| { | |
| "best_metric": 0.024474753066897392, | |
| "best_model_checkpoint": "deepfake_vs_real_image_detection/checkpoint-7142", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 7142, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14001680201624195, | |
| "grad_norm": 0.15100933611392975, | |
| "learning_rate": 9.365482233502537e-07, | |
| "loss": 0.0566, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.2800336040324839, | |
| "grad_norm": 10.631893157958984, | |
| "learning_rate": 8.660462492949803e-07, | |
| "loss": 0.054, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.42005040604872584, | |
| "grad_norm": 0.12740743160247803, | |
| "learning_rate": 7.955442752397067e-07, | |
| "loss": 0.0511, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.5600672080649678, | |
| "grad_norm": 0.05412658303976059, | |
| "learning_rate": 7.250423011844331e-07, | |
| "loss": 0.0551, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.7000840100812098, | |
| "grad_norm": 0.0381879098713398, | |
| "learning_rate": 6.545403271291596e-07, | |
| "loss": 0.0505, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.8401008120974517, | |
| "grad_norm": 4.40518856048584, | |
| "learning_rate": 5.840383530738861e-07, | |
| "loss": 0.0536, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.9801176141136937, | |
| "grad_norm": 0.04376288503408432, | |
| "learning_rate": 5.135363790186125e-07, | |
| "loss": 0.0478, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9918987408253568, | |
| "eval_loss": 0.024553103372454643, | |
| "eval_model_preparation_time": 0.0038, | |
| "eval_runtime": 684.3769, | |
| "eval_samples_per_second": 111.285, | |
| "eval_steps_per_second": 13.912, | |
| "step": 3571 | |
| }, | |
| { | |
| "epoch": 1.1201344161299356, | |
| "grad_norm": 3.1044564247131348, | |
| "learning_rate": 4.4303440496333894e-07, | |
| "loss": 0.0522, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.2601512181461776, | |
| "grad_norm": 9.938944816589355, | |
| "learning_rate": 3.725324309080654e-07, | |
| "loss": 0.049, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.4001680201624196, | |
| "grad_norm": 5.965790271759033, | |
| "learning_rate": 3.020304568527919e-07, | |
| "loss": 0.0521, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.5401848221786616, | |
| "grad_norm": 0.10780753195285797, | |
| "learning_rate": 2.3152848279751832e-07, | |
| "loss": 0.0488, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.6802016241949034, | |
| "grad_norm": 0.2710246741771698, | |
| "learning_rate": 1.6102650874224477e-07, | |
| "loss": 0.0518, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.8202184262111454, | |
| "grad_norm": 12.39289665222168, | |
| "learning_rate": 9.052453468697122e-08, | |
| "loss": 0.0449, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.9602352282273872, | |
| "grad_norm": 0.19405755400657654, | |
| "learning_rate": 2.002256063169769e-08, | |
| "loss": 0.0441, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9920694318614514, | |
| "eval_loss": 0.024474753066897392, | |
| "eval_model_preparation_time": 0.0038, | |
| "eval_runtime": 669.6791, | |
| "eval_samples_per_second": 113.728, | |
| "eval_steps_per_second": 14.217, | |
| "step": 7142 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 7142, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 1.770552477112121e+19, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |