Hugging Face's logo

Amir13
/
xlm-roberta-base-ncbi_disease-en

Token Classification
Transformers
PyTorch
xlm-roberta
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
1
Amir13 commited on
Commit
ffeb4f5
•
1 Parent(s): c410ca3

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +103 -0
README.md ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - ncbi_disease
7
+ metrics:
8
+ - precision
9
+ - recall
10
+ - f1
11
+ - accuracy
12
+ model-index:
13
+ - name: xlm-roberta-base-ncbi_disease-en
14
+ results:
15
+ - task:
16
+ name: Token Classification
17
+ type: token-classification
18
+ dataset:
19
+ name: ncbi_disease
20
+ type: ncbi_disease
21
+ config: ncbi_disease
22
+ split: validation
23
+ args: ncbi_disease
24
+ metrics:
25
+ - name: Precision
26
+ type: precision
27
+ value: 0.8562421185372006
28
+ - name: Recall
29
+ type: recall
30
+ value: 0.8627700127064803
31
+ - name: F1
32
+ type: f1
33
+ value: 0.859493670886076
34
+ - name: Accuracy
35
+ type: accuracy
36
+ value: 0.9868991989319092
37
+ ---
38
+
39
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
40
+ should probably proofread and complete it, then remove this comment. -->
41
+
42
+ # xlm-roberta-base-ncbi_disease-en
43
+
44
+ This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the ncbi_disease dataset.
45
+ It achieves the following results on the evaluation set:
46
+ - Loss: 0.0496
47
+ - Precision: 0.8562
48
+ - Recall: 0.8628
49
+ - F1: 0.8595
50
+ - Accuracy: 0.9869
51
+
52
+ ## Model description
53
+
54
+ More information needed
55
+
56
+ ## Intended uses & limitations
57
+
58
+ More information needed
59
+
60
+ ## Training and evaluation data
61
+
62
+ More information needed
63
+
64
+ ## Training procedure
65
+
66
+ ### Training hyperparameters
67
+
68
+ The following hyperparameters were used during training:
69
+ - learning_rate: 2e-05
70
+ - train_batch_size: 32
71
+ - eval_batch_size: 32
72
+ - seed: 42
73
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
74
+ - lr_scheduler_type: linear
75
+ - num_epochs: 15
76
+
77
+ ### Training results
78
+
79
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
80
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
81
+ | No log | 1.0 | 170 | 0.0555 | 0.7949 | 0.7980 | 0.7964 | 0.9833 |
82
+ | No log | 2.0 | 340 | 0.0524 | 0.7404 | 0.8551 | 0.7936 | 0.9836 |
83
+ | 0.0803 | 3.0 | 510 | 0.0484 | 0.7932 | 0.8869 | 0.8374 | 0.9849 |
84
+ | 0.0803 | 4.0 | 680 | 0.0496 | 0.8562 | 0.8628 | 0.8595 | 0.9869 |
85
+ | 0.0803 | 5.0 | 850 | 0.0562 | 0.7976 | 0.8615 | 0.8283 | 0.9848 |
86
+ | 0.0152 | 6.0 | 1020 | 0.0606 | 0.8086 | 0.8856 | 0.8454 | 0.9846 |
87
+ | 0.0152 | 7.0 | 1190 | 0.0709 | 0.8412 | 0.8412 | 0.8412 | 0.9866 |
88
+ | 0.0152 | 8.0 | 1360 | 0.0735 | 0.8257 | 0.8666 | 0.8456 | 0.9843 |
89
+ | 0.0059 | 9.0 | 1530 | 0.0730 | 0.8343 | 0.8767 | 0.8550 | 0.9866 |
90
+ | 0.0059 | 10.0 | 1700 | 0.0855 | 0.8130 | 0.8895 | 0.8495 | 0.9843 |
91
+ | 0.0059 | 11.0 | 1870 | 0.0868 | 0.8263 | 0.8767 | 0.8508 | 0.9860 |
92
+ | 0.0026 | 12.0 | 2040 | 0.0862 | 0.8273 | 0.8767 | 0.8513 | 0.9858 |
93
+ | 0.0026 | 13.0 | 2210 | 0.0875 | 0.8329 | 0.8806 | 0.8561 | 0.9859 |
94
+ | 0.0026 | 14.0 | 2380 | 0.0889 | 0.8287 | 0.8793 | 0.8533 | 0.9859 |
95
+ | 0.0013 | 15.0 | 2550 | 0.0884 | 0.8321 | 0.8755 | 0.8533 | 0.9861 |
96
+
97
+
98
+ ### Framework versions
99
+
100
+ - Transformers 4.26.1
101
+ - Pytorch 1.13.1+cu116
102
+ - Datasets 2.9.0
103
+ - Tokenizers 0.13.2