Hugging Face's logo

tf-tpu
/
roberta-base-epochs-100

Fill-Mask
Transformers
TensorFlow
roberta
generated_from_keras_callback
Inference Endpoints
Model card Files Community
1
sayakpaul HF staff commited on
Commit
9c4b75c
·
1 Parent(s): ff02285

Training in progress epoch 93

Browse files
Files changed (2) hide show
  1. README.md +4 -3
  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: 1.0484
18
  - Train Accuracy: 0.1134
19
- - Validation Loss: 1.0063
20
  - Validation Accuracy: 0.1141
21
- - Epoch: 92
22
 
23
  ## Model description
24
 
@@ -137,6 +137,7 @@ The following hyperparameters were used during training:
137
  | 1.0522 | 0.1133 | 0.9951 | 0.1134 | 90 |
138
  | 1.0505 | 0.1134 | 1.0283 | 0.1136 | 91 |
139
  | 1.0484 | 0.1134 | 1.0063 | 0.1141 | 92 |
 
140
 
141
 
142
  ### 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: 1.0482
18
  - Train Accuracy: 0.1134
19
+ - Validation Loss: 0.9917
20
  - Validation Accuracy: 0.1141
21
+ - Epoch: 93
22
 
23
  ## Model description
24
 
 
137
  | 1.0522 | 0.1133 | 0.9951 | 0.1134 | 90 |
138
  | 1.0505 | 0.1134 | 1.0283 | 0.1136 | 91 |
139
  | 1.0484 | 0.1134 | 1.0063 | 0.1141 | 92 |
140
+ | 1.0482 | 0.1134 | 0.9917 | 0.1141 | 93 |
141
 
142
 
143
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c032a8cf98f6410619615cb072b71d756f2f23589ad915b6b7240a064f6a6f1d
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e8bed9638e5e67607927005b48020737afe413ef2ac90101a749d3328079dab
3
  size 499741936