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
381c399
•
1 Parent(s): a6e3f7d

Training in progress epoch 195

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: 0.8322
18
  - Train Accuracy: 0.1188
19
- - Validation Loss: 0.8574
20
- - Validation Accuracy: 0.1199
21
- - Epoch: 194
22
 
23
  ## Model description
24
 
@@ -239,6 +239,7 @@ The following hyperparameters were used during training:
239
  | 0.8334 | 0.1187 | 0.8486 | 0.1187 | 192 |
240
  | 0.8325 | 0.1188 | 0.8535 | 0.1182 | 193 |
241
  | 0.8322 | 0.1188 | 0.8574 | 0.1199 | 194 |
 
242
 
243
 
244
  ### 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: 0.8314
18
  - Train Accuracy: 0.1188
19
+ - Validation Loss: 0.8472
20
+ - Validation Accuracy: 0.1202
21
+ - Epoch: 195
22
 
23
  ## Model description
24
 
 
239
  | 0.8334 | 0.1187 | 0.8486 | 0.1187 | 192 |
240
  | 0.8325 | 0.1188 | 0.8535 | 0.1182 | 193 |
241
  | 0.8322 | 0.1188 | 0.8574 | 0.1199 | 194 |
242
+ | 0.8314 | 0.1188 | 0.8472 | 0.1202 | 195 |
243
 
244
 
245
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:512b48d349299413a31c900c95e1d78e33b0b6ee6992711b77aaa9e9e355bc1c
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e5af8a37b29996216df07e8ca957fbdfa92140fa51646df6cee4d3c93b05961
3
  size 499741936