Hugging Face's logo

dnttestmee
/
starclass_modernbert

Text Classification
Transformers
TensorBoard
Safetensors
modernbert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
Metrics Community
dnttestmee commited on
Commit
4310541
·
verified ·
1 Parent(s): 5e525bb

End of training

Browse files
Files changed (3) hide show
  1. README.md +12 -10
  2. logs/events.out.tfevents.1737587003.PC +2 -2
  3. model.safetensors +1 -1
README.md CHANGED
@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
21
 
22
  This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on the None dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 0.3933
25
- - Accuracy: 0.8906
26
- - Precision: 0.8974
27
- - Recall: 0.8906
28
- - F1: 0.8899
29
 
30
  ## Model description
31
 
@@ -49,16 +49,18 @@ The following hyperparameters were used during training:
49
  - eval_batch_size: 16
50
  - seed: 42
51
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
- - lr_scheduler_type: linear
53
- - num_epochs: 3
54
 
55
  ### Training results
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
58
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
59
- | 1.2798 | 1.0 | 16 | 0.7683 | 0.7344 | 0.8181 | 0.7344 | 0.7226 |
60
- | 0.1812 | 2.0 | 32 | 0.3600 | 0.8906 | 0.8974 | 0.8906 | 0.8899 |
61
- | 0.0363 | 3.0 | 48 | 0.3933 | 0.8906 | 0.8974 | 0.8906 | 0.8899 |
 
 
62
 
63
 
64
  ### Framework versions
 
21
 
22
  This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on the None dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 0.1793
25
+ - Accuracy: 0.9048
26
+ - Precision: 0.9140
27
+ - Recall: 0.9048
28
+ - F1: 0.9037
29
 
30
  ## Model description
31
 
 
49
  - eval_batch_size: 16
50
  - seed: 42
51
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
+ - lr_scheduler_type: cosine
53
+ - num_epochs: 5
54
 
55
  ### Training results
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
58
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
59
+ | 1.2429 | 1.0 | 16 | 0.4839 | 0.8095 | 0.8631 | 0.8095 | 0.8122 |
60
+ | 0.2833 | 2.0 | 32 | 0.1735 | 0.9365 | 0.9374 | 0.9365 | 0.9365 |
61
+ | 0.0735 | 3.0 | 48 | 0.1645 | 0.9365 | 0.9364 | 0.9365 | 0.9360 |
62
+ | 0.0038 | 4.0 | 64 | 0.1804 | 0.9048 | 0.9147 | 0.9048 | 0.9055 |
63
+ | 0.0009 | 5.0 | 80 | 0.1793 | 0.9048 | 0.9140 | 0.9048 | 0.9037 |
64
 
65
 
66
  ### Framework versions
logs/events.out.tfevents.1737587003.PC CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e4c1017b804fd4eea1d934479916657a24739df219581eb9b82ef8961d35c5ec
3
- size 9343
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff1bcb0abfe0b5ec812510daaf52a9676598f4c4628c4fc55c59bea7c310aae2
3
+ size 10154
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69ff2b8dd9a16370d913d9c850901845cc6eb8a179b95756a6c5440ab293be4f
3
  size 598445936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ccbe29a7092f115f3689d8746ed210128905844a02038a055de5f980ea1aaa6
3
  size 598445936