| { | |
| "best_metric": 0.6985413290113451, | |
| "best_model_checkpoint": "/content/dissertation/scripts/ner/output/checkpoint-1736", | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 2480, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9477686162533286, | |
| "eval_f1": 0.63506625891947, | |
| "eval_loss": 0.16486208140850067, | |
| "eval_precision": 0.5941821649976157, | |
| "eval_recall": 0.6819923371647509, | |
| "eval_runtime": 5.5136, | |
| "eval_samples_per_second": 456.871, | |
| "eval_steps_per_second": 57.132, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9476402836151304, | |
| "eval_f1": 0.6630581867388362, | |
| "eval_loss": 0.18148483335971832, | |
| "eval_precision": 0.6557815845824411, | |
| "eval_recall": 0.6704980842911877, | |
| "eval_runtime": 5.4181, | |
| "eval_samples_per_second": 464.925, | |
| "eval_steps_per_second": 58.139, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 2.0161290322580645, | |
| "grad_norm": 0.6250831484794617, | |
| "learning_rate": 3.991935483870968e-05, | |
| "loss": 0.134, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9491802752735089, | |
| "eval_f1": 0.6810897435897436, | |
| "eval_loss": 0.2111387550830841, | |
| "eval_precision": 0.6651017214397497, | |
| "eval_recall": 0.6978653530377669, | |
| "eval_runtime": 5.4844, | |
| "eval_samples_per_second": 459.302, | |
| "eval_steps_per_second": 57.435, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9488434020982386, | |
| "eval_f1": 0.6900026518164943, | |
| "eval_loss": 0.25230270624160767, | |
| "eval_precision": 0.6692386831275721, | |
| "eval_recall": 0.7120963327859879, | |
| "eval_runtime": 5.4481, | |
| "eval_samples_per_second": 462.36, | |
| "eval_steps_per_second": 57.818, | |
| "step": 992 | |
| }, | |
| { | |
| "epoch": 4.032258064516129, | |
| "grad_norm": 0.7998089790344238, | |
| "learning_rate": 2.9838709677419357e-05, | |
| "loss": 0.026, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9490840257948603, | |
| "eval_f1": 0.6847083552285864, | |
| "eval_loss": 0.27709877490997314, | |
| "eval_precision": 0.6584133400707428, | |
| "eval_recall": 0.7131910235358512, | |
| "eval_runtime": 5.6532, | |
| "eval_samples_per_second": 445.585, | |
| "eval_steps_per_second": 55.72, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9486348615611665, | |
| "eval_f1": 0.6907651715039579, | |
| "eval_loss": 0.2968369126319885, | |
| "eval_precision": 0.6668364747834946, | |
| "eval_recall": 0.7164750957854407, | |
| "eval_runtime": 5.4549, | |
| "eval_samples_per_second": 461.787, | |
| "eval_steps_per_second": 57.746, | |
| "step": 1488 | |
| }, | |
| { | |
| "epoch": 6.048387096774194, | |
| "grad_norm": 0.15673314034938812, | |
| "learning_rate": 1.975806451612903e-05, | |
| "loss": 0.0084, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9496936058263018, | |
| "eval_f1": 0.6985413290113451, | |
| "eval_loss": 0.3088673949241638, | |
| "eval_precision": 0.6896, | |
| "eval_recall": 0.7077175697865353, | |
| "eval_runtime": 5.5771, | |
| "eval_samples_per_second": 451.669, | |
| "eval_steps_per_second": 56.481, | |
| "step": 1736 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9498861047835991, | |
| "eval_f1": 0.6946236559139785, | |
| "eval_loss": 0.31877079606056213, | |
| "eval_precision": 0.6825145272054939, | |
| "eval_recall": 0.7071702244116037, | |
| "eval_runtime": 5.3015, | |
| "eval_samples_per_second": 475.15, | |
| "eval_steps_per_second": 59.417, | |
| "step": 1984 | |
| }, | |
| { | |
| "epoch": 8.064516129032258, | |
| "grad_norm": 0.22283445298671722, | |
| "learning_rate": 9.67741935483871e-06, | |
| "loss": 0.0042, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.9494529821296801, | |
| "eval_f1": 0.6979722518676629, | |
| "eval_loss": 0.3295721411705017, | |
| "eval_precision": 0.6808953669963561, | |
| "eval_recall": 0.715927750410509, | |
| "eval_runtime": 5.4512, | |
| "eval_samples_per_second": 462.102, | |
| "eval_steps_per_second": 57.786, | |
| "step": 2232 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9498861047835991, | |
| "eval_f1": 0.6985058697972252, | |
| "eval_loss": 0.33284899592399597, | |
| "eval_precision": 0.6814159292035398, | |
| "eval_recall": 0.7164750957854407, | |
| "eval_runtime": 5.5975, | |
| "eval_samples_per_second": 450.025, | |
| "eval_steps_per_second": 56.276, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 2480, | |
| "total_flos": 7718163558521760.0, | |
| "train_loss": 0.03527186407196906, | |
| "train_runtime": 706.0488, | |
| "train_samples_per_second": 224.46, | |
| "train_steps_per_second": 3.513 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2480, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "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": 7718163558521760.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |