Hugging Face's logo

ekaterinatao
/
nerel-bio-RuBioBERT-al

Token Classification
Transformers
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
ekaterinatao commited on
Commit
99d2ef0
•
1 Parent(s): b447eda

Model save

Browse files
Files changed (4) hide show
  1. README.md +18 -18
  2. config.json +1 -1
  3. model.safetensors +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -19,11 +19,11 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [alexyalunin/RuBioBERT](https://huggingface.co/alexyalunin/RuBioBERT) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.9026
23
- - Precision: 0.7943
24
- - Recall: 0.7969
25
- - F1: 0.7956
26
- - Accuracy: 0.8601
27
 
28
  ## Model description
29
 
@@ -55,21 +55,21 @@ The following hyperparameters were used during training:
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
- | 0.0824 | 1.0 | 107 | 0.7494 | 0.7913 | 0.7941 | 0.7927 | 0.8564 |
59
- | 0.0463 | 2.0 | 214 | 0.8337 | 0.7781 | 0.7814 | 0.7798 | 0.8491 |
60
- | 0.0368 | 3.0 | 321 | 0.8365 | 0.7893 | 0.7941 | 0.7917 | 0.8538 |
61
- | 0.0214 | 4.0 | 428 | 0.8609 | 0.7888 | 0.7875 | 0.7882 | 0.8561 |
62
- | 0.0117 | 5.0 | 535 | 0.8701 | 0.7926 | 0.7913 | 0.7919 | 0.8577 |
63
- | 0.0069 | 6.0 | 642 | 0.8605 | 0.7889 | 0.7906 | 0.7897 | 0.8558 |
64
- | 0.004 | 7.0 | 749 | 0.8890 | 0.7932 | 0.7997 | 0.7964 | 0.8597 |
65
- | 0.0035 | 8.0 | 856 | 0.8995 | 0.7922 | 0.7967 | 0.7944 | 0.8589 |
66
- | 0.0021 | 9.0 | 963 | 0.9024 | 0.7943 | 0.7969 | 0.7956 | 0.8601 |
67
- | 0.0014 | 10.0 | 1070 | 0.9026 | 0.7943 | 0.7969 | 0.7956 | 0.8601 |
68
 
69
 
70
  ### Framework versions
71
 
72
- - Transformers 4.38.1
73
- - Pytorch 2.1.0+cu121
74
- - Datasets 2.17.1
75
  - Tokenizers 0.15.2
 
19
 
20
  This model is a fine-tuned version of [alexyalunin/RuBioBERT](https://huggingface.co/alexyalunin/RuBioBERT) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.8600
23
+ - Precision: 0.7989
24
+ - Recall: 0.8058
25
+ - F1: 0.8023
26
+ - Accuracy: 0.8685
27
 
28
  ## Model description
29
 
 
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
+ | 0.1037 | 1.0 | 153 | 0.7450 | 0.7933 | 0.8002 | 0.7967 | 0.8632 |
59
+ | 0.043 | 2.0 | 306 | 0.7535 | 0.7742 | 0.7882 | 0.7812 | 0.8558 |
60
+ | 0.0314 | 3.0 | 459 | 0.7996 | 0.7874 | 0.7981 | 0.7927 | 0.8605 |
61
+ | 0.0173 | 4.0 | 612 | 0.8434 | 0.7814 | 0.7906 | 0.7860 | 0.8570 |
62
+ | 0.0133 | 5.0 | 765 | 0.7945 | 0.7988 | 0.8046 | 0.8017 | 0.8679 |
63
+ | 0.007 | 6.0 | 918 | 0.8361 | 0.7947 | 0.8042 | 0.7994 | 0.8673 |
64
+ | 0.0031 | 7.0 | 1071 | 0.8614 | 0.7969 | 0.8023 | 0.7996 | 0.8670 |
65
+ | 0.0028 | 8.0 | 1224 | 0.8582 | 0.7971 | 0.8035 | 0.8003 | 0.8681 |
66
+ | 0.0005 | 9.0 | 1377 | 0.8587 | 0.7989 | 0.8051 | 0.8020 | 0.8682 |
67
+ | 0.0004 | 10.0 | 1530 | 0.8600 | 0.7989 | 0.8058 | 0.8023 | 0.8685 |
68
 
69
 
70
  ### Framework versions
71
 
72
+ - Transformers 4.38.2
73
+ - Pytorch 2.2.1+cu121
74
+ - Datasets 2.18.0
75
  - Tokenizers 0.15.2
config.json CHANGED
@@ -118,7 +118,7 @@
118
  "pooler_type": "first_token_transform",
119
  "position_embedding_type": "absolute",
120
  "torch_dtype": "float32",
121
- "transformers_version": "4.38.1",
122
  "type_vocab_size": 2,
123
  "use_cache": true,
124
  "vocab_size": 120138
 
118
  "pooler_type": "first_token_transform",
119
  "position_embedding_type": "absolute",
120
  "torch_dtype": "float32",
121
+ "transformers_version": "4.38.2",
122
  "type_vocab_size": 2,
123
  "use_cache": true,
124
  "vocab_size": 120138
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee86b1d40d71965c06f66916e70faee2e3c0fcf44f5dc8ccb4f8155181a3339e
3
  size 711028724
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54153cc0f2e3c890b01558b6b4faf71a6b4839c67a695ec766a633509443fc0d
3
  size 711028724
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:49631093f34a5de60a822b33c8e428bdad43a3447b643ffb5a473e543d18de08
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cb7833245a14278793c77d29c8b6693bf1a0cd02ae2a6e776ef22079b7504e1
3
  size 4984