Hugging Face's logo

Ghunghru
/
German-MedBERT

Text Classification
Transformers
PyTorch
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
Ghunghru commited on
Commit
43bb57d
•
1 Parent(s): 908e86b

End of training

Browse files
Files changed (4) hide show
  1. README.md +54 -14
  2. pytorch_model.bin +1 -1
  3. tokenizer.json +1 -8
  4. training_args.bin +1 -1
README.md CHANGED
@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [smanjil/German-MedBERT](https://huggingface.co/smanjil/German-MedBERT) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.6756
20
- - F1: 0.5231
21
 
22
  ## Model description
23
 
@@ -36,28 +36,68 @@ More information needed
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
- - learning_rate: 2e-06
40
  - train_batch_size: 8
41
  - eval_batch_size: 8
42
  - seed: 42
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
- - num_epochs: 10
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | F1 |
50
  |:-------------:|:-----:|:----:|:---------------:|:------:|
51
- | 0.6685 | 1.0 | 189 | 0.6026 | 0.0 |
52
- | 0.6161 | 2.0 | 378 | 0.5464 | 0.2326 |
53
- | 0.569 | 3.0 | 567 | 0.5510 | 0.2273 |
54
- | 0.5636 | 4.0 | 756 | 0.5546 | 0.3704 |
55
- | 0.5668 | 5.0 | 945 | 0.5323 | 0.4571 |
56
- | 0.4882 | 6.0 | 1134 | 0.7460 | 0.3265 |
57
- | 0.5819 | 7.0 | 1323 | 0.6150 | 0.4776 |
58
- | 0.4747 | 8.0 | 1512 | 0.6596 | 0.4923 |
59
- | 0.5035 | 9.0 | 1701 | 0.6764 | 0.5 |
60
- | 0.463 | 10.0 | 1890 | 0.6756 | 0.5231 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
61
 
62
 
63
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [smanjil/German-MedBERT](https://huggingface.co/smanjil/German-MedBERT) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.5145
20
+ - F1: 0.4561
21
 
22
  ## Model description
23
 
 
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
+ - learning_rate: 2e-07
40
  - train_batch_size: 8
41
  - eval_batch_size: 8
42
  - seed: 42
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
+ - num_epochs: 50
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | F1 |
50
  |:-------------:|:-----:|:----:|:---------------:|:------:|
51
+ | 0.693 | 1.0 | 189 | 0.6754 | 0.0698 |
52
+ | 0.6853 | 2.0 | 378 | 0.6626 | 0.0339 |
53
+ | 0.6654 | 3.0 | 567 | 0.6499 | 0.0488 |
54
+ | 0.6562 | 4.0 | 756 | 0.6399 | 0.0541 |
55
+ | 0.6554 | 5.0 | 945 | 0.6335 | 0.0556 |
56
+ | 0.6394 | 6.0 | 1134 | 0.6260 | 0.0571 |
57
+ | 0.6452 | 7.0 | 1323 | 0.6220 | 0.0571 |
58
+ | 0.6257 | 8.0 | 1512 | 0.6161 | 0.0571 |
59
+ | 0.6334 | 9.0 | 1701 | 0.6117 | 0.0571 |
60
+ | 0.6302 | 10.0 | 1890 | 0.6068 | 0.0571 |
61
+ | 0.6151 | 11.0 | 2079 | 0.6011 | 0.0571 |
62
+ | 0.6121 | 12.0 | 2268 | 0.5961 | 0.0571 |
63
+ | 0.6097 | 13.0 | 2457 | 0.5915 | 0.0571 |
64
+ | 0.5929 | 14.0 | 2646 | 0.5865 | 0.0556 |
65
+ | 0.5955 | 15.0 | 2835 | 0.5822 | 0.0556 |
66
+ | 0.5893 | 16.0 | 3024 | 0.5776 | 0.1053 |
67
+ | 0.5936 | 17.0 | 3213 | 0.5731 | 0.1 |
68
+ | 0.5769 | 18.0 | 3402 | 0.5687 | 0.1 |
69
+ | 0.5692 | 19.0 | 3591 | 0.5646 | 0.1 |
70
+ | 0.5739 | 20.0 | 3780 | 0.5604 | 0.2326 |
71
+ | 0.5705 | 21.0 | 3969 | 0.5564 | 0.2326 |
72
+ | 0.5651 | 22.0 | 4158 | 0.5525 | 0.2727 |
73
+ | 0.5654 | 23.0 | 4347 | 0.5494 | 0.2727 |
74
+ | 0.5527 | 24.0 | 4536 | 0.5456 | 0.2727 |
75
+ | 0.5542 | 25.0 | 4725 | 0.5425 | 0.2727 |
76
+ | 0.5464 | 26.0 | 4914 | 0.5395 | 0.2727 |
77
+ | 0.5383 | 27.0 | 5103 | 0.5364 | 0.3111 |
78
+ | 0.5323 | 28.0 | 5292 | 0.5348 | 0.3111 |
79
+ | 0.5343 | 29.0 | 5481 | 0.5318 | 0.3404 |
80
+ | 0.5305 | 30.0 | 5670 | 0.5299 | 0.4082 |
81
+ | 0.5252 | 31.0 | 5859 | 0.5278 | 0.4 |
82
+ | 0.516 | 32.0 | 6048 | 0.5270 | 0.3922 |
83
+ | 0.5181 | 33.0 | 6237 | 0.5243 | 0.4231 |
84
+ | 0.5202 | 34.0 | 6426 | 0.5230 | 0.4231 |
85
+ | 0.5068 | 35.0 | 6615 | 0.5224 | 0.4231 |
86
+ | 0.514 | 36.0 | 6804 | 0.5205 | 0.4528 |
87
+ | 0.5014 | 37.0 | 6993 | 0.5194 | 0.4528 |
88
+ | 0.4899 | 38.0 | 7182 | 0.5188 | 0.4444 |
89
+ | 0.5104 | 39.0 | 7371 | 0.5164 | 0.4364 |
90
+ | 0.4823 | 40.0 | 7560 | 0.5174 | 0.4444 |
91
+ | 0.515 | 41.0 | 7749 | 0.5155 | 0.4364 |
92
+ | 0.4906 | 42.0 | 7938 | 0.5154 | 0.4364 |
93
+ | 0.4853 | 43.0 | 8127 | 0.5158 | 0.4364 |
94
+ | 0.5006 | 44.0 | 8316 | 0.5153 | 0.4364 |
95
+ | 0.503 | 45.0 | 8505 | 0.5146 | 0.4561 |
96
+ | 0.4915 | 46.0 | 8694 | 0.5141 | 0.4561 |
97
+ | 0.4903 | 47.0 | 8883 | 0.5144 | 0.4561 |
98
+ | 0.4892 | 48.0 | 9072 | 0.5146 | 0.4561 |
99
+ | 0.4939 | 49.0 | 9261 | 0.5146 | 0.4561 |
100
+ | 0.5007 | 50.0 | 9450 | 0.5145 | 0.4561 |
101
 
102
 
103
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a51b43fb204382da48f62dfdd44503811ce6e0b202836e3d5a717fc735d91736
3
  size 436400366
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1393c98d9ff3204224abf1e0d7128b79af6b3dfc5381fb01c58c3a2a2e70aaba
3
  size 436400366
tokenizer.json CHANGED
@@ -6,14 +6,7 @@
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
9
- "padding": {
10
- "strategy": "BatchLongest",
11
- "direction": "Right",
12
- "pad_to_multiple_of": null,
13
- "pad_id": 0,
14
- "pad_type_id": 0,
15
- "pad_token": "[PAD]"
16
- },
17
  "added_tokens": [
18
  {
19
  "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:fb3a669c13f8a4768782da76a54388fc8af4d97afaf45bdb8492f13dca4bb3af
3
  size 4536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:777acf9b33e7171a694431120a4c5729c879cd1f3d36d08fe66fb6b9bf5840d2
3
  size 4536