Hugging Face's logo

VampeeHuntee
/
xlm-roberta-base_detect_span

Token Classification
Transformers
Safetensors
Vietnamese
xlm-roberta
Generated from Trainer
Model card Files
xet
 Community
VampeeHuntee commited on
Commit
c60decb
·
verified ·
1 Parent(s): 5ae73e8

End of training

Browse files
Files changed (4) hide show
  1. README.md +11 -20
  2. config.json +4 -40
  3. model.safetensors +2 -2
  4. training_args.bin +1 -1
README.md CHANGED
@@ -17,19 +17,10 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [FacebookAI/xlm-roberta-base](https://huggingface.co/FacebookAI/xlm-roberta-base) on the covid19_ner dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.0807
21
- - Patient Id: 0.9855
22
- - Name: 0.9337
23
- - Gender: 0.9714
24
- - Age: 0.9834
25
- - Job: 0.8092
26
- - Location: 0.9596
27
- - Organization: 0.8897
28
- - Date: 0.9860
29
- - Symptom And Disease: 0.8885
30
- - Transportation: 1.0
31
- - F1 Macro: 0.9407
32
- - F1 Micro: 0.9541
33
 
34
  ## Model description
35
 
@@ -58,13 +49,13 @@ The following hyperparameters were used during training:
58
 
59
  ### Training results
60
 
61
- | Training Loss | Epoch | Step | Validation Loss | Patient Id | Name | Gender | Age | Job | Location | Organization | Date | Symptom And Disease | Transportation | F1 Macro | F1 Micro |
62
- |:-------------:|:-----:|:----:|:---------------:|:----------:|:------:|:------:|:------:|:------:|:--------:|:------------:|:------:|:-------------------:|:--------------:|:--------:|:--------:|
63
- | 0.216 | 1.0 | 629 | 0.0912 | 0.9477 | 0.9143 | 0.8367 | 0.9237 | 0.6228 | 0.9426 | 0.8234 | 0.9811 | 0.8603 | 0.9827 | 0.8835 | 0.9202 |
64
- | 0.0478 | 2.0 | 1258 | 0.0832 | 0.9860 | 0.8942 | 0.9414 | 0.9741 | 0.5368 | 0.9434 | 0.8584 | 0.9811 | 0.8722 | 0.9829 | 0.8970 | 0.9369 |
65
- | 0.0306 | 3.0 | 1887 | 0.0744 | 0.9867 | 0.9206 | 0.9494 | 0.9780 | 0.7664 | 0.9550 | 0.8913 | 0.9860 | 0.8791 | 0.9829 | 0.9295 | 0.9492 |
66
- | 0.0211 | 4.0 | 2516 | 0.0789 | 0.9863 | 0.9309 | 0.9661 | 0.9793 | 0.7795 | 0.9549 | 0.8859 | 0.9860 | 0.8844 | 1.0 | 0.9353 | 0.9508 |
67
- | 0.0153 | 5.0 | 3145 | 0.0807 | 0.9855 | 0.9337 | 0.9714 | 0.9834 | 0.8092 | 0.9596 | 0.8897 | 0.9860 | 0.8885 | 1.0 | 0.9407 | 0.9541 |
68
 
69
 
70
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [FacebookAI/xlm-roberta-base](https://huggingface.co/FacebookAI/xlm-roberta-base) on the covid19_ner dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.0709
21
+ - X: 0.9587
22
+ - F1 Macro: 0.9587
23
+ - F1 Micro: 0.9587
 
 
 
 
 
 
 
 
 
24
 
25
  ## Model description
26
 
 
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss | X | F1 Macro | F1 Micro |
53
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:--------:|:--------:|
54
+ | 0.0949 | 1.0 | 629 | 0.0695 | 0.9338 | 0.9338 | 0.9338 |
55
+ | 0.0303 | 2.0 | 1258 | 0.0620 | 0.9500 | 0.9500 | 0.9500 |
56
+ | 0.0199 | 3.0 | 1887 | 0.0648 | 0.9570 | 0.9570 | 0.9570 |
57
+ | 0.0129 | 4.0 | 2516 | 0.0644 | 0.9584 | 0.9584 | 0.9584 |
58
+ | 0.0097 | 5.0 | 3145 | 0.0709 | 0.9587 | 0.9587 | 0.9587 |
59
 
60
 
61
  ### Framework versions
config.json CHANGED
@@ -12,50 +12,14 @@
12
  "hidden_size": 768,
13
  "id2label": {
14
  "0": "O",
15
- "1": "B-PATIENT_ID",
16
- "2": "I-PATIENT_ID",
17
- "3": "B-NAME",
18
- "4": "I-NAME",
19
- "5": "B-GENDER",
20
- "6": "I-GENDER",
21
- "7": "B-AGE",
22
- "8": "I-AGE",
23
- "9": "B-JOB",
24
- "10": "I-JOB",
25
- "11": "B-LOCATION",
26
- "12": "I-LOCATION",
27
- "13": "B-ORGANIZATION",
28
- "14": "I-ORGANIZATION",
29
- "15": "B-DATE",
30
- "16": "I-DATE",
31
- "17": "B-SYMPTOM_AND_DISEASE",
32
- "18": "I-SYMPTOM_AND_DISEASE",
33
- "19": "B-TRANSPORTATION",
34
- "20": "I-TRANSPORTATION"
35
  },
36
  "initializer_range": 0.02,
37
  "intermediate_size": 3072,
38
  "label2id": {
39
- "B-AGE": 7,
40
- "B-DATE": 15,
41
- "B-GENDER": 5,
42
- "B-JOB": 9,
43
- "B-LOCATION": 11,
44
- "B-NAME": 3,
45
- "B-ORGANIZATION": 13,
46
- "B-PATIENT_ID": 1,
47
- "B-SYMPTOM_AND_DISEASE": 17,
48
- "B-TRANSPORTATION": 19,
49
- "I-AGE": 8,
50
- "I-DATE": 16,
51
- "I-GENDER": 6,
52
- "I-JOB": 10,
53
- "I-LOCATION": 12,
54
- "I-NAME": 4,
55
- "I-ORGANIZATION": 14,
56
- "I-PATIENT_ID": 2,
57
- "I-SYMPTOM_AND_DISEASE": 18,
58
- "I-TRANSPORTATION": 20,
59
  "O": 0
60
  },
61
  "layer_norm_eps": 1e-05,
 
12
  "hidden_size": 768,
13
  "id2label": {
14
  "0": "O",
15
+ "1": "B-X",
16
+ "2": "I-X"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
17
  },
18
  "initializer_range": 0.02,
19
  "intermediate_size": 3072,
20
  "label2id": {
21
+ "B-X": 1,
22
+ "I-X": 2,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
23
  "O": 0
24
  },
25
  "layer_norm_eps": 1e-05,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5d68966d3e6de6171b5c9dca6be81d3d3701a3eb7e76d927c19e306eeaa43a3
3
- size 1109900868
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48ea510922ee1ae4e9906a550d42655bf6250699a05ffbda7d9a7be0039dfb41
3
+ size 1109845500
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf670d0160c8de0ac3f12a000b5412a4dced2fde07591283d2b69b3c9e3934e6
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7dec8925bc2af6b3c9c7f98923ba9206205a40e3847ccd19bfe8ff55f20399c0
3
  size 5240