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
eb4e9e4
•
1 Parent(s): c9816d5

Training in progress epoch 382

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: 0.7350
18
  - Train Accuracy: 0.1213
19
- - Validation Loss: 0.8140
20
- - Validation Accuracy: 0.1203
21
- - Epoch: 381
22
 
23
  ## Model description
24
 
@@ -426,6 +426,7 @@ The following hyperparameters were used during training:
426
  | 0.7360 | 0.1213 | 0.8037 | 0.1203 | 379 |
427
  | 0.7352 | 0.1213 | 0.7974 | 0.1203 | 380 |
428
  | 0.7350 | 0.1213 | 0.8140 | 0.1203 | 381 |
 
429
 
430
 
431
  ### 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: 0.7341
18
  - Train Accuracy: 0.1213
19
+ - Validation Loss: 0.7891
20
+ - Validation Accuracy: 0.1217
21
+ - Epoch: 382
22
 
23
  ## Model description
24
 
 
426
  | 0.7360 | 0.1213 | 0.8037 | 0.1203 | 379 |
427
  | 0.7352 | 0.1213 | 0.7974 | 0.1203 | 380 |
428
  | 0.7350 | 0.1213 | 0.8140 | 0.1203 | 381 |
429
+ | 0.7341 | 0.1213 | 0.7891 | 0.1217 | 382 |
430
 
431
 
432
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:848ce9b99785a3a2b151715cd310e48b39889386f1fa9f710d16575216e385bb
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b463c94fa363af95d58caec3c2f0ce88ba655761695308dde2cdf61b1ddbc822
3
  size 499741936