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
a206ac9
•
1 Parent(s): 632d6bb

Training in progress epoch 119

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: 0.9287
18
  - Train Accuracy: 0.1163
19
- - Validation Loss: 0.9243
20
- - Validation Accuracy: 0.1169
21
- - Epoch: 118
22
 
23
  ## Model description
24
 
@@ -163,6 +163,7 @@ The following hyperparameters were used during training:
163
  | 0.9317 | 0.1163 | 0.9277 | 0.1169 | 116 |
164
  | 0.9295 | 0.1164 | 0.9292 | 0.1169 | 117 |
165
  | 0.9287 | 0.1163 | 0.9243 | 0.1169 | 118 |
 
166
 
167
 
168
  ### 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: 0.9266
18
  - Train Accuracy: 0.1163
19
+ - Validation Loss: 0.8892
20
+ - Validation Accuracy: 0.1170
21
+ - Epoch: 119
22
 
23
  ## Model description
24
 
 
163
  | 0.9317 | 0.1163 | 0.9277 | 0.1169 | 116 |
164
  | 0.9295 | 0.1164 | 0.9292 | 0.1169 | 117 |
165
  | 0.9287 | 0.1163 | 0.9243 | 0.1169 | 118 |
166
+ | 0.9266 | 0.1163 | 0.8892 | 0.1170 | 119 |
167
 
168
 
169
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb1b9ff95614e64246a7edbbbd81082342e3f83027782dad050a52f2160f7e93
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49c04c116bc6f8e6430924e127cf8bfc771b9b85a7bc6a90aaf1ff6d4b68f14c
3
  size 499741936