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
993370a
•
1 Parent(s): e00b7b3

Training in progress epoch 286

Browse files
Files changed (2) hide show
  1. README.md +5 -4
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -15,10 +15,10 @@ probably proofread and complete it, then remove this comment. -->
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: 0.7733
18
- - Train Accuracy: 0.1203
19
- - Validation Loss: 0.8223
20
- - Validation Accuracy: 0.1206
21
- - Epoch: 285
22
 
23
  ## Model description
24
 
@@ -330,6 +330,7 @@ The following hyperparameters were used during training:
330
  | 0.7746 | 0.1203 | 0.8008 | 0.1186 | 283 |
331
  | 0.7746 | 0.1203 | 0.8105 | 0.1193 | 284 |
332
  | 0.7733 | 0.1203 | 0.8223 | 0.1206 | 285 |
 
333
 
334
 
335
  ### Framework versions
 
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: 0.7733
18
+ - Train Accuracy: 0.1204
19
+ - Validation Loss: 0.8125
20
+ - Validation Accuracy: 0.1199
21
+ - Epoch: 286
22
 
23
  ## Model description
24
 
 
330
  | 0.7746 | 0.1203 | 0.8008 | 0.1186 | 283 |
331
  | 0.7746 | 0.1203 | 0.8105 | 0.1193 | 284 |
332
  | 0.7733 | 0.1203 | 0.8223 | 0.1206 | 285 |
333
+ | 0.7733 | 0.1204 | 0.8125 | 0.1199 | 286 |
334
 
335
 
336
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0484e4a3a1321b6862657d612e65cb89e04b892e3cc749fcc4b320d7102224cf
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:404d25b80984c4f0af024d833320e94fd2712245826d5849c535c1d502210b75
3
  size 499741936