| { | |
| "best_metric": 0.78, | |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-student_six_classes-finetuned-student_six_classes/checkpoint-3", | |
| "epoch": 9.23076923076923, | |
| "eval_steps": 500, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.9230769230769231, | |
| "eval_accuracy": 0.78, | |
| "eval_loss": 0.5972073674201965, | |
| "eval_runtime": 4.255, | |
| "eval_samples_per_second": 23.502, | |
| "eval_steps_per_second": 0.94, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.8461538461538463, | |
| "eval_accuracy": 0.78, | |
| "eval_loss": 0.9760183095932007, | |
| "eval_runtime": 3.309, | |
| "eval_samples_per_second": 30.221, | |
| "eval_steps_per_second": 1.209, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 2.769230769230769, | |
| "eval_accuracy": 0.78, | |
| "eval_loss": 0.7597123980522156, | |
| "eval_runtime": 2.5315, | |
| "eval_samples_per_second": 39.502, | |
| "eval_steps_per_second": 1.58, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 3.076923076923077, | |
| "grad_norm": 8.534769058227539, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.5361, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.78, | |
| "eval_loss": 0.5870408415794373, | |
| "eval_runtime": 2.5994, | |
| "eval_samples_per_second": 38.471, | |
| "eval_steps_per_second": 1.539, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 4.923076923076923, | |
| "eval_accuracy": 0.78, | |
| "eval_loss": 0.5333480834960938, | |
| "eval_runtime": 2.6785, | |
| "eval_samples_per_second": 37.335, | |
| "eval_steps_per_second": 1.493, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 5.846153846153846, | |
| "eval_accuracy": 0.78, | |
| "eval_loss": 0.5039618015289307, | |
| "eval_runtime": 3.2653, | |
| "eval_samples_per_second": 30.625, | |
| "eval_steps_per_second": 1.225, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 6.153846153846154, | |
| "grad_norm": 2.764887809753418, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.4032, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 6.769230769230769, | |
| "eval_accuracy": 0.78, | |
| "eval_loss": 0.498999685049057, | |
| "eval_runtime": 3.381, | |
| "eval_samples_per_second": 29.577, | |
| "eval_steps_per_second": 1.183, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.78, | |
| "eval_loss": 0.507302463054657, | |
| "eval_runtime": 2.5333, | |
| "eval_samples_per_second": 39.474, | |
| "eval_steps_per_second": 1.579, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 8.923076923076923, | |
| "eval_accuracy": 0.78, | |
| "eval_loss": 0.5070222020149231, | |
| "eval_runtime": 3.7024, | |
| "eval_samples_per_second": 27.01, | |
| "eval_steps_per_second": 1.08, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 9.23076923076923, | |
| "grad_norm": 4.270540237426758, | |
| "learning_rate": 0.0, | |
| "loss": 0.3579, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 9.23076923076923, | |
| "eval_accuracy": 0.78, | |
| "eval_loss": 0.5073193907737732, | |
| "eval_runtime": 3.8479, | |
| "eval_samples_per_second": 25.988, | |
| "eval_steps_per_second": 1.04, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 9.23076923076923, | |
| "step": 30, | |
| "total_flos": 9.186773529172378e+16, | |
| "train_loss": 0.4323955456415812, | |
| "train_runtime": 176.1042, | |
| "train_samples_per_second": 22.714, | |
| "train_steps_per_second": 0.17 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 9.186773529172378e+16, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |