Evaluation on the test set completed on 2024_09_18.
Browse files- README.md +156 -0
- all_results.json +17 -0
- logs/events.out.tfevents.1726457760.datavisu2 +2 -2
- logs/events.out.tfevents.1726673937.datavisu2 +3 -0
- model.safetensors +1 -1
- test_results.json +12 -0
- train_results.json +9 -0
- trainer_state.json +1578 -0
README.md
ADDED
|
@@ -0,0 +1,156 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: facebook/dinov2-large
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: Joseph-large-2024_09_16-batch-size32_epochs150_freeze
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# Joseph-large-2024_09_16-batch-size32_epochs150_freeze
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [facebook/dinov2-large](https://huggingface.co/facebook/dinov2-large) on the None dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.1207
|
| 22 |
+
- F1 Micro: 0.8214
|
| 23 |
+
- F1 Macro: 0.7191
|
| 24 |
+
- Roc Auc: 0.8814
|
| 25 |
+
- Accuracy: 0.3118
|
| 26 |
+
- Learning Rate: 0.0000
|
| 27 |
+
|
| 28 |
+
## Model description
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Intended uses & limitations
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training and evaluation data
|
| 37 |
+
|
| 38 |
+
More information needed
|
| 39 |
+
|
| 40 |
+
## Training procedure
|
| 41 |
+
|
| 42 |
+
### Training hyperparameters
|
| 43 |
+
|
| 44 |
+
The following hyperparameters were used during training:
|
| 45 |
+
- learning_rate: 0.001
|
| 46 |
+
- train_batch_size: 32
|
| 47 |
+
- eval_batch_size: 32
|
| 48 |
+
- seed: 42
|
| 49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
+
- lr_scheduler_type: linear
|
| 51 |
+
- num_epochs: 150
|
| 52 |
+
- mixed_precision_training: Native AMP
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 Micro | F1 Macro | Roc Auc | Accuracy | Rate |
|
| 57 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|:-------:|:--------:|:------:|
|
| 58 |
+
| No log | 1.0 | 273 | 0.1776 | 0.7478 | 0.5385 | 0.8364 | 0.2166 | 0.001 |
|
| 59 |
+
| 0.2726 | 2.0 | 546 | 0.1539 | 0.7697 | 0.5761 | 0.8448 | 0.2453 | 0.001 |
|
| 60 |
+
| 0.2726 | 3.0 | 819 | 0.1474 | 0.7745 | 0.6098 | 0.8447 | 0.2516 | 0.001 |
|
| 61 |
+
| 0.1701 | 4.0 | 1092 | 0.1465 | 0.7739 | 0.6214 | 0.8440 | 0.2536 | 0.001 |
|
| 62 |
+
| 0.1701 | 5.0 | 1365 | 0.1452 | 0.7815 | 0.6353 | 0.8503 | 0.2502 | 0.001 |
|
| 63 |
+
| 0.1622 | 6.0 | 1638 | 0.1446 | 0.7813 | 0.6142 | 0.8479 | 0.2578 | 0.001 |
|
| 64 |
+
| 0.1622 | 7.0 | 1911 | 0.1445 | 0.7801 | 0.6233 | 0.8500 | 0.2620 | 0.001 |
|
| 65 |
+
| 0.159 | 8.0 | 2184 | 0.1437 | 0.7879 | 0.6339 | 0.8585 | 0.2585 | 0.001 |
|
| 66 |
+
| 0.159 | 9.0 | 2457 | 0.1447 | 0.7855 | 0.6443 | 0.8548 | 0.2578 | 0.001 |
|
| 67 |
+
| 0.1563 | 10.0 | 2730 | 0.1539 | 0.7683 | 0.6149 | 0.8341 | 0.2443 | 0.001 |
|
| 68 |
+
| 0.1558 | 11.0 | 3003 | 0.1389 | 0.7897 | 0.6335 | 0.8561 | 0.2633 | 0.001 |
|
| 69 |
+
| 0.1558 | 12.0 | 3276 | 0.1395 | 0.7908 | 0.6406 | 0.8586 | 0.2640 | 0.001 |
|
| 70 |
+
| 0.155 | 13.0 | 3549 | 0.1390 | 0.7894 | 0.6557 | 0.8535 | 0.2651 | 0.001 |
|
| 71 |
+
| 0.155 | 14.0 | 3822 | 0.1391 | 0.7878 | 0.6405 | 0.8540 | 0.2623 | 0.001 |
|
| 72 |
+
| 0.154 | 15.0 | 4095 | 0.1399 | 0.7885 | 0.6406 | 0.8550 | 0.2540 | 0.001 |
|
| 73 |
+
| 0.154 | 16.0 | 4368 | 0.1394 | 0.7848 | 0.6375 | 0.8490 | 0.2668 | 0.001 |
|
| 74 |
+
| 0.1527 | 17.0 | 4641 | 0.1594 | 0.7857 | 0.6425 | 0.8640 | 0.2419 | 0.001 |
|
| 75 |
+
| 0.1527 | 18.0 | 4914 | 0.1319 | 0.8037 | 0.6768 | 0.8679 | 0.2755 | 0.0001 |
|
| 76 |
+
| 0.149 | 19.0 | 5187 | 0.1324 | 0.8038 | 0.6715 | 0.8680 | 0.2789 | 0.0001 |
|
| 77 |
+
| 0.149 | 20.0 | 5460 | 0.1306 | 0.8066 | 0.6734 | 0.8722 | 0.2789 | 0.0001 |
|
| 78 |
+
| 0.1412 | 21.0 | 5733 | 0.1303 | 0.8037 | 0.6728 | 0.8651 | 0.2817 | 0.0001 |
|
| 79 |
+
| 0.1385 | 22.0 | 6006 | 0.1287 | 0.8074 | 0.6735 | 0.8697 | 0.2841 | 0.0001 |
|
| 80 |
+
| 0.1385 | 23.0 | 6279 | 0.1287 | 0.8058 | 0.6785 | 0.8654 | 0.2841 | 0.0001 |
|
| 81 |
+
| 0.1377 | 24.0 | 6552 | 0.1280 | 0.8058 | 0.6841 | 0.8663 | 0.2869 | 0.0001 |
|
| 82 |
+
| 0.1377 | 25.0 | 6825 | 0.1274 | 0.8074 | 0.6787 | 0.8696 | 0.2859 | 0.0001 |
|
| 83 |
+
| 0.1361 | 26.0 | 7098 | 0.1283 | 0.8064 | 0.6740 | 0.8673 | 0.2859 | 0.0001 |
|
| 84 |
+
| 0.1361 | 27.0 | 7371 | 0.1268 | 0.8110 | 0.6890 | 0.8744 | 0.2883 | 0.0001 |
|
| 85 |
+
| 0.1354 | 28.0 | 7644 | 0.1267 | 0.8100 | 0.6813 | 0.8708 | 0.2893 | 0.0001 |
|
| 86 |
+
| 0.1354 | 29.0 | 7917 | 0.1268 | 0.8081 | 0.6881 | 0.8667 | 0.2918 | 0.0001 |
|
| 87 |
+
| 0.1339 | 30.0 | 8190 | 0.1264 | 0.8109 | 0.6873 | 0.8701 | 0.2928 | 0.0001 |
|
| 88 |
+
| 0.1339 | 31.0 | 8463 | 0.1258 | 0.8089 | 0.6824 | 0.8674 | 0.2914 | 0.0001 |
|
| 89 |
+
| 0.1332 | 32.0 | 8736 | 0.1260 | 0.8113 | 0.6924 | 0.8731 | 0.2931 | 0.0001 |
|
| 90 |
+
| 0.1321 | 33.0 | 9009 | 0.1250 | 0.8133 | 0.6960 | 0.8736 | 0.2911 | 0.0001 |
|
| 91 |
+
| 0.1321 | 34.0 | 9282 | 0.1251 | 0.8116 | 0.6891 | 0.8708 | 0.2942 | 0.0001 |
|
| 92 |
+
| 0.1309 | 35.0 | 9555 | 0.1249 | 0.8124 | 0.6945 | 0.8724 | 0.2956 | 0.0001 |
|
| 93 |
+
| 0.1309 | 36.0 | 9828 | 0.1253 | 0.8115 | 0.6971 | 0.8688 | 0.2942 | 0.0001 |
|
| 94 |
+
| 0.1305 | 37.0 | 10101 | 0.1248 | 0.8116 | 0.6961 | 0.8702 | 0.2952 | 0.0001 |
|
| 95 |
+
| 0.1305 | 38.0 | 10374 | 0.1250 | 0.8130 | 0.6991 | 0.8726 | 0.3004 | 0.0001 |
|
| 96 |
+
| 0.1285 | 39.0 | 10647 | 0.1252 | 0.8142 | 0.6971 | 0.8768 | 0.2952 | 0.0001 |
|
| 97 |
+
| 0.1285 | 40.0 | 10920 | 0.1249 | 0.8167 | 0.7070 | 0.8790 | 0.2956 | 0.0001 |
|
| 98 |
+
| 0.129 | 41.0 | 11193 | 0.1250 | 0.8104 | 0.6962 | 0.8684 | 0.2897 | 0.0001 |
|
| 99 |
+
| 0.129 | 42.0 | 11466 | 0.1235 | 0.8165 | 0.7064 | 0.8763 | 0.3039 | 0.0001 |
|
| 100 |
+
| 0.1277 | 43.0 | 11739 | 0.1237 | 0.8150 | 0.7047 | 0.8771 | 0.2956 | 0.0001 |
|
| 101 |
+
| 0.1279 | 44.0 | 12012 | 0.1237 | 0.8170 | 0.7054 | 0.8789 | 0.3008 | 0.0001 |
|
| 102 |
+
| 0.1279 | 45.0 | 12285 | 0.1233 | 0.8163 | 0.7058 | 0.8758 | 0.3015 | 0.0001 |
|
| 103 |
+
| 0.1264 | 46.0 | 12558 | 0.1230 | 0.8159 | 0.6993 | 0.8746 | 0.3008 | 0.0001 |
|
| 104 |
+
| 0.1264 | 47.0 | 12831 | 0.1237 | 0.8135 | 0.7026 | 0.8720 | 0.2990 | 0.0001 |
|
| 105 |
+
| 0.1267 | 48.0 | 13104 | 0.1233 | 0.8169 | 0.7044 | 0.8757 | 0.3018 | 0.0001 |
|
| 106 |
+
| 0.1267 | 49.0 | 13377 | 0.1232 | 0.8161 | 0.7050 | 0.8762 | 0.3021 | 0.0001 |
|
| 107 |
+
| 0.1249 | 50.0 | 13650 | 0.1227 | 0.8180 | 0.7086 | 0.8775 | 0.3015 | 0.0001 |
|
| 108 |
+
| 0.1249 | 51.0 | 13923 | 0.1231 | 0.8190 | 0.7108 | 0.8794 | 0.3021 | 0.0001 |
|
| 109 |
+
| 0.1243 | 52.0 | 14196 | 0.1228 | 0.8164 | 0.7041 | 0.8743 | 0.3021 | 0.0001 |
|
| 110 |
+
| 0.1243 | 53.0 | 14469 | 0.1225 | 0.8189 | 0.7080 | 0.8794 | 0.3039 | 0.0001 |
|
| 111 |
+
| 0.1248 | 54.0 | 14742 | 0.1238 | 0.8163 | 0.7054 | 0.8755 | 0.3018 | 0.0001 |
|
| 112 |
+
| 0.1233 | 55.0 | 15015 | 0.1221 | 0.8181 | 0.7093 | 0.8772 | 0.3028 | 0.0001 |
|
| 113 |
+
| 0.1233 | 56.0 | 15288 | 0.1226 | 0.8188 | 0.7092 | 0.8809 | 0.3049 | 0.0001 |
|
| 114 |
+
| 0.1237 | 57.0 | 15561 | 0.1223 | 0.8184 | 0.7056 | 0.8785 | 0.3053 | 0.0001 |
|
| 115 |
+
| 0.1237 | 58.0 | 15834 | 0.1223 | 0.8180 | 0.7094 | 0.8765 | 0.3028 | 0.0001 |
|
| 116 |
+
| 0.1234 | 59.0 | 16107 | 0.1223 | 0.8198 | 0.7102 | 0.8789 | 0.3073 | 0.0001 |
|
| 117 |
+
| 0.1234 | 60.0 | 16380 | 0.1237 | 0.8173 | 0.7068 | 0.8762 | 0.2980 | 0.0001 |
|
| 118 |
+
| 0.1232 | 61.0 | 16653 | 0.1224 | 0.8201 | 0.7139 | 0.8791 | 0.3060 | 0.0001 |
|
| 119 |
+
| 0.1232 | 62.0 | 16926 | 0.1222 | 0.8209 | 0.7189 | 0.8808 | 0.3028 | 1e-05 |
|
| 120 |
+
| 0.1204 | 63.0 | 17199 | 0.1208 | 0.8208 | 0.7191 | 0.8797 | 0.3098 | 1e-05 |
|
| 121 |
+
| 0.1204 | 64.0 | 17472 | 0.1209 | 0.8218 | 0.7188 | 0.8813 | 0.3108 | 1e-05 |
|
| 122 |
+
| 0.12 | 65.0 | 17745 | 0.1209 | 0.8210 | 0.7187 | 0.8787 | 0.3080 | 1e-05 |
|
| 123 |
+
| 0.1187 | 66.0 | 18018 | 0.1208 | 0.8216 | 0.7186 | 0.8805 | 0.3136 | 1e-05 |
|
| 124 |
+
| 0.1187 | 67.0 | 18291 | 0.1210 | 0.8232 | 0.7239 | 0.8848 | 0.3112 | 1e-05 |
|
| 125 |
+
| 0.1179 | 68.0 | 18564 | 0.1208 | 0.8212 | 0.7201 | 0.8815 | 0.3125 | 1e-05 |
|
| 126 |
+
| 0.1179 | 69.0 | 18837 | 0.1211 | 0.8210 | 0.7198 | 0.8795 | 0.3101 | 1e-05 |
|
| 127 |
+
| 0.1177 | 70.0 | 19110 | 0.1211 | 0.8213 | 0.7197 | 0.8802 | 0.3112 | 1e-05 |
|
| 128 |
+
| 0.1177 | 71.0 | 19383 | 0.1206 | 0.8206 | 0.7164 | 0.8780 | 0.3112 | 1e-05 |
|
| 129 |
+
| 0.1179 | 72.0 | 19656 | 0.1208 | 0.8206 | 0.7172 | 0.8783 | 0.3129 | 1e-05 |
|
| 130 |
+
| 0.1179 | 73.0 | 19929 | 0.1208 | 0.8217 | 0.7214 | 0.8804 | 0.3132 | 1e-05 |
|
| 131 |
+
| 0.1177 | 74.0 | 20202 | 0.1209 | 0.8201 | 0.7155 | 0.8760 | 0.3108 | 1e-05 |
|
| 132 |
+
| 0.1177 | 75.0 | 20475 | 0.1205 | 0.8207 | 0.7151 | 0.8790 | 0.3153 | 1e-05 |
|
| 133 |
+
| 0.1171 | 76.0 | 20748 | 0.1203 | 0.8221 | 0.7224 | 0.8820 | 0.3157 | 1e-05 |
|
| 134 |
+
| 0.1171 | 77.0 | 21021 | 0.1208 | 0.8232 | 0.7234 | 0.8851 | 0.3136 | 1e-05 |
|
| 135 |
+
| 0.1171 | 78.0 | 21294 | 0.1210 | 0.8230 | 0.7233 | 0.8837 | 0.3115 | 1e-05 |
|
| 136 |
+
| 0.1168 | 79.0 | 21567 | 0.1205 | 0.8202 | 0.7173 | 0.8777 | 0.3101 | 1e-05 |
|
| 137 |
+
| 0.1168 | 80.0 | 21840 | 0.1207 | 0.8232 | 0.7249 | 0.8843 | 0.3119 | 1e-05 |
|
| 138 |
+
| 0.1171 | 81.0 | 22113 | 0.1203 | 0.8221 | 0.7213 | 0.8806 | 0.3129 | 1e-05 |
|
| 139 |
+
| 0.1171 | 82.0 | 22386 | 0.1205 | 0.8215 | 0.7178 | 0.8796 | 0.3143 | 1e-05 |
|
| 140 |
+
| 0.1157 | 83.0 | 22659 | 0.1214 | 0.8180 | 0.7113 | 0.8743 | 0.3112 | 0.0000 |
|
| 141 |
+
| 0.1157 | 84.0 | 22932 | 0.1204 | 0.8234 | 0.7251 | 0.8827 | 0.3115 | 0.0000 |
|
| 142 |
+
| 0.1169 | 85.0 | 23205 | 0.1204 | 0.8230 | 0.7213 | 0.8832 | 0.3132 | 0.0000 |
|
| 143 |
+
| 0.1169 | 86.0 | 23478 | 0.1225 | 0.8196 | 0.7218 | 0.8800 | 0.3077 | 0.0000 |
|
| 144 |
+
| 0.1157 | 87.0 | 23751 | 0.1208 | 0.8204 | 0.7152 | 0.8789 | 0.3091 | 0.0000 |
|
| 145 |
+
| 0.1156 | 88.0 | 24024 | 0.1209 | 0.8215 | 0.7168 | 0.8824 | 0.3084 | 0.0000 |
|
| 146 |
+
| 0.1156 | 89.0 | 24297 | 0.1211 | 0.8245 | 0.7340 | 0.8875 | 0.3164 | 0.0000 |
|
| 147 |
+
| 0.1157 | 90.0 | 24570 | 0.1209 | 0.8232 | 0.7246 | 0.8861 | 0.3119 | 0.0000 |
|
| 148 |
+
| 0.1157 | 91.0 | 24843 | 0.1204 | 0.8201 | 0.7163 | 0.8785 | 0.3115 | 0.0000 |
|
| 149 |
+
|
| 150 |
+
|
| 151 |
+
### Framework versions
|
| 152 |
+
|
| 153 |
+
- Transformers 4.44.2
|
| 154 |
+
- Pytorch 2.4.1+cu121
|
| 155 |
+
- Datasets 3.0.0
|
| 156 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 91.0,
|
| 3 |
+
"eval_accuracy": 0.31176470588235294,
|
| 4 |
+
"eval_f1_macro": 0.7191048917769186,
|
| 5 |
+
"eval_f1_micro": 0.8213660245183888,
|
| 6 |
+
"eval_loss": 0.12070130556821823,
|
| 7 |
+
"eval_roc_auc": 0.8813715838939836,
|
| 8 |
+
"eval_runtime": 622.9062,
|
| 9 |
+
"eval_samples_per_second": 4.64,
|
| 10 |
+
"eval_steps_per_second": 0.146,
|
| 11 |
+
"learning_rate": 1.0000000000000002e-07,
|
| 12 |
+
"total_flos": 1.1760993126572918e+21,
|
| 13 |
+
"train_loss": 0.13338198287712655,
|
| 14 |
+
"train_runtime": 215448.2605,
|
| 15 |
+
"train_samples_per_second": 6.068,
|
| 16 |
+
"train_steps_per_second": 0.19
|
| 17 |
+
}
|
logs/events.out.tfevents.1726457760.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 sha256:4d8b7d3b0f4425d59322d6d14c8e7c09cb39b750b250d514e97eba603d43506c
|
| 3 |
+
size 67047
|
logs/events.out.tfevents.1726673937.datavisu2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f09697f570b60dfc8a1535d8cec2ea951880b09a0aab1caabeedda46d7eb595d
|
| 3 |
+
size 40
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1228107508
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d32a89c0262992772590dfc54c36158856e1f2c72726a9ec7d709b2dcab20476
|
| 3 |
size 1228107508
|
test_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 91.0,
|
| 3 |
+
"eval_accuracy": 0.31176470588235294,
|
| 4 |
+
"eval_f1_macro": 0.7191048917769186,
|
| 5 |
+
"eval_f1_micro": 0.8213660245183888,
|
| 6 |
+
"eval_loss": 0.12070130556821823,
|
| 7 |
+
"eval_roc_auc": 0.8813715838939836,
|
| 8 |
+
"eval_runtime": 622.9062,
|
| 9 |
+
"eval_samples_per_second": 4.64,
|
| 10 |
+
"eval_steps_per_second": 0.146,
|
| 11 |
+
"learning_rate": 1.0000000000000002e-07
|
| 12 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 91.0,
|
| 3 |
+
"learning_rate": 1.0000000000000002e-07,
|
| 4 |
+
"total_flos": 1.1760993126572918e+21,
|
| 5 |
+
"train_loss": 0.13338198287712655,
|
| 6 |
+
"train_runtime": 215448.2605,
|
| 7 |
+
"train_samples_per_second": 6.068,
|
| 8 |
+
"train_steps_per_second": 0.19
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1578 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.12031927704811096,
|
| 3 |
+
"best_model_checkpoint": "Joseph-large-2024_09_16-batch-size32_epochs150_freeze/checkpoint-22113",
|
| 4 |
+
"epoch": 91.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 24843,
|
| 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": 0.21656271656271656,
|
| 14 |
+
"eval_f1_macro": 0.5384503258991854,
|
| 15 |
+
"eval_f1_micro": 0.7477812526413659,
|
| 16 |
+
"eval_loss": 0.17758780717849731,
|
| 17 |
+
"eval_roc_auc": 0.8364480125638629,
|
| 18 |
+
"eval_runtime": 594.1704,
|
| 19 |
+
"eval_samples_per_second": 4.857,
|
| 20 |
+
"eval_steps_per_second": 0.153,
|
| 21 |
+
"learning_rate": 0.001,
|
| 22 |
+
"step": 273
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 1.8315018315018317,
|
| 26 |
+
"grad_norm": 0.2863590717315674,
|
| 27 |
+
"learning_rate": 0.001,
|
| 28 |
+
"loss": 0.2726,
|
| 29 |
+
"step": 500
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 2.0,
|
| 33 |
+
"eval_accuracy": 0.24532224532224534,
|
| 34 |
+
"eval_f1_macro": 0.5760774961516321,
|
| 35 |
+
"eval_f1_micro": 0.7697450182129848,
|
| 36 |
+
"eval_loss": 0.153945192694664,
|
| 37 |
+
"eval_roc_auc": 0.8447603712499155,
|
| 38 |
+
"eval_runtime": 583.9253,
|
| 39 |
+
"eval_samples_per_second": 4.942,
|
| 40 |
+
"eval_steps_per_second": 0.156,
|
| 41 |
+
"learning_rate": 0.001,
|
| 42 |
+
"step": 546
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 3.0,
|
| 46 |
+
"eval_accuracy": 0.2515592515592516,
|
| 47 |
+
"eval_f1_macro": 0.6098114408992151,
|
| 48 |
+
"eval_f1_micro": 0.7744839226208509,
|
| 49 |
+
"eval_loss": 0.14735348522663116,
|
| 50 |
+
"eval_roc_auc": 0.8447204921454395,
|
| 51 |
+
"eval_runtime": 592.1092,
|
| 52 |
+
"eval_samples_per_second": 4.874,
|
| 53 |
+
"eval_steps_per_second": 0.154,
|
| 54 |
+
"learning_rate": 0.001,
|
| 55 |
+
"step": 819
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 3.663003663003663,
|
| 59 |
+
"grad_norm": 0.24709707498550415,
|
| 60 |
+
"learning_rate": 0.001,
|
| 61 |
+
"loss": 0.1701,
|
| 62 |
+
"step": 1000
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 4.0,
|
| 66 |
+
"eval_accuracy": 0.25363825363825365,
|
| 67 |
+
"eval_f1_macro": 0.6213514572326843,
|
| 68 |
+
"eval_f1_micro": 0.7738915615654661,
|
| 69 |
+
"eval_loss": 0.14645476639270782,
|
| 70 |
+
"eval_roc_auc": 0.8440185501551167,
|
| 71 |
+
"eval_runtime": 589.7047,
|
| 72 |
+
"eval_samples_per_second": 4.894,
|
| 73 |
+
"eval_steps_per_second": 0.154,
|
| 74 |
+
"learning_rate": 0.001,
|
| 75 |
+
"step": 1092
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 5.0,
|
| 79 |
+
"eval_accuracy": 0.25017325017325015,
|
| 80 |
+
"eval_f1_macro": 0.6353051230272125,
|
| 81 |
+
"eval_f1_micro": 0.78146492434663,
|
| 82 |
+
"eval_loss": 0.14515458047389984,
|
| 83 |
+
"eval_roc_auc": 0.850253359073442,
|
| 84 |
+
"eval_runtime": 596.3244,
|
| 85 |
+
"eval_samples_per_second": 4.84,
|
| 86 |
+
"eval_steps_per_second": 0.153,
|
| 87 |
+
"learning_rate": 0.001,
|
| 88 |
+
"step": 1365
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 5.4945054945054945,
|
| 92 |
+
"grad_norm": 0.24183644354343414,
|
| 93 |
+
"learning_rate": 0.001,
|
| 94 |
+
"loss": 0.1622,
|
| 95 |
+
"step": 1500
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 6.0,
|
| 99 |
+
"eval_accuracy": 0.2577962577962578,
|
| 100 |
+
"eval_f1_macro": 0.6141782571643486,
|
| 101 |
+
"eval_f1_micro": 0.781259480778399,
|
| 102 |
+
"eval_loss": 0.1445809006690979,
|
| 103 |
+
"eval_roc_auc": 0.8479418733548026,
|
| 104 |
+
"eval_runtime": 590.8762,
|
| 105 |
+
"eval_samples_per_second": 4.884,
|
| 106 |
+
"eval_steps_per_second": 0.154,
|
| 107 |
+
"learning_rate": 0.001,
|
| 108 |
+
"step": 1638
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 7.0,
|
| 112 |
+
"eval_accuracy": 0.26195426195426197,
|
| 113 |
+
"eval_f1_macro": 0.6232727577909734,
|
| 114 |
+
"eval_f1_micro": 0.7800943800943801,
|
| 115 |
+
"eval_loss": 0.14445114135742188,
|
| 116 |
+
"eval_roc_auc": 0.8500464116049401,
|
| 117 |
+
"eval_runtime": 601.2858,
|
| 118 |
+
"eval_samples_per_second": 4.8,
|
| 119 |
+
"eval_steps_per_second": 0.151,
|
| 120 |
+
"learning_rate": 0.001,
|
| 121 |
+
"step": 1911
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 7.326007326007326,
|
| 125 |
+
"grad_norm": 0.2069859653711319,
|
| 126 |
+
"learning_rate": 0.001,
|
| 127 |
+
"loss": 0.159,
|
| 128 |
+
"step": 2000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 8.0,
|
| 132 |
+
"eval_accuracy": 0.25848925848925847,
|
| 133 |
+
"eval_f1_macro": 0.6339480584029394,
|
| 134 |
+
"eval_f1_micro": 0.7879197465681098,
|
| 135 |
+
"eval_loss": 0.14366209506988525,
|
| 136 |
+
"eval_roc_auc": 0.8585186757078976,
|
| 137 |
+
"eval_runtime": 584.2361,
|
| 138 |
+
"eval_samples_per_second": 4.94,
|
| 139 |
+
"eval_steps_per_second": 0.156,
|
| 140 |
+
"learning_rate": 0.001,
|
| 141 |
+
"step": 2184
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 9.0,
|
| 145 |
+
"eval_accuracy": 0.2577962577962578,
|
| 146 |
+
"eval_f1_macro": 0.6442804243684905,
|
| 147 |
+
"eval_f1_micro": 0.785476860138072,
|
| 148 |
+
"eval_loss": 0.1447097659111023,
|
| 149 |
+
"eval_roc_auc": 0.8547549628224266,
|
| 150 |
+
"eval_runtime": 597.754,
|
| 151 |
+
"eval_samples_per_second": 4.828,
|
| 152 |
+
"eval_steps_per_second": 0.152,
|
| 153 |
+
"learning_rate": 0.001,
|
| 154 |
+
"step": 2457
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 9.157509157509157,
|
| 158 |
+
"grad_norm": 0.2012098729610443,
|
| 159 |
+
"learning_rate": 0.001,
|
| 160 |
+
"loss": 0.1563,
|
| 161 |
+
"step": 2500
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 10.0,
|
| 165 |
+
"eval_accuracy": 0.2442827442827443,
|
| 166 |
+
"eval_f1_macro": 0.6149084687726756,
|
| 167 |
+
"eval_f1_micro": 0.7683399403144626,
|
| 168 |
+
"eval_loss": 0.1538563072681427,
|
| 169 |
+
"eval_roc_auc": 0.8340795854397406,
|
| 170 |
+
"eval_runtime": 582.8083,
|
| 171 |
+
"eval_samples_per_second": 4.952,
|
| 172 |
+
"eval_steps_per_second": 0.156,
|
| 173 |
+
"learning_rate": 0.001,
|
| 174 |
+
"step": 2730
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 10.989010989010989,
|
| 178 |
+
"grad_norm": 0.1713365614414215,
|
| 179 |
+
"learning_rate": 0.001,
|
| 180 |
+
"loss": 0.1558,
|
| 181 |
+
"step": 3000
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 11.0,
|
| 185 |
+
"eval_accuracy": 0.26334026334026334,
|
| 186 |
+
"eval_f1_macro": 0.6334773464226039,
|
| 187 |
+
"eval_f1_micro": 0.7896514859952961,
|
| 188 |
+
"eval_loss": 0.1389196366071701,
|
| 189 |
+
"eval_roc_auc": 0.8560665869710553,
|
| 190 |
+
"eval_runtime": 581.0367,
|
| 191 |
+
"eval_samples_per_second": 4.967,
|
| 192 |
+
"eval_steps_per_second": 0.157,
|
| 193 |
+
"learning_rate": 0.001,
|
| 194 |
+
"step": 3003
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 12.0,
|
| 198 |
+
"eval_accuracy": 0.26403326403326405,
|
| 199 |
+
"eval_f1_macro": 0.6406158966836866,
|
| 200 |
+
"eval_f1_micro": 0.7908438442264407,
|
| 201 |
+
"eval_loss": 0.1395249217748642,
|
| 202 |
+
"eval_roc_auc": 0.8586128939486779,
|
| 203 |
+
"eval_runtime": 577.8577,
|
| 204 |
+
"eval_samples_per_second": 4.994,
|
| 205 |
+
"eval_steps_per_second": 0.157,
|
| 206 |
+
"learning_rate": 0.001,
|
| 207 |
+
"step": 3276
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 12.820512820512821,
|
| 211 |
+
"grad_norm": 0.1511967033147812,
|
| 212 |
+
"learning_rate": 0.001,
|
| 213 |
+
"loss": 0.155,
|
| 214 |
+
"step": 3500
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 13.0,
|
| 218 |
+
"eval_accuracy": 0.26507276507276506,
|
| 219 |
+
"eval_f1_macro": 0.6557265830014797,
|
| 220 |
+
"eval_f1_micro": 0.7893533497260687,
|
| 221 |
+
"eval_loss": 0.1390257179737091,
|
| 222 |
+
"eval_roc_auc": 0.8535165777960444,
|
| 223 |
+
"eval_runtime": 583.6052,
|
| 224 |
+
"eval_samples_per_second": 4.945,
|
| 225 |
+
"eval_steps_per_second": 0.156,
|
| 226 |
+
"learning_rate": 0.001,
|
| 227 |
+
"step": 3549
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 14.0,
|
| 231 |
+
"eval_accuracy": 0.2623007623007623,
|
| 232 |
+
"eval_f1_macro": 0.640540413256037,
|
| 233 |
+
"eval_f1_micro": 0.787792943600309,
|
| 234 |
+
"eval_loss": 0.13910652697086334,
|
| 235 |
+
"eval_roc_auc": 0.8540478028799876,
|
| 236 |
+
"eval_runtime": 575.9469,
|
| 237 |
+
"eval_samples_per_second": 5.011,
|
| 238 |
+
"eval_steps_per_second": 0.158,
|
| 239 |
+
"learning_rate": 0.001,
|
| 240 |
+
"step": 3822
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 14.652014652014651,
|
| 244 |
+
"grad_norm": 0.17730183899402618,
|
| 245 |
+
"learning_rate": 0.001,
|
| 246 |
+
"loss": 0.154,
|
| 247 |
+
"step": 4000
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 15.0,
|
| 251 |
+
"eval_accuracy": 0.253984753984754,
|
| 252 |
+
"eval_f1_macro": 0.6406412255611948,
|
| 253 |
+
"eval_f1_micro": 0.7885381419454319,
|
| 254 |
+
"eval_loss": 0.13990363478660583,
|
| 255 |
+
"eval_roc_auc": 0.8550214137243141,
|
| 256 |
+
"eval_runtime": 589.3337,
|
| 257 |
+
"eval_samples_per_second": 4.897,
|
| 258 |
+
"eval_steps_per_second": 0.154,
|
| 259 |
+
"learning_rate": 0.001,
|
| 260 |
+
"step": 4095
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 16.0,
|
| 264 |
+
"eval_accuracy": 0.2668052668052668,
|
| 265 |
+
"eval_f1_macro": 0.6374513053376879,
|
| 266 |
+
"eval_f1_micro": 0.7847859161051945,
|
| 267 |
+
"eval_loss": 0.13938209414482117,
|
| 268 |
+
"eval_roc_auc": 0.8490304535245456,
|
| 269 |
+
"eval_runtime": 577.6041,
|
| 270 |
+
"eval_samples_per_second": 4.997,
|
| 271 |
+
"eval_steps_per_second": 0.158,
|
| 272 |
+
"learning_rate": 0.001,
|
| 273 |
+
"step": 4368
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 16.483516483516482,
|
| 277 |
+
"grad_norm": 0.16627363860607147,
|
| 278 |
+
"learning_rate": 0.001,
|
| 279 |
+
"loss": 0.1527,
|
| 280 |
+
"step": 4500
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 17.0,
|
| 284 |
+
"eval_accuracy": 0.24185724185724186,
|
| 285 |
+
"eval_f1_macro": 0.6424904129432089,
|
| 286 |
+
"eval_f1_micro": 0.7857319587628866,
|
| 287 |
+
"eval_loss": 0.15936270356178284,
|
| 288 |
+
"eval_roc_auc": 0.8640092624686252,
|
| 289 |
+
"eval_runtime": 582.0471,
|
| 290 |
+
"eval_samples_per_second": 4.958,
|
| 291 |
+
"eval_steps_per_second": 0.156,
|
| 292 |
+
"learning_rate": 0.001,
|
| 293 |
+
"step": 4641
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 18.0,
|
| 297 |
+
"eval_accuracy": 0.27546777546777546,
|
| 298 |
+
"eval_f1_macro": 0.6768028620378452,
|
| 299 |
+
"eval_f1_micro": 0.8036556603773585,
|
| 300 |
+
"eval_loss": 0.13188092410564423,
|
| 301 |
+
"eval_roc_auc": 0.8679473273890709,
|
| 302 |
+
"eval_runtime": 578.2193,
|
| 303 |
+
"eval_samples_per_second": 4.991,
|
| 304 |
+
"eval_steps_per_second": 0.157,
|
| 305 |
+
"learning_rate": 0.0001,
|
| 306 |
+
"step": 4914
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 18.315018315018314,
|
| 310 |
+
"grad_norm": 0.17489519715309143,
|
| 311 |
+
"learning_rate": 0.0001,
|
| 312 |
+
"loss": 0.149,
|
| 313 |
+
"step": 5000
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 19.0,
|
| 317 |
+
"eval_accuracy": 0.27893277893277896,
|
| 318 |
+
"eval_f1_macro": 0.6715138701269487,
|
| 319 |
+
"eval_f1_micro": 0.8038422649140546,
|
| 320 |
+
"eval_loss": 0.13244545459747314,
|
| 321 |
+
"eval_roc_auc": 0.8679532160291196,
|
| 322 |
+
"eval_runtime": 573.231,
|
| 323 |
+
"eval_samples_per_second": 5.035,
|
| 324 |
+
"eval_steps_per_second": 0.159,
|
| 325 |
+
"learning_rate": 0.0001,
|
| 326 |
+
"step": 5187
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 20.0,
|
| 330 |
+
"eval_accuracy": 0.27893277893277896,
|
| 331 |
+
"eval_f1_macro": 0.6733647561041333,
|
| 332 |
+
"eval_f1_micro": 0.8066104665720725,
|
| 333 |
+
"eval_loss": 0.1306440383195877,
|
| 334 |
+
"eval_roc_auc": 0.8722063701403293,
|
| 335 |
+
"eval_runtime": 585.8615,
|
| 336 |
+
"eval_samples_per_second": 4.926,
|
| 337 |
+
"eval_steps_per_second": 0.155,
|
| 338 |
+
"learning_rate": 0.0001,
|
| 339 |
+
"step": 5460
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 20.146520146520146,
|
| 343 |
+
"grad_norm": 0.15949666500091553,
|
| 344 |
+
"learning_rate": 0.0001,
|
| 345 |
+
"loss": 0.1412,
|
| 346 |
+
"step": 5500
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 21.0,
|
| 350 |
+
"eval_accuracy": 0.2817047817047817,
|
| 351 |
+
"eval_f1_macro": 0.6728395801753237,
|
| 352 |
+
"eval_f1_micro": 0.8037271837637748,
|
| 353 |
+
"eval_loss": 0.1302667111158371,
|
| 354 |
+
"eval_roc_auc": 0.8650841471907833,
|
| 355 |
+
"eval_runtime": 573.2529,
|
| 356 |
+
"eval_samples_per_second": 5.034,
|
| 357 |
+
"eval_steps_per_second": 0.159,
|
| 358 |
+
"learning_rate": 0.0001,
|
| 359 |
+
"step": 5733
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 21.978021978021978,
|
| 363 |
+
"grad_norm": 0.1902228742837906,
|
| 364 |
+
"learning_rate": 0.0001,
|
| 365 |
+
"loss": 0.1385,
|
| 366 |
+
"step": 6000
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 22.0,
|
| 370 |
+
"eval_accuracy": 0.2841302841302841,
|
| 371 |
+
"eval_f1_macro": 0.6735047356746011,
|
| 372 |
+
"eval_f1_micro": 0.8074214632089395,
|
| 373 |
+
"eval_loss": 0.12870918214321136,
|
| 374 |
+
"eval_roc_auc": 0.869659164440877,
|
| 375 |
+
"eval_runtime": 581.2149,
|
| 376 |
+
"eval_samples_per_second": 4.965,
|
| 377 |
+
"eval_steps_per_second": 0.157,
|
| 378 |
+
"learning_rate": 0.0001,
|
| 379 |
+
"step": 6006
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 23.0,
|
| 383 |
+
"eval_accuracy": 0.2841302841302841,
|
| 384 |
+
"eval_f1_macro": 0.678520497542563,
|
| 385 |
+
"eval_f1_micro": 0.8058198574902932,
|
| 386 |
+
"eval_loss": 0.1287251114845276,
|
| 387 |
+
"eval_roc_auc": 0.8654212081182214,
|
| 388 |
+
"eval_runtime": 576.7801,
|
| 389 |
+
"eval_samples_per_second": 5.004,
|
| 390 |
+
"eval_steps_per_second": 0.158,
|
| 391 |
+
"learning_rate": 0.0001,
|
| 392 |
+
"step": 6279
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 23.80952380952381,
|
| 396 |
+
"grad_norm": 0.20738890767097473,
|
| 397 |
+
"learning_rate": 0.0001,
|
| 398 |
+
"loss": 0.1377,
|
| 399 |
+
"step": 6500
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 24.0,
|
| 403 |
+
"eval_accuracy": 0.2869022869022869,
|
| 404 |
+
"eval_f1_macro": 0.6840871439155845,
|
| 405 |
+
"eval_f1_micro": 0.8057504997660669,
|
| 406 |
+
"eval_loss": 0.1279863715171814,
|
| 407 |
+
"eval_roc_auc": 0.8662783338824032,
|
| 408 |
+
"eval_runtime": 580.6409,
|
| 409 |
+
"eval_samples_per_second": 4.97,
|
| 410 |
+
"eval_steps_per_second": 0.157,
|
| 411 |
+
"learning_rate": 0.0001,
|
| 412 |
+
"step": 6552
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 25.0,
|
| 416 |
+
"eval_accuracy": 0.28586278586278585,
|
| 417 |
+
"eval_f1_macro": 0.6787317976982782,
|
| 418 |
+
"eval_f1_micro": 0.8074392712550608,
|
| 419 |
+
"eval_loss": 0.127402663230896,
|
| 420 |
+
"eval_roc_auc": 0.8696325247161917,
|
| 421 |
+
"eval_runtime": 571.2341,
|
| 422 |
+
"eval_samples_per_second": 5.052,
|
| 423 |
+
"eval_steps_per_second": 0.159,
|
| 424 |
+
"learning_rate": 0.0001,
|
| 425 |
+
"step": 6825
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 25.641025641025642,
|
| 429 |
+
"grad_norm": 0.18043966591358185,
|
| 430 |
+
"learning_rate": 0.0001,
|
| 431 |
+
"loss": 0.1361,
|
| 432 |
+
"step": 7000
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 26.0,
|
| 436 |
+
"eval_accuracy": 0.28586278586278585,
|
| 437 |
+
"eval_f1_macro": 0.6740298841901063,
|
| 438 |
+
"eval_f1_micro": 0.8063818050664064,
|
| 439 |
+
"eval_loss": 0.12828372418880463,
|
| 440 |
+
"eval_roc_auc": 0.8672987185031534,
|
| 441 |
+
"eval_runtime": 580.3575,
|
| 442 |
+
"eval_samples_per_second": 4.973,
|
| 443 |
+
"eval_steps_per_second": 0.157,
|
| 444 |
+
"learning_rate": 0.0001,
|
| 445 |
+
"step": 7098
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 27.0,
|
| 449 |
+
"eval_accuracy": 0.2882882882882883,
|
| 450 |
+
"eval_f1_macro": 0.68897744745899,
|
| 451 |
+
"eval_f1_micro": 0.8110456615281781,
|
| 452 |
+
"eval_loss": 0.12681305408477783,
|
| 453 |
+
"eval_roc_auc": 0.8743537519356053,
|
| 454 |
+
"eval_runtime": 580.6984,
|
| 455 |
+
"eval_samples_per_second": 4.97,
|
| 456 |
+
"eval_steps_per_second": 0.157,
|
| 457 |
+
"learning_rate": 0.0001,
|
| 458 |
+
"step": 7371
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 27.47252747252747,
|
| 462 |
+
"grad_norm": 0.17303021252155304,
|
| 463 |
+
"learning_rate": 0.0001,
|
| 464 |
+
"loss": 0.1354,
|
| 465 |
+
"step": 7500
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 28.0,
|
| 469 |
+
"eval_accuracy": 0.28932778932778935,
|
| 470 |
+
"eval_f1_macro": 0.6812786729949134,
|
| 471 |
+
"eval_f1_micro": 0.8099940913311386,
|
| 472 |
+
"eval_loss": 0.12666279077529907,
|
| 473 |
+
"eval_roc_auc": 0.8708112319303257,
|
| 474 |
+
"eval_runtime": 576.4341,
|
| 475 |
+
"eval_samples_per_second": 5.007,
|
| 476 |
+
"eval_steps_per_second": 0.158,
|
| 477 |
+
"learning_rate": 0.0001,
|
| 478 |
+
"step": 7644
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 29.0,
|
| 482 |
+
"eval_accuracy": 0.29175329175329173,
|
| 483 |
+
"eval_f1_macro": 0.6881122302734826,
|
| 484 |
+
"eval_f1_micro": 0.8081058020477816,
|
| 485 |
+
"eval_loss": 0.12675043940544128,
|
| 486 |
+
"eval_roc_auc": 0.8666940799181009,
|
| 487 |
+
"eval_runtime": 578.6537,
|
| 488 |
+
"eval_samples_per_second": 4.987,
|
| 489 |
+
"eval_steps_per_second": 0.157,
|
| 490 |
+
"learning_rate": 0.0001,
|
| 491 |
+
"step": 7917
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 29.304029304029303,
|
| 495 |
+
"grad_norm": 0.17676015198230743,
|
| 496 |
+
"learning_rate": 0.0001,
|
| 497 |
+
"loss": 0.1339,
|
| 498 |
+
"step": 8000
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 30.0,
|
| 502 |
+
"eval_accuracy": 0.2927927927927928,
|
| 503 |
+
"eval_f1_macro": 0.6872571297964245,
|
| 504 |
+
"eval_f1_micro": 0.8108657880239013,
|
| 505 |
+
"eval_loss": 0.12635387480258942,
|
| 506 |
+
"eval_roc_auc": 0.8701037366439205,
|
| 507 |
+
"eval_runtime": 582.8932,
|
| 508 |
+
"eval_samples_per_second": 4.951,
|
| 509 |
+
"eval_steps_per_second": 0.156,
|
| 510 |
+
"learning_rate": 0.0001,
|
| 511 |
+
"step": 8190
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 31.0,
|
| 515 |
+
"eval_accuracy": 0.29140679140679143,
|
| 516 |
+
"eval_f1_macro": 0.6823767206574823,
|
| 517 |
+
"eval_f1_micro": 0.8089332139965051,
|
| 518 |
+
"eval_loss": 0.1258317530155182,
|
| 519 |
+
"eval_roc_auc": 0.867421427567313,
|
| 520 |
+
"eval_runtime": 578.6563,
|
| 521 |
+
"eval_samples_per_second": 4.987,
|
| 522 |
+
"eval_steps_per_second": 0.157,
|
| 523 |
+
"learning_rate": 0.0001,
|
| 524 |
+
"step": 8463
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 31.135531135531135,
|
| 528 |
+
"grad_norm": 0.19538064301013947,
|
| 529 |
+
"learning_rate": 0.0001,
|
| 530 |
+
"loss": 0.1332,
|
| 531 |
+
"step": 8500
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 32.0,
|
| 535 |
+
"eval_accuracy": 0.29313929313929316,
|
| 536 |
+
"eval_f1_macro": 0.6924178674344362,
|
| 537 |
+
"eval_f1_micro": 0.8112645318336341,
|
| 538 |
+
"eval_loss": 0.1260402798652649,
|
| 539 |
+
"eval_roc_auc": 0.8731307927316745,
|
| 540 |
+
"eval_runtime": 588.1542,
|
| 541 |
+
"eval_samples_per_second": 4.907,
|
| 542 |
+
"eval_steps_per_second": 0.155,
|
| 543 |
+
"learning_rate": 0.0001,
|
| 544 |
+
"step": 8736
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 32.967032967032964,
|
| 548 |
+
"grad_norm": 0.20809406042099,
|
| 549 |
+
"learning_rate": 0.0001,
|
| 550 |
+
"loss": 0.1321,
|
| 551 |
+
"step": 9000
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 33.0,
|
| 555 |
+
"eval_accuracy": 0.2910602910602911,
|
| 556 |
+
"eval_f1_macro": 0.6959916792345996,
|
| 557 |
+
"eval_f1_micro": 0.8133097762073027,
|
| 558 |
+
"eval_loss": 0.1250443458557129,
|
| 559 |
+
"eval_roc_auc": 0.8735809182308003,
|
| 560 |
+
"eval_runtime": 593.1758,
|
| 561 |
+
"eval_samples_per_second": 4.865,
|
| 562 |
+
"eval_steps_per_second": 0.153,
|
| 563 |
+
"learning_rate": 0.0001,
|
| 564 |
+
"step": 9009
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 34.0,
|
| 568 |
+
"eval_accuracy": 0.29417879417879417,
|
| 569 |
+
"eval_f1_macro": 0.6891130310994343,
|
| 570 |
+
"eval_f1_micro": 0.8116187492060803,
|
| 571 |
+
"eval_loss": 0.12511762976646423,
|
| 572 |
+
"eval_roc_auc": 0.8707582878249215,
|
| 573 |
+
"eval_runtime": 596.9449,
|
| 574 |
+
"eval_samples_per_second": 4.835,
|
| 575 |
+
"eval_steps_per_second": 0.152,
|
| 576 |
+
"learning_rate": 0.0001,
|
| 577 |
+
"step": 9282
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 34.798534798534796,
|
| 581 |
+
"grad_norm": 0.23537498712539673,
|
| 582 |
+
"learning_rate": 0.0001,
|
| 583 |
+
"loss": 0.1309,
|
| 584 |
+
"step": 9500
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 35.0,
|
| 588 |
+
"eval_accuracy": 0.2955647955647956,
|
| 589 |
+
"eval_f1_macro": 0.6945448365895581,
|
| 590 |
+
"eval_f1_micro": 0.8124288545048274,
|
| 591 |
+
"eval_loss": 0.12488266825675964,
|
| 592 |
+
"eval_roc_auc": 0.8724487031041583,
|
| 593 |
+
"eval_runtime": 587.4735,
|
| 594 |
+
"eval_samples_per_second": 4.913,
|
| 595 |
+
"eval_steps_per_second": 0.155,
|
| 596 |
+
"learning_rate": 0.0001,
|
| 597 |
+
"step": 9555
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 36.0,
|
| 601 |
+
"eval_accuracy": 0.29417879417879417,
|
| 602 |
+
"eval_f1_macro": 0.6971439978031583,
|
| 603 |
+
"eval_f1_micro": 0.8115410842141152,
|
| 604 |
+
"eval_loss": 0.1252983808517456,
|
| 605 |
+
"eval_roc_auc": 0.8688457809436633,
|
| 606 |
+
"eval_runtime": 588.3939,
|
| 607 |
+
"eval_samples_per_second": 4.905,
|
| 608 |
+
"eval_steps_per_second": 0.155,
|
| 609 |
+
"learning_rate": 0.0001,
|
| 610 |
+
"step": 9828
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 36.63003663003663,
|
| 614 |
+
"grad_norm": 0.2208484709262848,
|
| 615 |
+
"learning_rate": 0.0001,
|
| 616 |
+
"loss": 0.1305,
|
| 617 |
+
"step": 10000
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 37.0,
|
| 621 |
+
"eval_accuracy": 0.29521829521829523,
|
| 622 |
+
"eval_f1_macro": 0.6961006786941204,
|
| 623 |
+
"eval_f1_micro": 0.8116249469664828,
|
| 624 |
+
"eval_loss": 0.12479764968156815,
|
| 625 |
+
"eval_roc_auc": 0.870187076326433,
|
| 626 |
+
"eval_runtime": 588.2172,
|
| 627 |
+
"eval_samples_per_second": 4.906,
|
| 628 |
+
"eval_steps_per_second": 0.155,
|
| 629 |
+
"learning_rate": 0.0001,
|
| 630 |
+
"step": 10101
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 38.0,
|
| 634 |
+
"eval_accuracy": 0.3004158004158004,
|
| 635 |
+
"eval_f1_macro": 0.6991177533793484,
|
| 636 |
+
"eval_f1_micro": 0.8129930394431555,
|
| 637 |
+
"eval_loss": 0.12497606873512268,
|
| 638 |
+
"eval_roc_auc": 0.8725859392689393,
|
| 639 |
+
"eval_runtime": 593.6086,
|
| 640 |
+
"eval_samples_per_second": 4.862,
|
| 641 |
+
"eval_steps_per_second": 0.153,
|
| 642 |
+
"learning_rate": 0.0001,
|
| 643 |
+
"step": 10374
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 38.46153846153846,
|
| 647 |
+
"grad_norm": 0.27702799439430237,
|
| 648 |
+
"learning_rate": 0.0001,
|
| 649 |
+
"loss": 0.1285,
|
| 650 |
+
"step": 10500
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 39.0,
|
| 654 |
+
"eval_accuracy": 0.29521829521829523,
|
| 655 |
+
"eval_f1_macro": 0.6970545191351545,
|
| 656 |
+
"eval_f1_micro": 0.8141541282874172,
|
| 657 |
+
"eval_loss": 0.1252022236585617,
|
| 658 |
+
"eval_roc_auc": 0.8767588388621269,
|
| 659 |
+
"eval_runtime": 586.6264,
|
| 660 |
+
"eval_samples_per_second": 4.92,
|
| 661 |
+
"eval_steps_per_second": 0.155,
|
| 662 |
+
"learning_rate": 0.0001,
|
| 663 |
+
"step": 10647
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 40.0,
|
| 667 |
+
"eval_accuracy": 0.2955647955647956,
|
| 668 |
+
"eval_f1_macro": 0.7070171403235663,
|
| 669 |
+
"eval_f1_micro": 0.816655585106383,
|
| 670 |
+
"eval_loss": 0.12485132366418839,
|
| 671 |
+
"eval_roc_auc": 0.8790201839509206,
|
| 672 |
+
"eval_runtime": 586.1423,
|
| 673 |
+
"eval_samples_per_second": 4.924,
|
| 674 |
+
"eval_steps_per_second": 0.155,
|
| 675 |
+
"learning_rate": 0.0001,
|
| 676 |
+
"step": 10920
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 40.29304029304029,
|
| 680 |
+
"grad_norm": 0.24468237161636353,
|
| 681 |
+
"learning_rate": 0.0001,
|
| 682 |
+
"loss": 0.129,
|
| 683 |
+
"step": 11000
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 41.0,
|
| 687 |
+
"eval_accuracy": 0.28967428967428965,
|
| 688 |
+
"eval_f1_macro": 0.6961881266838973,
|
| 689 |
+
"eval_f1_micro": 0.8103573101656658,
|
| 690 |
+
"eval_loss": 0.12500154972076416,
|
| 691 |
+
"eval_roc_auc": 0.8684120872988876,
|
| 692 |
+
"eval_runtime": 589.4017,
|
| 693 |
+
"eval_samples_per_second": 4.896,
|
| 694 |
+
"eval_steps_per_second": 0.154,
|
| 695 |
+
"learning_rate": 0.0001,
|
| 696 |
+
"step": 11193
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 42.0,
|
| 700 |
+
"eval_accuracy": 0.3038808038808039,
|
| 701 |
+
"eval_f1_macro": 0.7064304960359926,
|
| 702 |
+
"eval_f1_micro": 0.816535301022975,
|
| 703 |
+
"eval_loss": 0.12350151687860489,
|
| 704 |
+
"eval_roc_auc": 0.8763375931853813,
|
| 705 |
+
"eval_runtime": 591.1388,
|
| 706 |
+
"eval_samples_per_second": 4.882,
|
| 707 |
+
"eval_steps_per_second": 0.154,
|
| 708 |
+
"learning_rate": 0.0001,
|
| 709 |
+
"step": 11466
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 42.124542124542124,
|
| 713 |
+
"grad_norm": 0.29772019386291504,
|
| 714 |
+
"learning_rate": 0.0001,
|
| 715 |
+
"loss": 0.1277,
|
| 716 |
+
"step": 11500
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 43.0,
|
| 720 |
+
"eval_accuracy": 0.2955647955647956,
|
| 721 |
+
"eval_f1_macro": 0.7047254887418923,
|
| 722 |
+
"eval_f1_micro": 0.8150093808630394,
|
| 723 |
+
"eval_loss": 0.12367021292448044,
|
| 724 |
+
"eval_roc_auc": 0.8771339814503815,
|
| 725 |
+
"eval_runtime": 597.1526,
|
| 726 |
+
"eval_samples_per_second": 4.833,
|
| 727 |
+
"eval_steps_per_second": 0.152,
|
| 728 |
+
"learning_rate": 0.0001,
|
| 729 |
+
"step": 11739
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 43.956043956043956,
|
| 733 |
+
"grad_norm": 0.32455483078956604,
|
| 734 |
+
"learning_rate": 0.0001,
|
| 735 |
+
"loss": 0.1279,
|
| 736 |
+
"step": 12000
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 44.0,
|
| 740 |
+
"eval_accuracy": 0.30076230076230076,
|
| 741 |
+
"eval_f1_macro": 0.705396366545505,
|
| 742 |
+
"eval_f1_micro": 0.8170209225905745,
|
| 743 |
+
"eval_loss": 0.12371324002742767,
|
| 744 |
+
"eval_roc_auc": 0.8789390307110687,
|
| 745 |
+
"eval_runtime": 618.592,
|
| 746 |
+
"eval_samples_per_second": 4.665,
|
| 747 |
+
"eval_steps_per_second": 0.147,
|
| 748 |
+
"learning_rate": 0.0001,
|
| 749 |
+
"step": 12012
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 45.0,
|
| 753 |
+
"eval_accuracy": 0.30145530145530147,
|
| 754 |
+
"eval_f1_macro": 0.7058009223379548,
|
| 755 |
+
"eval_f1_micro": 0.8163231034048448,
|
| 756 |
+
"eval_loss": 0.12333343178033829,
|
| 757 |
+
"eval_roc_auc": 0.8758137724962146,
|
| 758 |
+
"eval_runtime": 593.5671,
|
| 759 |
+
"eval_samples_per_second": 4.862,
|
| 760 |
+
"eval_steps_per_second": 0.153,
|
| 761 |
+
"learning_rate": 0.0001,
|
| 762 |
+
"step": 12285
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 45.78754578754579,
|
| 766 |
+
"grad_norm": 0.2913854718208313,
|
| 767 |
+
"learning_rate": 0.0001,
|
| 768 |
+
"loss": 0.1264,
|
| 769 |
+
"step": 12500
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 46.0,
|
| 773 |
+
"eval_accuracy": 0.30076230076230076,
|
| 774 |
+
"eval_f1_macro": 0.6992655670184796,
|
| 775 |
+
"eval_f1_micro": 0.8158692722371967,
|
| 776 |
+
"eval_loss": 0.12297776341438293,
|
| 777 |
+
"eval_roc_auc": 0.8746400552002995,
|
| 778 |
+
"eval_runtime": 597.9766,
|
| 779 |
+
"eval_samples_per_second": 4.826,
|
| 780 |
+
"eval_steps_per_second": 0.152,
|
| 781 |
+
"learning_rate": 0.0001,
|
| 782 |
+
"step": 12558
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 47.0,
|
| 786 |
+
"eval_accuracy": 0.29902979902979904,
|
| 787 |
+
"eval_f1_macro": 0.7026416067016249,
|
| 788 |
+
"eval_f1_micro": 0.8135392426486143,
|
| 789 |
+
"eval_loss": 0.12366960942745209,
|
| 790 |
+
"eval_roc_auc": 0.8720258880176504,
|
| 791 |
+
"eval_runtime": 608.7312,
|
| 792 |
+
"eval_samples_per_second": 4.741,
|
| 793 |
+
"eval_steps_per_second": 0.149,
|
| 794 |
+
"learning_rate": 0.0001,
|
| 795 |
+
"step": 12831
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 47.61904761904762,
|
| 799 |
+
"grad_norm": 0.2678842842578888,
|
| 800 |
+
"learning_rate": 0.0001,
|
| 801 |
+
"loss": 0.1267,
|
| 802 |
+
"step": 13000
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 48.0,
|
| 806 |
+
"eval_accuracy": 0.30180180180180183,
|
| 807 |
+
"eval_f1_macro": 0.7044430417074125,
|
| 808 |
+
"eval_f1_micro": 0.8169049621530698,
|
| 809 |
+
"eval_loss": 0.12326876819133759,
|
| 810 |
+
"eval_roc_auc": 0.8756520830494087,
|
| 811 |
+
"eval_runtime": 581.2988,
|
| 812 |
+
"eval_samples_per_second": 4.965,
|
| 813 |
+
"eval_steps_per_second": 0.157,
|
| 814 |
+
"learning_rate": 0.0001,
|
| 815 |
+
"step": 13104
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 49.0,
|
| 819 |
+
"eval_accuracy": 0.30214830214830213,
|
| 820 |
+
"eval_f1_macro": 0.705026725915288,
|
| 821 |
+
"eval_f1_micro": 0.8161126713333613,
|
| 822 |
+
"eval_loss": 0.12315386533737183,
|
| 823 |
+
"eval_roc_auc": 0.8761665945900701,
|
| 824 |
+
"eval_runtime": 586.6485,
|
| 825 |
+
"eval_samples_per_second": 4.919,
|
| 826 |
+
"eval_steps_per_second": 0.155,
|
| 827 |
+
"learning_rate": 0.0001,
|
| 828 |
+
"step": 13377
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 49.45054945054945,
|
| 832 |
+
"grad_norm": 0.31903648376464844,
|
| 833 |
+
"learning_rate": 0.0001,
|
| 834 |
+
"loss": 0.1249,
|
| 835 |
+
"step": 13500
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 50.0,
|
| 839 |
+
"eval_accuracy": 0.30145530145530147,
|
| 840 |
+
"eval_f1_macro": 0.7085649491291086,
|
| 841 |
+
"eval_f1_micro": 0.8179686845851126,
|
| 842 |
+
"eval_loss": 0.12265044450759888,
|
| 843 |
+
"eval_roc_auc": 0.877547259354487,
|
| 844 |
+
"eval_runtime": 581.1034,
|
| 845 |
+
"eval_samples_per_second": 4.966,
|
| 846 |
+
"eval_steps_per_second": 0.157,
|
| 847 |
+
"learning_rate": 0.0001,
|
| 848 |
+
"step": 13650
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 51.0,
|
| 852 |
+
"eval_accuracy": 0.30214830214830213,
|
| 853 |
+
"eval_f1_macro": 0.710831288086539,
|
| 854 |
+
"eval_f1_micro": 0.8190420609445996,
|
| 855 |
+
"eval_loss": 0.12310674786567688,
|
| 856 |
+
"eval_roc_auc": 0.87941579593488,
|
| 857 |
+
"eval_runtime": 606.1273,
|
| 858 |
+
"eval_samples_per_second": 4.761,
|
| 859 |
+
"eval_steps_per_second": 0.15,
|
| 860 |
+
"learning_rate": 0.0001,
|
| 861 |
+
"step": 13923
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 51.282051282051285,
|
| 865 |
+
"grad_norm": 0.26118701696395874,
|
| 866 |
+
"learning_rate": 0.0001,
|
| 867 |
+
"loss": 0.1243,
|
| 868 |
+
"step": 14000
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 52.0,
|
| 872 |
+
"eval_accuracy": 0.30214830214830213,
|
| 873 |
+
"eval_f1_macro": 0.704117146056294,
|
| 874 |
+
"eval_f1_micro": 0.816390260370511,
|
| 875 |
+
"eval_loss": 0.12280686944723129,
|
| 876 |
+
"eval_roc_auc": 0.8743457841629654,
|
| 877 |
+
"eval_runtime": 611.1334,
|
| 878 |
+
"eval_samples_per_second": 4.722,
|
| 879 |
+
"eval_steps_per_second": 0.149,
|
| 880 |
+
"learning_rate": 0.0001,
|
| 881 |
+
"step": 14196
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 53.0,
|
| 885 |
+
"eval_accuracy": 0.3038808038808039,
|
| 886 |
+
"eval_f1_macro": 0.7080185810697228,
|
| 887 |
+
"eval_f1_micro": 0.8189015751312609,
|
| 888 |
+
"eval_loss": 0.1225290596485138,
|
| 889 |
+
"eval_roc_auc": 0.8794495583654101,
|
| 890 |
+
"eval_runtime": 586.3165,
|
| 891 |
+
"eval_samples_per_second": 4.922,
|
| 892 |
+
"eval_steps_per_second": 0.155,
|
| 893 |
+
"learning_rate": 0.0001,
|
| 894 |
+
"step": 14469
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 53.11355311355312,
|
| 898 |
+
"grad_norm": 0.24176084995269775,
|
| 899 |
+
"learning_rate": 0.0001,
|
| 900 |
+
"loss": 0.1248,
|
| 901 |
+
"step": 14500
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 54.0,
|
| 905 |
+
"eval_accuracy": 0.30180180180180183,
|
| 906 |
+
"eval_f1_macro": 0.7053875588266636,
|
| 907 |
+
"eval_f1_micro": 0.8162527837304089,
|
| 908 |
+
"eval_loss": 0.12376156449317932,
|
| 909 |
+
"eval_roc_auc": 0.8755284752634194,
|
| 910 |
+
"eval_runtime": 590.1707,
|
| 911 |
+
"eval_samples_per_second": 4.89,
|
| 912 |
+
"eval_steps_per_second": 0.154,
|
| 913 |
+
"learning_rate": 0.0001,
|
| 914 |
+
"step": 14742
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 54.94505494505494,
|
| 918 |
+
"grad_norm": 0.3652552366256714,
|
| 919 |
+
"learning_rate": 0.0001,
|
| 920 |
+
"loss": 0.1233,
|
| 921 |
+
"step": 15000
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 55.0,
|
| 925 |
+
"eval_accuracy": 0.30284130284130284,
|
| 926 |
+
"eval_f1_macro": 0.7092508494713976,
|
| 927 |
+
"eval_f1_micro": 0.818075117370892,
|
| 928 |
+
"eval_loss": 0.12211860716342926,
|
| 929 |
+
"eval_roc_auc": 0.8772347053641084,
|
| 930 |
+
"eval_runtime": 591.2857,
|
| 931 |
+
"eval_samples_per_second": 4.881,
|
| 932 |
+
"eval_steps_per_second": 0.154,
|
| 933 |
+
"learning_rate": 0.0001,
|
| 934 |
+
"step": 15015
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 56.0,
|
| 938 |
+
"eval_accuracy": 0.3049203049203049,
|
| 939 |
+
"eval_f1_macro": 0.7091508009521661,
|
| 940 |
+
"eval_f1_micro": 0.818769689935334,
|
| 941 |
+
"eval_loss": 0.12255053967237473,
|
| 942 |
+
"eval_roc_auc": 0.8809376807503978,
|
| 943 |
+
"eval_runtime": 619.809,
|
| 944 |
+
"eval_samples_per_second": 4.656,
|
| 945 |
+
"eval_steps_per_second": 0.147,
|
| 946 |
+
"learning_rate": 0.0001,
|
| 947 |
+
"step": 15288
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 56.776556776556774,
|
| 951 |
+
"grad_norm": 0.2984638214111328,
|
| 952 |
+
"learning_rate": 0.0001,
|
| 953 |
+
"loss": 0.1237,
|
| 954 |
+
"step": 15500
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 57.0,
|
| 958 |
+
"eval_accuracy": 0.3052668052668053,
|
| 959 |
+
"eval_f1_macro": 0.7056269081565454,
|
| 960 |
+
"eval_f1_micro": 0.8183564389510606,
|
| 961 |
+
"eval_loss": 0.12233822792768478,
|
| 962 |
+
"eval_roc_auc": 0.8785286099375562,
|
| 963 |
+
"eval_runtime": 613.5916,
|
| 964 |
+
"eval_samples_per_second": 4.703,
|
| 965 |
+
"eval_steps_per_second": 0.148,
|
| 966 |
+
"learning_rate": 0.0001,
|
| 967 |
+
"step": 15561
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 58.0,
|
| 971 |
+
"eval_accuracy": 0.30284130284130284,
|
| 972 |
+
"eval_f1_macro": 0.7093876090831799,
|
| 973 |
+
"eval_f1_micro": 0.8179678964618875,
|
| 974 |
+
"eval_loss": 0.12230789661407471,
|
| 975 |
+
"eval_roc_auc": 0.8764581158068805,
|
| 976 |
+
"eval_runtime": 607.5944,
|
| 977 |
+
"eval_samples_per_second": 4.75,
|
| 978 |
+
"eval_steps_per_second": 0.15,
|
| 979 |
+
"learning_rate": 0.0001,
|
| 980 |
+
"step": 15834
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 58.608058608058606,
|
| 984 |
+
"grad_norm": 0.2825208604335785,
|
| 985 |
+
"learning_rate": 0.0001,
|
| 986 |
+
"loss": 0.1234,
|
| 987 |
+
"step": 16000
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 59.0,
|
| 991 |
+
"eval_accuracy": 0.30734580734580735,
|
| 992 |
+
"eval_f1_macro": 0.7102428483836337,
|
| 993 |
+
"eval_f1_micro": 0.8198051269184126,
|
| 994 |
+
"eval_loss": 0.12226579338312149,
|
| 995 |
+
"eval_roc_auc": 0.8788947787212716,
|
| 996 |
+
"eval_runtime": 579.6776,
|
| 997 |
+
"eval_samples_per_second": 4.979,
|
| 998 |
+
"eval_steps_per_second": 0.157,
|
| 999 |
+
"learning_rate": 0.0001,
|
| 1000 |
+
"step": 16107
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 60.0,
|
| 1004 |
+
"eval_accuracy": 0.29799029799029797,
|
| 1005 |
+
"eval_f1_macro": 0.7068409531794828,
|
| 1006 |
+
"eval_f1_micro": 0.8173416232565955,
|
| 1007 |
+
"eval_loss": 0.1236739531159401,
|
| 1008 |
+
"eval_roc_auc": 0.8761882980515712,
|
| 1009 |
+
"eval_runtime": 577.7976,
|
| 1010 |
+
"eval_samples_per_second": 4.995,
|
| 1011 |
+
"eval_steps_per_second": 0.157,
|
| 1012 |
+
"learning_rate": 0.0001,
|
| 1013 |
+
"step": 16380
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 60.43956043956044,
|
| 1017 |
+
"grad_norm": 0.313997745513916,
|
| 1018 |
+
"learning_rate": 0.0001,
|
| 1019 |
+
"loss": 0.1232,
|
| 1020 |
+
"step": 16500
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 61.0,
|
| 1024 |
+
"eval_accuracy": 0.305959805959806,
|
| 1025 |
+
"eval_f1_macro": 0.7139384635953806,
|
| 1026 |
+
"eval_f1_micro": 0.8201011747982775,
|
| 1027 |
+
"eval_loss": 0.12236195057630539,
|
| 1028 |
+
"eval_roc_auc": 0.8791326851447451,
|
| 1029 |
+
"eval_runtime": 576.7269,
|
| 1030 |
+
"eval_samples_per_second": 5.004,
|
| 1031 |
+
"eval_steps_per_second": 0.158,
|
| 1032 |
+
"learning_rate": 0.0001,
|
| 1033 |
+
"step": 16653
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 62.0,
|
| 1037 |
+
"eval_accuracy": 0.30284130284130284,
|
| 1038 |
+
"eval_f1_macro": 0.7188990083298508,
|
| 1039 |
+
"eval_f1_micro": 0.8209334277030684,
|
| 1040 |
+
"eval_loss": 0.12215279042720795,
|
| 1041 |
+
"eval_roc_auc": 0.8808361117698756,
|
| 1042 |
+
"eval_runtime": 585.2414,
|
| 1043 |
+
"eval_samples_per_second": 4.931,
|
| 1044 |
+
"eval_steps_per_second": 0.155,
|
| 1045 |
+
"learning_rate": 1e-05,
|
| 1046 |
+
"step": 16926
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 62.27106227106227,
|
| 1050 |
+
"grad_norm": 0.322051465511322,
|
| 1051 |
+
"learning_rate": 1e-05,
|
| 1052 |
+
"loss": 0.1204,
|
| 1053 |
+
"step": 17000
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 63.0,
|
| 1057 |
+
"eval_accuracy": 0.3097713097713098,
|
| 1058 |
+
"eval_f1_macro": 0.7190866276619315,
|
| 1059 |
+
"eval_f1_micro": 0.820752746564184,
|
| 1060 |
+
"eval_loss": 0.12084941565990448,
|
| 1061 |
+
"eval_roc_auc": 0.8797410795822204,
|
| 1062 |
+
"eval_runtime": 586.6749,
|
| 1063 |
+
"eval_samples_per_second": 4.919,
|
| 1064 |
+
"eval_steps_per_second": 0.155,
|
| 1065 |
+
"learning_rate": 1e-05,
|
| 1066 |
+
"step": 17199
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 64.0,
|
| 1070 |
+
"eval_accuracy": 0.3108108108108108,
|
| 1071 |
+
"eval_f1_macro": 0.7187730185556146,
|
| 1072 |
+
"eval_f1_micro": 0.8218151540383014,
|
| 1073 |
+
"eval_loss": 0.12093428522348404,
|
| 1074 |
+
"eval_roc_auc": 0.8813373302757117,
|
| 1075 |
+
"eval_runtime": 589.1584,
|
| 1076 |
+
"eval_samples_per_second": 4.899,
|
| 1077 |
+
"eval_steps_per_second": 0.154,
|
| 1078 |
+
"learning_rate": 1e-05,
|
| 1079 |
+
"step": 17472
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 64.1025641025641,
|
| 1083 |
+
"grad_norm": 0.32896944880485535,
|
| 1084 |
+
"learning_rate": 1e-05,
|
| 1085 |
+
"loss": 0.12,
|
| 1086 |
+
"step": 17500
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 65.0,
|
| 1090 |
+
"eval_accuracy": 0.30803880803880807,
|
| 1091 |
+
"eval_f1_macro": 0.7186584702198188,
|
| 1092 |
+
"eval_f1_micro": 0.8209837715435904,
|
| 1093 |
+
"eval_loss": 0.12085793167352676,
|
| 1094 |
+
"eval_roc_auc": 0.8787241154699269,
|
| 1095 |
+
"eval_runtime": 587.8337,
|
| 1096 |
+
"eval_samples_per_second": 4.91,
|
| 1097 |
+
"eval_steps_per_second": 0.155,
|
| 1098 |
+
"learning_rate": 1e-05,
|
| 1099 |
+
"step": 17745
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 65.93406593406593,
|
| 1103 |
+
"grad_norm": 0.3432726263999939,
|
| 1104 |
+
"learning_rate": 1e-05,
|
| 1105 |
+
"loss": 0.1187,
|
| 1106 |
+
"step": 18000
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 66.0,
|
| 1110 |
+
"eval_accuracy": 0.3135828135828136,
|
| 1111 |
+
"eval_f1_macro": 0.7185770967712465,
|
| 1112 |
+
"eval_f1_micro": 0.8215507887488523,
|
| 1113 |
+
"eval_loss": 0.12076118588447571,
|
| 1114 |
+
"eval_roc_auc": 0.8804684272314324,
|
| 1115 |
+
"eval_runtime": 588.6607,
|
| 1116 |
+
"eval_samples_per_second": 4.903,
|
| 1117 |
+
"eval_steps_per_second": 0.155,
|
| 1118 |
+
"learning_rate": 1e-05,
|
| 1119 |
+
"step": 18018
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 67.0,
|
| 1123 |
+
"eval_accuracy": 0.31115731115731116,
|
| 1124 |
+
"eval_f1_macro": 0.7239469969506999,
|
| 1125 |
+
"eval_f1_micro": 0.8232429532417151,
|
| 1126 |
+
"eval_loss": 0.1210499182343483,
|
| 1127 |
+
"eval_roc_auc": 0.8847649346106092,
|
| 1128 |
+
"eval_runtime": 591.9527,
|
| 1129 |
+
"eval_samples_per_second": 4.875,
|
| 1130 |
+
"eval_steps_per_second": 0.154,
|
| 1131 |
+
"learning_rate": 1e-05,
|
| 1132 |
+
"step": 18291
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 67.76556776556777,
|
| 1136 |
+
"grad_norm": 0.3457956612110138,
|
| 1137 |
+
"learning_rate": 1e-05,
|
| 1138 |
+
"loss": 0.1179,
|
| 1139 |
+
"step": 18500
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 68.0,
|
| 1143 |
+
"eval_accuracy": 0.3125433125433125,
|
| 1144 |
+
"eval_f1_macro": 0.720063006101889,
|
| 1145 |
+
"eval_f1_micro": 0.8211584808443447,
|
| 1146 |
+
"eval_loss": 0.1208076998591423,
|
| 1147 |
+
"eval_roc_auc": 0.8815457934989414,
|
| 1148 |
+
"eval_runtime": 585.5944,
|
| 1149 |
+
"eval_samples_per_second": 4.928,
|
| 1150 |
+
"eval_steps_per_second": 0.155,
|
| 1151 |
+
"learning_rate": 1e-05,
|
| 1152 |
+
"step": 18564
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 69.0,
|
| 1156 |
+
"eval_accuracy": 0.31011781011781014,
|
| 1157 |
+
"eval_f1_macro": 0.7197984794848579,
|
| 1158 |
+
"eval_f1_micro": 0.821014765549839,
|
| 1159 |
+
"eval_loss": 0.12105683237314224,
|
| 1160 |
+
"eval_roc_auc": 0.8794876936812611,
|
| 1161 |
+
"eval_runtime": 586.2959,
|
| 1162 |
+
"eval_samples_per_second": 4.922,
|
| 1163 |
+
"eval_steps_per_second": 0.155,
|
| 1164 |
+
"learning_rate": 1e-05,
|
| 1165 |
+
"step": 18837
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 69.59706959706959,
|
| 1169 |
+
"grad_norm": 0.2593284845352173,
|
| 1170 |
+
"learning_rate": 1e-05,
|
| 1171 |
+
"loss": 0.1177,
|
| 1172 |
+
"step": 19000
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 70.0,
|
| 1176 |
+
"eval_accuracy": 0.31115731115731116,
|
| 1177 |
+
"eval_f1_macro": 0.719699492247552,
|
| 1178 |
+
"eval_f1_micro": 0.821309285237141,
|
| 1179 |
+
"eval_loss": 0.12111356854438782,
|
| 1180 |
+
"eval_roc_auc": 0.8802103867562204,
|
| 1181 |
+
"eval_runtime": 592.4319,
|
| 1182 |
+
"eval_samples_per_second": 4.871,
|
| 1183 |
+
"eval_steps_per_second": 0.154,
|
| 1184 |
+
"learning_rate": 1e-05,
|
| 1185 |
+
"step": 19110
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 71.0,
|
| 1189 |
+
"eval_accuracy": 0.31115731115731116,
|
| 1190 |
+
"eval_f1_macro": 0.7163966165871272,
|
| 1191 |
+
"eval_f1_micro": 0.8206033106461642,
|
| 1192 |
+
"eval_loss": 0.12063230574131012,
|
| 1193 |
+
"eval_roc_auc": 0.8779552656514418,
|
| 1194 |
+
"eval_runtime": 588.5502,
|
| 1195 |
+
"eval_samples_per_second": 4.904,
|
| 1196 |
+
"eval_steps_per_second": 0.155,
|
| 1197 |
+
"learning_rate": 1e-05,
|
| 1198 |
+
"step": 19383
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 71.42857142857143,
|
| 1202 |
+
"grad_norm": 0.3827510476112366,
|
| 1203 |
+
"learning_rate": 1e-05,
|
| 1204 |
+
"loss": 0.1179,
|
| 1205 |
+
"step": 19500
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 72.0,
|
| 1209 |
+
"eval_accuracy": 0.3128898128898129,
|
| 1210 |
+
"eval_f1_macro": 0.7171818163524962,
|
| 1211 |
+
"eval_f1_micro": 0.8206118081490495,
|
| 1212 |
+
"eval_loss": 0.12075439840555191,
|
| 1213 |
+
"eval_roc_auc": 0.8783204820582929,
|
| 1214 |
+
"eval_runtime": 584.4453,
|
| 1215 |
+
"eval_samples_per_second": 4.938,
|
| 1216 |
+
"eval_steps_per_second": 0.156,
|
| 1217 |
+
"learning_rate": 1e-05,
|
| 1218 |
+
"step": 19656
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 73.0,
|
| 1222 |
+
"eval_accuracy": 0.31323631323631324,
|
| 1223 |
+
"eval_f1_macro": 0.7214307826544399,
|
| 1224 |
+
"eval_f1_micro": 0.8217462106977327,
|
| 1225 |
+
"eval_loss": 0.12078637629747391,
|
| 1226 |
+
"eval_roc_auc": 0.8804145307491638,
|
| 1227 |
+
"eval_runtime": 588.6768,
|
| 1228 |
+
"eval_samples_per_second": 4.903,
|
| 1229 |
+
"eval_steps_per_second": 0.155,
|
| 1230 |
+
"learning_rate": 1e-05,
|
| 1231 |
+
"step": 19929
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 73.26007326007326,
|
| 1235 |
+
"grad_norm": 0.29221299290657043,
|
| 1236 |
+
"learning_rate": 1e-05,
|
| 1237 |
+
"loss": 0.1177,
|
| 1238 |
+
"step": 20000
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 74.0,
|
| 1242 |
+
"eval_accuracy": 0.3108108108108108,
|
| 1243 |
+
"eval_f1_macro": 0.715483654869702,
|
| 1244 |
+
"eval_f1_micro": 0.8200794388574326,
|
| 1245 |
+
"eval_loss": 0.12086880952119827,
|
| 1246 |
+
"eval_roc_auc": 0.8759783190736136,
|
| 1247 |
+
"eval_runtime": 595.2281,
|
| 1248 |
+
"eval_samples_per_second": 4.849,
|
| 1249 |
+
"eval_steps_per_second": 0.153,
|
| 1250 |
+
"learning_rate": 1e-05,
|
| 1251 |
+
"step": 20202
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 75.0,
|
| 1255 |
+
"eval_accuracy": 0.3153153153153153,
|
| 1256 |
+
"eval_f1_macro": 0.7151281975948514,
|
| 1257 |
+
"eval_f1_micro": 0.8207404925448148,
|
| 1258 |
+
"eval_loss": 0.12054955214262009,
|
| 1259 |
+
"eval_roc_auc": 0.8789508616462007,
|
| 1260 |
+
"eval_runtime": 588.2243,
|
| 1261 |
+
"eval_samples_per_second": 4.906,
|
| 1262 |
+
"eval_steps_per_second": 0.155,
|
| 1263 |
+
"learning_rate": 1e-05,
|
| 1264 |
+
"step": 20475
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 75.0915750915751,
|
| 1268 |
+
"grad_norm": 0.3488374352455139,
|
| 1269 |
+
"learning_rate": 1e-05,
|
| 1270 |
+
"loss": 0.1171,
|
| 1271 |
+
"step": 20500
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 76.0,
|
| 1275 |
+
"eval_accuracy": 0.31566181566181567,
|
| 1276 |
+
"eval_f1_macro": 0.722403613960237,
|
| 1277 |
+
"eval_f1_micro": 0.8221261740503699,
|
| 1278 |
+
"eval_loss": 0.12033110857009888,
|
| 1279 |
+
"eval_roc_auc": 0.8820333836259857,
|
| 1280 |
+
"eval_runtime": 591.3419,
|
| 1281 |
+
"eval_samples_per_second": 4.88,
|
| 1282 |
+
"eval_steps_per_second": 0.154,
|
| 1283 |
+
"learning_rate": 1e-05,
|
| 1284 |
+
"step": 20748
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 76.92307692307692,
|
| 1288 |
+
"grad_norm": 0.37617847323417664,
|
| 1289 |
+
"learning_rate": 1e-05,
|
| 1290 |
+
"loss": 0.1171,
|
| 1291 |
+
"step": 21000
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 77.0,
|
| 1295 |
+
"eval_accuracy": 0.3135828135828136,
|
| 1296 |
+
"eval_f1_macro": 0.7234417953998725,
|
| 1297 |
+
"eval_f1_micro": 0.8231996372480317,
|
| 1298 |
+
"eval_loss": 0.12079885601997375,
|
| 1299 |
+
"eval_roc_auc": 0.8850904999468814,
|
| 1300 |
+
"eval_runtime": 598.1869,
|
| 1301 |
+
"eval_samples_per_second": 4.825,
|
| 1302 |
+
"eval_steps_per_second": 0.152,
|
| 1303 |
+
"learning_rate": 1e-05,
|
| 1304 |
+
"step": 21021
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 78.0,
|
| 1308 |
+
"eval_accuracy": 0.3115038115038115,
|
| 1309 |
+
"eval_f1_macro": 0.7233107692667189,
|
| 1310 |
+
"eval_f1_micro": 0.8230326613403982,
|
| 1311 |
+
"eval_loss": 0.12099317461252213,
|
| 1312 |
+
"eval_roc_auc": 0.8837231818723246,
|
| 1313 |
+
"eval_runtime": 585.8629,
|
| 1314 |
+
"eval_samples_per_second": 4.926,
|
| 1315 |
+
"eval_steps_per_second": 0.155,
|
| 1316 |
+
"learning_rate": 1e-05,
|
| 1317 |
+
"step": 21294
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 78.75457875457876,
|
| 1321 |
+
"grad_norm": 0.36047452688217163,
|
| 1322 |
+
"learning_rate": 1e-05,
|
| 1323 |
+
"loss": 0.1168,
|
| 1324 |
+
"step": 21500
|
| 1325 |
+
},
|
| 1326 |
+
{
|
| 1327 |
+
"epoch": 79.0,
|
| 1328 |
+
"eval_accuracy": 0.31011781011781014,
|
| 1329 |
+
"eval_f1_macro": 0.7172980311198172,
|
| 1330 |
+
"eval_f1_micro": 0.8202369947054374,
|
| 1331 |
+
"eval_loss": 0.12051720172166824,
|
| 1332 |
+
"eval_roc_auc": 0.8777043478820749,
|
| 1333 |
+
"eval_runtime": 595.4358,
|
| 1334 |
+
"eval_samples_per_second": 4.847,
|
| 1335 |
+
"eval_steps_per_second": 0.153,
|
| 1336 |
+
"learning_rate": 1e-05,
|
| 1337 |
+
"step": 21567
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 80.0,
|
| 1341 |
+
"eval_accuracy": 0.31185031185031187,
|
| 1342 |
+
"eval_f1_macro": 0.7248558336823359,
|
| 1343 |
+
"eval_f1_micro": 0.8231793006530544,
|
| 1344 |
+
"eval_loss": 0.12073608487844467,
