| { | |
| "best_metric": 0.8028747433264887, | |
| "best_model_checkpoint": "vit-base-patch16-224-in21k-finetuned-pokemon-classification/checkpoint-204", | |
| "epoch": 5.956204379562044, | |
| "global_step": 204, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 2.380952380952381e-05, | |
| "loss": 5.0112, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.761904761904762e-05, | |
| "loss": 4.969, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.754098360655738e-05, | |
| "loss": 4.9109, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.14989733059548255, | |
| "eval_loss": 4.819316864013672, | |
| "eval_runtime": 5.776, | |
| "eval_samples_per_second": 84.314, | |
| "eval_steps_per_second": 2.77, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 4.4808743169398906e-05, | |
| "loss": 4.8065, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 4.207650273224044e-05, | |
| "loss": 4.7209, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 3.934426229508197e-05, | |
| "loss": 4.6433, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_accuracy": 0.46611909650924027, | |
| "eval_loss": 4.536120891571045, | |
| "eval_runtime": 6.1813, | |
| "eval_samples_per_second": 78.786, | |
| "eval_steps_per_second": 2.588, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 3.66120218579235e-05, | |
| "loss": 4.5616, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 3.387978142076503e-05, | |
| "loss": 4.45, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 3.114754098360656e-05, | |
| "loss": 4.3805, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 2.841530054644809e-05, | |
| "loss": 4.2878, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "eval_accuracy": 0.6837782340862423, | |
| "eval_loss": 4.254587173461914, | |
| "eval_runtime": 5.9626, | |
| "eval_samples_per_second": 81.676, | |
| "eval_steps_per_second": 2.683, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 2.568306010928962e-05, | |
| "loss": 4.1948, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 2.295081967213115e-05, | |
| "loss": 4.1254, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 2.0218579234972678e-05, | |
| "loss": 4.0792, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7679671457905544, | |
| "eval_loss": 4.0353474617004395, | |
| "eval_runtime": 6.1211, | |
| "eval_samples_per_second": 79.561, | |
| "eval_steps_per_second": 2.614, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 1.7486338797814207e-05, | |
| "loss": 4.0257, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 1.4754098360655739e-05, | |
| "loss": 3.9619, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "learning_rate": 1.2021857923497268e-05, | |
| "loss": 3.9236, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 9.2896174863388e-06, | |
| "loss": 3.8934, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_accuracy": 0.7926078028747433, | |
| "eval_loss": 3.912012815475464, | |
| "eval_runtime": 6.009, | |
| "eval_samples_per_second": 81.045, | |
| "eval_steps_per_second": 2.663, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 5.26, | |
| "learning_rate": 6.557377049180328e-06, | |
| "loss": 3.8488, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 5.55, | |
| "learning_rate": 3.825136612021858e-06, | |
| "loss": 3.8633, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 5.84, | |
| "learning_rate": 1.092896174863388e-06, | |
| "loss": 3.8294, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 5.96, | |
| "eval_accuracy": 0.8028747433264887, | |
| "eval_loss": 3.8734209537506104, | |
| "eval_runtime": 5.8906, | |
| "eval_samples_per_second": 82.675, | |
| "eval_steps_per_second": 2.716, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 5.96, | |
| "step": 204, | |
| "total_flos": 2.0253789729052508e+18, | |
| "train_loss": 4.31497132544424, | |
| "train_runtime": 1061.9918, | |
| "train_samples_per_second": 24.757, | |
| "train_steps_per_second": 0.192 | |
| } | |
| ], | |
| "max_steps": 204, | |
| "num_train_epochs": 6, | |
| "total_flos": 2.0253789729052508e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |