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
f288a61
·
1 Parent(s): 1fc8225

Training in progress epoch 319

Browse files
Files changed (2) hide show
  1. README.md +6 -5
  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: 0.7678
18
- - Train Accuracy: 0.1205
19
- - Validation Loss: 0.8008
20
- - Validation Accuracy: 0.1205
21
- - Epoch: 318
22
 
23
  ## Model description
24
 
@@ -363,6 +363,7 @@ The following hyperparameters were used during training:
363
  | 0.7584 | 0.1207 | 0.8315 | 0.1198 | 316 |
364
  | 0.7592 | 0.1207 | 0.8228 | 0.1198 | 317 |
365
  | 0.7678 | 0.1205 | 0.8008 | 0.1205 | 318 |
 
366
 
367
 
368
  ### 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: 0.7598
18
+ - Train Accuracy: 0.1207
19
+ - Validation Loss: 0.8091
20
+ - Validation Accuracy: 0.1216
21
+ - Epoch: 319
22
 
23
  ## Model description
24
 
 
363
  | 0.7584 | 0.1207 | 0.8315 | 0.1198 | 316 |
364
  | 0.7592 | 0.1207 | 0.8228 | 0.1198 | 317 |
365
  | 0.7678 | 0.1205 | 0.8008 | 0.1205 | 318 |
366
+ | 0.7598 | 0.1207 | 0.8091 | 0.1216 | 319 |
367
 
368
 
369
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cbb15dd188333efc9677f17dd43edd2a74c3a57ac50f20e07e9425e7b82ddedc
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a82b70b5c55e74a3e398edeb4a3634db983d360fa91f455e193656b296cf9a5d
3
  size 499741936