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
8564faa
·
1 Parent(s): 2936d78

Training in progress epoch 63

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: 1.1318
18
  - Train Accuracy: 0.1114
19
- - Validation Loss: 1.0811
20
- - Validation Accuracy: 0.1131
21
- - Epoch: 62
22
 
23
  ## Model description
24
 
@@ -107,6 +107,7 @@ The following hyperparameters were used during training:
107
  | 1.1403 | 0.1111 | 1.0874 | 0.1123 | 60 |
108
  | 1.1360 | 0.1112 | 1.0742 | 0.1145 | 61 |
109
  | 1.1318 | 0.1114 | 1.0811 | 0.1131 | 62 |
 
110
 
111
 
112
  ### 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: 1.1277
18
  - Train Accuracy: 0.1114
19
+ - Validation Loss: 1.0723
20
+ - Validation Accuracy: 0.1129
21
+ - Epoch: 63
22
 
23
  ## Model description
24
 
 
107
  | 1.1403 | 0.1111 | 1.0874 | 0.1123 | 60 |
108
  | 1.1360 | 0.1112 | 1.0742 | 0.1145 | 61 |
109
  | 1.1318 | 0.1114 | 1.0811 | 0.1131 | 62 |
110
+ | 1.1277 | 0.1114 | 1.0723 | 0.1129 | 63 |
111
 
112
 
113
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:98254f3b6c6d5dec26f5c1c8dc400ea992f0b26c5e850fece9f46c7d6b20bc2e
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66b9fb064d928b45329dc130bfc15e412239f6c64d3c39c9735b6d3bdfa6041f
3
  size 499741936