| { | |
| "best_metric": 0.7674418604651163, | |
| "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-144", | |
| "epoch": 5.938144329896907, | |
| "eval_steps": 500, | |
| "global_step": 144, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.9896907216494846, | |
| "eval_accuracy": 0.6098191214470284, | |
| "eval_f1": 0.5527821682108387, | |
| "eval_loss": 1.0193405151367188, | |
| "eval_precision": 0.7003292379638224, | |
| "eval_recall": 0.6098191214470284, | |
| "eval_runtime": 1.7319, | |
| "eval_samples_per_second": 223.453, | |
| "eval_steps_per_second": 28.293, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.9793814432989691, | |
| "eval_accuracy": 0.6795865633074936, | |
| "eval_f1": 0.6650515718181741, | |
| "eval_loss": 0.7780925631523132, | |
| "eval_precision": 0.6877908327609833, | |
| "eval_recall": 0.6795865633074936, | |
| "eval_runtime": 1.7105, | |
| "eval_samples_per_second": 226.247, | |
| "eval_steps_per_second": 28.646, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.9690721649484537, | |
| "eval_accuracy": 0.7260981912144703, | |
| "eval_f1": 0.7125387559196679, | |
| "eval_loss": 0.663092315196991, | |
| "eval_precision": 0.7236217153897081, | |
| "eval_recall": 0.7260981912144703, | |
| "eval_runtime": 1.7131, | |
| "eval_samples_per_second": 225.911, | |
| "eval_steps_per_second": 28.604, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7493540051679587, | |
| "eval_f1": 0.7323843170610034, | |
| "eval_loss": 0.5870956778526306, | |
| "eval_precision": 0.7505520883603423, | |
| "eval_recall": 0.7493540051679587, | |
| "eval_runtime": 1.7332, | |
| "eval_samples_per_second": 223.293, | |
| "eval_steps_per_second": 28.272, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 4.989690721649485, | |
| "eval_accuracy": 0.7648578811369509, | |
| "eval_f1": 0.7570271532827265, | |
| "eval_loss": 0.5548774003982544, | |
| "eval_precision": 0.7717080207133444, | |
| "eval_recall": 0.7648578811369509, | |
| "eval_runtime": 1.744, | |
| "eval_samples_per_second": 221.907, | |
| "eval_steps_per_second": 28.097, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 5.938144329896907, | |
| "eval_accuracy": 0.7674418604651163, | |
| "eval_f1": 0.7605087043783928, | |
| "eval_loss": 0.5497403144836426, | |
| "eval_precision": 0.7731114884926515, | |
| "eval_recall": 0.7674418604651163, | |
| "eval_runtime": 1.7702, | |
| "eval_samples_per_second": 218.618, | |
| "eval_steps_per_second": 27.68, | |
| "step": 144 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 144, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.087967404736e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |