| { | |
| "best_metric": 0.6037027835845947, | |
| "best_model_checkpoint": "deepfake_vit/checkpoint-846", | |
| "epoch": 6.0, | |
| "eval_steps": 500, | |
| "global_step": 846, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6076666666666667, | |
| "eval_loss": 0.6674891710281372, | |
| "eval_model_preparation_time": 0.0106, | |
| "eval_runtime": 111.6369, | |
| "eval_samples_per_second": 26.873, | |
| "eval_steps_per_second": 3.359, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6446666666666667, | |
| "eval_loss": 0.632375180721283, | |
| "eval_model_preparation_time": 0.0106, | |
| "eval_runtime": 110.9746, | |
| "eval_samples_per_second": 27.033, | |
| "eval_steps_per_second": 3.379, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.6636666666666666, | |
| "eval_loss": 0.6149229407310486, | |
| "eval_model_preparation_time": 0.0106, | |
| "eval_runtime": 110.2307, | |
| "eval_samples_per_second": 27.216, | |
| "eval_steps_per_second": 3.402, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 3.546099290780142, | |
| "grad_norm": 21.022438049316406, | |
| "learning_rate": 8.693467336683417e-07, | |
| "loss": 0.6216, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.6673333333333333, | |
| "eval_loss": 0.6062994003295898, | |
| "eval_model_preparation_time": 0.0106, | |
| "eval_runtime": 110.5429, | |
| "eval_samples_per_second": 27.139, | |
| "eval_steps_per_second": 3.392, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.664, | |
| "eval_loss": 0.6095455884933472, | |
| "eval_model_preparation_time": 0.0106, | |
| "eval_runtime": 112.228, | |
| "eval_samples_per_second": 26.731, | |
| "eval_steps_per_second": 3.341, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.6673333333333333, | |
| "eval_loss": 0.6037027835845947, | |
| "eval_model_preparation_time": 0.0106, | |
| "eval_runtime": 111.7991, | |
| "eval_samples_per_second": 26.834, | |
| "eval_steps_per_second": 3.354, | |
| "step": 846 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 846, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "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": 2.261398387175424e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |