| { | |
| "best_metric": 1.0, | |
| "best_model_checkpoint": "cvt-13-finetuned-waste/checkpoint-117", | |
| "epoch": 2.9936305732484074, | |
| "global_step": 351, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 7.9487, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 6.9548, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 4.6619, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.936507936507937e-05, | |
| "loss": 2.2104, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.7777777777777784e-05, | |
| "loss": 0.9647, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.6190476190476194e-05, | |
| "loss": 0.4498, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.460317460317461e-05, | |
| "loss": 0.1823, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.301587301587302e-05, | |
| "loss": 0.1543, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.1428571428571437e-05, | |
| "loss": 0.1095, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 3.984126984126984e-05, | |
| "loss": 0.1266, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.8253968253968256e-05, | |
| "loss": 0.1715, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 2.0537798263831064e-05, | |
| "eval_runtime": 73.8748, | |
| "eval_samples_per_second": 135.784, | |
| "eval_steps_per_second": 4.25, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 3.6666666666666666e-05, | |
| "loss": 0.171, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 3.5079365079365075e-05, | |
| "loss": 0.1278, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.349206349206349e-05, | |
| "loss": 0.1283, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.19047619047619e-05, | |
| "loss": 0.1861, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 3.0317460317460318e-05, | |
| "loss": 0.1497, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 2.8730158730158728e-05, | |
| "loss": 0.1633, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 2.714285714285714e-05, | |
| "loss": 0.1733, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 2.5555555555555554e-05, | |
| "loss": 0.1624, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 2.396825396825397e-05, | |
| "loss": 0.1725, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 2.2380952380952384e-05, | |
| "loss": 0.172, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 2.0793650793650797e-05, | |
| "loss": 0.1514, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 1.920634920634921e-05, | |
| "loss": 0.1194, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 1.5838317267480306e-05, | |
| "eval_runtime": 73.1043, | |
| "eval_samples_per_second": 137.215, | |
| "eval_steps_per_second": 4.295, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 1.761904761904762e-05, | |
| "loss": 0.1772, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 1.6031746031746033e-05, | |
| "loss": 0.1811, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 1.4444444444444444e-05, | |
| "loss": 0.1552, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 1.2857142857142857e-05, | |
| "loss": 0.1242, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 1.126984126984127e-05, | |
| "loss": 0.124, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 9.682539682539683e-06, | |
| "loss": 0.1551, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 8.095238095238097e-06, | |
| "loss": 0.1902, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 6.507936507936509e-06, | |
| "loss": 0.1134, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 4.920634920634921e-06, | |
| "loss": 0.1701, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.134, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 1.7460317460317462e-06, | |
| "loss": 0.1645, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 1.5873015873015874e-07, | |
| "loss": 0.1496, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 1.7963629943551496e-05, | |
| "eval_runtime": 72.7324, | |
| "eval_samples_per_second": 137.917, | |
| "eval_steps_per_second": 4.317, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "step": 351, | |
| "total_flos": 8.139769344619315e+17, | |
| "train_loss": 0.788053667698151, | |
| "train_runtime": 1008.4422, | |
| "train_samples_per_second": 44.76, | |
| "train_steps_per_second": 0.348 | |
| } | |
| ], | |
| "max_steps": 351, | |
| "num_train_epochs": 3, | |
| "total_flos": 8.139769344619315e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |