Hugging Face's logo

Rocketknight1
/
bert-base-cased-finetuned-swag

Multiple Choice
Transformers
TensorFlow
TensorBoard
bert
generated_from_keras_callback
Inference Endpoints
Model card Files Metrics Community
1
Rocketknight1 HF staff commited on
Commit
30cdf01
·
1 Parent(s): cfa27f1

Training in progress epoch 0

Browse files
Files changed (4) hide show
  1. README.md +6 -7
  2. logs/train/events.out.tfevents.1643382535.matt-TRX40-AORUS-PRO-WIFI.31912.0.v2 +3 -0
  3. logs/validation/events.out.tfevents.1643383287.matt-TRX40-AORUS-PRO-WIFI.31912.1.v2 +3 -0
  4. tf_model.h5 +1 -1
README.md CHANGED
@@ -14,11 +14,11 @@ probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Train Loss: 0.3996
18
- - Train Sparse Categorical Accuracy: 0.8516
19
- - Validation Loss: 0.6312
20
- - Validation Sparse Categorical Accuracy: 0.7720
21
- - Epoch: 1
22
 
23
  ## Model description
24
 
@@ -44,8 +44,7 @@ The following hyperparameters were used during training:
44
 
45
  | Train Loss | Train Sparse Categorical Accuracy | Validation Loss | Validation Sparse Categorical Accuracy | Epoch |
46
  |:----------:|:---------------------------------:|:---------------:|:--------------------------------------:|:-----:|
47
- | 0.8890 | 0.6377 | 0.6206 | 0.7531 | 0 |
48
- | 0.3996 | 0.8516 | 0.6312 | 0.7720 | 1 |
49
 
50
 
51
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Train Loss: 0.8880
18
+ - Train Sparse Categorical Accuracy: 0.6390
19
+ - Validation Loss: 0.6278
20
+ - Validation Sparse Categorical Accuracy: 0.7548
21
+ - Epoch: 0
22
 
23
  ## Model description
24
 
 
44
 
45
  | Train Loss | Train Sparse Categorical Accuracy | Validation Loss | Validation Sparse Categorical Accuracy | Epoch |
46
  |:----------:|:---------------------------------:|:---------------:|:--------------------------------------:|:-----:|
47
+ | 0.8880 | 0.6390 | 0.6278 | 0.7548 | 0 |
 
48
 
49
 
50
  ### Framework versions
logs/train/events.out.tfevents.1643382535.matt-TRX40-AORUS-PRO-WIFI.31912.0.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c039511f104b678ee9e0b0053a654d80b7a152a3a351b1984693a9994230964c
3
+ size 2758048
logs/validation/events.out.tfevents.1643383287.matt-TRX40-AORUS-PRO-WIFI.31912.1.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:504fe37a17f548309fb66fd0a98d028a623187bc8b338e00e4e0bd9165d5dde1
3
+ size 394
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e63d1e5a7edc47809b9dc972367e37e8259f413f241eb06eb6841cca3f35d4a4
3
  size 433515860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d073be3764d0a4f90551d1df34ba687e93d1d77b22e75df5fb353ad5624e239d
3
  size 433515860