| { | |
| "best_metric": 0.01880481094121933, | |
| "best_model_checkpoint": "2025-01-21-16-13-04-vit-base-patch16-224/checkpoint-136", | |
| "epoch": 6.0, | |
| "eval_steps": 500, | |
| "global_step": 204, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "train_accuracy": 0.7324074074074074 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 3.5079495906829834, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7465, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9365925925925925, | |
| "eval_error_rate": 0.06340740740740747, | |
| "eval_f1": 0.9400418302275843, | |
| "eval_loss": 0.10922861099243164, | |
| "eval_precision": 0.9535535535535536, | |
| "eval_recall": 0.9407407407407408, | |
| "eval_runtime": 3.1454, | |
| "eval_samples_per_second": 42.919, | |
| "eval_steps_per_second": 1.59, | |
| "eval_top1_accuracy": 0.9407407407407408, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "train_accuracy": 0.9325102880658436 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 7.9865288734436035, | |
| "learning_rate": 0.00017777777777777779, | |
| "loss": 0.212, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9048571428571428, | |
| "eval_error_rate": 0.0951428571428572, | |
| "eval_f1": 0.9061150336512657, | |
| "eval_loss": 0.2753830850124359, | |
| "eval_precision": 0.9337830687830687, | |
| "eval_recall": 0.9111111111111111, | |
| "eval_runtime": 3.3128, | |
| "eval_samples_per_second": 40.752, | |
| "eval_steps_per_second": 1.509, | |
| "eval_top1_accuracy": 0.9111111111111111, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "train_accuracy": 0.9547325102880658 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 5.545481204986572, | |
| "learning_rate": 0.00015555555555555556, | |
| "loss": 0.115, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.985103448275862, | |
| "eval_error_rate": 0.014896551724137952, | |
| "eval_f1": 0.9851769394626537, | |
| "eval_loss": 0.05338314175605774, | |
| "eval_precision": 0.9854497354497354, | |
| "eval_recall": 0.9851851851851852, | |
| "eval_runtime": 3.7379, | |
| "eval_samples_per_second": 36.117, | |
| "eval_steps_per_second": 1.338, | |
| "eval_top1_accuracy": 0.9851851851851852, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "train_accuracy": 0.9794238683127572 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.0631272941827774, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 0.0723, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.993103448275862, | |
| "eval_error_rate": 0.006896551724137945, | |
| "eval_f1": 0.992600236975882, | |
| "eval_loss": 0.01880481094121933, | |
| "eval_precision": 0.9928774928774929, | |
| "eval_recall": 0.9925925925925926, | |
| "eval_runtime": 3.324, | |
| "eval_samples_per_second": 40.614, | |
| "eval_steps_per_second": 1.504, | |
| "eval_top1_accuracy": 0.9925925925925926, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "train_accuracy": 0.9769547325102881 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 2.755014657974243, | |
| "learning_rate": 0.00011111111111111112, | |
| "loss": 0.0716, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.992, | |
| "eval_error_rate": 0.008000000000000007, | |
| "eval_f1": 0.9925797814417668, | |
| "eval_loss": 0.019506702199578285, | |
| "eval_precision": 0.9928395061728394, | |
| "eval_recall": 0.9925925925925926, | |
| "eval_runtime": 3.2893, | |
| "eval_samples_per_second": 41.043, | |
| "eval_steps_per_second": 1.52, | |
| "eval_top1_accuracy": 0.9925925925925926, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "train_accuracy": 0.9934156378600824 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.016526084393262863, | |
| "learning_rate": 8.888888888888889e-05, | |
| "loss": 0.0161, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9774928774928775, | |
| "eval_error_rate": 0.0225071225071225, | |
| "eval_f1": 0.9777679307755747, | |
| "eval_loss": 0.038870733231306076, | |
| "eval_precision": 0.979122085048011, | |
| "eval_recall": 0.9777777777777777, | |
| "eval_runtime": 3.6761, | |
| "eval_samples_per_second": 36.724, | |
| "eval_steps_per_second": 1.36, | |
| "eval_top1_accuracy": 0.9777777777777777, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "step": 204, | |
| "total_flos": 5.0216159448612864e+17, | |
| "train_loss": 0.2055974360190186, | |
| "train_runtime": 303.9865, | |
| "train_samples_per_second": 35.528, | |
| "train_steps_per_second": 1.118 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 340, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 2 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.0216159448612864e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |