Hugging Face's logo

haryoaw
/
scenario-TCR-NER_data-univner_half

PyTorch
xlm-roberta
Generated from Trainer
Model card Files Community
haryoaw commited on
Commit
a39ec7e
•
1 Parent(s): 4870170

Initial Commit

Browse files
Files changed (5) hide show
  1. README.md +27 -30
  2. config.json +14 -21
  3. eval_result_ner.json +1 -1
  4. pytorch_model.bin +2 -2
  5. training_args.bin +1 -1
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  license: mit
3
- base_model: microsoft/mdeberta-v3-base
4
  tags:
5
  - generated_from_trainer
6
  metrics:
@@ -18,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  # scenario-TCR-NER_data-univner_half
20
 
21
- This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.1170
24
- - Precision: 0.8494
25
- - Recall: 0.8655
26
- - F1: 0.8574
27
- - Accuracy: 0.9842
28
 
29
  ## Model description
30
 
@@ -53,29 +53,26 @@ The following hyperparameters were used during training:
53
 
54
  ### Training results
55
 
56
- | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
- |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
- | 0.1168 | 0.58 | 500 | 0.0625 | 0.8182 | 0.8512 | 0.8344 | 0.9825 |
59
- | 0.0433 | 1.17 | 1000 | 0.0594 | 0.8396 | 0.8632 | 0.8512 | 0.9843 |
60
- | 0.0305 | 1.75 | 1500 | 0.0677 | 0.8296 | 0.8703 | 0.8495 | 0.9836 |
61
- | 0.0213 | 2.33 | 2000 | 0.0761 | 0.8253 | 0.8833 | 0.8533 | 0.9839 |
62
- | 0.0185 | 2.91 | 2500 | 0.0738 | 0.8600 | 0.8612 | 0.8606 | 0.9850 |
63
- | 0.012 | 3.5 | 3000 | 0.0784 | 0.8374 | 0.8572 | 0.8471 | 0.9835 |
64
- | 0.0124 | 4.08 | 3500 | 0.0832 | 0.8363 | 0.8704 | 0.8530 | 0.9843 |
65
- | 0.0095 | 4.66 | 4000 | 0.0806 | 0.8423 | 0.8713 | 0.8565 | 0.9845 |
66
- | 0.008 | 5.24 | 4500 | 0.1049 | 0.8218 | 0.8625 | 0.8417 | 0.9823 |
67
- | 0.0071 | 5.83 | 5000 | 0.0879 | 0.8420 | 0.8632 | 0.8525 | 0.9842 |
68
- | 0.0068 | 6.41 | 5500 | 0.0918 | 0.8507 | 0.8733 | 0.8619 | 0.9846 |
69
- | 0.0058 | 6.99 | 6000 | 0.0951 | 0.8488 | 0.8667 | 0.8577 | 0.9845 |
70
- | 0.0047 | 7.58 | 6500 | 0.0991 | 0.8467 | 0.8651 | 0.8558 | 0.9842 |
71
- | 0.0047 | 8.16 | 7000 | 0.1025 | 0.8603 | 0.8573 | 0.8588 | 0.9845 |
72
- | 0.0043 | 8.74 | 7500 | 0.1020 | 0.8473 | 0.8678 | 0.8574 | 0.9845 |
73
- | 0.0031 | 9.32 | 8000 | 0.1085 | 0.8437 | 0.8582 | 0.8509 | 0.9842 |
74
- | 0.0038 | 9.91 | 8500 | 0.1082 | 0.8602 | 0.8440 | 0.8520 | 0.9839 |
75
- | 0.0024 | 10.49 | 9000 | 0.1163 | 0.8533 | 0.8544 | 0.8539 | 0.9838 |
76
- | 0.0038 | 11.07 | 9500 | 0.1139 | 0.8528 | 0.8567 | 0.8548 | 0.9843 |
77
- | 0.0024 | 11.66 | 10000 | 0.1130 | 0.8619 | 0.8476 | 0.8547 | 0.9841 |
78
- | 0.0024 | 12.24 | 10500 | 0.1170 | 0.8494 | 0.8655 | 0.8574 | 0.9842 |
79
 
80
 
81
  ### Framework versions
 
1
  ---
2
  license: mit
3
+ base_model: xlm-roberta-base
4
  tags:
5
  - generated_from_trainer
6
  metrics:
 
18
 
19
  # scenario-TCR-NER_data-univner_half
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: 0.1160
24
+ - Precision: 0.8555
25
+ - Recall: 0.8189
26
+ - F1: 0.8368
27
+ - Accuracy: 0.9828
28
 
29
  ## Model description
30
 
 
53
 
54
  ### Training results
55
 
56
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
+ | 0.1189 | 0.58 | 500 | 0.0623 | 0.8010 | 0.8531 | 0.8262 | 0.9822 |
59
+ | 0.0469 | 1.17 | 1000 | 0.0640 | 0.8246 | 0.8567 | 0.8404 | 0.9833 |
60
+ | 0.0348 | 1.75 | 1500 | 0.0668 | 0.8335 | 0.8550 | 0.8441 | 0.9834 |
61
+ | 0.0242 | 2.33 | 2000 | 0.0734 | 0.8202 | 0.8538 | 0.8367 | 0.9826 |
62
+ | 0.0215 | 2.91 | 2500 | 0.0717 | 0.8455 | 0.8598 | 0.8526 | 0.9843 |
63
+ | 0.0142 | 3.5 | 3000 | 0.0802 | 0.8383 | 0.8424 | 0.8404 | 0.9836 |
64
+ | 0.0144 | 4.08 | 3500 | 0.0836 | 0.8443 | 0.8554 | 0.8499 | 0.9843 |
65
+ | 0.0103 | 4.66 | 4000 | 0.0811 | 0.8479 | 0.8590 | 0.8534 | 0.9844 |
66
+ | 0.0087 | 5.24 | 4500 | 0.0887 | 0.8364 | 0.8628 | 0.8494 | 0.9840 |
67
+ | 0.0092 | 5.83 | 5000 | 0.0876 | 0.8367 | 0.8430 | 0.8399 | 0.9833 |
68
+ | 0.0076 | 6.41 | 5500 | 0.1004 | 0.8440 | 0.8495 | 0.8468 | 0.9841 |
69
+ | 0.007 | 6.99 | 6000 | 0.1080 | 0.8215 | 0.8518 | 0.8364 | 0.9830 |
70
+ | 0.0055 | 7.58 | 6500 | 0.0988 | 0.8454 | 0.8358 | 0.8406 | 0.9831 |
71
+ | 0.0055 | 8.16 | 7000 | 0.0950 | 0.8485 | 0.8461 | 0.8473 | 0.9839 |
72
+ | 0.0044 | 8.74 | 7500 | 0.1001 | 0.8456 | 0.8414 | 0.8435 | 0.9836 |
73
+ | 0.004 | 9.32 | 8000 | 0.1084 | 0.8340 | 0.8495 | 0.8417 | 0.9834 |
74
+ | 0.004 | 9.91 | 8500 | 0.1175 | 0.8351 | 0.8505 | 0.8427 | 0.9829 |
75
+ | 0.0033 | 10.49 | 9000 | 0.1160 | 0.8555 | 0.8189 | 0.8368 | 0.9828 |
 
 
 
76
 
77
 
78
  ### Framework versions
config.json CHANGED
@@ -1,9 +1,12 @@
1
  {
2
- "_name_or_path": "microsoft/mdeberta-v3-base",
3
  "architectures": [
4
- "DebertaV2ForTokenClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
 
 
 
7
  "hidden_act": "gelu",
8
  "hidden_dropout_prob": 0.1,
9
  "hidden_size": 768,
@@ -27,27 +30,17 @@
27
  "LABEL_5": 5,
28
  "LABEL_6": 6
29
  },
30
- "layer_norm_eps": 1e-07,
31
- "max_position_embeddings": 512,
32
- "max_relative_positions": -1,
33
- "model_type": "deberta-v2",
34
- "norm_rel_ebd": "layer_norm",
35
  "num_attention_heads": 12,
36
  "num_hidden_layers": 12,
37
- "pad_token_id": 0,
38
- "pooler_dropout": 0,
39
- "pooler_hidden_act": "gelu",
40
- "pooler_hidden_size": 768,
41
- "pos_att_type": [
42
- "p2c",
43
- "c2p"
44
- ],
45
- "position_biased_input": false,
46
- "position_buckets": 256,
47
- "relative_attention": true,
48
- "share_att_key": true,
49
  "torch_dtype": "float32",
50
  "transformers_version": "4.33.3",
51
- "type_vocab_size": 0,
52
- "vocab_size": 251000
 
53
  }
 
1
  {
2
+ "_name_or_path": "xlm-roberta-base",
3
  "architectures": [
4
+ "XLMRobertaForTokenClassification"
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,
 
30
  "LABEL_5": 5,
31
  "LABEL_6": 6
32
  },
33
+ "layer_norm_eps": 1e-05,
34
+ "max_position_embeddings": 514,
35
+ "model_type": "xlm-roberta",
 
 
36
  "num_attention_heads": 12,
37
  "num_hidden_layers": 12,
38
+ "output_past": true,
39
+ "pad_token_id": 1,
40
+ "position_embedding_type": "absolute",
 
 
 
 
 
 
 
 
 
41
  "torch_dtype": "float32",
42
  "transformers_version": "4.33.3",
43
+ "type_vocab_size": 1,
44
+ "use_cache": true,
45
+ "vocab_size": 250002
46
  }
eval_result_ner.json CHANGED
@@ -1 +1 @@
1
- {"zh_gsd": {"precision": 0.8458646616541353, "recall": 0.8800521512385919, "f1": 0.8626198083067093, "accuracy": 0.9806859806859807}, "zh_gsdsimp": {"precision": 0.8640406607369758, "recall": 0.891218872870249, "f1": 0.8774193548387097, "accuracy": 0.9823509823509824}, "hr_set": {"precision": 0.9101508916323731, "recall": 0.9458303635067712, "f1": 0.9276476756378887, "accuracy": 0.990560593569662}, "da_ddt": {"precision": 0.8681818181818182, "recall": 0.854586129753915, "f1": 0.8613303269447576, "accuracy": 0.9895240945824604}, "en_ewt": {"precision": 0.836555360281195, "recall": 0.875, "f1": 0.8553459119496856, "accuracy": 0.9850579750567797}, "pt_bosque": {"precision": 0.8723404255319149, "recall": 0.8436213991769548, "f1": 0.8577405857740587, "accuracy": 0.9858716128097377}, "sr_set": {"precision": 0.9494117647058824, "recall": 0.9527744982290437, "f1": 0.9510901591043017, "accuracy": 0.990631293231766}, "sk_snk": {"precision": 0.8242229367631297, "recall": 0.8404371584699454, "f1": 0.8322510822510822, "accuracy": 0.9757380653266332}, "sv_talbanken": {"precision": 0.7763713080168776, "recall": 0.9387755102040817, "f1": 0.8498845265588915, "accuracy": 0.9969082789419443}}
 
1
+ {"zh_gsd": {"precision": 0.8505154639175257, "recall": 0.8604954367666232, "f1": 0.8554763447828905, "accuracy": 0.9792707292707292}, "zh_gsdsimp": {"precision": 0.8438709677419355, "recall": 0.8571428571428571, "f1": 0.8504551365409622, "accuracy": 0.9788544788544788}, "hr_set": {"precision": 0.9336158192090396, "recall": 0.9422665716322167, "f1": 0.9379212486697411, "accuracy": 0.9921681780708986}, "da_ddt": {"precision": 0.8604651162790697, "recall": 0.8277404921700223, "f1": 0.8437856328392246, "accuracy": 0.9873291429711664}, "en_ewt": {"precision": 0.7928321678321678, "recall": 0.8336397058823529, "f1": 0.8127240143369175, "accuracy": 0.9813125074710125}, "pt_bosque": {"precision": 0.8833189282627485, "recall": 0.8411522633744856, "f1": 0.8617200674536256, "accuracy": 0.9859802927112012}, "sr_set": {"precision": 0.9481132075471698, "recall": 0.9492325855962219, "f1": 0.9486725663716813, "accuracy": 0.9908064092461255}, "sk_snk": {"precision": 0.7928802588996764, "recall": 0.8032786885245902, "f1": 0.7980456026058632, "accuracy": 0.9713410804020101}, "sv_talbanken": {"precision": 0.8457943925233645, "recall": 0.923469387755102, "f1": 0.8829268292682927, "accuracy": 0.9976444030033862}}
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b17284dbdc47a46c624b01a42698c89dde812636572a5924ce8bda92d62475f5
3
- size 1112965930
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d31bc77304f2506a4e74bd52e946c4d1e15f552689161cb025655e60157a12ac
3
+ size 1109902502
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2af879047a05ce26c181c49037265b598df6baec29f1ae74753378b1c252b119
3
  size 4536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2aaaf29ee04e5c9b3b9d85d1d55b1168a49f834a24e985655e81602d96dae98
3
  size 4536