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
be19d12
•
1 Parent(s): 7332048

Training in progress epoch 277

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: 0.7788
18
  - Train Accuracy: 0.1202
19
- - Validation Loss: 0.8325
20
- - Validation Accuracy: 0.1202
21
- - Epoch: 276
22
 
23
  ## Model description
24
 
@@ -321,6 +321,7 @@ The following hyperparameters were used during training:
321
  | 0.7787 | 0.1202 | 0.8389 | 0.1206 | 274 |
322
  | 0.7786 | 0.1202 | 0.8286 | 0.1208 | 275 |
323
  | 0.7788 | 0.1202 | 0.8325 | 0.1202 | 276 |
 
324
 
325
 
326
  ### 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: 0.7777
18
  - Train Accuracy: 0.1202
19
+ - Validation Loss: 0.8301
20
+ - Validation Accuracy: 0.1194
21
+ - Epoch: 277
22
 
23
  ## Model description
24
 
 
321
  | 0.7787 | 0.1202 | 0.8389 | 0.1206 | 274 |
322
  | 0.7786 | 0.1202 | 0.8286 | 0.1208 | 275 |
323
  | 0.7788 | 0.1202 | 0.8325 | 0.1202 | 276 |
324
+ | 0.7777 | 0.1202 | 0.8301 | 0.1194 | 277 |
325
 
326
 
327
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d4804714326e58a6150173fa354576a74ac80e17276f9a4c0569ccec6176cac
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abf9e04e103d17f60f65b75b111e6bcb6806df1f2e46d097b0f84f49e412eace
3
  size 499741936