Initial Commit
Browse files- README.md +91 -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 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
license: mit
|
4 |
+
base_model: haryoaw/scenario-TCR-NER_data-univner_full
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
metrics:
|
8 |
+
- precision
|
9 |
+
- recall
|
10 |
+
- f1
|
11 |
+
- accuracy
|
12 |
+
model-index:
|
13 |
+
- name: scenario-non-kd-scr-ner-full_data-univner_full55
|
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-scr-ner-full_data-univner_full55
|
21 |
+
|
22 |
+
This model is a fine-tuned version of [haryoaw/scenario-TCR-NER_data-univner_full](https://huggingface.co/haryoaw/scenario-TCR-NER_data-univner_full) on the None dataset.
|
23 |
+
It achieves the following results on the evaluation set:
|
24 |
+
- Loss: 0.1084
|
25 |
+
- Precision: 0.8506
|
26 |
+
- Recall: 0.8628
|
27 |
+
- F1: 0.8567
|
28 |
+
- Accuracy: 0.9845
|
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 |
+
| 0.0097 | 0.2910 | 500 | 0.0794 | 0.8535 | 0.8668 | 0.8601 | 0.9850 |
|
60 |
+
| 0.0108 | 0.5821 | 1000 | 0.0802 | 0.8457 | 0.8634 | 0.8544 | 0.9846 |
|
61 |
+
| 0.0115 | 0.8731 | 1500 | 0.0724 | 0.8486 | 0.8693 | 0.8588 | 0.9850 |
|
62 |
+
| 0.0087 | 1.1641 | 2000 | 0.0877 | 0.8448 | 0.8680 | 0.8562 | 0.9841 |
|
63 |
+
| 0.008 | 1.4552 | 2500 | 0.0810 | 0.8576 | 0.8645 | 0.8610 | 0.9850 |
|
64 |
+
| 0.0084 | 1.7462 | 3000 | 0.0844 | 0.8508 | 0.8661 | 0.8584 | 0.9846 |
|
65 |
+
| 0.0081 | 2.0373 | 3500 | 0.0859 | 0.8524 | 0.8634 | 0.8579 | 0.9846 |
|
66 |
+
| 0.0066 | 2.3283 | 4000 | 0.0920 | 0.8386 | 0.8778 | 0.8577 | 0.9845 |
|
67 |
+
| 0.0065 | 2.6193 | 4500 | 0.0907 | 0.8480 | 0.8624 | 0.8551 | 0.9841 |
|
68 |
+
| 0.0074 | 2.9104 | 5000 | 0.0873 | 0.8342 | 0.8665 | 0.8500 | 0.9838 |
|
69 |
+
| 0.0056 | 3.2014 | 5500 | 0.0997 | 0.8490 | 0.8602 | 0.8546 | 0.9842 |
|
70 |
+
| 0.0056 | 3.4924 | 6000 | 0.0908 | 0.8451 | 0.8696 | 0.8571 | 0.9847 |
|
71 |
+
| 0.0049 | 3.7835 | 6500 | 0.0991 | 0.8534 | 0.8621 | 0.8577 | 0.9849 |
|
72 |
+
| 0.0053 | 4.0745 | 7000 | 0.1107 | 0.8444 | 0.8641 | 0.8541 | 0.9844 |
|
73 |
+
| 0.0041 | 4.3655 | 7500 | 0.0994 | 0.8414 | 0.8658 | 0.8534 | 0.9839 |
|
74 |
+
| 0.0047 | 4.6566 | 8000 | 0.1016 | 0.8498 | 0.8664 | 0.8580 | 0.9839 |
|
75 |
+
| 0.0052 | 4.9476 | 8500 | 0.1000 | 0.8369 | 0.8746 | 0.8554 | 0.9844 |
|
76 |
+
| 0.0039 | 5.2386 | 9000 | 0.1097 | 0.8292 | 0.8777 | 0.8527 | 0.9835 |
|
77 |
+
| 0.0042 | 5.5297 | 9500 | 0.1000 | 0.8451 | 0.8703 | 0.8575 | 0.9844 |
|
78 |
+
| 0.0042 | 5.8207 | 10000 | 0.1087 | 0.8468 | 0.8612 | 0.8539 | 0.9841 |
|
79 |
+
| 0.0042 | 6.1118 | 10500 | 0.1120 | 0.8312 | 0.8753 | 0.8527 | 0.9839 |
|
80 |
+
| 0.0032 | 6.4028 | 11000 | 0.1144 | 0.8510 | 0.8540 | 0.8525 | 0.9842 |
|
81 |
+
| 0.0039 | 6.6938 | 11500 | 0.1075 | 0.8330 | 0.8689 | 0.8506 | 0.9837 |
|
82 |
+
| 0.0038 | 6.9849 | 12000 | 0.1112 | 0.8295 | 0.8677 | 0.8482 | 0.9833 |
