Hugging Face's logo

pythonist
/
distilbert-base-uncased-finetuned-PubmedQA

Question Answering
Transformers
PyTorch
TensorBoard
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
2
pythonist commited on
Commit
96c8426
路
1 Parent(s): baf4d14

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +105 -0
README.md ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: distilbert-base-uncased-finetuned-PubmedQA
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # distilbert-base-uncased-finetuned-PubmedQA
14
+
15
+ This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 4.2735
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 2e-05
37
+ - train_batch_size: 16
38
+ - eval_batch_size: 16
39
+ - seed: 42
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: linear
42
+ - num_epochs: 50
43
+
44
+ ### Training results
45
+
46
+ | Training Loss | Epoch | Step | Validation Loss |
47
+ |:-------------:|:-----:|:----:|:---------------:|
48
+ | No log | 1.0 | 21 | 3.9141 |
49
+ | No log | 2.0 | 42 | 3.3827 |
50
+ | No log | 3.0 | 63 | 3.3102 |
51
+ | No log | 4.0 | 84 | 3.3278 |
52
+ | No log | 5.0 | 105 | 3.2799 |
53
+ | No log | 6.0 | 126 | 3.2335 |
54
+ | No log | 7.0 | 147 | 3.2149 |
55
+ | No log | 8.0 | 168 | 3.3183 |
56
+ | No log | 9.0 | 189 | 3.2546 |
57
+ | No log | 10.0 | 210 | 3.3986 |
58
+ | No log | 11.0 | 231 | 3.4373 |
59
+ | No log | 12.0 | 252 | 3.4295 |
60
+ | No log | 13.0 | 273 | 3.3938 |
61
+ | No log | 14.0 | 294 | 3.5758 |
62
+ | No log | 15.0 | 315 | 3.5537 |
63
+ | No log | 16.0 | 336 | 3.5703 |
64
+ | No log | 17.0 | 357 | 3.6736 |
65
+ | No log | 18.0 | 378 | 3.7491 |
66
+ | No log | 19.0 | 399 | 3.5866 |
67
+ | No log | 20.0 | 420 | 3.6808 |
68
+ | No log | 21.0 | 441 | 3.7708 |
69
+ | No log | 22.0 | 462 | 3.7708 |
70
+ | No log | 23.0 | 483 | 3.8242 |
71
+ | 1.8524 | 24.0 | 504 | 3.9128 |
72
+ | 1.8524 | 25.0 | 525 | 4.0270 |
73
+ | 1.8524 | 26.0 | 546 | 3.8988 |
74
+ | 1.8524 | 27.0 | 567 | 3.9395 |
75
+ | 1.8524 | 28.0 | 588 | 3.8722 |
76
+ | 1.8524 | 29.0 | 609 | 3.9539 |
77
+ | 1.8524 | 30.0 | 630 | 4.0016 |
78
+ | 1.8524 | 31.0 | 651 | 4.0417 |
79
+ | 1.8524 | 32.0 | 672 | 4.1438 |
80
+ | 1.8524 | 33.0 | 693 | 4.0106 |
81
+ | 1.8524 | 34.0 | 714 | 4.0280 |
82
+ | 1.8524 | 35.0 | 735 | 4.0046 |
83
+ | 1.8524 | 36.0 | 756 | 4.1615 |
84
+ | 1.8524 | 37.0 | 777 | 4.1172 |
85
+ | 1.8524 | 38.0 | 798 | 4.1556 |
86
+ | 1.8524 | 39.0 | 819 | 4.1488 |
87
+ | 1.8524 | 40.0 | 840 | 4.1369 |
88
+ | 1.8524 | 41.0 | 861 | 4.2727 |
89
+ | 1.8524 | 42.0 | 882 | 4.1593 |
90
+ | 1.8524 | 43.0 | 903 | 4.1426 |
91
+ | 1.8524 | 44.0 | 924 | 4.1823 |
92
+ | 1.8524 | 45.0 | 945 | 4.2314 |
93
+ | 1.8524 | 46.0 | 966 | 4.2269 |
94
+ | 1.8524 | 47.0 | 987 | 4.2228 |
95
+ | 0.3824 | 48.0 | 1008 | 4.2576 |
96
+ | 0.3824 | 49.0 | 1029 | 4.2784 |
97
+ | 0.3824 | 50.0 | 1050 | 4.2735 |
98
+
99
+
100
+ ### Framework versions
101
+
102
+ - Transformers 4.23.1
103
+ - Pytorch 1.12.1+cu113
104
+ - Datasets 2.6.1
105
+ - Tokenizers 0.13.1