| { |
| "best_metric": 0.043110452592372894, |
| "best_model_checkpoint": "./output/vit-base-riego/checkpoint-500", |
| "epoch": 3.0, |
| "global_step": 630, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.05, |
| "learning_rate": 0.00019714285714285716, |
| "loss": 0.2579, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 0.000193968253968254, |
| "loss": 0.1457, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.14, |
| "learning_rate": 0.00019079365079365082, |
| "loss": 0.0975, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.19, |
| "learning_rate": 0.00018761904761904763, |
| "loss": 0.0565, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.24, |
| "learning_rate": 0.00018444444444444446, |
| "loss": 0.0579, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.29, |
| "learning_rate": 0.00018126984126984127, |
| "loss": 0.0302, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.33, |
| "learning_rate": 0.0001780952380952381, |
| "loss": 0.0039, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 0.00017492063492063493, |
| "loss": 0.0441, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.43, |
| "learning_rate": 0.00017174603174603174, |
| "loss": 0.0414, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.48, |
| "learning_rate": 0.00016857142857142857, |
| "loss": 0.0443, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.48, |
| "eval_f1": 0.8742058449809403, |
| "eval_loss": 0.4737350344657898, |
| "eval_runtime": 8.752, |
| "eval_samples_per_second": 95.978, |
| "eval_steps_per_second": 11.997, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.52, |
| "learning_rate": 0.0001653968253968254, |
| "loss": 0.1463, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.57, |
| "learning_rate": 0.00016222222222222224, |
| "loss": 0.0683, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.62, |
| "learning_rate": 0.00015904761904761904, |
| "loss": 0.0551, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.67, |
| "learning_rate": 0.0001561904761904762, |
| "loss": 0.1104, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.71, |
| "learning_rate": 0.00015301587301587302, |
| "loss": 0.0087, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.76, |
| "learning_rate": 0.00014984126984126986, |
| "loss": 0.0566, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.81, |
| "learning_rate": 0.00014666666666666666, |
| "loss": 0.1618, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.86, |
| "learning_rate": 0.0001434920634920635, |
| "loss": 0.1098, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.9, |
| "learning_rate": 0.0001403174603174603, |
| "loss": 0.0608, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.95, |
| "learning_rate": 0.00013714285714285716, |
| "loss": 0.0349, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.95, |
| "eval_f1": 0.973293768545994, |
| "eval_loss": 0.07742569595575333, |
| "eval_runtime": 10.0816, |
| "eval_samples_per_second": 83.32, |
| "eval_steps_per_second": 10.415, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.0, |
| "learning_rate": 0.00013396825396825397, |
| "loss": 0.0455, |
| "step": 210 |
| }, |
| { |
| "epoch": 1.05, |
| "learning_rate": 0.0001307936507936508, |
| "loss": 0.0756, |
| "step": 220 |
| }, |
| { |
| "epoch": 1.1, |
| "learning_rate": 0.0001276190476190476, |
| "loss": 0.0065, |
| "step": 230 |
| }, |
| { |
| "epoch": 1.14, |
| "learning_rate": 0.00012444444444444444, |
| "loss": 0.0255, |
| "step": 240 |
| }, |
| { |
| "epoch": 1.19, |
| "learning_rate": 0.00012126984126984127, |
| "loss": 0.0841, |
| "step": 250 |
| }, |
| { |
| "epoch": 1.24, |
| "learning_rate": 0.0001180952380952381, |
| "loss": 0.1931, |
| "step": 260 |
| }, |
| { |
| "epoch": 1.29, |
| "learning_rate": 0.00011492063492063491, |
| "loss": 0.0206, |
| "step": 270 |
| }, |
| { |
| "epoch": 1.33, |
| "learning_rate": 0.00011174603174603176, |
| "loss": 0.0431, |
| "step": 280 |
| }, |
| { |
| "epoch": 1.38, |
| "learning_rate": 0.00010857142857142856, |
| "loss": 0.0103, |
| "step": 290 |
| }, |
| { |
| "epoch": 1.43, |
| "learning_rate": 0.00010539682539682541, |
| "loss": 0.003, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.43, |
| "eval_f1": 0.9794117647058823, |
| "eval_loss": 0.0675111711025238, |
| "eval_runtime": 9.6291, |
| "eval_samples_per_second": 87.235, |
| "eval_steps_per_second": 10.904, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.48, |
| "learning_rate": 0.00010222222222222222, |
| "loss": 0.0345, |
| "step": 310 |
| }, |
| { |
| "epoch": 1.52, |
| "learning_rate": 9.904761904761905e-05, |
| "loss": 0.0022, |
| "step": 320 |
| }, |
| { |
| "epoch": 1.57, |
| "learning_rate": 9.587301587301588e-05, |
| "loss": 0.0362, |
| "step": 330 |
| }, |
| { |
| "epoch": 1.62, |
| "learning_rate": 9.26984126984127e-05, |
| "loss": 0.0733, |
| "step": 340 |
| }, |
| { |
| "epoch": 1.67, |
| "learning_rate": 8.952380952380953e-05, |
| "loss": 0.1402, |
| "step": 350 |
| }, |
| { |
| "epoch": 1.71, |
| "learning_rate": 8.634920634920635e-05, |
| "loss": 0.0135, |
| "step": 360 |
| }, |
| { |
| "epoch": 1.76, |
| "learning_rate": 8.317460317460319e-05, |
| "loss": 0.0309, |
| "step": 370 |
| }, |
| { |
| "epoch": 1.81, |
| "learning_rate": 8e-05, |
| "loss": 0.0301, |
| "step": 380 |
| }, |
| { |
| "epoch": 1.86, |
| "learning_rate": 7.682539682539684e-05, |
| "loss": 0.0023, |
| "step": 390 |
| }, |
| { |
| "epoch": 1.9, |
| "learning_rate": 7.365079365079366e-05, |
| "loss": 0.002, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.9, |
| "eval_f1": 0.9809663250366033, |
| "eval_loss": 0.06742586195468903, |
| "eval_runtime": 9.4801, |
| "eval_samples_per_second": 88.606, |
| "eval_steps_per_second": 11.076, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.95, |
| "learning_rate": 7.047619047619048e-05, |
| "loss": 0.0193, |
| "step": 410 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 6.730158730158731e-05, |
| "loss": 0.0465, |
| "step": 420 |
| }, |
| { |
| "epoch": 2.05, |
| "learning_rate": 6.412698412698413e-05, |
| "loss": 0.0019, |
| "step": 430 |
| }, |
| { |
| "epoch": 2.1, |
| "learning_rate": 6.0952380952380964e-05, |
| "loss": 0.0019, |
| "step": 440 |
| }, |
| { |
| "epoch": 2.14, |
| "learning_rate": 5.7777777777777776e-05, |
| "loss": 0.0017, |
| "step": 450 |
| }, |
| { |
| "epoch": 2.19, |
| "learning_rate": 5.46031746031746e-05, |
| "loss": 0.0015, |
| "step": 460 |
| }, |
| { |
| "epoch": 2.24, |
| "learning_rate": 5.142857142857143e-05, |
| "loss": 0.0014, |
| "step": 470 |
| }, |
| { |
| "epoch": 2.29, |
| "learning_rate": 4.8253968253968255e-05, |
| "loss": 0.0014, |
| "step": 480 |
| }, |
| { |
| "epoch": 2.33, |
| "learning_rate": 4.507936507936508e-05, |
| "loss": 0.0014, |
| "step": 490 |
| }, |
| { |
| "epoch": 2.38, |
| "learning_rate": 4.190476190476191e-05, |
| "loss": 0.0014, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.38, |
| "eval_f1": 0.9870875179340028, |
| "eval_loss": 0.043110452592372894, |
| "eval_runtime": 12.9756, |
| "eval_samples_per_second": 64.737, |
| "eval_steps_per_second": 8.092, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.43, |
| "learning_rate": 3.8730158730158734e-05, |
| "loss": 0.0014, |
| "step": 510 |
| }, |
| { |
| "epoch": 2.48, |
| "learning_rate": 3.555555555555556e-05, |
| "loss": 0.0013, |
| "step": 520 |
| }, |
| { |
| "epoch": 2.52, |
| "learning_rate": 3.2380952380952386e-05, |
| "loss": 0.0014, |
| "step": 530 |
| }, |
| { |
| "epoch": 2.57, |
| "learning_rate": 2.920634920634921e-05, |
| "loss": 0.0104, |
| "step": 540 |
| }, |
| { |
| "epoch": 2.62, |
| "learning_rate": 2.6031746031746035e-05, |
| "loss": 0.0012, |
| "step": 550 |
| }, |
| { |
| "epoch": 2.67, |
| "learning_rate": 2.2857142857142858e-05, |
| "loss": 0.0012, |
| "step": 560 |
| }, |
| { |
| "epoch": 2.71, |
| "learning_rate": 1.9682539682539684e-05, |
| "loss": 0.0013, |
| "step": 570 |
| }, |
| { |
| "epoch": 2.76, |
| "learning_rate": 1.6507936507936507e-05, |
| "loss": 0.0013, |
| "step": 580 |
| }, |
| { |
| "epoch": 2.81, |
| "learning_rate": 1.3333333333333333e-05, |
| "loss": 0.0013, |
| "step": 590 |
| }, |
| { |
| "epoch": 2.86, |
| "learning_rate": 1.015873015873016e-05, |
| "loss": 0.0011, |
| "step": 600 |
| }, |
| { |
| "epoch": 2.86, |
| "eval_f1": 0.9853801169590642, |
| "eval_loss": 0.05441011115908623, |
| "eval_runtime": 11.2209, |
| "eval_samples_per_second": 74.86, |
| "eval_steps_per_second": 9.358, |
| "step": 600 |
| }, |
| { |
| "epoch": 2.9, |
| "learning_rate": 6.984126984126985e-06, |
| "loss": 0.0424, |
| "step": 610 |
| }, |
| { |
| "epoch": 2.95, |
| "learning_rate": 3.8095238095238102e-06, |
| "loss": 0.0013, |
| "step": 620 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 6.34920634920635e-07, |
| "loss": 0.0033, |
| "step": 630 |
| }, |
| { |
| "epoch": 3.0, |
| "step": 630, |
| "total_flos": 7.811192553150874e+17, |
| "train_loss": 0.0414532983113849, |
| "train_runtime": 358.5996, |
| "train_samples_per_second": 28.109, |
| "train_steps_per_second": 1.757 |
| } |
| ], |
| "max_steps": 630, |
| "num_train_epochs": 3, |
| "total_flos": 7.811192553150874e+17, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
