{ "best_metric": 0.07263224571943283, "best_model_checkpoint": "vit-fine-tuned-image-classification-beans-3\\checkpoint-100", "epoch": 3.0, "eval_steps": 100, "global_step": 195, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.15384615384615385, "grad_norm": 1.4810495376586914, "learning_rate": 0.00018974358974358974, "loss": 0.7793, "step": 10 }, { "epoch": 0.3076923076923077, "grad_norm": 0.9975818991661072, "learning_rate": 0.0001794871794871795, "loss": 0.3134, "step": 20 }, { "epoch": 0.46153846153846156, "grad_norm": 0.4794284701347351, "learning_rate": 0.00016923076923076923, "loss": 0.2445, "step": 30 }, { "epoch": 0.6153846153846154, "grad_norm": 5.960256576538086, "learning_rate": 0.00015897435897435896, "loss": 0.2035, "step": 40 }, { "epoch": 0.7692307692307693, "grad_norm": 0.5773417949676514, "learning_rate": 0.00014871794871794872, "loss": 0.1504, "step": 50 }, { "epoch": 0.9230769230769231, "grad_norm": 0.7223901152610779, "learning_rate": 0.00013846153846153847, "loss": 0.2487, "step": 60 }, { "epoch": 1.0769230769230769, "grad_norm": 0.22385026514530182, "learning_rate": 0.00012820512820512823, "loss": 0.1184, "step": 70 }, { "epoch": 1.2307692307692308, "grad_norm": 0.1481306254863739, "learning_rate": 0.00011794871794871796, "loss": 0.1035, "step": 80 }, { "epoch": 1.3846153846153846, "grad_norm": 0.13421788811683655, "learning_rate": 0.0001076923076923077, "loss": 0.0605, "step": 90 }, { "epoch": 1.5384615384615383, "grad_norm": 0.12463743984699249, "learning_rate": 9.743589743589744e-05, "loss": 0.0423, "step": 100 }, { "epoch": 1.5384615384615383, "eval_accuracy": 0.9849624060150376, "eval_loss": 0.07263224571943283, "eval_runtime": 29.5405, "eval_samples_per_second": 4.502, "eval_steps_per_second": 0.575, "step": 100 }, { "epoch": 1.6923076923076923, "grad_norm": 2.560662031173706, "learning_rate": 8.717948717948718e-05, "loss": 0.0546, "step": 110 }, { "epoch": 1.8461538461538463, "grad_norm": 0.3537278175354004, "learning_rate": 7.692307692307693e-05, "loss": 0.1158, "step": 120 }, { "epoch": 2.0, "grad_norm": 5.119251251220703, "learning_rate": 6.666666666666667e-05, "loss": 0.0996, "step": 130 }, { "epoch": 2.1538461538461537, "grad_norm": 0.0981154814362526, "learning_rate": 5.6410256410256414e-05, "loss": 0.0401, "step": 140 }, { "epoch": 2.3076923076923075, "grad_norm": 5.4543890953063965, "learning_rate": 4.615384615384616e-05, "loss": 0.0254, "step": 150 }, { "epoch": 2.4615384615384617, "grad_norm": 3.7947781085968018, "learning_rate": 3.58974358974359e-05, "loss": 0.0716, "step": 160 }, { "epoch": 2.6153846153846154, "grad_norm": 0.08916320651769638, "learning_rate": 2.564102564102564e-05, "loss": 0.0444, "step": 170 }, { "epoch": 2.769230769230769, "grad_norm": 0.08607500791549683, "learning_rate": 1.5384615384615387e-05, "loss": 0.0165, "step": 180 }, { "epoch": 2.9230769230769234, "grad_norm": 0.08345240354537964, "learning_rate": 5.128205128205128e-06, "loss": 0.0164, "step": 190 }, { "epoch": 3.0, "step": 195, "total_flos": 2.4038230623573197e+17, "train_loss": 0.14139964565252647, "train_runtime": 2174.3416, "train_samples_per_second": 1.427, "train_steps_per_second": 0.09 } ], "logging_steps": 10, "max_steps": 195, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 100, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 2.4038230623573197e+17, "train_batch_size": 16, "trial_name": null, "trial_params": null }