muratti18462
commited on
Commit
•
073239a
1
Parent(s):
26d2878
End of training
Browse files- README.md +75 -0
- config.json +37 -0
- model.safetensors +3 -0
- runs/Sep09_13-39-20_ip-10-3-48-151.eu-central-1.compute.internal/events.out.tfevents.1725889166.ip-10-3-48-151.eu-central-1.compute.internal +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +60 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
license: apache-2.0
|
4 |
+
base_model: alvaroalon2/biobert_chemical_ner
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
model-index:
|
8 |
+
- name: murat_chem_model
|
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 |
+
# murat_chem_model
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [alvaroalon2/biobert_chemical_ner](https://huggingface.co/alvaroalon2/biobert_chemical_ner) on the None dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.3827
|
20 |
+
- Chemical: {'precision': 0.8843176605504587, 'recall': 0.8439124487004104, 'f1': 0.863642727145457, 'number': 7310}
|
21 |
+
- Overall Precision: 0.8843
|
22 |
+
- Overall Recall: 0.8439
|
23 |
+
- Overall F1: 0.8636
|
24 |
+
- Overall Accuracy: 0.9447
|
25 |
+
|
26 |
+
## Model description
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Intended uses & limitations
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training and evaluation data
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Training procedure
|
39 |
+
|
40 |
+
### Training hyperparameters
|
41 |
+
|
42 |
+
The following hyperparameters were used during training:
|
43 |
+
- learning_rate: 5e-05
|
44 |
+
- train_batch_size: 8
|
45 |
+
- eval_batch_size: 8
|
46 |
+
- seed: 42
|
47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
+
- lr_scheduler_type: linear
|
49 |
+
- num_epochs: 15
|
50 |
+
- mixed_precision_training: Native AMP
|
51 |
+
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss | Chemical | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
|
55 |
+
|:-------------:|:-------:|:----:|:---------------:|:---------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
|
56 |
+
| 1.6817 | 1.2048 | 100 | 0.3090 | {'precision': 0.8702002710435175, 'recall': 0.7905608755129959, 'f1': 0.828471077342126, 'number': 7310} | 0.8702 | 0.7906 | 0.8285 | 0.9204 |
|
57 |
+
| 1.6817 | 2.4096 | 200 | 0.2900 | {'precision': 0.8720861611094718, 'recall': 0.8086183310533516, 'f1': 0.8391538898353209, 'number': 7310} | 0.8721 | 0.8086 | 0.8392 | 0.9312 |
|
58 |
+
| 1.6817 | 3.6145 | 300 | 0.3071 | {'precision': 0.8830255057167986, 'recall': 0.824076607387141, 'f1': 0.8525332578545147, 'number': 7310} | 0.8830 | 0.8241 | 0.8525 | 0.9398 |
|
59 |
+
| 1.6817 | 4.8193 | 400 | 0.3099 | {'precision': 0.882646325363063, 'recall': 0.8231190150478797, 'f1': 0.8518439866921499, 'number': 7310} | 0.8826 | 0.8231 | 0.8518 | 0.9411 |
|
60 |
+
| 0.1018 | 6.0241 | 500 | 0.3891 | {'precision': 0.8816456613066782, 'recall': 0.8325581395348837, 'f1': 0.8563990712727785, 'number': 7310} | 0.8816 | 0.8326 | 0.8564 | 0.9402 |
|
61 |
+
| 0.1018 | 7.2289 | 600 | 0.3672 | {'precision': 0.8851640513552068, 'recall': 0.8488372093023255, 'f1': 0.8666201117318435, 'number': 7310} | 0.8852 | 0.8488 | 0.8666 | 0.9451 |
|
62 |
+
| 0.1018 | 8.4337 | 700 | 0.3459 | {'precision': 0.8812949640287769, 'recall': 0.8378932968536251, 'f1': 0.8590462833099579, 'number': 7310} | 0.8813 | 0.8379 | 0.8590 | 0.9449 |
|
63 |
+
| 0.1018 | 9.6386 | 800 | 0.3601 | {'precision': 0.880656108597285, 'recall': 0.8519835841313269, 'f1': 0.8660826032540675, 'number': 7310} | 0.8807 | 0.8520 | 0.8661 | 0.9462 |
|
64 |
+
| 0.1018 | 10.8434 | 900 | 0.3711 | {'precision': 0.881471972614463, 'recall': 0.8454172366621067, 'f1': 0.8630682214929124, 'number': 7310} | 0.8815 | 0.8454 | 0.8631 | 0.9443 |
|
65 |
+
| 0.0038 | 12.0482 | 1000 | 0.3779 | {'precision': 0.8816542644533486, 'recall': 0.8428180574555404, 'f1': 0.8617988529864317, 'number': 7310} | 0.8817 | 0.8428 | 0.8618 | 0.9437 |
|
66 |
+
| 0.0038 | 13.2530 | 1100 | 0.3829 | {'precision': 0.8837275985663082, 'recall': 0.8432284541723666, 'f1': 0.863003150157508, 'number': 7310} | 0.8837 | 0.8432 | 0.8630 | 0.9447 |
|
67 |
+
| 0.0038 | 14.4578 | 1200 | 0.3827 | {'precision': 0.8843176605504587, 'recall': 0.8439124487004104, 'f1': 0.863642727145457, 'number': 7310} | 0.8843 | 0.8439 | 0.8636 | 0.9447 |
|
68 |
+
|
69 |
+
|
70 |
+
### Framework versions
|
71 |
+
|
72 |
+
- Transformers 4.44.2
|
73 |
+
- Pytorch 2.3.0+cu121
|
74 |
+
- Datasets 2.21.0
|
75 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "alvaroalon2/biobert_chemical_ner",
|
3 |
+
"_num_labels": 3,
|
4 |
+
"architectures": [
|
5 |
+
"BertForTokenClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "B-CHEMICAL",
|
15 |
+
"1": "I-CHEMICAL",
|
16 |
+
"2": "O"
|
17 |
+
},
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"intermediate_size": 3072,
|
20 |
+
"label2id": {
|
21 |
+
"B-CHEMICAL": 0,
|
22 |
+
"I-CHEMICAL": 1,
|
23 |
+
"O": 2
|
24 |
+
},
|
25 |
+
"layer_norm_eps": 1e-12,
|
26 |
+
"max_position_embeddings": 512,
|
27 |
+
"model_type": "bert",
|
28 |
+
"num_attention_heads": 12,
|
29 |
+
"num_hidden_layers": 12,
|
30 |
+
"pad_token_id": 0,
|
31 |
+
"position_embedding_type": "absolute",
|
32 |
+
"torch_dtype": "float32",
|
33 |
+
"transformers_version": "4.44.2",
|
34 |
+
"type_vocab_size": 2,
|
35 |
+
"use_cache": true,
|
36 |
+
"vocab_size": 28996
|
37 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6b6903a47375eed1ffb714b7304ab2794114f2293bed1614dbb334362c7916e
|
3 |
+
size 430911284
|
runs/Sep09_13-39-20_ip-10-3-48-151.eu-central-1.compute.internal/events.out.tfevents.1725889166.ip-10-3-48-151.eu-central-1.compute.internal
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d8a4fe8d166b92f9fbdaec60ba8aef0400256b7fbcd322c8b0500651a784d59
|
3 |
+
size 12103
|
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 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": false,
|
48 |
+
"init_inputs": [],
|
49 |
+
"mask_token": "[MASK]",
|
50 |
+
"max_len": 512,
|
51 |
+
"model_max_length": 512,
|
52 |
+
"never_split": null,
|
53 |
+
"pad_token": "[PAD]",
|
54 |
+
"sep_token": "[SEP]",
|
55 |
+
"special_tokens": true,
|
56 |
+
"strip_accents": null,
|
57 |
+
"tokenize_chinese_chars": true,
|
58 |
+
"tokenizer_class": "BertTokenizer",
|
59 |
+
"unk_token": "[UNK]"
|
60 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6dba1d19c5b4fc62c7de2c66a7b90ef7aea0031664758a21ce389de96c02db24
|
3 |
+
size 5240
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|