Hugging Face's logo

ewfian
/
xlm-roberta-ner-ja

Token Classification
Transformers
Safetensors
Japanese
xlm-roberta
ner
Inference Endpoints
Model card Files Community
ewfian commited on
Commit
5e61774
•
1 Parent(s): 3498d9a

End of training

Browse files
Files changed (26) hide show
  1. .gitattributes +1 -0
  2. README.md +65 -0
  3. config.json +44 -0
  4. model.safetensors +3 -0
  5. runs/Dec02_19-06-14_featurize/events.out.tfevents.1701515199.featurize.19718.0 +3 -0
  6. runs/Dec02_19-11-44_featurize/events.out.tfevents.1701515516.featurize.19718.1 +3 -0
  7. runs/Dec02_19-13-16_featurize/events.out.tfevents.1701515600.featurize.19718.2 +3 -0
  8. runs/Dec02_19-24-45_featurize/events.out.tfevents.1701516297.featurize.19718.3 +3 -0
  9. runs/Dec02_19-30-18_featurize/events.out.tfevents.1701516633.featurize.20497.0 +3 -0
  10. runs/Nov24_13-56-40_featurize/events.out.tfevents.1700805428.featurize.20028.0 +3 -0
  11. runs/Nov24_15-02-30_featurize/events.out.tfevents.1700809404.featurize.19696.0 +3 -0
  12. runs/Nov24_15-09-05_featurize/events.out.tfevents.1700809770.featurize.19818.0 +3 -0
  13. runs/Nov24_15-11-25_featurize/events.out.tfevents.1700809888.featurize.19696.1 +3 -0
  14. runs/Nov25_10-34-03_featurize/events.out.tfevents.1700879663.featurize.19674.0 +3 -0
  15. runs/Nov25_10-37-51_featurize/events.out.tfevents.1700879883.featurize.19850.0 +3 -0
  16. runs/Nov25_10-41-18_featurize/events.out.tfevents.1700880101.featurize.20030.0 +3 -0
  17. runs/Nov25_10-46-22_featurize/events.out.tfevents.1700880401.featurize.20189.0 +3 -0
  18. runs/Nov25_10-52-09_featurize/events.out.tfevents.1700880770.featurize.20283.0 +3 -0
  19. runs/Nov25_10-54-10_featurize/events.out.tfevents.1700880860.featurize.20365.0 +3 -0
  20. runs/Nov25_11-04-02_featurize/events.out.tfevents.1700881460.featurize.20791.0 +3 -0
  21. runs/Nov25_11-04-02_featurize/events.out.tfevents.1700881750.featurize.20791.1 +3 -0
  22. runs/Nov25_12-26-13_featurize/events.out.tfevents.1700886383.featurize.23522.0 +3 -0
  23. special_tokens_map.json +15 -0
  24. tokenizer.json +3 -0
  25. tokenizer_config.json +54 -0
  26. training_args.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: xlm-roberta-base
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - f1
8
+ model-index:
9
+ - name: xlm-roberta-ner-ja
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # xlm-roberta-ner-ja
17
+
18
+ This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.1301
21
+ - F1: 0.8804
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 5e-05
41
+ - train_batch_size: 12
42
+ - eval_batch_size: 12
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 5
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | F1 |
52
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
53
+ | No log | 1.0 | 1451 | 0.1113 | 0.8286 |
54
+ | No log | 2.0 | 2902 | 0.0990 | 0.8487 |
55
+ | No log | 3.0 | 4353 | 0.1079 | 0.8611 |
56
+ | No log | 4.0 | 5804 | 0.1120 | 0.8738 |
57
+ | No log | 5.0 | 7255 | 0.1301 | 0.8804 |
58
+
59
+
60
+ ### Framework versions
61
+
62
+ - Transformers 4.35.2
63
+ - Pytorch 2.0.1+cu118
64
+ - Datasets 2.15.0
65
+ - Tokenizers 0.15.0
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-base",
3
+ "architectures": [
4
+ "RobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "O",
15
+ "1": "ORGANIZATION",
16
+ "2": "LOCATION",
17
+ "3": "DATE",
18
+ "4": "MONEY",
19
+ "5": "PERCENT"
20
+ },
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 3072,
23
+ "label2id": {
24
+ "DATE": 3,
25
+ "LOCATION": 2,
26
+ "MONEY": 4,
27
+ "O": 0,
28
+ "ORGANIZATION": 1,
29
+ "PERCENT": 5
30
+ },
31
+ "layer_norm_eps": 1e-05,
32
+ "max_position_embeddings": 514,
33
+ "model_type": "xlm-roberta",
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 12,
36
+ "output_past": true,
37
+ "pad_token_id": 1,
38
+ "position_embedding_type": "absolute",
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.35.2",
41
+ "type_vocab_size": 1,
42
+ "use_cache": true,
43
+ "vocab_size": 250002
44
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8313b5d237cfa0708fb94d6ae482dee8fa3c0e1e2fb4f65a0155c7f21e451947
3
+ size 1109854728
runs/Dec02_19-06-14_featurize/events.out.tfevents.1701515199.featurize.19718.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8a65d182ac7452c84d01a6a3a38c54ddae7ff73d3ac64becbfe35699370adcf
3
+ size 8924
runs/Dec02_19-11-44_featurize/events.out.tfevents.1701515516.featurize.19718.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d13603ed76a8fee9af2933643b8911105568ceb9233d0217c850f6f3a146534b
3
+ size 4505
runs/Dec02_19-13-16_featurize/events.out.tfevents.1701515600.featurize.19718.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34aee58460d4c05e06b158e551a5a1ccf8081f2e748ac98983021b994147d148
3
+ size 5176
runs/Dec02_19-24-45_featurize/events.out.tfevents.1701516297.featurize.19718.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2eb0d3c728a85a9c88ab89099d54f71ac48d1db78b604bf120d6dd458cdc8f43
3
+ size 88
runs/Dec02_19-30-18_featurize/events.out.tfevents.1701516633.featurize.20497.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4aafb5545a513bf58fcc6c2dc2a184e2ab8c6c048c85153a268d09567ff47d52
3
+ size 6445
runs/Nov24_13-56-40_featurize/events.out.tfevents.1700805428.featurize.20028.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31cc5d170ee53f1acbf8a666771464628fbc0d9eff89454bf0a12ed479ec42f7
3
+ size 5232
runs/Nov24_15-02-30_featurize/events.out.tfevents.1700809404.featurize.19696.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34fd16a3e2663e0bf3e14c1c6f87b90d962acfcbe0ffac63a3eab8406ece3b43
3
+ size 5548
runs/Nov24_15-09-05_featurize/events.out.tfevents.1700809770.featurize.19818.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd06344e90b289e3546fa28d6681f024d3f4b6b550609ded7ab4a1986c39b562
3
+ size 5232
runs/Nov24_15-11-25_featurize/events.out.tfevents.1700809888.featurize.19696.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8df0ad7784f3c5e0ba031f0eff3964be56e85f843512a7f9c89e41d0335a776e
3
+ size 5547
runs/Nov25_10-34-03_featurize/events.out.tfevents.1700879663.featurize.19674.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8017bbdc64c2f04407faf08a6c8c6e92fa4f3902a9abf70b2951aa3f18e7e8c6
3
+ size 5548
runs/Nov25_10-37-51_featurize/events.out.tfevents.1700879883.featurize.19850.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19ecec5092765d3085acbf532342c2e466b547c37c97957f7b51544d7291a45a
3
+ size 5548
runs/Nov25_10-41-18_featurize/events.out.tfevents.1700880101.featurize.20030.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20ba7377067193c2aa7f89d2836a9f67d1dff5eafc45218bf8b1bbe2cde27f47
3
+ size 6816
runs/Nov25_10-46-22_featurize/events.out.tfevents.1700880401.featurize.20189.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e20a253fcf784be885836f7b487168f7fb96fcf03862215699befa675e905efe
3
+ size 6500
runs/Nov25_10-52-09_featurize/events.out.tfevents.1700880770.featurize.20283.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad165a095f4d06d1956d5a5f53405b16a4f18aac88dbe02d3483790a33a39b65
3
+ size 4877
runs/Nov25_10-54-10_featurize/events.out.tfevents.1700880860.featurize.20365.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38128cb9b426e5bbcdad149940ea13da19af22cefe5f50dc34df71cf9a576a8a
3
+ size 6816
runs/Nov25_11-04-02_featurize/events.out.tfevents.1700881460.featurize.20791.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e0d0fda3edcf55bc68f3cc1d4d1aa28e887c72997e7b0106c8706569a1f7e1a
3
+ size 9666
runs/Nov25_11-04-02_featurize/events.out.tfevents.1700881750.featurize.20791.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e5b169edfb3ff21595dacd4432485558b9488ea5a0b27d506f9b14e5ece281f
3
+ size 17169
runs/Nov25_12-26-13_featurize/events.out.tfevents.1700886383.featurize.23522.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1272c2590ff92e4093e57ad615ff986b9d612fed69eb2c27902920389de3e729
3
+ size 7275
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a4661b2cb6b8a1007906509fe18cbfbc03062a086102bf7b80cfedb80f16c37
3
+ size 17082854
tokenizer_config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "model_max_length": 512,
50
+ "pad_token": "<pad>",
51
+ "sep_token": "</s>",
52
+ "tokenizer_class": "XLMRobertaTokenizer",
53
+ "unk_token": "<unk>"
54
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d32ea33aaa299dd2bcec0846092ce4c61082c723f1a3bd8d84fa491bd5e98ea
3
+ size 4091