| { | |
| "best_metric": 0.5476600527763367, | |
| "best_model_checkpoint": "autotrain-stfol-259iu/checkpoint-15", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 15, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 12.681371688842773, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.9608, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 8.062833786010742, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7349, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 14.134114265441895, | |
| "learning_rate": 4.615384615384616e-05, | |
| "loss": 0.7334, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 7.968293190002441, | |
| "learning_rate": 4.230769230769231e-05, | |
| "loss": 0.5725, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 11.32354736328125, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 0.6612, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6, | |
| "eval_auc": 0.92, | |
| "eval_f1": 0.6, | |
| "eval_loss": 0.7027295827865601, | |
| "eval_precision": 0.6, | |
| "eval_recall": 0.6, | |
| "eval_runtime": 2.7247, | |
| "eval_samples_per_second": 3.67, | |
| "eval_steps_per_second": 0.367, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 6.763383388519287, | |
| "learning_rate": 3.461538461538462e-05, | |
| "loss": 0.4969, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 5.934206485748291, | |
| "learning_rate": 3.0769230769230774e-05, | |
| "loss": 0.3405, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 6.117756366729736, | |
| "learning_rate": 2.6923076923076923e-05, | |
| "loss": 0.4799, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 6.462957382202148, | |
| "learning_rate": 2.307692307692308e-05, | |
| "loss": 0.3804, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 4.997406005859375, | |
| "learning_rate": 1.923076923076923e-05, | |
| "loss": 0.2619, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8, | |
| "eval_auc": 1.0, | |
| "eval_f1": 0.8000000000000002, | |
| "eval_loss": 0.5533014535903931, | |
| "eval_precision": 0.8, | |
| "eval_recall": 0.8, | |
| "eval_runtime": 2.6603, | |
| "eval_samples_per_second": 3.759, | |
| "eval_steps_per_second": 0.376, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "grad_norm": 5.67341423034668, | |
| "learning_rate": 1.5384615384615387e-05, | |
| "loss": 0.3258, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 8.994383811950684, | |
| "learning_rate": 1.153846153846154e-05, | |
| "loss": 0.3379, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "grad_norm": 4.565295696258545, | |
| "learning_rate": 7.692307692307694e-06, | |
| "loss": 0.2759, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "grad_norm": 3.521322011947632, | |
| "learning_rate": 3.846153846153847e-06, | |
| "loss": 0.1379, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 6.472116470336914, | |
| "learning_rate": 0.0, | |
| "loss": 0.4121, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8, | |
| "eval_auc": 0.9600000000000001, | |
| "eval_f1": 0.8000000000000002, | |
| "eval_loss": 0.5476600527763367, | |
| "eval_precision": 0.8, | |
| "eval_recall": 0.8, | |
| "eval_runtime": 3.3326, | |
| "eval_samples_per_second": 3.001, | |
| "eval_steps_per_second": 0.3, | |
| "step": 15 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 15, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 8834086816063488.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |