Hugging Face's logo

nhidinh2
/
xlm-roberta-base-finetuned-ner-thesis-dseb

Token Classification
Transformers
TensorBoard
Safetensors
xlm-roberta
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
nhidinh2 commited on
Commit
8260c9c
•
1 Parent(s): 2efa433

End of training

Browse files
Files changed (11) hide show
  1. README.md +20 -20
  2. config.json +5 -1
  3. model.safetensors +2 -2
  4. runs/Jul08_09-37-51_710793e53bac/events.out.tfevents.1720431494.710793e53bac.504.0 +3 -0
  5. runs/Jul08_09-38-53_710793e53bac/events.out.tfevents.1720431539.710793e53bac.504.1 +3 -0
  6. runs/Jul08_09-38-53_710793e53bac/events.out.tfevents.1720431589.710793e53bac.504.2 +3 -0
  7. runs/Jul08_09-41-51_710793e53bac/events.out.tfevents.1720431714.710793e53bac.504.3 +3 -0
  8. runs/Jul08_09-53-32_710793e53bac/events.out.tfevents.1720432418.710793e53bac.504.4 +3 -0
  9. runs/Jul08_09-54-09_710793e53bac/events.out.tfevents.1720432451.710793e53bac.504.5 +3 -0
  10. runs/Jul08_09-54-09_710793e53bac/events.out.tfevents.1720432698.710793e53bac.504.6 +3 -0
  11. training_args.bin +1 -1
README.md CHANGED
@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.0876
24
- - Precision: 0.4444
25
- - Recall: 0.8571
26
- - F1: 0.5854
27
- - Accuracy: 0.9855
28
 
29
  ## Model description
30
 
@@ -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
- | 0.0573 | 1.0 | 50 | 0.2845 | 0.0 | 0.0 | 0.0 | 0.9466 |
59
- | 0.1031 | 2.0 | 100 | 0.2074 | 0.0 | 0.0 | 0.0 | 0.9466 |
60
- | 0.0649 | 3.0 | 150 | 0.1621 | 0.0294 | 0.025 | 0.0270 | 0.9534 |
61
- | 0.0192 | 4.0 | 200 | 0.1812 | 0.1905 | 0.2 | 0.1951 | 0.9548 |
62
- | 0.0228 | 5.0 | 250 | 0.1621 | 0.3556 | 0.4 | 0.3765 | 0.9660 |
63
- | 0.0272 | 6.0 | 300 | 0.2737 | 0.5 | 0.15 | 0.2308 | 0.9601 |
64
- | 0.0013 | 7.0 | 350 | 0.1610 | 0.5854 | 0.6 | 0.5926 | 0.9734 |
65
- | 0.0024 | 8.0 | 400 | 0.2034 | 0.5 | 0.4 | 0.4444 | 0.9653 |
66
- | 0.001 | 9.0 | 450 | 0.1780 | 0.5385 | 0.525 | 0.5316 | 0.9694 |
67
- | 0.0022 | 10.0 | 500 | 0.1907 | 0.6389 | 0.575 | 0.6053 | 0.9703 |
68
- | 0.0009 | 11.0 | 550 | 0.1783 | 0.5682 | 0.625 | 0.5952 | 0.9727 |
69
- | 0.001 | 12.0 | 600 | 0.1960 | 0.6098 | 0.625 | 0.6173 | 0.9710 |
70
- | 0.0004 | 13.0 | 650 | 0.1881 | 0.6098 | 0.625 | 0.6173 | 0.9714 |
71
- | 0.0015 | 14.0 | 700 | 0.1920 | 0.5714 | 0.6 | 0.5854 | 0.9698 |
72
- | 0.0022 | 15.0 | 750 | 0.1892 | 0.625 | 0.625 | 0.625 | 0.9703 |
73
 
74
 
75
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.1100
24
+ - Precision: 0.4783
25
+ - Recall: 0.7857
26
+ - F1: 0.5946
27
+ - Accuracy: 0.9853
28
 
