Hugging Face's logo

DayCardoso
/
valueeval24-modern-bert-cos-initialfreeze-diff-lr

Text Classification
Transformers
Safetensors
modernbert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
DayCardoso commited on
Commit
1e90229
·
verified ·
1 Parent(s): 4de6593

Model save

Browse files
Files changed (2) hide show
  1. README.md +15 -17
  2. model.safetensors +1 -1
README.md CHANGED
@@ -19,10 +19,10 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.5229
23
- - F1: 0.2202
24
- - Roc Auc: 0.5793
25
- - Accuracy: 0.1532
26
 
27
  ## Model description
28
 
@@ -55,23 +55,21 @@ The following hyperparameters were used during training:
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
57
  |:-------------:|:-----:|:-----:|:---------------:|:------:|:-------:|:--------:|
58
- | 0.0235 | 1.0 | 2889 | 0.1633 | 0.2106 | 0.5711 | 0.15 |
59
- | 0.02 | 2.0 | 5778 | 0.1807 | 0.2132 | 0.5743 | 0.1474 |
60
- | 0.017 | 3.0 | 8667 | 0.2094 | 0.2038 | 0.5671 | 0.1478 |
61
- | 0.0125 | 4.0 | 11556 | 0.2373 | 0.2210 | 0.5792 | 0.15 |
62
- | 0.0108 | 5.0 | 14445 | 0.2820 | 0.2249 | 0.5796 | 0.1567 |
63
- | 0.009 | 6.0 | 17334 | 0.3568 | 0.2224 | 0.5798 | 0.1539 |
64
- | 0.0076 | 7.0 | 20223 | 0.4262 | 0.2255 | 0.5816 | 0.1562 |
65
- | 0.007 | 8.0 | 23112 | 0.4740 | 0.2197 | 0.5785 | 0.1512 |
66
- | 0.0064 | 9.0 | 26001 | 0.4817 | 0.2222 | 0.5802 | 0.1559 |
67
- | 0.0056 | 10.0 | 28890 | 0.5066 | 0.2244 | 0.5814 | 0.1570 |
68
- | 0.0052 | 11.0 | 31779 | 0.5178 | 0.2229 | 0.5808 | 0.1549 |
69
- | 0.005 | 12.0 | 34668 | 0.5229 | 0.2202 | 0.5793 | 0.1532 |
70
 
71
 
72
  ### Framework versions
73
 
74
- - Transformers 4.53.0
75
  - Pytorch 2.6.0+cu124
76
  - Datasets 2.14.4
77
  - Tokenizers 0.21.2
 
19
 
20
  This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.7684
23
+ - F1: 0.2039
24
+ - Roc Auc: 0.5705
25
+ - Accuracy: 0.1033
26
 
27
  ## Model description
28
 
 
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
57
  |:-------------:|:-----:|:-----:|:---------------:|:------:|:-------:|:--------:|
58
+ | 0.0167 | 1.0 | 3115 | 0.2207 | 0.2035 | 0.5691 | 0.1071 |
59
+ | 0.0138 | 2.0 | 6230 | 0.2613 | 0.2091 | 0.5730 | 0.1083 |
60
+ | 0.0102 | 3.0 | 9345 | 0.3444 | 0.2249 | 0.5841 | 0.1147 |
61
+ | 0.0073 | 4.0 | 12460 | 0.6223 | 0.1944 | 0.5654 | 0.0991 |
62
+ | 0.0053 | 5.0 | 15575 | 0.6920 | 0.1973 | 0.5668 | 0.1004 |
63
+ | 0.0022 | 6.0 | 18690 | 0.7143 | 0.1983 | 0.5680 | 0.0996 |
64
+ | 0.0012 | 7.0 | 21805 | 0.7309 | 0.1968 | 0.5672 | 0.0993 |
65
+ | 0.0007 | 8.0 | 24920 | 0.7349 | 0.2035 | 0.5706 | 0.1031 |
66
+ | 0.0006 | 9.0 | 28035 | 0.7521 | 0.2064 | 0.5718 | 0.1070 |
67
+ | 0.0003 | 10.0 | 31150 | 0.7684 | 0.2039 | 0.5705 | 0.1033 |
 
 
68
 
69
 
70
  ### Framework versions
71
 
72
+ - Transformers 4.53.1
73
  - Pytorch 2.6.0+cu124
74
  - Datasets 2.14.4
75
  - Tokenizers 0.21.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c8a21d17fa2c0168ca94ba9bc56f485c47c51b8f74562e0d0c666fce7513e42f
3
  size 598550528
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29d8f3d2bac2b37aed50662051a663481d8c12f5383f073b147a40f63d178e39
3
  size 598550528