Hugging Face's logo

leomaurodesenv
/
bert-basketball-qa

Question Answering
Transformers
Safetensors
bert
Generated from Trainer
Model card Files
xet
 Community
leomaurodesenv commited on
Commit
35fffb4
路
verified 路
1 Parent(s): 18b4b05

End of training

Browse files
Files changed (3) hide show
  1. README.md +18 -13
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -18,16 +18,16 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [deepset/bert-base-uncased-squad2](https://huggingface.co/deepset/bert-base-uncased-squad2) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 1.8979
22
- - Exact: 76.4706
23
- - F1: 80.4599
24
  - Total: 68
25
- - Hasans Exact: 76.4706
26
- - Hasans F1: 80.4599
27
  - Hasans Total: 68
28
- - Best Exact: 76.4706
29
  - Best Exact Thresh: 0.0
30
- - Best F1: 80.4599
31
  - Best F1 Thresh: 0.0
32
 
33
  ## Model description
@@ -62,12 +62,17 @@ The following hyperparameters were used during training:
62
 
63
  | Training Loss | Epoch | Step | Validation Loss | Exact | F1 | Total | Hasans Exact | Hasans F1 | Hasans Total | Best Exact | Best Exact Thresh | Best F1 | Best F1 Thresh |
64
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-----:|:------------:|:---------:|:------------:|:----------:|:-----------------:|:-------:|:--------------:|
65
- | 0.0 | 5.0 | 10 | 1.5949 | 79.4118 | 82.5210 | 68 | 79.4118 | 82.5210 | 68 | 79.4118 | 0.0 | 82.5210 | 0.0 |
66
- | 0.0 | 10.0 | 20 | 1.7120 | 79.4118 | 82.5210 | 68 | 79.4118 | 82.5210 | 68 | 79.4118 | 0.0 | 82.5210 | 0.0 |
67
- | 0.0 | 15.0 | 30 | 1.7751 | 77.9412 | 81.8908 | 68 | 77.9412 | 81.8908 | 68 | 77.9412 | 0.0 | 81.8908 | 0.0 |
68
- | 0.0 | 20.0 | 40 | 1.8369 | 76.4706 | 80.4599 | 68 | 76.4706 | 80.4599 | 68 | 76.4706 | 0.0 | 80.4599 | 0.0 |
69
- | 0.0 | 25.0 | 50 | 1.8761 | 76.4706 | 80.4599 | 68 | 76.4706 | 80.4599 | 68 | 76.4706 | 0.0 | 80.4599 | 0.0 |
70
- | 0.0 | 30.0 | 60 | 1.8979 | 76.4706 | 80.4599 | 68 | 76.4706 | 80.4599 | 68 | 76.4706 | 0.0 | 80.4599 | 0.0 |
 
 
 
 
 
71
 
72
 
73
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [deepset/bert-base-uncased-squad2](https://huggingface.co/deepset/bert-base-uncased-squad2) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 2.1374
22
+ - Exact: 77.9412
23
+ - F1: 81.9305
24
  - Total: 68
25
+ - Hasans Exact: 77.9412
26
+ - Hasans F1: 81.9305
27
  - Hasans Total: 68
28
+ - Best Exact: 77.9412
29
  - Best Exact Thresh: 0.0
30
+ - Best F1: 81.9305
31
  - Best F1 Thresh: 0.0
32
 
33
  ## Model description
 
62
 
63
  | Training Loss | Epoch | Step | Validation Loss | Exact | F1 | Total | Hasans Exact | Hasans F1 | Hasans Total | Best Exact | Best Exact Thresh | Best F1 | Best F1 Thresh |
64
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-----:|:------------:|:---------:|:------------:|:----------:|:-----------------:|:-------:|:--------------:|
65
+ | 0.0 | 5.0 | 10 | 1.9354 | 77.9412 | 81.9305 | 68 | 77.9412 | 81.9305 | 68 | 77.9412 | 0.0 | 81.9305 | 0.0 |
66
+ | 0.0 | 10.0 | 20 | 1.9762 | 77.9412 | 81.9305 | 68 | 77.9412 | 81.9305 | 68 | 77.9412 | 0.0 | 81.9305 | 0.0 |
67
+ | 0.0 | 15.0 | 30 | 2.0047 | 77.9412 | 81.9305 | 68 | 77.9412 | 81.9305 | 68 | 77.9412 | 0.0 | 81.9305 | 0.0 |
68
+ | 0.0 | 20.0 | 40 | 2.0367 | 77.9412 | 81.9305 | 68 | 77.9412 | 81.9305 | 68 | 77.9412 | 0.0 | 81.9305 | 0.0 |
69
+ | 0.0 | 25.0 | 50 | 2.0600 | 77.9412 | 81.9305 | 68 | 77.9412 | 81.9305 | 68 | 77.9412 | 0.0 | 81.9305 | 0.0 |
70
+ | 0.0 | 30.0 | 60 | 2.0772 | 77.9412 | 81.9305 | 68 | 77.9412 | 81.9305 | 68 | 77.9412 | 0.0 | 81.9305 | 0.0 |
71
+ | 0.0 | 35.0 | 70 | 2.0958 | 77.9412 | 81.9305 | 68 | 77.9412 | 81.9305 | 68 | 77.9412 | 0.0 | 81.9305 | 0.0 |
72
+ | 0.0 | 40.0 | 80 | 2.1096 | 77.9412 | 81.9305 | 68 | 77.9412 | 81.9305 | 68 | 77.9412 | 0.0 | 81.9305 | 0.0 |
73
+ | 0.0 | 45.0 | 90 | 2.1211 | 77.9412 | 81.9305 | 68 | 77.9412 | 81.9305 | 68 | 77.9412 | 0.0 | 81.9305 | 0.0 |
74
+ | 0.0 | 50.0 | 100 | 2.1294 | 77.9412 | 81.9305 | 68 | 77.9412 | 81.9305 | 68 | 77.9412 | 0.0 | 81.9305 | 0.0 |
75
+ | 0.0 | 55.0 | 110 | 2.1374 | 77.9412 | 81.9305 | 68 | 77.9412 | 81.9305 | 68 | 77.9412 | 0.0 | 81.9305 | 0.0 |
76
 
77
 
78
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed097575c33b5d6f3b211af69b08b8234cf34a1dbd22e3a7702fc340988307eb
3
  size 435596088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bf7fdb4f875a1bcbde6ee0cc021d2b53d1915ac29d048d2cf855ad0e301206a
3
  size 435596088
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e12acceccd5a28c86fd3b82e108b226f884d0d54e4008e12d88f61b388d9035
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eef0a7eec07bb0beb07903497b38c9bccf39d414fc95a191bb3565927cbab5bf
3
  size 5304