End of training
Browse files- README.md +120 -0
- config.json +33 -0
- model.safetensors +3 -0
- runs/Jul14_10-21-56_8141a392dcea/events.out.tfevents.1752488542.8141a392dcea.5512.0 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,120 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
base_model: dmis-lab/biobert-base-cased-v1.1
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
- precision
|
9 |
+
- recall
|
10 |
+
- f1
|
11 |
+
model-index:
|
12 |
+
- name: Biobert_combo_v1
|
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 |
+
# Biobert_combo_v1
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [dmis-lab/biobert-base-cased-v1.1](https://huggingface.co/dmis-lab/biobert-base-cased-v1.1) on the None dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.4421
|
24 |
+
- Accuracy: 0.769
|
25 |
+
- Auc: 0.867
|
26 |
+
- Precision: 0.745
|
27 |
+
- Recall: 0.887
|
28 |
+
- F1: 0.81
|
29 |
+
- F1-macro: 0.757
|
30 |
+
- F1-micro: 0.769
|
31 |
+
- F1-weighted: 0.763
|
32 |
+
|
33 |
+
## Model description
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Intended uses & limitations
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Training and evaluation data
|
42 |
+
|
43 |
+
More information needed
|
44 |
+
|
45 |
+
## Training procedure
|
46 |
+
|
47 |
+
### Training hyperparameters
|
48 |
+
|
49 |
+
The following hyperparameters were used during training:
|
50 |
+
- learning_rate: 2e-05
|
51 |
+
- train_batch_size: 8
|
52 |
+
- eval_batch_size: 8
|
53 |
+
- seed: 42
|
54 |
+
- gradient_accumulation_steps: 4
|
55 |
+
- total_train_batch_size: 32
|
56 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
57 |
+
- lr_scheduler_type: linear
|
58 |
+
- num_epochs: 5
|
59 |
+
- mixed_precision_training: Native AMP
|
60 |
+
|
61 |
+
### Training results
|
62 |
+
|
63 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Auc | Precision | Recall | F1 | F1-macro | F1-micro | F1-weighted |
|
64 |
+
|:-------------:|:------:|:-----:|:---------------:|:--------:|:-----:|:---------:|:------:|:-----:|:--------:|:--------:|:-----------:|
|
65 |
+
| 0.6198 | 0.1028 | 500 | 0.5619 | 0.693 | 0.769 | 0.676 | 0.858 | 0.757 | 0.671 | 0.693 | 0.681 |
|
66 |
+
| 0.5401 | 0.2057 | 1000 | 0.5167 | 0.717 | 0.807 | 0.717 | 0.81 | 0.761 | 0.708 | 0.717 | 0.713 |
|
67 |
+
| 0.5141 | 0.3085 | 1500 | 0.4933 | 0.731 | 0.827 | 0.75 | 0.772 | 0.761 | 0.726 | 0.731 | 0.73 |
|
68 |
+
| 0.4886 | 0.4114 | 2000 | 0.4942 | 0.736 | 0.827 | 0.727 | 0.841 | 0.78 | 0.726 | 0.736 | 0.732 |
|
69 |
+
| 0.4882 | 0.5142 | 2500 | 0.4814 | 0.743 | 0.838 | 0.712 | 0.901 | 0.795 | 0.724 | 0.743 | 0.732 |
|
70 |
+
| 0.4734 | 0.6170 | 3000 | 0.4718 | 0.746 | 0.843 | 0.724 | 0.878 | 0.794 | 0.733 | 0.746 | 0.739 |
|
71 |
+
| 0.4659 | 0.7199 | 3500 | 0.4767 | 0.748 | 0.843 | 0.733 | 0.859 | 0.791 | 0.737 | 0.748 | 0.743 |
|
72 |
+
| 0.4632 | 0.8227 | 4000 | 0.4617 | 0.755 | 0.852 | 0.724 | 0.901 | 0.803 | 0.739 | 0.755 | 0.746 |
|
73 |
+
| 0.4602 | 0.9255 | 4500 | 0.4639 | 0.752 | 0.852 | 0.717 | 0.915 | 0.804 | 0.734 | 0.752 | 0.742 |
|
74 |
+
| 0.457 | 1.0284 | 5000 | 0.4613 | 0.752 | 0.85 | 0.729 | 0.881 | 0.798 | 0.739 | 0.752 | 0.745 |
|
75 |
+
| 0.4468 | 1.1312 | 5500 | 0.4541 | 0.757 | 0.855 | 0.731 | 0.891 | 0.803 | 0.743 | 0.757 | 0.75 |
|
76 |
+
| 0.4421 | 1.2341 | 6000 | 0.4591 | 0.755 | 0.853 | 0.727 | 0.892 | 0.801 | 0.74 | 0.755 | 0.747 |
|
77 |
+
| 0.4373 | 1.3369 | 6500 | 0.4537 | 0.759 | 0.856 | 0.739 | 0.874 | 0.801 | 0.748 | 0.759 | 0.753 |
|
78 |
+
| 0.4402 | 1.4397 | 7000 | 0.4552 | 0.755 | 0.855 | 0.74 | 0.863 | 0.797 | 0.745 | 0.755 | 0.751 |
|
79 |
+
| 0.4296 | 1.5426 | 7500 | 0.4545 | 0.76 | 0.857 | 0.742 | 0.87 | 0.801 | 0.749 | 0.76 | 0.755 |
|
80 |
+
| 0.4407 | 1.6454 | 8000 | 0.4458 | 0.762 | 0.86 | 0.742 | 0.877 | 0.804 | 0.751 | 0.762 | 0.757 |
|
81 |
+
| 0.4225 | 1.7483 | 8500 | 0.4472 | 0.761 | 0.86 | 0.735 | 0.889 | 0.805 | 0.748 | 0.761 | 0.754 |
|
82 |
+
| 0.4327 | 1.8511 | 9000 | 0.4485 | 0.758 | 0.858 | 0.741 | 0.867 | 0.799 | 0.747 | 0.758 | 0.753 |
|
83 |
+
| 0.4311 | 1.9539 | 9500 | 0.4479 | 0.76 | 0.859 | 0.742 | 0.869 | 0.801 | 0.749 | 0.76 | 0.755 |
|
84 |
+
| 0.4288 | 2.0568 | 10000 | 0.4527 | 0.761 | 0.859 | 0.742 | 0.873 | 0.802 | 0.75 | 0.761 | 0.756 |
|
85 |
+
| 0.4124 | 2.1596 | 10500 | 0.4477 | 0.762 | 0.861 | 0.736 | 0.891 | 0.806 | 0.749 | 0.762 | 0.756 |
|
86 |
+
| 0.4181 | 2.2624 | 11000 | 0.4569 | 0.759 | 0.857 | 0.741 | 0.87 | 0.8 | 0.748 | 0.759 | 0.754 |
|
87 |
+
| 0.4178 | 2.3653 | 11500 | 0.4469 | 0.762 | 0.861 | 0.741 | 0.879 | 0.804 | 0.751 | 0.762 | 0.757 |
|
88 |
+
| 0.4127 | 2.4681 | 12000 | 0.4448 | 0.764 | 0.863 | 0.742 | 0.881 | 0.806 | 0.753 | 0.764 | 0.759 |
|
89 |
+
| 0.419 | 2.5710 | 12500 | 0.4454 | 0.764 | 0.864 | 0.734 | 0.902 | 0.809 | 0.75 | 0.764 | 0.757 |
|
90 |
+
| 0.4232 | 2.6738 | 13000 | 0.4394 | 0.766 | 0.864 | 0.747 | 0.873 | 0.805 | 0.756 | 0.766 | 0.761 |
|
91 |
+
| 0.4226 | 2.7766 | 13500 | 0.4404 | 0.766 | 0.864 | 0.747 | 0.873 | 0.805 | 0.756 | 0.766 | 0.761 |
|
92 |
+
| 0.4196 | 2.8795 | 14000 | 0.4477 | 0.765 | 0.862 | 0.758 | 0.846 | 0.8 | 0.757 | 0.765 | 0.762 |
|
93 |
+
| 0.408 | 2.9823 | 14500 | 0.4497 | 0.763 | 0.862 | 0.745 | 0.871 | 0.803 | 0.752 | 0.763 | 0.758 |
|
94 |
+
| 0.4054 | 3.0852 | 15000 | 0.4404 | 0.765 | 0.865 | 0.749 | 0.865 | 0.803 | 0.755 | 0.765 | 0.76 |
|
95 |
+
| 0.4155 | 3.1880 | 15500 | 0.4466 | 0.764 | 0.863 | 0.74 | 0.885 | 0.806 | 0.752 | 0.764 | 0.758 |
|
96 |
+
| 0.4155 | 3.2908 | 16000 | 0.4417 | 0.765 | 0.864 | 0.744 | 0.879 | 0.806 | 0.754 | 0.765 | 0.76 |
|
97 |
+
| 0.4104 | 3.3937 | 16500 | 0.4407 | 0.766 | 0.866 | 0.742 | 0.887 | 0.808 | 0.755 | 0.766 | 0.761 |
|
98 |
+
| 0.4081 | 3.4965 | 17000 | 0.4406 | 0.765 | 0.866 | 0.753 | 0.859 | 0.802 | 0.756 | 0.765 | 0.762 |
|
99 |
+
| 0.4046 | 3.5993 | 17500 | 0.4384 | 0.768 | 0.868 | 0.742 | 0.891 | 0.81 | 0.756 | 0.768 | 0.762 |
|
100 |
+
| 0.4065 | 3.7022 | 18000 | 0.4443 | 0.766 | 0.866 | 0.742 | 0.888 | 0.808 | 0.754 | 0.766 | 0.76 |
|
101 |
+
| 0.4028 | 3.8050 | 18500 | 0.4438 | 0.768 | 0.866 | 0.746 | 0.882 | 0.808 | 0.757 | 0.768 | 0.763 |
|
102 |
+
| 0.4035 | 3.9079 | 19000 | 0.4453 | 0.766 | 0.865 | 0.753 | 0.862 | 0.804 | 0.758 | 0.766 | 0.763 |
|
103 |
+
| 0.4003 | 4.0107 | 19500 | 0.4426 | 0.767 | 0.865 | 0.75 | 0.87 | 0.806 | 0.757 | 0.767 | 0.763 |
|
104 |