|
| 1345 |
+
"eval_roc_auc": 0.8842671366132298,
|
| 1346 |
+
"eval_runtime": 604.2206,
|
| 1347 |
+
"eval_samples_per_second": 4.776,
|
| 1348 |
+
"eval_steps_per_second": 0.151,
|
| 1349 |
+
"learning_rate": 1e-05,
|
| 1350 |
+
"step": 21840
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 80.58608058608058,
|
| 1354 |
+
"grad_norm": 0.35180962085723877,
|
| 1355 |
+
"learning_rate": 1e-05,
|
| 1356 |
+
"loss": 0.1171,
|
| 1357 |
+
"step": 22000
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 81.0,
|
| 1361 |
+
"eval_accuracy": 0.3128898128898129,
|
| 1362 |
+
"eval_f1_macro": 0.7212996450160633,
|
| 1363 |
+
"eval_f1_micro": 0.822080253872813,
|
| 1364 |
+
"eval_loss": 0.12031927704811096,
|
| 1365 |
+
"eval_roc_auc": 0.8805991577232666,
|
| 1366 |
+
"eval_runtime": 597.4583,
|
| 1367 |
+
"eval_samples_per_second": 4.83,
|
| 1368 |
+
"eval_steps_per_second": 0.152,
|
| 1369 |
+
"learning_rate": 1e-05,
|
| 1370 |
+
"step": 22113
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 82.0,
|
| 1374 |
+
"eval_accuracy": 0.3142758142758143,
|
| 1375 |
+
"eval_f1_macro": 0.7178066335813648,
|
| 1376 |
+
"eval_f1_micro": 0.8215302193202746,
|
| 1377 |
+
"eval_loss": 0.1204884946346283,
|
| 1378 |
+
"eval_roc_auc": 0.8795852787754633,
|
| 1379 |
+
"eval_runtime": 583.2227,
|
| 1380 |
+
"eval_samples_per_second": 4.948,
|
| 1381 |
+
"eval_steps_per_second": 0.156,
|
| 1382 |
+
"learning_rate": 1e-05,
|
| 1383 |
+
"step": 22386
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 82.41758241758242,
|
| 1387 |
+
"grad_norm": 0.3334418535232544,
|
| 1388 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1389 |
+
"loss": 0.1157,
|
| 1390 |
+
"step": 22500
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"epoch": 83.0,
|
| 1394 |
+
"eval_accuracy": 0.31115731115731116,
|
| 1395 |
+
"eval_f1_macro": 0.7113142483409282,
|
| 1396 |
+
"eval_f1_micro": 0.8179971218149497,
|
| 1397 |
+
"eval_loss": 0.12136666476726532,
|
| 1398 |
+
"eval_roc_auc": 0.8743461195069316,
|
| 1399 |
+
"eval_runtime": 580.12,
|
| 1400 |
+
"eval_samples_per_second": 4.975,
|
| 1401 |
+
"eval_steps_per_second": 0.157,
|
| 1402 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1403 |
+
"step": 22659
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 84.0,
|
| 1407 |
+
"eval_accuracy": 0.3115038115038115,
|
| 1408 |
+
"eval_f1_macro": 0.7250649377579587,
|
| 1409 |
+
"eval_f1_micro": 0.8234267187629895,
|
| 1410 |
+
"eval_loss": 0.12041348963975906,
|
| 1411 |
+
"eval_roc_auc": 0.8827056007271329,
|
| 1412 |
+
"eval_runtime": 581.6672,
|
| 1413 |
+
"eval_samples_per_second": 4.962,
|
| 1414 |
+
"eval_steps_per_second": 0.156,
|
| 1415 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1416 |
+
"step": 22932
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 84.24908424908425,
|
| 1420 |
+
"grad_norm": 0.3593423068523407,
|
| 1421 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1422 |
+
"loss": 0.1169,
|
| 1423 |
+
"step": 23000
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 85.0,
|
| 1427 |
+
"eval_accuracy": 0.31323631323631324,
|
| 1428 |
+
"eval_f1_macro": 0.7213085414821642,
|
| 1429 |
+
"eval_f1_micro": 0.8229879338226147,
|
| 1430 |
+
"eval_loss": 0.12035409361124039,
|
| 1431 |
+
"eval_roc_auc": 0.8831987441502598,
|
| 1432 |
+
"eval_runtime": 579.5593,
|
| 1433 |
+
"eval_samples_per_second": 4.98,
|
| 1434 |
+
"eval_steps_per_second": 0.157,
|
| 1435 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1436 |
+
"step": 23205
|
| 1437 |
+
},
|
| 1438 |
+
{
|
| 1439 |
+
"epoch": 86.0,
|
| 1440 |
+
"eval_accuracy": 0.3076923076923077,
|
| 1441 |
+
"eval_f1_macro": 0.7218120076279698,
|
| 1442 |
+
"eval_f1_micro": 0.8196243388446962,
|
| 1443 |
+
"eval_loss": 0.12250283360481262,
|
| 1444 |
+
"eval_roc_auc": 0.8800111790264615,
|
| 1445 |
+
"eval_runtime": 583.2647,
|
| 1446 |
+
"eval_samples_per_second": 4.948,
|
| 1447 |
+
"eval_steps_per_second": 0.156,
|
| 1448 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1449 |
+
"step": 23478
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 86.08058608058609,
|
| 1453 |
+
"grad_norm": 0.3458651602268219,
|
| 1454 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1455 |
+
"loss": 0.1157,
|
| 1456 |
+
"step": 23500
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 87.0,
|
| 1460 |
+
"eval_accuracy": 0.3090783090783091,
|
| 1461 |
+
"eval_f1_macro": 0.7151954083158903,
|
| 1462 |
+
"eval_f1_micro": 0.8203968852047224,
|
| 1463 |
+
"eval_loss": 0.12075748294591904,
|
| 1464 |
+
"eval_roc_auc": 0.8788858049167326,
|
| 1465 |
+
"eval_runtime": 580.273,
|
| 1466 |
+
"eval_samples_per_second": 4.974,
|
| 1467 |
+
"eval_steps_per_second": 0.157,
|
| 1468 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1469 |
+
"step": 23751
|
| 1470 |
+
},
|
| 1471 |
+
{
|
| 1472 |
+
"epoch": 87.91208791208791,
|
| 1473 |
+
"grad_norm": 0.2947898507118225,
|
| 1474 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1475 |
+
"loss": 0.1156,
|
| 1476 |
+
"step": 24000
|
| 1477 |
+
},
|
| 1478 |
+
{
|
| 1479 |
+
"epoch": 88.0,
|
| 1480 |
+
"eval_accuracy": 0.30838530838530837,
|
| 1481 |
+
"eval_f1_macro": 0.7168335672232342,
|
| 1482 |
+
"eval_f1_micro": 0.8215440749647566,
|
| 1483 |
+
"eval_loss": 0.12086642533540726,
|
| 1484 |
+
"eval_roc_auc": 0.8824075738373759,
|
| 1485 |
+
"eval_runtime": 581.7056,
|
| 1486 |
+
"eval_samples_per_second": 4.961,
|
| 1487 |
+
"eval_steps_per_second": 0.156,
|
| 1488 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1489 |
+
"step": 24024
|
| 1490 |
+
},
|
| 1491 |
+
{
|
| 1492 |
+
"epoch": 89.0,
|
| 1493 |
+
"eval_accuracy": 0.3163548163548164,
|
| 1494 |
+
"eval_f1_macro": 0.733984551040518,
|
| 1495 |
+
"eval_f1_micro": 0.8244650323850127,
|
| 1496 |
+
"eval_loss": 0.12105640023946762,
|
| 1497 |
+
"eval_roc_auc": 0.8874893628893881,
|
| 1498 |
+
"eval_runtime": 592.213,
|
| 1499 |
+
"eval_samples_per_second": 4.873,
|
| 1500 |
+
"eval_steps_per_second": 0.154,
|
| 1501 |
+
"learning_rate": 1.0000000000000002e-07,
|
| 1502 |
+
"step": 24297
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 89.74358974358974,
|
| 1506 |
+
"grad_norm": 0.27441146969795227,
|
| 1507 |
+
"learning_rate": 1.0000000000000002e-07,
|
| 1508 |
+
"loss": 0.1157,
|
| 1509 |
+
"step": 24500
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 90.0,
|
| 1513 |
+
"eval_accuracy": 0.31185031185031187,
|
| 1514 |
+
"eval_f1_macro": 0.7245620055819162,
|
| 1515 |
+
"eval_f1_micro": 0.8232248520710059,
|
| 1516 |
+
"eval_loss": 0.12090421468019485,
|
| 1517 |
+
"eval_roc_auc": 0.8860665789228,
|
| 1518 |
+
"eval_runtime": 602.5705,
|
| 1519 |
+
"eval_samples_per_second": 4.789,
|
| 1520 |
+
"eval_steps_per_second": 0.151,
|
| 1521 |
+
"learning_rate": 1.0000000000000002e-07,
|
| 1522 |
+
"step": 24570
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 91.0,
|
| 1526 |
+
"eval_accuracy": 0.3115038115038115,
|
| 1527 |
+
"eval_f1_macro": 0.7163143946337084,
|
| 1528 |
+
"eval_f1_micro": 0.8200938495056143,
|
| 1529 |
+
"eval_loss": 0.12043782323598862,
|
| 1530 |
+
"eval_roc_auc": 0.8784951828509925,
|
| 1531 |
+
"eval_runtime": 602.4626,
|
| 1532 |
+
"eval_samples_per_second": 4.79,
|
| 1533 |
+
"eval_steps_per_second": 0.151,
|
| 1534 |
+
"learning_rate": 1.0000000000000002e-07,
|
| 1535 |
+
"step": 24843
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 91.0,
|
| 1539 |
+
"learning_rate": 1.0000000000000002e-07,
|
| 1540 |
+
"step": 24843,
|
| 1541 |
+
"total_flos": 1.1760993126572918e+21,
|
| 1542 |
+
"train_loss": 0.13338198287712655,
|
| 1543 |
+
"train_runtime": 215448.2605,
|
| 1544 |
+
"train_samples_per_second": 6.068,
|
| 1545 |
+
"train_steps_per_second": 0.19
|
| 1546 |
+
}
|
| 1547 |
+
],
|
| 1548 |
+
"logging_steps": 500,
|
| 1549 |
+
"max_steps": 40950,
|
| 1550 |
+
"num_input_tokens_seen": 0,
|
| 1551 |
+
"num_train_epochs": 150,
|
| 1552 |
+
"save_steps": 500,
|
| 1553 |
+
"stateful_callbacks": {
|
| 1554 |
+
"EarlyStoppingCallback": {
|
| 1555 |
+
"args": {
|
| 1556 |
+
"early_stopping_patience": 10,
|
| 1557 |
+
"early_stopping_threshold": 0.0
|
| 1558 |
+
},
|
| 1559 |
+
"attributes": {
|
| 1560 |
+
"early_stopping_patience_counter": 0
|
| 1561 |
+
}
|
| 1562 |
+
},
|
| 1563 |
+
"TrainerControl": {
|
| 1564 |
+
"args": {
|
| 1565 |
+
"should_epoch_stop": false,
|
| 1566 |
+
"should_evaluate": false,
|
| 1567 |
+
"should_log": false,
|
| 1568 |
+
"should_save": true,
|
| 1569 |
+
"should_training_stop": true
|
| 1570 |
+
},
|
| 1571 |
+
"attributes": {}
|
| 1572 |
+
}
|
| 1573 |
+
},
|
| 1574 |
+
"total_flos": 1.1760993126572918e+21,
|
| 1575 |
+
"train_batch_size": 32,
|
| 1576 |
+
"trial_name": null,
|
| 1577 |
+
"trial_params": null
|
| 1578 |
+
}
|