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
d66f452
•
1 Parent(s): 7bf16ff

Training in progress epoch 188

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: 0.8378
18
  - Train Accuracy: 0.1186
19
- - Validation Loss: 0.8628
20
- - Validation Accuracy: 0.1185
21
- - Epoch: 187
22
 
23
  ## Model description
24
 
@@ -232,6 +232,7 @@ The following hyperparameters were used during training:
232
  | 0.8391 | 0.1186 | 0.8560 | 0.1188 | 185 |
233
  | 0.8396 | 0.1186 | 0.8413 | 0.1188 | 186 |
234
  | 0.8378 | 0.1186 | 0.8628 | 0.1185 | 187 |
 
235
 
236
 
237
  ### 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: 0.8374
18
  - Train Accuracy: 0.1186
19
+ - Validation Loss: 0.8374
20
+ - Validation Accuracy: 0.1195
21
+ - Epoch: 188
22
 
23
  ## Model description
24
 
 
232
  | 0.8391 | 0.1186 | 0.8560 | 0.1188 | 185 |
233
  | 0.8396 | 0.1186 | 0.8413 | 0.1188 | 186 |
234
  | 0.8378 | 0.1186 | 0.8628 | 0.1185 | 187 |
235
+ | 0.8374 | 0.1186 | 0.8374 | 0.1195 | 188 |
236
 
237
 
238
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08877a3dbae72595f961eb9275fa4d5161930463edd11b370d6de1dd57091345
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eab8b2acb4b288c648ac15ec729563a87abf15cd801374c623d000441669a02e
3
  size 499741936