|
83 |
+
| 0.0031 | 7.2759 | 12500 | 0.1084 | 0.8506 | 0.8628 | 0.8567 | 0.9845 |
|
84 |
+
|
85 |
+
|
86 |
+
### Framework versions
|
87 |
+
|
88 |
+
- Transformers 4.44.2
|
89 |
+
- Pytorch 2.1.1+cu121
|
90 |
+
- Datasets 2.14.5
|
91 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "haryoaw/scenario-TCR-NER_data-univner_full",
|
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": 0.7580645161290323, "recall": 0.9591836734693877, "f1": 0.8468468468468467, "accuracy": 0.9861003861003861}, "en_pud": {"precision": 0.8141509433962264, "recall": 0.8027906976744186, "f1": 0.8084309133489461, "accuracy": 0.9816301473366075}, "de_pud": {"precision": 0.7988826815642458, "recall": 0.8257940327237728, "f1": 0.8121154756270705, "accuracy": 0.9791383432562937}, "pt_pud": {"precision": 0.8729037952338923, "recall": 0.899909008189263, "f1": 0.8862007168458782, "accuracy": 0.9891485453069595}, "ru_pud": {"precision": 0.7230347349177331, "recall": 0.7635135135135135, "f1": 0.7427230046948357, "accuracy": 0.9740635494704211}, "sv_pud": {"precision": 0.8643067846607669, "recall": 0.8542274052478134, "f1": 0.8592375366568914, "accuracy": 0.9857412455441392}, "tl_trg": {"precision": 1.0, "recall": 0.9565217391304348, "f1": 0.9777777777777777, "accuracy": 0.9986376021798365}, "tl_ugnayan": {"precision": 0.6486486486486487, "recall": 0.7272727272727273, "f1": 0.6857142857142857, "accuracy": 0.9735642661804923}, "zh_gsd": {"precision": 0.8492063492063492, "recall": 0.8370273794002607, "f1": 0.8430728824688116, "accuracy": 0.9784382284382285}, "zh_gsdsimp": {"precision": 0.8494055482166446, "recall": 0.8427260812581914, "f1": 0.8460526315789473, "accuracy": 0.9792707292707292}, "hr_set": {"precision": 0.9159138290479499, "recall": 0.9394155381325731, "f1": 0.9275158339197747, "accuracy": 0.9915086562242375}, "da_ddt": {"precision": 0.8714953271028038, "recall": 0.8344519015659956, "f1": 0.8525714285714285, "accuracy": 0.9888257008879577}, "en_ewt": {"precision": 0.8059149722735675, "recall": 0.8014705882352942, "f1": 0.8036866359447005, "accuracy": 0.9794796190779774}, "pt_bosque": {"precision": 0.8819157720891825, "recall": 0.8790123456790123, "f1": 0.8804616652926629, "accuracy": 0.9875742645993334}, "sr_set": {"precision": 0.9653937947494033, "recall": 0.9551357733175915, "f1": 0.9602373887240355, "accuracy": 0.9926451273969005}, "sk_snk": {"precision": 0.825503355704698, "recall": 0.8065573770491803, "f1": 0.8159203980099503, "accuracy": 0.9719692211055276}, "sv_talbanken": {"precision": 0.8921568627450981, "recall": 0.9285714285714286, "f1": 0.9099999999999999, "accuracy": 0.9983314521273985}}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c385d2fc2a6c9caef3950622471dc6bbcee1ac6cdc6af82248b0e03a192bedb
|
3 |
+
size 1109857804
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:10d2be90fbb6fd58628c360cbf23de6ae0a1c8d5215d4b9a548a5104aa947fb3
|
3 |
+
size 5304
|