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
13b0102
•
1 Parent(s): ed15c7c

Training in progress epoch 316

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: 0.7600
18
  - Train Accuracy: 0.1207
19
- - Validation Loss: 0.8237
20
- - Validation Accuracy: 0.1189
21
- - Epoch: 315
22
 
23
  ## Model description
24
 
@@ -360,6 +360,7 @@ The following hyperparameters were used during training:
360
  | 0.7606 | 0.1207 | 0.7900 | 0.1201 | 313 |
361
  | 0.7597 | 0.1207 | 0.8057 | 0.1201 | 314 |
362
  | 0.7600 | 0.1207 | 0.8237 | 0.1189 | 315 |
 
363
 
364
 
365
  ### 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: 0.7584
18
  - Train Accuracy: 0.1207
19
+ - Validation Loss: 0.8315
20
+ - Validation Accuracy: 0.1198
21
+ - Epoch: 316
22
 
23
  ## Model description
24
 
 
360
  | 0.7606 | 0.1207 | 0.7900 | 0.1201 | 313 |
361
  | 0.7597 | 0.1207 | 0.8057 | 0.1201 | 314 |
362
  | 0.7600 | 0.1207 | 0.8237 | 0.1189 | 315 |
363
+ | 0.7584 | 0.1207 | 0.8315 | 0.1198 | 316 |
364
 
365
 
366
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a56c7ad0b0124b17dd759b1a8e8a0f730eec43545e090ce69ab7ff50e9847e1
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9bcb93030ad41e33d8fe3ee4134ab77d879598b0d440c6d3b6ad163f6aec664
3
  size 499741936