End of training
Browse files- README.md +82 -0
- config.json +55 -0
- model.safetensors +3 -0
- runs/Mar07_11-00-45_archlinux/events.out.tfevents.1709805648.archlinux.2530787.0 +3 -0
- runs/Mar07_11-09-10_archlinux/events.out.tfevents.1709806152.archlinux.2534847.0 +3 -0
- runs/Mar07_12-05-47_archlinux/events.out.tfevents.1709809548.archlinux.2534847.1 +3 -0
- runs/Mar07_12-13-09_archlinux/events.out.tfevents.1709809990.archlinux.2534847.2 +3 -0
- runs/Mar07_12-34-21_archlinux/events.out.tfevents.1709811263.archlinux.2569236.0 +3 -0
- runs/Mar07_12-42-56_archlinux/events.out.tfevents.1709811778.archlinux.2572753.0 +3 -0
- runs/Mar07_14-00-05_archlinux/events.out.tfevents.1709816408.archlinux.2602258.0 +3 -0
- runs/Mar07_14-02-16_archlinux/events.out.tfevents.1709816538.archlinux.2604731.0 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-nc-4.0
|
3 |
+
base_model: NYTK/PULI-BERT-Large
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
- f1
|
10 |
+
- accuracy
|
11 |
+
model-index:
|
12 |
+
- name: kmdb_ner_model
|
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 |
+
# kmdb_ner_model
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [NYTK/PULI-BERT-Large](https://huggingface.co/NYTK/PULI-BERT-Large) on an unknown dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.0405
|
24 |
+
- Precision: 0.8023
|
25 |
+
- Recall: 0.8261
|
26 |
+
- F1: 0.8140
|
27 |
+
- Accuracy: 0.9842
|
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: 2e-05
|
47 |
+
- train_batch_size: 4
|
48 |
+
- eval_batch_size: 4
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- num_epochs: 2
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
57 |
+
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
58 |
+
| 0.0613 | 0.11 | 1000 | 0.0575 | 0.7102 | 0.7359 | 0.7228 | 0.9776 |
|
59 |
+
| 0.0559 | 0.23 | 2000 | 0.0525 | 0.7108 | 0.7611 | 0.7351 | 0.9788 |
|
60 |
+
| 0.0569 | 0.34 | 3000 | 0.0512 | 0.7375 | 0.7856 | 0.7608 | 0.9798 |
|
61 |
+
| 0.0481 | 0.45 | 4000 | 0.0496 | 0.7402 | 0.7975 | 0.7678 | 0.9803 |
|
62 |
+
| 0.041 | 0.57 | 5000 | 0.0474 | 0.7567 | 0.7981 | 0.7769 | 0.9809 |
|
63 |
+
| 0.0434 | 0.68 | 6000 | 0.0463 | 0.7588 | 0.7853 | 0.7718 | 0.9813 |
|
64 |
+
| 0.0577 | 0.8 | 7000 | 0.0462 | 0.7592 | 0.7896 | 0.7741 | 0.9812 |
|
65 |
+
| 0.0422 | 0.91 | 8000 | 0.0428 | 0.7820 | 0.8057 | 0.7937 | 0.9828 |
|
66 |
+
| 0.0346 | 1.02 | 9000 | 0.0443 | 0.7758 | 0.8153 | 0.7951 | 0.9825 |
|
67 |
+
| 0.0301 | 1.14 | 10000 | 0.0431 | 0.7831 | 0.8124 | 0.7974 | 0.9830 |
|
68 |
+
| 0.0305 | 1.25 | 11000 | 0.0427 | 0.7955 | 0.8162 | 0.8057 | 0.9834 |
|
69 |
+
| 0.0347 | 1.36 | 12000 | 0.0420 | 0.7923 | 0.8171 | 0.8045 | 0.9834 |
|
70 |
+
| 0.0397 | 1.48 | 13000 | 0.0422 | 0.7923 | 0.8220 | 0.8069 | 0.9835 |
|
71 |
+
| 0.0267 | 1.59 | 14000 | 0.0411 | 0.7970 | 0.8209 | 0.8087 | 0.9838 |
|
72 |
+
| 0.03 | 1.71 | 15000 | 0.0415 | 0.7946 | 0.8230 | 0.8085 | 0.9838 |
|
73 |
+
| 0.0311 | 1.82 | 16000 | 0.0407 | 0.8023 | 0.8253 | 0.8136 | 0.9842 |
|
74 |
+
| 0.0283 | 1.93 | 17000 | 0.0405 | 0.8023 | 0.8261 | 0.8140 | 0.9842 |
|
75 |
+
|
76 |
+
|
77 |
+
### Framework versions
|
78 |
+
|
79 |
+
- Transformers 4.38.1
|
80 |
+
- Pytorch 2.0.1+cu117
|
81 |
+
- Datasets 2.16.1
|
82 |
+
- Tokenizers 0.15.0
|
config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "NYTK/PULI-BERT-Large",
|
3 |
+
"architectures": [
|
4 |
+
"MegatronBertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"hidden_act": "gelu",
|
8 |
+
"hidden_dropout_prob": 0.1,
|
9 |
+
"hidden_size": 1024,
|
10 |
+
"id2label": {
|
11 |
+
"0": "O",
|
12 |
+
"1": "B-NEG-ORG",
|
13 |
+
"2": "B-POS-ORG",
|
14 |
+
"3": "I-NEG-ORG",
|
15 |
+
"4": "I-POS-ORG",
|
16 |
+
"5": "B-NEG-PER",
|
17 |
+
"6": "B-POS-PER",
|
18 |
+
"7": "I-NEG-PER",
|
19 |
+
"8": "I-POS-PER",
|
20 |
+
"9": "B-NEG-LOC",
|
21 |
+
"10": "B-POS-LOC",
|
22 |
+
"11": "I-NEG-LOC",
|
23 |
+
"12": "I-POS-LOC"
|
24 |
+
},
|
25 |
+
"initializer_range": 0.02,
|
26 |
+
"intermediate_size": 4096,
|
27 |
+
"label2id": {
|
28 |
+
"B-NEG-LOC": 9,
|
29 |
+
"B-NEG-ORG": 1,
|
30 |
+
"B-NEG-PER": 5,
|
31 |
+
"B-POS-LOC": 10,
|
32 |
+
"B-POS-ORG": 2,
|
33 |
+
"B-POS-PER": 6,
|
34 |
+
"I-NEG-LOC": 11,
|
35 |
+
"I-NEG-ORG": 3,
|
36 |
+
"I-NEG-PER": 7,
|
37 |
+
"I-POS-LOC": 12,
|
38 |
+
"I-POS-ORG": 4,
|
39 |
+
"I-POS-PER": 8,
|
40 |
+
"O": 0
|
41 |
+
},
|
42 |
+
"layer_norm_eps": 1e-12,
|
43 |
+
"max_position_embeddings": 512,
|
44 |
+
"model_type": "megatron-bert",
|
45 |
+
"num_attention_heads": 16,
|
46 |
+
"num_hidden_layers": 24,
|
47 |
+
"pad_token_id": 0,
|
48 |
+
"position_embedding_type": "absolute",
|
49 |
+
"tokenizer_type": "BertWordPieceCase",
|
50 |
+
"torch_dtype": "float32",
|
51 |
+
"transformers_version": "4.38.1",
|
52 |
+
"type_vocab_size": 2,
|
53 |
+
"use_cache": true,
|
54 |
+
"vocab_size": 32256
|
55 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aefbf4ec155949bafa41e3e4ffef6f8deed3934e025c3141bbcdc174d6943f63
|
3 |
+
size 1343570396
|
runs/Mar07_11-00-45_archlinux/events.out.tfevents.1709805648.archlinux.2530787.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:89d44ad4605936301f7c4c9f5ae64a33cafb78cc04dd576caf813a365e203c4f
|
3 |
+
size 5112
|
runs/Mar07_11-09-10_archlinux/events.out.tfevents.1709806152.archlinux.2534847.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28f1c7797804a37a5790a6a552431bdacaba4c1fc87cb27a538a3ae80b92d5c2
|
3 |
+
size 6167
|
runs/Mar07_12-05-47_archlinux/events.out.tfevents.1709809548.archlinux.2534847.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa89ecb8c773a39500f316f13b8b84445bc7fa4e887ca0f12d3e71da3a589c37
|
3 |
+
size 5951
|
runs/Mar07_12-13-09_archlinux/events.out.tfevents.1709809990.archlinux.2534847.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2df6cee5ef695149c8023e365ff07f578054944552f9741129613c60f0ead51
|
3 |
+
size 5527
|
runs/Mar07_12-34-21_archlinux/events.out.tfevents.1709811263.archlinux.2569236.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b89a9b60f7189f43b1bed84b2754b7e1b32a32b52c038e077cde111aef8eadbc
|
3 |
+
size 5999
|
runs/Mar07_12-42-56_archlinux/events.out.tfevents.1709811778.archlinux.2572753.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:36e8a9945c78381b57d0bf2ee7d5aed0625f712c6cc361f99b2a7d4dd2a5e7b3
|
3 |
+
size 48471
|
runs/Mar07_14-00-05_archlinux/events.out.tfevents.1709816408.archlinux.2602258.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dcf6abf61f8a1c7c8ada1cc86d9f6af1c11135861efbf8085b4a78ed65f046b1
|
3 |
+
size 4184
|
runs/Mar07_14-02-16_archlinux/events.out.tfevents.1709816538.archlinux.2604731.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7dafaefa7b0fad6a4802e7f8eed1f4bf04ce42ab590aa49cb1bbb176abc0fba3
|
3 |
+
size 385066
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"4": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_basic_tokenize": true,
|
47 |
+
"do_lower_case": true,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 1000000000000000019884624838656,
|
50 |
+
"never_split": null,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"sep_token": "[SEP]",
|
53 |
+
"strip_accents": null,
|
54 |
+
"tokenize_chinese_chars": true,
|
55 |
+
"tokenizer_class": "BertTokenizer",
|
56 |
+
"unk_token": "[UNK]"
|
57 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4fd97eb8ae6457a7638d3e93a35fca14068c329ccb55de3e7b4c667105fcee4
|
3 |
+
size 4475
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|