{ "best_metric": null, "best_model_checkpoint": null, "epoch": 18.0, "eval_steps": 500, "global_step": 18, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "grad_norm": 4.865087985992432, "learning_rate": 2.5e-05, "loss": 0.5553, "step": 1 }, { "epoch": 1.0, "eval_Macro F1": 0.0, "eval_Macro Precision": 0.0, "eval_Macro Recall": 0.0, "eval_Micro F1": 0.0, "eval_Micro Precision": 0.0, "eval_Micro Recall": 0.0, "eval_Weighted F1": 0.0, "eval_Weighted Precision": 0.0, "eval_Weighted Recall": 0.0, "eval_accuracy": 0.0, "eval_loss": 2.791379451751709, "eval_runtime": 3.111, "eval_samples_per_second": 0.321, "eval_steps_per_second": 0.321, "step": 1 }, { "epoch": 2.0, "eval_Macro F1": 0.0, "eval_Macro Precision": 0.0, "eval_Macro Recall": 0.0, "eval_Micro F1": 0.0, "eval_Micro Precision": 0.0, "eval_Micro Recall": 0.0, "eval_Weighted F1": 0.0, "eval_Weighted Precision": 0.0, "eval_Weighted Recall": 0.0, "eval_accuracy": 0.0, "eval_loss": 2.4681010246276855, "eval_runtime": 2.3459, "eval_samples_per_second": 0.426, "eval_steps_per_second": 0.426, "step": 2 }, { "epoch": 3.0, "eval_Macro F1": 0.0, "eval_Macro Precision": 0.0, "eval_Macro Recall": 0.0, "eval_Micro F1": 0.0, "eval_Micro Precision": 0.0, "eval_Micro Recall": 0.0, "eval_Weighted F1": 0.0, "eval_Weighted Precision": 0.0, "eval_Weighted Recall": 0.0, "eval_accuracy": 0.0, "eval_loss": 1.868812084197998, "eval_runtime": 2.4851, "eval_samples_per_second": 0.402, "eval_steps_per_second": 0.402, "step": 3 }, { "epoch": 4.0, "eval_Macro F1": 1.0, "eval_Macro Precision": 1.0, "eval_Macro Recall": 1.0, "eval_Micro F1": 1.0, "eval_Micro Precision": 1.0, "eval_Micro Recall": 1.0, "eval_Weighted F1": 1.0, "eval_Weighted Precision": 1.0, "eval_Weighted Recall": 1.0, "eval_accuracy": 1.0, "eval_loss": 1.3606051206588745, "eval_runtime": 2.664, "eval_samples_per_second": 0.375, "eval_steps_per_second": 0.375, "step": 4 }, { "epoch": 5.0, "eval_Macro F1": 1.0, "eval_Macro Precision": 1.0, "eval_Macro Recall": 1.0, "eval_Micro F1": 1.0, "eval_Micro Precision": 1.0, "eval_Micro Recall": 1.0, "eval_Weighted F1": 1.0, "eval_Weighted Precision": 1.0, "eval_Weighted Recall": 1.0, "eval_accuracy": 1.0, "eval_loss": 0.9826632142066956, "eval_runtime": 2.3833, "eval_samples_per_second": 0.42, "eval_steps_per_second": 0.42, "step": 5 }, { "epoch": 6.0, "eval_Macro F1": 1.0, "eval_Macro Precision": 1.0, "eval_Macro Recall": 1.0, "eval_Micro F1": 1.0, "eval_Micro Precision": 1.0, "eval_Micro Recall": 1.0, "eval_Weighted F1": 1.0, "eval_Weighted Precision": 1.0, "eval_Weighted Recall": 1.0, "eval_accuracy": 1.0, "eval_loss": 0.7991973757743835, "eval_runtime": 2.3865, "eval_samples_per_second": 0.419, "eval_steps_per_second": 0.419, "step": 6 }, { "epoch": 7.0, "eval_Macro F1": 1.0, "eval_Macro Precision": 1.0, "eval_Macro Recall": 1.0, "eval_Micro F1": 1.0, "eval_Micro Precision": 1.0, "eval_Micro Recall": 1.0, "eval_Weighted F1": 1.0, "eval_Weighted Precision": 1.0, "eval_Weighted Recall": 1.0, "eval_accuracy": 1.0, "eval_loss": 0.5434778332710266, "eval_runtime": 2.4197, "eval_samples_per_second": 0.413, "eval_steps_per_second": 0.413, "step": 7 }, { "epoch": 8.0, "grad_norm": 2.9049506187438965, "learning_rate": 3.125e-05, "loss": 0.3458, "step": 8 }, { "epoch": 8.0, "eval_Macro F1": 1.0, "eval_Macro Precision": 1.0, "eval_Macro Recall": 1.0, "eval_Micro F1": 1.0, "eval_Micro Precision": 1.0, "eval_Micro Recall": 1.0, "eval_Weighted F1": 1.0, "eval_Weighted Precision": 1.0, "eval_Weighted Recall": 1.0, "eval_accuracy": 1.0, "eval_loss": 0.34662869572639465, "eval_runtime": 2.5941, "eval_samples_per_second": 0.385, "eval_steps_per_second": 0.385, "step": 8 }, { "epoch": 9.0, "eval_Macro F1": 1.0, "eval_Macro Precision": 1.0, "eval_Macro Recall": 1.0, "eval_Micro F1": 1.0, "eval_Micro Precision": 1.0, "eval_Micro Recall": 1.0, "eval_Weighted F1": 1.0, "eval_Weighted Precision": 1.0, "eval_Weighted Recall": 1.0, "eval_accuracy": 1.0, "eval_loss": 0.2157200425863266, "eval_runtime": 2.3657, "eval_samples_per_second": 0.423, "eval_steps_per_second": 0.423, "step": 9 }, { "epoch": 10.0, "eval_Macro F1": 1.0, "eval_Macro Precision": 1.0, "eval_Macro Recall": 1.0, "eval_Micro F1": 1.0, "eval_Micro Precision": 1.0, "eval_Micro Recall": 1.0, "eval_Weighted F1": 1.0, "eval_Weighted Precision": 1.0, "eval_Weighted Recall": 1.0, "eval_accuracy": 1.0, "eval_loss": 0.15205366909503937, "eval_runtime": 2.4557, "eval_samples_per_second": 0.407, "eval_steps_per_second": 0.407, "step": 10 }, { "epoch": 11.0, "eval_Macro F1": 1.0, "eval_Macro Precision": 1.0, "eval_Macro Recall": 1.0, "eval_Micro F1": 1.0, "eval_Micro Precision": 1.0, "eval_Micro Recall": 1.0, "eval_Weighted F1": 1.0, "eval_Weighted Precision": 1.0, "eval_Weighted Recall": 1.0, "eval_accuracy": 1.0, "eval_loss": 0.12508539855480194, "eval_runtime": 3.5047, "eval_samples_per_second": 0.285, "eval_steps_per_second": 0.285, "step": 11 }, { "epoch": 12.0, "eval_Macro F1": 1.0, "eval_Macro Precision": 1.0, "eval_Macro Recall": 1.0, "eval_Micro F1": 1.0, "eval_Micro Precision": 1.0, "eval_Micro Recall": 1.0, "eval_Weighted F1": 1.0, "eval_Weighted Precision": 1.0, "eval_Weighted Recall": 1.0, "eval_accuracy": 1.0, "eval_loss": 0.10588796436786652, "eval_runtime": 2.5523, "eval_samples_per_second": 0.392, "eval_steps_per_second": 0.392, "step": 12 }, { "epoch": 13.0, "eval_Macro F1": 1.0, "eval_Macro Precision": 1.0, "eval_Macro Recall": 1.0, "eval_Micro F1": 1.0, "eval_Micro Precision": 1.0, "eval_Micro Recall": 1.0, "eval_Weighted F1": 1.0, "eval_Weighted Precision": 1.0, "eval_Weighted Recall": 1.0, "eval_accuracy": 1.0, "eval_loss": 0.09097960591316223, "eval_runtime": 2.7254, "eval_samples_per_second": 0.367, "eval_steps_per_second": 0.367, "step": 13 }, { "epoch": 14.0, "eval_Macro F1": 1.0, "eval_Macro Precision": 1.0, "eval_Macro Recall": 1.0, "eval_Micro F1": 1.0, "eval_Micro Precision": 1.0, "eval_Micro Recall": 1.0, "eval_Weighted F1": 1.0, "eval_Weighted Precision": 1.0, "eval_Weighted Recall": 1.0, "eval_accuracy": 1.0, "eval_loss": 0.08067251741886139, "eval_runtime": 3.1629, "eval_samples_per_second": 0.316, "eval_steps_per_second": 0.316, "step": 14 }, { "epoch": 15.0, "eval_Macro F1": 1.0, "eval_Macro Precision": 1.0, "eval_Macro Recall": 1.0, "eval_Micro F1": 1.0, "eval_Micro Precision": 1.0, "eval_Micro Recall": 1.0, "eval_Weighted F1": 1.0, "eval_Weighted Precision": 1.0, "eval_Weighted Recall": 1.0, "eval_accuracy": 1.0, "eval_loss": 0.07393598556518555, "eval_runtime": 2.2691, "eval_samples_per_second": 0.441, "eval_steps_per_second": 0.441, "step": 15 }, { "epoch": 16.0, "grad_norm": 4.167747974395752, "learning_rate": 6.25e-06, "loss": 0.1206, "step": 16 }, { "epoch": 16.0, "eval_Macro F1": 1.0, "eval_Macro Precision": 1.0, "eval_Macro Recall": 1.0, "eval_Micro F1": 1.0, "eval_Micro Precision": 1.0, "eval_Micro Recall": 1.0, "eval_Weighted F1": 1.0, "eval_Weighted Precision": 1.0, "eval_Weighted Recall": 1.0, "eval_accuracy": 1.0, "eval_loss": 0.06927751749753952, "eval_runtime": 2.4236, "eval_samples_per_second": 0.413, "eval_steps_per_second": 0.413, "step": 16 }, { "epoch": 17.0, "eval_Macro F1": 1.0, "eval_Macro Precision": 1.0, "eval_Macro Recall": 1.0, "eval_Micro F1": 1.0, "eval_Micro Precision": 1.0, "eval_Micro Recall": 1.0, "eval_Weighted F1": 1.0, "eval_Weighted Precision": 1.0, "eval_Weighted Recall": 1.0, "eval_accuracy": 1.0, "eval_loss": 0.0666036382317543, "eval_runtime": 2.3816, "eval_samples_per_second": 0.42, "eval_steps_per_second": 0.42, "step": 17 }, { "epoch": 18.0, "eval_Macro F1": 1.0, "eval_Macro Precision": 1.0, "eval_Macro Recall": 1.0, "eval_Micro F1": 1.0, "eval_Micro Precision": 1.0, "eval_Micro Recall": 1.0, "eval_Weighted F1": 1.0, "eval_Weighted Precision": 1.0, "eval_Weighted Recall": 1.0, "eval_accuracy": 1.0, "eval_loss": 0.06531175971031189, "eval_runtime": 2.6334, "eval_samples_per_second": 0.38, "eval_steps_per_second": 0.38, "step": 18 }, { "epoch": 18.0, "step": 18, "total_flos": 4185579438931968.0, "train_loss": 0.22384852460689014, "train_runtime": 209.9511, "train_samples_per_second": 0.257, "train_steps_per_second": 0.086 } ], "logging_steps": 8, "max_steps": 18, "num_input_tokens_seen": 0, "num_train_epochs": 18, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 4185579438931968.0, "train_batch_size": 32, "trial_name": null, "trial_params": null }