Initial Commit
Browse files- README.md +74 -0
- config.json +46 -0
- eval_result_ner.json +1 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: haryoaw/scenario-TCR-NER_data-univner_half
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
- f1
|
10 |
+
- accuracy
|
11 |
+
model-index:
|
12 |
+
- name: scenario-kd-scr-ner-full-xlmr-halfen_data-univner_en66
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# scenario-kd-scr-ner-full-xlmr-halfen_data-univner_en66
|
20 |
+
|
21 |
+
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.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 250.6721
|
24 |
+
- Precision: 0.4368
|
25 |
+
- Recall: 0.2754
|
26 |
+
- F1: 0.3378
|
27 |
+
- Accuracy: 0.9532
|
28 |
+
|
29 |
+
## Model description
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Intended uses & limitations
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training and evaluation data
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Training procedure
|
42 |
+
|
43 |
+
### Training hyperparameters
|
44 |
+
|
45 |
+
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 3e-05
|
47 |
+
- train_batch_size: 8
|
48 |
+
- eval_batch_size: 32
|
49 |
+
- seed: 66
|
50 |
+
- gradient_accumulation_steps: 4
|
51 |
+
- total_train_batch_size: 32
|
52 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
53 |
+
- lr_scheduler_type: linear
|
54 |
+
- num_epochs: 10
|
55 |
+
|
56 |
+
### Training results
|
57 |
+
|
58 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
59 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
60 |
+
| 426.5331 | 1.28 | 500 | 343.1131 | 0.4717 | 0.0259 | 0.0491 | 0.9413 |
|
61 |
+
| 317.8317 | 2.55 | 1000 | 306.4857 | 0.3815 | 0.1066 | 0.1667 | 0.9449 |
|
62 |
+
| 288.4479 | 3.83 | 1500 | 285.8158 | 0.4429 | 0.1284 | 0.1990 | 0.9461 |
|
63 |
+
| 270.6268 | 5.1 | 2000 | 271.5317 | 0.3921 | 0.2050 | 0.2692 | 0.9494 |
|
64 |
+
| 257.3109 | 6.38 | 2500 | 260.7265 | 0.3853 | 0.2381 | 0.2943 | 0.9517 |
|
65 |
+
| 248.4864 | 7.65 | 3000 | 253.9278 | 0.3950 | 0.2940 | 0.3371 | 0.9527 |
|
66 |
+
| 242.8456 | 8.93 | 3500 | 250.6721 | 0.4368 | 0.2754 | 0.3378 | 0.9532 |
|
67 |
+
|
68 |
+
|
69 |
+
### Framework versions
|
70 |
+
|
71 |
+
- Transformers 4.33.3
|
72 |
+
- Pytorch 2.1.1+cu121
|
73 |
+
- Datasets 2.14.5
|
74 |
+
- Tokenizers 0.13.3
|
config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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,
|
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": 6,
|
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
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"ceb_gja": {"precision": 0.3191489361702128, "recall": 0.30612244897959184, "f1": 0.3125, "accuracy": 0.9451737451737452}, "en_pud": {"precision": 0.34501845018450183, "recall": 0.173953488372093, "f1": 0.2312925170068027, "accuracy": 0.935681904042312}, "de_pud": {"precision": 0.1561938958707361, "recall": 0.08373435996150144, "f1": 0.10902255639097745, "accuracy": 0.9213820261591111}, "pt_pud": {"precision": 0.271356783919598, "recall": 0.04913557779799818, "f1": 0.08320493066255777, "accuracy": 0.9331396590763447}, "ru_pud": {"precision": 0.046511627906976744, "recall": 0.0019305019305019305, "f1": 0.0037071362372567192, "accuracy": 0.9222939808834927}, "sv_pud": {"precision": 0.28879310344827586, "recall": 0.06511175898931001, "f1": 0.10626486915146709, "accuracy": 0.9270287271964772}, "tl_trg": {"precision": 0.3, "recall": 0.391304347826087, "f1": 0.33962264150943394, "accuracy": 0.946866485013624}, "tl_ugnayan": {"precision": 0.0, "recall": 0.0, "f1": 0.0, "accuracy": 0.9443938012762079}, "zh_gsd": {"precision": 0.2, "recall": 0.002607561929595828, "f1": 0.005148005148005148, "accuracy": 0.8827006327006327}, "zh_gsdsimp": {"precision": 0.0, "recall": 0.0, "f1": 0.0, "accuracy": 0.883033633033633}, "hr_set": {"precision": 0.14622641509433962, "recall": 0.022095509622238062, "f1": 0.03839009287925697, "accuracy": 0.9139323990107172}, "da_ddt": {"precision": 0.21238938053097345, "recall": 0.053691275167785234, "f1": 0.08571428571428573, "accuracy": 0.9365459443280455}, "en_ewt": {"precision": 0.4687022900763359, "recall": 0.2821691176470588, "f1": 0.35226620768789446, "accuracy": 0.9482806709965335}, "pt_bosque": {"precision": 0.18303571428571427, "recall": 0.03374485596707819, "f1": 0.05698401667824879, "accuracy": 0.9232357629329083}, "sr_set": {"precision": 0.09090909090909091, "recall": 0.009445100354191263, "f1": 0.017112299465240642, "accuracy": 0.8927414412047981}, "sk_snk": {"precision": 0.20093457943925233, "recall": 0.046994535519125684, "f1": 0.07617360496014171, "accuracy": 0.8885050251256281}, "sv_talbanken": {"precision": 0.14184397163120568, "recall": 0.10204081632653061, "f1": 0.11869436201780416, "accuracy": 0.9839034205231388}}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:70e59418b10636e37f48616986ad14d5a450ea33d0c06d0785fa6cb3ece76c38
|
3 |
+
size 939760294
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c0e47657862944a57e76da62acfc0e88e816bc193a752c941ddf71caf5780e4
|
3 |
+
size 4600
|