Hugging Face's logo

Zemulax
/
masked-lm-tpu

Fill-Mask
Transformers
TensorFlow
roberta
generated_from_keras_callback
Inference Endpoints
Model card Files Community
Zemulax commited on
Commit
bc98d9f
·
1 Parent(s): 5d05830

Training in progress epoch 36

Browse files
Files changed (2) hide show
  1. README.md +6 -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: 8.7333
18
- - Train Accuracy: 0.0228
19
- - Validation Loss: 8.6801
20
  - Validation Accuracy: 0.0223
21
- - Epoch: 34
22
 
23
  ## Model description
24
 
@@ -79,6 +79,8 @@ The following hyperparameters were used during training:
79
  | 8.7798 | 0.0231 | 8.7506 | 0.0221 | 32 |
80
  | 8.7535 | 0.0231 | 8.7055 | 0.0222 | 33 |
81
  | 8.7333 | 0.0228 | 8.6801 | 0.0223 | 34 |
 
 
82
 
83
 
84
  ### 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: 8.6816
18
+ - Train Accuracy: 0.0229
19
+ - Validation Loss: 8.6243
20
  - Validation Accuracy: 0.0223
21
+ - Epoch: 36
22
 
23
  ## Model description
24
 
 
79
  | 8.7798 | 0.0231 | 8.7506 | 0.0221 | 32 |
80
  | 8.7535 | 0.0231 | 8.7055 | 0.0222 | 33 |
81
  | 8.7333 | 0.0228 | 8.6801 | 0.0223 | 34 |
82
+ | 8.6985 | 0.0231 | 8.6837 | 0.0220 | 35 |
83
+ | 8.6816 | 0.0229 | 8.6243 | 0.0223 | 36 |
84
 
85
 
86
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6c54d51b1c19d7bbb48c52d83c47e82991c4b6603fcfe587f95ea47aa436b05
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:036c6d1ad18cfe194b66a316c72737dac6cfb11f4a9888354241f6affe6cf805
3
  size 499741936