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
343aa1f
•
1 Parent(s): 2ebc520

Training in progress epoch 219

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: 0.8133
18
- - Train Accuracy: 0.1192
19
- - Validation Loss: 0.8491
20
- - Validation Accuracy: 0.1202
21
- - Epoch: 218
22
 
23
  ## Model description
24
 
@@ -263,6 +263,7 @@ The following hyperparameters were used during training:
263
  | 0.8149 | 0.1192 | 0.8286 | 0.1191 | 216 |
264
  | 0.8141 | 0.1193 | 0.8389 | 0.1202 | 217 |
265
  | 0.8133 | 0.1192 | 0.8491 | 0.1202 | 218 |
 
266
 
267
 
268
  ### 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: 0.8127
18
+ - Train Accuracy: 0.1193
19
+ - Validation Loss: 0.8730
20
+ - Validation Accuracy: 0.1185
21
+ - Epoch: 219
22
 
23
  ## Model description
24
 
 
263
  | 0.8149 | 0.1192 | 0.8286 | 0.1191 | 216 |
264
  | 0.8141 | 0.1193 | 0.8389 | 0.1202 | 217 |
265
  | 0.8133 | 0.1192 | 0.8491 | 0.1202 | 218 |
266
+ | 0.8127 | 0.1193 | 0.8730 | 0.1185 | 219 |
267
 
268
 
269
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:55f3fdd96819d158237ceb46a1441aebb1dab9cf316f4c7943b768815eb092f2
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad2ffb89811702d350d3766f0f947d0c582807291d89bd9bfffe4a58a7bc8c9e
3
  size 499741936