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
8d1de93
•
1 Parent(s): b8bcad5

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 +13 -13
  2. model.safetensors +1 -1
  3. spiece.model +3 -0
  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: 0.3001
32
- - Accuracy: 0.904
33
- - Precision: 0.8054
34
- - Recall: 0.7645
35
- - F1: 0.782
36
- - Weighted F1: 0.9033
37
 
38
  ## Model description
39
 
@@ -64,17 +64,17 @@ 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 | 0.3323 | 0.886 | 0.8098 | 0.7466 | 0.7749 | 0.883 |
68
- | No log | 2.0 | 50 | 0.3214 | 0.8925 | 0.7932 | 0.8007 | 0.7959 | 0.8916 |
69
- | No log | 3.0 | 75 | 0.3224 | 0.8899 | 0.7877 | 0.8196 | 0.802 | 0.8918 |
70
- | No log | 4.0 | 100 | 0.3175 | 0.9016 | 0.8367 | 0.7969 | 0.8149 | 0.9005 |
71
- | No log | 5.0 | 125 | 0.3334 | 0.8978 | 0.8189 | 0.8093 | 0.8123 | 0.8985 |
72
- | No log | 6.0 | 150 | 0.3463 | 0.9029 | 0.8146 | 0.8099 | 0.812 | 0.9027 |
73
 
74
 
75
  ### Framework versions
76
 
77
  - Transformers 4.35.2
78
  - Pytorch 2.0.1+cu117
79
- - Datasets 2.12.0
80
  - Tokenizers 0.15.0
 
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: 0.1516
32
+ - Accuracy: 0.9538
33
+ - Precision: 0.8555
34
+ - Recall: 0.8548
35
+ - F1: 0.8549
36
+ - Weighted F1: 0.9538
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 | 20 | 0.2179 | 0.9233 | 0.7641 | 0.7884 | 0.772 | 0.9245 |
68
+ | No log | 2.0 | 40 | 0.1948 | 0.9381 | 0.8288 | 0.793 | 0.8081 | 0.9375 |
69
+ | No log | 3.0 | 60 | 0.1924 | 0.9427 | 0.8614 | 0.8014 | 0.8293 | 0.9416 |
70
+ | No log | 4.0 | 80 | 0.1917 | 0.9442 | 0.8333 | 0.8085 | 0.8204 | 0.9434 |
71
+ | No log | 5.0 | 100 | 0.1993 | 0.9432 | 0.8365 | 0.8228 | 0.8295 | 0.9428 |
72
+ | No log | 6.0 | 120 | 0.2087 | 0.9418 | 0.8305 | 0.8273 | 0.8286 | 0.9418 |
73
 
74
 
75
  ### Framework versions
76
 
77
  - Transformers 4.35.2
78
  - Pytorch 2.0.1+cu117
79
+ - Datasets 2.18.0
80
  - Tokenizers 0.15.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d7798d1941290b3bfc375a30ae7783c366b781d40eb18ae8be4887dc73d98342
3
  size 466917412
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93f0f057cd7f4d3dda586f71ec046d610931f2a1de3a3f332c53f55d74807f56
3
  size 466917412
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f8c1c0bc2854d1af911a8550288c1258af5ba50277f3a5c829b98eb86fc5646
3
+ size 798011
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:50041f5b6e78071a83b55f3e07af36c4ddeb56183a5f98e5bc1597ef419d25a5
3
  size 4219
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ee1ab3677da6ebf70cd27c751691d9d61c3d91e3e79930debebad4fac9df028
3
  size 4219