Hugging Face's logo

Zemulax
/
masked-lm-tpu

Fill-Mask
Transformers
TensorFlow
roberta
generated_from_keras_callback
Inference Endpoints
Model card Files Community
Zemulax commited on
Commit
2338dbd
·
1 Parent(s): c22c8c7

Training in progress epoch 54

Browse files
Files changed (2) hide show
  1. README.md +6 -4
  2. 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 [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Train Loss: 8.3428
18
- - Train Accuracy: 0.0235
19
- - Validation Loss: 8.3540
20
  - Validation Accuracy: 0.0221
21
- - Epoch: 52
22
 
23
  ## Model description
24
 
@@ -97,6 +97,8 @@ The following hyperparameters were used during training:
97
  | 8.4005 | 0.0229 | 8.3768 | 0.0218 | 50 |
98
  | 8.3583 | 0.0235 | 8.3470 | 0.0224 | 51 |
99
  | 8.3428 | 0.0235 | 8.3540 | 0.0221 | 52 |
 
 
100
 
101
 
102
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Train Loss: 8.3551
18
+ - Train Accuracy: 0.0231
19
+ - Validation Loss: 8.3382
20
  - Validation Accuracy: 0.0221
21
+ - Epoch: 54
22
 
23
  ## Model description
24
 
 
97
  | 8.4005 | 0.0229 | 8.3768 | 0.0218 | 50 |
98
  | 8.3583 | 0.0235 | 8.3470 | 0.0224 | 51 |
99
  | 8.3428 | 0.0235 | 8.3540 | 0.0221 | 52 |
100
+ | 8.3491 | 0.0231 | 8.3201 | 0.0225 | 53 |
101
+ | 8.3551 | 0.0231 | 8.3382 | 0.0221 | 54 |
102
 
103
 
104
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a1936c7cedfe6e1fdf1ec410e1828231192130be129dfb0c9afec455dda1c80
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a80b9e1511e87fd0a26ba5776e4f1cefa7fced130e366795d35bdff0e446814
3
  size 499741936