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
cca893f
·
1 Parent(s): 352f3b5

Training in progress epoch 361

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: 0.7421
18
  - Train Accuracy: 0.1212
19
- - Validation Loss: 0.8081
20
- - Validation Accuracy: 0.1200
21
- - Epoch: 360
22
 
23
  ## Model description
24
 
@@ -405,6 +405,7 @@ The following hyperparameters were used during training:
405
  | 0.7426 | 0.1211 | 0.8013 | 0.1205 | 358 |
406
  | 0.7419 | 0.1211 | 0.8003 | 0.1199 | 359 |
407
  | 0.7421 | 0.1212 | 0.8081 | 0.1200 | 360 |
 
408
 
409
 
410
  ### 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: 0.7417
18
  - Train Accuracy: 0.1212
19
+ - Validation Loss: 0.7964
20
+ - Validation Accuracy: 0.1199
21
+ - Epoch: 361
22
 
23
  ## Model description
24
 
 
405
  | 0.7426 | 0.1211 | 0.8013 | 0.1205 | 358 |
406
  | 0.7419 | 0.1211 | 0.8003 | 0.1199 | 359 |
407
  | 0.7421 | 0.1212 | 0.8081 | 0.1200 | 360 |
408
+ | 0.7417 | 0.1212 | 0.7964 | 0.1199 | 361 |
409
 
410
 
411
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:441cb76ad7bda986e50f1bd3a94c69d3b1a9b44d285759b25813dd992e74e30c
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5664bb73931c61eaed8a4697bf29ca1e7e544254af5560b95fe345dc9cd4fbbd
3
  size 499741936