Hugging Face's logo

DayCardoso
/
modern-bert-seq-class-values-no-context

Text Classification
Transformers
Safetensors
modernbert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
DayCardoso commited on
Commit
8359027
·
verified ·
1 Parent(s): 92a36cf

Model save

Browse files
Files changed (2) hide show
  1. README.md +28 -22
  2. model.safetensors +1 -1
README.md CHANGED
@@ -16,13 +16,13 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.3498
20
- - Subset Accuracy: 0.2823
21
- - F1 Macro: 0.3178
22
- - F1 Micro: 0.3947
23
- - Precision Macro: 0.4117
24
- - Recall Macro: 0.2727
25
- - Roc Auc: 0.8081
26
 
27
  ## Model description
28
 
@@ -55,21 +55,27 @@ The following hyperparameters were used during training:
55
 
56
  ### Training results
57
 
58
- | Training Loss | Epoch | Step | Validation Loss | Subset Accuracy | F1 Macro | F1 Micro | Precision Macro | Recall Macro | Roc Auc |
59
- |:-------------:|:------:|:----:|:---------------:|:---------------:|:--------:|:--------:|:---------------:|:------------:|:-------:|
60
- | 1.2206 | 0.5002 | 767 | 0.1854 | 0.0531 | 0.0594 | 0.1006 | 0.2895 | 0.0357 | 0.7592 |
61
- | 0.6858 | 1.0 | 1534 | 0.1660 | 0.1251 | 0.1449 | 0.2153 | 0.4531 | 0.0953 | 0.8282 |
62
- | 0.6256 | 1.5002 | 2301 | 0.1618 | 0.1878 | 0.2129 | 0.3043 | 0.4703 | 0.1570 | 0.8418 |
63
- | 0.6116 | 2.0 | 3068 | 0.1570 | 0.2319 | 0.2292 | 0.3476 | 0.6082 | 0.1696 | 0.8506 |
64
- | 0.4803 | 2.5002 | 3835 | 0.1713 | 0.2648 | 0.2827 | 0.3776 | 0.4858 | 0.2214 | 0.8431 |
65
- | 0.4586 | 3.0 | 4602 | 0.1662 | 0.2646 | 0.2866 | 0.3777 | 0.4969 | 0.2183 | 0.8457 |
66
- | 0.278 | 3.5002 | 5369 | 0.2105 | 0.2871 | 0.3268 | 0.4007 | 0.4623 | 0.2814 | 0.8320 |
67
- | 0.2365 | 4.0 | 6136 | 0.2242 | 0.2955 | 0.3330 | 0.4112 | 0.3961 | 0.3055 | 0.8269 |
68
- | 0.1441 | 4.5002 | 6903 | 0.2515 | 0.2819 | 0.3321 | 0.4045 | 0.4042 | 0.2977 | 0.8188 |
69
- | 0.1158 | 5.0 | 7670 | 0.2738 | 0.2779 | 0.3037 | 0.3941 | 0.4121 | 0.2601 | 0.8100 |
70
- | 0.0819 | 5.5002 | 8437 | 0.3033 | 0.2786 | 0.3286 | 0.4019 | 0.4065 | 0.2885 | 0.8110 |
71
- | 0.0648 | 6.0 | 9204 | 0.3143 | 0.2774 | 0.3302 | 0.4051 | 0.4056 | 0.2966 | 0.8065 |
72
- | 0.0522 | 6.5002 | 9971 | 0.3498 | 0.2823 | 0.3178 | 0.3947 | 0.4117 | 0.2727 | 0.8081 |
 
 
 
 
 
 
73
 
74
 
75
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.4170
20
+ - Subset Accuracy: 0.2778
21
+ - F1 Macro: 0.3294
22
+ - F1 Micro: 0.3990
23
+ - Precision Macro: 0.4078
24
+ - Recall Macro: 0.2869
25
+ - Roc Auc: 0.8058
26
 
27
  ## Model description
28
 
 
55
 
56
  ### Training results
57
 
58
+ | Training Loss | Epoch | Step | Validation Loss | Subset Accuracy | F1 Macro | F1 Micro | Precision Macro | Recall Macro | Roc Auc |
59
+ |:-------------:|:------:|:-----:|:---------------:|:---------------:|:--------:|:--------:|:---------------:|:------------:|:-------:|
60
+ | 1.1783 | 0.5002 | 767 | 0.1854 | 0.0679 | 0.0755 | 0.1256 | 0.3030 | 0.0466 | 0.7610 |
61
+ | 0.6868 | 1.0 | 1534 | 0.1661 | 0.1378 | 0.1564 | 0.2358 | 0.5075 | 0.1038 | 0.8281 |
62
+ | 0.6248 | 1.5002 | 2301 | 0.1613 | 0.2025 | 0.2269 | 0.3192 | 0.5102 | 0.1713 | 0.8416 |
63
+ | 0.6101 | 2.0 | 3068 | 0.1561 | 0.2364 | 0.2349 | 0.3546 | 0.5593 | 0.1735 | 0.8521 |
64
+ | 0.4834 | 2.5002 | 3835 | 0.1669 | 0.2506 | 0.2784 | 0.3696 | 0.5196 | 0.2150 | 0.8427 |
65
+ | 0.4572 | 3.0 | 4602 | 0.1663 | 0.2645 | 0.2952 | 0.3769 | 0.5287 | 0.2266 | 0.8445 |
66
+ | 0.2812 | 3.5002 | 5369 | 0.2168 | 0.2803 | 0.3263 | 0.3868 | 0.3978 | 0.2925 | 0.8280 |
67
+ | 0.2386 | 4.0 | 6136 | 0.2064 | 0.2894 | 0.3236 | 0.4024 | 0.4280 | 0.2785 | 0.8263 |
68
+ | 0.1431 | 4.5002 | 6903 | 0.2515 | 0.2842 | 0.3292 | 0.3992 | 0.4010 | 0.2898 | 0.8179 |
69
+ | 0.123 | 5.0 | 7670 | 0.2675 | 0.2736 | 0.3156 | 0.3847 | 0.3955 | 0.2744 | 0.8145 |
70
+ | 0.0905 | 5.5002 | 8437 | 0.3188 | 0.2851 | 0.3272 | 0.3999 | 0.3789 | 0.2947 | 0.8143 |
71
+ | 0.0678 | 6.0 | 9204 | 0.3120 | 0.2762 | 0.3217 | 0.3860 | 0.4000 | 0.2736 | 0.8112 |
72
+ | 0.0544 | 6.5002 | 9971 | 0.3340 | 0.2847 | 0.3330 | 0.4064 | 0.4040 | 0.2937 | 0.8085 |
73
+ | 0.0395 | 7.0 | 10738 | 0.3480 | 0.2811 | 0.3341 | 0.3964 | 0.3944 | 0.2954 | 0.8096 |
74
+ | 0.0257 | 7.5002 | 11505 | 0.3684 | 0.2865 | 0.3275 | 0.4046 | 0.4225 | 0.2841 | 0.8056 |
75
+ | 0.0291 | 8.0 | 12272 | 0.3824 | 0.2821 | 0.3210 | 0.3994 | 0.4053 | 0.2835 | 0.8038 |
76
+ | 0.0173 | 8.5002 | 13039 | 0.3921 | 0.2821 | 0.3194 | 0.3945 | 0.4329 | 0.2679 | 0.8053 |
77
+ | 0.0157 | 9.0 | 13806 | 0.4061 | 0.2829 | 0.3307 | 0.4065 | 0.3905 | 0.2954 | 0.8035 |
78
+ | 0.0123 | 9.5002 | 14573 | 0.4170 | 0.2778 | 0.3294 | 0.3990 | 0.4078 | 0.2869 | 0.8058 |
79
 
80
 
81
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5d9b68f0d41d55db96696a53e5e259e3e50b79c1ed5b7e29b2cfc14e8bdc568
3
  size 598492084
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee9ecdf9cb4fbd243717fc25888f9d3a5235d8e5290242390fa6dec648742dc0
3
  size 598492084