Evaluation on the test set completed on 2024_09_27.
Browse files- README.md +170 -0
- all_results.json +16 -0
- logs/events.out.tfevents.1727136392.datavisu4 +2 -2
- logs/events.out.tfevents.1727388366.datavisu4 +3 -0
- model.safetensors +1 -1
- test_results.json +11 -0
- train_results.json +9 -0
- trainer_state.json +1723 -0
README.md
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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: DinoVdeauTest-large-2024_09_24-batch-size32_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 |
+
# DinoVdeauTest-large-2024_09_24-batch-size32_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: 0.1204
|
| 22 |
+
- F1 Micro: 0.8214
|
| 23 |
+
- F1 Macro: 0.7191
|
| 24 |
+
- Accuracy: 0.3135
|
| 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 | Accuracy | Rate |
|
| 56 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|:--------:|:------:|
|
| 57 |
+
| No log | 1.0 | 273 | 0.1776 | 0.7486 | 0.5520 | 0.2169 | 0.001 |
|
| 58 |
+
| 0.2736 | 2.0 | 546 | 0.1528 | 0.7693 | 0.5698 | 0.2405 | 0.001 |
|
| 59 |
+
| 0.2736 | 3.0 | 819 | 0.1483 | 0.7774 | 0.6217 | 0.2495 | 0.001 |
|
| 60 |
+
| 0.1699 | 4.0 | 1092 | 0.1467 | 0.7772 | 0.6272 | 0.2554 | 0.001 |
|
| 61 |
+
| 0.1699 | 5.0 | 1365 | 0.1453 | 0.7772 | 0.6281 | 0.2464 | 0.001 |
|
| 62 |
+
| 0.1622 | 6.0 | 1638 | 0.1437 | 0.7810 | 0.6191 | 0.2630 | 0.001 |
|
| 63 |
+
| 0.1622 | 7.0 | 1911 | 0.1428 | 0.7811 | 0.6172 | 0.2599 | 0.001 |
|
| 64 |
+
| 0.1593 | 8.0 | 2184 | 0.1433 | 0.7799 | 0.6253 | 0.2557 | 0.001 |
|
| 65 |
+
| 0.1593 | 9.0 | 2457 | 0.1420 | 0.7893 | 0.6530 | 0.2519 | 0.001 |
|
| 66 |
+
| 0.1569 | 10.0 | 2730 | 0.2462 | 0.7441 | 0.6022 | 0.2554 | 0.001 |
|
| 67 |
+
| 0.156 | 11.0 | 3003 | 0.1400 | 0.7883 | 0.6483 | 0.2703 | 0.001 |
|
| 68 |
+
| 0.156 | 12.0 | 3276 | 0.1400 | 0.7906 | 0.6590 | 0.2599 | 0.001 |
|
| 69 |
+
| 0.1547 | 13.0 | 3549 | 0.1394 | 0.7876 | 0.6467 | 0.2644 | 0.001 |
|
| 70 |
+
| 0.1547 | 14.0 | 3822 | 0.1399 | 0.7879 | 0.6469 | 0.2640 | 0.001 |
|
| 71 |
+
| 0.1543 | 15.0 | 4095 | 0.1391 | 0.7881 | 0.6413 | 0.2512 | 0.001 |
|
| 72 |
+
| 0.1543 | 16.0 | 4368 | 0.1414 | 0.7907 | 0.6348 | 0.2633 | 0.001 |
|
| 73 |
+
| 0.1536 | 17.0 | 4641 | 0.1403 | 0.7903 | 0.6445 | 0.2616 | 0.001 |
|
| 74 |
+
| 0.1536 | 18.0 | 4914 | 0.1404 | 0.7929 | 0.6464 | 0.2602 | 0.001 |
|
| 75 |
+
| 0.1556 | 19.0 | 5187 | 0.1404 | 0.7936 | 0.6526 | 0.2585 | 0.001 |
|
| 76 |
+
| 0.1556 | 20.0 | 5460 | 0.1391 | 0.7900 | 0.6491 | 0.2550 | 0.001 |
|
| 77 |
+
| 0.1534 | 21.0 | 5733 | 0.1383 | 0.7917 | 0.6508 | 0.2581 | 0.001 |
|
| 78 |
+
| 0.1533 | 22.0 | 6006 | 0.1389 | 0.7935 | 0.6489 | 0.2685 | 0.001 |
|
| 79 |
+
| 0.1533 | 23.0 | 6279 | 0.1385 | 0.7843 | 0.6550 | 0.2561 | 0.001 |
|
| 80 |
+
| 0.1531 | 24.0 | 6552 | 0.1367 | 0.7921 | 0.6507 | 0.2696 | 0.001 |
|
| 81 |
+
| 0.1531 | 25.0 | 6825 | 0.1379 | 0.7894 | 0.6408 | 0.2751 | 0.001 |
|
| 82 |
+
| 0.1533 | 26.0 | 7098 | 0.1375 | 0.7943 | 0.6469 | 0.2710 | 0.001 |
|
| 83 |
+
| 0.1533 | 27.0 | 7371 | 0.1392 | 0.7921 | 0.6516 | 0.2644 | 0.001 |
|
| 84 |
+
| 0.1529 | 28.0 | 7644 | 0.1385 | 0.7918 | 0.6425 | 0.2637 | 0.001 |
|
| 85 |
+
| 0.1529 | 29.0 | 7917 | 0.1402 | 0.7883 | 0.6497 | 0.2626 | 0.001 |
|
| 86 |
+
| 0.153 | 30.0 | 8190 | 0.1377 | 0.7887 | 0.6553 | 0.2668 | 0.001 |
|
| 87 |
+
| 0.153 | 31.0 | 8463 | 0.1313 | 0.8018 | 0.6718 | 0.2789 | 0.0001 |
|
| 88 |
+
| 0.1486 | 32.0 | 8736 | 0.1318 | 0.8061 | 0.6772 | 0.2807 | 0.0001 |
|
| 89 |
+
| 0.1415 | 33.0 | 9009 | 0.1309 | 0.8050 | 0.6792 | 0.2775 | 0.0001 |
|
| 90 |
+
| 0.1415 | 34.0 | 9282 | 0.1296 | 0.8049 | 0.6775 | 0.2821 | 0.0001 |
|
| 91 |
+
| 0.1395 | 35.0 | 9555 | 0.1282 | 0.8085 | 0.6865 | 0.2893 | 0.0001 |
|
| 92 |
+
| 0.1395 | 36.0 | 9828 | 0.1289 | 0.8055 | 0.6828 | 0.2831 | 0.0001 |
|
| 93 |
+
| 0.1387 | 37.0 | 10101 | 0.1277 | 0.8055 | 0.6775 | 0.2831 | 0.0001 |
|
| 94 |
+
| 0.1387 | 38.0 | 10374 | 0.1275 | 0.8084 | 0.6883 | 0.2890 | 0.0001 |
|
| 95 |
+
| 0.1354 | 39.0 | 10647 | 0.1266 | 0.8099 | 0.6854 | 0.2879 | 0.0001 |
|
| 96 |
+
| 0.1354 | 40.0 | 10920 | 0.1282 | 0.8117 | 0.6981 | 0.2886 | 0.0001 |
|
| 97 |
+
| 0.1355 | 41.0 | 11193 | 0.1267 | 0.8082 | 0.6851 | 0.2883 | 0.0001 |
|
| 98 |
+
| 0.1355 | 42.0 | 11466 | 0.1262 | 0.8112 | 0.6942 | 0.2907 | 0.0001 |
|
| 99 |
+
| 0.1347 | 43.0 | 11739 | 0.1259 | 0.8107 | 0.6908 | 0.2911 | 0.0001 |
|
| 100 |
+
| 0.1337 | 44.0 | 12012 | 0.1264 | 0.8115 | 0.6925 | 0.2931 | 0.0001 |
|
| 101 |
+
| 0.1337 | 45.0 | 12285 | 0.1258 | 0.8110 | 0.6975 | 0.2966 | 0.0001 |
|
| 102 |
+
| 0.1329 | 46.0 | 12558 | 0.1254 | 0.8109 | 0.6941 | 0.2987 | 0.0001 |
|
| 103 |
+
| 0.1329 | 47.0 | 12831 | 0.1257 | 0.8098 | 0.6937 | 0.2921 | 0.0001 |
|
| 104 |
+
| 0.1331 | 48.0 | 13104 | 0.1254 | 0.8107 | 0.6905 | 0.2914 | 0.0001 |
|
| 105 |
+
| 0.1331 | 49.0 | 13377 | 0.1252 | 0.8137 | 0.6974 | 0.2945 | 0.0001 |
|
| 106 |
+
| 0.1309 | 50.0 | 13650 | 0.1248 | 0.8150 | 0.7026 | 0.2983 | 0.0001 |
|
| 107 |
+
| 0.1309 | 51.0 | 13923 | 0.1246 | 0.8158 | 0.7067 | 0.2959 | 0.0001 |
|
| 108 |
+
| 0.1304 | 52.0 | 14196 | 0.1246 | 0.8121 | 0.7009 | 0.2952 | 0.0001 |
|
| 109 |
+
| 0.1304 | 53.0 | 14469 | 0.1242 | 0.8143 | 0.6974 | 0.2990 | 0.0001 |
|
| 110 |
+
| 0.1309 | 54.0 | 14742 | 0.1241 | 0.8135 | 0.7001 | 0.2966 | 0.0001 |
|
| 111 |
+
| 0.1289 | 55.0 | 15015 | 0.1242 | 0.8131 | 0.6997 | 0.2952 | 0.0001 |
|
| 112 |
+
| 0.1289 | 56.0 | 15288 | 0.1235 | 0.8179 | 0.7064 | 0.3021 | 0.0001 |
|
| 113 |
+
| 0.1286 | 57.0 | 15561 | 0.1235 | 0.8150 | 0.6963 | 0.2994 | 0.0001 |
|
| 114 |
+
| 0.1286 | 58.0 | 15834 | 0.1231 | 0.8145 | 0.7012 | 0.2983 | 0.0001 |
|
| 115 |
+
| 0.1282 | 59.0 | 16107 | 0.1234 | 0.8153 | 0.7022 | 0.3001 | 0.0001 |
|
| 116 |
+
| 0.1282 | 60.0 | 16380 | 0.1239 | 0.8122 | 0.6978 | 0.2973 | 0.0001 |
|
| 117 |
+
| 0.1282 | 61.0 | 16653 | 0.1236 | 0.8158 | 0.7114 | 0.3015 | 0.0001 |
|
| 118 |
+
| 0.1282 | 62.0 | 16926 | 0.1227 | 0.8168 | 0.7120 | 0.3032 | 0.0001 |
|
| 119 |
+
| 0.1265 | 63.0 | 17199 | 0.1231 | 0.8137 | 0.7077 | 0.2949 | 0.0001 |
|
| 120 |
+
| 0.1265 | 64.0 | 17472 | 0.1228 | 0.8172 | 0.7084 | 0.3056 | 0.0001 |
|
| 121 |
+
| 0.1273 | 65.0 | 17745 | 0.1232 | 0.8183 | 0.7103 | 0.3077 | 0.0001 |
|
| 122 |
+
| 0.1258 | 66.0 | 18018 | 0.1226 | 0.8179 | 0.7065 | 0.3035 | 0.0001 |
|
| 123 |
+
| 0.1258 | 67.0 | 18291 | 0.1228 | 0.8185 | 0.7105 | 0.3053 | 0.0001 |
|
| 124 |
+
| 0.125 | 68.0 | 18564 | 0.1228 | 0.8181 | 0.7128 | 0.3042 | 0.0001 |
|
| 125 |
+
| 0.125 | 69.0 | 18837 | 0.1228 | 0.8137 | 0.7038 | 0.3053 | 0.0001 |
|
| 126 |
+
| 0.125 | 70.0 | 19110 | 0.1232 | 0.8155 | 0.7080 | 0.3018 | 0.0001 |
|
| 127 |
+
| 0.125 | 71.0 | 19383 | 0.1231 | 0.8156 | 0.7111 | 0.2990 | 0.0001 |
|
| 128 |
+
| 0.1245 | 72.0 | 19656 | 0.1223 | 0.8162 | 0.7150 | 0.3008 | 0.0001 |
|
| 129 |
+
| 0.1245 | 73.0 | 19929 | 0.1223 | 0.8174 | 0.7042 | 0.3049 | 0.0001 |
|
| 130 |
+
| 0.1248 | 74.0 | 20202 | 0.1237 | 0.8125 | 0.7009 | 0.2963 | 0.0001 |
|
| 131 |
+
| 0.1248 | 75.0 | 20475 | 0.1225 | 0.8152 | 0.7045 | 0.3046 | 0.0001 |
|
| 132 |
+
| 0.1249 | 76.0 | 20748 | 0.1247 | 0.8160 | 0.7099 | 0.3008 | 0.0001 |
|
| 133 |
+
| 0.1238 | 77.0 | 21021 | 0.1225 | 0.8179 | 0.7139 | 0.2990 | 0.0001 |
|
| 134 |
+
| 0.1238 | 78.0 | 21294 | 0.1222 | 0.8188 | 0.7061 | 0.3046 | 0.0001 |
|
| 135 |
+
| 0.1233 | 79.0 | 21567 | 0.1246 | 0.8152 | 0.7101 | 0.3018 | 0.0001 |
|
| 136 |
+
| 0.1233 | 80.0 | 21840 | 0.1221 | 0.8180 | 0.7103 | 0.3039 | 0.0001 |
|
| 137 |
+
| 0.1225 | 81.0 | 22113 | 0.1212 | 0.8185 | 0.7157 | 0.3018 | 0.0001 |
|
| 138 |
+
| 0.1225 | 82.0 | 22386 | 0.1216 | 0.8152 | 0.7089 | 0.3080 | 0.0001 |
|
| 139 |
+
| 0.1216 | 83.0 | 22659 | 0.1214 | 0.8165 | 0.7090 | 0.3080 | 0.0001 |
|
| 140 |
+
| 0.1216 | 84.0 | 22932 | 0.1216 | 0.8169 | 0.7100 | 0.3070 | 0.0001 |
|
| 141 |
+
| 0.1232 | 85.0 | 23205 | 0.1216 | 0.8188 | 0.7109 | 0.3053 | 0.0001 |
|
| 142 |
+
| 0.1232 | 86.0 | 23478 | 0.1219 | 0.8191 | 0.7176 | 0.3070 | 0.0001 |
|
| 143 |
+
| 0.1221 | 87.0 | 23751 | 0.1220 | 0.8177 | 0.7080 | 0.3063 | 0.0001 |
|
| 144 |
+
| 0.1208 | 88.0 | 24024 | 0.1210 | 0.8211 | 0.7158 | 0.3049 | 1e-05 |
|
| 145 |
+
| 0.1208 | 89.0 | 24297 | 0.1210 | 0.8241 | 0.7312 | 0.3073 | 1e-05 |
|
| 146 |
+
| 0.1189 | 90.0 | 24570 | 0.1206 | 0.8235 | 0.7232 | 0.3070 | 1e-05 |
|
| 147 |
+
| 0.1189 | 91.0 | 24843 | 0.1204 | 0.8191 | 0.7148 | 0.3087 | 1e-05 |
|
| 148 |
+
| 0.1181 | 92.0 | 25116 | 0.1203 | 0.8194 | 0.7132 | 0.3087 | 1e-05 |
|
| 149 |
+
| 0.1181 | 93.0 | 25389 | 0.1204 | 0.8215 | 0.7184 | 0.3084 | 1e-05 |
|
| 150 |
+
| 0.1183 | 94.0 | 25662 | 0.1201 | 0.8207 | 0.7195 | 0.3067 | 1e-05 |
|
| 151 |
+
| 0.1183 | 95.0 | 25935 | 0.1201 | 0.8197 | 0.7158 | 0.3084 | 1e-05 |
|
| 152 |
+
| 0.117 | 96.0 | 26208 | 0.1198 | 0.8217 | 0.7193 | 0.3053 | 1e-05 |
|
| 153 |
+
| 0.117 | 97.0 | 26481 | 0.1201 | 0.8205 | 0.7211 | 0.3063 | 1e-05 |
|
| 154 |
+
| 0.1176 | 98.0 | 26754 | 0.1201 | 0.8227 | 0.7250 | 0.3080 | 1e-05 |
|
| 155 |
+
| 0.1176 | 99.0 | 27027 | 0.1200 | 0.8206 | 0.7226 | 0.3073 | 1e-05 |
|
| 156 |
+
| 0.1176 | 100.0 | 27300 | 0.1200 | 0.8216 | 0.7191 | 0.3080 | 1e-05 |
|
| 157 |
+
| 0.117 | 101.0 | 27573 | 0.1199 | 0.8228 | 0.7242 | 0.3098 | 1e-05 |
|
| 158 |
+
| 0.117 | 102.0 | 27846 | 0.1204 | 0.8192 | 0.7216 | 0.3073 | 1e-05 |
|
| 159 |
+
| 0.1159 | 103.0 | 28119 | 0.1200 | 0.8222 | 0.7232 | 0.3067 | 0.0000 |
|
| 160 |
+
| 0.1159 | 104.0 | 28392 | 0.1204 | 0.8218 | 0.7235 | 0.3101 | 0.0000 |
|
| 161 |
+
| 0.1151 | 105.0 | 28665 | 0.1199 | 0.8219 | 0.7206 | 0.3077 | 0.0000 |
|
| 162 |
+
| 0.1151 | 106.0 | 28938 | 0.1198 | 0.8228 | 0.7270 | 0.3105 | 0.0000 |
|
| 163 |
+
|
| 164 |
+
|
| 165 |
+
### Framework versions
|
| 166 |
+
|
| 167 |
+
- Transformers 4.44.2
|
| 168 |
+
- Pytorch 2.4.1+cu121
|
| 169 |
+
- Datasets 3.0.0
|
| 170 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 106.0,
|
| 3 |
+
"eval_accuracy": 0.3134948096885813,
|
| 4 |
+
"eval_f1_macro": 0.7190539348139566,
|
| 5 |
+
"eval_f1_micro": 0.8213781065580583,
|
| 6 |
+
"eval_loss": 0.12041561305522919,
|
| 7 |
+
"eval_runtime": 583.846,
|
| 8 |
+
"eval_samples_per_second": 4.95,
|
| 9 |
+
"eval_steps_per_second": 0.156,
|
| 10 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 11 |
+
"total_flos": 1.3699618367216817e+21,
|
| 12 |
+
"train_loss": 0.13672988786670365,
|
| 13 |
+
"train_runtime": 251282.626,
|
| 14 |
+
"train_samples_per_second": 5.203,
|
| 15 |
+
"train_steps_per_second": 0.163
|
| 16 |
+
}
|
logs/events.out.tfevents.1727136392.datavisu4
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 sha256:895059fb3d2cba7898ea858e4caf116fe841f3f5c45c2bc11866a3c423c23767
|
| 3 |
+
size 71496
|
logs/events.out.tfevents.1727388366.datavisu4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f994b42ffba6f2d6ad10c45aea2f57dae76dea4726a8b6e500fa2538a6bc6eea
|
| 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 sha256:40f6bbb3150482fc01936b48a8545486303d283ab3c157fdb5334fb65ca6e0f6
|
| 3 |
size 1228107508
|
test_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 106.0,
|
| 3 |
+
"eval_accuracy": 0.3134948096885813,
|
| 4 |
+
"eval_f1_macro": 0.7190539348139566,
|
| 5 |
+
"eval_f1_micro": 0.8213781065580583,
|
| 6 |
+
"eval_loss": 0.12041561305522919,
|
| 7 |
+
"eval_runtime": 583.846,
|
| 8 |
+
"eval_samples_per_second": 4.95,
|
| 9 |
+
"eval_steps_per_second": 0.156,
|
| 10 |
+
"learning_rate": 1.0000000000000002e-06
|
| 11 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 106.0,
|
| 3 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 4 |
+
"total_flos": 1.3699618367216817e+21,
|
| 5 |
+
"train_loss": 0.13672988786670365,
|
| 6 |
+
"train_runtime": 251282.626,
|
| 7 |
+
"train_samples_per_second": 5.203,
|
| 8 |
+
"train_steps_per_second": 0.163
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1723 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.1198035180568695,
|
| 3 |
+
"best_model_checkpoint": "DinoVdeauTest-large-2024_09_24-batch-size32_freeze/checkpoint-26208",
|
| 4 |
+
"epoch": 106.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 28938,
|
| 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": 0.2169092169092169,
|
| 14 |
+
"eval_f1_macro": 0.5520222156367808,
|
| 15 |
+
"eval_f1_micro": 0.7485599799649386,
|
| 16 |
+
"eval_loss": 0.17755262553691864,
|
| 17 |
+
"eval_runtime": 583.8306,
|
| 18 |
+
"eval_samples_per_second": 4.943,
|
| 19 |
+
"eval_steps_per_second": 0.156,
|
| 20 |
+
"learning_rate": 0.001,
|
| 21 |
+
"step": 273
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 1.8315018315018317,
|
| 25 |
+
"grad_norm": 0.2782972455024719,
|
| 26 |
+
"learning_rate": 0.001,
|
| 27 |
+
"loss": 0.2736,
|
| 28 |
+
"step": 500
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 2.0,
|
| 32 |
+
"eval_accuracy": 0.24047124047124047,
|
| 33 |
+
"eval_f1_macro": 0.5698350844395493,
|
| 34 |
+
"eval_f1_micro": 0.7693301744561706,
|
| 35 |
+
"eval_loss": 0.15282750129699707,
|
| 36 |
+
"eval_runtime": 589.1224,
|
| 37 |
+
"eval_samples_per_second": 4.899,
|
| 38 |
+
"eval_steps_per_second": 0.154,
|
| 39 |
+
"learning_rate": 0.001,
|
| 40 |
+
"step": 546
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 3.0,
|
| 44 |
+
"eval_accuracy": 0.2494802494802495,
|
| 45 |
+
"eval_f1_macro": 0.6216984689952817,
|
| 46 |
+
"eval_f1_micro": 0.7773639211038686,
|
| 47 |
+
"eval_loss": 0.14834792912006378,
|
| 48 |
+
"eval_runtime": 584.7179,
|
| 49 |
+
"eval_samples_per_second": 4.936,
|
| 50 |
+
"eval_steps_per_second": 0.156,
|
| 51 |
+
"learning_rate": 0.001,
|
| 52 |
+
"step": 819
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 3.663003663003663,
|
| 56 |
+
"grad_norm": 0.260547012090683,
|
| 57 |
+
"learning_rate": 0.001,
|
| 58 |
+
"loss": 0.1699,
|
| 59 |
+
"step": 1000
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 4.0,
|
| 63 |
+
"eval_accuracy": 0.2553707553707554,
|
| 64 |
+
"eval_f1_macro": 0.6272242063327677,
|
| 65 |
+
"eval_f1_micro": 0.777158535539741,
|
| 66 |
+
"eval_loss": 0.1467081755399704,
|
| 67 |
+
"eval_runtime": 581.5001,
|
| 68 |
+
"eval_samples_per_second": 4.963,
|
| 69 |
+
"eval_steps_per_second": 0.156,
|
| 70 |
+
"learning_rate": 0.001,
|
| 71 |
+
"step": 1092
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 5.0,
|
| 75 |
+
"eval_accuracy": 0.24636174636174638,
|
| 76 |
+
"eval_f1_macro": 0.6281234234815563,
|
| 77 |
+
"eval_f1_micro": 0.7772219080349763,
|
| 78 |
+
"eval_loss": 0.1453460305929184,
|
| 79 |
+
"eval_runtime": 586.5696,
|
| 80 |
+
"eval_samples_per_second": 4.92,
|
| 81 |
+
"eval_steps_per_second": 0.155,
|
| 82 |
+
"learning_rate": 0.001,
|
| 83 |
+
"step": 1365
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 5.4945054945054945,
|
| 87 |
+
"grad_norm": 0.18768520653247833,
|
| 88 |
+
"learning_rate": 0.001,
|
| 89 |
+
"loss": 0.1622,
|
| 90 |
+
"step": 1500
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 6.0,
|
| 94 |
+
"eval_accuracy": 0.262993762993763,
|
| 95 |
+
"eval_f1_macro": 0.6191104313765434,
|
| 96 |
+
"eval_f1_micro": 0.7809704878364948,
|
| 97 |
+
"eval_loss": 0.14370940625667572,
|
| 98 |
+
"eval_runtime": 588.2849,
|
| 99 |
+
"eval_samples_per_second": 4.906,
|
| 100 |
+
"eval_steps_per_second": 0.155,
|
| 101 |
+
"learning_rate": 0.001,
|
| 102 |
+
"step": 1638
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 7.0,
|
| 106 |
+
"eval_accuracy": 0.2598752598752599,
|
| 107 |
+
"eval_f1_macro": 0.6172423187752968,
|
| 108 |
+
"eval_f1_micro": 0.7811054928907905,
|
| 109 |
+
"eval_loss": 0.14275749027729034,
|
| 110 |
+
"eval_runtime": 590.2652,
|
| 111 |
+
"eval_samples_per_second": 4.889,
|
| 112 |
+
"eval_steps_per_second": 0.154,
|
| 113 |
+
"learning_rate": 0.001,
|
| 114 |
+
"step": 1911
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 7.326007326007326,
|
| 118 |
+
"grad_norm": 0.21249784529209137,
|
| 119 |
+
"learning_rate": 0.001,
|
| 120 |
+
"loss": 0.1593,
|
| 121 |
+
"step": 2000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 8.0,
|
| 125 |
+
"eval_accuracy": 0.25571725571725573,
|
| 126 |
+
"eval_f1_macro": 0.6252572102986063,
|
| 127 |
+
"eval_f1_micro": 0.7799277605779154,
|
| 128 |
+
"eval_loss": 0.1432911604642868,
|
| 129 |
+
"eval_runtime": 589.0928,
|
| 130 |
+
"eval_samples_per_second": 4.899,
|
| 131 |
+
"eval_steps_per_second": 0.154,
|
| 132 |
+
"learning_rate": 0.001,
|
| 133 |
+
"step": 2184
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 9.0,
|
| 137 |
+
"eval_accuracy": 0.25190575190575193,
|
| 138 |
+
"eval_f1_macro": 0.6529741984810739,
|
| 139 |
+
"eval_f1_micro": 0.7892645815722739,
|
| 140 |
+
"eval_loss": 0.14202255010604858,
|
| 141 |
+
"eval_runtime": 586.5195,
|
| 142 |
+
"eval_samples_per_second": 4.921,
|
| 143 |
+
"eval_steps_per_second": 0.155,
|
| 144 |
+
"learning_rate": 0.001,
|
| 145 |
+
"step": 2457
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 9.157509157509157,
|
| 149 |
+
"grad_norm": 0.19528812170028687,
|
| 150 |
+
"learning_rate": 0.001,
|
| 151 |
+
"loss": 0.1569,
|
| 152 |
+
"step": 2500
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 10.0,
|
| 156 |
+
"eval_accuracy": 0.2553707553707554,
|
| 157 |
+
"eval_f1_macro": 0.6021759252294137,
|
| 158 |
+
"eval_f1_micro": 0.7441173839133935,
|
| 159 |
+
"eval_loss": 0.24619852006435394,
|
| 160 |
+
"eval_runtime": 594.8068,
|
| 161 |
+
"eval_samples_per_second": 4.852,
|
| 162 |
+
"eval_steps_per_second": 0.153,
|
| 163 |
+
"learning_rate": 0.001,
|
| 164 |
+
"step": 2730
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 10.989010989010989,
|
| 168 |
+
"grad_norm": 0.16383688151836395,
|
| 169 |
+
"learning_rate": 0.001,
|
| 170 |
+
"loss": 0.156,
|
| 171 |
+
"step": 3000
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 11.0,
|
| 175 |
+
"eval_accuracy": 0.2702702702702703,
|
| 176 |
+
"eval_f1_macro": 0.6483450509947135,
|
| 177 |
+
"eval_f1_micro": 0.7882727742379886,
|
| 178 |
+
"eval_loss": 0.14001792669296265,
|
| 179 |
+
"eval_runtime": 585.5736,
|
| 180 |
+
"eval_samples_per_second": 4.929,
|
| 181 |
+
"eval_steps_per_second": 0.155,
|
| 182 |
+
"learning_rate": 0.001,
|
| 183 |
+
"step": 3003
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 12.0,
|
| 187 |
+
"eval_accuracy": 0.2598752598752599,
|
| 188 |
+
"eval_f1_macro": 0.6590290067827226,
|
| 189 |
+
