Hugging Face's logo

tf-tpu
/
roberta-base-epochs-100

Fill-Mask
Transformers
TensorFlow
roberta
generated_from_keras_callback
Model card Files Community
1
sayakpaul HF staff commited on
Commit
a2fd40e
·
1 Parent(s): 9c4b75c

Training in progress epoch 94

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: 1.0482
18
- - Train Accuracy: 0.1134
19
- - Validation Loss: 0.9917
20
- - Validation Accuracy: 0.1141
21
- - Epoch: 93
22
 
23
  ## Model description
24
 
@@ -138,6 +138,7 @@ The following hyperparameters were used during training:
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
 
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: 1.0463
18
+ - Train Accuracy: 0.1135
19
+ - Validation Loss: 1.0244
20
+ - Validation Accuracy: 0.1145
21
+ - Epoch: 94
22
 
23
  ## Model description
24
 
 
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
+ | 1.0463 | 0.1135 | 1.0244 | 0.1145 | 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 sha256:2e8bed9638e5e67607927005b48020737afe413ef2ac90101a749d3328079dab
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1215555a3f56b7363272bb0305098f79ce91b926e88f9118b49ae864cbab554
3
  size 499741936