+
| 0.4011 | 4.1135 | 20000 | 0.4423 | 0.767 | 0.867 | 0.741 | 0.892 | 0.81 | 0.755 | 0.767 | 0.761 |
|
105 |
+
| 0.3924 | 4.2164 | 20500 | 0.4394 | 0.768 | 0.867 | 0.75 | 0.874 | 0.807 | 0.758 | 0.768 | 0.764 |
|
106 |
+
| 0.4043 | 4.3192 | 21000 | 0.4421 | 0.768 | 0.867 | 0.744 | 0.887 | 0.809 | 0.757 | 0.768 | 0.762 |
|
107 |
+
| 0.395 | 4.4220 | 21500 | 0.4450 | 0.767 | 0.865 | 0.75 | 0.87 | 0.805 | 0.757 | 0.767 | 0.763 |
|
108 |
+
| 0.4072 | 4.5249 | 22000 | 0.4392 | 0.769 | 0.867 | 0.751 | 0.874 | 0.808 | 0.759 | 0.769 | 0.765 |
|
109 |
+
| 0.4055 | 4.6277 | 22500 | 0.4439 | 0.768 | 0.866 | 0.745 | 0.885 | 0.809 | 0.757 | 0.768 | 0.762 |
|
110 |
+
| 0.3987 | 4.7306 | 23000 | 0.4435 | 0.768 | 0.866 | 0.747 | 0.881 | 0.808 | 0.758 | 0.768 | 0.763 |
|
111 |
+
| 0.396 | 4.8334 | 23500 | 0.4430 | 0.768 | 0.867 | 0.745 | 0.885 | 0.809 | 0.757 | 0.768 | 0.763 |
|
112 |
+
| 0.4017 | 4.9362 | 24000 | 0.4421 | 0.769 | 0.867 | 0.745 | 0.887 | 0.81 | 0.757 | 0.769 | 0.763 |
|
113 |
+
|
114 |
+
|
115 |
+
### Framework versions
|
116 |
+
|
117 |
+
- Transformers 4.53.1
|
118 |
+
- Pytorch 2.6.0+cu124
|
119 |
+
- Datasets 2.14.4
|
120 |
+
- Tokenizers 0.21.2
|
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"BertForSequenceClassification"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0.1,
|
6 |
+
"classifier_dropout": null,
|
7 |
+
"hidden_act": "gelu",
|
8 |
+
"hidden_dropout_prob": 0.1,
|
9 |
+
"hidden_size": 768,
|
10 |
+
"id2label": {
|
11 |
+
"0": "fake",
|
12 |
+
"1": "real"
|
13 |
+
},
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 3072,
|
16 |
+
"label2id": {
|
17 |
+
"fake": 0,
|
18 |
+
"real": 1
|
19 |
+
},
|
20 |
+
"layer_norm_eps": 1e-12,
|
21 |
+
"max_position_embeddings": 512,
|
22 |
+
"model_type": "bert",
|
23 |
+
"num_attention_heads": 12,
|
24 |
+
"num_hidden_layers": 12,
|
25 |
+
"pad_token_id": 0,
|
26 |
+
"position_embedding_type": "absolute",
|
27 |
+
"problem_type": "single_label_classification",
|
28 |
+
"torch_dtype": "float32",
|
29 |
+
"transformers_version": "4.53.1",
|
30 |
+
"type_vocab_size": 2,
|
31 |
+
"use_cache": true,
|
32 |
+
"vocab_size": 28996
|
33 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2c50b70f9717f2fa6cc531cbc0b711317ad4e99632ddb4df37ca89cde4d7f3b
|
3 |
+
size 433270768
|
runs/Jul14_10-21-56_8141a392dcea/events.out.tfevents.1752488542.8141a392dcea.5512.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5a22a085118d9c2811e3f0d7e05599a2584741808293f579b3a00ce8868e510
|
3 |
+
size 48290
|
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 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"extra_special_tokens": {},
|
49 |
+
"mask_token": "[MASK]",
|
50 |
+
"model_max_length": 1000000000000000019884624838656,
|
51 |
+
"never_split": null,
|
52 |
+
"pad_token": "[PAD]",
|
53 |
+
"sep_token": "[SEP]",
|
54 |
+
"strip_accents": null,
|
55 |
+
"tokenize_chinese_chars": true,
|
56 |
+
"tokenizer_class": "BertTokenizer",
|
57 |
+
"unk_token": "[UNK]"
|
58 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c25413d499c775d41a49c798775d6800a3963be7d4472825320d3c836e749a16
|
3 |
+
size 5368
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|