| { | |
| "best_metric": 0.3946281671524048, | |
| "best_model_checkpoint": "autotrain-c0iln-xl83j/checkpoint-18", | |
| "epoch": 9.0, | |
| "eval_steps": 500, | |
| "global_step": 18, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 27.526565551757812, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.7713, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 18.068647384643555, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7697, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5, | |
| "eval_auc": 0.0, | |
| "eval_f1": 0.6666666666666666, | |
| "eval_loss": 0.9978442192077637, | |
| "eval_precision": 0.5, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.0806, | |
| "eval_samples_per_second": 24.82, | |
| "eval_steps_per_second": 12.41, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 11.910748481750488, | |
| "learning_rate": 4.722222222222222e-05, | |
| "loss": 0.401, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 24.258024215698242, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 1.4374, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.5, | |
| "eval_auc": 1.0, | |
| "eval_f1": 0.6666666666666666, | |
| "eval_loss": 0.5882669687271118, | |
| "eval_precision": 0.5, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.0768, | |
| "eval_samples_per_second": 26.044, | |
| "eval_steps_per_second": 13.022, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 20.304765701293945, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.7518, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 16.334768295288086, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.6696, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.5, | |
| "eval_auc": 1.0, | |
| "eval_f1": 0.6666666666666666, | |
| "eval_loss": 0.6670193672180176, | |
| "eval_precision": 0.5, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.083, | |
| "eval_samples_per_second": 24.106, | |
| "eval_steps_per_second": 12.053, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "grad_norm": 21.92859649658203, | |
| "learning_rate": 3.611111111111111e-05, | |
| "loss": 1.2565, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 19.558080673217773, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.443, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.5, | |
| "eval_auc": 1.0, | |
| "eval_f1": 0.6666666666666666, | |
| "eval_loss": 0.694669246673584, | |
| "eval_precision": 0.5, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.0794, | |
| "eval_samples_per_second": 25.176, | |
| "eval_steps_per_second": 12.588, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "grad_norm": 13.385185241699219, | |
| "learning_rate": 3.055555555555556e-05, | |
| "loss": 0.4886, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 20.257001876831055, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.5923, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.5, | |
| "eval_auc": 1.0, | |
| "eval_f1": 0.6666666666666666, | |
| "eval_loss": 0.6438201069831848, | |
| "eval_precision": 0.5, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.0867, | |
| "eval_samples_per_second": 23.068, | |
| "eval_steps_per_second": 11.534, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "grad_norm": 11.043343544006348, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.3391, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 18.80914306640625, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.9555, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.5, | |
| "eval_auc": 1.0, | |
| "eval_f1": 0.6666666666666666, | |
| "eval_loss": 0.4542161524295807, | |
| "eval_precision": 0.5, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.0861, | |
| "eval_samples_per_second": 23.233, | |
| "eval_steps_per_second": 11.617, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 6.5, | |
| "grad_norm": 11.015345573425293, | |
| "learning_rate": 1.9444444444444445e-05, | |
| "loss": 0.4014, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 19.664325714111328, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.9119, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.5, | |
| "eval_auc": 1.0, | |
| "eval_f1": 0.6666666666666666, | |
| "eval_loss": 0.6708225011825562, | |
| "eval_precision": 0.5, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.0791, | |
| "eval_samples_per_second": 25.271, | |
| "eval_steps_per_second": 12.636, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "grad_norm": 17.03907585144043, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.7005, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 18.77954864501953, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.5855, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.5, | |
| "eval_auc": 1.0, | |
| "eval_f1": 0.6666666666666666, | |
| "eval_loss": 0.521186113357544, | |
| "eval_precision": 0.5, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.0775, | |
| "eval_samples_per_second": 25.818, | |
| "eval_steps_per_second": 12.909, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 8.5, | |
| "grad_norm": 13.248153686523438, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.5395, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "grad_norm": 23.6978702545166, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.6486, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.3946281671524048, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.0835, | |
| "eval_samples_per_second": 23.942, | |
| "eval_steps_per_second": 11.971, | |
| "step": 18 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 20, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 189101405896704.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |