599147121536, | |
| "eval_f1_macro": 0.5992706992706992, | |
| "eval_f1_weighted": 0.829400158611246, | |
| "eval_loss": 0.06970743834972382, | |
| "eval_precision_macro": 0.6140893452063056, | |
| "eval_precision_weighted": 0.8365234937694226, | |
| "eval_recall_macro": 0.5961441974373008, | |
| "eval_recall_weighted": 0.8251599147121536, | |
| "eval_runtime": 5.0788, | |
| "eval_samples_per_second": 184.689, | |
| "eval_steps_per_second": 46.271, | |
| "step": 3752 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.03722580894827843, | |
| "learning_rate": 3.486973746877771e-06, | |
| "loss": 0.0395, | |
| "step": 5628 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.849680170575693, | |
| "eval_f1_macro": 0.5773129404708353, | |
| "eval_f1_weighted": 0.8345452465837384, | |
| "eval_loss": 0.08055932819843292, | |
| "eval_precision_macro": 0.6424363946177801, | |
| "eval_precision_weighted": 0.8274003556291218, | |
| "eval_recall_macro": 0.5397910877436739, | |
| "eval_recall_weighted": 0.849680170575693, | |
| "eval_runtime": 5.0482, | |
| "eval_samples_per_second": 185.807, | |
| "eval_steps_per_second": 46.551, | |
| "step": 5628 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.22263826429843903, | |
| "learning_rate": 9.648338779170968e-07, | |
| "loss": 0.0239, | |
| "step": 7504 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8336886993603412, | |
| "eval_f1_macro": 0.6007231820008035, | |
| "eval_f1_weighted": 0.8327353646735044, | |
| "eval_loss": 0.0956118032336235, | |
| "eval_precision_macro": 0.6171054012879108, | |
| "eval_precision_weighted": 0.8329684712250969, | |
| "eval_recall_macro": 0.5898380302115934, | |
| "eval_recall_weighted": 0.8336886993603412, | |
| "eval_runtime": 5.0679, | |
| "eval_samples_per_second": 185.087, | |
| "eval_steps_per_second": 46.371, | |
| "step": 7504 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 9380, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1987576294404096.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |