Initial Commit
Browse files- README.md +96 -0
- config.json +46 -0
- eval_result_ner.json +1 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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-non-kd-pre-ner-full-xlmr_data-univner_half55
|
14 |
+
results: []
|
15 |
+
---
|
16 |
+
|
17 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
18 |
+
should probably proofread and complete it, then remove this comment. -->
|
19 |
+
|
20 |
+
# scenario-non-kd-pre-ner-full-xlmr_data-univner_half55
|
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: 0.1450
|
25 |
+
- Precision: 0.8516
|
26 |
+
- Recall: 0.8357
|
27 |
+
- F1: 0.8436
|
28 |
+
- Accuracy: 0.9832
|
29 |
+
|
30 |
+
## Model description
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Intended uses & limitations
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Training and evaluation data
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Training procedure
|
43 |
+
|
44 |
+
### Training hyperparameters
|
45 |
+
|
46 |
+
The following hyperparameters were used during training:
|
47 |
+
- learning_rate: 3e-05
|
48 |
+
- train_batch_size: 32
|
49 |
+
- eval_batch_size: 32
|
50 |
+
- seed: 55
|
51 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
52 |
+
- lr_scheduler_type: linear
|
53 |
+
- num_epochs: 30
|
54 |
+
|
55 |
+
### Training results
|
56 |
+
|
57 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
58 |
+
|:-------------:|:-------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
59 |
+
| 0.0106 | 0.5828 | 500 | 0.0804 | 0.8385 | 0.8489 | 0.8437 | 0.9838 |
|
60 |
+
| 0.0101 | 1.1655 | 1000 | 0.0863 | 0.8549 | 0.8432 | 0.8490 | 0.9838 |
|
61 |
+
| 0.009 | 1.7483 | 1500 | 0.0960 | 0.8282 | 0.8557 | 0.8418 | 0.9829 |
|
62 |
+
| 0.0077 | 2.3310 | 2000 | 0.1040 | 0.8320 | 0.8498 | 0.8408 | 0.9827 |
|
63 |
+
| 0.0077 | 2.9138 | 2500 | 0.0931 | 0.8461 | 0.8478 | 0.8469 | 0.9835 |
|
64 |
+
| 0.0054 | 3.4965 | 3000 | 0.0982 | 0.8482 | 0.8523 | 0.8502 | 0.9843 |
|
65 |
+
| 0.0061 | 4.0793 | 3500 | 0.1075 | 0.8450 | 0.8355 | 0.8402 | 0.9832 |
|
66 |
+
| 0.0053 | 4.6620 | 4000 | 0.1068 | 0.8409 | 0.8536 | 0.8472 | 0.9839 |
|
67 |
+
| 0.0047 | 5.2448 | 4500 | 0.1073 | 0.8372 | 0.8592 | 0.8480 | 0.9837 |
|
68 |
+
| 0.0047 | 5.8275 | 5000 | 0.1100 | 0.8451 | 0.8585 | 0.8517 | 0.9839 |
|
69 |
+
| 0.0034 | 6.4103 | 5500 | 0.1167 | 0.8350 | 0.8497 | 0.8422 | 0.9832 |
|
70 |
+
| 0.0034 | 6.9930 | 6000 | 0.1122 | 0.8405 | 0.8478 | 0.8441 | 0.9836 |
|
71 |
+
| 0.0035 | 7.5758 | 6500 | 0.1125 | 0.8424 | 0.8419 | 0.8421 | 0.9834 |
|
72 |
+
| 0.0032 | 8.1585 | 7000 | 0.1145 | 0.8454 | 0.8504 | 0.8479 | 0.9836 |
|
73 |
+
| 0.0035 | 8.7413 | 7500 | 0.1075 | 0.8499 | 0.8407 | 0.8453 | 0.9838 |
|
74 |
+
| 0.0027 | 9.3240 | 8000 | 0.1213 | 0.8493 | 0.8384 | 0.8438 | 0.9837 |
|
75 |
+
| 0.0031 | 9.9068 | 8500 | 0.1083 | 0.8551 | 0.8440 | 0.8495 | 0.9842 |
|
76 |
+
| 0.0027 | 10.4895 | 9000 | 0.1273 | 0.8329 | 0.8639 | 0.8482 | 0.9835 |
|
77 |
+
| 0.0024 | 11.0723 | 9500 | 0.1247 | 0.8478 | 0.8411 | 0.8444 | 0.9834 |
|
78 |
+
| 0.0021 | 11.6550 | 10000 | 0.1161 | 0.8487 | 0.8378 | 0.8432 | 0.9838 |
|
79 |
+
| 0.0019 | 12.2378 | 10500 | 0.1284 | 0.8316 | 0.8556 | 0.8434 | 0.9830 |
|
80 |
+
| 0.0021 | 12.8205 | 11000 | 0.1208 | 0.8492 | 0.8510 | 0.8501 | 0.9840 |
|
81 |
+
| 0.0015 | 13.4033 | 11500 | 0.1266 | 0.8374 | 0.8499 | 0.8436 | 0.9830 |
|
82 |
+
| 0.002 | 13.9860 | 12000 | 0.1236 | 0.8403 | 0.8530 | 0.8466 | 0.9832 |
|
83 |
+
| 0.0016 | 14.5688 | 12500 | 0.1313 | 0.8453 | 0.8409 | 0.8430 | 0.9833 |
|
84 |
+
| 0.0013 | 15.1515 | 13000 | 0.1362 | 0.8460 | 0.8482 | 0.8471 | 0.9835 |
|
85 |
+
| 0.0015 | 15.7343 | 13500 | 0.1246 | 0.8480 | 0.8511 | 0.8496 | 0.9840 |
|
86 |
+
| 0.0012 | 16.3170 | 14000 | 0.1335 | 0.8549 | 0.8423 | 0.8485 | 0.9837 |
|
87 |
+
| 0.0014 | 16.8998 | 14500 | 0.1265 | 0.8445 | 0.8433 | 0.8439 | 0.9833 |
|
88 |
+
| 0.0009 | 17.4825 | 15000 | 0.1450 | 0.8516 | 0.8357 | 0.8436 | 0.9832 |
|
89 |
+
|
90 |
+
|
91 |
+
### Framework versions
|
92 |
+
|
93 |
+
- Transformers 4.44.2
|
94 |
+
- Pytorch 2.1.1+cu121
|
95 |
+
- Datasets 2.14.5
|
96 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "haryoaw/scenario-TCR-NER_data-univner_half",
|
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,
|
13 |
+
"id2label": {
|
14 |
+
"0": "LABEL_0",
|
15 |
+
"1": "LABEL_1",
|
16 |
+
"2": "LABEL_2",
|
17 |
+
"3": "LABEL_3",
|
18 |
+
"4": "LABEL_4",
|
19 |
+
"5": "LABEL_5",
|
20 |
+
"6": "LABEL_6"
|
21 |
+
},
|
22 |
+
"initializer_range": 0.02,
|
23 |
+
"intermediate_size": 3072,
|
24 |
+
"label2id": {
|
25 |
+
"LABEL_0": 0,
|
26 |
+
"LABEL_1": 1,
|
27 |
+
"LABEL_2": 2,
|
28 |
+
"LABEL_3": 3,
|
29 |
+
"LABEL_4": 4,
|
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": "4.44.2",
|
43 |
+
"type_vocab_size": 1,
|
44 |
+
"use_cache": true,
|
45 |
+
"vocab_size": 250002
|
46 |
+
}
|
eval_result_ner.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"ceb_gja": {"precision": 0.5542168674698795, "recall": 0.9387755102040817, "f1": 0.6969696969696971, "accuracy": 0.9683397683397683}, "en_pud": {"precision": 0.8, "recall": 0.8037209302325582, "f1": 0.8018561484918794, "accuracy": 0.9800245561012467}, "de_pud": {"precision": 0.7734303912647862, "recall": 0.8180943214629451, "f1": 0.7951356407857811, "accuracy": 0.9769818573906521}, "pt_pud": {"precision": 0.8683974932855864, "recall": 0.8826205641492265, "f1": 0.875451263537906, "accuracy": 0.9871405989661213}, "ru_pud": {"precision": 0.7193140794223827, "recall": 0.7693050193050193, "f1": 0.7434701492537313, "accuracy": 0.9733918884009299}, "sv_pud": {"precision": 0.8602661596958175, "recall": 0.8794946550048591, "f1": 0.8697741470446901, "accuracy": 0.9863703082407214}, "tl_trg": {"precision": 0.9166666666666666, "recall": 0.9565217391304348, "f1": 0.9361702127659574, "accuracy": 0.9959128065395095}, "tl_ugnayan": {"precision": 0.6923076923076923, "recall": 0.8181818181818182, "f1": 0.7500000000000001, "accuracy": 0.9808568824065633}, "zh_gsd": {"precision": 0.8696219035202086, "recall": 0.8696219035202086, "f1": 0.8696219035202086, "accuracy": 0.9805194805194806}, "zh_gsdsimp": {"precision": 0.8620236530880421, "recall": 0.8597640891218873, "f1": 0.8608923884514434, "accuracy": 0.97993672993673}, "hr_set": {"precision": 0.9109730848861284, "recall": 0.9408410548823949, "f1": 0.9256661991584852, "accuracy": 0.9897774113767519}, "da_ddt": {"precision": 0.8486238532110092, "recall": 0.8277404921700223, "f1": 0.8380520951302378, "accuracy": 0.9881273071934551}, "en_ewt": {"precision": 0.8045574057843996, "recall": 0.84375, "f1": 0.8236877523553163, "accuracy": 0.9815914252699526}, "pt_bosque": {"precision": 0.878657487091222, "recall": 0.8403292181069959, "f1": 0.8590660496424064, "accuracy": 0.986306332415592}, "sr_set": {"precision": 0.9523241954707986, "recall": 0.9433293978748524, "f1": 0.9478054567022538, "accuracy": 0.9898432711671482}, "sk_snk": {"precision": 0.7984749455337691, "recall": 0.8010928961748633, "f1": 0.7997817785051827, "accuracy": 0.9707914572864321}, "sv_talbanken": {"precision": 0.8497652582159625, "recall": 0.923469387755102, "f1": 0.8850855745721271, "accuracy": 0.9977425528782451}}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f413f2a0395de218455d609296d85d9bc8056925319fa2068b2aaabb02c367a0
|
3 |
+
size 1109857804
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f2b557dafab528d18f935b242bf05f6e8a44c428f5f8eb27604d8202961468c
|
3 |
+
size 5304
|