haryoaw commited on
Commit
71e458c
1 Parent(s): ab1bb70

Initial Commit

Browse files
Files changed (5) hide show
  1. README.md +31 -31
  2. config.json +2 -2
  3. eval_result_ner.json +1 -1
  4. model.safetensors +2 -2
  5. training_args.bin +1 -1
README.md CHANGED
@@ -1,14 +1,14 @@
1
  ---
2
- base_model: haryoaw/scenario-TCR-NER_data-univner_en
3
  library_name: transformers
4
  license: mit
 
 
 
5
  metrics:
6
  - precision
7
  - recall
8
  - f1
9
  - accuracy
10
- tags:
11
- - generated_from_trainer
12
  model-index:
13
  - name: scenario-non-kd-po-ner-full-mdeberta_data-univner_en44
14
  results: []
@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
21
 
22
  This model is a fine-tuned version of [haryoaw/scenario-TCR-NER_data-univner_en](https://huggingface.co/haryoaw/scenario-TCR-NER_data-univner_en) on the None dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 0.1418
25
- - Precision: 0.8347
26
- - Recall: 0.8416
27
- - F1: 0.8381
28
- - Accuracy: 0.9853
29
 
30
  ## Model description
31
 
@@ -56,29 +56,29 @@ The following hyperparameters were used during training:
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
58
  |:-------------:|:-------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
59
- | 0.0023 | 1.2755 | 500 | 0.1132 | 0.8279 | 0.8364 | 0.8321 | 0.9857 |
60
- | 0.0022 | 2.5510 | 1000 | 0.1035 | 0.8234 | 0.8540 | 0.8384 | 0.9858 |
61
- | 0.0021 | 3.8265 | 1500 | 0.0987 | 0.8228 | 0.8509 | 0.8366 | 0.9851 |
62
- | 0.0013 | 5.1020 | 2000 | 0.1237 | 0.7955 | 0.8458 | 0.8199 | 0.9839 |
63
- | 0.0008 | 6.3776 | 2500 | 0.1278 | 0.8173 | 0.8292 | 0.8232 | 0.9845 |
64
- | 0.0007 | 7.6531 | 3000 | 0.1257 | 0.8257 | 0.8437 | 0.8346 | 0.9848 |
65
- | 0.0006 | 8.9286 | 3500 | 0.1257 | 0.8466 | 0.8282 | 0.8373 | 0.9855 |
66
- | 0.0011 | 10.2041 | 4000 | 0.1250 | 0.8141 | 0.8251 | 0.8195 | 0.9843 |
67
- | 0.0007 | 11.4796 | 4500 | 0.1240 | 0.8206 | 0.8240 | 0.8223 | 0.9840 |
68
- | 0.0004 | 12.7551 | 5000 | 0.1297 | 0.8192 | 0.8395 | 0.8292 | 0.9847 |
69
- | 0.0008 | 14.0306 | 5500 | 0.1342 | 0.8270 | 0.8116 | 0.8192 | 0.9844 |
70
- | 0.0004 | 15.3061 | 6000 | 0.1295 | 0.8147 | 0.8240 | 0.8194 | 0.9843 |
71
- | 0.0004 | 16.5816 | 6500 | 0.1374 | 0.8118 | 0.8437 | 0.8274 | 0.9839 |
72
- | 0.0003 | 17.8571 | 7000 | 0.1416 | 0.8092 | 0.8209 | 0.8150 | 0.9837 |
73
- | 0.0003 | 19.1327 | 7500 | 0.1264 | 0.8249 | 0.8489 | 0.8367 | 0.9852 |
74
- | 0.0002 | 20.4082 | 8000 | 0.1323 | 0.8262 | 0.8416 | 0.8338 | 0.9854 |
75
- | 0.0003 | 21.6837 | 8500 | 0.1341 | 0.8239 | 0.8427 | 0.8332 | 0.9854 |
76
- | 0.0001 | 22.9592 | 9000 | 0.1400 | 0.8251 | 0.8499 | 0.8373 | 0.9852 |
77
- | 0.0002 | 24.2347 | 9500 | 0.1342 | 0.8219 | 0.8406 | 0.8311 | 0.9849 |
78
- | 0.0002 | 25.5102 | 10000 | 0.1355 | 0.8352 | 0.8447 | 0.8399 | 0.9855 |
79
- | 0.0001 | 26.7857 | 10500 | 0.1454 | 0.8254 | 0.8416 | 0.8334 | 0.9846 |
80
- | 0.0001 | 28.0612 | 11000 | 0.1448 | 0.8254 | 0.8416 | 0.8334 | 0.9849 |
81
- | 0.0001 | 29.3367 | 11500 | 0.1418 | 0.8347 | 0.8416 | 0.8381 | 0.9853 |
82
 
83
 
84
  ### Framework versions
 
1
  ---
 
2
  library_name: transformers
3
  license: mit
4
+ base_model: haryoaw/scenario-TCR-NER_data-univner_en
5
+ tags:
6
+ - generated_from_trainer
7
  metrics:
8
  - precision
9
  - recall
10
  - f1
11
  - accuracy
 
 
12
  model-index:
13
  - name: scenario-non-kd-po-ner-full-mdeberta_data-univner_en44
14
  results: []
 
21
 
22
  This model is a fine-tuned version of [haryoaw/scenario-TCR-NER_data-univner_en](https://huggingface.co/haryoaw/scenario-TCR-NER_data-univner_en) on the None dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 0.1841
25
+ - Precision: 0.7385
26
+ - Recall: 0.7453
27
+ - F1: 0.7419
28
+ - Accuracy: 0.9788
29
 
30
  ## Model description
31
 
 
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
58
  |:-------------:|:-------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
59
+ | 0.1167 | 1.2755 | 500 | 0.1161 | 0.5076 | 0.6573 | 0.5728 | 0.9647 |
60
+ | 0.0436 | 2.5510 | 1000 | 0.0883 | 0.6536 | 0.7422 | 0.6951 | 0.9754 |
61
+ | 0.0227 | 3.8265 | 1500 | 0.1011 | 0.6709 | 0.7153 | 0.6924 | 0.9767 |
62
+ | 0.0129 | 5.1020 | 2000 | 0.1175 | 0.6537 | 0.7505 | 0.6988 | 0.9757 |
63
+ | 0.008 | 6.3776 | 2500 | 0.1207 | 0.7106 | 0.7143 | 0.7124 | 0.9774 |
64
+ | 0.006 | 7.6531 | 3000 | 0.1357 | 0.6951 | 0.7340 | 0.7140 | 0.9773 |
65
+ | 0.004 | 8.9286 | 3500 | 0.1415 | 0.7146 | 0.7153 | 0.7150 | 0.9778 |
66
+ | 0.0032 | 10.2041 | 4000 | 0.1439 | 0.7198 | 0.7391 | 0.7293 | 0.9784 |
67
+ | 0.0027 | 11.4796 | 4500 | 0.1432 | 0.7150 | 0.7609 | 0.7372 | 0.9780 |
68
+ | 0.0022 | 12.7551 | 5000 | 0.1500 | 0.7205 | 0.7578 | 0.7386 | 0.9788 |
69
+ | 0.0017 | 14.0306 | 5500 | 0.1416 | 0.7129 | 0.7453 | 0.7287 | 0.9781 |
70
+ | 0.0015 | 15.3061 | 6000 | 0.1543 | 0.7164 | 0.7402 | 0.7281 | 0.9780 |
71
+ | 0.0013 | 16.5816 | 6500 | 0.1558 | 0.6989 | 0.7640 | 0.7300 | 0.9779 |
72
+ | 0.0009 | 17.8571 | 7000 | 0.1592 | 0.7019 | 0.7433 | 0.7220 | 0.9778 |
73
+ | 0.0007 | 19.1327 | 7500 | 0.1642 | 0.7227 | 0.7391 | 0.7308 | 0.9785 |
74
+ | 0.0007 | 20.4082 | 8000 | 0.1614 | 0.7316 | 0.7422 | 0.7369 | 0.9791 |
75
+ | 0.0006 | 21.6837 | 8500 | 0.1739 | 0.7179 | 0.7402 | 0.7288 | 0.9781 |
76
+ | 0.0004 | 22.9592 | 9000 | 0.1742 | 0.7260 | 0.7350 | 0.7305 | 0.9783 |
77
+ | 0.0004 | 24.2347 | 9500 | 0.1701 | 0.7154 | 0.7547 | 0.7345 | 0.9781 |
78
+ | 0.0003 | 25.5102 | 10000 | 0.1795 | 0.7354 | 0.7422 | 0.7388 | 0.9790 |
79
+ | 0.0003 | 26.7857 | 10500 | 0.1825 | 0.7278 | 0.7391 | 0.7334 | 0.9785 |
80
+ | 0.0002 | 28.0612 | 11000 | 0.1839 | 0.7384 | 0.7391 | 0.7387 | 0.9786 |
81
+ | 0.0003 | 29.3367 | 11500 | 0.1841 | 0.7385 | 0.7453 | 0.7419 | 0.9788 |
82
 
83
 
84
  ### Framework versions
config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "_name_or_path": "haryoaw/scenario-TCR-NER_data-univner_en",
3
  "architectures": [
4
- "DebertaV2ForTokenClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
  "hidden_act": "gelu",
@@ -33,7 +33,7 @@
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",
 
1
  {
2
  "_name_or_path": "haryoaw/scenario-TCR-NER_data-univner_en",
3
  "architectures": [
4
+ "DebertaForTokenClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
  "hidden_act": "gelu",
 
33
  "model_type": "deberta-v2",
34
  "norm_rel_ebd": "layer_norm",
35
  "num_attention_heads": 12,
36
+ "num_hidden_layers": 6,
37
  "pad_token_id": 0,
38
  "pooler_dropout": 0,
39
  "pooler_hidden_act": "gelu",
eval_result_ner.json CHANGED
@@ -1 +1 @@
1
- {"ceb_gja": {"precision": 0.7818181818181819, "recall": 0.8775510204081632, "f1": 0.8269230769230769, "accuracy": 0.9868725868725868}, "en_pud": {"precision": 0.8199419167473379, "recall": 0.7879069767441861, "f1": 0.8036053130929791, "accuracy": 0.9821496033245183}, "de_pud": {"precision": 0.8028169014084507, "recall": 0.7680461982675649, "f1": 0.7850467289719626, "accuracy": 0.9771693779007079}, "pt_pud": {"precision": 0.8466019417475729, "recall": 0.7934485896269335, "f1": 0.8191639267261626, "accuracy": 0.9810313154184646}, "ru_pud": {"precision": 0.693437806072478, "recall": 0.6833976833976834, "f1": 0.6883811375789985, "accuracy": 0.9667269439421338}, "sv_pud": {"precision": 0.8518896833503575, "recall": 0.8104956268221575, "f1": 0.8306772908366535, "accuracy": 0.981862025581883}, "tl_trg": {"precision": 0.76, "recall": 0.8260869565217391, "f1": 0.7916666666666667, "accuracy": 0.9877384196185286}, "tl_ugnayan": {"precision": 0.6428571428571429, "recall": 0.8181818181818182, "f1": 0.7200000000000001, "accuracy": 0.9772105742935278}, "zh_gsd": {"precision": 0.6801152737752162, "recall": 0.6153846153846154, "f1": 0.646132785763176, "accuracy": 0.9503829503829504}, "zh_gsdsimp": {"precision": 0.6727272727272727, "recall": 0.6304062909567497, "f1": 0.6508795669824087, "accuracy": 0.9508824508824509}, "hr_set": {"precision": 0.8332028191072827, "recall": 0.7583749109052031, "f1": 0.7940298507462686, "accuracy": 0.9739076669414675}, "da_ddt": {"precision": 0.808, "recall": 0.6778523489932886, "f1": 0.7372262773722629, "accuracy": 0.9792477302204928}, "en_ewt": {"precision": 0.8561840843720039, "recall": 0.8207720588235294, "f1": 0.8381041764429845, "accuracy": 0.9825477148663186}, "pt_bosque": {"precision": 0.8219584569732937, "recall": 0.6839506172839506, "f1": 0.7466307277628033, "accuracy": 0.9729749311693957}, "sr_set": {"precision": 0.8600508905852418, "recall": 0.7981109799291618, "f1": 0.8279240661359463, "accuracy": 0.9718938796952982}, "sk_snk": {"precision": 0.7631578947368421, "recall": 0.6655737704918033, "f1": 0.7110332749562173, "accuracy": 0.9608982412060302}, "sv_talbanken": {"precision": 0.88, "recall": 0.8979591836734694, "f1": 0.888888888888889, "accuracy": 0.9976934779408156}}
 
1
+ {"ceb_gja": {"precision": 0.34285714285714286, "recall": 0.7346938775510204, "f1": 0.4675324675324676, "accuracy": 0.9289575289575289}, "en_pud": {"precision": 0.7065326633165829, "recall": 0.653953488372093, "f1": 0.6792270531400967, "accuracy": 0.9703437854174537}, "de_pud": {"precision": 0.6268320180383314, "recall": 0.5351299326275265, "f1": 0.5773624091381101, "accuracy": 0.9595424499554639}, "pt_pud": {"precision": 0.6356837606837606, "recall": 0.5414012738853503, "f1": 0.5847665847665847, "accuracy": 0.9609945742726534}, "ru_pud": {"precision": 0.5489989462592202, "recall": 0.502895752895753, "f1": 0.5249370277078086, "accuracy": 0.9506587445104624}, "sv_pud": {"precision": 0.741504854368932, "recall": 0.5937803692905733, "f1": 0.6594711279007014, "accuracy": 0.9670790522122038}, "tl_trg": {"precision": 0.2413793103448276, "recall": 0.6086956521739131, "f1": 0.345679012345679, "accuracy": 0.9237057220708447}, "tl_ugnayan": {"precision": 0.328125, "recall": 0.6363636363636364, "f1": 0.4329896907216495, "accuracy": 0.9434822242479489}, "zh_gsd": {"precision": 0.42328042328042326, "recall": 0.20860495436766624, "f1": 0.27947598253275113, "accuracy": 0.9079254079254079}, "zh_gsdsimp": {"precision": 0.41621621621621624, "recall": 0.2018348623853211, "f1": 0.27184466019417475, "accuracy": 0.9083416583416584}, "hr_set": {"precision": 0.6017191977077364, "recall": 0.44903777619387025, "f1": 0.5142857142857142, "accuracy": 0.9448062654575433}, "da_ddt": {"precision": 0.6997167138810199, "recall": 0.5525727069351231, "f1": 0.6175, "accuracy": 0.9705676943031029}, "en_ewt": {"precision": 0.7705078125, "recall": 0.7251838235294118, "f1": 0.7471590909090909, "accuracy": 0.9750567796947842}, "pt_bosque": {"precision": 0.6152197213290461, "recall": 0.47242798353909465, "f1": 0.5344506517690876, "accuracy": 0.9535212288074192}, "sr_set": {"precision": 0.6217105263157895, "recall": 0.4462809917355372, "f1": 0.5195876288659794, "accuracy": 0.933455914543385}, "sk_snk": {"precision": 0.5291777188328912, "recall": 0.4360655737704918, "f1": 0.4781306171360096, "accuracy": 0.9290201005025126}, "sv_talbanken": {"precision": 0.7253886010362695, "recall": 0.7142857142857143, "f1": 0.7197943444730078, "accuracy": 0.9945526819453305}}
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:68996c8a719eb31e8d40e71bb92fdb9f5aa74ce058394f744eed8b324fc5542c
3
- size 1112921036
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b8188a88d38bc92667c61ab3a6029c334bb4b1106486a6e07bbd67b4fc819ba
3
+ size 944366708
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ce5376320c9b99b88a04d339e47ddd7117ebae5fe7c787756a82b0cd6d94b449
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cda8b230747d7f9a2d3c87c991b6df8ee633fec5030d9cd1947a9abacd86ee90
3
  size 5304