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
4892895
·
1 Parent(s): b182b10

Training in progress epoch 94

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: 0.9884
18
  - Train Accuracy: 0.1149
19
- - Validation Loss: 0.9546
20
- - Validation Accuracy: 0.1156
21
- - Epoch: 93
22
 
23
  ## Model description
24
 
@@ -138,6 +138,7 @@ The following hyperparameters were used during training:
138
  | 0.9947 | 0.1147 | 0.9570 | 0.1157 | 91 |
139
  | 0.9921 | 0.1148 | 0.9360 | 0.1166 | 92 |
140
  | 0.9884 | 0.1149 | 0.9546 | 0.1156 | 93 |
 
141
 
142
 
143
  ### 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: 0.9851
18
  - Train Accuracy: 0.1149
19
+ - Validation Loss: 0.9536
20
+ - Validation Accuracy: 0.1149
21
+ - Epoch: 94
22
 
23
  ## Model description
24
 
 
138
  | 0.9947 | 0.1147 | 0.9570 | 0.1157 | 91 |
139
  | 0.9921 | 0.1148 | 0.9360 | 0.1166 | 92 |
140
  | 0.9884 | 0.1149 | 0.9546 | 0.1156 | 93 |
141
+ | 0.9851 | 0.1149 | 0.9536 | 0.1149 | 94 |
142
 
143
 
144
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5c023e217d37692c11041dbb3aed88cddadedc17c9d637a94c3c542cf505dbb
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9245eb9bdd6003732365b0398332909a2613a1d36a1e85cfd77ddc3b397c4d0
3
  size 499741936