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
db97f6f
路
verified 路
1 Parent(s): f754692

End of training

Browse files
Files changed (3) hide show
  1. README.md +7 -12
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -18,7 +18,7 @@ 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: 1.1835
22
  - Exact: 79.4118
23
  - F1: 82.5210
24
  - Total: 68
@@ -62,17 +62,12 @@ 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
- | No log | 5.0 | 10 | 0.9865 | 79.4118 | 81.8301 | 68 | 79.4118 | 81.8301 | 68 | 79.4118 | 0.0 | 81.8301 | 0.0 |
66
- | No log | 10.0 | 20 | 0.9599 | 79.4118 | 82.4370 | 68 | 79.4118 | 82.4370 | 68 | 79.4118 | 0.0 | 82.4370 | 0.0 |
67
- | No log | 15.0 | 30 | 1.0088 | 77.9412 | 82.2269 | 68 | 77.9412 | 82.2269 | 68 | 77.9412 | 0.0 | 82.2269 | 0.0 |
68
- | No log | 20.0 | 40 | 1.0701 | 77.9412 | 82.2269 | 68 | 77.9412 | 82.2269 | 68 | 77.9412 | 0.0 | 82.2269 | 0.0 |
69
- | No log | 25.0 | 50 | 1.1151 | 77.9412 | 82.2269 | 68 | 77.9412 | 82.2269 | 68 | 77.9412 | 0.0 | 82.2269 | 0.0 |
70
- | No log | 30.0 | 60 | 1.1411 | 79.4118 | 82.5210 | 68 | 79.4118 | 82.5210 | 68 | 79.4118 | 0.0 | 82.5210 | 0.0 |
71
- | No log | 35.0 | 70 | 1.1566 | 79.4118 | 82.5210 | 68 | 79.4118 | 82.5210 | 68 | 79.4118 | 0.0 | 82.5210 | 0.0 |
72
- | No log | 40.0 | 80 | 1.1653 | 79.4118 | 82.5210 | 68 | 79.4118 | 82.5210 | 68 | 79.4118 | 0.0 | 82.5210 | 0.0 |
73
- | No log | 45.0 | 90 | 1.1723 | 79.4118 | 82.5210 | 68 | 79.4118 | 82.5210 | 68 | 79.4118 | 0.0 | 82.5210 | 0.0 |
74
- | 0.1023 | 50.0 | 100 | 1.1777 | 79.4118 | 82.5210 | 68 | 79.4118 | 82.5210 | 68 | 79.4118 | 0.0 | 82.5210 | 0.0 |
75
- | 0.1023 | 55.0 | 110 | 1.1835 | 79.4118 | 82.5210 | 68 | 79.4118 | 82.5210 | 68 | 79.4118 | 0.0 | 82.5210 | 0.0 |
76
 
77
 
78
  ### 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: 1.4612
22
  - Exact: 79.4118
23
  - F1: 82.5210
24
  - Total: 68
 
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
+ | 0.0005 | 5.0 | 10 | 1.3052 | 79.4118 | 82.5210 | 68 | 79.4118 | 82.5210 | 68 | 79.4118 | 0.0 | 82.5210 | 0.0 |
66
+ | 0.0002 | 10.0 | 20 | 1.3620 | 79.4118 | 82.5210 | 68 | 79.4118 | 82.5210 | 68 | 79.4118 | 0.0 | 82.5210 | 0.0 |
67
+ | 0.0001 | 15.0 | 30 | 1.3976 | 79.4118 | 82.5210 | 68 | 79.4118 | 82.5210 | 68 | 79.4118 | 0.0 | 82.5210 | 0.0 |
68
+ | 0.0001 | 20.0 | 40 | 1.4235 | 79.4118 | 82.5210 | 68 | 79.4118 | 82.5210 | 68 | 79.4118 | 0.0 | 82.5210 | 0.0 |
69
+ | 0.0001 | 25.0 | 50 | 1.4453 | 79.4118 | 82.5210 | 68 | 79.4118 | 82.5210 | 68 | 79.4118 | 0.0 | 82.5210 | 0.0 |
70
+ | 0.0001 | 30.0 | 60 | 1.4612 | 79.4118 | 82.5210 | 68 | 79.4118 | 82.5210 | 68 | 79.4118 | 0.0 | 82.5210 | 0.0 |
 
 
 
 
 
71
 
72
 
73
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4644259a633cc147dfc91d9f71246deb20b2937614fcd99b4546ada61b0f6f48
3
  size 435596088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:266863d39d89129a28180845041c60d856072759dc00a33920111cd0ab849f81
3
  size 435596088
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:72f64bfd676dfe8cf2d1eec690181a1551c579914d53580d914c56170660f6b7
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ee3c1ea40528eca60ecb183df5d2df3ddd5b90693a16ab18abcbff9d672ba59
3
  size 5304