Initial Commit
Browse files- README.md +117 -0
- config.json +53 -0
- eval_result_ner.json +1 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,117 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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-po-ner-full-mdeberta_data-univner_half44
|
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-po-ner-full-mdeberta_data-univner_half44
|
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: 0.1473
|
25 |
+
- Precision: 0.8609
|
26 |
+
- Recall: 0.8706
|
27 |
+
- F1: 0.8657
|
28 |
+
- Accuracy: 0.9852
|
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: 44
|
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 |
+
| 0.0061 | 0.5828 | 500 | 0.0903 | 0.8587 | 0.8507 | 0.8547 | 0.9842 |
|
60 |
+
| 0.0071 | 1.1655 | 1000 | 0.1028 | 0.8407 | 0.8732 | 0.8566 | 0.9845 |
|
61 |
+
| 0.0061 | 1.7483 | 1500 | 0.0990 | 0.8455 | 0.8495 | 0.8475 | 0.9833 |
|
62 |
+
| 0.0055 | 2.3310 | 2000 | 0.1022 | 0.8571 | 0.8517 | 0.8544 | 0.9842 |
|
63 |
+
| 0.0047 | 2.9138 | 2500 | 0.0968 | 0.8396 | 0.8668 | 0.8530 | 0.9840 |
|
64 |
+
| 0.0037 | 3.4965 | 3000 | 0.1138 | 0.8275 | 0.8707 | 0.8486 | 0.9832 |
|
65 |
+
| 0.0035 | 4.0793 | 3500 | 0.1145 | 0.8490 | 0.8588 | 0.8538 | 0.9837 |
|
66 |
+
| 0.0036 | 4.6620 | 4000 | 0.1066 | 0.8388 | 0.8687 | 0.8535 | 0.9840 |
|
67 |
+
| 0.0032 | 5.2448 | 4500 | 0.1206 | 0.8495 | 0.8575 | 0.8535 | 0.9840 |
|
68 |
+
| 0.0032 | 5.8275 | 5000 | 0.1192 | 0.8502 | 0.8564 | 0.8533 | 0.9840 |
|
69 |
+
| 0.0027 | 6.4103 | 5500 | 0.1153 | 0.8463 | 0.8683 | 0.8571 | 0.9844 |
|
70 |
+
| 0.0033 | 6.9930 | 6000 | 0.1199 | 0.8437 | 0.8722 | 0.8577 | 0.9843 |
|
71 |
+
| 0.003 | 7.5758 | 6500 | 0.1121 | 0.8533 | 0.8525 | 0.8529 | 0.9843 |
|
72 |
+
| 0.0023 | 8.1585 | 7000 | 0.1152 | 0.8508 | 0.8435 | 0.8471 | 0.9831 |
|
73 |
+
| 0.0028 | 8.7413 | 7500 | 0.1131 | 0.8368 | 0.8536 | 0.8451 | 0.9835 |
|
74 |
+
| 0.0026 | 9.3240 | 8000 | 0.1213 | 0.8415 | 0.8670 | 0.8540 | 0.9834 |
|
75 |
+
| 0.0021 | 9.9068 | 8500 | 0.1207 | 0.8313 | 0.8716 | 0.8510 | 0.9833 |
|
76 |
+
| 0.0015 | 10.4895 | 9000 | 0.1268 | 0.8566 | 0.8609 | 0.8587 | 0.9844 |
|
77 |
+
| 0.0016 | 11.0723 | 9500 | 0.1223 | 0.8525 | 0.8528 | 0.8527 | 0.9839 |
|
78 |
+
| 0.0021 | 11.6550 | 10000 | 0.1262 | 0.8402 | 0.8602 | 0.8501 | 0.9834 |
|
79 |
+
| 0.0012 | 12.2378 | 10500 | 0.1237 | 0.8575 | 0.8453 | 0.8514 | 0.9837 |
|
80 |
+
| 0.0014 | 12.8205 | 11000 | 0.1319 | 0.8537 | 0.8551 | 0.8544 | 0.9840 |
|
81 |
+
| 0.0013 | 13.4033 | 11500 | 0.1308 | 0.8316 | 0.8619 | 0.8465 | 0.9830 |
|
82 |
+
| 0.0014 | 13.9860 | 12000 | 0.1237 | 0.8615 | 0.8536 | 0.8575 | 0.9843 |
|
83 |
+
| 0.0008 | 14.5688 | 12500 | 0.1361 | 0.8436 | 0.8638 | 0.8536 | 0.9839 |
|
84 |
+
| 0.0013 | 15.1515 | 13000 | 0.1383 | 0.8466 | 0.8576 | 0.8521 | 0.9839 |
|
85 |
+
| 0.0011 | 15.7343 | 13500 | 0.1356 | 0.8595 | 0.8527 | 0.8561 | 0.9843 |
|
86 |
+
| 0.0007 | 16.3170 | 14000 | 0.1366 | 0.8533 | 0.8618 | 0.8575 | 0.9843 |
|
87 |
+
| 0.0008 | 16.8998 | 14500 | 0.1334 | 0.8608 | 0.8625 | 0.8616 | 0.9846 |
|
88 |
+
| 0.0007 | 17.4825 | 15000 | 0.1382 | 0.8549 | 0.8644 | 0.8596 | 0.9847 |
|
89 |
+
| 0.0007 | 18.0653 | 15500 | 0.1432 | 0.8682 | 0.8488 | 0.8584 | 0.9845 |
|
90 |
+
| 0.0006 | 18.6480 | 16000 | 0.1408 | 0.8551 | 0.8613 | 0.8582 | 0.9844 |
|
91 |
+
| 0.0009 | 19.2308 | 16500 | 0.1366 | 0.8551 | 0.8567 | 0.8559 | 0.9844 |
|
92 |
+
| 0.0007 | 19.8135 | 17000 | 0.1320 | 0.8518 | 0.8641 | 0.8579 | 0.9845 |
|
93 |
+
| 0.0005 | 20.3963 | 17500 | 0.1399 | 0.8506 | 0.8655 | 0.8580 | 0.9844 |
|
94 |
+
| 0.0005 | 20.9790 | 18000 | 0.1399 | 0.8510 | 0.8631 | 0.8570 | 0.9845 |
|
95 |
+
| 0.0005 | 21.5618 | 18500 | 0.1430 | 0.8633 | 0.8622 | 0.8628 | 0.9849 |
|
96 |
+
| 0.0005 | 22.1445 | 19000 | 0.1368 | 0.8549 | 0.8673 | 0.8611 | 0.9848 |
|
97 |
+
| 0.0004 | 22.7273 | 19500 | 0.1364 | 0.8548 | 0.8678 | 0.8613 | 0.9848 |
|
98 |
+
| 0.0005 | 23.3100 | 20000 | 0.1400 | 0.8616 | 0.8650 | 0.8633 | 0.9848 |
|
99 |
+
| 0.0003 | 23.8928 | 20500 | 0.1452 | 0.8458 | 0.8723 | 0.8589 | 0.9843 |
|
100 |
+
| 0.0002 | 24.4755 | 21000 | 0.1398 | 0.8552 | 0.8665 | 0.8608 | 0.9849 |
|
101 |
+
| 0.0003 | 25.0583 | 21500 | 0.1405 | 0.8578 | 0.8710 | 0.8643 | 0.9849 |
|
102 |
+
| 0.0002 | 25.6410 | 22000 | 0.1408 | 0.8601 | 0.8691 | 0.8646 | 0.9851 |
|
103 |
+
| 0.0002 | 26.2238 | 22500 | 0.1453 | 0.8578 | 0.8730 | 0.8654 | 0.9852 |
|
104 |
+
| 0.0002 | 26.8065 | 23000 | 0.1463 | 0.8574 | 0.8736 | 0.8654 | 0.9851 |
|
105 |
+
| 0.0002 | 27.3893 | 23500 | 0.1458 | 0.8637 | 0.8714 | 0.8676 | 0.9854 |
|
106 |
+
| 0.0001 | 27.9720 | 24000 | 0.1465 | 0.8565 | 0.8732 | 0.8648 | 0.9851 |
|
107 |
+
| 0.0001 | 28.5548 | 24500 | 0.1464 | 0.8602 | 0.8727 | 0.8664 | 0.9852 |
|
108 |
+
| 0.0002 | 29.1375 | 25000 | 0.1474 | 0.8598 | 0.8714 | 0.8656 | 0.9852 |
|
109 |
+
| 0.0001 | 29.7203 | 25500 | 0.1473 | 0.8609 | 0.8706 | 0.8657 | 0.9852 |
|
110 |
+
|
111 |
+
|
112 |
+
### Framework versions
|
113 |
+
|
114 |
+
- Transformers 4.44.2
|
115 |
+
- Pytorch 2.1.1+cu121
|
116 |
+
- Datasets 2.14.5
|
117 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "haryoaw/scenario-TCR-NER_data-univner_half",
|
3 |
+
"architectures": [
|
4 |
+
"DebertaV2ForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"hidden_act": "gelu",
|
8 |
+
"hidden_dropout_prob": 0.1,
|
9 |
+
"hidden_size": 768,
|
10 |
+
"id2label": {
|
11 |
+
"0": "LABEL_0",
|
12 |
+
"1": "LABEL_1",
|
13 |
+
"2": "LABEL_2",
|
14 |
+
"3": "LABEL_3",
|
15 |
+
"4": "LABEL_4",
|
16 |
+
"5": "LABEL_5",
|
17 |
+
"6": "LABEL_6"
|
18 |
+
},
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"intermediate_size": 3072,
|
21 |
+
"label2id": {
|
22 |
+
"LABEL_0": 0,
|
23 |
+
"LABEL_1": 1,
|
24 |
+
"LABEL_2": 2,
|
25 |
+
"LABEL_3": 3,
|
26 |
+
"LABEL_4": 4,
|
27 |
+
"LABEL_5": 5,
|
28 |
+
"LABEL_6": 6
|
29 |
+
},
|
30 |
+
"layer_norm_eps": 1e-07,
|
31 |
+
"max_position_embeddings": 512,
|
32 |
+
"max_relative_positions": -1,
|
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",
|
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": 0,
|
52 |
+
"vocab_size": 251000
|
53 |
+
}
|
eval_result_ner.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"ceb_gja": {"precision": 0.8333333333333334, "recall": 0.8163265306122449, "f1": 0.8247422680412372, "accuracy": 0.9868725868725868}, "en_pud": {"precision": 0.8344497607655502, "recall": 0.8111627906976744, "f1": 0.8226415094339622, "accuracy": 0.9822440498677748}, "de_pud": {"precision": 0.8224568138195777, "recall": 0.8248315688161694, "f1": 0.8236424795771263, "accuracy": 0.980591627209226}, "pt_pud": {"precision": 0.876750700280112, "recall": 0.8544131028207461, "f1": 0.8654377880184331, "accuracy": 0.9862434314521297}, "ru_pud": {"precision": 0.7327188940092166, "recall": 0.7673745173745173, "f1": 0.7496463932107497, "accuracy": 0.9746835443037974}, "sv_pud": {"precision": 0.8848780487804878, "recall": 0.8814382896015549, "f1": 0.8831548198636806, "accuracy": 0.988467183895995}, "tl_trg": {"precision": 0.9166666666666666, "recall": 0.9565217391304348, "f1": 0.9361702127659574, "accuracy": 0.9959128065395095}, "tl_ugnayan": {"precision": 0.6341463414634146, "recall": 0.7878787878787878, "f1": 0.7027027027027027, "accuracy": 0.9762989972652689}, "zh_gsd": {"precision": 0.8745046235138706, "recall": 0.863102998696219, "f1": 0.8687664041994752, "accuracy": 0.9816849816849816}, "zh_gsdsimp": {"precision": 0.8824306472919419, "recall": 0.8754914809960681, "f1": 0.8789473684210526, "accuracy": 0.9819347319347319}, "hr_set": {"precision": 0.922752808988764, "recall": 0.9365645046329294, "f1": 0.9296073576229218, "accuracy": 0.990684253915911}, "da_ddt": {"precision": 0.8489208633093526, "recall": 0.7919463087248322, "f1": 0.8194444444444445, "accuracy": 0.9860321261099472}, "en_ewt": {"precision": 0.8647887323943662, "recall": 0.8465073529411765, "f1": 0.8555503947979564, "accuracy": 0.9842212216599594}, "pt_bosque": {"precision": 0.8731009830205541, "recall": 0.8041152263374486, "f1": 0.8371893744644388, "accuracy": 0.9833357484422548}, "sr_set": {"precision": 0.9479289940828403, "recall": 0.9456906729634003, "f1": 0.9468085106382979, "accuracy": 0.9904561772174065}, "sk_snk": {"precision": 0.8122941822173436, "recall": 0.8087431693989071, "f1": 0.8105147864184009, "accuracy": 0.9738536432160804}, "sv_talbanken": {"precision": 0.8511627906976744, "recall": 0.9336734693877551, "f1": 0.8905109489051095, "accuracy": 0.9976444030033862}}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c3a2f61049e0e090d1dd4da96e9cdc6ad79b65ce064280ff833176eca502d217
|
3 |
+
size 1112921036
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:daf95f3e1e83a4a265e6cd703952e96337f1f2904298a81eac5585c40f513ab5
|
3 |
+
size 5304
|