| { | |
| "best_metric": 0.8635994587280108, | |
| "best_model_checkpoint": "vit-base-patch16-224-in21k-bantai_vitv1/checkpoint-345", | |
| "epoch": 2.995670995670996, | |
| "global_step": 345, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 1.3904, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 1.3115, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.2857142857142856e-05, | |
| "loss": 1.1847, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.9193548387096775e-05, | |
| "loss": 0.9772, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.7580645161290326e-05, | |
| "loss": 0.8358, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.596774193548387e-05, | |
| "loss": 0.7316, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 4.435483870967742e-05, | |
| "loss": 0.6985, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 4.2741935483870973e-05, | |
| "loss": 0.6644, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.112903225806452e-05, | |
| "loss": 0.6267, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 3.951612903225806e-05, | |
| "loss": 0.5925, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 3.7903225806451614e-05, | |
| "loss": 0.5997, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7886332882273343, | |
| "eval_loss": 0.5401414632797241, | |
| "eval_runtime": 43.7103, | |
| "eval_samples_per_second": 84.534, | |
| "eval_steps_per_second": 2.654, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 3.6290322580645165e-05, | |
| "loss": 0.6008, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 3.467741935483872e-05, | |
| "loss": 0.5502, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 3.306451612903226e-05, | |
| "loss": 0.5703, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 3.1451612903225806e-05, | |
| "loss": 0.5032, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.9838709677419357e-05, | |
| "loss": 0.5292, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 2.822580645161291e-05, | |
| "loss": 0.4798, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 2.661290322580645e-05, | |
| "loss": 0.4857, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.4893, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 2.338709677419355e-05, | |
| "loss": 0.4587, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 2.1774193548387097e-05, | |
| "loss": 0.4735, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 2.0161290322580645e-05, | |
| "loss": 0.486, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.8548387096774193e-05, | |
| "loss": 0.4696, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8481732070365359, | |
| "eval_loss": 0.4410068094730377, | |
| "eval_runtime": 43.5298, | |
| "eval_samples_per_second": 84.884, | |
| "eval_steps_per_second": 2.665, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 1.693548387096774e-05, | |
| "loss": 0.49, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.5322580645161292e-05, | |
| "loss": 0.397, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 1.3709677419354839e-05, | |
| "loss": 0.4055, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 1.2096774193548388e-05, | |
| "loss": 0.4111, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 1.0483870967741936e-05, | |
| "loss": 0.4216, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 8.870967741935484e-06, | |
| "loss": 0.4084, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 7.258064516129033e-06, | |
| "loss": 0.3866, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 5.64516129032258e-06, | |
| "loss": 0.3881, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 4.032258064516129e-06, | |
| "loss": 0.3809, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 2.4193548387096776e-06, | |
| "loss": 0.391, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 8.064516129032258e-07, | |
| "loss": 0.4019, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8635994587280108, | |
| "eval_loss": 0.3961198627948761, | |
| "eval_runtime": 43.4324, | |
| "eval_samples_per_second": 85.075, | |
| "eval_steps_per_second": 2.671, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 345, | |
| "total_flos": 3.4309418479871754e+18, | |
| "train_loss": 0.5908640992814216, | |
| "train_runtime": 1178.2294, | |
| "train_samples_per_second": 37.625, | |
| "train_steps_per_second": 0.293 | |
| } | |
| ], | |
| "max_steps": 345, | |
| "num_train_epochs": 3, | |
| "total_flos": 3.4309418479871754e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |