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
8766c44
·
1 Parent(s): 5b5456a

Training in progress epoch 464

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: 0.7125
18
  - Train Accuracy: 0.1219
19
- - Validation Loss: 0.7837
20
- - Validation Accuracy: 0.1208
21
- - Epoch: 463
22
 
23
  ## Model description
24
 
@@ -508,6 +508,7 @@ The following hyperparameters were used during training:
508
  | 0.7135 | 0.1219 | 0.7964 | 0.1206 | 461 |
509
  | 0.7128 | 0.1219 | 0.7969 | 0.1207 | 462 |
510
  | 0.7125 | 0.1219 | 0.7837 | 0.1208 | 463 |
 
511
 
512
 
513
  ### 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: 0.7134
18
  - Train Accuracy: 0.1219
19
+ - Validation Loss: 0.7788
20
+ - Validation Accuracy: 0.1219
21
+ - Epoch: 464
22
 
23
  ## Model description
24
 
 
508
  | 0.7135 | 0.1219 | 0.7964 | 0.1206 | 461 |
509
  | 0.7128 | 0.1219 | 0.7969 | 0.1207 | 462 |
510
  | 0.7125 | 0.1219 | 0.7837 | 0.1208 | 463 |
511
+ | 0.7134 | 0.1219 | 0.7788 | 0.1219 | 464 |
512
 
513
 
514
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e58e8be61e0e12302bf6401e03505709bddf117d9f13aaa8fd401d89c3094de
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25aba721cc4b0b8497419142f8063adb7742747acc750af464bc01995183ee9f
3
  size 499741936