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
d1150f8
·
1 Parent(s): 15312f9

Training in progress epoch 68

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: 1.0984
18
- - Train Accuracy: 0.1121
19
- - Validation Loss: 1.0366
20
- - Validation Accuracy: 0.1139
21
- - Epoch: 67
22
 
23
  ## Model description
24
 
@@ -112,6 +112,7 @@ The following hyperparameters were used during training:
112
  | 1.1114 | 0.1118 | 1.0474 | 0.1138 | 65 |
113
  | 1.1036 | 0.1120 | 1.0703 | 0.1134 | 66 |
114
  | 1.0984 | 0.1121 | 1.0366 | 0.1139 | 67 |
 
115
 
116
 
117
  ### 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: 1.0931
18
+ - Train Accuracy: 0.1122
19
+ - Validation Loss: 1.0513
20
+ - Validation Accuracy: 0.1134
21
+ - Epoch: 68
22
 
23
  ## Model description
24
 
 
112
  | 1.1114 | 0.1118 | 1.0474 | 0.1138 | 65 |
113
  | 1.1036 | 0.1120 | 1.0703 | 0.1134 | 66 |
114
  | 1.0984 | 0.1121 | 1.0366 | 0.1139 | 67 |
115
+ | 1.0931 | 0.1122 | 1.0513 | 0.1134 | 68 |
116
 
117
 
118
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b9e7b8b743125dd65d203c5f1e9e7b9d3978df2aa9f85114c1322680b4d6bcc3
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6952e0f76778f094fbc641326a83946dd034cab31201a301aa9426a3a223f72
3
  size 499741936