Zamoranesis commited on
Commit
8d76a47
1 Parent(s): 2331e63

clinical_bert

Browse files
Files changed (5) hide show
  1. README.md +108 -0
  2. config.json +25 -0
  3. generation_config.json +5 -0
  4. pytorch_model.bin +3 -0
  5. 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