amirali900
commited on
Commit
•
b003e88
1
Parent(s):
24ecc07
End of training
Browse files- README.md +74 -0
- config.json +49 -0
- model.safetensors +3 -0
- runs/Jul09_06-59-19_7cdfbbe1be93/events.out.tfevents.1720508361.7cdfbbe1be93.345.2 +3 -0
- runs/Jul09_07-05-38_7cdfbbe1be93/events.out.tfevents.1720508739.7cdfbbe1be93.345.3 +3 -0
- runs/Jul09_07-05-38_7cdfbbe1be93/events.out.tfevents.1720511185.7cdfbbe1be93.345.4 +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 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: dmis-lab/biobert-base-cased-v1.2
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- accuracy
|
7 |
+
model-index:
|
8 |
+
- name: biobert-base-cased-v1.2-finetuned-NER
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# biobert-base-cased-v1.2-finetuned-NER
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [dmis-lab/biobert-base-cased-v1.2](https://huggingface.co/dmis-lab/biobert-base-cased-v1.2) on the None dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.0905
|
20 |
+
- Accuracy: 0.9765
|
21 |
+
- Precision (macro): 0.8596
|
22 |
+
- Recall (macro): 0.8601
|
23 |
+
- F1 (macro): 0.8563
|
24 |
+
- Precision (micro): 0.9765
|
25 |
+
- Recall (micro): 0.9765
|
26 |
+
- F1 (micro): 0.9765
|
27 |
+
|
28 |
+
## Model description
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Intended uses & limitations
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training and evaluation data
|
37 |
+
|
38 |
+
More information needed
|
39 |
+
|
40 |
+
## Training procedure
|
41 |
+
|
42 |
+
### Training hyperparameters
|
43 |
+
|
44 |
+
The following hyperparameters were used during training:
|
45 |
+
- learning_rate: 2e-05
|
46 |
+
- train_batch_size: 16
|
47 |
+
- eval_batch_size: 16
|
48 |
+
- seed: 42
|
49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
+
- lr_scheduler_type: linear
|
51 |
+
- num_epochs: 10
|
52 |
+
|
53 |
+
### Training results
|
54 |
+
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision (macro) | Recall (macro) | F1 (macro) | Precision (micro) | Recall (micro) | F1 (micro) |
|
56 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------------:|:--------------:|:----------:|:-----------------:|:--------------:|:----------:|
|
57 |
+
| No log | 1.0 | 152 | 0.1382 | 0.9621 | 0.8016 | 0.6594 | 0.6754 | 0.9621 | 0.9621 | 0.9621 |
|
58 |
+
| No log | 2.0 | 304 | 0.0907 | 0.9740 | 0.8363 | 0.7827 | 0.7993 | 0.9740 | 0.9740 | 0.9740 |
|
59 |
+
| No log | 3.0 | 456 | 0.0811 | 0.9750 | 0.8661 | 0.8285 | 0.8261 | 0.9750 | 0.9750 | 0.9750 |
|
60 |
+
| 0.1768 | 4.0 | 608 | 0.0829 | 0.9738 | 0.8322 | 0.8581 | 0.8410 | 0.9738 | 0.9738 | 0.9738 |
|
61 |
+
| 0.1768 | 5.0 | 760 | 0.0786 | 0.9755 | 0.8350 | 0.8737 | 0.8526 | 0.9755 | 0.9755 | 0.9755 |
|
62 |
+
| 0.1768 | 6.0 | 912 | 0.0866 | 0.9766 | 0.8539 | 0.8491 | 0.8490 | 0.9766 | 0.9766 | 0.9766 |
|
63 |
+
| 0.0496 | 7.0 | 1064 | 0.0828 | 0.9757 | 0.8454 | 0.8563 | 0.8494 | 0.9757 | 0.9757 | 0.9757 |
|
64 |
+
| 0.0496 | 8.0 | 1216 | 0.0932 | 0.9754 | 0.8416 | 0.8622 | 0.8511 | 0.9754 | 0.9754 | 0.9754 |
|
65 |
+
| 0.0496 | 9.0 | 1368 | 0.0939 | 0.9752 | 0.8368 | 0.8617 | 0.8483 | 0.9752 | 0.9752 | 0.9752 |
|
66 |
+
| 0.0297 | 10.0 | 1520 | 0.0955 | 0.9759 | 0.8426 | 0.8597 | 0.8500 | 0.9759 | 0.9759 | 0.9759 |
|
67 |
+
|
68 |
+
|
69 |
+
### Framework versions
|
70 |
+
|
71 |
+
- Transformers 4.41.2
|
72 |
+
- Pytorch 2.3.0+cu121
|
73 |
+
- Datasets 2.20.0
|
74 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dmis-lab/biobert-base-cased-v1.2",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": "LABEL_0",
|
13 |
+
"1": "LABEL_1",
|
14 |
+
"2": "LABEL_2",
|
15 |
+
"3": "LABEL_3",
|
16 |
+
"4": "LABEL_4",
|
17 |
+
"5": "LABEL_5",
|
18 |
+
"6": "LABEL_6",
|
19 |
+
"7": "LABEL_7",
|
20 |
+
"8": "LABEL_8",
|
21 |
+
"9": "LABEL_9"
|
22 |
+
},
|
23 |
+
"initializer_range": 0.02,
|
24 |
+
"intermediate_size": 3072,
|
25 |
+
"label2id": {
|
26 |
+
"LABEL_0": 0,
|
27 |
+
"LABEL_1": 1,
|
28 |
+
"LABEL_2": 2,
|
29 |
+
"LABEL_3": 3,
|
30 |
+
"LABEL_4": 4,
|
31 |
+
"LABEL_5": 5,
|
32 |
+
"LABEL_6": 6,
|
33 |
+
"LABEL_7": 7,
|
34 |
+
"LABEL_8": 8,
|
35 |
+
"LABEL_9": 9
|
36 |
+
},
|
37 |
+
"layer_norm_eps": 1e-12,
|
38 |
+
"max_position_embeddings": 512,
|
39 |
+
"model_type": "bert",
|
40 |
+
"num_attention_heads": 12,
|
41 |
+
"num_hidden_layers": 12,
|
42 |
+
"pad_token_id": 0,
|
43 |
+
"position_embedding_type": "absolute",
|
44 |
+
"torch_dtype": "float32",
|
45 |
+
"transformers_version": "4.41.2",
|
46 |
+
"type_vocab_size": 2,
|
47 |
+
"use_cache": true,
|
48 |
+
"vocab_size": 28996
|
49 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0dc552ab5a65d4e7d2bc1e2b0773c83dac27ba4d8eff3670d6e734439382d333
|
3 |
+
size 430932816
|
runs/Jul09_06-59-19_7cdfbbe1be93/events.out.tfevents.1720508361.7cdfbbe1be93.345.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e0a277e49b7aa1c35d98121162fcca9132ae6b52608b9ba5c58689a41333fbc
|
3 |
+
size 6288
|
runs/Jul09_07-05-38_7cdfbbe1be93/events.out.tfevents.1720508739.7cdfbbe1be93.345.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfbda90872038303c389bbee65cc04c0cfb324f2e3ba1d95bf59c3fd3e7de569
|
3 |
+
size 12943
|
runs/Jul09_07-05-38_7cdfbbe1be93/events.out.tfevents.1720511185.7cdfbbe1be93.345.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62e0846faa5d334be8fff45aa54fd2cf41f37eea35b8cc1084746f513a7a6569
|
3 |
+
size 757
|
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 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
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": 512,
|
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 sha256:842ebcfcd4df2b73ec2c46d3863bb03ccf2890aa2c5e769126a262e55610f714
|
3 |
+
size 5112
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|