swin-tiny-patch4-window7-224-finetuned-eurosat-leukemia-3000-finetuned-leukemia-1000
/
trainer_state.json
| { | |
| "best_metric": 1.0, | |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat-leukemia-3000-finetuned-leukemia-1000\\checkpoint-57", | |
| "epoch": 9.824561403508772, | |
| "eval_steps": 500, | |
| "global_step": 140, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.7017543859649122, | |
| "grad_norm": 10.25106143951416, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 0.5471, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.9824561403508771, | |
| "eval_accuracy": 0.955, | |
| "eval_loss": 0.12403497099876404, | |
| "eval_runtime": 71.4511, | |
| "eval_samples_per_second": 2.799, | |
| "eval_steps_per_second": 0.098, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.4035087719298245, | |
| "grad_norm": 12.660431861877441, | |
| "learning_rate": 4.761904761904762e-05, | |
| "loss": 0.1792, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.9649122807017543, | |
| "eval_accuracy": 0.985, | |
| "eval_loss": 0.04925594478845596, | |
| "eval_runtime": 70.8726, | |
| "eval_samples_per_second": 2.822, | |
| "eval_steps_per_second": 0.099, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.1052631578947367, | |
| "grad_norm": 12.378658294677734, | |
| "learning_rate": 4.3650793650793655e-05, | |
| "loss": 0.1079, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.807017543859649, | |
| "grad_norm": 7.088730335235596, | |
| "learning_rate": 3.968253968253968e-05, | |
| "loss": 0.0936, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.9473684210526314, | |
| "eval_accuracy": 0.965, | |
| "eval_loss": 0.12096397578716278, | |
| "eval_runtime": 69.7246, | |
| "eval_samples_per_second": 2.868, | |
| "eval_steps_per_second": 0.1, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 3.5087719298245617, | |
| "grad_norm": 7.469219207763672, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 0.0907, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.005616894923150539, | |
| "eval_runtime": 69.6907, | |
| "eval_samples_per_second": 2.87, | |
| "eval_steps_per_second": 0.1, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 4.2105263157894735, | |
| "grad_norm": 5.905189514160156, | |
| "learning_rate": 3.1746031746031745e-05, | |
| "loss": 0.0634, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 4.912280701754386, | |
| "grad_norm": 1.427998423576355, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.0441, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 4.982456140350877, | |
| "eval_accuracy": 0.995, | |
| "eval_loss": 0.01654110848903656, | |
| "eval_runtime": 71.9654, | |
| "eval_samples_per_second": 2.779, | |
| "eval_steps_per_second": 0.097, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 5.614035087719298, | |
| "grad_norm": 42.998802185058594, | |
| "learning_rate": 2.380952380952381e-05, | |
| "loss": 0.0341, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 5.964912280701754, | |
| "eval_accuracy": 0.995, | |
| "eval_loss": 0.0058908830396831036, | |
| "eval_runtime": 71.908, | |
| "eval_samples_per_second": 2.781, | |
| "eval_steps_per_second": 0.097, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 6.315789473684211, | |
| "grad_norm": 3.4468114376068115, | |
| "learning_rate": 1.984126984126984e-05, | |
| "loss": 0.0406, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 6.947368421052632, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0017600071150809526, | |
| "eval_runtime": 72.5057, | |
| "eval_samples_per_second": 2.758, | |
| "eval_steps_per_second": 0.097, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 7.017543859649122, | |
| "grad_norm": 9.760284423828125, | |
| "learning_rate": 1.5873015873015872e-05, | |
| "loss": 0.0521, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 7.719298245614035, | |
| "grad_norm": 10.58344841003418, | |
| "learning_rate": 1.1904761904761905e-05, | |
| "loss": 0.013, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.995, | |
| "eval_loss": 0.019968407228589058, | |
| "eval_runtime": 75.6615, | |
| "eval_samples_per_second": 2.643, | |
| "eval_steps_per_second": 0.093, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 8.421052631578947, | |
| "grad_norm": 5.659635543823242, | |
| "learning_rate": 7.936507936507936e-06, | |
| "loss": 0.0342, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 8.982456140350877, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.003038285067304969, | |
| "eval_runtime": 73.7463, | |
| "eval_samples_per_second": 2.712, | |
| "eval_steps_per_second": 0.095, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 9.12280701754386, | |
| "grad_norm": 9.32413101196289, | |
| "learning_rate": 3.968253968253968e-06, | |
| "loss": 0.0186, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 9.824561403508772, | |
| "grad_norm": 6.734475612640381, | |
| "learning_rate": 0.0, | |
| "loss": 0.0246, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 9.824561403508772, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.002627989277243614, | |
| "eval_runtime": 71.8163, | |
| "eval_samples_per_second": 2.785, | |
| "eval_steps_per_second": 0.097, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 9.824561403508772, | |
| "step": 140, | |
| "total_flos": 4.400504290055946e+17, | |
| "train_loss": 0.09594950729182788, | |
| "train_runtime": 15427.52, | |
| "train_samples_per_second": 1.167, | |
| "train_steps_per_second": 0.009 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 140, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 4.400504290055946e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |