{ "best_metric": 0.8656330749354005, "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-194", "epoch": 9.896907216494846, "eval_steps": 500, "global_step": 240, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.9896907216494846, "eval_accuracy": 0.48320413436692505, "eval_f1": 0.31484032448297905, "eval_loss": 1.1717983484268188, "eval_precision": 0.23348623546928937, "eval_recall": 0.48320413436692505, "eval_runtime": 1.6682, "eval_samples_per_second": 231.984, "eval_steps_per_second": 29.373, "step": 24 }, { "epoch": 1.9793814432989691, "eval_accuracy": 0.7235142118863049, "eval_f1": 0.7025965349533153, "eval_loss": 0.7550917863845825, "eval_precision": 0.7163905403042491, "eval_recall": 0.7235142118863049, "eval_runtime": 1.6003, "eval_samples_per_second": 241.836, "eval_steps_per_second": 30.62, "step": 48 }, { "epoch": 2.9690721649484537, "eval_accuracy": 0.7312661498708011, "eval_f1": 0.7074435618655927, "eval_loss": 0.6834394335746765, "eval_precision": 0.7620582207432803, "eval_recall": 0.7312661498708011, "eval_runtime": 1.604, "eval_samples_per_second": 241.278, "eval_steps_per_second": 30.549, "step": 72 }, { "epoch": 4.0, "eval_accuracy": 0.6201550387596899, "eval_f1": 0.616059564047211, "eval_loss": 0.9937827587127686, "eval_precision": 0.6843785822798868, "eval_recall": 0.6201550387596899, "eval_runtime": 1.5998, "eval_samples_per_second": 241.901, "eval_steps_per_second": 30.628, "step": 97 }, { "epoch": 4.989690721649485, "eval_accuracy": 0.7881136950904393, "eval_f1": 0.7854190251131377, "eval_loss": 0.4972754120826721, "eval_precision": 0.7961139879912458, "eval_recall": 0.7881136950904393, "eval_runtime": 1.5913, "eval_samples_per_second": 243.196, "eval_steps_per_second": 30.792, "step": 121 }, { "epoch": 5.979381443298969, "eval_accuracy": 0.7803617571059431, "eval_f1": 0.781727235222138, "eval_loss": 0.5254013538360596, "eval_precision": 0.7843017570642586, "eval_recall": 0.7803617571059431, "eval_runtime": 1.6096, "eval_samples_per_second": 240.428, "eval_steps_per_second": 30.442, "step": 145 }, { "epoch": 6.969072164948454, "eval_accuracy": 0.8475452196382429, "eval_f1": 0.8504309219603966, "eval_loss": 0.42636802792549133, "eval_precision": 0.8557626671638175, "eval_recall": 0.8475452196382429, "eval_runtime": 1.6741, "eval_samples_per_second": 231.171, "eval_steps_per_second": 29.27, "step": 169 }, { "epoch": 8.0, "eval_accuracy": 0.8656330749354005, "eval_f1": 0.8627731371728347, "eval_loss": 0.4414582848548889, "eval_precision": 0.8670254176803228, "eval_recall": 0.8656330749354005, "eval_runtime": 1.6573, "eval_samples_per_second": 233.512, "eval_steps_per_second": 29.566, "step": 194 }, { "epoch": 8.989690721649485, "eval_accuracy": 0.8656330749354005, "eval_f1": 0.8648808138390941, "eval_loss": 0.4115408658981323, "eval_precision": 0.8650901526054525, "eval_recall": 0.8656330749354005, "eval_runtime": 1.6461, "eval_samples_per_second": 235.106, "eval_steps_per_second": 29.768, "step": 218 }, { "epoch": 9.896907216494846, "eval_accuracy": 0.8656330749354005, "eval_f1": 0.8628955278832856, "eval_loss": 0.43414339423179626, "eval_precision": 0.8627959308862513, "eval_recall": 0.8656330749354005, "eval_runtime": 1.6443, "eval_samples_per_second": 235.354, "eval_steps_per_second": 29.799, "step": 240 } ], "logging_steps": 500, "max_steps": 240, "num_input_tokens_seen": 0, "num_train_epochs": 10, "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": 3.478884368832e+16, "train_batch_size": 8, "trial_name": null, "trial_params": null }