Initial Commit
Browse files- README.md +32 -60
- config.json +14 -21
- eval_result_ner.json +1 -1
- model.safetensors +2 -2
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,14 +1,14 @@
|
|
1 |
---
|
2 |
-
base_model: haryoaw/scenario-TCR-NER_data-univner_half
|
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-kd-po-ner-full_data-univner_full66
|
14 |
results: []
|
@@ -19,13 +19,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
19 |
|
20 |
# scenario-kd-po-ner-full_data-univner_full66
|
21 |
|
22 |
-
This model is a fine-tuned version of [haryoaw/scenario-TCR-NER_data-
|
23 |
It achieves the following results on the evaluation set:
|
24 |
-
- Loss: 0.
|
25 |
-
- Precision: 0.
|
26 |
-
- Recall: 0.
|
27 |
-
- F1: 0.
|
28 |
-
- Accuracy: 0.
|
29 |
|
30 |
## Model description
|
31 |
|
@@ -56,57 +56,29 @@ The following hyperparameters were used during training:
|
|
56 |
|
57 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
58 |
|:-------------:|:-------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
59 |
-
|
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.
|
65 |
-
| 0.
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
| 0.
|
69 |
-
| 0.
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.
|
77 |
-
| 0.
|
78 |
-
| 0.
|
79 |
-
| 0.
|
80 |
-
| 0.
|
81 |
-
| 0.
|
82 |
-
| 0.1079 | 13.9860 | 12000 | 0.3579 | 0.7888 | 0.7696 | 0.7791 | 0.9772 |
|
83 |
-
| 0.1049 | 14.5688 | 12500 | 0.3515 | 0.7756 | 0.7875 | 0.7815 | 0.9775 |
|
84 |
-
| 0.1025 | 15.1515 | 13000 | 0.3537 | 0.7922 | 0.7755 | 0.7838 | 0.9777 |
|
85 |
-
| 0.1025 | 15.7343 | 13500 | 0.3633 | 0.7988 | 0.7593 | 0.7786 | 0.9769 |
|
86 |
-
| 0.1013 | 16.3170 | 14000 | 0.3556 | 0.7995 | 0.7556 | 0.7769 | 0.9771 |
|
87 |
-
| 0.099 | 16.8998 | 14500 | 0.3611 | 0.7883 | 0.7638 | 0.7758 | 0.9770 |
|
88 |
-
| 0.0979 | 17.4825 | 15000 | 0.3492 | 0.8138 | 0.7513 | 0.7813 | 0.9775 |
|
89 |
-
| 0.0968 | 18.0653 | 15500 | 0.3440 | 0.7963 | 0.7706 | 0.7833 | 0.9778 |
|
90 |
-
| 0.0943 | 18.6480 | 16000 | 0.3488 | 0.7949 | 0.7752 | 0.7850 | 0.9777 |
|
91 |
-
| 0.0951 | 19.2308 | 16500 | 0.3452 | 0.7943 | 0.7709 | 0.7824 | 0.9779 |
|
92 |
-
| 0.0923 | 19.8135 | 17000 | 0.3336 | 0.7879 | 0.7793 | 0.7835 | 0.9782 |
|
93 |
-
| 0.0935 | 20.3963 | 17500 | 0.3401 | 0.8052 | 0.7614 | 0.7826 | 0.9777 |
|
94 |
-
| 0.0918 | 20.9790 | 18000 | 0.3368 | 0.7963 | 0.7794 | 0.7878 | 0.9781 |
|
95 |
-
| 0.0912 | 21.5618 | 18500 | 0.3391 | 0.8037 | 0.7713 | 0.7872 | 0.9778 |
|
96 |
-
| 0.09 | 22.1445 | 19000 | 0.3328 | 0.8001 | 0.7722 | 0.7859 | 0.9780 |
|
97 |
-
| 0.0892 | 22.7273 | 19500 | 0.3396 | 0.8075 | 0.7645 | 0.7854 | 0.9778 |
|
98 |
-
| 0.0885 | 23.3100 | 20000 | 0.3352 | 0.8024 | 0.7754 | 0.7887 | 0.9782 |
|
99 |
-
| 0.088 | 23.8928 | 20500 | 0.3298 | 0.8089 | 0.7775 | 0.7929 | 0.9786 |
|
100 |
-
| 0.0874 | 24.4755 | 21000 | 0.3278 | 0.7972 | 0.7756 | 0.7863 | 0.9782 |
|
101 |
-
| 0.087 | 25.0583 | 21500 | 0.3305 | 0.8063 | 0.7697 | 0.7876 | 0.9782 |
|
102 |
-
| 0.0857 | 25.6410 | 22000 | 0.3316 | 0.8093 | 0.7666 | 0.7873 | 0.9781 |
|
103 |
-
| 0.0862 | 26.2238 | 22500 | 0.3305 | 0.8011 | 0.7699 | 0.7852 | 0.9778 |
|
104 |
-
| 0.0858 | 26.8065 | 23000 | 0.3305 | 0.8062 | 0.7700 | 0.7877 | 0.9781 |
|
105 |
-
| 0.0857 | 27.3893 | 23500 | 0.3291 | 0.7981 | 0.7720 | 0.7848 | 0.9780 |
|
106 |
-
| 0.0847 | 27.9720 | 24000 | 0.3264 | 0.8108 | 0.7700 | 0.7899 | 0.9783 |
|
107 |
-
| 0.0846 | 28.5548 | 24500 | 0.3270 | 0.8038 | 0.7673 | 0.7851 | 0.9781 |
|
108 |
-
| 0.0848 | 29.1375 | 25000 | 0.3272 | 0.8078 | 0.7738 | 0.7904 | 0.9784 |
|
109 |
-
| 0.084 | 29.7203 | 25500 | 0.3242 | 0.8056 | 0.7751 | 0.7901 | 0.9783 |
|
110 |
|
111 |
|
112 |
### 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-kd-po-ner-full_data-univner_full66
|
14 |
results: []
|
|
|
19 |
|
20 |
# scenario-kd-po-ner-full_data-univner_full66
|
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: 0.5267
|
25 |
+
- Precision: 0.7744
|
26 |
+
- Recall: 0.7391
|
27 |
+
- F1: 0.7564
|
28 |
+
- Accuracy: 0.9807
|
29 |
|
30 |
## Model description
|
31 |
|
|
|
56 |
|
57 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
58 |
|:-------------:|:-------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
59 |
+
| 0.8089 | 1.2755 | 500 | 0.7185 | 0.7338 | 0.6791 | 0.7054 | 0.9767 |
|
60 |
+
| 0.4626 | 2.5510 | 1000 | 0.6447 | 0.7127 | 0.7319 | 0.7222 | 0.9787 |
|
61 |
+
| 0.3791 | 3.8265 | 1500 | 0.5975 | 0.7349 | 0.7288 | 0.7318 | 0.9794 |
|
62 |
+
| 0.3262 | 5.1020 | 2000 | 0.5889 | 0.7447 | 0.7277 | 0.7361 | 0.9797 |
|
63 |
+
| 0.2868 | 6.3776 | 2500 | 0.5714 | 0.7427 | 0.7381 | 0.7404 | 0.9799 |
|
64 |
+
| 0.2587 | 7.6531 | 3000 | 0.5688 | 0.7703 | 0.7257 | 0.7473 | 0.9807 |
|
65 |
+
| 0.2389 | 8.9286 | 3500 | 0.5610 | 0.7338 | 0.7246 | 0.7292 | 0.9791 |
|
66 |
+
| 0.2211 | 10.2041 | 4000 | 0.5571 | 0.7719 | 0.7495 | 0.7605 | 0.9800 |
|
67 |
+
| 0.2022 | 11.4796 | 4500 | 0.5692 | 0.776 | 0.7029 | 0.7376 | 0.9799 |
|
68 |
+
| 0.1903 | 12.7551 | 5000 | 0.5554 | 0.7711 | 0.7360 | 0.7532 | 0.9804 |
|
69 |
+
| 0.179 | 14.0306 | 5500 | 0.5411 | 0.7574 | 0.7371 | 0.7471 | 0.9803 |
|
70 |
+
| 0.1688 | 15.3061 | 6000 | 0.5353 | 0.7602 | 0.7516 | 0.7559 | 0.9804 |
|
71 |
+
| 0.1608 | 16.5816 | 6500 | 0.5383 | 0.7748 | 0.7267 | 0.75 | 0.9802 |
|
72 |
+
| 0.1552 | 17.8571 | 7000 | 0.5223 | 0.7716 | 0.7381 | 0.7545 | 0.9800 |
|
73 |
+
| 0.1489 | 19.1327 | 7500 | 0.5300 | 0.7721 | 0.7329 | 0.7520 | 0.9801 |
|
74 |
+
| 0.1439 | 20.4082 | 8000 | 0.5321 | 0.7634 | 0.7246 | 0.7435 | 0.9797 |
|
75 |
+
| 0.1391 | 21.6837 | 8500 | 0.5204 | 0.7798 | 0.7443 | 0.7617 | 0.9805 |
|
76 |
+
| 0.1351 | 22.9592 | 9000 | 0.5251 | 0.7489 | 0.7350 | 0.7419 | 0.9800 |
|
77 |
+
| 0.131 | 24.2347 | 9500 | 0.5164 | 0.7664 | 0.7505 | 0.7584 | 0.9808 |
|
78 |
+
| 0.1291 | 25.5102 | 10000 | 0.5216 | 0.7614 | 0.7236 | 0.7420 | 0.9798 |
|
79 |
+
| 0.1276 | 26.7857 | 10500 | 0.5257 | 0.7739 | 0.7371 | 0.7550 | 0.9804 |
|
80 |
+
| 0.1251 | 28.0612 | 11000 | 0.5156 | 0.7692 | 0.7453 | 0.7571 | 0.9808 |
|
81 |
+
| 0.1241 | 29.3367 | 11500 | 0.5267 | 0.7744 | 0.7391 | 0.7564 | 0.9807 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
82 |
|
83 |
|
84 |
### Framework versions
|
config.json
CHANGED
@@ -1,9 +1,12 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "haryoaw/scenario-TCR-NER_data-
|
3 |
"architectures": [
|
4 |
-
"
|
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-
|
31 |
-
"max_position_embeddings":
|
32 |
-
"
|
33 |
-
"model_type": "deberta-v2",
|
34 |
-
"norm_rel_ebd": "layer_norm",
|
35 |
"num_attention_heads": 12,
|
36 |
"num_hidden_layers": 6,
|
37 |
-
"
|
38 |
-
"
|
39 |
-
"
|
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": "4.44.2",
|
51 |
-
"type_vocab_size":
|
52 |
-
"
|
|
|
53 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "haryoaw/scenario-TCR-NER_data-univner_en",
|
3 |
"architectures": [
|
4 |
+
"XLMRobertaForTokenClassificationKD"
|
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": 6,
|
38 |
+
"output_past": true,
|
39 |
+
"pad_token_id": 1,
|
40 |
+
"position_embedding_type": "absolute",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
41 |
"torch_dtype": "float32",
|
42 |
"transformers_version": "4.44.2",
|
43 |
+
"type_vocab_size": 1,
|
44 |
+
"use_cache": true,
|
45 |
+
"vocab_size": 250002
|
46 |
}
|
eval_result_ner.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"ceb_gja": {"precision": 0.
|
|
|
1 |
+
{"ceb_gja": {"precision": 0.44594594594594594, "recall": 0.673469387755102, "f1": 0.5365853658536585, "accuracy": 0.9482625482625483}, "en_pud": {"precision": 0.7542120911793855, "recall": 0.707906976744186, "f1": 0.7303262955854126, "accuracy": 0.9746883264072534}, "de_pud": {"precision": 0.7038934426229508, "recall": 0.6612127045235804, "f1": 0.6818858560794044, "accuracy": 0.9671839107402372}, "pt_pud": {"precision": 0.780564263322884, "recall": 0.6797088262056415, "f1": 0.7266536964980544, "accuracy": 0.9725295851668304}, "ru_pud": {"precision": 0.6280552603613178, "recall": 0.5704633204633205, "f1": 0.5978755690440061, "accuracy": 0.9580470162748643}, "sv_pud": {"precision": 0.7890204520990313, "recall": 0.7123420796890184, "f1": 0.7487231869254342, "accuracy": 0.9742084294401342}, "tl_trg": {"precision": 0.6666666666666666, "recall": 0.782608695652174, "f1": 0.72, "accuracy": 0.9822888283378747}, "tl_ugnayan": {"precision": 0.5, "recall": 0.5454545454545454, "f1": 0.5217391304347826, "accuracy": 0.9653600729261622}, "zh_gsd": {"precision": 0.42066420664206644, "recall": 0.14863102998696218, "f1": 0.21965317919075147, "accuracy": 0.9029304029304029}, "zh_gsdsimp": {"precision": 0.42543859649122806, "recall": 0.127129750982962, "f1": 0.19576185671039356, "accuracy": 0.9024309024309024}, "hr_set": {"precision": 0.7464788732394366, "recall": 0.6421952957947256, "f1": 0.6904214559386973, "accuracy": 0.9617889530090684}, "da_ddt": {"precision": 0.7569832402234636, "recall": 0.6062639821029083, "f1": 0.6732919254658385, "accuracy": 0.9753566796368353}, "en_ewt": {"precision": 0.7956131605184447, "recall": 0.7334558823529411, "f1": 0.763271162123386, "accuracy": 0.9762919870900905}, "pt_bosque": {"precision": 0.7508055853920516, "recall": 0.5753086419753086, "f1": 0.6514445479962722, "accuracy": 0.963048833502391}, "sr_set": {"precision": 0.7551867219917012, "recall": 0.6446280991735537, "f1": 0.6955414012738853, "accuracy": 0.9533315821731897}, "sk_snk": {"precision": 0.6048484848484849, "recall": 0.5453551912568306, "f1": 0.5735632183908046, "accuracy": 0.9422895728643216}, "sv_talbanken": {"precision": 0.7627906976744186, "recall": 0.8367346938775511, "f1": 0.7980535279805352, "accuracy": 0.9960249300682141}}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9fcb9e43b9848329b0b5557fbc0cafbbba2bee9cdd963395a8ffbbdcc1cf0e92
|
3 |
+
size 939737140
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5304
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe2ffe61ae04710e7eeeb683e47c5f31255795d636a839f63cee6fcbf92aef4b
|
3 |
size 5304
|