Zamoranesis
commited on
Commit
•
8d76a47
1
Parent(s):
2331e63
clinical_bert
Browse files- README.md +108 -0
- config.json +25 -0
- generation_config.json +5 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,108 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: emilyalsentzer/Bio_ClinicalBERT
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: clinical_bert
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# clinical_bert
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [emilyalsentzer/Bio_ClinicalBERT](https://huggingface.co/emilyalsentzer/Bio_ClinicalBERT) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 1.6020
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 0.0005
|
38 |
+
- train_batch_size: 64
|
39 |
+
- eval_batch_size: 64
|
40 |
+
- seed: 42
|
41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
+
- lr_scheduler_type: linear
|
43 |
+
- lr_scheduler_warmup_ratio: 0.1
|
44 |
+
- lr_scheduler_warmup_steps: 100
|
45 |
+
- training_steps: 5000
|
46 |
+
|
47 |
+
### Training results
|
48 |
+
|
49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
50 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
51 |
+
| No log | 0.78 | 100 | 1.9485 |
|
52 |
+
| No log | 1.56 | 200 | 1.8681 |
|
53 |
+
| No log | 2.34 | 300 | 1.8152 |
|
54 |
+
| No log | 3.12 | 400 | 1.7886 |
|
55 |
+
| 1.9285 | 3.91 | 500 | 1.7309 |
|
56 |
+
| 1.9285 | 4.69 | 600 | 1.6810 |
|
57 |
+
| 1.9285 | 5.47 | 700 | 1.7065 |
|
58 |
+
| 1.9285 | 6.25 | 800 | 1.7067 |
|
59 |
+
| 1.9285 | 7.03 | 900 | 1.7312 |
|
60 |
+
| 1.6644 | 7.81 | 1000 | 1.7006 |
|
61 |
+
| 1.6644 | 8.59 | 1100 | 1.6736 |
|
62 |
+
| 1.6644 | 9.38 | 1200 | 1.6846 |
|
63 |
+
| 1.6644 | 10.16 | 1300 | 1.6621 |
|
64 |
+
| 1.6644 | 10.94 | 1400 | 1.6381 |
|
65 |
+
| 1.5247 | 11.72 | 1500 | 1.6281 |
|
66 |
+
| 1.5247 | 12.5 | 1600 | 1.6605 |
|
67 |
+
| 1.5247 | 13.28 | 1700 | 1.6770 |
|
68 |
+
| 1.5247 | 14.06 | 1800 | 1.6666 |
|
69 |
+
| 1.5247 | 14.84 | 1900 | 1.6620 |
|
70 |
+
| 1.4334 | 15.62 | 2000 | 1.6677 |
|
71 |
+
| 1.4334 | 16.41 | 2100 | 1.6311 |
|
72 |
+
| 1.4334 | 17.19 | 2200 | 1.6743 |
|
73 |
+
| 1.4334 | 17.97 | 2300 | 1.6586 |
|
74 |
+
| 1.4334 | 18.75 | 2400 | 1.6086 |
|
75 |
+
| 1.3423 | 19.53 | 2500 | 1.6229 |
|
76 |
+
| 1.3423 | 20.31 | 2600 | 1.6475 |
|
77 |
+
| 1.3423 | 21.09 | 2700 | 1.6388 |
|
78 |
+
| 1.3423 | 21.88 | 2800 | 1.6275 |
|
79 |
+
| 1.3423 | 22.66 | 2900 | 1.6372 |
|
80 |
+
| 1.2712 | 23.44 | 3000 | 1.6345 |
|
81 |
+
| 1.2712 | 24.22 | 3100 | 1.6442 |
|
82 |
+
| 1.2712 | 25.0 | 3200 | 1.6864 |
|
83 |
+
| 1.2712 | 25.78 | 3300 | 1.6139 |
|
84 |
+
| 1.2712 | 26.56 | 3400 | 1.6161 |
|
85 |
+
| 1.215 | 27.34 | 3500 | 1.6491 |
|
86 |
+
| 1.215 | 28.12 | 3600 | 1.6442 |
|
87 |
+
| 1.215 | 28.91 | 3700 | 1.6409 |
|
88 |
+
| 1.215 | 29.69 | 3800 | 1.6539 |
|
89 |
+
| 1.215 | 30.47 | 3900 | 1.6052 |
|
90 |
+
| 1.1652 | 31.25 | 4000 | 1.6459 |
|
91 |
+
| 1.1652 | 32.03 | 4100 | 1.6362 |
|
92 |
+
| 1.1652 | 32.81 | 4200 | 1.6413 |
|
93 |
+
| 1.1652 | 33.59 | 4300 | 1.6377 |
|
94 |
+
| 1.1652 | 34.38 | 4400 | 1.6344 |
|
95 |
+
| 1.1213 | 35.16 | 4500 | 1.6406 |
|
96 |
+
| 1.1213 | 35.94 | 4600 | 1.6113 |
|
97 |
+
| 1.1213 | 36.72 | 4700 | 1.6410 |
|
98 |
+
| 1.1213 | 37.5 | 4800 | 1.6378 |
|
99 |
+
| 1.1213 | 38.28 | 4900 | 1.6341 |
|
100 |
+
| 1.0939 | 39.06 | 5000 | 1.6020 |
|
101 |
+
|
102 |
+
|
103 |
+
### Framework versions
|
104 |
+
|
105 |
+
- Transformers 4.33.2
|
106 |
+
- Pytorch 2.0.1+cu118
|
107 |
+
- Datasets 2.14.5
|
108 |
+
- Tokenizers 0.13.3
|
config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "emilyalsentzer/Bio_ClinicalBERT",
|
3 |
+
"architectures": [
|
4 |
+
"BertForMaskedLM"
|
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 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 3072,
|
13 |
+
"layer_norm_eps": 1e-12,
|
14 |
+
"max_position_embeddings": 512,
|
15 |
+
"model_type": "bert",
|
16 |
+
"num_attention_heads": 12,
|
17 |
+
"num_hidden_layers": 12,
|
18 |
+
"pad_token_id": 0,
|
19 |
+
"position_embedding_type": "absolute",
|
20 |
+
"torch_dtype": "float32",
|
21 |
+
"transformers_version": "4.33.2",
|
22 |
+
"type_vocab_size": 2,
|
23 |
+
"use_cache": true,
|
24 |
+
"vocab_size": 28996
|
25 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"pad_token_id": 0,
|
4 |
+
"transformers_version": "4.33.2"
|
5 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac6d98ea406de37837e0126d5c928e2a207cfaf59079aa3830cee38f38b22900
|
3 |
+
size 433432181
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dabd44242aee2c7ec5126a2da6b2a51f5c357bd03d600e65a5247f88862fe69a
|
3 |
+
size 4027
|