| { | |
| "best_metric": 0.9011764705882352, | |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-90", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 90, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 7.228083610534668, | |
| "learning_rate": 4.938271604938271e-05, | |
| "loss": 2.4954, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 13.833573341369629, | |
| "learning_rate": 4.3209876543209875e-05, | |
| "loss": 1.6703, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 12.008746147155762, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.9086, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8117647058823529, | |
| "eval_loss": 0.5746737718582153, | |
| "eval_runtime": 7.2281, | |
| "eval_samples_per_second": 58.799, | |
| "eval_steps_per_second": 1.937, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "grad_norm": 14.395578384399414, | |
| "learning_rate": 3.08641975308642e-05, | |
| "loss": 0.6799, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "grad_norm": 10.231263160705566, | |
| "learning_rate": 2.4691358024691357e-05, | |
| "loss": 0.588, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 23.882062911987305, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.5057, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8705882352941177, | |
| "eval_loss": 0.35231178998947144, | |
| "eval_runtime": 7.011, | |
| "eval_samples_per_second": 60.619, | |
| "eval_steps_per_second": 1.997, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "grad_norm": 10.384401321411133, | |
| "learning_rate": 1.2345679012345678e-05, | |
| "loss": 0.5149, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "grad_norm": 7.370152473449707, | |
| "learning_rate": 6.172839506172839e-06, | |
| "loss": 0.5327, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 9.536111831665039, | |
| "learning_rate": 0.0, | |
| "loss": 0.4594, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9011764705882352, | |
| "eval_loss": 0.2881990969181061, | |
| "eval_runtime": 7.0288, | |
| "eval_samples_per_second": 60.465, | |
| "eval_steps_per_second": 1.992, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 90, | |
| "total_flos": 2.8493718701027328e+17, | |
| "train_loss": 0.9283154063754612, | |
| "train_runtime": 296.0589, | |
| "train_samples_per_second": 38.709, | |
| "train_steps_per_second": 0.304 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 90, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 2.8493718701027328e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |