Evaluation on the test set completed on 2024_09_05.
Browse files- README.md +175 -0
- all_results.json +17 -0
- logs/events.out.tfevents.1725353105.datavisu2 +2 -2
- logs/events.out.tfevents.1725551731.datavisu2 +3 -0
- model.safetensors +1 -1
- test_results.json +12 -0
- train_results.json +9 -0
- trainer_state.json +1915 -0
README.md
ADDED
|
@@ -0,0 +1,175 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: facebook/dinov2-base
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
model-index:
|
| 9 |
+
- name: DinoVdeau-base-2024_09_03-batch-size32_epochs150_freeze
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# DinoVdeau-base-2024_09_03-batch-size32_epochs150_freeze
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [facebook/dinov2-base](https://huggingface.co/facebook/dinov2-base) on the None dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.1260
|
| 21 |
+
- F1 Micro: 0.8131
|
| 22 |
+
- F1 Macro: 0.6976
|
| 23 |
+
- Roc Auc: 0.8760
|
| 24 |
+
- Accuracy: 0.3014
|
| 25 |
+
- Learning Rate: 0.0000
|
| 26 |
+
|
| 27 |
+
## Model description
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Intended uses & limitations
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training and evaluation data
|
| 36 |
+
|
| 37 |
+
More information needed
|
| 38 |
+
|
| 39 |
+
## Training procedure
|
| 40 |
+
|
| 41 |
+
### Training hyperparameters
|
| 42 |
+
|
| 43 |
+
The following hyperparameters were used during training:
|
| 44 |
+
- learning_rate: 0.001
|
| 45 |
+
- train_batch_size: 32
|
| 46 |
+
- eval_batch_size: 32
|
| 47 |
+
- seed: 42
|
| 48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
+
- lr_scheduler_type: linear
|
| 50 |
+
- num_epochs: 150
|
| 51 |
+
- mixed_precision_training: Native AMP
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 Micro | F1 Macro | Roc Auc | Accuracy | Rate |
|
| 56 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|:-------:|:--------:|:------:|
|
| 57 |
+
| No log | 1.0 | 273 | 0.1752 | 0.7311 | 0.5105 | 0.8187 | 0.2079 | 0.001 |
|
| 58 |
+
| 0.2857 | 2.0 | 546 | 0.1578 | 0.7583 | 0.5498 | 0.8363 | 0.2349 | 0.001 |
|
| 59 |
+
| 0.2857 | 3.0 | 819 | 0.1516 | 0.7722 | 0.6037 | 0.8505 | 0.2315 | 0.001 |
|
| 60 |
+
| 0.1764 | 4.0 | 1092 | 0.1522 | 0.7650 | 0.6140 | 0.8387 | 0.2422 | 0.001 |
|
| 61 |
+
| 0.1764 | 5.0 | 1365 | 0.1484 | 0.7720 | 0.6162 | 0.8403 | 0.2422 | 0.001 |
|
| 62 |
+
| 0.1677 | 6.0 | 1638 | 0.1482 | 0.7750 | 0.6052 | 0.8435 | 0.2561 | 0.001 |
|
| 63 |
+
| 0.1677 | 7.0 | 1911 | 0.1486 | 0.7729 | 0.6177 | 0.8431 | 0.2419 | 0.001 |
|
| 64 |
+
| 0.1652 | 8.0 | 2184 | 0.1486 | 0.7767 | 0.6172 | 0.8485 | 0.2512 | 0.001 |
|
| 65 |
+
| 0.1652 | 9.0 | 2457 | 0.1483 | 0.7805 | 0.6366 | 0.8570 | 0.2512 | 0.001 |
|
| 66 |
+
| 0.1617 | 10.0 | 2730 | 0.1503 | 0.7683 | 0.6081 | 0.8352 | 0.2453 | 0.001 |
|
| 67 |
+
| 0.1615 | 11.0 | 3003 | 0.1441 | 0.7757 | 0.6200 | 0.8409 | 0.2609 | 0.001 |
|
| 68 |
+
| 0.1615 | 12.0 | 3276 | 0.1487 | 0.7815 | 0.6299 | 0.8543 | 0.2495 | 0.001 |
|
| 69 |
+
| 0.1614 | 13.0 | 3549 | 0.1490 | 0.7779 | 0.6242 | 0.8446 | 0.2519 | 0.001 |
|
| 70 |
+
| 0.1614 | 14.0 | 3822 | 0.1434 | 0.7826 | 0.6379 | 0.8475 | 0.2606 | 0.001 |
|
| 71 |
+
| 0.1599 | 15.0 | 4095 | 0.1435 | 0.7874 | 0.6397 | 0.8552 | 0.2554 | 0.001 |
|
| 72 |
+
| 0.1599 | 16.0 | 4368 | 0.1439 | 0.7793 | 0.6344 | 0.8464 | 0.2568 | 0.001 |
|
| 73 |
+
| 0.1589 | 17.0 | 4641 | 0.1448 | 0.7878 | 0.6422 | 0.8596 | 0.2543 | 0.001 |
|
| 74 |
+
| 0.1589 | 18.0 | 4914 | 0.1440 | 0.7865 | 0.6417 | 0.8552 | 0.2568 | 0.001 |
|
| 75 |
+
| 0.1604 | 19.0 | 5187 | 0.1420 | 0.7864 | 0.6318 | 0.8550 | 0.2540 | 0.001 |
|
| 76 |
+
| 0.1604 | 20.0 | 5460 | 0.1409 | 0.7869 | 0.6409 | 0.8522 | 0.2588 | 0.001 |
|
| 77 |
+
| 0.1586 | 21.0 | 5733 | 0.1425 | 0.7865 | 0.6413 | 0.8561 | 0.2620 | 0.001 |
|
| 78 |
+
| 0.1587 | 22.0 | 6006 | 0.1538 | 0.7854 | 0.6371 | 0.8608 | 0.2370 | 0.001 |
|
| 79 |
+
| 0.1587 | 23.0 | 6279 | 0.1419 | 0.7842 | 0.6390 | 0.8497 | 0.2557 | 0.001 |
|
| 80 |
+
| 0.1592 | 24.0 | 6552 | 0.1414 | 0.7870 | 0.6459 | 0.8561 | 0.2599 | 0.001 |
|
| 81 |
+
| 0.1592 | 25.0 | 6825 | 0.1399 | 0.7868 | 0.6263 | 0.8523 | 0.2685 | 0.001 |
|
| 82 |
+
| 0.1586 | 26.0 | 7098 | 0.1465 | 0.7847 | 0.6238 | 0.8561 | 0.2592 | 0.001 |
|
| 83 |
+
| 0.1586 | 27.0 | 7371 | 0.1551 | 0.7720 | 0.6344 | 0.8433 | 0.2380 | 0.001 |
|
| 84 |
+
| 0.16 | 28.0 | 7644 | 0.1443 | 0.7891 | 0.6430 | 0.8550 | 0.2616 | 0.001 |
|
| 85 |
+
| 0.16 | 29.0 | 7917 | 0.1428 | 0.7874 | 0.6416 | 0.8565 | 0.2568 | 0.001 |
|
| 86 |
+
| 0.1589 | 30.0 | 8190 | 0.1416 | 0.7799 | 0.6308 | 0.8425 | 0.2526 | 0.001 |
|
| 87 |
+
| 0.1589 | 31.0 | 8463 | 0.1398 | 0.7895 | 0.6431 | 0.8566 | 0.2689 | 0.001 |
|
| 88 |
+
| 0.1588 | 32.0 | 8736 | 0.1448 | 0.7891 | 0.6521 | 0.8601 | 0.2568 | 0.001 |
|
| 89 |
+
| 0.1581 | 33.0 | 9009 | 0.1404 | 0.7896 | 0.6497 | 0.8582 | 0.2640 | 0.001 |
|
| 90 |
+
| 0.1581 | 34.0 | 9282 | 0.1426 | 0.7871 | 0.6449 | 0.8537 | 0.2557 | 0.001 |
|
| 91 |
+
| 0.1578 | 35.0 | 9555 | 0.1414 | 0.7846 | 0.6428 | 0.8487 | 0.2630 | 0.001 |
|
| 92 |
+
| 0.1578 | 36.0 | 9828 | 0.1465 | 0.7834 | 0.6434 | 0.8484 | 0.2678 | 0.001 |
|
| 93 |
+
| 0.1576 | 37.0 | 10101 | 0.1380 | 0.7924 | 0.6438 | 0.8577 | 0.2668 | 0.001 |
|
| 94 |
+
| 0.1576 | 38.0 | 10374 | 0.1392 | 0.7892 | 0.6475 | 0.8555 | 0.2637 | 0.001 |
|
| 95 |
+
| 0.1556 | 39.0 | 10647 | 0.1458 | 0.7872 | 0.6592 | 0.8680 | 0.2460 | 0.001 |
|
| 96 |
+
| 0.1556 | 40.0 | 10920 | 0.1389 | 0.7946 | 0.6469 | 0.8660 | 0.2699 | 0.001 |
|
| 97 |
+
| 0.1577 | 41.0 | 11193 | 0.1402 | 0.7848 | 0.6510 | 0.8491 | 0.2616 | 0.001 |
|
| 98 |
+
| 0.1577 | 42.0 | 11466 | 0.1404 | 0.7928 | 0.6609 | 0.8625 | 0.2717 | 0.001 |
|
| 99 |
+
| 0.1576 | 43.0 | 11739 | 0.1394 | 0.7931 | 0.6427 | 0.8593 | 0.2696 | 0.001 |
|
| 100 |
+
| 0.1543 | 44.0 | 12012 | 0.1367 | 0.7989 | 0.6568 | 0.8632 | 0.2755 | 0.0001 |
|
| 101 |
+
| 0.1543 | 45.0 | 12285 | 0.1362 | 0.8018 | 0.6686 | 0.8652 | 0.2827 | 0.0001 |
|
| 102 |
+
| 0.1481 | 46.0 | 12558 | 0.1338 | 0.8022 | 0.6640 | 0.8656 | 0.2852 | 0.0001 |
|
| 103 |
+
| 0.1481 | 47.0 | 12831 | 0.1410 | 0.7999 | 0.6573 | 0.8621 | 0.2786 | 0.0001 |
|
| 104 |
+
| 0.1472 | 48.0 | 13104 | 0.1338 | 0.8044 | 0.6728 | 0.8675 | 0.2848 | 0.0001 |
|
| 105 |
+
| 0.1472 | 49.0 | 13377 | 0.1322 | 0.8058 | 0.6742 | 0.8724 | 0.2855 | 0.0001 |
|
| 106 |
+
| 0.1448 | 50.0 | 13650 | 0.1332 | 0.8063 | 0.6739 | 0.8703 | 0.2897 | 0.0001 |
|
| 107 |
+
| 0.1448 | 51.0 | 13923 | 0.1306 | 0.8063 | 0.6771 | 0.8702 | 0.2897 | 0.0001 |
|
| 108 |
+
| 0.1432 | 52.0 | 14196 | 0.1311 | 0.8044 | 0.6727 | 0.8654 | 0.2872 | 0.0001 |
|
| 109 |
+
| 0.1432 | 53.0 | 14469 | 0.1316 | 0.8071 | 0.6703 | 0.8713 | 0.2872 | 0.0001 |
|
| 110 |
+
| 0.1438 | 54.0 | 14742 | 0.1316 | 0.8064 | 0.6788 | 0.8688 | 0.2883 | 0.0001 |
|
| 111 |
+
| 0.1417 | 55.0 | 15015 | 0.1308 | 0.8061 | 0.6699 | 0.8686 | 0.2876 | 0.0001 |
|
| 112 |
+
| 0.1417 | 56.0 | 15288 | 0.1297 | 0.8094 | 0.6800 | 0.8744 | 0.2942 | 0.0001 |
|
| 113 |
+
| 0.1415 | 57.0 | 15561 | 0.1296 | 0.8087 | 0.6717 | 0.8711 | 0.2935 | 0.0001 |
|
| 114 |
+
| 0.1415 | 58.0 | 15834 | 0.1297 | 0.8069 | 0.6785 | 0.8708 | 0.2924 | 0.0001 |
|
| 115 |
+
| 0.1413 | 59.0 | 16107 | 0.1300 | 0.8087 | 0.6811 | 0.8707 | 0.2911 | 0.0001 |
|
| 116 |
+
| 0.1413 | 60.0 | 16380 | 0.1302 | 0.8056 | 0.6726 | 0.8658 | 0.2879 | 0.0001 |
|
| 117 |
+
| 0.1404 | 61.0 | 16653 | 0.1287 | 0.8096 | 0.6843 | 0.8721 | 0.2949 | 0.0001 |
|
| 118 |
+
| 0.1404 | 62.0 | 16926 | 0.1291 | 0.8080 | 0.6822 | 0.8690 | 0.2900 | 0.0001 |
|
| 119 |
+
| 0.1393 | 63.0 | 17199 | 0.1287 | 0.8076 | 0.6813 | 0.8685 | 0.2980 | 0.0001 |
|
| 120 |
+
| 0.1393 | 64.0 | 17472 | 0.1286 | 0.8091 | 0.6806 | 0.8722 | 0.2959 | 0.0001 |
|
| 121 |
+
| 0.1395 | 65.0 | 17745 | 0.1280 | 0.8093 | 0.6838 | 0.8704 | 0.2931 | 0.0001 |
|
| 122 |
+
| 0.1389 | 66.0 | 18018 | 0.1278 | 0.8108 | 0.6855 | 0.8744 | 0.2959 | 0.0001 |
|
| 123 |
+
| 0.1389 | 67.0 | 18291 | 0.1282 | 0.8098 | 0.6849 | 0.8746 | 0.2949 | 0.0001 |
|
| 124 |
+
| 0.1376 | 68.0 | 18564 | 0.1280 | 0.8123 | 0.6903 | 0.8771 | 0.2980 | 0.0001 |
|
| 125 |
+
| 0.1376 | 69.0 | 18837 | 0.1280 | 0.8105 | 0.6800 | 0.8711 | 0.2952 | 0.0001 |
|
| 126 |
+
| 0.1375 | 70.0 | 19110 | 0.1276 | 0.8096 | 0.6848 | 0.8709 | 0.2931 | 0.0001 |
|
| 127 |
+
| 0.1375 | 71.0 | 19383 | 0.1279 | 0.8073 | 0.6797 | 0.8675 | 0.2904 | 0.0001 |
|
| 128 |
+
| 0.1368 | 72.0 | 19656 | 0.1278 | 0.8103 | 0.6802 | 0.8719 | 0.2938 | 0.0001 |
|
| 129 |
+
| 0.1368 | 73.0 | 19929 | 0.1272 | 0.8091 | 0.6806 | 0.8683 | 0.2976 | 0.0001 |
|
| 130 |
+
| 0.137 | 74.0 | 20202 | 0.1280 | 0.8064 | 0.6777 | 0.8648 | 0.2935 | 0.0001 |
|
| 131 |
+
| 0.137 | 75.0 | 20475 | 0.1273 | 0.8110 | 0.6885 | 0.8731 | 0.2924 | 0.0001 |
|
| 132 |
+
| 0.1367 | 76.0 | 20748 | 0.1273 | 0.8089 | 0.6811 | 0.8696 | 0.2973 | 0.0001 |
|
| 133 |
+
| 0.1358 | 77.0 | 21021 | 0.1275 | 0.8102 | 0.6863 | 0.8739 | 0.2924 | 0.0001 |
|
| 134 |
+
| 0.1358 | 78.0 | 21294 | 0.1271 | 0.8122 | 0.6897 | 0.8765 | 0.2945 | 0.0001 |
|
| 135 |
+
| 0.1352 | 79.0 | 21567 | 0.1271 | 0.8098 | 0.6882 | 0.8697 | 0.2935 | 0.0001 |
|
| 136 |
+
| 0.1352 | 80.0 | 21840 | 0.1272 | 0.8124 | 0.6914 | 0.8773 | 0.2983 | 0.0001 |
|
| 137 |
+
| 0.1353 | 81.0 | 22113 | 0.1265 | 0.8104 | 0.6899 | 0.8716 | 0.2966 | 0.0001 |
|
| 138 |
+
| 0.1353 | 82.0 | 22386 | 0.1264 | 0.8105 | 0.6845 | 0.8694 | 0.2914 | 0.0001 |
|
| 139 |
+
| 0.1337 | 83.0 | 22659 | 0.1273 | 0.8100 | 0.6832 | 0.8701 | 0.2935 | 0.0001 |
|
| 140 |
+
| 0.1337 | 84.0 | 22932 | 0.1264 | 0.8124 | 0.6944 | 0.8756 | 0.2959 | 0.0001 |
|
| 141 |
+
| 0.1354 | 85.0 | 23205 | 0.1265 | 0.8127 | 0.6880 | 0.8750 | 0.2973 | 0.0001 |
|
| 142 |
+
| 0.1354 | 86.0 | 23478 | 0.1259 | 0.8136 | 0.6933 | 0.8746 | 0.2952 | 0.0001 |
|
| 143 |
+
| 0.1334 | 87.0 | 23751 | 0.1264 | 0.8111 | 0.6882 | 0.8738 | 0.2966 | 0.0001 |
|
| 144 |
+
| 0.1335 | 88.0 | 24024 | 0.1264 | 0.8127 | 0.6860 | 0.8754 | 0.2990 | 0.0001 |
|
| 145 |
+
| 0.1335 | 89.0 | 24297 | 0.1269 | 0.8140 | 0.6990 | 0.8792 | 0.2983 | 0.0001 |
|
| 146 |
+
| 0.1332 | 90.0 | 24570 | 0.1261 | 0.8155 | 0.6994 | 0.8798 | 0.2980 | 0.0001 |
|
| 147 |
+
| 0.1332 | 91.0 | 24843 | 0.1268 | 0.8109 | 0.6828 | 0.8728 | 0.2893 | 0.0001 |
|
| 148 |
+
| 0.1326 | 92.0 | 25116 | 0.1261 | 0.8124 | 0.6858 | 0.8724 | 0.2952 | 0.0001 |
|
| 149 |
+
| 0.1326 | 93.0 | 25389 | 0.1258 | 0.8138 | 0.6897 | 0.8759 | 0.2966 | 1e-05 |
|
| 150 |
+
| 0.132 | 94.0 | 25662 | 0.1268 | 0.8138 | 0.6941 | 0.8755 | 0.2976 | 1e-05 |
|
| 151 |
+
| 0.132 | 95.0 | 25935 | 0.1257 | 0.8134 | 0.6913 | 0.8750 | 0.2949 | 1e-05 |
|
| 152 |
+
| 0.1294 | 96.0 | 26208 | 0.1259 | 0.8147 | 0.6957 | 0.8763 | 0.2976 | 1e-05 |
|
| 153 |
+
| 0.1294 | 97.0 | 26481 | 0.1256 | 0.8126 | 0.6941 | 0.8720 | 0.2945 | 1e-05 |
|
| 154 |
+
| 0.1302 | 98.0 | 26754 | 0.1253 | 0.8159 | 0.6951 | 0.8785 | 0.2994 | 1e-05 |
|
| 155 |
+
| 0.1298 | 99.0 | 27027 | 0.1249 | 0.8142 | 0.6968 | 0.8752 | 0.2994 | 1e-05 |
|
| 156 |
+
| 0.1298 | 100.0 | 27300 | 0.1252 | 0.8135 | 0.6936 | 0.8732 | 0.2973 | 1e-05 |
|
| 157 |
+
| 0.1304 | 101.0 | 27573 | 0.1248 | 0.8149 | 0.6961 | 0.8765 | 0.2990 | 1e-05 |
|
| 158 |
+
| 0.1304 | 102.0 | 27846 | 0.1266 | 0.8137 | 0.6927 | 0.8738 | 0.2963 | 1e-05 |
|
| 159 |
+
| 0.1287 | 103.0 | 28119 | 0.1249 | 0.8146 | 0.6954 | 0.8754 | 0.2990 | 1e-05 |
|
| 160 |
+
| 0.1287 | 104.0 | 28392 | 0.1252 | 0.8149 | 0.6927 | 0.8770 | 0.2976 | 1e-05 |
|
| 161 |
+
| 0.1282 | 105.0 | 28665 | 0.1251 | 0.8152 | 0.6962 | 0.8773 | 0.2990 | 1e-05 |
|
| 162 |
+
| 0.1282 | 106.0 | 28938 | 0.1251 | 0.8147 | 0.6964 | 0.8770 | 0.2997 | 1e-05 |
|
| 163 |
+
| 0.1293 | 107.0 | 29211 | 0.1250 | 0.8145 | 0.6946 | 0.8759 | 0.2980 | 1e-05 |
|
| 164 |
+
| 0.1293 | 108.0 | 29484 | 0.1249 | 0.8145 | 0.6935 | 0.8751 | 0.2997 | 0.0000 |
|
| 165 |
+
| 0.129 | 109.0 | 29757 | 0.1253 | 0.8116 | 0.6901 | 0.8713 | 0.2952 | 0.0000 |
|
| 166 |
+
| 0.1293 | 110.0 | 30030 | 0.1252 | 0.8144 | 0.6949 | 0.8768 | 0.2980 | 0.0000 |
|
| 167 |
+
| 0.1293 | 111.0 | 30303 | 0.1250 | 0.8137 | 0.6932 | 0.8755 | 0.2983 | 0.0000 |
|
| 168 |
+
|
| 169 |
+
|
| 170 |
+
### Framework versions
|
| 171 |
+
|
| 172 |
+
- Transformers 4.41.1
|
| 173 |
+
- Pytorch 2.3.0+cu121
|
| 174 |
+
- Datasets 2.19.1
|
| 175 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 111.0,
|
| 3 |
+
"eval_accuracy": 0.3013840830449827,
|
| 4 |
+
"eval_f1_macro": 0.6976400304065874,
|
| 5 |
+
"eval_f1_micro": 0.8130930981146274,
|
| 6 |
+
"eval_loss": 0.12597818672657013,
|
| 7 |
+
"eval_roc_auc": 0.8760340882370488,
|
| 8 |
+
"eval_runtime": 432.9745,
|
| 9 |
+
"eval_samples_per_second": 6.675,
|
| 10 |
+
"eval_steps_per_second": 0.21,
|
| 11 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 12 |
+
"total_flos": 4.1153080208666034e+20,
|
| 13 |
+
"train_loss": 0.14764341744551096,
|
| 14 |
+
"train_runtime": 198162.6547,
|
| 15 |
+
"train_samples_per_second": 6.598,
|
| 16 |
+
"train_steps_per_second": 0.207
|
| 17 |
+
}
|
logs/events.out.tfevents.1725353105.datavisu2
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b04fe6c51823156c262bde75364193f69381f715afc6ba33da8d6adaa146c241
|
| 3 |
+
size 80246
|
logs/events.out.tfevents.1725551731.datavisu2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c3fbd0fc43d75ecb221909ebcffdcf42e316dd03de1d63225b0c893961e4272f
|
| 3 |
+
size 40
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 352317916
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e360ebf9714bbbfe17e9afecac7c35a6ea74a89952fbd9b63779a00e57c7a674
|
| 3 |
size 352317916
|
test_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 111.0,
|
| 3 |
+
"eval_accuracy": 0.3013840830449827,
|
| 4 |
+
"eval_f1_macro": 0.6976400304065874,
|
| 5 |
+
"eval_f1_micro": 0.8130930981146274,
|
| 6 |
+
"eval_loss": 0.12597818672657013,
|
| 7 |
+
"eval_roc_auc": 0.8760340882370488,
|
| 8 |
+
"eval_runtime": 432.9745,
|
| 9 |
+
"eval_samples_per_second": 6.675,
|
| 10 |
+
"eval_steps_per_second": 0.21,
|
| 11 |
+
"learning_rate": 1.0000000000000002e-06
|
| 12 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 111.0,
|
| 3 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 4 |
+
"total_flos": 4.1153080208666034e+20,
|
| 5 |
+
"train_loss": 0.14764341744551096,
|
| 6 |
+
"train_runtime": 198162.6547,
|
| 7 |
+
"train_samples_per_second": 6.598,
|
| 8 |
+
"train_steps_per_second": 0.207
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1915 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.12475299090147018,
|
| 3 |
+
"best_model_checkpoint": "/home/datawork-iot-nos/Seatizen/models/multilabel/fine_scale/DinoVdeau-base-2024_09_03-batch-size32_epochs150_freeze/checkpoint-27573",
|
| 4 |
+
"epoch": 111.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 30303,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"eval_accuracy": 0.2079002079002079,
|
| 14 |
+
"eval_f1_macro": 0.5105390450682302,
|
| 15 |
+
"eval_f1_micro": 0.73108765167112,
|
| 16 |
+
"eval_loss": 0.17516958713531494,
|
| 17 |
+
"eval_roc_auc": 0.8186965528786462,
|
| 18 |
+
"eval_runtime": 453.901,
|
| 19 |
+
"eval_samples_per_second": 6.358,
|
| 20 |
+
"eval_steps_per_second": 0.2,
|
| 21 |
+
"learning_rate": 0.001,
|
| 22 |
+
"step": 273
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 1.8315018315018317,
|
| 26 |
+
"grad_norm": 0.2602289021015167,
|
| 27 |
+
"learning_rate": 0.001,
|
| 28 |
+
"loss": 0.2857,
|
| 29 |
+
"step": 500
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 2.0,
|
| 33 |
+
"eval_accuracy": 0.23492723492723494,
|
| 34 |
+
"eval_f1_macro": 0.5498069096094584,
|
| 35 |
+
"eval_f1_micro": 0.7582569600553347,
|
| 36 |
+
"eval_loss": 0.1577771008014679,
|
| 37 |
+
"eval_roc_auc": 0.8363419499741919,
|
| 38 |
+
"eval_runtime": 442.4314,
|
| 39 |
+
"eval_samples_per_second": 6.523,
|
| 40 |
+
"eval_steps_per_second": 0.206,
|
| 41 |
+
"learning_rate": 0.001,
|
| 42 |
+
"step": 546
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 3.0,
|
| 46 |
+
"eval_accuracy": 0.23146223146223147,
|
| 47 |
+
"eval_f1_macro": 0.6037272443934714,
|
| 48 |
+
"eval_f1_micro": 0.7721545657578696,
|
| 49 |
+
"eval_loss": 0.15162432193756104,
|
| 50 |
+
"eval_roc_auc": 0.8505384953411333,
|
| 51 |
+
"eval_runtime": 429.5087,
|
| 52 |
+
"eval_samples_per_second": 6.719,
|
| 53 |
+
"eval_steps_per_second": 0.212,
|
| 54 |
+
"learning_rate": 0.001,
|
| 55 |
+
"step": 819
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 3.663003663003663,
|
| 59 |
+
"grad_norm": 0.24485518038272858,
|
| 60 |
+
"learning_rate": 0.001,
|
| 61 |
+
"loss": 0.1764,
|
| 62 |
+
"step": 1000
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 4.0,
|
| 66 |
+
"eval_accuracy": 0.24220374220374222,
|
| 67 |
+
"eval_f1_macro": 0.613953187695023,
|
| 68 |
+
"eval_f1_micro": 0.7649537378914902,
|
| 69 |
+
"eval_loss": 0.15218119323253632,
|
| 70 |
+
"eval_roc_auc": 0.8386795656946878,
|
| 71 |
+
"eval_runtime": 440.157,
|
| 72 |
+
"eval_samples_per_second": 6.557,
|
| 73 |
+
"eval_steps_per_second": 0.207,
|
| 74 |
+
"learning_rate": 0.001,
|
| 75 |
+
"step": 1092
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 5.0,
|
| 79 |
+
"eval_accuracy": 0.24220374220374222,
|
| 80 |
+
"eval_f1_macro": 0.6161642626912543,
|
| 81 |
+
"eval_f1_micro": 0.7719928186714542,
|
| 82 |
+
"eval_loss": 0.14836864173412323,
|
| 83 |
+
"eval_roc_auc": 0.840338176952158,
|
| 84 |
+
"eval_runtime": 432.0583,
|
| 85 |
+
"eval_samples_per_second": 6.68,
|
| 86 |
+
"eval_steps_per_second": 0.211,
|
| 87 |
+
"learning_rate": 0.001,
|
| 88 |
+
"step": 1365
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 5.4945054945054945,
|
| 92 |
+
"grad_norm": 0.17316196858882904,
|
| 93 |
+
"learning_rate": 0.001,
|
| 94 |
+
"loss": 0.1677,
|
| 95 |
+
"step": 1500
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 6.0,
|
| 99 |
+
"eval_accuracy": 0.2560637560637561,
|
| 100 |
+
"eval_f1_macro": 0.6051867487843677,
|
| 101 |
+
"eval_f1_micro": 0.775030471878809,
|
| 102 |
+
"eval_loss": 0.14818257093429565,
|
| 103 |
+
"eval_roc_auc": 0.8434755477910759,
|
| 104 |
+
"eval_runtime": 432.9746,
|
| 105 |
+
"eval_samples_per_second": 6.666,
|
| 106 |
+
"eval_steps_per_second": 0.21,
|
| 107 |
+
"learning_rate": 0.001,
|
| 108 |
+
"step": 1638
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 7.0,
|
| 112 |
+
"eval_accuracy": 0.24185724185724186,
|
| 113 |
+
"eval_f1_macro": 0.617739220969942,
|
| 114 |
+
"eval_f1_micro": 0.7729166666666668,
|
| 115 |
+
"eval_loss": 0.1486394852399826,
|
| 116 |
+
"eval_roc_auc": 0.8431254755177443,
|
| 117 |
+
"eval_runtime": 432.8426,
|
| 118 |
+
"eval_samples_per_second": 6.668,
|
| 119 |
+
"eval_steps_per_second": 0.21,
|
| 120 |
+
"learning_rate": 0.001,
|
| 121 |
+
"step": 1911
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 7.326007326007326,
|
| 125 |
+
"grad_norm": 0.31019529700279236,
|
| 126 |
+
"learning_rate": 0.001,
|
| 127 |
+
"loss": 0.1652,
|
| 128 |
+
"step": 2000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 8.0,
|
| 132 |
+
"eval_accuracy": 0.2512127512127512,
|
| 133 |
+
"eval_f1_macro": 0.6171646674895677,
|
| 134 |
+
"eval_f1_micro": 0.7767065175472426,
|
| 135 |
+
"eval_loss": 0.14861202239990234,
|
| 136 |
+
"eval_roc_auc": 0.8485322128731306,
|
| 137 |
+
"eval_runtime": 436.0215,
|
| 138 |
+
"eval_samples_per_second": 6.619,
|
| 139 |
+
"eval_steps_per_second": 0.209,
|
| 140 |
+
"learning_rate": 0.001,
|
| 141 |
+
"step": 2184
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 9.0,
|
| 145 |
+
"eval_accuracy": 0.2512127512127512,
|
| 146 |
+
"eval_f1_macro": 0.6366264906922544,
|
| 147 |
+
"eval_f1_micro": 0.7805490458654168,
|
| 148 |
+
"eval_loss": 0.14834754168987274,
|
| 149 |
+
"eval_roc_auc": 0.857034765243127,
|
| 150 |
+
"eval_runtime": 443.0125,
|
| 151 |
+
"eval_samples_per_second": 6.514,
|
| 152 |
+
"eval_steps_per_second": 0.205,
|
| 153 |
+
"learning_rate": 0.001,
|
| 154 |
+
"step": 2457
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 9.157509157509157,
|
| 158 |
+
"grad_norm": 0.1974957138299942,
|
| 159 |
+
"learning_rate": 0.001,
|
| 160 |
+
"loss": 0.1617,
|
| 161 |
+
"step": 2500
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 10.0,
|
| 165 |
+
"eval_accuracy": 0.24532224532224534,
|
| 166 |
+
"eval_f1_macro": 0.6081428044829309,
|
| 167 |
+
"eval_f1_micro": 0.7682759232167399,
|
| 168 |
+
"eval_loss": 0.15029709041118622,
|
| 169 |
+
"eval_roc_auc": 0.8352362538484075,
|
| 170 |
+
"eval_runtime": 434.6587,
|
| 171 |
+
"eval_samples_per_second": 6.64,
|
| 172 |
+
"eval_steps_per_second": 0.209,
|
| 173 |
+
"learning_rate": 0.001,
|
| 174 |
+
"step": 2730
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 10.989010989010989,
|
| 178 |
+
"grad_norm": 0.16183075308799744,
|
| 179 |
+
"learning_rate": 0.001,
|
| 180 |
+
"loss": 0.1615,
|
| 181 |
+
"step": 3000
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 11.0,
|
| 185 |
+
"eval_accuracy": 0.2609147609147609,
|
| 186 |
+
"eval_f1_macro": 0.6199915554248129,
|
| 187 |
+
"eval_f1_micro": 0.7756647297059341,
|
| 188 |
+
"eval_loss": 0.14407172799110413,
|
| 189 |
+
"eval_roc_auc": 0.8408945796610934,
|
| 190 |
+
"eval_runtime": 431.8807,
|
| 191 |
+
"eval_samples_per_second": 6.682,
|
| 192 |
+
"eval_steps_per_second": 0.211,
|
| 193 |
+
"learning_rate": 0.001,
|
| 194 |
+
"step": 3003
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 12.0,
|
| 198 |
+
"eval_accuracy": 0.2494802494802495,
|
| 199 |
+
"eval_f1_macro": 0.6299207659511814,
|
| 200 |
+
"eval_f1_micro": 0.781485559413907,
|
| 201 |
+
"eval_loss": 0.14866559207439423,
|
| 202 |
+
"eval_roc_auc": 0.8542998474050816,
|
| 203 |
+
"eval_runtime": 435.7397,
|
| 204 |
+
"eval_samples_per_second": 6.623,
|
| 205 |
+
"eval_steps_per_second": 0.209,
|
| 206 |
+
"learning_rate": 0.001,
|
| 207 |
+
"step": 3276
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 12.820512820512821,
|
| 211 |
+
"grad_norm": 0.17374463379383087,
|
| 212 |
+
"learning_rate": 0.001,
|
| 213 |
+
"loss": 0.1614,
|
| 214 |
+
"step": 3500
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 13.0,
|
| 218 |
+
"eval_accuracy": 0.25190575190575193,
|
| 219 |
+
"eval_f1_macro": 0.6241659824597257,
|
| 220 |
+
"eval_f1_micro": 0.7779037321241716,
|
| 221 |
+
"eval_loss": 0.14902691543102264,
|
| 222 |
+
"eval_roc_auc": 0.8445867301441496,
|
| 223 |
+
"eval_runtime": 444.1918,
|
| 224 |
+
"eval_samples_per_second": 6.497,
|
| 225 |
+
"eval_steps_per_second": 0.205,
|
| 226 |
+
"learning_rate": 0.001,
|
| 227 |
+
"step": 3549
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 14.0,
|
| 231 |
+
"eval_accuracy": 0.26056826056826055,
|
| 232 |
+
"eval_f1_macro": 0.6378982802249643,
|
| 233 |
+
"eval_f1_micro": 0.7826389795829524,
|
| 234 |
+
"eval_loss": 0.14337006211280823,
|
| 235 |
+
"eval_roc_auc": 0.8474976901507599,
|
| 236 |
+
"eval_runtime": 437.9843,
|
| 237 |
+
"eval_samples_per_second": 6.589,
|
| 238 |
+
"eval_steps_per_second": 0.208,
|
| 239 |
+
"learning_rate": 0.001,
|
| 240 |
+
"step": 3822
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 14.652014652014651,
|
| 244 |
+
"grad_norm": 0.18867848813533783,
|
| 245 |
+
"learning_rate": 0.001,
|
| 246 |
+
"loss": 0.1599,
|
| 247 |
+
"step": 4000
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 15.0,
|
| 251 |
+
"eval_accuracy": 0.2553707553707554,
|
| 252 |
+
"eval_f1_macro": 0.639716503598517,
|
| 253 |
+
"eval_f1_micro": 0.7873585308562887,
|
| 254 |
+
"eval_loss": 0.14354591071605682,
|
| 255 |
+
"eval_roc_auc": 0.8551790656297652,
|
| 256 |
+
"eval_runtime": 440.9279,
|
| 257 |
+
"eval_samples_per_second": 6.545,
|
| 258 |
+
"eval_steps_per_second": 0.206,
|
| 259 |
+
"learning_rate": 0.001,
|
| 260 |
+
"step": 4095
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 16.0,
|
| 264 |
+
"eval_accuracy": 0.25675675675675674,
|
| 265 |
+
"eval_f1_macro": 0.6343613127126344,
|
| 266 |
+
"eval_f1_micro": 0.7792974686292388,
|
| 267 |
+
"eval_loss": 0.1439499706029892,
|
| 268 |
+
"eval_roc_auc": 0.8464149986210657,
|
| 269 |
+
"eval_runtime": 436.9638,
|
| 270 |
+
"eval_samples_per_second": 6.605,
|
| 271 |
+
"eval_steps_per_second": 0.208,
|
| 272 |
+
"learning_rate": 0.001,
|
| 273 |
+
"step": 4368
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 16.483516483516482,
|
| 277 |
+
"grad_norm": 0.16403253376483917,
|
| 278 |
+
"learning_rate": 0.001,
|
| 279 |
+
"loss": 0.1589,
|
| 280 |
+
"step": 4500
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 17.0,
|
| 284 |
+
"eval_accuracy": 0.2543312543312543,
|
| 285 |
+
"eval_f1_macro": 0.6422270697798029,
|
| 286 |
+
"eval_f1_micro": 0.787784461363732,
|
| 287 |
+
"eval_loss": 0.14478015899658203,
|
| 288 |
+
"eval_roc_auc": 0.8595889192695618,
|
| 289 |
+
"eval_runtime": 441.556,
|
| 290 |
+
"eval_samples_per_second": 6.536,
|
| 291 |
+
"eval_steps_per_second": 0.206,
|
| 292 |
+
"learning_rate": 0.001,
|
| 293 |
+
"step": 4641
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 18.0,
|
| 297 |
+
"eval_accuracy": 0.25675675675675674,
|
| 298 |
+
"eval_f1_macro": 0.6417123667888478,
|
| 299 |
+
"eval_f1_micro": 0.786493860845839,
|
| 300 |
+
"eval_loss": 0.14397625625133514,
|
| 301 |
+
"eval_roc_auc": 0.8551892735001003,
|
| 302 |
+
"eval_runtime": 445.1896,
|
| 303 |
+
"eval_samples_per_second": 6.483,
|
| 304 |
+
"eval_steps_per_second": 0.204,
|
| 305 |
+
"learning_rate": 0.001,
|
| 306 |
+
"step": 4914
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 18.315018315018314,
|
| 310 |
+
"grad_norm": 1.3815889358520508,
|
| 311 |
+
"learning_rate": 0.001,
|
| 312 |
+
"loss": 0.1604,
|
| 313 |
+
"step": 5000
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 19.0,
|
| 317 |
+
"eval_accuracy": 0.253984753984754,
|
| 318 |
+
"eval_f1_macro": 0.6317583185615991,
|
| 319 |
+
"eval_f1_micro": 0.7863510343356792,
|
| 320 |
+
"eval_loss": 0.14199253916740417,
|
| 321 |
+
"eval_roc_auc": 0.854983895441361,
|
| 322 |
+
"eval_runtime": 435.0664,
|
| 323 |
+
"eval_samples_per_second": 6.633,
|
| 324 |
+
"eval_steps_per_second": 0.209,
|
| 325 |
+
"learning_rate": 0.001,
|
| 326 |
+
"step": 5187
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 20.0,
|
| 330 |
+
"eval_accuracy": 0.2588357588357588,
|
| 331 |
+
"eval_f1_macro": 0.6408966299078661,
|
| 332 |
+
"eval_f1_micro": 0.7868513006341401,
|
| 333 |
+
"eval_loss": 0.14092272520065308,
|
| 334 |
+
"eval_roc_auc": 0.8521780322337986,
|
| 335 |
+
"eval_runtime": 434.5134,
|
| 336 |
+
"eval_samples_per_second": 6.642,
|
| 337 |
+
"eval_steps_per_second": 0.209,
|
| 338 |
+
"learning_rate": 0.001,
|
| 339 |
+
"step": 5460
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 20.146520146520146,
|
| 343 |
+
"grad_norm": 0.21049675345420837,
|
| 344 |
+
"learning_rate": 0.001,
|
| 345 |
+
"loss": 0.1586,
|
| 346 |
+
"step": 5500
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 21.0,
|
| 350 |
+
"eval_accuracy": 0.26195426195426197,
|
| 351 |
+
"eval_f1_macro": 0.6412583916380257,
|
| 352 |
+
"eval_f1_micro": 0.7864882090503504,
|
| 353 |
+
"eval_loss": 0.1425119787454605,
|
| 354 |
+
"eval_roc_auc": 0.8561061843865996,
|
| 355 |
+
"eval_runtime": 433.1377,
|
| 356 |
+
"eval_samples_per_second": 6.663,
|
| 357 |
+
"eval_steps_per_second": 0.21,
|
| 358 |
+
"learning_rate": 0.001,
|
| 359 |
+
"step": 5733
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 21.978021978021978,
|
| 363 |
+
"grad_norm": 0.159688800573349,
|
| 364 |
+
"learning_rate": 0.001,
|
| 365 |
+
"loss": 0.1587,
|
| 366 |
+
"step": 6000
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 22.0,
|
| 370 |
+
"eval_accuracy": 0.23700623700623702,
|
| 371 |
+
"eval_f1_macro": 0.6371452798177432,
|
| 372 |
+
"eval_f1_micro": 0.7854284761587195,
|
| 373 |
+
"eval_loss": 0.15379400551319122,
|
| 374 |
+
"eval_roc_auc": 0.860841268018702,
|
| 375 |
+
"eval_runtime": 439.1581,
|
| 376 |
+
"eval_samples_per_second": 6.572,
|
| 377 |
+
"eval_steps_per_second": 0.207,
|
| 378 |
+
"learning_rate": 0.001,
|
| 379 |
+
"step": 6006
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 23.0,
|
| 383 |
+
"eval_accuracy": 0.25571725571725573,
|
| 384 |
+
"eval_f1_macro": 0.6390434486158698,
|
| 385 |
+
"eval_f1_micro": 0.7841676771176165,
|
| 386 |
+
"eval_loss": 0.1418805718421936,
|
| 387 |
+
"eval_roc_auc": 0.8497106920533675,
|
| 388 |
+
"eval_runtime": 434.4927,
|
| 389 |
+
"eval_samples_per_second": 6.642,
|
| 390 |
+
"eval_steps_per_second": 0.209,
|
| 391 |
+
"learning_rate": 0.001,
|
| 392 |
+
"step": 6279
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 23.80952380952381,
|
| 396 |
+
"grad_norm": 0.20623169839382172,
|
| 397 |
+
"learning_rate": 0.001,
|
| 398 |
+
"loss": 0.1592,
|
| 399 |
+
"step": 6500
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 24.0,
|
| 403 |
+
"eval_accuracy": 0.2598752598752599,
|
| 404 |
+
"eval_f1_macro": 0.6458978920546691,
|
| 405 |
+
"eval_f1_micro": 0.7869535635312129,
|
| 406 |
+
"eval_loss": 0.14135514199733734,
|
| 407 |
+
"eval_roc_auc": 0.8561374786855376,
|
| 408 |
+
"eval_runtime": 437.945,
|
| 409 |
+
"eval_samples_per_second": 6.59,
|
| 410 |
+
"eval_steps_per_second": 0.208,
|
| 411 |
+
"learning_rate": 0.001,
|
| 412 |
+
"step": 6552
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 25.0,
|
| 416 |
+
"eval_accuracy": 0.26853776853776856,
|
| 417 |
+
"eval_f1_macro": 0.6262981090846956,
|
| 418 |
+
"eval_f1_micro": 0.786773581652009,
|
| 419 |
+
"eval_loss": 0.13985148072242737,
|
| 420 |
+
"eval_roc_auc": 0.8523112308572252,
|
| 421 |
+
"eval_runtime": 433.5621,
|
| 422 |
+
"eval_samples_per_second": 6.656,
|
| 423 |
+
"eval_steps_per_second": 0.21,
|
| 424 |
+
"learning_rate": 0.001,
|
| 425 |
+
"step": 6825
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 25.641025641025642,
|
| 429 |
+
"grad_norm": 0.167380690574646,
|
| 430 |
+
"learning_rate": 0.001,
|
| 431 |
+
"loss": 0.1586,
|
| 432 |
+
"step": 7000
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 26.0,
|
| 436 |
+
"eval_accuracy": 0.2591822591822592,
|
| 437 |
+
"eval_f1_macro": 0.6237830069375186,
|
| 438 |
+
"eval_f1_micro": 0.7846557710221018,
|
| 439 |
+
"eval_loss": 0.14649754762649536,
|
| 440 |
+
"eval_roc_auc": 0.8560739377107973,
|
| 441 |
+
"eval_runtime": 436.7443,
|
| 442 |
+
"eval_samples_per_second": 6.608,
|
| 443 |
+
"eval_steps_per_second": 0.208,
|
| 444 |
+
"learning_rate": 0.001,
|
| 445 |
+
"step": 7098
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 27.0,
|
| 449 |
+
"eval_accuracy": 0.23804573804573806,
|
| 450 |
+
"eval_f1_macro": 0.6344307952131357,
|
| 451 |
+
"eval_f1_micro": 0.7719951506754418,
|
| 452 |
+
"eval_loss": 0.15506784617900848,
|
| 453 |
+
"eval_roc_auc": 0.8432688820115058,
|
| 454 |
+
"eval_runtime": 431.1317,
|
| 455 |
+
"eval_samples_per_second": 6.694,
|
| 456 |
+
"eval_steps_per_second": 0.211,
|
| 457 |
+
"learning_rate": 0.001,
|
| 458 |
+
"step": 7371
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 27.47252747252747,
|
| 462 |
+
"grad_norm": 0.17562341690063477,
|
| 463 |
+
"learning_rate": 0.001,
|
| 464 |
+
"loss": 0.16,
|
| 465 |
+
"step": 7500
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 28.0,
|
| 469 |
+
"eval_accuracy": 0.2616077616077616,
|
| 470 |
+
"eval_f1_macro": 0.6429949936408241,
|
| 471 |
+
"eval_f1_micro": 0.7891238152420981,
|
| 472 |
+
"eval_loss": 0.14431345462799072,
|
| 473 |
+
"eval_roc_auc": 0.8549858001950897,
|
| 474 |
+
"eval_runtime": 430.551,
|
| 475 |
+
"eval_samples_per_second": 6.703,
|
| 476 |
+
"eval_steps_per_second": 0.211,
|
| 477 |
+
"learning_rate": 0.001,
|
| 478 |
+
"step": 7644
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 29.0,
|
| 482 |
+
"eval_accuracy": 0.25675675675675674,
|
| 483 |
+
"eval_f1_macro": 0.6415824285032449,
|
| 484 |
+
"eval_f1_micro": 0.7873995663818392,
|
| 485 |
+
"eval_loss": 0.14275498688220978,
|
| 486 |
+
"eval_roc_auc": 0.8564611929231155,
|
| 487 |
+
"eval_runtime": 443.3199,
|
| 488 |
+
"eval_samples_per_second": 6.51,
|
| 489 |
+
"eval_steps_per_second": 0.205,
|
| 490 |
+
"learning_rate": 0.001,
|
| 491 |
+
"step": 7917
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 29.304029304029303,
|
| 495 |
+
"grad_norm": 0.16407011449337006,
|
| 496 |
+
"learning_rate": 0.001,
|
| 497 |
+
"loss": 0.1589,
|
| 498 |
+
"step": 8000
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 30.0,
|
| 502 |
+
"eval_accuracy": 0.2525987525987526,
|
| 503 |
+
"eval_f1_macro": 0.6308133523221491,
|
| 504 |
+
"eval_f1_micro": 0.7798808735936467,
|
| 505 |
+
"eval_loss": 0.14164045453071594,
|
| 506 |
+
"eval_roc_auc": 0.8425187578001007,
|
| 507 |
+
"eval_runtime": 435.3871,
|
| 508 |
+
"eval_samples_per_second": 6.629,
|
| 509 |
+
"eval_steps_per_second": 0.209,
|
| 510 |
+
"learning_rate": 0.001,
|
| 511 |
+
"step": 8190
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 31.0,
|
| 515 |
+
"eval_accuracy": 0.26888426888426886,
|
| 516 |
+
"eval_f1_macro": 0.6431010910213645,
|
| 517 |
+
"eval_f1_micro": 0.7895365707945718,
|
| 518 |
+
"eval_loss": 0.13976627588272095,
|
| 519 |
+
"eval_roc_auc": 0.8565786303801245,
|
| 520 |
+
"eval_runtime": 429.7695,
|
| 521 |
+
"eval_samples_per_second": 6.715,
|
| 522 |
+
"eval_steps_per_second": 0.212,
|
| 523 |
+
"learning_rate": 0.001,
|
| 524 |
+
"step": 8463
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 31.135531135531135,
|
| 528 |
+
"grad_norm": 0.3522001802921295,
|
| 529 |
+
"learning_rate": 0.001,
|
| 530 |
+
"loss": 0.1588,
|
| 531 |
+
"step": 8500
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 32.0,
|
| 535 |
+
"eval_accuracy": 0.25675675675675674,
|
| 536 |
+
"eval_f1_macro": 0.6520927708015384,
|
| 537 |
+
"eval_f1_micro": 0.7891036166898235,
|
| 538 |
+
"eval_loss": 0.1448184847831726,
|
| 539 |
+
"eval_roc_auc": 0.8600551412790717,
|
| 540 |
+
"eval_runtime": 437.4042,
|
| 541 |
+
"eval_samples_per_second": 6.598,
|
| 542 |
+
"eval_steps_per_second": 0.208,
|
| 543 |
+
"learning_rate": 0.001,
|
| 544 |
+
"step": 8736
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 32.967032967032964,
|
| 548 |
+
"grad_norm": 0.16505810618400574,
|
| 549 |
+
"learning_rate": 0.001,
|
| 550 |
+
"loss": 0.1581,
|
| 551 |
+
"step": 9000
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 33.0,
|
| 555 |
+
"eval_accuracy": 0.26403326403326405,
|
| 556 |
+
"eval_f1_macro": 0.6496848321151188,
|
| 557 |
+
"eval_f1_micro": 0.7895652173913044,
|
| 558 |
+
"eval_loss": 0.14042973518371582,
|
| 559 |
+
"eval_roc_auc": 0.8582461081320644,
|
| 560 |
+
"eval_runtime": 438.9972,
|
| 561 |
+
"eval_samples_per_second": 6.574,
|
| 562 |
+
"eval_steps_per_second": 0.207,
|
| 563 |
+
"learning_rate": 0.001,
|
| 564 |
+
"step": 9009
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 34.0,
|
| 568 |
+
"eval_accuracy": 0.25571725571725573,
|
| 569 |
+
"eval_f1_macro": 0.6448790211155284,
|
| 570 |
+
"eval_f1_micro": 0.7870906828033133,
|
| 571 |
+
"eval_loss": 0.1426127403974533,
|
| 572 |
+
"eval_roc_auc": 0.8537051886564672,
|
| 573 |
+
"eval_runtime": 443.0007,
|
| 574 |
+
"eval_samples_per_second": 6.515,
|
| 575 |
+
"eval_steps_per_second": 0.205,
|
| 576 |
+
"learning_rate": 0.001,
|
| 577 |
+
"step": 9282
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 34.798534798534796,
|
| 581 |
+
"grad_norm": 0.17374606430530548,
|
| 582 |
+
"learning_rate": 0.001,
|
| 583 |
+
"loss": 0.1578,
|
| 584 |
+
"step": 9500
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 35.0,
|
| 588 |
+
"eval_accuracy": 0.262993762993763,
|
| 589 |
+
"eval_f1_macro": 0.6428423378015612,
|
| 590 |
+
"eval_f1_micro": 0.7846327880264532,
|
| 591 |
+
"eval_loss": 0.14135821163654327,
|
| 592 |
+
"eval_roc_auc": 0.8487055052211715,
|
| 593 |
+
"eval_runtime": 439.0163,
|
| 594 |
+
"eval_samples_per_second": 6.574,
|
| 595 |
+
"eval_steps_per_second": 0.207,
|
| 596 |
+
"learning_rate": 0.001,
|
| 597 |
+
"step": 9555
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 36.0,
|
| 601 |
+
"eval_accuracy": 0.26784476784476785,
|
| 602 |
+
"eval_f1_macro": 0.6434020884943297,
|
| 603 |
+
"eval_f1_micro": 0.7834209497328063,
|
| 604 |
+
"eval_loss": 0.14652539789676666,
|
| 605 |
+
"eval_roc_auc": 0.848444661270401,
|
| 606 |
+
"eval_runtime": 441.3143,
|
| 607 |
+
"eval_samples_per_second": 6.54,
|
| 608 |
+
"eval_steps_per_second": 0.206,
|
| 609 |
+
"learning_rate": 0.001,
|
| 610 |
+
"step": 9828
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 36.63003663003663,
|
| 614 |
+
"grad_norm": 0.1908567249774933,
|
| 615 |
+
"learning_rate": 0.001,
|
| 616 |
+
"loss": 0.1576,
|
| 617 |
+
"step": 10000
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 37.0,
|
| 621 |
+
"eval_accuracy": 0.2668052668052668,
|
| 622 |
+
"eval_f1_macro": 0.6438477431550106,
|
| 623 |
+
"eval_f1_micro": 0.792425408224331,
|
| 624 |
+
"eval_loss": 0.13795886933803558,
|
| 625 |
+
"eval_roc_auc": 0.8576696786814598,
|
| 626 |
+
"eval_runtime": 438.7851,
|
| 627 |
+
"eval_samples_per_second": 6.577,
|
| 628 |
+
"eval_steps_per_second": 0.207,
|
| 629 |
+
"learning_rate": 0.001,
|
| 630 |
+
"step": 10101
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 38.0,
|
| 634 |
+
"eval_accuracy": 0.2636867636867637,
|
| 635 |
+
"eval_f1_macro": 0.6475331965590188,
|
| 636 |
+
"eval_f1_micro": 0.7892280686732029,
|
| 637 |
+
"eval_loss": 0.13921019434928894,
|
| 638 |
+
"eval_roc_auc": 0.8555102379171546,
|
| 639 |
+
"eval_runtime": 440.2794,
|
| 640 |
+
"eval_samples_per_second": 6.555,
|
| 641 |
+
"eval_steps_per_second": 0.207,
|
| 642 |
+
"learning_rate": 0.001,
|
| 643 |
+
"step": 10374
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 38.46153846153846,
|
| 647 |
+
"grad_norm": 0.17312012612819672,
|
| 648 |
+
"learning_rate": 0.001,
|
| 649 |
+
"loss": 0.1556,
|
| 650 |
+
"step": 10500
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 39.0,
|
| 654 |
+
"eval_accuracy": 0.24601524601524602,
|
| 655 |
+
"eval_f1_macro": 0.659217552215385,
|
| 656 |
+
"eval_f1_micro": 0.7871620243872598,
|
| 657 |
+
"eval_loss": 0.14584119617938995,
|
| 658 |
+
"eval_roc_auc": 0.8679696612972285,
|
| 659 |
+
"eval_runtime": 440.7666,
|
| 660 |
+
"eval_samples_per_second": 6.548,
|
| 661 |
+
"eval_steps_per_second": 0.206,
|
| 662 |
+
"learning_rate": 0.001,
|
| 663 |
+
"step": 10647
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 40.0,
|
| 667 |
+
"eval_accuracy": 0.26992376992376993,
|
| 668 |
+
"eval_f1_macro": 0.6469476365862663,
|
| 669 |
+
"eval_f1_micro": 0.79463243873979,
|
| 670 |
+
"eval_loss": 0.1389026641845703,
|
| 671 |
+
"eval_roc_auc": 0.8659848006017948,
|
| 672 |
+
"eval_runtime": 449.7344,
|
| 673 |
+
"eval_samples_per_second": 6.417,
|
| 674 |
+
"eval_steps_per_second": 0.202,
|
| 675 |
+
"learning_rate": 0.001,
|
| 676 |
+
"step": 10920
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 40.29304029304029,
|
| 680 |
+
"grad_norm": 0.17165251076221466,
|
| 681 |
+
"learning_rate": 0.001,
|
| 682 |
+
"loss": 0.1577,
|
| 683 |
+
"step": 11000
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 41.0,
|
| 687 |
+
"eval_accuracy": 0.2616077616077616,
|
| 688 |
+
"eval_f1_macro": 0.6509894683187031,
|
| 689 |
+
"eval_f1_micro": 0.784842032071618,
|
| 690 |
+
"eval_loss": 0.14020991325378418,
|
| 691 |
+
"eval_roc_auc": 0.8491298897174419,
|
| 692 |
+
"eval_runtime": 442.6364,
|
| 693 |
+
"eval_samples_per_second": 6.52,
|
| 694 |
+
"eval_steps_per_second": 0.206,
|
| 695 |
+
"learning_rate": 0.001,
|
| 696 |
+
"step": 11193
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 42.0,
|
| 700 |
+
"eval_accuracy": 0.27165627165627165,
|
| 701 |
+
"eval_f1_macro": 0.6608924914997423,
|
| 702 |
+
"eval_f1_micro": 0.7927685516081564,
|
| 703 |
+
"eval_loss": 0.14042720198631287,
|
| 704 |
+
"eval_roc_auc": 0.8624648827798459,
|
| 705 |
+
"eval_runtime": 447.1222,
|
| 706 |
+
"eval_samples_per_second": 6.455,
|
| 707 |
+
"eval_steps_per_second": 0.204,
|
| 708 |
+
"learning_rate": 0.001,
|
| 709 |
+
"step": 11466
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 42.124542124542124,
|
| 713 |
+
"grad_norm": 0.16945631802082062,
|
| 714 |
+
"learning_rate": 0.001,
|
| 715 |
+
"loss": 0.1576,
|
| 716 |
+
"step": 11500
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 43.0,
|
| 720 |
+
"eval_accuracy": 0.2695772695772696,
|
| 721 |
+
"eval_f1_macro": 0.6427022769326964,
|
| 722 |
+
"eval_f1_micro": 0.7930726352070125,
|
| 723 |
+
"eval_loss": 0.13943640887737274,
|
| 724 |
+
"eval_roc_auc": 0.8592814088524369,
|
| 725 |
+
"eval_runtime": 443.0609,
|
| 726 |
+
"eval_samples_per_second": 6.514,
|
| 727 |
+
"eval_steps_per_second": 0.205,
|
| 728 |
+
"learning_rate": 0.001,
|
| 729 |
+
"step": 11739
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 43.956043956043956,
|
| 733 |
+
"grad_norm": 0.17723415791988373,
|
| 734 |
+
"learning_rate": 0.0001,
|
| 735 |
+
"loss": 0.1543,
|
| 736 |
+
"step": 12000
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 44.0,
|
| 740 |
+
"eval_accuracy": 0.27546777546777546,
|
| 741 |
+
"eval_f1_macro": 0.6567716426576066,
|
| 742 |
+
"eval_f1_micro": 0.7989137353078458,
|
| 743 |
+
"eval_loss": 0.1367315948009491,
|
| 744 |
+
"eval_roc_auc": 0.8632369250728903,
|
| 745 |
+
"eval_runtime": 444.9892,
|
| 746 |
+
"eval_samples_per_second": 6.486,
|
| 747 |
+
"eval_steps_per_second": 0.204,
|
| 748 |
+
"learning_rate": 0.0001,
|
| 749 |
+
"step": 12012
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 45.0,
|
| 753 |
+
"eval_accuracy": 0.28274428274428276,
|
| 754 |
+
"eval_f1_macro": 0.6686203083248894,
|
| 755 |
+
"eval_f1_micro": 0.8018308187828446,
|
| 756 |
+
"eval_loss": 0.13616175949573517,
|
| 757 |
+
"eval_roc_auc": 0.8651714707596159,
|
| 758 |
+
"eval_runtime": 435.6671,
|
| 759 |
+
"eval_samples_per_second": 6.624,
|
| 760 |
+
"eval_steps_per_second": 0.209,
|
| 761 |
+
"learning_rate": 0.0001,
|
| 762 |
+
"step": 12285
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 45.78754578754579,
|
| 766 |
+
"grad_norm": 0.15646368265151978,
|
| 767 |
+
"learning_rate": 0.0001,
|
| 768 |
+
"loss": 0.1481,
|
| 769 |
+
"step": 12500
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 46.0,
|
| 773 |
+
"eval_accuracy": 0.2851697851697852,
|
| 774 |
+
"eval_f1_macro": 0.6640104860714046,
|
| 775 |
+
"eval_f1_micro": 0.8021852369457503,
|
| 776 |
+
"eval_loss": 0.13375289738178253,
|
| 777 |
+
"eval_roc_auc": 0.8655685984983028,
|
| 778 |
+
"eval_runtime": 439.641,
|
| 779 |
+
"eval_samples_per_second": 6.564,
|
| 780 |
+
"eval_steps_per_second": 0.207,
|
| 781 |
+
"learning_rate": 0.0001,
|
| 782 |
+
"step": 12558
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 47.0,
|
| 786 |
+
"eval_accuracy": 0.2785862785862786,
|
| 787 |
+
"eval_f1_macro": 0.65726703563479,
|
| 788 |
+
"eval_f1_micro": 0.7998804746862461,
|
| 789 |
+
"eval_loss": 0.14095526933670044,
|
| 790 |
+
"eval_roc_auc": 0.8620771714997334,
|
| 791 |
+
"eval_runtime": 432.1404,
|
| 792 |
+
"eval_samples_per_second": 6.678,
|
| 793 |
+
"eval_steps_per_second": 0.211,
|
| 794 |
+
"learning_rate": 0.0001,
|
| 795 |
+
"step": 12831
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 47.61904761904762,
|
| 799 |
+
"grad_norm": 0.14561912417411804,
|
| 800 |
+
"learning_rate": 0.0001,
|
| 801 |
+
"loss": 0.1472,
|
| 802 |
+
"step": 13000
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 48.0,
|
| 806 |
+
"eval_accuracy": 0.28482328482328484,
|
| 807 |
+
"eval_f1_macro": 0.6728387979723557,
|
| 808 |
+
"eval_f1_micro": 0.8044442566853957,
|
| 809 |
+
"eval_loss": 0.13375185430049896,
|
| 810 |
+
"eval_roc_auc": 0.8674991066436737,
|
| 811 |
+
"eval_runtime": 444.9787,
|
| 812 |
+
"eval_samples_per_second": 6.486,
|
| 813 |
+
"eval_steps_per_second": 0.205,
|
| 814 |
+
"learning_rate": 0.0001,
|
| 815 |
+
"step": 13104
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 49.0,
|
| 819 |
+
"eval_accuracy": 0.2855162855162855,
|
| 820 |
+
"eval_f1_macro": 0.674164075762875,
|
| 821 |
+
"eval_f1_micro": 0.8058309037900874,
|
| 822 |
+
"eval_loss": 0.13221527636051178,
|
| 823 |
+
"eval_roc_auc": 0.8723556652741397,
|
| 824 |
+
"eval_runtime": 443.2861,
|
| 825 |
+
"eval_samples_per_second": 6.51,
|
| 826 |
+
"eval_steps_per_second": 0.205,
|
| 827 |
+
"learning_rate": 0.0001,
|
| 828 |
+
"step": 13377
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 49.45054945054945,
|
| 832 |
+
"grad_norm": 0.18880312144756317,
|
| 833 |
+
"learning_rate": 0.0001,
|
| 834 |
+
"loss": 0.1448,
|
| 835 |
+
"step": 13500
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 50.0,
|
| 839 |
+
"eval_accuracy": 0.28967428967428965,
|
| 840 |
+
"eval_f1_macro": 0.6738599949249782,
|
| 841 |
+
"eval_f1_micro": 0.8062985513331933,
|
| 842 |
+
"eval_loss": 0.13315953314304352,
|
| 843 |
+
"eval_roc_auc": 0.8702548292213903,
|
| 844 |
+
"eval_runtime": 434.9136,
|
| 845 |
+
"eval_samples_per_second": 6.636,
|
| 846 |
+
"eval_steps_per_second": 0.209,
|
| 847 |
+
"learning_rate": 0.0001,
|
| 848 |
+
"step": 13650
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 51.0,
|
| 852 |
+
"eval_accuracy": 0.28967428967428965,
|
| 853 |
+
"eval_f1_macro": 0.6770873238469556,
|
| 854 |
+
"eval_f1_micro": 0.8062836021505377,
|
| 855 |
+
"eval_loss": 0.13057135045528412,
|
| 856 |
+
"eval_roc_auc": 0.8701618987014408,
|
| 857 |
+
"eval_runtime": 431.3628,
|
| 858 |
+
"eval_samples_per_second": 6.69,
|
| 859 |
+
"eval_steps_per_second": 0.211,
|
| 860 |
+
"learning_rate": 0.0001,
|
| 861 |
+
"step": 13923
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 51.282051282051285,
|
| 865 |
+
"grad_norm": 0.17863284051418304,
|
| 866 |
+
"learning_rate": 0.0001,
|
| 867 |
+
"loss": 0.1432,
|
| 868 |
+
"step": 14000
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 52.0,
|
| 872 |
+
"eval_accuracy": 0.2872487872487873,
|
| 873 |
+
"eval_f1_macro": 0.6726562275384118,
|
| 874 |
+
"eval_f1_micro": 0.8043922369765066,
|
| 875 |
+
"eval_loss": 0.13108478486537933,
|
| 876 |
+
"eval_roc_auc": 0.8653604706190395,
|
| 877 |
+
"eval_runtime": 432.9945,
|
| 878 |
+
"eval_samples_per_second": 6.665,
|
| 879 |
+
"eval_steps_per_second": 0.21,
|
| 880 |
+
"learning_rate": 0.0001,
|
| 881 |
+
"step": 14196
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 53.0,
|
| 885 |
+
"eval_accuracy": 0.2872487872487873,
|
| 886 |
+
"eval_f1_macro": 0.6702824874792834,
|
| 887 |
+
"eval_f1_micro": 0.8070734160241367,
|
| 888 |
+
"eval_loss": 0.13161474466323853,
|
| 889 |
+
"eval_roc_auc": 0.8712745968092424,
|
| 890 |
+
"eval_runtime": 437.0691,
|
| 891 |
+
"eval_samples_per_second": 6.603,
|
| 892 |
+
"eval_steps_per_second": 0.208,
|
| 893 |
+
"learning_rate": 0.0001,
|
| 894 |
+
"step": 14469
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 53.11355311355312,
|
| 898 |
+
"grad_norm": 0.15456052124500275,
|
| 899 |
+
"learning_rate": 0.0001,
|
| 900 |
+
"loss": 0.1438,
|
| 901 |
+
"step": 14500
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 54.0,
|
| 905 |
+
"eval_accuracy": 0.2882882882882883,
|
| 906 |
+
"eval_f1_macro": 0.6787531928667037,
|
| 907 |
+
"eval_f1_micro": 0.8064162093710426,
|
| 908 |
+
"eval_loss": 0.1315840184688568,
|
| 909 |
+
"eval_roc_auc": 0.8688063579069815,
|
| 910 |
+
"eval_runtime": 432.9273,
|
| 911 |
+
"eval_samples_per_second": 6.666,
|
| 912 |
+
"eval_steps_per_second": 0.21,
|
| 913 |
+
"learning_rate": 0.0001,
|
| 914 |
+
"step": 14742
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 54.94505494505494,
|
| 918 |
+
"grad_norm": 0.20175035297870636,
|
| 919 |
+
"learning_rate": 0.0001,
|
| 920 |
+
"loss": 0.1417,
|
| 921 |
+
"step": 15000
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 55.0,
|
| 925 |
+
"eval_accuracy": 0.2875952875952876,
|
| 926 |
+
"eval_f1_macro": 0.6698514928377199,
|
| 927 |
+
"eval_f1_micro": 0.8061478697800111,
|
| 928 |
+
"eval_loss": 0.13084293901920319,
|
| 929 |
+
"eval_roc_auc": 0.8685749571564548,
|
| 930 |
+
"eval_runtime": 434.5176,
|
| 931 |
+
"eval_samples_per_second": 6.642,
|
| 932 |
+
"eval_steps_per_second": 0.209,
|
| 933 |
+
"learning_rate": 0.0001,
|
| 934 |
+
"step": 15015
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 56.0,
|
| 938 |
+
"eval_accuracy": 0.29417879417879417,
|
| 939 |
+
"eval_f1_macro": 0.6799502024965028,
|
| 940 |
+
"eval_f1_micro": 0.8094286190238215,
|
| 941 |
+
"eval_loss": 0.12969879806041718,
|
| 942 |
+
"eval_roc_auc": 0.8743735506433774,
|
| 943 |
+
"eval_runtime": 432.6673,
|
| 944 |
+
"eval_samples_per_second": 6.67,
|
| 945 |
+
"eval_steps_per_second": 0.21,
|
| 946 |
+
"learning_rate": 0.0001,
|
| 947 |
+
"step": 15288
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 56.776556776556774,
|
| 951 |
+
"grad_norm": 0.2052290290594101,
|
| 952 |
+
"learning_rate": 0.0001,
|
| 953 |
+
"loss": 0.1415,
|
| 954 |
+
"step": 15500
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 57.0,
|
| 958 |
+
"eval_accuracy": 0.2934857934857935,
|
| 959 |
+
"eval_f1_macro": 0.6716759101412201,
|
| 960 |
+
"eval_f1_micro": 0.8086806577785254,
|
| 961 |
+
"eval_loss": 0.1296372264623642,
|
| 962 |
+
"eval_roc_auc": 0.8711020824592034,
|
| 963 |
+
"eval_runtime": 430.2029,
|
| 964 |
+
"eval_samples_per_second": 6.708,
|
| 965 |
+
"eval_steps_per_second": 0.212,
|
| 966 |
+
"learning_rate": 0.0001,
|
| 967 |
+
"step": 15561
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 58.0,
|
| 971 |
+
"eval_accuracy": 0.29244629244629244,
|
| 972 |
+
"eval_f1_macro": 0.6784509633805341,
|
| 973 |
+
"eval_f1_micro": 0.8068982880161129,
|
| 974 |
+
"eval_loss": 0.12973745167255402,
|
| 975 |
+
"eval_roc_auc": 0.8707904271906546,
|
| 976 |
+
"eval_runtime": 437.8438,
|
| 977 |
+
"eval_samples_per_second": 6.591,
|
| 978 |
+
"eval_steps_per_second": 0.208,
|
| 979 |
+
"learning_rate": 0.0001,
|
| 980 |
+
"step": 15834
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 58.608058608058606,
|
| 984 |
+
"grad_norm": 0.18146342039108276,
|
| 985 |
+
"learning_rate": 0.0001,
|
| 986 |
+
"loss": 0.1413,
|
| 987 |
+
"step": 16000
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 59.0,
|
| 991 |
+
"eval_accuracy": 0.2910602910602911,
|
| 992 |
+
"eval_f1_macro": 0.6811347101829983,
|
| 993 |
+
"eval_f1_micro": 0.8087436297013858,
|
| 994 |
+
"eval_loss": 0.12995606660842896,
|
| 995 |
+
"eval_roc_auc": 0.8707232376735605,
|
| 996 |
+
"eval_runtime": 440.1545,
|
| 997 |
+
"eval_samples_per_second": 6.557,
|
| 998 |
+
"eval_steps_per_second": 0.207,
|
| 999 |
+
"learning_rate": 0.0001,
|
| 1000 |
+
"step": 16107
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 60.0,
|
| 1004 |
+
"eval_accuracy": 0.28794178794178793,
|
| 1005 |
+
"eval_f1_macro": 0.6725887638706813,
|
| 1006 |
+
"eval_f1_micro": 0.8056052474657126,
|
| 1007 |
+
"eval_loss": 0.13024823367595673,
|
| 1008 |
+
"eval_roc_auc": 0.8658006699367622,
|
| 1009 |
+
"eval_runtime": 442.8738,
|
| 1010 |
+
"eval_samples_per_second": 6.517,
|
| 1011 |
+
"eval_steps_per_second": 0.205,
|
| 1012 |
+
"learning_rate": 0.0001,
|
| 1013 |
+
"step": 16380
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 60.43956043956044,
|
| 1017 |
+
"grad_norm": 0.18909117579460144,
|
| 1018 |
+
"learning_rate": 0.0001,
|
| 1019 |
+
"loss": 0.1404,
|
| 1020 |
+
"step": 16500
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 61.0,
|
| 1024 |
+
"eval_accuracy": 0.2948717948717949,
|
| 1025 |
+
"eval_f1_macro": 0.6842961167409227,
|
| 1026 |
+
"eval_f1_micro": 0.8095537925534148,
|
| 1027 |
+
"eval_loss": 0.12872998416423798,
|
| 1028 |
+
"eval_roc_auc": 0.8721413670658958,
|
| 1029 |
+
"eval_runtime": 442.546,
|
| 1030 |
+
"eval_samples_per_second": 6.521,
|
| 1031 |
+
"eval_steps_per_second": 0.206,
|
| 1032 |
+
"learning_rate": 0.0001,
|
| 1033 |
+
"step": 16653
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 62.0,
|
| 1037 |
+
"eval_accuracy": 0.29002079002079,
|
| 1038 |
+
"eval_f1_macro": 0.6821531683206365,
|
| 1039 |
+
"eval_f1_micro": 0.8079526226734349,
|
| 1040 |
+
"eval_loss": 0.12909561395645142,
|
| 1041 |
+
"eval_roc_auc": 0.8690393280672706,
|
| 1042 |
+
"eval_runtime": 439.5646,
|
| 1043 |
+
"eval_samples_per_second": 6.566,
|
| 1044 |
+
"eval_steps_per_second": 0.207,
|
| 1045 |
+
"learning_rate": 0.0001,
|
| 1046 |
+
"step": 16926
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 62.27106227106227,
|
| 1050 |
+
"grad_norm": 0.18229062855243683,
|
| 1051 |
+
"learning_rate": 0.0001,
|
| 1052 |
+
"loss": 0.1393,
|
| 1053 |
+
"step": 17000
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 63.0,
|
| 1057 |
+
"eval_accuracy": 0.29799029799029797,
|
| 1058 |
+
"eval_f1_macro": 0.6812919501021206,
|
| 1059 |
+
"eval_f1_micro": 0.8075538806791719,
|
| 1060 |
+
"eval_loss": 0.12872986495494843,
|
| 1061 |
+
"eval_roc_auc": 0.8685427641356871,
|
| 1062 |
+
"eval_runtime": 439.5217,
|
| 1063 |
+
"eval_samples_per_second": 6.566,
|
| 1064 |
+
"eval_steps_per_second": 0.207,
|
| 1065 |
+
"learning_rate": 0.0001,
|
| 1066 |
+
"step": 17199
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 64.0,
|
| 1070 |
+
"eval_accuracy": 0.2959112959112959,
|
| 1071 |
+
"eval_f1_macro": 0.6805602232602442,
|
| 1072 |
+
"eval_f1_micro": 0.8090726144558109,
|
| 1073 |
+
"eval_loss": 0.12864243984222412,
|
| 1074 |
+
"eval_roc_auc": 0.8722296430115927,
|
| 1075 |
+
"eval_runtime": 436.4112,
|
| 1076 |
+
"eval_samples_per_second": 6.613,
|
| 1077 |
+
"eval_steps_per_second": 0.209,
|
| 1078 |
+
"learning_rate": 0.0001,
|
| 1079 |
+
"step": 17472
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 64.1025641025641,
|
| 1083 |
+
"grad_norm": 0.2255202978849411,
|
| 1084 |
+
"learning_rate": 0.0001,
|
| 1085 |
+
"loss": 0.1395,
|
| 1086 |
+
"step": 17500
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 65.0,
|
| 1090 |
+
"eval_accuracy": 0.29313929313929316,
|
| 1091 |
+
"eval_f1_macro": 0.6837997472607307,
|
| 1092 |
+
"eval_f1_micro": 0.809268560334276,
|
| 1093 |
+
"eval_loss": 0.12800218164920807,
|
| 1094 |
+
"eval_roc_auc": 0.8704023269115411,
|
| 1095 |
+
"eval_runtime": 436.6673,
|
| 1096 |
+
"eval_samples_per_second": 6.609,
|
| 1097 |
+
"eval_steps_per_second": 0.208,
|
| 1098 |
+
"learning_rate": 0.0001,
|
| 1099 |
+
"step": 17745
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 65.93406593406593,
|
| 1103 |
+
"grad_norm": 0.20691530406475067,
|
| 1104 |
+
"learning_rate": 0.0001,
|
| 1105 |
+
"loss": 0.1389,
|
| 1106 |
+
"step": 18000
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 66.0,
|
| 1110 |
+
"eval_accuracy": 0.2959112959112959,
|
| 1111 |
+
"eval_f1_macro": 0.685457875933014,
|
| 1112 |
+
"eval_f1_micro": 0.8107521495951249,
|
| 1113 |
+
"eval_loss": 0.12777170538902283,
|
| 1114 |
+
"eval_roc_auc": 0.8744479165213509,
|
| 1115 |
+
"eval_runtime": 443.2239,
|
| 1116 |
+
"eval_samples_per_second": 6.511,
|
| 1117 |
+
"eval_steps_per_second": 0.205,
|
| 1118 |
+
"learning_rate": 0.0001,
|
| 1119 |
+
"step": 18018
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 67.0,
|
| 1123 |
+
"eval_accuracy": 0.2948717948717949,
|
| 1124 |
+
"eval_f1_macro": 0.6849396578990685,
|
| 1125 |
+
"eval_f1_micro": 0.8098450774612694,
|
| 1126 |
+
"eval_loss": 0.12816764414310455,
|
| 1127 |
+
"eval_roc_auc": 0.874604334361006,
|
| 1128 |
+
"eval_runtime": 435.2924,
|
| 1129 |
+
"eval_samples_per_second": 6.63,
|
| 1130 |
+
"eval_steps_per_second": 0.209,
|
| 1131 |
+
"learning_rate": 0.0001,
|
| 1132 |
+
"step": 18291
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 67.76556776556777,
|
| 1136 |
+
"grad_norm": 0.23671405017375946,
|
| 1137 |
+
"learning_rate": 0.0001,
|
| 1138 |
+
"loss": 0.1376,
|
| 1139 |
+
"step": 18500
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 68.0,
|
| 1143 |
+
"eval_accuracy": 0.29799029799029797,
|
| 1144 |
+
"eval_f1_macro": 0.6903099963278952,
|
| 1145 |
+
"eval_f1_micro": 0.8123470107455503,
|
| 1146 |
+
"eval_loss": 0.12804801762104034,
|
| 1147 |
+
"eval_roc_auc": 0.8771048199390693,
|
| 1148 |
+
"eval_runtime": 435.6555,
|
| 1149 |
+
"eval_samples_per_second": 6.625,
|
| 1150 |
+
"eval_steps_per_second": 0.209,
|
| 1151 |
+
"learning_rate": 0.0001,
|
| 1152 |
+
"step": 18564
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 69.0,
|
| 1156 |
+
"eval_accuracy": 0.29521829521829523,
|
| 1157 |
+
"eval_f1_macro": 0.6800351861453543,
|
| 1158 |
+
"eval_f1_micro": 0.8104663431103608,
|
| 1159 |
+
"eval_loss": 0.12803924083709717,
|
| 1160 |
+
"eval_roc_auc": 0.8710816667185332,
|
| 1161 |
+
"eval_runtime": 435.4705,
|
| 1162 |
+
"eval_samples_per_second": 6.627,
|
| 1163 |
+
"eval_steps_per_second": 0.209,
|
| 1164 |
+
"learning_rate": 0.0001,
|
| 1165 |
+
"step": 18837
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 69.59706959706959,
|
| 1169 |
+
"grad_norm": 0.19641809165477753,
|
| 1170 |
+
"learning_rate": 0.0001,
|
| 1171 |
+
"loss": 0.1375,
|
| 1172 |
+
"step": 19000
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 70.0,
|
| 1176 |
+
"eval_accuracy": 0.29313929313929316,
|
| 1177 |
+
"eval_f1_macro": 0.684802818649885,
|
| 1178 |
+
"eval_f1_micro": 0.8096462751380749,
|
| 1179 |
+
"eval_loss": 0.12764029204845428,
|
| 1180 |
+
"eval_roc_auc": 0.8709255305678097,
|
| 1181 |
+
"eval_runtime": 438.0603,
|
| 1182 |
+
"eval_samples_per_second": 6.588,
|
| 1183 |
+
"eval_steps_per_second": 0.208,
|
| 1184 |
+
"learning_rate": 0.0001,
|
| 1185 |
+
"step": 19110
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 71.0,
|
| 1189 |
+
"eval_accuracy": 0.29036729036729036,
|
| 1190 |
+
"eval_f1_macro": 0.6796736257485385,
|
| 1191 |
+
"eval_f1_micro": 0.8072724183339705,
|
| 1192 |
+
"eval_loss": 0.12794704735279083,
|
| 1193 |
+
"eval_roc_auc": 0.8674678659997703,
|
| 1194 |
+
"eval_runtime": 438.6839,
|
| 1195 |
+
"eval_samples_per_second": 6.579,
|
| 1196 |
+
"eval_steps_per_second": 0.207,
|
| 1197 |
+
"learning_rate": 0.0001,
|
| 1198 |
+
"step": 19383
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 71.42857142857143,
|
| 1202 |
+
"grad_norm": 0.23725061118602753,
|
| 1203 |
+
"learning_rate": 0.0001,
|
| 1204 |
+
"loss": 0.1368,
|
| 1205 |
+
"step": 19500
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 72.0,
|
| 1209 |
+
"eval_accuracy": 0.2938322938322938,
|
| 1210 |
+
"eval_f1_macro": 0.6802343842914587,
|
| 1211 |
+
"eval_f1_micro": 0.8102650399663442,
|
| 1212 |
+
"eval_loss": 0.12780210375785828,
|
| 1213 |
+
"eval_roc_auc": 0.8718861300662425,
|
| 1214 |
+
"eval_runtime": 436.1264,
|
| 1215 |
+
"eval_samples_per_second": 6.617,
|
| 1216 |
+
"eval_steps_per_second": 0.209,
|
| 1217 |
+
"learning_rate": 0.0001,
|
| 1218 |
+
"step": 19656
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 73.0,
|
| 1222 |
+
"eval_accuracy": 0.29764379764379767,
|
| 1223 |
+
"eval_f1_macro": 0.6805723882610378,
|
| 1224 |
+
"eval_f1_micro": 0.8091473263623224,
|
| 1225 |
+
"eval_loss": 0.12723641097545624,
|
| 1226 |
+
"eval_roc_auc": 0.8683039589903839,
|
| 1227 |
+
"eval_runtime": 430.6869,
|
| 1228 |
+
"eval_samples_per_second": 6.701,
|
| 1229 |
+
"eval_steps_per_second": 0.211,
|
| 1230 |
+
"learning_rate": 0.0001,
|
| 1231 |
+
"step": 19929
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 73.26007326007326,
|
| 1235 |
+
"grad_norm": 0.2105712741613388,
|
| 1236 |
+
"learning_rate": 0.0001,
|
| 1237 |
+
"loss": 0.137,
|
| 1238 |
+
"step": 20000
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 74.0,
|
| 1242 |
+
"eval_accuracy": 0.2934857934857935,
|
| 1243 |
+
"eval_f1_macro": 0.6777188921642516,
|
| 1244 |
+
"eval_f1_micro": 0.8064391831142698,
|
| 1245 |
+
"eval_loss": 0.12804573774337769,
|
| 1246 |
+
"eval_roc_auc": 0.8647877433658233,
|
| 1247 |
+
"eval_runtime": 435.4406,
|
| 1248 |
+
"eval_samples_per_second": 6.628,
|
| 1249 |
+
"eval_steps_per_second": 0.209,
|
| 1250 |
+
"learning_rate": 0.0001,
|
| 1251 |
+
"step": 20202
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 75.0,
|
| 1255 |
+
"eval_accuracy": 0.29244629244629244,
|
| 1256 |
+
"eval_f1_macro": 0.6885203936930924,
|
| 1257 |
+
"eval_f1_micro": 0.8109922383050138,
|
| 1258 |
+
"eval_loss": 0.1273234635591507,
|
| 1259 |
+
"eval_roc_auc": 0.8730787473480999,
|
| 1260 |
+
"eval_runtime": 433.0115,
|
| 1261 |
+
"eval_samples_per_second": 6.665,
|
| 1262 |
+
"eval_steps_per_second": 0.21,
|
| 1263 |
+
"learning_rate": 0.0001,
|
| 1264 |
+
"step": 20475
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 75.0915750915751,
|
| 1268 |
+
"grad_norm": 0.24889850616455078,
|
| 1269 |
+
"learning_rate": 0.0001,
|
| 1270 |
+
"loss": 0.1367,
|
| 1271 |
+
"step": 20500
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 76.0,
|
| 1275 |
+
"eval_accuracy": 0.2972972972972973,
|
| 1276 |
+
"eval_f1_macro": 0.6810578369044884,
|
| 1277 |
+
"eval_f1_micro": 0.8088975345709815,
|
| 1278 |
+
"eval_loss": 0.1272992193698883,
|
| 1279 |
+
"eval_roc_auc": 0.8696399827660029,
|
| 1280 |
+
"eval_runtime": 432.2403,
|
| 1281 |
+
"eval_samples_per_second": 6.677,
|
| 1282 |
+
"eval_steps_per_second": 0.211,
|
| 1283 |
+
"learning_rate": 0.0001,
|
| 1284 |
+
"step": 20748
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 76.92307692307692,
|
| 1288 |
+
"grad_norm": 0.24539624154567719,
|
| 1289 |
+
"learning_rate": 0.0001,
|
| 1290 |
+
"loss": 0.1358,
|
| 1291 |
+
"step": 21000
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 77.0,
|
| 1295 |
+
"eval_accuracy": 0.29244629244629244,
|
| 1296 |
+
"eval_f1_macro": 0.6863183190306963,
|
| 1297 |
+
"eval_f1_micro": 0.8102101349375445,
|
| 1298 |
+
"eval_loss": 0.12745273113250732,
|
| 1299 |
+
"eval_roc_auc": 0.8738921845003481,
|
| 1300 |
+
"eval_runtime": 434.2537,
|
| 1301 |
+
"eval_samples_per_second": 6.646,
|
| 1302 |
+
"eval_steps_per_second": 0.21,
|
| 1303 |
+
"learning_rate": 0.0001,
|
| 1304 |
+
"step": 21021
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 78.0,
|
| 1308 |
+
"eval_accuracy": 0.2945252945252945,
|
| 1309 |
+
"eval_f1_macro": 0.6897104532016692,
|
| 1310 |
+
"eval_f1_micro": 0.8121675531914894,
|
| 1311 |
+
"eval_loss": 0.12705788016319275,
|
| 1312 |
+
"eval_roc_auc": 0.876527719800532,
|
| 1313 |
+
"eval_runtime": 444.7222,
|
| 1314 |
+
"eval_samples_per_second": 6.489,
|
| 1315 |
+
"eval_steps_per_second": 0.205,
|
| 1316 |
+
"learning_rate": 0.0001,
|
| 1317 |
+
"step": 21294
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 78.75457875457876,
|
| 1321 |
+
"grad_norm": 0.23895101249217987,
|
| 1322 |
+
"learning_rate": 0.0001,
|
| 1323 |
+
"loss": 0.1352,
|
| 1324 |
+
"step": 21500
|
| 1325 |
+
},
|
| 1326 |
+
{
|
| 1327 |
+
"epoch": 79.0,
|
| 1328 |
+
"eval_accuracy": 0.2934857934857935,
|
| 1329 |
+
"eval_f1_macro": 0.6881838490414868,
|
| 1330 |
+
"eval_f1_micro": 0.809842452990005,
|
| 1331 |
+
"eval_loss": 0.12710121273994446,
|
| 1332 |
+
"eval_roc_auc": 0.869729211088564,
|
| 1333 |
+
"eval_runtime": 435.3871,
|
| 1334 |
+
"eval_samples_per_second": 6.629,
|
| 1335 |
+
"eval_steps_per_second": 0.209,
|
| 1336 |
+
"learning_rate": 0.0001,
|
| 1337 |
+
"step": 21567
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 80.0,
|
| 1341 |
+
"eval_accuracy": 0.2983367983367983,
|
| 1342 |
+
"eval_f1_macro": 0.6914032136958002,
|
| 1343 |
+
"eval_f1_micro": 0.8123911420751431,
|
| 1344 |
+
"eval_loss": 0.12715762853622437,
|
| 1345 |
+
"eval_roc_auc": 0.8772640412542829,
|
| 1346 |
+
"eval_runtime": 435.2387,
|
| 1347 |
+
"eval_samples_per_second": 6.631,
|
| 1348 |
+
"eval_steps_per_second": 0.209,
|
| 1349 |
+
"learning_rate": 0.0001,
|
| 1350 |
+
"step": 21840
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 80.58608058608058,
|
| 1354 |
+
"grad_norm": 0.28309133648872375,
|
| 1355 |
+
"learning_rate": 0.0001,
|
| 1356 |
+
"loss": 0.1353,
|
| 1357 |
+
"step": 22000
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 81.0,
|
| 1361 |
+
"eval_accuracy": 0.2966042966042966,
|
| 1362 |
+
"eval_f1_macro": 0.6899389708752343,
|
| 1363 |
+
"eval_f1_micro": 0.810378232667846,
|
| 1364 |
+
"eval_loss": 0.12650521099567413,
|
| 1365 |
+
"eval_roc_auc": 0.8716067214734959,
|
| 1366 |
+
"eval_runtime": 440.2197,
|
| 1367 |
+
"eval_samples_per_second": 6.556,
|
| 1368 |
+
"eval_steps_per_second": 0.207,
|
| 1369 |
+
"learning_rate": 0.0001,
|
| 1370 |
+
"step": 22113
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 82.0,
|
| 1374 |
+
"eval_accuracy": 0.29140679140679143,
|
| 1375 |
+
"eval_f1_macro": 0.6844864031747653,
|
| 1376 |
+
"eval_f1_micro": 0.8105446364138047,
|
| 1377 |
+
"eval_loss": 0.12635371088981628,
|
| 1378 |
+
"eval_roc_auc": 0.8694408286912787,
|
| 1379 |
+
"eval_runtime": 441.9602,
|
| 1380 |
+
"eval_samples_per_second": 6.53,
|
| 1381 |
+
"eval_steps_per_second": 0.206,
|
| 1382 |
+
"learning_rate": 0.0001,
|
| 1383 |
+
"step": 22386
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 82.41758241758242,
|
| 1387 |
+
"grad_norm": 0.24017925560474396,
|
| 1388 |
+
"learning_rate": 0.0001,
|
| 1389 |
+
"loss": 0.1337,
|
| 1390 |
+
"step": 22500
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"epoch": 83.0,
|
| 1394 |
+
"eval_accuracy": 0.2934857934857935,
|
| 1395 |
+
"eval_f1_macro": 0.6832392344549459,
|
| 1396 |
+
"eval_f1_micro": 0.8099670022844573,
|
| 1397 |
+
"eval_loss": 0.1272997260093689,
|
| 1398 |
+
"eval_roc_auc": 0.8701139445142557,
|
| 1399 |
+
"eval_runtime": 442.0471,
|
| 1400 |
+
"eval_samples_per_second": 6.529,
|
| 1401 |
+
"eval_steps_per_second": 0.206,
|
| 1402 |
+
"learning_rate": 0.0001,
|
| 1403 |
+
"step": 22659
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 84.0,
|
| 1407 |
+
"eval_accuracy": 0.2959112959112959,
|
| 1408 |
+
"eval_f1_macro": 0.6944491344986764,
|
| 1409 |
+
"eval_f1_micro": 0.8124478558318038,
|
| 1410 |
+
"eval_loss": 0.12640425562858582,
|
| 1411 |
+
"eval_roc_auc": 0.875556912431764,
|
| 1412 |
+
"eval_runtime": 443.3633,
|
| 1413 |
+
"eval_samples_per_second": 6.509,
|
| 1414 |
+
"eval_steps_per_second": 0.205,
|
| 1415 |
+
"learning_rate": 0.0001,
|
| 1416 |
+
"step": 22932
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 84.24908424908425,
|
| 1420 |
+
"grad_norm": 0.22998856008052826,
|
| 1421 |
+
"learning_rate": 0.0001,
|
| 1422 |
+
"loss": 0.1354,
|
| 1423 |
+
"step": 23000
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 85.0,
|
| 1427 |
+
"eval_accuracy": 0.2972972972972973,
|
| 1428 |
+
"eval_f1_macro": 0.6879519222426981,
|
| 1429 |
+
"eval_f1_micro": 0.812659392115055,
|
| 1430 |
+
"eval_loss": 0.12647400796413422,
|
| 1431 |
+
"eval_roc_auc": 0.8750247349709565,
|
| 1432 |
+
"eval_runtime": 442.8099,
|
| 1433 |
+
"eval_samples_per_second": 6.517,
|
| 1434 |
+
"eval_steps_per_second": 0.206,
|
| 1435 |
+
"learning_rate": 0.0001,
|
| 1436 |
+
"step": 23205
|
| 1437 |
+
},
|
| 1438 |
+
{
|
| 1439 |
+
"epoch": 86.0,
|
| 1440 |
+
"eval_accuracy": 0.29521829521829523,
|
| 1441 |
+
"eval_f1_macro": 0.6933253774763921,
|
| 1442 |
+
"eval_f1_micro": 0.8135877542461731,
|
| 1443 |
+
"eval_loss": 0.12585221230983734,
|
| 1444 |
+
"eval_roc_auc": 0.8746291766420319,
|
| 1445 |
+
"eval_runtime": 440.9089,
|
| 1446 |
+
"eval_samples_per_second": 6.546,
|
| 1447 |
+
"eval_steps_per_second": 0.206,
|
| 1448 |
+
"learning_rate": 0.0001,
|
| 1449 |
+
"step": 23478
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 86.08058608058609,
|
| 1453 |
+
"grad_norm": 0.29592010378837585,
|
| 1454 |
+
"learning_rate": 0.0001,
|
| 1455 |
+
"loss": 0.1334,
|
| 1456 |
+
"step": 23500
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 87.0,
|
| 1460 |
+
"eval_accuracy": 0.2966042966042966,
|
| 1461 |
+
"eval_f1_macro": 0.6882459007361815,
|
| 1462 |
+
"eval_f1_micro": 0.8111366966715512,
|
| 1463 |
+
"eval_loss": 0.12641744315624237,
|
| 1464 |
+
"eval_roc_auc": 0.8737689120583252,
|
| 1465 |
+
"eval_runtime": 444.5125,
|
| 1466 |
+
"eval_samples_per_second": 6.493,
|
| 1467 |
+
"eval_steps_per_second": 0.205,
|
| 1468 |
+
"learning_rate": 0.0001,
|
| 1469 |
+
"step": 23751
|
| 1470 |
+
},
|
| 1471 |
+
{
|
| 1472 |
+
"epoch": 87.91208791208791,
|
| 1473 |
+
"grad_norm": 0.252650648355484,
|
| 1474 |
+
"learning_rate": 0.0001,
|
| 1475 |
+
"loss": 0.1335,
|
| 1476 |
+
"step": 24000
|
| 1477 |
+
},
|
| 1478 |
+
{
|
| 1479 |
+
"epoch": 88.0,
|
| 1480 |
+
"eval_accuracy": 0.29902979902979904,
|
| 1481 |
+
"eval_f1_macro": 0.6859575429209334,
|
| 1482 |
+
"eval_f1_micro": 0.8126931106471816,
|
| 1483 |
+
"eval_loss": 0.1263686865568161,
|
| 1484 |
+
"eval_roc_auc": 0.8754230967754396,
|
| 1485 |
+
"eval_runtime": 448.2495,
|
| 1486 |
+
"eval_samples_per_second": 6.438,
|
| 1487 |
+
"eval_steps_per_second": 0.203,
|
| 1488 |
+
"learning_rate": 0.0001,
|
| 1489 |
+
"step": 24024
|
| 1490 |
+
},
|
| 1491 |
+
{
|
| 1492 |
+
"epoch": 89.0,
|
| 1493 |
+
"eval_accuracy": 0.2983367983367983,
|
| 1494 |
+
"eval_f1_macro": 0.6990366097632199,
|
| 1495 |
+
"eval_f1_micro": 0.8140188460902628,
|
| 1496 |
+
"eval_loss": 0.12690132856369019,
|
| 1497 |
+
"eval_roc_auc": 0.8791768834795075,
|
| 1498 |
+
"eval_runtime": 441.4136,
|
| 1499 |
+
"eval_samples_per_second": 6.538,
|
| 1500 |
+
"eval_steps_per_second": 0.206,
|
| 1501 |
+
"learning_rate": 0.0001,
|
| 1502 |
+
"step": 24297
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 89.74358974358974,
|
| 1506 |
+
"grad_norm": 0.2610660791397095,
|
| 1507 |
+
"learning_rate": 0.0001,
|
| 1508 |
+
"loss": 0.1332,
|
| 1509 |
+
"step": 24500
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 90.0,
|
| 1513 |
+
"eval_accuracy": 0.29799029799029797,
|
| 1514 |
+
"eval_f1_macro": 0.6994167448254883,
|
| 1515 |
+
"eval_f1_micro": 0.8155163144617673,
|
| 1516 |
+
"eval_loss": 0.12612390518188477,
|
| 1517 |
+
"eval_roc_auc": 0.8798283494960182,
|
| 1518 |
+
"eval_runtime": 445.6794,
|
| 1519 |
+
"eval_samples_per_second": 6.476,
|
| 1520 |
+
"eval_steps_per_second": 0.204,
|
| 1521 |
+
"learning_rate": 0.0001,
|
| 1522 |
+
"step": 24570
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 91.0,
|
| 1526 |
+
"eval_accuracy": 0.28932778932778935,
|
| 1527 |
+
"eval_f1_macro": 0.6827913109763548,
|
| 1528 |
+
"eval_f1_micro": 0.8108811552831535,
|
| 1529 |
+
"eval_loss": 0.1268243044614792,
|
| 1530 |
+
"eval_roc_auc": 0.8728467295646753,
|
| 1531 |
+
"eval_runtime": 442.1487,
|
| 1532 |
+
"eval_samples_per_second": 6.527,
|
| 1533 |
+
"eval_steps_per_second": 0.206,
|
| 1534 |
+
"learning_rate": 0.0001,
|
| 1535 |
+
"step": 24843
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 91.57509157509158,
|
| 1539 |
+
"grad_norm": 0.28306326270103455,
|
| 1540 |
+
"learning_rate": 0.0001,
|
| 1541 |
+
"loss": 0.1326,
|
| 1542 |
+
"step": 25000
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 92.0,
|
| 1546 |
+
"eval_accuracy": 0.29521829521829523,
|
| 1547 |
+
"eval_f1_macro": 0.6858483939371968,
|
| 1548 |
+
"eval_f1_micro": 0.8123787840458724,
|
| 1549 |
+
"eval_loss": 0.12613284587860107,
|
| 1550 |
+
"eval_roc_auc": 0.8724090520335794,
|
| 1551 |
+
"eval_runtime": 447.7751,
|
| 1552 |
+
"eval_samples_per_second": 6.445,
|
| 1553 |
+
"eval_steps_per_second": 0.203,
|
| 1554 |
+
"learning_rate": 0.0001,
|
| 1555 |
+
"step": 25116
|
| 1556 |
+
},
|
| 1557 |
+
{
|
| 1558 |
+
"epoch": 93.0,
|
| 1559 |
+
"eval_accuracy": 0.2966042966042966,
|
| 1560 |
+
"eval_f1_macro": 0.6897216822080747,
|
| 1561 |
+
"eval_f1_micro": 0.8138213420238991,
|
| 1562 |
+
"eval_loss": 0.1258293092250824,
|
| 1563 |
+
"eval_roc_auc": 0.8758502847472687,
|
| 1564 |
+
"eval_runtime": 442.7745,
|
| 1565 |
+
"eval_samples_per_second": 6.518,
|
| 1566 |
+
"eval_steps_per_second": 0.206,
|
| 1567 |
+
"learning_rate": 1e-05,
|
| 1568 |
+
"step": 25389
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 93.4065934065934,
|
| 1572 |
+
"grad_norm": 0.36196333169937134,
|
| 1573 |
+
"learning_rate": 1e-05,
|
| 1574 |
+
"loss": 0.132,
|
| 1575 |
+
"step": 25500
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 94.0,
|
| 1579 |
+
"eval_accuracy": 0.29764379764379767,
|
| 1580 |
+
"eval_f1_macro": 0.6940665827082791,
|
| 1581 |
+
"eval_f1_micro": 0.8137706015226304,
|
| 1582 |
+
"eval_loss": 0.12682591378688812,
|
| 1583 |
+
"eval_roc_auc": 0.8754785626674707,
|
| 1584 |
+
"eval_runtime": 447.9681,
|
| 1585 |
+
"eval_samples_per_second": 6.442,
|
| 1586 |
+
"eval_steps_per_second": 0.203,
|
| 1587 |
+
"learning_rate": 1e-05,
|
| 1588 |
+
"step": 25662
|
| 1589 |
+
},
|
| 1590 |
+
{
|
| 1591 |
+
"epoch": 95.0,
|
| 1592 |
+
"eval_accuracy": 0.2948717948717949,
|
| 1593 |
+
"eval_f1_macro": 0.6913394393323408,
|
| 1594 |
+
"eval_f1_micro": 0.8133975298304374,
|
| 1595 |
+
"eval_loss": 0.1256789118051529,
|
| 1596 |
+
"eval_roc_auc": 0.8750151441335194,
|
| 1597 |
+
"eval_runtime": 494.4109,
|
| 1598 |
+
"eval_samples_per_second": 5.837,
|
| 1599 |
+
"eval_steps_per_second": 0.184,
|
| 1600 |
+
"learning_rate": 1e-05,
|
| 1601 |
+
"step": 25935
|
| 1602 |
+
},
|
| 1603 |
+
{
|
| 1604 |
+
"epoch": 95.23809523809524,
|
| 1605 |
+
"grad_norm": 0.28360626101493835,
|
| 1606 |
+
"learning_rate": 1e-05,
|
| 1607 |
+
"loss": 0.1294,
|
| 1608 |
+
"step": 26000
|
| 1609 |
+
},
|
| 1610 |
+
{
|
| 1611 |
+
"epoch": 96.0,
|
| 1612 |
+
"eval_accuracy": 0.29764379764379767,
|
| 1613 |
+
"eval_f1_macro": 0.6957055849225957,
|
| 1614 |
+
"eval_f1_micro": 0.8147281313996739,
|
| 1615 |
+
"eval_loss": 0.12587758898735046,
|
| 1616 |
+
"eval_roc_auc": 0.876265078406102,
|
| 1617 |
+
"eval_runtime": 456.43,
|
| 1618 |
+
"eval_samples_per_second": 6.323,
|
| 1619 |
+
"eval_steps_per_second": 0.199,
|
| 1620 |
+
"learning_rate": 1e-05,
|
| 1621 |
+
"step": 26208
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 97.0,
|
| 1625 |
+
"eval_accuracy": 0.2945252945252945,
|
| 1626 |
+
"eval_f1_macro": 0.6940781337907567,
|
| 1627 |
+
"eval_f1_micro": 0.8126029480086159,
|
| 1628 |
+
"eval_loss": 0.1256256103515625,
|
| 1629 |
+
"eval_roc_auc": 0.8720295902150387,
|
| 1630 |
+
"eval_runtime": 440.8704,
|
| 1631 |
+
"eval_samples_per_second": 6.546,
|
| 1632 |
+
"eval_steps_per_second": 0.206,
|
| 1633 |
+
"learning_rate": 1e-05,
|
| 1634 |
+
"step": 26481
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 97.06959706959707,
|
| 1638 |
+
"grad_norm": 0.29758304357528687,
|
| 1639 |
+
"learning_rate": 1e-05,
|
| 1640 |
+
"loss": 0.1302,
|
| 1641 |
+
"step": 26500
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 98.0,
|
| 1645 |
+
"eval_accuracy": 0.2993762993762994,
|
| 1646 |
+
"eval_f1_macro": 0.6951390304078455,
|
| 1647 |
+
"eval_f1_micro": 0.8158955813276801,
|
| 1648 |
+
"eval_loss": 0.1253080666065216,
|
| 1649 |
+
"eval_roc_auc": 0.8785118427392398,
|
| 1650 |
+
"eval_runtime": 432.3413,
|
| 1651 |
+
"eval_samples_per_second": 6.675,
|
| 1652 |
+
"eval_steps_per_second": 0.21,
|
| 1653 |
+
"learning_rate": 1e-05,
|
| 1654 |
+
"step": 26754
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 98.9010989010989,
|
| 1658 |
+
"grad_norm": 0.3460623621940613,
|
| 1659 |
+
"learning_rate": 1e-05,
|
| 1660 |
+
"loss": 0.1298,
|
| 1661 |
+
"step": 27000
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 99.0,
|
| 1665 |
+
"eval_accuracy": 0.2993762993762994,
|
| 1666 |
+
"eval_f1_macro": 0.6968244403216463,
|
| 1667 |
+
"eval_f1_micro": 0.8141971169963125,
|
| 1668 |
+
"eval_loss": 0.12485036998987198,
|
| 1669 |
+
"eval_roc_auc": 0.8751979200089282,
|
| 1670 |
+
"eval_runtime": 440.8458,
|
| 1671 |
+
"eval_samples_per_second": 6.547,
|
| 1672 |
+
"eval_steps_per_second": 0.206,
|
| 1673 |
+
"learning_rate": 1e-05,
|
| 1674 |
+
"step": 27027
|
| 1675 |
+
},
|
| 1676 |
+
{
|
| 1677 |
+
"epoch": 100.0,
|
| 1678 |
+
"eval_accuracy": 0.2972972972972973,
|
| 1679 |
+
"eval_f1_macro": 0.693647218520028,
|
| 1680 |
+
"eval_f1_micro": 0.8134507606084869,
|
| 1681 |
+
"eval_loss": 0.12519583106040955,
|
| 1682 |
+
"eval_roc_auc": 0.8731552996687338,
|
| 1683 |
+
"eval_runtime": 426.3213,
|
| 1684 |
+
"eval_samples_per_second": 6.77,
|
| 1685 |
+
"eval_steps_per_second": 0.213,
|
| 1686 |
+
"learning_rate": 1e-05,
|
| 1687 |
+
"step": 27300
|
| 1688 |
+
},
|
| 1689 |
+
{
|
| 1690 |
+
"epoch": 100.73260073260073,
|
| 1691 |
+
"grad_norm": 0.2845664918422699,
|
| 1692 |
+
"learning_rate": 1e-05,
|
| 1693 |
+
"loss": 0.1304,
|
| 1694 |
+
"step": 27500
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 101.0,
|
| 1698 |
+
"eval_accuracy": 0.29902979902979904,
|
| 1699 |
+
"eval_f1_macro": 0.6961023046950545,
|
| 1700 |
+
"eval_f1_micro": 0.8148550421923302,
|
| 1701 |
+
"eval_loss": 0.12475299090147018,
|
| 1702 |
+
"eval_roc_auc": 0.8764704564648416,
|
| 1703 |
+
"eval_runtime": 432.286,
|
| 1704 |
+
"eval_samples_per_second": 6.676,
|
| 1705 |
+
"eval_steps_per_second": 0.211,
|
| 1706 |
+
"learning_rate": 1e-05,
|
| 1707 |
+
"step": 27573
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 102.0,
|
| 1711 |
+
"eval_accuracy": 0.29625779625779625,
|
| 1712 |
+
"eval_f1_macro": 0.692743439816851,
|
| 1713 |
+
"eval_f1_micro": 0.81366198367965,
|
| 1714 |
+
"eval_loss": 0.12659381330013275,
|
| 1715 |
+
"eval_roc_auc": 0.8737986906025352,
|
| 1716 |
+
"eval_runtime": 429.8933,
|
| 1717 |
+
"eval_samples_per_second": 6.713,
|
| 1718 |
+
"eval_steps_per_second": 0.212,
|
| 1719 |
+
"learning_rate": 1e-05,
|
| 1720 |
+
"step": 27846
|
| 1721 |
+
},
|
| 1722 |
+
{
|
| 1723 |
+
"epoch": 102.56410256410257,
|
| 1724 |
+
"grad_norm": 0.276334673166275,
|
| 1725 |
+
"learning_rate": 1e-05,
|
| 1726 |
+
"loss": 0.1287,
|
| 1727 |
+
"step": 28000
|
| 1728 |
+
},
|
| 1729 |
+
{
|
| 1730 |
+
"epoch": 103.0,
|
| 1731 |
+
"eval_accuracy": 0.29902979902979904,
|
| 1732 |
+
"eval_f1_macro": 0.6954353634647259,
|
| 1733 |
+
"eval_f1_micro": 0.8146347596496376,
|
| 1734 |
+
"eval_loss": 0.124935083091259,
|
| 1735 |
+
"eval_roc_auc": 0.8754020640018715,
|
| 1736 |
+
"eval_runtime": 433.4496,
|
| 1737 |
+
"eval_samples_per_second": 6.658,
|
| 1738 |
+
"eval_steps_per_second": 0.21,
|
| 1739 |
+
"learning_rate": 1e-05,
|
| 1740 |
+
"step": 28119
|
| 1741 |
+
},
|
| 1742 |
+
{
|
| 1743 |
+
"epoch": 104.0,
|
| 1744 |
+
"eval_accuracy": 0.29764379764379767,
|
| 1745 |
+
"eval_f1_macro": 0.692659001716947,
|
| 1746 |
+
"eval_f1_micro": 0.8148796863922599,
|
| 1747 |
+
"eval_loss": 0.12519653141498566,
|
| 1748 |
+
"eval_roc_auc": 0.8769883885139594,
|
| 1749 |
+
"eval_runtime": 435.0406,
|
| 1750 |
+
"eval_samples_per_second": 6.634,
|
| 1751 |
+
"eval_steps_per_second": 0.209,
|
| 1752 |
+
"learning_rate": 1e-05,
|
| 1753 |
+
"step": 28392
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 104.3956043956044,
|
| 1757 |
+
"grad_norm": 0.2987622320652008,
|
| 1758 |
+
"learning_rate": 1e-05,
|
| 1759 |
+
"loss": 0.1282,
|
| 1760 |
+
"step": 28500
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 105.0,
|
| 1764 |
+
"eval_accuracy": 0.29902979902979904,
|
| 1765 |
+
"eval_f1_macro": 0.6961790886935857,
|
| 1766 |
+
"eval_f1_micro": 0.8152223750573132,
|
| 1767 |
+
"eval_loss": 0.12513257563114166,
|
| 1768 |
+
"eval_roc_auc": 0.8773257311303291,
|
| 1769 |
+
"eval_runtime": 430.7348,
|
| 1770 |
+
"eval_samples_per_second": 6.7,
|
| 1771 |
+
"eval_steps_per_second": 0.211,
|
| 1772 |
+
"learning_rate": 1e-05,
|
| 1773 |
+
"step": 28665
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 106.0,
|
| 1777 |
+
"eval_accuracy": 0.29972279972279975,
|
| 1778 |
+
"eval_f1_macro": 0.6963861386142265,
|
| 1779 |
+
"eval_f1_micro": 0.8147252563995664,
|
| 1780 |
+
"eval_loss": 0.12511174380779266,
|
| 1781 |
+
"eval_roc_auc": 0.8769890055468574,
|
| 1782 |
+
"eval_runtime": 434.1489,
|
| 1783 |
+
"eval_samples_per_second": 6.647,
|
| 1784 |
+
"eval_steps_per_second": 0.21,
|
| 1785 |
+
"learning_rate": 1e-05,
|
| 1786 |
+
"step": 28938
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 106.22710622710623,
|
| 1790 |
+
"grad_norm": 0.2862643301486969,
|
| 1791 |
+
"learning_rate": 1e-05,
|
| 1792 |
+
"loss": 0.1293,
|
| 1793 |
+
"step": 29000
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 107.0,
|
| 1797 |
+
"eval_accuracy": 0.29799029799029797,
|
| 1798 |
+
"eval_f1_macro": 0.694620567930595,
|
| 1799 |
+
"eval_f1_micro": 0.8144894800685992,
|
| 1800 |
+
"eval_loss": 0.12498941272497177,
|
| 1801 |
+
"eval_roc_auc": 0.8758874676862554,
|
| 1802 |
+
"eval_runtime": 435.6169,
|
| 1803 |
+
"eval_samples_per_second": 6.625,
|
| 1804 |
+
"eval_steps_per_second": 0.209,
|
| 1805 |
+
"learning_rate": 1e-05,
|
| 1806 |
+
"step": 29211
|
| 1807 |
+
},
|
| 1808 |
+
{
|
| 1809 |
+
"epoch": 108.0,
|
| 1810 |
+
"eval_accuracy": 0.29972279972279975,
|
| 1811 |
+
"eval_f1_macro": 0.6934713387989168,
|
| 1812 |
+
"eval_f1_micro": 0.8144792584203683,
|
| 1813 |
+
"eval_loss": 0.1248873621225357,
|
| 1814 |
+
"eval_roc_auc": 0.8750706100255504,
|
| 1815 |
+
"eval_runtime": 426.658,
|
| 1816 |
+
"eval_samples_per_second": 6.764,
|
| 1817 |
+
"eval_steps_per_second": 0.213,
|
| 1818 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1819 |
+
"step": 29484
|
| 1820 |
+
},
|
| 1821 |
+
{
|
| 1822 |
+
"epoch": 108.05860805860806,
|
| 1823 |
+
"grad_norm": 0.2752939760684967,
|
| 1824 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1825 |
+
"loss": 0.129,
|
| 1826 |
+
"step": 29500
|
| 1827 |
+
},
|
| 1828 |
+
{
|
| 1829 |
+
"epoch": 109.0,
|
| 1830 |
+
"eval_accuracy": 0.29521829521829523,
|
| 1831 |
+
"eval_f1_macro": 0.6900779361953018,
|
| 1832 |
+
"eval_f1_micro": 0.8116150302210575,
|
| 1833 |
+
"eval_loss": 0.12527066469192505,
|
| 1834 |
+
"eval_roc_auc": 0.8712697142010926,
|
| 1835 |
+
"eval_runtime": 434.9611,
|
| 1836 |
+
"eval_samples_per_second": 6.635,
|
| 1837 |
+
"eval_steps_per_second": 0.209,
|
| 1838 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1839 |
+
"step": 29757
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 109.89010989010988,
|
| 1843 |
+
"grad_norm": 0.2989753484725952,
|
| 1844 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1845 |
+
"loss": 0.1293,
|
| 1846 |
+
"step": 30000
|
| 1847 |
+
},
|
| 1848 |
+
{
|
| 1849 |
+
"epoch": 110.0,
|
| 1850 |
+
"eval_accuracy": 0.29799029799029797,
|
| 1851 |
+
"eval_f1_macro": 0.69491512245201,
|
| 1852 |
+
"eval_f1_micro": 0.8143917285082964,
|
| 1853 |
+
"eval_loss": 0.125152125954628,
|
| 1854 |
+
"eval_roc_auc": 0.8768043785727546,
|
| 1855 |
+
"eval_runtime": 434.3393,
|
| 1856 |
+
"eval_samples_per_second": 6.645,
|
| 1857 |
+
"eval_steps_per_second": 0.21,
|
| 1858 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1859 |
+
"step": 30030
|
| 1860 |
+
},
|
| 1861 |
+
{
|
| 1862 |
+
"epoch": 111.0,
|
| 1863 |
+
"eval_accuracy": 0.2983367983367983,
|
| 1864 |
+
"eval_f1_macro": 0.6932228755688746,
|
| 1865 |
+
"eval_f1_micro": 0.8137025263510123,
|
| 1866 |
+
"eval_loss": 0.12495684623718262,
|
| 1867 |
+
"eval_roc_auc": 0.8754655513215771,
|
| 1868 |
+
"eval_runtime": 431.8608,
|
| 1869 |
+
"eval_samples_per_second": 6.683,
|
| 1870 |
+
"eval_steps_per_second": 0.211,
|
| 1871 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1872 |
+
"step": 30303
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 111.0,
|
| 1876 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1877 |
+
"step": 30303,
|
| 1878 |
+
"total_flos": 4.1153080208666034e+20,
|
| 1879 |
+
"train_loss": 0.14764341744551096,
|
| 1880 |
+
"train_runtime": 198162.6547,
|
| 1881 |
+
"train_samples_per_second": 6.598,
|
| 1882 |
+
"train_steps_per_second": 0.207
|
| 1883 |
+
}
|
| 1884 |
+
],
|
| 1885 |
+
"logging_steps": 500,
|
| 1886 |
+
"max_steps": 40950,
|
| 1887 |
+
"num_input_tokens_seen": 0,
|
| 1888 |
+
"num_train_epochs": 150,
|
| 1889 |
+
"save_steps": 500,
|
| 1890 |
+
"stateful_callbacks": {
|
| 1891 |
+
"EarlyStoppingCallback": {
|
| 1892 |
+
"args": {
|
| 1893 |
+
"early_stopping_patience": 10,
|
| 1894 |
+
"early_stopping_threshold": 0.0
|
| 1895 |
+
},
|
| 1896 |
+
"attributes": {
|
| 1897 |
+
"early_stopping_patience_counter": 0
|
| 1898 |
+
}
|
| 1899 |
+
},
|
| 1900 |
+
"TrainerControl": {
|
| 1901 |
+
"args": {
|
| 1902 |
+
"should_epoch_stop": false,
|
| 1903 |
+
"should_evaluate": false,
|
| 1904 |
+
"should_log": false,
|
| 1905 |
+
"should_save": true,
|
| 1906 |
+
"should_training_stop": true
|
| 1907 |
+
},
|
| 1908 |
+
"attributes": {}
|
| 1909 |
+
}
|
| 1910 |
+
},
|
| 1911 |
+
"total_flos": 4.1153080208666034e+20,
|
| 1912 |
+
"train_batch_size": 32,
|
| 1913 |
+
"trial_name": null,
|
| 1914 |
+
"trial_params": null
|
| 1915 |
+
}
|