| { | |
| "best_metric": 0.64765864610672, | |
| "best_model_checkpoint": "autotrain-8fohv-7gjpn/checkpoint-3", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 3, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 3.5731441974639893, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7078, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5, | |
| "eval_auc": 0.0, | |
| "eval_f1": 0.6666666666666666, | |
| "eval_loss": 0.7588332891464233, | |
| "eval_precision": 0.5, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.4987, | |
| "eval_samples_per_second": 4.01, | |
| "eval_steps_per_second": 2.005, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 4.275372505187988, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.6821, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.5, | |
| "eval_auc": 1.0, | |
| "eval_f1": 0.6666666666666666, | |
| "eval_loss": 0.7033029198646545, | |
| "eval_precision": 0.5, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.4071, | |
| "eval_samples_per_second": 4.913, | |
| "eval_steps_per_second": 2.456, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 5.158136367797852, | |
| "learning_rate": 0.0, | |
| "loss": 0.513, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.5, | |
| "eval_auc": 1.0, | |
| "eval_f1": 0.6666666666666666, | |
| "eval_loss": 0.64765864610672, | |
| "eval_precision": 0.5, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.4326, | |
| "eval_samples_per_second": 4.624, | |
| "eval_steps_per_second": 2.312, | |
| "step": 3 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 3, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 1578666332160.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |