Hugging Face's logo

Dagobert42
/
xlnet-base-cased-biored-augmented

Token Classification
Transformers
Safetensors
English
xlnet
low-resource NER
token_classification
biomedicine
medical NER
Generated from Trainer
Inference Endpoints
Model card Files Community
Dagobert42 commited on
Commit
df393d7
•
1 Parent(s): 262a74b

Push ../models/xlnet/xlnet-base-cased/biored-augmentations-only/ trained on biored-train_160_splits.pt (160 samples)

Browse files
Files changed (4) hide show
  1. README.md +15 -17
  2. model.safetensors +1 -1
  3. tokenizer.json +1 -10
  4. 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 [xlnet-base-cased](https://huggingface.co/xlnet-base-cased) on the bigbio/biored dataset.
30
  It achieves the following results on the evaluation set:
31
- - Loss: 0.1676
32
- - Accuracy: 0.9551
33
- - Precision: 0.8878
34
- - Recall: 0.847
35
- - F1: 0.8624
36
- - Weighted F1: 0.9551
37
 
38
  ## Model description
39
 
@@ -52,7 +52,7 @@ More information needed
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
- - learning_rate: 1.8e-05
56
  - train_batch_size: 8
57
  - eval_batch_size: 8
58
  - seed: 42
@@ -64,16 +64,14 @@ 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 | 20 | 0.2094 | 0.9301 | 0.7924 | 0.7914 | 0.7886 | 0.9301 |
68
- | No log | 2.0 | 40 | 0.1915 | 0.9391 | 0.8202 | 0.8032 | 0.808 | 0.9383 |
69
- | No log | 3.0 | 60 | 0.1901 | 0.9425 | 0.8239 | 0.8169 | 0.8197 | 0.9418 |
70
- | No log | 4.0 | 80 | 0.1872 | 0.9461 | 0.8361 | 0.8277 | 0.8304 | 0.9453 |
71
- | No log | 5.0 | 100 | 0.2001 | 0.9455 | 0.8269 | 0.8251 | 0.8245 | 0.9448 |
72
- | No log | 6.0 | 120 | 0.2063 | 0.9462 | 0.845 | 0.8288 | 0.8354 | 0.9457 |
73
- | No log | 7.0 | 140 | 0.2081 | 0.9458 | 0.8153 | 0.8353 | 0.8235 | 0.9458 |
74
- | No log | 8.0 | 160 | 0.2274 | 0.9454 | 0.8192 | 0.8329 | 0.8245 | 0.9452 |
75
- | No log | 9.0 | 180 | 0.2286 | 0.9475 | 0.8298 | 0.8332 | 0.8303 | 0.9471 |
76
- | No log | 10.0 | 200 | 0.2404 | 0.9473 | 0.8352 | 0.83 | 0.8314 | 0.9467 |
77
 
78
 
79
  ### Framework versions
 
28
 
29
  This model is a fine-tuned version of [xlnet-base-cased](https://huggingface.co/xlnet-base-cased) on the bigbio/biored dataset.
30
  It achieves the following results on the evaluation set:
31
+ - Loss: 0.1576
32
+ - Accuracy: 0.9544
33
+ - Precision: 0.8802
34
+ - Recall: 0.858
35
+ - F1: 0.8663
36
+ - Weighted F1: 0.9546
37
 
38
  ## Model description
39
 
 
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
+ - learning_rate: 1.5e-05
56
  - train_batch_size: 8
57
  - eval_batch_size: 8
58
  - seed: 42
 
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Weighted F1 |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:-----------:|
67
+ | No log | 1.0 | 20 | 0.2001 | 0.9348 | 0.8286 | 0.7628 | 0.791 | 0.9332 |
68
+ | No log | 2.0 | 40 | 0.1961 | 0.9367 | 0.7938 | 0.8119 | 0.8015 | 0.9365 |
69
+ | No log | 3.0 | 60 | 0.1902 | 0.9422 | 0.8297 | 0.8124 | 0.8202 | 0.9416 |
70
+ | No log | 4.0 | 80 | 0.1948 | 0.9426 | 0.8323 | 0.8226 | 0.8269 | 0.9422 |
71
+ | No log | 5.0 | 100 | 0.1969 | 0.9429 | 0.8152 | 0.8279 | 0.8208 | 0.9431 |
72
+ | No log | 6.0 | 120 | 0.2071 | 0.9426 | 0.8194 | 0.8324 | 0.8257 | 0.943 |
73
+ | No log | 7.0 | 140 | 0.2024 | 0.9455 | 0.8244 | 0.8284 | 0.8258 | 0.9453 |
74
+ | No log | 8.0 | 160 | 0.2143 | 0.9451 | 0.8241 | 0.8294 | 0.8257 | 0.9449 |
 
 
75
 
76
 
77
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6fc847eeef8ba0fc8a3adff9f6e6a20c8d8dc83b149570197b4e5d667ef97849
3
  size 466917412
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38a73cc9e217b8b60675df8c2a4c0c5733837592ce2ce1f85fa2e0f7e71265f7
3
  size 466917412
tokenizer.json CHANGED
@@ -6,16 +6,7 @@
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
9
- "padding": {
10
- "strategy": {
11
- "Fixed": 512
12
- },
13
- "direction": "Left",
14
- "pad_to_multiple_of": null,
15
- "pad_id": 5,
16
- "pad_type_id": 3,
17
- "pad_token": "<pad>"
18
- },
19
  "added_tokens": [
20
  {
21
  "id": 0,
 
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
9
+ "padding": null,
 
 
 
 
 
 
 
 
 
10
  "added_tokens": [
11
  {
12
  "id": 0,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:64e325d07f2a1379926408048773612769801fda2abced01956b307b5d668c19
3
  size 4219
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:015e17f0f2bafab9d81d61e5dfd4433b10c65c6fda6d23e857668b07ec8838d2
3
  size 4219