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
4ca0bfe
•
1 Parent(s): a64bf1e

Training in progress epoch 385

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: 0.7340
18
  - Train Accuracy: 0.1214
19
- - Validation Loss: 0.7739
20
- - Validation Accuracy: 0.1208
21
- - Epoch: 384
22
 
23
  ## Model description
24
 
@@ -429,6 +429,7 @@ The following hyperparameters were used during training:
429
  | 0.7341 | 0.1213 | 0.7891 | 0.1217 | 382 |
430
  | 0.7349 | 0.1214 | 0.7891 | 0.1208 | 383 |
431
  | 0.7340 | 0.1214 | 0.7739 | 0.1208 | 384 |
 
432
 
433
 
434
  ### 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: 0.7339
18
  - Train Accuracy: 0.1214
19
+ - Validation Loss: 0.7871
20
+ - Validation Accuracy: 0.1210
21
+ - Epoch: 385
22
 
23
  ## Model description
24
 
 
429
  | 0.7341 | 0.1213 | 0.7891 | 0.1217 | 382 |
430
  | 0.7349 | 0.1214 | 0.7891 | 0.1208 | 383 |
431
  | 0.7340 | 0.1214 | 0.7739 | 0.1208 | 384 |
432
+ | 0.7339 | 0.1214 | 0.7871 | 0.1210 | 385 |
433
 
434
 
435
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:48891f26475dae2df320b00be7b10a680e5690aad01b1a5e6527f20522ecee97
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:119cfca87de507d5ae6b979bf88f5c286230e0d209148cb6a419a5bd9644a7aa
3
  size 499741936