Hugging Face's logo

tf-tpu
/
roberta-base-epochs-500-no-wd

Fill-Mask
Transformers
TensorFlow
roberta
generated_from_keras_callback
Inference Endpoints
Model card Files Community
2
sayakpaul HF staff commited on
Commit
13b3574
•
1 Parent(s): a3e0a6d

Training in progress epoch 423

Browse files
Files changed (2) hide show
  1. README.md +5 -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: 0.7235
18
  - Train Accuracy: 0.1216
19
- - Validation Loss: 0.7949
20
- - Validation Accuracy: 0.1191
21
- - Epoch: 422
22
 
23
  ## Model description
24
 
@@ -467,6 +467,7 @@ The following hyperparameters were used during training:
467
  | 0.7238 | 0.1217 | 0.7930 | 0.1216 | 420 |
468
  | 0.7231 | 0.1216 | 0.7935 | 0.1210 | 421 |
469
  | 0.7235 | 0.1216 | 0.7949 | 0.1191 | 422 |
 
470
 
471
 
472
  ### 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: 0.7226
18
  - Train Accuracy: 0.1216
19
+ - Validation Loss: 0.7925
20
+ - Validation Accuracy: 0.1203
21
+ - Epoch: 423
22
 
23
  ## Model description
24
 
 
467
  | 0.7238 | 0.1217 | 0.7930 | 0.1216 | 420 |
468
  | 0.7231 | 0.1216 | 0.7935 | 0.1210 | 421 |
469
  | 0.7235 | 0.1216 | 0.7949 | 0.1191 | 422 |
470
+ | 0.7226 | 0.1216 | 0.7925 | 0.1203 | 423 |
471
 
472
 
473
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca8677b16d64fca193d2a21ae5cacfdc6fde6a8406d587a2e3abe6a6a98b6915
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ee9fbd81d61cf9ac7110c661ceeafb90a9f752f20ffbdc95d498ca69ed3af45
3
  size 499741936