"eval_f1_micro": 0.7905884326636748,
|
| 190 |
+
"eval_loss": 0.13999028503894806,
|
| 191 |
+
"eval_runtime": 594.5312,
|
| 192 |
+
"eval_samples_per_second": 4.854,
|
| 193 |
+
"eval_steps_per_second": 0.153,
|
| 194 |
+
"learning_rate": 0.001,
|
| 195 |
+
"step": 3276
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 12.820512820512821,
|
| 199 |
+
"grad_norm": 0.164137601852417,
|
| 200 |
+
"learning_rate": 0.001,
|
| 201 |
+
"loss": 0.1547,
|
| 202 |
+
"step": 3500
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 13.0,
|
| 206 |
+
"eval_accuracy": 0.2643797643797644,
|
| 207 |
+
"eval_f1_macro": 0.6466696619852873,
|
| 208 |
+
"eval_f1_micro": 0.7875647668393783,
|
| 209 |
+
"eval_loss": 0.13937941193580627,
|
| 210 |
+
"eval_runtime": 616.229,
|
| 211 |
+
"eval_samples_per_second": 4.683,
|
| 212 |
+
"eval_steps_per_second": 0.148,
|
| 213 |
+
"learning_rate": 0.001,
|
| 214 |
+
"step": 3549
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 14.0,
|
| 218 |
+
"eval_accuracy": 0.26403326403326405,
|
| 219 |
+
"eval_f1_macro": 0.6469191780902835,
|
| 220 |
+
"eval_f1_micro": 0.7879462374796679,
|
| 221 |
+
"eval_loss": 0.13986562192440033,
|
| 222 |
+
"eval_runtime": 604.9775,
|
| 223 |
+
"eval_samples_per_second": 4.77,
|
| 224 |
+
"eval_steps_per_second": 0.15,
|
| 225 |
+
"learning_rate": 0.001,
|
| 226 |
+
"step": 3822
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 14.652014652014651,
|
| 230 |
+
"grad_norm": 0.17560669779777527,
|
| 231 |
+
"learning_rate": 0.001,
|
| 232 |
+
"loss": 0.1543,
|
| 233 |
+
"step": 4000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 15.0,
|
| 237 |
+
"eval_accuracy": 0.2512127512127512,
|
| 238 |
+
"eval_f1_macro": 0.6413408300553888,
|
| 239 |
+
"eval_f1_micro": 0.7881215116526777,
|
| 240 |
+
"eval_loss": 0.13914281129837036,
|
| 241 |
+
"eval_runtime": 609.152,
|
| 242 |
+
"eval_samples_per_second": 4.738,
|
| 243 |
+
"eval_steps_per_second": 0.149,
|
| 244 |
+
"learning_rate": 0.001,
|
| 245 |
+
"step": 4095
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 16.0,
|
| 249 |
+
"eval_accuracy": 0.26334026334026334,
|
| 250 |
+
"eval_f1_macro": 0.6347762053394217,
|
| 251 |
+
"eval_f1_micro": 0.7906518010291596,
|
| 252 |
+
"eval_loss": 0.14137022197246552,
|
| 253 |
+
"eval_runtime": 599.9977,
|
| 254 |
+
"eval_samples_per_second": 4.81,
|
| 255 |
+
"eval_steps_per_second": 0.152,
|
| 256 |
+
"learning_rate": 0.001,
|
| 257 |
+
"step": 4368
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 16.483516483516482,
|
| 261 |
+
"grad_norm": 0.16528823971748352,
|
| 262 |
+
"learning_rate": 0.001,
|
| 263 |
+
"loss": 0.1536,
|
| 264 |
+
"step": 4500
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 17.0,
|
| 268 |
+
"eval_accuracy": 0.2616077616077616,
|
| 269 |
+
"eval_f1_macro": 0.6445091939759507,
|
| 270 |
+
"eval_f1_micro": 0.7903470350404312,
|
| 271 |
+
"eval_loss": 0.14031356573104858,
|
| 272 |
+
"eval_runtime": 579.4575,
|
| 273 |
+
"eval_samples_per_second": 4.981,
|
| 274 |
+
"eval_steps_per_second": 0.157,
|
| 275 |
+
"learning_rate": 0.001,
|
| 276 |
+
"step": 4641
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 18.0,
|
| 280 |
+
"eval_accuracy": 0.26022176022176025,
|
| 281 |
+
"eval_f1_macro": 0.6463740590949281,
|
| 282 |
+
"eval_f1_micro": 0.792909822326517,
|
| 283 |
+
"eval_loss": 0.14039942622184753,
|
| 284 |
+
"eval_runtime": 586.9618,
|
| 285 |
+
"eval_samples_per_second": 4.917,
|
| 286 |
+
"eval_steps_per_second": 0.155,
|
| 287 |
+
"learning_rate": 0.001,
|
| 288 |
+
"step": 4914
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 18.315018315018314,
|
| 292 |
+
"grad_norm": 0.17777948081493378,
|
| 293 |
+
"learning_rate": 0.001,
|
| 294 |
+
"loss": 0.1556,
|
| 295 |
+
"step": 5000
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 19.0,
|
| 299 |
+
"eval_accuracy": 0.25848925848925847,
|
| 300 |
+
"eval_f1_macro": 0.6526097604635809,
|
| 301 |
+
"eval_f1_micro": 0.7935513900055008,
|
| 302 |
+
"eval_loss": 0.14035724103450775,
|
| 303 |
+
"eval_runtime": 574.4193,
|
| 304 |
+
"eval_samples_per_second": 5.024,
|
| 305 |
+
"eval_steps_per_second": 0.158,
|
| 306 |
+
"learning_rate": 0.001,
|
| 307 |
+
"step": 5187
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 20.0,
|
| 311 |
+
"eval_accuracy": 0.255024255024255,
|
| 312 |
+
"eval_f1_macro": 0.6491113591903472,
|
| 313 |
+
"eval_f1_micro": 0.7900462566386842,
|
| 314 |
+
"eval_loss": 0.1390993297100067,
|
| 315 |
+
"eval_runtime": 576.4077,
|
| 316 |
+
"eval_samples_per_second": 5.007,
|
| 317 |
+
"eval_steps_per_second": 0.158,
|
| 318 |
+
"learning_rate": 0.001,
|
| 319 |
+
"step": 5460
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 20.146520146520146,
|
| 323 |
+
"grad_norm": 0.14455388486385345,
|
| 324 |
+
"learning_rate": 0.001,
|
| 325 |
+
"loss": 0.1534,
|
| 326 |
+
"step": 5500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 21.0,
|
| 330 |
+
"eval_accuracy": 0.25814275814275817,
|
| 331 |
+
"eval_f1_macro": 0.6507882842254223,
|
| 332 |
+
"eval_f1_micro": 0.7916862276471341,
|
| 333 |
+
"eval_loss": 0.13827534019947052,
|
| 334 |
+
"eval_runtime": 598.284,
|
| 335 |
+
"eval_samples_per_second": 4.824,
|
| 336 |
+
"eval_steps_per_second": 0.152,
|
| 337 |
+
"learning_rate": 0.001,
|
| 338 |
+
"step": 5733
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 21.978021978021978,
|
| 342 |
+
"grad_norm": 0.1771659553050995,
|
| 343 |
+
"learning_rate": 0.001,
|
| 344 |
+
"loss": 0.1533,
|
| 345 |
+
"step": 6000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 22.0,
|
| 349 |
+
"eval_accuracy": 0.26853776853776856,
|
| 350 |
+
"eval_f1_macro": 0.6489112697391156,
|
| 351 |
+
"eval_f1_micro": 0.7935178133197935,
|
| 352 |
+
"eval_loss": 0.13889800012111664,
|
| 353 |
+
"eval_runtime": 594.9509,
|
| 354 |
+
"eval_samples_per_second": 4.851,
|
| 355 |
+
"eval_steps_per_second": 0.153,
|
| 356 |
+
"learning_rate": 0.001,
|
| 357 |
+
"step": 6006
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 23.0,
|
| 361 |
+
"eval_accuracy": 0.2560637560637561,
|
| 362 |
+
"eval_f1_macro": 0.6549504216490796,
|
| 363 |
+
"eval_f1_micro": 0.7842915050342152,
|
| 364 |
+
"eval_loss": 0.1385144591331482,
|
| 365 |
+
"eval_runtime": 583.6881,
|
| 366 |
+
"eval_samples_per_second": 4.944,
|
| 367 |
+
"eval_steps_per_second": 0.156,
|
| 368 |
+
"learning_rate": 0.001,
|
| 369 |
+
"step": 6279
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 23.80952380952381,
|
| 373 |
+
"grad_norm": 0.17443060874938965,
|
| 374 |
+
"learning_rate": 0.001,
|
| 375 |
+
"loss": 0.1531,
|
| 376 |
+
"step": 6500
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 24.0,
|
| 380 |
+
"eval_accuracy": 0.2695772695772696,
|
| 381 |
+
"eval_f1_macro": 0.6507209930045859,
|
| 382 |
+
"eval_f1_micro": 0.7921174652241113,
|
| 383 |
+
"eval_loss": 0.13674499094486237,
|
| 384 |
+
"eval_runtime": 574.2321,
|
| 385 |
+
"eval_samples_per_second": 5.026,
|
| 386 |
+
"eval_steps_per_second": 0.158,
|
| 387 |
+
"learning_rate": 0.001,
|
| 388 |
+
"step": 6552
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 25.0,
|
| 392 |
+
"eval_accuracy": 0.2751212751212751,
|
| 393 |
+
"eval_f1_macro": 0.6408412361180978,
|
| 394 |
+
"eval_f1_micro": 0.7893792922444337,
|
| 395 |
+
"eval_loss": 0.13791973888874054,
|
| 396 |
+
"eval_runtime": 577.6745,
|
| 397 |
+
"eval_samples_per_second": 4.996,
|
| 398 |
+
"eval_steps_per_second": 0.158,
|
| 399 |
+
"learning_rate": 0.001,
|
| 400 |
+
"step": 6825
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 25.641025641025642,
|
| 404 |
+
"grad_norm": 0.16064241528511047,
|
| 405 |
+
"learning_rate": 0.001,
|
| 406 |
+
"loss": 0.1533,
|
| 407 |
+
"step": 7000
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 26.0,
|
| 411 |
+
"eval_accuracy": 0.27096327096327094,
|
| 412 |
+
"eval_f1_macro": 0.6468889221342444,
|
| 413 |
+
"eval_f1_micro": 0.7942844956280657,
|
| 414 |
+
"eval_loss": 0.1375003606081009,
|
| 415 |
+
"eval_runtime": 576.2047,
|
| 416 |
+
"eval_samples_per_second": 5.009,
|
| 417 |
+
"eval_steps_per_second": 0.158,
|
| 418 |
+
"learning_rate": 0.001,
|
| 419 |
+
"step": 7098
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 27.0,
|
| 423 |
+
"eval_accuracy": 0.2643797643797644,
|
| 424 |
+
"eval_f1_macro": 0.6516252219978993,
|
| 425 |
+
"eval_f1_micro": 0.7921208479958802,
|
| 426 |
+
"eval_loss": 0.13920167088508606,
|
| 427 |
+
"eval_runtime": 574.3969,
|
| 428 |
+
"eval_samples_per_second": 5.024,
|
| 429 |
+
"eval_steps_per_second": 0.158,
|
| 430 |
+
"learning_rate": 0.001,
|
| 431 |
+
"step": 7371
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 27.47252747252747,
|
| 435 |
+
"grad_norm": 0.15187925100326538,
|
| 436 |
+
"learning_rate": 0.001,
|
| 437 |
+
"loss": 0.1529,
|
| 438 |
+
"step": 7500
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 28.0,
|
| 442 |
+
"eval_accuracy": 0.2636867636867637,
|
| 443 |
+
"eval_f1_macro": 0.6424574000169906,
|
| 444 |
+
"eval_f1_micro": 0.7917504599717599,
|
| 445 |
+
"eval_loss": 0.13846370577812195,
|
| 446 |
+
"eval_runtime": 583.6888,
|
| 447 |
+
"eval_samples_per_second": 4.944,
|
| 448 |
+
"eval_steps_per_second": 0.156,
|
| 449 |
+
"learning_rate": 0.001,
|
| 450 |
+
"step": 7644
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 29.0,
|
| 454 |
+
"eval_accuracy": 0.2626472626472626,
|
| 455 |
+
"eval_f1_macro": 0.6496760555529415,
|
| 456 |
+
"eval_f1_micro": 0.7883173722754258,
|
| 457 |
+
"eval_loss": 0.14017289876937866,
|
| 458 |
+
"eval_runtime": 569.4194,
|
| 459 |
+
"eval_samples_per_second": 5.068,
|
| 460 |
+
"eval_steps_per_second": 0.16,
|
| 461 |
+
"learning_rate": 0.001,
|
| 462 |
+
"step": 7917
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 29.304029304029303,
|
| 466 |
+
"grad_norm": 0.1429462879896164,
|
| 467 |
+
"learning_rate": 0.001,
|
| 468 |
+
"loss": 0.153,
|
| 469 |
+
"step": 8000
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 30.0,
|
| 473 |
+
"eval_accuracy": 0.2668052668052668,
|
| 474 |
+
"eval_f1_macro": 0.6553418932728605,
|
| 475 |
+
"eval_f1_micro": 0.788684508761224,
|
| 476 |
+
"eval_loss": 0.13773277401924133,
|
| 477 |
+
"eval_runtime": 575.6917,
|
| 478 |
+
"eval_samples_per_second": 5.013,
|
| 479 |
+
"eval_steps_per_second": 0.158,
|
| 480 |
+
"learning_rate": 0.001,
|
| 481 |
+
"step": 8190
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 31.0,
|
| 485 |
+
"eval_accuracy": 0.27893277893277896,
|
| 486 |
+
"eval_f1_macro": 0.6718196714045327,
|
| 487 |
+
"eval_f1_micro": 0.8017825006427286,
|
| 488 |
+
"eval_loss": 0.1312580555677414,
|
| 489 |
+
"eval_runtime": 580.0807,
|
| 490 |
+
"eval_samples_per_second": 4.975,
|
| 491 |
+
"eval_steps_per_second": 0.157,
|
| 492 |
+
"learning_rate": 0.0001,
|
| 493 |
+
"step": 8463
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 31.135531135531135,
|
| 497 |
+
"grad_norm": 0.1542915403842926,
|
| 498 |
+
"learning_rate": 0.0001,
|
| 499 |
+
"loss": 0.1486,
|
| 500 |
+
"step": 8500
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 32.0,
|
| 504 |
+
"eval_accuracy": 0.2806652806652807,
|
| 505 |
+
"eval_f1_macro": 0.6772473958552189,
|
| 506 |
+
"eval_f1_micro": 0.8060657118786858,
|
| 507 |
+
"eval_loss": 0.1318267583847046,
|
| 508 |
+
"eval_runtime": 567.7754,
|
| 509 |
+
"eval_samples_per_second": 5.083,
|
| 510 |
+
"eval_steps_per_second": 0.16,
|
| 511 |
+
"learning_rate": 0.0001,
|
| 512 |
+
"step": 8736
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 32.967032967032964,
|
| 516 |
+
"grad_norm": 0.1691681146621704,
|
| 517 |
+
"learning_rate": 0.0001,
|
| 518 |
+
"loss": 0.1415,
|
| 519 |
+
"step": 9000
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 33.0,
|
| 523 |
+
"eval_accuracy": 0.27754677754677753,
|
| 524 |
+
"eval_f1_macro": 0.6791810095569879,
|
| 525 |
+
"eval_f1_micro": 0.8050148746281343,
|
| 526 |
+
"eval_loss": 0.1309264600276947,
|
| 527 |
+
"eval_runtime": 573.2692,
|
| 528 |
+
"eval_samples_per_second": 5.034,
|
| 529 |
+
"eval_steps_per_second": 0.159,
|
| 530 |
+
"learning_rate": 0.0001,
|
| 531 |
+
"step": 9009
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 34.0,
|
| 535 |
+
"eval_accuracy": 0.28205128205128205,
|
| 536 |
+
"eval_f1_macro": 0.6774879025186358,
|
| 537 |
+
"eval_f1_micro": 0.804873906767428,
|
| 538 |
+
"eval_loss": 0.1296369731426239,
|
| 539 |
+
"eval_runtime": 573.8273,
|
| 540 |
+
"eval_samples_per_second": 5.029,
|
| 541 |
+
"eval_steps_per_second": 0.159,
|
| 542 |
+
"learning_rate": 0.0001,
|
| 543 |
+
"step": 9282
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 34.798534798534796,
|
| 547 |
+
"grad_norm": 0.16409221291542053,
|
| 548 |
+
"learning_rate": 0.0001,
|
| 549 |
+
"loss": 0.1395,
|
| 550 |
+
"step": 9500
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 35.0,
|
| 554 |
+
"eval_accuracy": 0.28932778932778935,
|
| 555 |
+
"eval_f1_macro": 0.6864816840760736,
|
| 556 |
+
"eval_f1_micro": 0.8084945013272659,
|
| 557 |
+
"eval_loss": 0.12816031277179718,
|
| 558 |
+
"eval_runtime": 577.8146,
|
| 559 |
+
"eval_samples_per_second": 4.995,
|
| 560 |
+
"eval_steps_per_second": 0.157,
|
| 561 |
+
"learning_rate": 0.0001,
|
| 562 |
+
"step": 9555
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 36.0,
|
| 566 |
+
"eval_accuracy": 0.2830907830907831,
|
| 567 |
+
"eval_f1_macro": 0.6827519815644174,
|
| 568 |
+
"eval_f1_micro": 0.8055151151836945,
|
| 569 |
+
"eval_loss": 0.12886497378349304,
|
| 570 |
+
"eval_runtime": 576.0485,
|
| 571 |
+
"eval_samples_per_second": 5.01,
|
| 572 |
+
"eval_steps_per_second": 0.158,
|
| 573 |
+
"learning_rate": 0.0001,
|
| 574 |
+
"step": 9828
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 36.63003663003663,
|
| 578 |
+
"grad_norm": 0.1629299372434616,
|
| 579 |
+
"learning_rate": 0.0001,
|
| 580 |
+
"loss": 0.1387,
|
| 581 |
+
"step": 10000
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 37.0,
|
| 585 |
+
"eval_accuracy": 0.2830907830907831,
|
| 586 |
+
"eval_f1_macro": 0.677476009100308,
|
| 587 |
+
"eval_f1_micro": 0.8054549328787556,
|
| 588 |
+
"eval_loss": 0.12768980860710144,
|
| 589 |
+
"eval_runtime": 578.6622,
|
| 590 |
+
"eval_samples_per_second": 4.987,
|
| 591 |
+
"eval_steps_per_second": 0.157,
|
| 592 |
+
"learning_rate": 0.0001,
|
| 593 |
+
"step": 10101
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 38.0,
|
| 597 |
+
"eval_accuracy": 0.288981288981289,
|
| 598 |
+
"eval_f1_macro": 0.6882635597933275,
|
| 599 |
+
"eval_f1_micro": 0.8084112149532711,
|
| 600 |
+
"eval_loss": 0.1274958997964859,
|
| 601 |
+
"eval_runtime": 583.3399,
|
| 602 |
+
"eval_samples_per_second": 4.947,
|
| 603 |
+
"eval_steps_per_second": 0.156,
|
| 604 |
+
"learning_rate": 0.0001,
|
| 605 |
+
"step": 10374
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 38.46153846153846,
|
| 609 |
+
"grad_norm": 0.20412367582321167,
|
| 610 |
+
"learning_rate": 0.0001,
|
| 611 |
+
"loss": 0.1354,
|
| 612 |
+
"step": 10500
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 39.0,
|
| 616 |
+
"eval_accuracy": 0.28794178794178793,
|
| 617 |
+
"eval_f1_macro": 0.6853651532137502,
|
| 618 |
+
"eval_f1_micro": 0.8099270562589084,
|
| 619 |
+
"eval_loss": 0.12658803164958954,
|
| 620 |
+
"eval_runtime": 588.9538,
|
| 621 |
+
"eval_samples_per_second": 4.9,
|
| 622 |
+
"eval_steps_per_second": 0.155,
|
| 623 |
+
"learning_rate": 0.0001,
|
| 624 |
+
"step": 10647
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 40.0,
|
| 628 |
+
"eval_accuracy": 0.28863478863478864,
|
| 629 |
+
"eval_f1_macro": 0.698146081234717,
|
| 630 |
+
"eval_f1_micro": 0.8117343111925994,
|
| 631 |
+
"eval_loss": 0.12820227444171906,
|
| 632 |
+
"eval_runtime": 583.5775,
|
| 633 |
+
"eval_samples_per_second": 4.945,
|
| 634 |
+
"eval_steps_per_second": 0.156,
|
| 635 |
+
"learning_rate": 0.0001,
|
| 636 |
+
"step": 10920
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 40.29304029304029,
|
| 640 |
+
"grad_norm": 0.1920085847377777,
|
| 641 |
+
"learning_rate": 0.0001,
|
| 642 |
+
"loss": 0.1355,
|
| 643 |
+
"step": 11000
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 41.0,
|
| 647 |
+
"eval_accuracy": 0.2882882882882883,
|
| 648 |
+
"eval_f1_macro": 0.6850722645729148,
|
| 649 |
+
"eval_f1_micro": 0.8081688455951466,
|
| 650 |
+
"eval_loss": 0.12668322026729584,
|
| 651 |
+
"eval_runtime": 580.9481,
|
| 652 |
+
"eval_samples_per_second": 4.968,
|
| 653 |
+
"eval_steps_per_second": 0.157,
|
| 654 |
+
"learning_rate": 0.0001,
|
| 655 |
+
"step": 11193
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 42.0,
|
| 659 |
+
"eval_accuracy": 0.2907137907137907,
|
| 660 |
+
"eval_f1_macro": 0.6941693850580287,
|
| 661 |
+
"eval_f1_micro": 0.8112331081081081,
|
| 662 |
+
"eval_loss": 0.12620903551578522,
|
| 663 |
+
"eval_runtime": 587.956,
|
| 664 |
+
"eval_samples_per_second": 4.909,
|
| 665 |
+
"eval_steps_per_second": 0.155,
|
| 666 |
+
"learning_rate": 0.0001,
|
| 667 |
+
"step": 11466
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 42.124542124542124,
|
| 671 |
+
"grad_norm": 0.20102928578853607,
|
| 672 |
+
"learning_rate": 0.0001,
|
| 673 |
+
"loss": 0.1347,
|
| 674 |
+
"step": 11500
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 43.0,
|
| 678 |
+
"eval_accuracy": 0.2910602910602911,
|
| 679 |
+
"eval_f1_macro": 0.69077693559172,
|
| 680 |
+
"eval_f1_micro": 0.8107360033550011,
|
| 681 |
+
"eval_loss": 0.12590545415878296,
|
| 682 |
+
"eval_runtime": 582.6431,
|
| 683 |
+
"eval_samples_per_second": 4.953,
|
| 684 |
+
"eval_steps_per_second": 0.156,
|
| 685 |
+
"learning_rate": 0.0001,
|
| 686 |
+
"step": 11739
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 43.956043956043956,
|
| 690 |
+
"grad_norm": 0.20798929035663605,
|
| 691 |
+
"learning_rate": 0.0001,
|
| 692 |
+
"loss": 0.1337,
|
| 693 |
+
"step": 12000
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 44.0,
|
| 697 |
+
"eval_accuracy": 0.29313929313929316,
|
| 698 |
+
"eval_f1_macro": 0.6925170228864211,
|
| 699 |
+
"eval_f1_micro": 0.8114530416894076,
|
| 700 |
+
"eval_loss": 0.12642185389995575,
|
| 701 |
+
"eval_runtime": 580.9769,
|
| 702 |
+
"eval_samples_per_second": 4.967,
|
| 703 |
+
"eval_steps_per_second": 0.157,
|
| 704 |
+
"learning_rate": 0.0001,
|
| 705 |
+
"step": 12012
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 45.0,
|
| 709 |
+
"eval_accuracy": 0.2966042966042966,
|
| 710 |
+
"eval_f1_macro": 0.6974852591826903,
|
| 711 |
+
"eval_f1_micro": 0.8110017663386323,
|
| 712 |
+
"eval_loss": 0.1257808804512024,
|
| 713 |
+
"eval_runtime": 587.2129,
|
| 714 |
+
"eval_samples_per_second": 4.915,
|
| 715 |
+
"eval_steps_per_second": 0.155,
|
| 716 |
+
"learning_rate": 0.0001,
|
| 717 |
+
"step": 12285
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 45.78754578754579,
|
| 721 |
+
"grad_norm": 0.21279653906822205,
|
| 722 |
+
"learning_rate": 0.0001,
|
| 723 |
+
"loss": 0.1329,
|
| 724 |
+
"step": 12500
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 46.0,
|
| 728 |
+
"eval_accuracy": 0.2986832986832987,
|
| 729 |
+
"eval_f1_macro": 0.694112624204446,
|
| 730 |
+
"eval_f1_micro": 0.8109046268467172,
|
| 731 |
+
"eval_loss": 0.12542255222797394,
|
| 732 |
+
"eval_runtime": 584.2715,
|
| 733 |
+
"eval_samples_per_second": 4.939,
|
| 734 |
+
"eval_steps_per_second": 0.156,
|
| 735 |
+
"learning_rate": 0.0001,
|
| 736 |
+
"step": 12558
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 47.0,
|
| 740 |
+
"eval_accuracy": 0.2920997920997921,
|
| 741 |
+
"eval_f1_macro": 0.6937033329875891,
|
| 742 |
+
"eval_f1_micro": 0.8098117995347853,
|
| 743 |
+
"eval_loss": 0.1256514936685562,
|
| 744 |
+
"eval_runtime": 582.8653,
|
| 745 |
+
"eval_samples_per_second": 4.951,
|
| 746 |
+
"eval_steps_per_second": 0.156,
|
| 747 |
+
"learning_rate": 0.0001,
|
| 748 |
+
"step": 12831
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 47.61904761904762,
|
| 752 |
+
"grad_norm": 0.19104164838790894,
|
| 753 |
+
"learning_rate": 0.0001,
|
| 754 |
+
"loss": 0.1331,
|
| 755 |
+
"step": 13000
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 48.0,
|
| 759 |
+
"eval_accuracy": 0.29140679140679143,
|
| 760 |
+
"eval_f1_macro": 0.6904792900172609,
|
| 761 |
+
"eval_f1_micro": 0.8106740862526874,
|
| 762 |
+
"eval_loss": 0.1253652125597,
|
| 763 |
+
"eval_runtime": 590.5724,
|
| 764 |
+
"eval_samples_per_second": 4.887,
|
| 765 |
+
"eval_steps_per_second": 0.154,
|
| 766 |
+
"learning_rate": 0.0001,
|
| 767 |
+
"step": 13104
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 49.0,
|
| 771 |
+
"eval_accuracy": 0.2945252945252945,
|
| 772 |
+
"eval_f1_macro": 0.6973960572840976,
|
| 773 |
+
"eval_f1_micro": 0.8136526746223817,
|
| 774 |
+
"eval_loss": 0.1252448409795761,
|
| 775 |
+
"eval_runtime": 596.869,
|
| 776 |
+
"eval_samples_per_second": 4.835,
|
| 777 |
+
"eval_steps_per_second": 0.152,
|
| 778 |
+
"learning_rate": 0.0001,
|
| 779 |
+
"step": 13377
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 49.45054945054945,
|
| 783 |
+
"grad_norm": 0.25627467036247253,
|
| 784 |
+
"learning_rate": 0.0001,
|
| 785 |
+
"loss": 0.1309,
|
| 786 |
+
"step": 13500
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 50.0,
|
| 790 |
+
"eval_accuracy": 0.2983367983367983,
|
| 791 |
+
"eval_f1_macro": 0.7025806374316313,
|
| 792 |
+
"eval_f1_micro": 0.814972104255142,
|
| 793 |
+
"eval_loss": 0.12482810020446777,
|
| 794 |
+
"eval_runtime": 598.3632,
|
| 795 |
+
"eval_samples_per_second": 4.823,
|
| 796 |
+
"eval_steps_per_second": 0.152,
|
| 797 |
+
"learning_rate": 0.0001,
|
| 798 |
+
"step": 13650
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 51.0,
|
| 802 |
+
"eval_accuracy": 0.2959112959112959,
|
| 803 |
+
"eval_f1_macro": 0.7066639116616246,
|
| 804 |
+
"eval_f1_micro": 0.815773054365459,
|
| 805 |
+
"eval_loss": 0.12458823621273041,
|
| 806 |
+
"eval_runtime": 578.8177,
|
| 807 |
+
"eval_samples_per_second": 4.986,
|
| 808 |
+
"eval_steps_per_second": 0.157,
|
| 809 |
+
"learning_rate": 0.0001,
|
| 810 |
+
"step": 13923
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 51.282051282051285,
|
| 814 |
+
"grad_norm": 0.2170032560825348,
|
| 815 |
+
"learning_rate": 0.0001,
|
| 816 |
+
"loss": 0.1304,
|
| 817 |
+
"step": 14000
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 52.0,
|
| 821 |
+
"eval_accuracy": 0.29521829521829523,
|
| 822 |
+
"eval_f1_macro": 0.7008785276837475,
|
| 823 |
+
"eval_f1_micro": 0.8120651620566774,
|
| 824 |
+
"eval_loss": 0.12461517751216888,
|
| 825 |
+
"eval_runtime": 581.8661,
|
| 826 |
+
"eval_samples_per_second": 4.96,
|
| 827 |
+
"eval_steps_per_second": 0.156,
|
| 828 |
+
"learning_rate": 0.0001,
|
| 829 |
+
"step": 14196
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 53.0,
|
| 833 |
+
"eval_accuracy": 0.29902979902979904,
|
| 834 |
+
"eval_f1_macro": 0.697381421827107,
|
| 835 |
+
"eval_f1_micro": 0.8142762173840784,
|
| 836 |
+
"eval_loss": 0.12417320907115936,
|
| 837 |
+
"eval_runtime": 587.3587,
|
| 838 |
+
"eval_samples_per_second": 4.914,
|
| 839 |
+
"eval_steps_per_second": 0.155,
|
| 840 |
+
"learning_rate": 0.0001,
|
| 841 |
+
"step": 14469
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 53.11355311355312,
|
| 845 |
+
"grad_norm": 0.18614046275615692,
|
| 846 |
+
"learning_rate": 0.0001,
|
| 847 |
+
"loss": 0.1309,
|
| 848 |
+
"step": 14500
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 54.0,
|
| 852 |
+
"eval_accuracy": 0.2966042966042966,
|
| 853 |
+
"eval_f1_macro": 0.7000554609843794,
|
| 854 |
+
"eval_f1_micro": 0.8135221716405328,
|
| 855 |
+
"eval_loss": 0.12411519885063171,
|
| 856 |
+
"eval_runtime": 590.4943,
|
| 857 |
+
"eval_samples_per_second": 4.887,
|
| 858 |
+
"eval_steps_per_second": 0.154,
|
| 859 |
+
"learning_rate": 0.0001,
|
| 860 |
+
"step": 14742
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 54.94505494505494,
|
| 864 |
+
"grad_norm": 0.296142578125,
|
| 865 |
+
"learning_rate": 0.0001,
|
| 866 |
+
"loss": 0.1289,
|
| 867 |
+
"step": 15000
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 55.0,
|
| 871 |
+
"eval_accuracy": 0.29521829521829523,
|
| 872 |
+
"eval_f1_macro": 0.6996806217177095,
|
| 873 |
+
"eval_f1_micro": 0.8130868668154448,
|
| 874 |
+
"eval_loss": 0.12417341023683548,
|
| 875 |
+
"eval_runtime": 580.598,
|
| 876 |
+
"eval_samples_per_second": 4.971,
|
| 877 |
+
"eval_steps_per_second": 0.157,
|
| 878 |
+
"learning_rate": 0.0001,
|
| 879 |
+
"step": 15015
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 56.0,
|
| 883 |
+
"eval_accuracy": 0.30214830214830213,
|
| 884 |
+
"eval_f1_macro": 0.7064033143378504,
|
| 885 |
+
"eval_f1_micro": 0.8178580303155802,
|
| 886 |
+
"eval_loss": 0.1234845370054245,
|
| 887 |
+
"eval_runtime": 578.4648,
|
| 888 |
+
"eval_samples_per_second": 4.989,
|
| 889 |
+
"eval_steps_per_second": 0.157,
|
| 890 |
+
"learning_rate": 0.0001,
|
| 891 |
+
"step": 15288
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 56.776556776556774,
|
| 895 |
+
"grad_norm": 0.23026500642299652,
|
| 896 |
+
"learning_rate": 0.0001,
|
| 897 |
+
"loss": 0.1286,
|
| 898 |
+
"step": 15500
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 57.0,
|
| 902 |
+
"eval_accuracy": 0.2993762993762994,
|
| 903 |
+
"eval_f1_macro": 0.6963082116005005,
|
| 904 |
+
"eval_f1_micro": 0.8150138550675959,
|
| 905 |
+
"eval_loss": 0.12350637465715408,
|
| 906 |
+
"eval_runtime": 578.6503,
|
| 907 |
+
"eval_samples_per_second": 4.987,
|
| 908 |
+
"eval_steps_per_second": 0.157,
|
| 909 |
+
"learning_rate": 0.0001,
|
| 910 |
+
"step": 15561
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 58.0,
|
| 914 |
+
"eval_accuracy": 0.2983367983367983,
|
| 915 |
+
"eval_f1_macro": 0.7011763866264856,
|
| 916 |
+
"eval_f1_micro": 0.814454598809424,
|
| 917 |
+
"eval_loss": 0.12311282008886337,
|
| 918 |
+
"eval_runtime": 575.7868,
|
| 919 |
+
"eval_samples_per_second": 5.012,
|
| 920 |
+
"eval_steps_per_second": 0.158,
|
| 921 |
+
"learning_rate": 0.0001,
|
| 922 |
+
"step": 15834
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 58.608058608058606,
|
| 926 |
+
"grad_norm": 0.2271023392677307,
|
| 927 |
+
"learning_rate": 0.0001,
|
| 928 |
+
"loss": 0.1282,
|
| 929 |
+
"step": 16000
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 59.0,
|
| 933 |
+
"eval_accuracy": 0.30006930006930005,
|
| 934 |
+
"eval_f1_macro": 0.7021882450681799,
|
| 935 |
+
"eval_f1_micro": 0.8153207895067678,
|
| 936 |
+
"eval_loss": 0.12340909987688065,
|
| 937 |
+
"eval_runtime": 574.6752,
|
| 938 |
+
"eval_samples_per_second": 5.022,
|
| 939 |
+
"eval_steps_per_second": 0.158,
|
| 940 |
+
"learning_rate": 0.0001,
|
| 941 |
+
"step": 16107
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 60.0,
|
| 945 |
+
"eval_accuracy": 0.2972972972972973,
|
| 946 |
+
"eval_f1_macro": 0.6978379224258093,
|
| 947 |
+
"eval_f1_micro": 0.8121788610981358,
|
| 948 |
+
"eval_loss": 0.12386388331651688,
|
| 949 |
+
"eval_runtime": 580.8249,
|
| 950 |
+
"eval_samples_per_second": 4.969,
|
| 951 |
+
"eval_steps_per_second": 0.157,
|
| 952 |
+
"learning_rate": 0.0001,
|
| 953 |
+
"step": 16380
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 60.43956043956044,
|
| 957 |
+
"grad_norm": 0.26319652795791626,
|
| 958 |
+
"learning_rate": 0.0001,
|
| 959 |
+
"loss": 0.1282,
|
| 960 |
+
"step": 16500
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 61.0,
|
| 964 |
+
"eval_accuracy": 0.30145530145530147,
|
| 965 |
+
"eval_f1_macro": 0.7114090358686158,
|
| 966 |
+
"eval_f1_micro": 0.8157532819337362,
|
| 967 |
+
"eval_loss": 0.12355918437242508,
|
| 968 |
+
"eval_runtime": 580.0589,
|
| 969 |
+
"eval_samples_per_second": 4.975,
|
| 970 |
+
"eval_steps_per_second": 0.157,
|
| 971 |
+
"learning_rate": 0.0001,
|
| 972 |
+
"step": 16653
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 62.0,
|
| 976 |
+
"eval_accuracy": 0.3031878031878032,
|
| 977 |
+
"eval_f1_macro": 0.7119609165997448,
|
| 978 |
+
"eval_f1_micro": 0.8168304358780549,
|
| 979 |
+
"eval_loss": 0.12266429513692856,
|
| 980 |
+
"eval_runtime": 571.7568,
|
| 981 |
+
"eval_samples_per_second": 5.048,
|
| 982 |
+
"eval_steps_per_second": 0.159,
|
| 983 |
+
"learning_rate": 0.0001,
|
| 984 |
+
"step": 16926
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 62.27106227106227,
|
| 988 |
+
"grad_norm": 0.2723998725414276,
|
| 989 |
+
"learning_rate": 0.0001,
|
| 990 |
+
"loss": 0.1265,
|
| 991 |
+
"step": 17000
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 63.0,
|
| 995 |
+
"eval_accuracy": 0.2948717948717949,
|
| 996 |
+
"eval_f1_macro": 0.7077249537938423,
|
| 997 |
+
"eval_f1_micro": 0.8136965505608501,
|
| 998 |
+
"eval_loss": 0.12305888533592224,
|
| 999 |
+
"eval_runtime": 579.5124,
|
| 1000 |
+
"eval_samples_per_second": 4.98,
|
| 1001 |
+
"eval_steps_per_second": 0.157,
|
| 1002 |
+
"learning_rate": 0.0001,
|
| 1003 |
+
"step": 17199
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 64.0,
|
| 1007 |
+
"eval_accuracy": 0.30561330561330563,
|
| 1008 |
+
"eval_f1_macro": 0.708440477929098,
|
| 1009 |
+
"eval_f1_micro": 0.8172187094342783,
|
| 1010 |
+
"eval_loss": 0.12276986986398697,
|
| 1011 |
+
"eval_runtime": 580.0855,
|
| 1012 |
+
"eval_samples_per_second": 4.975,
|
| 1013 |
+
"eval_steps_per_second": 0.157,
|
| 1014 |
+
"learning_rate": 0.0001,
|
| 1015 |
+
"step": 17472
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 64.1025641025641,
|
| 1019 |
+
"grad_norm": 0.2615499794483185,
|
| 1020 |
+
"learning_rate": 0.0001,
|
| 1021 |
+
"loss": 0.1273,
|
| 1022 |
+
"step": 17500
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 65.0,
|
| 1026 |
+
"eval_accuracy": 0.3076923076923077,
|
| 1027 |
+
"eval_f1_macro": 0.7103116175502073,
|
| 1028 |
+
"eval_f1_micro": 0.8182651445712857,
|
| 1029 |
+
"eval_loss": 0.12323789298534393,
|
| 1030 |
+
"eval_runtime": 578.4314,
|
| 1031 |
+
"eval_samples_per_second": 4.989,
|
| 1032 |
+
"eval_steps_per_second": 0.157,
|
| 1033 |
+
"learning_rate": 0.0001,
|
| 1034 |
+
"step": 17745
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 65.93406593406593,
|
| 1038 |
+
"grad_norm": 0.278421550989151,
|
| 1039 |
+
"learning_rate": 0.0001,
|
| 1040 |
+
"loss": 0.1258,
|
| 1041 |
+
"step": 18000
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 66.0,
|
| 1045 |
+
"eval_accuracy": 0.30353430353430355,
|
| 1046 |
+
"eval_f1_macro": 0.706549053618703,
|
| 1047 |
+
"eval_f1_micro": 0.8178908425822006,
|
| 1048 |
+
"eval_loss": 0.12264254689216614,
|
| 1049 |
+
"eval_runtime": 582.1432,
|
| 1050 |
+
"eval_samples_per_second": 4.958,
|
| 1051 |
+
"eval_steps_per_second": 0.156,
|
| 1052 |
+
"learning_rate": 0.0001,
|
| 1053 |
+
"step": 18018
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 67.0,
|
| 1057 |
+
"eval_accuracy": 0.3052668052668053,
|
| 1058 |
+
"eval_f1_macro": 0.7104724530407897,
|
| 1059 |
+
"eval_f1_micro": 0.8184709429598117,
|
| 1060 |
+
"eval_loss": 0.12282951176166534,
|
| 1061 |
+
"eval_runtime": 572.3604,
|
| 1062 |
+
"eval_samples_per_second": 5.042,
|
| 1063 |
+
"eval_steps_per_second": 0.159,
|
| 1064 |
+
"learning_rate": 0.0001,
|
| 1065 |
+
"step": 18291
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 67.76556776556777,
|
| 1069 |
+
"grad_norm": 0.33604416251182556,
|
| 1070 |
+
"learning_rate": 0.0001,
|
| 1071 |
+
"loss": 0.125,
|
| 1072 |
+
"step": 18500
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 68.0,
|
| 1076 |
+
"eval_accuracy": 0.3042273042273042,
|
| 1077 |
+
"eval_f1_macro": 0.7127667888432785,
|
| 1078 |
+
"eval_f1_micro": 0.818125541661508,
|
| 1079 |
+
"eval_loss": 0.12277437746524811,
|
| 1080 |
+
"eval_runtime": 566.9946,
|
| 1081 |
+
"eval_samples_per_second": 5.09,
|
| 1082 |
+
"eval_steps_per_second": 0.16,
|
| 1083 |
+
"learning_rate": 0.0001,
|
| 1084 |
+
"step": 18564
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 69.0,
|
| 1088 |
+
"eval_accuracy": 0.3052668052668053,
|
| 1089 |
+
"eval_f1_macro": 0.703803449192515,
|
| 1090 |
+
"eval_f1_micro": 0.8137196924896511,
|
| 1091 |
+
"eval_loss": 0.12282923609018326,
|
| 1092 |
+
"eval_runtime": 578.0179,
|
| 1093 |
+
"eval_samples_per_second": 4.993,
|
| 1094 |
+
"eval_steps_per_second": 0.157,
|
| 1095 |
+
"learning_rate": 0.0001,
|
| 1096 |
+
"step": 18837
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 69.59706959706959,
|
| 1100 |
+
"grad_norm": 0.237099289894104,
|
| 1101 |
+
"learning_rate": 0.0001,
|
| 1102 |
+
"loss": 0.125,
|
| 1103 |
+
"step": 19000
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 70.0,
|
| 1107 |
+
"eval_accuracy": 0.30180180180180183,
|
| 1108 |
+
"eval_f1_macro": 0.7079779831387449,
|
| 1109 |
+
"eval_f1_micro": 0.8154847434705434,
|
| 1110 |
+
"eval_loss": 0.1231524795293808,
|
| 1111 |
+
"eval_runtime": 578.443,
|
| 1112 |
+
"eval_samples_per_second": 4.989,
|
| 1113 |
+
"eval_steps_per_second": 0.157,
|
| 1114 |
+
"learning_rate": 0.0001,
|
| 1115 |
+
"step": 19110
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 71.0,
|
| 1119 |
+
"eval_accuracy": 0.29902979902979904,
|
| 1120 |
+
"eval_f1_macro": 0.7111485120209401,
|
| 1121 |
+
"eval_f1_micro": 0.8155765340525961,
|
| 1122 |
+
"eval_loss": 0.12310803681612015,
|
| 1123 |
+
"eval_runtime": 577.0393,
|
| 1124 |
+
"eval_samples_per_second": 5.001,
|
| 1125 |
+
"eval_steps_per_second": 0.158,
|
| 1126 |
+
"learning_rate": 0.0001,
|
| 1127 |
+
"step": 19383
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 71.42857142857143,
|
| 1131 |
+
"grad_norm": 0.31944581866264343,
|
| 1132 |
+
"learning_rate": 0.0001,
|
| 1133 |
+
"loss": 0.1245,
|
| 1134 |
+
"step": 19500
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 72.0,
|
| 1138 |
+
"eval_accuracy": 0.30076230076230076,
|
| 1139 |
+
"eval_f1_macro": 0.7149554589558469,
|
| 1140 |
+
"eval_f1_micro": 0.8161826422695988,
|
| 1141 |
+
"eval_loss": 0.12233748286962509,
|
| 1142 |
+
"eval_runtime": 578.4014,
|
| 1143 |
+
"eval_samples_per_second": 4.99,
|
| 1144 |
+
"eval_steps_per_second": 0.157,
|
| 1145 |
+
"learning_rate": 0.0001,
|
| 1146 |
+
"step": 19656
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 73.0,
|
| 1150 |
+
"eval_accuracy": 0.3049203049203049,
|
| 1151 |
+
"eval_f1_macro": 0.7041677932151664,
|
| 1152 |
+
"eval_f1_micro": 0.8173891171292027,
|
| 1153 |
+
"eval_loss": 0.12232980877161026,
|
| 1154 |
+
"eval_runtime": 572.1622,
|
| 1155 |
+
"eval_samples_per_second": 5.044,
|
| 1156 |
+
"eval_steps_per_second": 0.159,
|
| 1157 |
+
"learning_rate": 0.0001,
|
| 1158 |
+
"step": 19929
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 73.26007326007326,
|
| 1162 |
+
"grad_norm": 0.2972647249698639,
|
| 1163 |
+
"learning_rate": 0.0001,
|
| 1164 |
+
"loss": 0.1248,
|
| 1165 |
+
"step": 20000
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 74.0,
|
| 1169 |
+
"eval_accuracy": 0.29625779625779625,
|
| 1170 |
+
"eval_f1_macro": 0.7009378784168091,
|
| 1171 |
+
"eval_f1_micro": 0.8124655033329088,
|
| 1172 |
+
"eval_loss": 0.12370481342077255,
|
| 1173 |
+
"eval_runtime": 589.0452,
|
| 1174 |
+
"eval_samples_per_second": 4.899,
|
| 1175 |
+
"eval_steps_per_second": 0.154,
|
| 1176 |
+
"learning_rate": 0.0001,
|
| 1177 |
+
"step": 20202
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 75.0,
|
| 1181 |
+
"eval_accuracy": 0.30457380457380456,
|
| 1182 |
+
"eval_f1_macro": 0.7045397920320168,
|
| 1183 |
+
"eval_f1_micro": 0.8151614807319335,
|
| 1184 |
+
"eval_loss": 0.12251079827547073,
|
| 1185 |
+
"eval_runtime": 585.6991,
|
| 1186 |
+
"eval_samples_per_second": 4.927,
|
| 1187 |
+
"eval_steps_per_second": 0.155,
|
| 1188 |
+
"learning_rate": 0.0001,
|
| 1189 |
+
"step": 20475
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 75.0915750915751,
|
| 1193 |
+
"grad_norm": 0.34343692660331726,
|
| 1194 |
+
"learning_rate": 0.0001,
|
| 1195 |
+
"loss": 0.1249,
|
| 1196 |
+
"step": 20500
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 76.0,
|
| 1200 |
+
"eval_accuracy": 0.30076230076230076,
|
| 1201 |
+
"eval_f1_macro": 0.7099467053038022,
|
| 1202 |
+
"eval_f1_micro": 0.8159596808063839,
|
| 1203 |
+
"eval_loss": 0.12471619248390198,
|
| 1204 |
+
"eval_runtime": 580.0788,
|
| 1205 |
+
"eval_samples_per_second": 4.975,
|
| 1206 |
+
"eval_steps_per_second": 0.157,
|
| 1207 |
+
"learning_rate": 0.0001,
|
| 1208 |
+
"step": 20748
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 76.92307692307692,
|
| 1212 |
+
"grad_norm": 0.34839001297950745,
|
| 1213 |
+
"learning_rate": 0.0001,
|
| 1214 |
+
"loss": 0.1238,
|
| 1215 |
+
"step": 21000
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 77.0,
|
| 1219 |
+
"eval_accuracy": 0.29902979902979904,
|
| 1220 |
+
"eval_f1_macro": 0.7139220834888879,
|
| 1221 |
+
"eval_f1_micro": 0.8179482930062977,
|
| 1222 |
+
"eval_loss": 0.1225149855017662,
|
| 1223 |
+
"eval_runtime": 592.1949,
|
| 1224 |
+
"eval_samples_per_second": 4.873,
|
| 1225 |
+
"eval_steps_per_second": 0.154,
|
| 1226 |
+
"learning_rate": 0.0001,
|
| 1227 |
+
"step": 21021
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 78.0,
|
| 1231 |
+
"eval_accuracy": 0.30457380457380456,
|
| 1232 |
+
"eval_f1_macro": 0.7060530834173799,
|
| 1233 |
+
"eval_f1_micro": 0.8188081009296149,
|
| 1234 |
+
"eval_loss": 0.12218895554542542,
|
| 1235 |
+
"eval_runtime": 580.5057,
|
| 1236 |
+
"eval_samples_per_second": 4.972,
|
| 1237 |
+
"eval_steps_per_second": 0.157,
|
| 1238 |
+
"learning_rate": 0.0001,
|
| 1239 |
+
"step": 21294
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 78.75457875457876,
|
| 1243 |
+
"grad_norm": 0.3252258002758026,
|
| 1244 |
+
"learning_rate": 0.0001,
|
| 1245 |
+
"loss": 0.1233,
|
| 1246 |
+
"step": 21500
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 79.0,
|
| 1250 |
+
"eval_accuracy": 0.30180180180180183,
|
| 1251 |
+
"eval_f1_macro": 0.7100736740896743,
|
| 1252 |
+
"eval_f1_micro": 0.8152018201735907,
|
| 1253 |
+
"eval_loss": 0.12460680305957794,
|
| 1254 |
+
"eval_runtime": 580.1369,
|
| 1255 |
+
"eval_samples_per_second": 4.975,
|
| 1256 |
+
"eval_steps_per_second": 0.157,
|
| 1257 |
+
"learning_rate": 0.0001,
|
| 1258 |
+
"step": 21567
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 80.0,
|
| 1262 |
+
"eval_accuracy": 0.3038808038808039,
|
| 1263 |
+
"eval_f1_macro": 0.710254660316209,
|
| 1264 |
+
"eval_f1_micro": 0.8179503235232728,
|
| 1265 |
+
"eval_loss": 0.12210072576999664,
|
| 1266 |
+
"eval_runtime": 588.8207,
|
| 1267 |
+
"eval_samples_per_second": 4.901,
|
| 1268 |
+
"eval_steps_per_second": 0.155,
|
| 1269 |
+
"learning_rate": 0.0001,
|
| 1270 |
+
"step": 21840
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 80.58608058608058,
|
| 1274 |
+
"grad_norm": 0.31095778942108154,
|
| 1275 |
+
"learning_rate": 0.0001,
|
| 1276 |
+
"loss": 0.1225,
|
| 1277 |
+
"step": 22000
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 81.0,
|
| 1281 |
+
"eval_accuracy": 0.30180180180180183,
|
| 1282 |
+
"eval_f1_macro": 0.7156736962695093,
|
| 1283 |
+
"eval_f1_micro": 0.8184843191082273,
|
| 1284 |
+
"eval_loss": 0.12116113305091858,
|
| 1285 |
+
"eval_runtime": 583.0708,
|
| 1286 |
+
"eval_samples_per_second": 4.95,
|
| 1287 |
+
"eval_steps_per_second": 0.156,
|
| 1288 |
+
"learning_rate": 0.0001,
|
| 1289 |
+
"step": 22113
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 82.0,
|
| 1293 |
+
"eval_accuracy": 0.30803880803880807,
|
| 1294 |
+
"eval_f1_macro": 0.7088973142030256,
|
| 1295 |
+
"eval_f1_micro": 0.8151834668916069,
|
| 1296 |
+
"eval_loss": 0.12159755080938339,
|
| 1297 |
+
"eval_runtime": 583.0652,
|
| 1298 |
+
"eval_samples_per_second": 4.95,
|
| 1299 |
+
"eval_steps_per_second": 0.156,
|
| 1300 |
+
"learning_rate": 0.0001,
|
| 1301 |
+
"step": 22386
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 82.41758241758242,
|
| 1305 |
+
"grad_norm": 0.30886727571487427,
|
| 1306 |
+
"learning_rate": 0.0001,
|
| 1307 |
+
"loss": 0.1216,
|
| 1308 |
+
"step": 22500
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 83.0,
|
| 1312 |
+
"eval_accuracy": 0.30803880803880807,
|
| 1313 |
+
"eval_f1_macro": 0.7090314532601811,
|
| 1314 |
+
"eval_f1_micro": 0.8164913756836348,
|
| 1315 |
+
"eval_loss": 0.12142453342676163,
|
| 1316 |
+
"eval_runtime": 587.9863,
|
| 1317 |
+
"eval_samples_per_second": 4.908,
|
| 1318 |
+
"eval_steps_per_second": 0.155,
|
| 1319 |
+
"learning_rate": 0.0001,
|
| 1320 |
+
"step": 22659
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 84.0,
|
| 1324 |
+
"eval_accuracy": 0.306999306999307,
|
| 1325 |
+
"eval_f1_macro": 0.7100088286352488,
|
| 1326 |
+
"eval_f1_micro": 0.8168789808917197,
|
| 1327 |
+
"eval_loss": 0.12157817929983139,
|
| 1328 |
+
"eval_runtime": 574.5086,
|
| 1329 |
+
"eval_samples_per_second": 5.023,
|
| 1330 |
+
"eval_steps_per_second": 0.158,
|
| 1331 |
+
"learning_rate": 0.0001,
|
| 1332 |
+
"step": 22932
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 84.24908424908425,
|
| 1336 |
+
"grad_norm": 0.33512353897094727,
|
| 1337 |
+
"learning_rate": 0.0001,
|
| 1338 |
+
"loss": 0.1232,
|
| 1339 |
+
"step": 23000
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 85.0,
|
| 1343 |
+
"eval_accuracy": 0.3052668052668053,
|
| 1344 |
+
"eval_f1_macro": 0.7109093140233731,
|
| 1345 |
+
"eval_f1_micro": 0.8188048474717927,
|
| 1346 |
+
"eval_loss": 0.12155645340681076,
|
| 1347 |
+
"eval_runtime": 588.285,
|
| 1348 |
+
"eval_samples_per_second": 4.906,
|
| 1349 |
+
"eval_steps_per_second": 0.155,
|
| 1350 |
+
"learning_rate": 0.0001,
|
| 1351 |
+
"step": 23205
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 86.0,
|
| 1355 |
+
"eval_accuracy": 0.306999306999307,
|
| 1356 |
+
"eval_f1_macro": 0.7176309861117636,
|
| 1357 |
+
"eval_f1_micro": 0.8190986316274009,
|
| 1358 |
+
"eval_loss": 0.12185127288103104,
|
| 1359 |
+
"eval_runtime": 596.3097,
|
| 1360 |
+
"eval_samples_per_second": 4.84,
|
| 1361 |
+
"eval_steps_per_second": 0.153,
|
| 1362 |
+
"learning_rate": 0.0001,
|
| 1363 |
+
"step": 23478
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 86.08058608058609,
|
| 1367 |
+
"grad_norm": 0.3552737832069397,
|
| 1368 |
+
"learning_rate": 0.0001,
|
| 1369 |
+
"loss": 0.1221,
|
| 1370 |
+
"step": 23500
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 87.0,
|
| 1374 |
+
"eval_accuracy": 0.3063063063063063,
|
| 1375 |
+
"eval_f1_macro": 0.7080074645247395,
|
| 1376 |
+
"eval_f1_micro": 0.8176601181250785,
|
| 1377 |
+
"eval_loss": 0.12196006625890732,
|
| 1378 |
+
"eval_runtime": 582.057,
|
| 1379 |
+
"eval_samples_per_second": 4.958,
|
| 1380 |
+
"eval_steps_per_second": 0.156,
|
| 1381 |
+
"learning_rate": 0.0001,
|
| 1382 |
+
"step": 23751
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 87.91208791208791,
|
| 1386 |
+
"grad_norm": 0.31451234221458435,
|
| 1387 |
+
"learning_rate": 1e-05,
|
| 1388 |
+
"loss": 0.1208,
|
| 1389 |
+
"step": 24000
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 88.0,
|
| 1393 |
+
"eval_accuracy": 0.3049203049203049,
|
| 1394 |
+
"eval_f1_macro": 0.7158455151348946,
|
| 1395 |
+
"eval_f1_micro": 0.8210709982967056,
|
| 1396 |
+
"eval_loss": 0.1209772601723671,
|
| 1397 |
+
"eval_runtime": 583.2281,
|
| 1398 |
+
"eval_samples_per_second": 4.948,
|
| 1399 |
+
"eval_steps_per_second": 0.156,
|
| 1400 |
+
"learning_rate": 1e-05,
|
| 1401 |
+
"step": 24024
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 89.0,
|
| 1405 |
+
"eval_accuracy": 0.30734580734580735,
|
| 1406 |
+
"eval_f1_macro": 0.7312085502704033,
|
| 1407 |
+
"eval_f1_micro": 0.82409381663113,
|
| 1408 |
+
"eval_loss": 0.12103869765996933,
|
| 1409 |
+
"eval_runtime": 571.5547,
|
| 1410 |
+
"eval_samples_per_second": 5.049,
|
| 1411 |
+
"eval_steps_per_second": 0.159,
|
| 1412 |
+
"learning_rate": 1e-05,
|
| 1413 |
+
"step": 24297
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 89.74358974358974,
|
| 1417 |
+
"grad_norm": 0.3047947883605957,
|
| 1418 |
+
"learning_rate": 1e-05,
|
| 1419 |
+
"loss": 0.1189,
|
| 1420 |
+
"step": 24500
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 90.0,
|
| 1424 |
+
"eval_accuracy": 0.306999306999307,
|
| 1425 |
+
"eval_f1_macro": 0.7232165780756572,
|
| 1426 |
+
"eval_f1_micro": 0.823466447097571,
|
| 1427 |
+
"eval_loss": 0.12060839682817459,
|
| 1428 |
+
"eval_runtime": 577.3382,
|
| 1429 |
+
"eval_samples_per_second": 4.999,
|
| 1430 |
+
"eval_steps_per_second": 0.158,
|
| 1431 |
+
"learning_rate": 1e-05,
|
| 1432 |
+
"step": 24570
|
| 1433 |
+
},
|
| 1434 |
+
{
|
| 1435 |
+
"epoch": 91.0,
|
| 1436 |
+
"eval_accuracy": 0.3087318087318087,
|
| 1437 |
+
"eval_f1_macro": 0.714800773362679,
|
| 1438 |
+
"eval_f1_micro": 0.8190853196327803,
|
| 1439 |
+
"eval_loss": 0.12036494165658951,
|
| 1440 |
+
"eval_runtime": 575.4555,
|
| 1441 |
+
"eval_samples_per_second": 5.015,
|
| 1442 |
+
"eval_steps_per_second": 0.158,
|
| 1443 |
+
"learning_rate": 1e-05,
|
| 1444 |
+
"step": 24843
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 91.57509157509158,
|
| 1448 |
+
"grad_norm": 0.28365448117256165,
|
| 1449 |
+
"learning_rate": 1e-05,
|
| 1450 |
+
"loss": 0.1181,
|
| 1451 |
+
"step": 25000
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 92.0,
|
| 1455 |
+
"eval_accuracy": 0.3087318087318087,
|
| 1456 |
+
"eval_f1_macro": 0.7131694962358415,
|
| 1457 |
+
"eval_f1_micro": 0.8194187804468336,
|
| 1458 |
+
"eval_loss": 0.12028194963932037,
|
| 1459 |
+
"eval_runtime": 576.0948,
|
| 1460 |
+
"eval_samples_per_second": 5.01,
|
| 1461 |
+
"eval_steps_per_second": 0.158,
|
| 1462 |
+
"learning_rate": 1e-05,
|
| 1463 |
+
"step": 25116
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 93.0,
|
| 1467 |
+
"eval_accuracy": 0.30838530838530837,
|
| 1468 |
+
"eval_f1_macro": 0.7183857334665726,
|
| 1469 |
+
"eval_f1_micro": 0.8214921910601102,
|
| 1470 |
+
"eval_loss": 0.12036142498254776,
