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
2f4f8a0
•
1 Parent(s): 78a42ee

Training in progress epoch 99

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: 1.0433
18
- - Train Accuracy: 0.1135
19
- - Validation Loss: 0.9946
20
- - Validation Accuracy: 0.1137
21
- - Epoch: 98
22
 
23
  ## Model description
24
 
@@ -143,6 +143,7 @@ The following hyperparameters were used during training:
143
  | 1.0448 | 0.1135 | 0.9785 | 0.1147 | 96 |
144
  | 1.0435 | 0.1135 | 0.9771 | 0.1155 | 97 |
145
  | 1.0433 | 0.1135 | 0.9946 | 0.1137 | 98 |
 
146
 
147
 
148
  ### 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: 1.0414
18
+ - Train Accuracy: 0.1136
19
+ - Validation Loss: 1.0103
20
+ - Validation Accuracy: 0.1144
21
+ - Epoch: 99
22
 
23
  ## Model description
24
 
 
143
  | 1.0448 | 0.1135 | 0.9785 | 0.1147 | 96 |
144
  | 1.0435 | 0.1135 | 0.9771 | 0.1155 | 97 |
145
  | 1.0433 | 0.1135 | 0.9946 | 0.1137 | 98 |
146
+ | 1.0414 | 0.1136 | 1.0103 | 0.1144 | 99 |
147
 
148
 
149
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:406ca0e9f492c0f2dd0d71b4874b59f0d79ab887332d515b1969a74c9d352691
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77f84dfeac7ae5314716de58fed6809f6b55a479afa46a7a1a14e315c94bcb22
3
  size 499741936