| { | |
| "best_metric": 0.8627450980392157, | |
| "best_model_checkpoint": "vit-base-patch16-224-ve-U10-12\\checkpoint-94", | |
| "epoch": 11.428571428571429, | |
| "eval_steps": 500, | |
| "global_step": 180, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 5.467836257309941e-05, | |
| "loss": 1.3634, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_accuracy": 0.49019607843137253, | |
| "eval_loss": 1.228261113166809, | |
| "eval_runtime": 0.912, | |
| "eval_samples_per_second": 55.923, | |
| "eval_steps_per_second": 2.193, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 5.1461988304093566e-05, | |
| "loss": 1.2422, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 4.824561403508772e-05, | |
| "loss": 1.099, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "eval_accuracy": 0.6274509803921569, | |
| "eval_loss": 1.009804606437683, | |
| "eval_runtime": 0.7828, | |
| "eval_samples_per_second": 65.149, | |
| "eval_steps_per_second": 2.555, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 4.502923976608187e-05, | |
| "loss": 0.9373, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 0.8729690909385681, | |
| "eval_runtime": 0.7821, | |
| "eval_samples_per_second": 65.206, | |
| "eval_steps_per_second": 2.557, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 4.1812865497076025e-05, | |
| "loss": 0.8023, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 3.859649122807018e-05, | |
| "loss": 0.7066, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.803921568627451, | |
| "eval_loss": 0.6674012541770935, | |
| "eval_runtime": 0.7999, | |
| "eval_samples_per_second": 63.759, | |
| "eval_steps_per_second": 2.5, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 3.5380116959064324e-05, | |
| "loss": 0.6035, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "eval_accuracy": 0.7647058823529411, | |
| "eval_loss": 0.6062445044517517, | |
| "eval_runtime": 0.7697, | |
| "eval_samples_per_second": 66.263, | |
| "eval_steps_per_second": 2.599, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 5.08, | |
| "learning_rate": 3.216374269005848e-05, | |
| "loss": 0.5052, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "learning_rate": 2.894736842105263e-05, | |
| "loss": 0.4011, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "eval_accuracy": 0.8627450980392157, | |
| "eval_loss": 0.5809429883956909, | |
| "eval_runtime": 0.7759, | |
| "eval_samples_per_second": 65.729, | |
| "eval_steps_per_second": 2.578, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 6.35, | |
| "learning_rate": 2.5730994152046783e-05, | |
| "loss": 0.3438, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 6.98, | |
| "learning_rate": 2.2514619883040936e-05, | |
| "loss": 0.2799, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 6.98, | |
| "eval_accuracy": 0.803921568627451, | |
| "eval_loss": 0.623532235622406, | |
| "eval_runtime": 0.8145, | |
| "eval_samples_per_second": 62.613, | |
| "eval_steps_per_second": 2.455, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 7.62, | |
| "learning_rate": 1.929824561403509e-05, | |
| "loss": 0.2572, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.7647058823529411, | |
| "eval_loss": 0.669582724571228, | |
| "eval_runtime": 0.778, | |
| "eval_samples_per_second": 65.555, | |
| "eval_steps_per_second": 2.571, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 8.25, | |
| "learning_rate": 1.608187134502924e-05, | |
| "loss": 0.2402, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "learning_rate": 1.2865497076023392e-05, | |
| "loss": 0.2384, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 8.95, | |
| "eval_accuracy": 0.7647058823529411, | |
| "eval_loss": 0.6868889927864075, | |
| "eval_runtime": 0.7916, | |
| "eval_samples_per_second": 64.426, | |
| "eval_steps_per_second": 2.526, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 9.52, | |
| "learning_rate": 9.649122807017545e-06, | |
| "loss": 0.2104, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 9.97, | |
| "eval_accuracy": 0.7254901960784313, | |
| "eval_loss": 0.7198700308799744, | |
| "eval_runtime": 0.7795, | |
| "eval_samples_per_second": 65.43, | |
| "eval_steps_per_second": 2.566, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 10.16, | |
| "learning_rate": 6.432748538011696e-06, | |
| "loss": 0.2159, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 10.79, | |
| "learning_rate": 3.216374269005848e-06, | |
| "loss": 0.1894, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 10.98, | |
| "eval_accuracy": 0.8431372549019608, | |
| "eval_loss": 0.5567971467971802, | |
| "eval_runtime": 0.7722, | |
| "eval_samples_per_second": 66.043, | |
| "eval_steps_per_second": 2.59, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 11.43, | |
| "learning_rate": 0.0, | |
| "loss": 0.1917, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 11.43, | |
| "eval_accuracy": 0.8431372549019608, | |
| "eval_loss": 0.5610877275466919, | |
| "eval_runtime": 0.7721, | |
| "eval_samples_per_second": 66.054, | |
| "eval_steps_per_second": 2.59, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 11.43, | |
| "step": 180, | |
| "total_flos": 1.7803328819545866e+18, | |
| "train_loss": 0.5459669225745731, | |
| "train_runtime": 356.8634, | |
| "train_samples_per_second": 67.589, | |
| "train_steps_per_second": 0.504 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 180, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 12, | |
| "save_steps": 500, | |
| "total_flos": 1.7803328819545866e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |