Initial Commit
Browse files- README.md +61 -31
- config.json +13 -20
- 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-scr-ner-full_data-univner_full44
|
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_half](https://huggingface.co/haryoaw/scenario-TCR-NER_data-univner_half) on the None dataset.
|
23 |
It achieves the following results on the evaluation set:
|
24 |
-
- Loss:
|
25 |
-
- Precision: 0.
|
26 |
-
- Recall: 0.
|
27 |
-
- F1: 0.
|
28 |
-
- Accuracy: 0.
|
29 |
|
30 |
## Model description
|
31 |
|
@@ -54,29 +54,59 @@ The following hyperparameters were used during training:
|
|
54 |
|
55 |
### Training results
|
56 |
|
57 |
-
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1
|
58 |
-
|
59 |
-
|
|
60 |
-
|
|
61 |
-
|
|
62 |
-
|
|
63 |
-
|
|
64 |
-
|
|
65 |
-
|
|
66 |
-
|
|
67 |
-
|
|
68 |
-
|
|
69 |
-
|
|
70 |
-
|
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.
|
77 |
-
| 0.
|
78 |
-
| 0.
|
79 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
80 |
|
81 |
|
82 |
### Framework versions
|
|
|
1 |
---
|
|
|
2 |
library_name: transformers
|
3 |
license: mit
|
4 |
+
base_model: haryoaw/scenario-TCR-NER_data-univner_half
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
metrics:
|
8 |
- precision
|
9 |
- recall
|
10 |
- f1
|
11 |
- accuracy
|
|
|
|
|
12 |
model-index:
|
13 |
- name: scenario-kd-scr-ner-full_data-univner_full44
|
14 |
results: []
|
|
|
21 |
|
22 |
This model is a fine-tuned version of [haryoaw/scenario-TCR-NER_data-univner_half](https://huggingface.co/haryoaw/scenario-TCR-NER_data-univner_half) on the None dataset.
|
23 |
It achieves the following results on the evaluation set:
|
24 |
+
- Loss: 1.6199
|
25 |
+
- Precision: 0.4352
|
26 |
+
- Recall: 0.3701
|
27 |
+
- F1: 0.4000
|
28 |
+
- Accuracy: 0.9387
|
29 |
|
30 |
## Model description
|
31 |
|
|
|
54 |
|
55 |
### Training results
|
56 |
|
57 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
58 |
+
|:-------------:|:-------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
59 |
+
| 2.9268 | 0.5828 | 500 | 2.5728 | 0.4130 | 0.0082 | 0.0161 | 0.9245 |
|
60 |
+
| 2.2111 | 1.1655 | 1000 | 2.6038 | 0.2535 | 0.0757 | 0.1166 | 0.9230 |
|
61 |
+
| 1.9667 | 1.7483 | 1500 | 2.4899 | 0.2074 | 0.1753 | 0.1900 | 0.9168 |
|
62 |
+
| 1.7467 | 2.3310 | 2000 | 2.1434 | 0.3184 | 0.1717 | 0.2231 | 0.9291 |
|
63 |
+
| 1.6429 | 2.9138 | 2500 | 2.1913 | 0.2798 | 0.1997 | 0.2330 | 0.9274 |
|
64 |
+
| 1.4992 | 3.4965 | 3000 | 2.0144 | 0.2988 | 0.2192 | 0.2529 | 0.9291 |
|
65 |
+
| 1.3977 | 4.0793 | 3500 | 2.0470 | 0.3052 | 0.2575 | 0.2793 | 0.9284 |
|
66 |
+
| 1.2778 | 4.6620 | 4000 | 2.1220 | 0.3168 | 0.2727 | 0.2931 | 0.9248 |
|
67 |
+
| 1.2224 | 5.2448 | 4500 | 1.9196 | 0.3273 | 0.2679 | 0.2946 | 0.9303 |
|
68 |
+
| 1.1262 | 5.8275 | 5000 | 1.9602 | 0.3120 | 0.3111 | 0.3115 | 0.9280 |
|
69 |
+
| 1.0371 | 6.4103 | 5500 | 2.0035 | 0.3100 | 0.3189 | 0.3144 | 0.9238 |
|
70 |
+
| 1.0053 | 6.9930 | 6000 | 1.8674 | 0.3395 | 0.2821 | 0.3081 | 0.9303 |
|
71 |
+
| 0.9232 | 7.5758 | 6500 | 1.8771 | 0.3290 | 0.3262 | 0.3276 | 0.9303 |
|
72 |
+
| 0.872 | 8.1585 | 7000 | 1.8623 | 0.3228 | 0.3269 | 0.3249 | 0.9286 |
|
73 |
+
| 0.8387 | 8.7413 | 7500 | 1.8017 | 0.3676 | 0.3295 | 0.3475 | 0.9341 |
|
74 |
+
| 0.7799 | 9.3240 | 8000 | 1.9406 | 0.2966 | 0.3473 | 0.3200 | 0.9220 |
|
75 |
+
| 0.7627 | 9.9068 | 8500 | 1.8042 | 0.3618 | 0.3474 | 0.3545 | 0.9336 |
|
76 |
+
| 0.7129 | 10.4895 | 9000 | 1.7746 | 0.3609 | 0.3440 | 0.3522 | 0.9355 |
|
77 |
+
| 0.6964 | 11.0723 | 9500 | 1.7343 | 0.4023 | 0.3438 | 0.3708 | 0.9379 |
|
78 |
+
| 0.6547 | 11.6550 | 10000 | 1.7256 | 0.3996 | 0.3616 | 0.3796 | 0.9366 |
|
79 |
+
| 0.6363 | 12.2378 | 10500 | 1.7899 | 0.3701 | 0.3735 | 0.3718 | 0.9319 |
|
80 |
+
| 0.6183 | 12.8205 | 11000 | 1.8503 | 0.3564 | 0.3575 | 0.3570 | 0.9280 |
|
81 |
+
| 0.5881 | 13.4033 | 11500 | 1.7546 | 0.3679 | 0.3708 | 0.3693 | 0.9325 |
|
82 |
+
| 0.5822 | 13.9860 | 12000 | 1.6888 | 0.4090 | 0.3331 | 0.3672 | 0.9371 |
|
83 |
+
| 0.5475 | 14.5688 | 12500 | 1.6986 | 0.4197 | 0.3507 | 0.3821 | 0.9371 |
|
84 |
+
| 0.5396 | 15.1515 | 13000 | 1.7398 | 0.3979 | 0.3698 | 0.3833 | 0.9344 |
|
85 |
+
| 0.5248 | 15.7343 | 13500 | 1.7333 | 0.3914 | 0.3620 | 0.3761 | 0.9340 |
|
86 |
+
| 0.5096 | 16.3170 | 14000 | 1.6605 | 0.4354 | 0.3561 | 0.3918 | 0.9388 |
|
87 |
+
| 0.5037 | 16.8998 | 14500 | 1.7022 | 0.3882 | 0.3771 | 0.3826 | 0.9355 |
|
88 |
+
| 0.4839 | 17.4825 | 15000 | 1.6857 | 0.4071 | 0.3587 | 0.3814 | 0.9365 |
|
89 |
+
| 0.4769 | 18.0653 | 15500 | 1.6599 | 0.4432 | 0.3516 | 0.3921 | 0.9389 |
|
90 |
+
| 0.4607 | 18.6480 | 16000 | 1.6403 | 0.4445 | 0.3650 | 0.4009 | 0.9396 |
|
91 |
+
| 0.4567 | 19.2308 | 16500 | 1.6463 | 0.4321 | 0.3546 | 0.3895 | 0.9388 |
|
92 |
+
| 0.4449 | 19.8135 | 17000 | 1.6771 | 0.4148 | 0.3836 | 0.3986 | 0.9366 |
|
93 |
+
| 0.4363 | 20.3963 | 17500 | 1.7157 | 0.3993 | 0.3735 | 0.3860 | 0.9341 |
|
94 |
+
| 0.437 | 20.9790 | 18000 | 1.6571 | 0.4148 | 0.3738 | 0.3932 | 0.9372 |
|
95 |
+
| 0.4221 | 21.5618 | 18500 | 1.6544 | 0.4196 | 0.3582 | 0.3865 | 0.9372 |
|
96 |
+
| 0.4168 | 22.1445 | 19000 | 1.6168 | 0.4472 | 0.3428 | 0.3881 | 0.9399 |
|
97 |
+
| 0.409 | 22.7273 | 19500 | 1.6285 | 0.4335 | 0.3572 | 0.3917 | 0.9388 |
|
98 |
+
| 0.4081 | 23.3100 | 20000 | 1.6653 | 0.4058 | 0.3758 | 0.3903 | 0.9353 |
|
99 |
+
| 0.4009 | 23.8928 | 20500 | 1.6389 | 0.4263 | 0.3662 | 0.3940 | 0.9380 |
|
100 |
+
| 0.3886 | 24.4755 | 21000 | 1.6027 | 0.4632 | 0.3657 | 0.4087 | 0.9407 |
|
101 |
+
| 0.3947 | 25.0583 | 21500 | 1.6297 | 0.4377 | 0.3632 | 0.3969 | 0.9387 |
|
102 |
+
| 0.3839 | 25.6410 | 22000 | 1.6285 | 0.4317 | 0.3670 | 0.3968 | 0.9384 |
|
103 |
+
| 0.382 | 26.2238 | 22500 | 1.6517 | 0.4226 | 0.3740 | 0.3968 | 0.9372 |
|
104 |
+
| 0.3797 | 26.8065 | 23000 | 1.6248 | 0.4441 | 0.3711 | 0.4043 | 0.9389 |
|
105 |
+
| 0.3748 | 27.3893 | 23500 | 1.6254 | 0.4379 | 0.3754 | 0.4043 | 0.9388 |
|
106 |
+
| 0.3736 | 27.9720 | 24000 | 1.6162 | 0.4515 | 0.3659 | 0.4042 | 0.9392 |
|
107 |
+
| 0.3714 | 28.5548 | 24500 | 1.6312 | 0.4289 | 0.3748 | 0.4001 | 0.9380 |
|
108 |
+
| 0.3719 | 29.1375 | 25000 | 1.6199 | 0.4390 | 0.3720 | 0.4027 | 0.9384 |
|
109 |
+
| 0.3684 | 29.7203 | 25500 | 1.6199 | 0.4352 | 0.3701 | 0.4000 | 0.9387 |
|
110 |
|
111 |
|
112 |
### Framework versions
|
config.json
CHANGED
@@ -1,9 +1,12 @@
|
|
1 |
{
|
2 |
"_name_or_path": "haryoaw/scenario-TCR-NER_data-univner_half",
|
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_half",
|
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": 0.4, "recall": 0.24489795918367346, "f1": 0.30379746835443044, "accuracy": 0.9552123552123553}, "en_pud": {"precision": 0.4603825136612022, "recall": 0.31348837209302327, "f1": 0.3729939125622579, "accuracy": 0.9435209671326029}, "de_pud": {"precision": 0.1388888888888889, "recall": 0.12993262752646775, "f1": 0.1342615614122327, "accuracy": 0.892363227227978}, "pt_pud": {"precision": 0.268348623853211, "recall": 0.10646041856232939, "f1": 0.152442996742671, "accuracy": 0.928739266031529}, "ru_pud": {"precision": 0.015625, "recall": 0.015444015444015444, "f1": 0.015533980582524271, "accuracy": 0.8305347455437871}, "sv_pud": {"precision": 0.18719211822660098, "recall": 0.11078717201166181, "f1": 0.1391941391941392, "accuracy": 0.9084189557559237}, "tl_trg": {"precision": 0.5263157894736842, "recall": 0.43478260869565216, "f1": 0.47619047619047616, "accuracy": 0.9686648501362398}, "tl_ugnayan": {"precision": 0.03571428571428571, "recall": 0.030303030303030304, "f1": 0.03278688524590164, "accuracy": 0.9334548769371012}, "zh_gsd": {"precision": 0.5314787701317716, "recall": 0.47327249022164275, "f1": 0.5006896551724138, "accuracy": 0.9335664335664335}, "zh_gsdsimp": {"precision": 0.48214285714285715, "recall": 0.42463958060288337, "f1": 0.4515679442508711, "accuracy": 0.9289044289044289}, "hr_set": {"precision": 0.6854014598540146, "recall": 0.66928011404134, "f1": 0.6772448611611973, "accuracy": 0.9651690024732069}, "da_ddt": {"precision": 0.25, "recall": 0.12304250559284116, "f1": 0.16491754122938532, "accuracy": 0.934949615883468}, "en_ewt": {"precision": 0.5731272294887039, "recall": 0.4430147058823529, "f1": 0.4997407983411093, "accuracy": 0.9567677411642825}, "pt_bosque": {"precision": 0.20082815734989648, "recall": 0.07983539094650206, "f1": 0.11425206124852769, "accuracy": 0.9212795247065643}, "sr_set": {"precision": 0.6670902160101652, "recall": 0.6198347107438017, "f1": 0.642594859241126, "accuracy": 0.9485158917783031}, "sk_snk": {"precision": 0.19081272084805653, "recall": 0.1180327868852459, "f1": 0.14584740040513167, "accuracy": 0.8800251256281407}, "sv_talbanken": {"precision": 0.055401662049861494, "recall": 0.10204081632653061, "f1": 0.0718132854578097, "accuracy": 0.9638808460519213}}
|
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:bd465ad3d3ec511cbd82db1bbc532be7c983c7c94d7e2635d542dec208f75228
|
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 sha256:868ddb0c64e7be3d1d948649bc919954f9c67150bfdd30ad601ec98990942154
|
3 |
size 5304
|