| { | |
| "best_metric": 0.02310723066329956, | |
| "best_model_checkpoint": "deepfake_vs_real_image_detection/checkpoint-3571", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 3571, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 6.2275071144104, | |
| "learning_rate": 9.365482233502537e-07, | |
| "loss": 0.0626, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 10.569954872131348, | |
| "learning_rate": 8.660462492949803e-07, | |
| "loss": 0.0574, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 10.928681373596191, | |
| "learning_rate": 7.955442752397067e-07, | |
| "loss": 0.0657, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 1.1176731586456299, | |
| "learning_rate": 7.250423011844331e-07, | |
| "loss": 0.0568, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 9.849133491516113, | |
| "learning_rate": 6.545403271291596e-07, | |
| "loss": 0.0546, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 2.835080862045288, | |
| "learning_rate": 5.840383530738861e-07, | |
| "loss": 0.0552, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 0.03996190056204796, | |
| "learning_rate": 5.135363790186125e-07, | |
| "loss": 0.0603, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9927259358464305, | |
| "eval_loss": 0.02310723066329956, | |
| "eval_runtime": 806.2331, | |
| "eval_samples_per_second": 94.465, | |
| "eval_steps_per_second": 11.809, | |
| "step": 3571 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 7142, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "total_flos": 8.852762385560605e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |