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
24c845e
•
1 Parent(s): e8e81fc

Training in progress epoch 228

Browse files
Files changed (2) hide show
  1. README.md +6 -5
  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: 0.8065
18
- - Train Accuracy: 0.1195
19
- - Validation Loss: 0.8379
20
- - Validation Accuracy: 0.1202
21
- - Epoch: 227
22
 
23
  ## Model description
24
 
@@ -272,6 +272,7 @@ The following hyperparameters were used during training:
272
  | 0.8081 | 0.1194 | 0.8311 | 0.1184 | 225 |
273
  | 0.8081 | 0.1194 | 0.8413 | 0.1198 | 226 |
274
  | 0.8065 | 0.1195 | 0.8379 | 0.1202 | 227 |
 
275
 
276
 
277
  ### 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: 0.8064
18
+ - Train Accuracy: 0.1194
19
+ - Validation Loss: 0.8398
20
+ - Validation Accuracy: 0.1196
21
+ - Epoch: 228
22
 
23
  ## Model description
24
 
 
272
  | 0.8081 | 0.1194 | 0.8311 | 0.1184 | 225 |
273
  | 0.8081 | 0.1194 | 0.8413 | 0.1198 | 226 |
274
  | 0.8065 | 0.1195 | 0.8379 | 0.1202 | 227 |
275
+ | 0.8064 | 0.1194 | 0.8398 | 0.1196 | 228 |
276
 
277
 
278
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aebf069d7a088cdde81c8f9ed13cd73a160658ea1a463a3064da8e7cd65fc9ef
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c4e91932f4e9b765d9bd2e66199b82e8bd200bb2ece0c263a851da2d188c089
3
  size 499741936