{ "best_metric": 3.259751319885254, "best_model_checkpoint": "../experiments/attribute_minig_mslacerda/run-1/checkpoint-129", "epoch": 3.0, "eval_steps": 500, "global_step": 129, "is_hyper_param_search": true, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "eval_accuracy": 0.03543543543543543, "eval_f1": 0.004940711462450594, "eval_loss": 4.673229217529297, "eval_precision": 0.004108463434675432, "eval_recall": 0.006195786864931847, "eval_runtime": 0.3918, "eval_samples_per_second": 742.66, "eval_steps_per_second": 94.428, "step": 43 }, { "epoch": 2.0, "eval_accuracy": 0.12612612612612611, "eval_f1": 0.019381056580181303, "eval_loss": 4.209076881408691, "eval_precision": 0.019558359621451103, "eval_recall": 0.019206939281288724, "eval_runtime": 0.3924, "eval_samples_per_second": 741.507, "eval_steps_per_second": 94.281, "step": 86 }, { "epoch": 3.0, "eval_accuracy": 0.3282282282282282, "eval_f1": 0.10037453183520599, "eval_loss": 3.259751319885254, "eval_precision": 0.1268939393939394, "eval_recall": 0.08302354399008674, "eval_runtime": 0.4015, "eval_samples_per_second": 724.86, "eval_steps_per_second": 92.164, "step": 129 } ], "logging_steps": 500, "max_steps": 559, "num_input_tokens_seen": 0, "num_train_epochs": 13, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 0, "train_batch_size": 32, "trial_name": null, "trial_params": { "learning_rate": 3.979306441518639e-05, "num_train_epochs": 13, "per_device_train_batch_size": 32, "warmup_steps": 286, "weight_decay": 0.144636026358464 } }