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
b462d5b
·
1 Parent(s): 79016fb

Training in progress epoch 82

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: 1.0296
18
  - Train Accuracy: 0.1138
19
- - Validation Loss: 0.9961
20
- - Validation Accuracy: 0.1152
21
- - Epoch: 81
22
 
23
  ## Model description
24
 
@@ -126,6 +126,7 @@ The following hyperparameters were used during training:
126
  | 1.0372 | 0.1137 | 0.9995 | 0.1151 | 79 |
127
  | 1.0340 | 0.1137 | 1.0059 | 0.1153 | 80 |
128
  | 1.0296 | 0.1138 | 0.9961 | 0.1152 | 81 |
 
129
 
130
 
131
  ### 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: 1.0272
18
  - Train Accuracy: 0.1138
19
+ - Validation Loss: 1.0132
20
+ - Validation Accuracy: 0.1138
21
+ - Epoch: 82
22
 
23
  ## Model description
24
 
 
126
  | 1.0372 | 0.1137 | 0.9995 | 0.1151 | 79 |
127
  | 1.0340 | 0.1137 | 1.0059 | 0.1153 | 80 |
128
  | 1.0296 | 0.1138 | 0.9961 | 0.1152 | 81 |
129
+ | 1.0272 | 0.1138 | 1.0132 | 0.1138 | 82 |
130
 
131
 
132
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c8cc841a9f0038866ec99f2ccad16d8a0d19326bf3e3d5f2878cb0b6cd2bc9fa
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:070c4ce8c6d1adc2ed90ebd4aa0a13cafd2c0f3f28da336709f436ec0290e15f
3
  size 499741936