Hugging Face's logo

Eurosmart
/
bert-qa-mash-covid

Question Answering
Transformers
TensorBoard
Safetensors
bert
nlp
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Eurosmart commited on
Commit
80de8c1
•
1 Parent(s): e748e58

Model save

Browse files
Files changed (4) hide show
  1. README.md +11 -60
  2. model.safetensors +1 -1
  3. runs/Jun04_08-52-05_cb7fc95f01c2/events.out.tfevents.1717491126.cb7fc95f01c2.34.0 +2 -2
  4. training_args.bin +1 -1
README.md CHANGED
@@ -1,9 +1,7 @@
1
  ---
2
  license: apache-2.0
3
- base_model: google/bigbird-roberta-base
4
  tags:
5
- - question-answering
6
- - nlp
7
  - generated_from_trainer
8
  model-index:
9
  - name: bert-qa-mash-covid
@@ -15,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # bert-qa-mash-covid
17
 
18
- This model is a fine-tuned version of [google/bigbird-roberta-base](https://huggingface.co/google/bigbird-roberta-base) on the mashqa_covid_dataset dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 4.1822
21
 
22
  ## Model description
23
 
@@ -37,67 +35,20 @@ More information needed
37
 
38
  The following hyperparameters were used during training:
39
  - learning_rate: 2e-05
40
- - train_batch_size: 16
41
- - eval_batch_size: 16
42
  - seed: 42
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
- - num_epochs: 50
46
 
47
  ### Training results
48
 
49
- | Training Loss | Epoch | Step | Validation Loss |
50
- |:-------------:|:-----:|:-----:|:---------------:|
51
- | 1.5553 | 1.0 | 657 | 1.0374 |
52
- | 1.0747 | 2.0 | 1314 | 0.9805 |
53
- | 0.8656 | 3.0 | 1971 | 1.0557 |
54
- | 0.5949 | 4.0 | 2628 | 1.1109 |
55
- | 0.4757 | 5.0 | 3285 | 1.1982 |
56
- | 0.3937 | 6.0 | 3942 | 1.3565 |
57
- | 0.2476 | 7.0 | 4599 | 1.4817 |
58
- | 0.2064 | 8.0 | 5256 | 1.5591 |
59
- | 0.191 | 9.0 | 5913 | 2.0118 |
60
- | 0.1382 | 10.0 | 6570 | 2.1637 |
61
- | 0.1161 | 11.0 | 7227 | 2.1896 |
62
- | 0.1066 | 12.0 | 7884 | 2.3879 |
63
- | 0.1017 | 13.0 | 8541 | 2.6023 |
64
- | 0.0901 | 14.0 | 9198 | 2.8120 |
65
- | 0.0859 | 15.0 | 9855 | 2.8291 |
66
- | 0.0666 | 16.0 | 10512 | 2.8947 |
67
- | 0.0598 | 17.0 | 11169 | 3.1198 |
68
- | 0.0459 | 18.0 | 11826 | 3.0020 |
69
- | 0.0533 | 19.0 | 12483 | 3.1257 |
70
- | 0.0546 | 20.0 | 13140 | 3.1757 |
71
- | 0.0487 | 21.0 | 13797 | 3.4253 |
72
- | 0.0424 | 22.0 | 14454 | 3.2998 |
73
- | 0.0465 | 23.0 | 15111 | 3.4184 |
74
- | 0.0298 | 24.0 | 15768 | 3.6026 |
75
- | 0.038 | 25.0 | 16425 | 3.7422 |
76
- | 0.032 | 26.0 | 17082 | 3.6208 |
77
- | 0.0247 | 27.0 | 17739 | 3.6113 |
78
- | 0.0283 | 28.0 | 18396 | 3.8404 |
79
- | 0.0237 | 29.0 | 19053 | 3.6326 |
80
- | 0.017 | 30.0 | 19710 | 3.8710 |
81
- | 0.0195 | 31.0 | 20367 | 3.8173 |
82
- | 0.0205 | 32.0 | 21024 | 3.7101 |
83
- | 0.0187 | 33.0 | 21681 | 3.8000 |
84
- | 0.0236 | 34.0 | 22338 | 3.7253 |
85
- | 0.0251 | 35.0 | 22995 | 3.7891 |
86
- | 0.0399 | 36.0 | 23652 | 3.8655 |
87
- | 0.0355 | 37.0 | 24309 | 3.7444 |
88
- | 0.0214 | 38.0 | 24966 | 3.9477 |
89
- | 0.0132 | 39.0 | 25623 | 4.1278 |
90
- | 0.019 | 40.0 | 26280 | 4.1814 |
91
- | 0.0227 | 41.0 | 26937 | 3.9744 |
92
- | 0.0161 | 42.0 | 27594 | 4.1047 |
93
- | 0.0165 | 43.0 | 28251 | 4.2342 |
94
- | 0.0162 | 44.0 | 28908 | 4.1003 |
95
- | 0.013 | 45.0 | 29565 | 4.2922 |
96
- | 0.0158 | 46.0 | 30222 | 4.1349 |
97
- | 0.0118 | 47.0 | 30879 | 4.1534 |
98
- | 0.0155 | 48.0 | 31536 | 4.1656 |
99
- | 0.0167 | 49.0 | 32193 | 4.1763 |
100
- | 0.0205 | 50.0 | 32850 | 4.1822 |
101
 
102
 
103
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
+ base_model: google-bert/bert-base-uncased
4
  tags:
 
 
5
  - generated_from_trainer
6
  model-index:
7
  - name: bert-qa-mash-covid
 
13
 
14
  # bert-qa-mash-covid
15
 
16
+ This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 1.2296
19
 
20
  ## Model description
21
 
 
35
 
36
  The following hyperparameters were used during training:
37
  - learning_rate: 2e-05
38
+ - train_batch_size: 32
39
+ - eval_batch_size: 32
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
+ - num_epochs: 3
44
 
45
  ### Training results
46
 
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-----:|:----:|:---------------:|
49
+ | No log | 1.0 | 329 | 1.3881 |
50
+ | 1.6542 | 2.0 | 658 | 1.3044 |
51
+ | 1.6542 | 3.0 | 987 | 1.2296 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
52
 
53
 
54
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1dda176ded5bfaf3d3e0eba1ff6bc79a0afa8aae5b7c6acae09f732b2926438a
3
  size 435596088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:608ef00b0c877479eb7c0fdaa0c772306cf38b6ab47b9613ad73a8baacae5bc1
3
  size 435596088
runs/Jun04_08-52-05_cb7fc95f01c2/events.out.tfevents.1717491126.cb7fc95f01c2.34.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e295b9568e02cb715443be84feb300bc5573a8ae248c19b50fc688257d518f3
3
- size 5100
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c58abe481e9b8e8b4c8a8869f77d2345791bd5a8ad6d0ff9c70b0108e84b42ac
3
+ size 5996
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:037c5f6e5aabc50f4b1f4501f4be8082424213021a4dbd5f17bb9a36d3237aa3
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae07ad3e4e783a8e9354ccd830320148ad3d7d294a472e783772073d2ad19dbc
3
  size 4920