|
| 1471 |
+
"eval_runtime": 576.2755,
|
| 1472 |
+
"eval_samples_per_second": 5.008,
|
| 1473 |
+
"eval_steps_per_second": 0.158,
|
| 1474 |
+
"learning_rate": 1e-05,
|
| 1475 |
+
"step": 25389
|
| 1476 |
+
},
|
| 1477 |
+
{
|
| 1478 |
+
"epoch": 93.4065934065934,
|
| 1479 |
+
"grad_norm": 0.3265780806541443,
|
| 1480 |
+
"learning_rate": 1e-05,
|
| 1481 |
+
"loss": 0.1183,
|
| 1482 |
+
"step": 25500
|
| 1483 |
+
},
|
| 1484 |
+
{
|
| 1485 |
+
"epoch": 94.0,
|
| 1486 |
+
"eval_accuracy": 0.30665280665280664,
|
| 1487 |
+
"eval_f1_macro": 0.7195089038891936,
|
| 1488 |
+
"eval_f1_micro": 0.8207247828991316,
|
| 1489 |
+
"eval_loss": 0.12012535333633423,
|
| 1490 |
+
"eval_runtime": 574.7766,
|
| 1491 |
+
"eval_samples_per_second": 5.021,
|
| 1492 |
+
"eval_steps_per_second": 0.158,
|
| 1493 |
+
"learning_rate": 1e-05,
|
| 1494 |
+
"step": 25662
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 95.0,
|
| 1498 |
+
"eval_accuracy": 0.30838530838530837,
|
| 1499 |
+
"eval_f1_macro": 0.7157953029268052,
|
| 1500 |
+
"eval_f1_micro": 0.8197421299397187,
|
| 1501 |
+
"eval_loss": 0.12010551244020462,
|
| 1502 |
+
"eval_runtime": 579.3324,
|
| 1503 |
+
"eval_samples_per_second": 4.982,
|
| 1504 |
+
"eval_steps_per_second": 0.157,
|
| 1505 |
+
"learning_rate": 1e-05,
|
| 1506 |
+
"step": 25935
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 95.23809523809524,
|
| 1510 |
+
"grad_norm": 0.3151456415653229,
|
| 1511 |
+
"learning_rate": 1e-05,
|
| 1512 |
+
"loss": 0.117,
|
| 1513 |
+
"step": 26000
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 96.0,
|
| 1517 |
+
"eval_accuracy": 0.3052668052668053,
|
| 1518 |
+
"eval_f1_macro": 0.7193329750108997,
|
| 1519 |
+
"eval_f1_micro": 0.8217099503939306,
|
| 1520 |
+
"eval_loss": 0.1198035180568695,
|
| 1521 |
+
"eval_runtime": 605.2902,
|
| 1522 |
+
"eval_samples_per_second": 4.768,
|
| 1523 |
+
"eval_steps_per_second": 0.15,
|
| 1524 |
+
"learning_rate": 1e-05,
|
| 1525 |
+
"step": 26208
|
| 1526 |
+
},
|
| 1527 |
+
{
|
| 1528 |
+
"epoch": 97.0,
|
| 1529 |
+
"eval_accuracy": 0.3063063063063063,
|
| 1530 |
+
"eval_f1_macro": 0.7210913273742954,
|
| 1531 |
+
"eval_f1_micro": 0.8204592028773368,
|
| 1532 |
+
"eval_loss": 0.12007978558540344,
|
| 1533 |
+
"eval_runtime": 637.4782,
|
| 1534 |
+
"eval_samples_per_second": 4.527,
|
| 1535 |
+
"eval_steps_per_second": 0.143,
|
| 1536 |
+
"learning_rate": 1e-05,
|
| 1537 |
+
"step": 26481
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 97.06959706959707,
|
| 1541 |
+
"grad_norm": 0.32921385765075684,
|
| 1542 |
+
"learning_rate": 1e-05,
|
| 1543 |
+
"loss": 0.1176,
|
| 1544 |
+
"step": 26500
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 98.0,
|
| 1548 |
+
"eval_accuracy": 0.30803880803880807,
|
| 1549 |
+
"eval_f1_macro": 0.7250050738866957,
|
| 1550 |
+
"eval_f1_micro": 0.8226615276223631,
|
| 1551 |
+
"eval_loss": 0.12013950198888779,
|
| 1552 |
+
"eval_runtime": 575.4419,
|
| 1553 |
+
"eval_samples_per_second": 5.015,
|
| 1554 |
+
"eval_steps_per_second": 0.158,
|
| 1555 |
+
"learning_rate": 1e-05,
|
| 1556 |
+
"step": 26754
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 98.9010989010989,
|
| 1560 |
+
"grad_norm": 0.37390851974487305,
|
| 1561 |
+
"learning_rate": 1e-05,
|
| 1562 |
+
"loss": 0.1176,
|
| 1563 |
+
"step": 27000
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 99.0,
|
| 1567 |
+
"eval_accuracy": 0.30734580734580735,
|
| 1568 |
+
"eval_f1_macro": 0.7226446473273916,
|
| 1569 |
+
"eval_f1_micro": 0.8206050968740846,
|
| 1570 |
+
"eval_loss": 0.12003140896558762,
|
| 1571 |
+
"eval_runtime": 619.3031,
|
| 1572 |
+
"eval_samples_per_second": 4.66,
|
| 1573 |
+
"eval_steps_per_second": 0.147,
|
| 1574 |
+
"learning_rate": 1e-05,
|
| 1575 |
+
"step": 27027
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 100.0,
|
| 1579 |
+
"eval_accuracy": 0.30803880803880807,
|
| 1580 |
+
"eval_f1_macro": 0.7191058080317732,
|
| 1581 |
+
"eval_f1_micro": 0.8216021451315569,
|
| 1582 |
+
"eval_loss": 0.1200241968035698,
|
| 1583 |
+
"eval_runtime": 615.3025,
|
| 1584 |
+
"eval_samples_per_second": 4.69,
|
| 1585 |
+
"eval_steps_per_second": 0.148,
|
| 1586 |
+
"learning_rate": 1e-05,
|
| 1587 |
+
"step": 27300
|
| 1588 |
+
},
|
| 1589 |
+
{
|
| 1590 |
+
"epoch": 100.73260073260073,
|
| 1591 |
+
"grad_norm": 0.39757904410362244,
|
| 1592 |
+
"learning_rate": 1e-05,
|
| 1593 |
+
"loss": 0.117,
|
| 1594 |
+
"step": 27500
|
| 1595 |
+
},
|
| 1596 |
+
{
|
| 1597 |
+
"epoch": 101.0,
|
| 1598 |
+
"eval_accuracy": 0.3097713097713098,
|
| 1599 |
+
"eval_f1_macro": 0.724185821594473,
|
| 1600 |
+
"eval_f1_micro": 0.8228338260398884,
|
| 1601 |
+
"eval_loss": 0.11989927291870117,
|
| 1602 |
+
"eval_runtime": 574.4571,
|
| 1603 |
+
"eval_samples_per_second": 5.024,
|
| 1604 |
+
"eval_steps_per_second": 0.158,
|
| 1605 |
+
"learning_rate": 1e-05,
|
| 1606 |
+
"step": 27573
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 102.0,
|
| 1610 |
+
"eval_accuracy": 0.30734580734580735,
|
| 1611 |
+
"eval_f1_macro": 0.7216480982679994,
|
| 1612 |
+
"eval_f1_micro": 0.8192071374463429,
|
| 1613 |
+
"eval_loss": 0.12043397128582001,
|
| 1614 |
+
"eval_runtime": 627.7673,
|
| 1615 |
+
"eval_samples_per_second": 4.597,
|
| 1616 |
+
"eval_steps_per_second": 0.145,
|
| 1617 |
+
"learning_rate": 1e-05,
|
| 1618 |
+
"step": 27846
|
| 1619 |
+
},
|
| 1620 |
+
{
|
| 1621 |
+
"epoch": 102.56410256410257,
|
| 1622 |
+
"grad_norm": 0.3315370976924896,
|
| 1623 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1624 |
+
"loss": 0.1159,
|
| 1625 |
+
"step": 28000
|
| 1626 |
+
},
|
| 1627 |
+
{
|
| 1628 |
+
"epoch": 103.0,
|
| 1629 |
+
"eval_accuracy": 0.30665280665280664,
|
| 1630 |
+
"eval_f1_macro": 0.7231653777895258,
|
| 1631 |
+
"eval_f1_micro": 0.8221990402670561,
|
| 1632 |
+
"eval_loss": 0.1199527159333229,
|
| 1633 |
+
"eval_runtime": 574.6395,
|
| 1634 |
+
"eval_samples_per_second": 5.022,
|
| 1635 |
+
"eval_steps_per_second": 0.158,
|
| 1636 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1637 |
+
"step": 28119
|
| 1638 |
+
},
|
| 1639 |
+
{
|
| 1640 |
+
"epoch": 104.0,
|
| 1641 |
+
"eval_accuracy": 0.31011781011781014,
|
| 1642 |
+
"eval_f1_macro": 0.7234886652066129,
|
| 1643 |
+
"eval_f1_micro": 0.8217751676454663,
|
| 1644 |
+
"eval_loss": 0.12043838202953339,
|
| 1645 |
+
"eval_runtime": 571.7276,
|
| 1646 |
+
"eval_samples_per_second": 5.048,
|
| 1647 |
+
"eval_steps_per_second": 0.159,
|
| 1648 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1649 |
+
"step": 28392
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 104.3956043956044,
|
| 1653 |
+
"grad_norm": 0.3368052840232849,
|
| 1654 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1655 |
+
"loss": 0.1151,
|
| 1656 |
+
"step": 28500
|
| 1657 |
+
},
|
| 1658 |
+
{
|
| 1659 |
+
"epoch": 105.0,
|
| 1660 |
+
"eval_accuracy": 0.3076923076923077,
|
| 1661 |
+
"eval_f1_macro": 0.7205886261735153,
|
| 1662 |
+
"eval_f1_micro": 0.8219212232009308,
|
| 1663 |
+
"eval_loss": 0.11985885351896286,
|
| 1664 |
+
"eval_runtime": 623.1101,
|
| 1665 |
+
"eval_samples_per_second": 4.632,
|
| 1666 |
+
"eval_steps_per_second": 0.146,
|
| 1667 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1668 |
+
"step": 28665
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 106.0,
|
| 1672 |
+
"eval_accuracy": 0.31046431046431044,
|
| 1673 |
+
"eval_f1_macro": 0.7270103073654017,
|
| 1674 |
+
"eval_f1_micro": 0.8228195739014648,
|
| 1675 |
+
"eval_loss": 0.11984959244728088,
|
| 1676 |
+
"eval_runtime": 582.6782,
|
| 1677 |
+
"eval_samples_per_second": 4.953,
|
| 1678 |
+
"eval_steps_per_second": 0.156,
|
| 1679 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1680 |
+
"step": 28938
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"epoch": 106.0,
|
| 1684 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1685 |
+
"step": 28938,
|
| 1686 |
+
"total_flos": 1.3699618367216817e+21,
|
| 1687 |
+
"train_loss": 0.13672988786670365,
|
| 1688 |
+
"train_runtime": 251282.626,
|
| 1689 |
+
"train_samples_per_second": 5.203,
|
| 1690 |
+
"train_steps_per_second": 0.163
|
| 1691 |
+
}
|
| 1692 |
+
],
|
| 1693 |
+
"logging_steps": 500,
|
| 1694 |
+
"max_steps": 40950,
|
| 1695 |
+
"num_input_tokens_seen": 0,
|
| 1696 |
+
"num_train_epochs": 150,
|
| 1697 |
+
"save_steps": 500,
|
| 1698 |
+
"stateful_callbacks": {
|
| 1699 |
+
"EarlyStoppingCallback": {
|
| 1700 |
+
"args": {
|
| 1701 |
+
"early_stopping_patience": 10,
|
| 1702 |
+
"early_stopping_threshold": 0.0
|
| 1703 |
+
},
|
| 1704 |
+
"attributes": {
|
| 1705 |
+
"early_stopping_patience_counter": 0
|
| 1706 |
+
}
|
| 1707 |
+
},
|
| 1708 |
+
"TrainerControl": {
|
| 1709 |
+
"args": {
|
| 1710 |
+
"should_epoch_stop": false,
|
| 1711 |
+
"should_evaluate": false,
|
| 1712 |
+
"should_log": false,
|
| 1713 |
+
"should_save": true,
|
| 1714 |
+
"should_training_stop": true
|
| 1715 |
+
},
|
| 1716 |
+
"attributes": {}
|
| 1717 |
+
}
|
| 1718 |
+
},
|
| 1719 |
+
"total_flos": 1.3699618367216817e+21,
|
| 1720 |
+
"train_batch_size": 32,
|
| 1721 |
+
"trial_name": null,
|
| 1722 |
+
"trial_params": null
|
| 1723 |
+
}
|