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
c29ec66
•
1 Parent(s): e65e0ea

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

Browse files
Files changed (3) hide show
  1. README.md +12 -23
  2. model.safetensors +1 -1
  3. training_args.bin +2 -2
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: 0.1552
32
- - Accuracy: 0.9545
33
- - Precision: 0.8651
34
- - Recall: 0.8306
35
- - F1: 0.8454
36
- - Weighted F1: 0.9544
37
 
38
  ## Model description
39
 
@@ -52,34 +52,23 @@ 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
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
- - lr_scheduler_warmup_ratio: 0.004
62
  - num_epochs: 50
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Weighted F1 |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:-----------:|
68
- | No log | 0.5 | 10 | 0.2276 | 0.9252 | 0.7871 | 0.7482 | 0.7616 | 0.9233 |
69
- | No log | 1.0 | 20 | 0.2124 | 0.9318 | 0.8363 | 0.7571 | 0.7923 | 0.9298 |
70
- | No log | 1.5 | 30 | 0.2052 | 0.9342 | 0.8199 | 0.794 | 0.8057 | 0.9334 |
71
- | No log | 2.0 | 40 | 0.1958 | 0.9396 | 0.8132 | 0.8049 | 0.8038 | 0.9384 |
72
- | No log | 2.5 | 50 | 0.2043 | 0.9385 | 0.8162 | 0.8086 | 0.811 | 0.9377 |
73
- | No log | 3.0 | 60 | 0.1948 | 0.9409 | 0.8413 | 0.8109 | 0.8249 | 0.9404 |
74
- | No log | 3.5 | 70 | 0.1951 | 0.9436 | 0.8449 | 0.7963 | 0.8186 | 0.9425 |
75
- | No log | 4.0 | 80 | 0.2032 | 0.941 | 0.8169 | 0.8158 | 0.8158 | 0.9411 |
76
- | No log | 4.5 | 90 | 0.1984 | 0.944 | 0.827 | 0.8125 | 0.8194 | 0.9435 |
77
- | No log | 5.0 | 100 | 0.1982 | 0.9451 | 0.8313 | 0.8072 | 0.8184 | 0.9443 |
78
- | No log | 5.5 | 110 | 0.1968 | 0.9456 | 0.8249 | 0.8124 | 0.8178 | 0.945 |
79
- | No log | 6.0 | 120 | 0.2083 | 0.9432 | 0.8113 | 0.8173 | 0.8136 | 0.9429 |
80
- | No log | 6.5 | 130 | 0.2105 | 0.9441 | 0.8355 | 0.8132 | 0.8236 | 0.9436 |
81
- | No log | 7.0 | 140 | 0.2083 | 0.9439 | 0.8312 | 0.8207 | 0.8253 | 0.9439 |
82
- | No log | 7.5 | 150 | 0.2145 | 0.9447 | 0.8293 | 0.8051 | 0.8161 | 0.9437 |
83
 
84
 
85
  ### 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: 0.1510
32
+ - Accuracy: 0.9508
33
+ - Precision: 0.8521
34
+ - Recall: 0.8278
35
+ - F1: 0.8391
36
+ - Weighted F1: 0.9506
37
 
38
  ## Model description
39
 
 
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
+ - learning_rate: 2e-05
56
  - train_batch_size: 8
57
  - eval_batch_size: 8
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
 
61
  - num_epochs: 50
62
 
63
  ### Training results
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Weighted F1 |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:-----------:|
67
+ | No log | 1.0 | 20 | 0.2068 | 0.9335 | 0.8641 | 0.7475 | 0.7976 | 0.9312 |
68
+ | No log | 2.0 | 40 | 0.1962 | 0.939 | 0.8035 | 0.8046 | 0.8013 | 0.9382 |
69
+ | No log | 3.0 | 60 | 0.1965 | 0.9429 | 0.8654 | 0.7947 | 0.826 | 0.9415 |
70
+ | No log | 4.0 | 80 | 0.1964 | 0.9443 | 0.8279 | 0.8174 | 0.8218 | 0.9436 |
71
+ | No log | 5.0 | 100 | 0.2051 | 0.9438 | 0.8441 | 0.8184 | 0.8286 | 0.9435 |
 
 
 
 
 
 
 
 
 
 
72
 
73
 
74
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8adedbe2a2a3862faa23dd17c7b61acad050afe83a4fe5f037e78c2b8f7012a6
3
  size 466917412
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92740ba814283aa0031de770387afff16addd2c30207a78bbb762b5bab3ee2f9
3
  size 466917412
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dbfd8252c3e73a251e113d4d0e44bc99babc57e7aeadb226a7b36d08aa8feace
3
- size 4283
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33d0e9fefe52cfeae34d833d1327d4c0ccdffc8d553028dc3310aee862880718
3
+ size 4219