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
47e8862
•
1 Parent(s): 17ac284

Training in progress epoch 108

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: 0.9515
18
  - Train Accuracy: 0.1158
19
- - Validation Loss: 0.9434
20
- - Validation Accuracy: 0.1161
21
- - Epoch: 107
22
 
23
  ## Model description
24
 
@@ -152,6 +152,7 @@ The following hyperparameters were used during training:
152
  | 0.9561 | 0.1157 | 0.9346 | 0.1173 | 105 |
153
  | 0.9537 | 0.1157 | 0.9331 | 0.1168 | 106 |
154
  | 0.9515 | 0.1158 | 0.9434 | 0.1161 | 107 |
 
155
 
156
 
157
  ### 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: 0.9488
18
  - Train Accuracy: 0.1158
19
+ - Validation Loss: 0.9131
20
+ - Validation Accuracy: 0.1176
21
+ - Epoch: 108
22
 
23
  ## Model description
24
 
 
152
  | 0.9561 | 0.1157 | 0.9346 | 0.1173 | 105 |
153
  | 0.9537 | 0.1157 | 0.9331 | 0.1168 | 106 |
154
  | 0.9515 | 0.1158 | 0.9434 | 0.1161 | 107 |
155
+ | 0.9488 | 0.1158 | 0.9131 | 0.1176 | 108 |
156
 
157
 
158
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cef53572f082fbc5cfe81056f8a160b7361ab082f356e0277cd4cf099594f49c
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23b29e85515b1088004c36a903673b55edac3a17d576ce288d8147808c83dacb
3
  size 499741936