29
  ## Model description
30
 
 
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
+ | 0.056 | 1.0 | 50 | 0.1647 | 0.2593 | 0.175 | 0.2090 | 0.9608 |
59
+ | 0.0154 | 2.0 | 100 | 0.2252 | 0.3846 | 0.25 | 0.3030 | 0.9629 |
60
+ | 0.0078 | 3.0 | 150 | 0.2033 | 0.5366 | 0.55 | 0.5432 | 0.9669 |
61
+ | 0.0032 | 4.0 | 200 | 0.2098 | 0.5385 | 0.525 | 0.5316 | 0.9673 |
62
+ | 0.0022 | 5.0 | 250 | 0.2502 | 0.4167 | 0.375 | 0.3947 | 0.9651 |
63
+ | 0.0025 | 6.0 | 300 | 0.2565 | 0.4516 | 0.35 | 0.3944 | 0.9655 |
64
+ | 0.0039 | 7.0 | 350 | 0.2308 | 0.3684 | 0.35 | 0.3590 | 0.9667 |
65
+ | 0.0029 | 8.0 | 400 | 0.2048 | 0.4091 | 0.45 | 0.4286 | 0.9723 |
66
+ | 0.004 | 9.0 | 450 | 0.1996 | 0.6047 | 0.65 | 0.6265 | 0.9725 |
67
+ | 0.0012 | 10.0 | 500 | 0.3041 | 0.4483 | 0.325 | 0.3768 | 0.9635 |
68
+ | 0.0014 | 11.0 | 550 | 0.2086 | 0.6222 | 0.7 | 0.6588 | 0.9709 |
69
+ | 0.0003 | 12.0 | 600 | 0.2162 | 0.5682 | 0.625 | 0.5952 | 0.9705 |
70
+ | 0.0003 | 13.0 | 650 | 0.2180 | 0.5952 | 0.625 | 0.6098 | 0.9705 |
71
+ | 0.0003 | 14.0 | 700 | 0.2186 | 0.5814 | 0.625 | 0.6024 | 0.9707 |
72
+ | 0.0012 | 15.0 | 750 | 0.2196 | 0.5814 | 0.625 | 0.6024 | 0.9709 |
73
 
74
 
75
  ### Framework versions
config.json CHANGED
@@ -13,13 +13,17 @@
13
  "id2label": {
14
  "0": "O",
15
  "1": "B-HL",
16
- "2": "I-HL"
 
 
17
  },
18
  "initializer_range": 0.02,
19
  "intermediate_size": 3072,
20
  "label2id": {
21
  "B-HL": 1,
 
22
  "I-HL": 2,
 
23
  "O": 0
24
  },
25
  "layer_norm_eps": 1e-05,
 
13
  "id2label": {
14
  "0": "O",
15
  "1": "B-HL",
16
+ "2": "I-HL",
17
+ "3": "B-SHL",
18
+ "4": "I-SHL"
19
  },
20
  "initializer_range": 0.02,
21
  "intermediate_size": 3072,
22
  "label2id": {
23
  "B-HL": 1,
24
+ "B-SHL": 3,
25
  "I-HL": 2,
26
+ "I-SHL": 4,
27
  "O": 0
28
  },
29
  "layer_norm_eps": 1e-05,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:428e30b76f740b942a6b4a4a2ca5775dc8bc2508ff8ce480f749145f4a52e665
3
- size 1109845500
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96feb1de550e5430f5f041ad986171de2ecfb6f23939f9e8b16e2ca9ee54a987
3
+ size 1109851652
runs/Jul08_09-37-51_710793e53bac/events.out.tfevents.1720431494.710793e53bac.504.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be122e233ee80b3824390f3d71cd3b78d393ff4b450dd1634e14c67597c0efd4
3
+ size 20096
runs/Jul08_09-38-53_710793e53bac/events.out.tfevents.1720431539.710793e53bac.504.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02201c6bfa020a10f6765211065e5f7dd0583c4a0975a3f128f67b8ea87cebad
3
+ size 20133
runs/Jul08_09-38-53_710793e53bac/events.out.tfevents.1720431589.710793e53bac.504.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:249fcf82a14c420d97a6ecf17248bf0ad42c444803ad39275ac86facf6537d50
3
+ size 1014
runs/Jul08_09-41-51_710793e53bac/events.out.tfevents.1720431714.710793e53bac.504.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d89c9afdd1a30df69d5f9c1dbee02050fad2c924064d4ca628441d5e0231810a
3
+ size 17160
runs/Jul08_09-53-32_710793e53bac/events.out.tfevents.1720432418.710793e53bac.504.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cd6ff27585d8daabfe169b97c5653da9a3b1b1e303c35493e52804e93147b89
3
+ size 6279
runs/Jul08_09-54-09_710793e53bac/events.out.tfevents.1720432451.710793e53bac.504.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ada9f7b3fe3a5200eb4170a9df4f1ecd40185357fe94b3e24de805bd56f9111c
3
+ size 15718
runs/Jul08_09-54-09_710793e53bac/events.out.tfevents.1720432698.710793e53bac.504.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecfcbc97d1c8bbb4416ceccb5ce2467f57ad1c73033d9d759c215a52c0354a5a
3
+ size 1032
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06b00a6e48dadb52778009df93f1c87ce18da16d1b353bb4926e7423a4e2c610
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58eacd704c4d900c6ea19c6d2e93fb04fedb2597f1bb06b08d747e509ff22d81
3
  size 5176