Hugging Face's logo

Dagobert42
/
distilbert-base-uncased-biored-augmented

Token Classification
Transformers
Safetensors
English
distilbert
low-resource NER
token_classification
biomedicine
medical NER
Generated from Trainer
Inference Endpoints
Model card Files Community
Dagobert42 commited on
Commit
c733bb4
•
1 Parent(s): 2a0f460

Push ../models/distilbert-base-uncased/biored-augmentations-only/ trained on biored-original_splits.pt (200 samples)

Browse files
Files changed (3) hide show
  1. README.md +12 -11
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -28,12 +28,12 @@ should probably proofread and complete it, then remove this comment. -->
28
 
29
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the bigbio/biored dataset.
30
  It achieves the following results on the evaluation set:
31
- - Loss: 0.5261
32
- - Accuracy: 0.8137
33
- - Precision: 0.6201
34
- - Recall: 0.5381
35
- - F1: 0.5692
36
- - Weighted F1: 0.8049
37
 
38
  ## Model description
39
 
@@ -64,11 +64,12 @@ The following hyperparameters were used during training:
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Weighted F1 |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:-----------:|
67
- | No log | 1.0 | 25 | 0.5643 | 0.8003 | 0.6481 | 0.4892 | 0.5295 | 0.7835 |
68
- | No log | 2.0 | 50 | 0.5615 | 0.8027 | 0.6359 | 0.5316 | 0.562 | 0.7934 |
69
- | No log | 3.0 | 75 | 0.5523 | 0.8093 | 0.6493 | 0.5434 | 0.576 | 0.7992 |
70
- | No log | 4.0 | 100 | 0.5566 | 0.8087 | 0.6275 | 0.5834 | 0.6012 | 0.8032 |
71
- | No log | 5.0 | 125 | 0.5615 | 0.8089 | 0.6316 | 0.593 | 0.6055 | 0.8052 |
 
72
 
73
 
74
  ### Framework versions
 
28
 
29
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the bigbio/biored dataset.
30
  It achieves the following results on the evaluation set:
31
+ - Loss: 0.5260
32
+ - Accuracy: 0.8133
33
+ - Precision: 0.6083
34
+ - Recall: 0.5678
35
+ - F1: 0.5839
36
+ - Weighted F1: 0.8098
37
 
38
  ## Model description
39
 
 
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Weighted F1 |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:-----------:|
67
+ | No log | 1.0 | 25 | 0.5511 | 0.8048 | 0.594 | 0.5104 | 0.5398 | 0.792 |
68
+ | No log | 2.0 | 50 | 0.5480 | 0.8075 | 0.6351 | 0.5573 | 0.5824 | 0.8 |
69
+ | No log | 3.0 | 75 | 0.5479 | 0.8128 | 0.657 | 0.5467 | 0.5781 | 0.8032 |
70
+ | No log | 4.0 | 100 | 0.5472 | 0.8111 | 0.6286 | 0.5859 | 0.6033 | 0.8063 |
71
+ | No log | 5.0 | 125 | 0.5590 | 0.8099 | 0.6159 | 0.5816 | 0.5914 | 0.8065 |
72
+ | No log | 6.0 | 150 | 0.5616 | 0.8131 | 0.5851 | 0.5673 | 0.5756 | 0.8098 |
73
 
74
 
75
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41173b02617312228bb8a89f0c876c8d3772fc8eb4118905cffa7864c745be3d
3
  size 265485396
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01e3b1e74db6c9610152a99449672c679dd2c1ad3628a49307237c3d57cc9a03
3
  size 265485396
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc42f705404d3b1f29599205dda0d8071f4d694a59e2a9a3664d16e8522e7ea7
3
  size 4219
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e763d358eeb8947f2af1349e7277d42802ee2f6d84af1b860ccd89672c096ccf
3
  size 4219