| { | |
| "best_metric": 0.9755555555555555, | |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-378", | |
| "epoch": 2.9822485207100593, | |
| "eval_steps": 500, | |
| "global_step": 378, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07889546351084813, | |
| "grad_norm": 4.885411262512207, | |
| "learning_rate": 1.3157894736842106e-05, | |
| "loss": 2.2985, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.15779092702169625, | |
| "grad_norm": 6.575764179229736, | |
| "learning_rate": 2.6315789473684212e-05, | |
| "loss": 2.0642, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.23668639053254437, | |
| "grad_norm": 8.125149726867676, | |
| "learning_rate": 3.9473684210526316e-05, | |
| "loss": 1.5012, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3155818540433925, | |
| "grad_norm": 11.912463188171387, | |
| "learning_rate": 4.970588235294118e-05, | |
| "loss": 0.8692, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.39447731755424065, | |
| "grad_norm": 15.561235427856445, | |
| "learning_rate": 4.823529411764706e-05, | |
| "loss": 0.6062, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.47337278106508873, | |
| "grad_norm": 22.308109283447266, | |
| "learning_rate": 4.6764705882352944e-05, | |
| "loss": 0.4878, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5522682445759369, | |
| "grad_norm": 16.376893997192383, | |
| "learning_rate": 4.5294117647058826e-05, | |
| "loss": 0.4598, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.631163708086785, | |
| "grad_norm": 20.709991455078125, | |
| "learning_rate": 4.382352941176471e-05, | |
| "loss": 0.3735, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.7100591715976331, | |
| "grad_norm": 19.054445266723633, | |
| "learning_rate": 4.235294117647059e-05, | |
| "loss": 0.4128, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.7889546351084813, | |
| "grad_norm": 10.85267162322998, | |
| "learning_rate": 4.0882352941176474e-05, | |
| "loss": 0.3343, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.8678500986193294, | |
| "grad_norm": 12.394430160522461, | |
| "learning_rate": 3.9411764705882356e-05, | |
| "loss": 0.3172, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.9467455621301775, | |
| "grad_norm": 13.280746459960938, | |
| "learning_rate": 3.794117647058824e-05, | |
| "loss": 0.2875, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.9940828402366864, | |
| "eval_accuracy": 0.9516666666666667, | |
| "eval_loss": 0.15403828024864197, | |
| "eval_runtime": 32.6659, | |
| "eval_samples_per_second": 165.31, | |
| "eval_steps_per_second": 5.174, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 1.0256410256410255, | |
| "grad_norm": 11.388362884521484, | |
| "learning_rate": 3.6470588235294114e-05, | |
| "loss": 0.2601, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.1045364891518739, | |
| "grad_norm": 21.39406394958496, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.287, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.183431952662722, | |
| "grad_norm": 14.232524871826172, | |
| "learning_rate": 3.352941176470588e-05, | |
| "loss": 0.2604, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.26232741617357, | |
| "grad_norm": 9.439920425415039, | |
| "learning_rate": 3.205882352941177e-05, | |
| "loss": 0.2563, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.3412228796844181, | |
| "grad_norm": 22.91378402709961, | |
| "learning_rate": 3.058823529411765e-05, | |
| "loss": 0.2376, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.4201183431952662, | |
| "grad_norm": 26.201648712158203, | |
| "learning_rate": 2.9117647058823534e-05, | |
| "loss": 0.2354, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.4990138067061145, | |
| "grad_norm": 11.116905212402344, | |
| "learning_rate": 2.7647058823529416e-05, | |
| "loss": 0.2424, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.5779092702169626, | |
| "grad_norm": 9.413314819335938, | |
| "learning_rate": 2.6176470588235295e-05, | |
| "loss": 0.2572, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.6568047337278107, | |
| "grad_norm": 11.392881393432617, | |
| "learning_rate": 2.4705882352941178e-05, | |
| "loss": 0.227, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.7357001972386588, | |
| "grad_norm": 8.600625038146973, | |
| "learning_rate": 2.323529411764706e-05, | |
| "loss": 0.2078, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.8145956607495068, | |
| "grad_norm": 11.280962944030762, | |
| "learning_rate": 2.1764705882352943e-05, | |
| "loss": 0.2259, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.893491124260355, | |
| "grad_norm": 5.870893955230713, | |
| "learning_rate": 2.0294117647058825e-05, | |
| "loss": 0.1989, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.972386587771203, | |
| "grad_norm": 12.228656768798828, | |
| "learning_rate": 1.8823529411764708e-05, | |
| "loss": 0.2201, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.9960552268244576, | |
| "eval_accuracy": 0.975, | |
| "eval_loss": 0.08536241203546524, | |
| "eval_runtime": 32.8385, | |
| "eval_samples_per_second": 164.441, | |
| "eval_steps_per_second": 5.146, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 2.051282051282051, | |
| "grad_norm": 7.734664440155029, | |
| "learning_rate": 1.735294117647059e-05, | |
| "loss": 0.1785, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.1301775147928996, | |
| "grad_norm": 13.498882293701172, | |
| "learning_rate": 1.588235294117647e-05, | |
| "loss": 0.2043, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.2090729783037477, | |
| "grad_norm": 11.542675971984863, | |
| "learning_rate": 1.4411764705882352e-05, | |
| "loss": 0.1842, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.287968441814596, | |
| "grad_norm": 10.036293029785156, | |
| "learning_rate": 1.2941176470588238e-05, | |
| "loss": 0.1996, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.366863905325444, | |
| "grad_norm": 8.317439079284668, | |
| "learning_rate": 1.1470588235294118e-05, | |
| "loss": 0.1573, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.445759368836292, | |
| "grad_norm": 6.859732627868652, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1835, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.52465483234714, | |
| "grad_norm": 13.328524589538574, | |
| "learning_rate": 8.529411764705883e-06, | |
| "loss": 0.187, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.603550295857988, | |
| "grad_norm": 7.502381801605225, | |
| "learning_rate": 7.058823529411765e-06, | |
| "loss": 0.1502, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.6824457593688362, | |
| "grad_norm": 14.761018753051758, | |
| "learning_rate": 5.588235294117647e-06, | |
| "loss": 0.193, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.7613412228796843, | |
| "grad_norm": 10.346915245056152, | |
| "learning_rate": 4.11764705882353e-06, | |
| "loss": 0.1617, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.8402366863905324, | |
| "grad_norm": 12.84180736541748, | |
| "learning_rate": 2.647058823529412e-06, | |
| "loss": 0.1645, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.9191321499013805, | |
| "grad_norm": 7.301783561706543, | |
| "learning_rate": 1.1764705882352942e-06, | |
| "loss": 0.1714, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.9822485207100593, | |
| "eval_accuracy": 0.9755555555555555, | |
| "eval_loss": 0.07779138535261154, | |
| "eval_runtime": 33.1571, | |
| "eval_samples_per_second": 162.861, | |
| "eval_steps_per_second": 5.097, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 2.9822485207100593, | |
| "step": 378, | |
| "total_flos": 1.2017076524313477e+18, | |
| "train_loss": 0.406993343716576, | |
| "train_runtime": 795.2889, | |
| "train_samples_per_second": 61.11, | |
| "train_steps_per_second": 0.475 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 378, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.2017076524313477e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |