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
99967a8
•
1 Parent(s): 1761e6c

Training in progress epoch 336

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: 0.7519
18
  - Train Accuracy: 0.1209
19
- - Validation Loss: 0.7798
20
- - Validation Accuracy: 0.1211
21
- - Epoch: 335
22
 
23
  ## Model description
24
 
@@ -380,6 +380,7 @@ The following hyperparameters were used during training:
380
  | 0.7523 | 0.1209 | 0.8110 | 0.1197 | 333 |
381
  | 0.7521 | 0.1209 | 0.7998 | 0.1208 | 334 |
382
  | 0.7519 | 0.1209 | 0.7798 | 0.1211 | 335 |
 
383
 
384
 
385
  ### 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: 0.7505
18
  - Train Accuracy: 0.1209
19
+ - Validation Loss: 0.8076
20
+ - Validation Accuracy: 0.1202
21
+ - Epoch: 336
22
 
23
  ## Model description
24
 
 
380
  | 0.7523 | 0.1209 | 0.8110 | 0.1197 | 333 |
381
  | 0.7521 | 0.1209 | 0.7998 | 0.1208 | 334 |
382
  | 0.7519 | 0.1209 | 0.7798 | 0.1211 | 335 |
383
+ | 0.7505 | 0.1209 | 0.8076 | 0.1202 | 336 |
384
 
385
 
386
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c0e270a1eb2d717acc69d062ba392afb80630917141c3a2f56611379cc057960
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:661fba370ef8317764580a3c4702a403b4b833f5f3e1769874837a57ba8bba71
3
  size 499741936