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
8979f53
•
1 Parent(s): 5723a5d

Training in progress epoch 225

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: 0.8089
18
  - Train Accuracy: 0.1194
19
- - Validation Loss: 0.8101
20
- - Validation Accuracy: 0.1195
21
- - Epoch: 224
22
 
23
  ## Model description
24
 
@@ -269,6 +269,7 @@ The following hyperparameters were used during training:
269
  | 0.8095 | 0.1194 | 0.8340 | 0.1195 | 222 |
270
  | 0.8090 | 0.1194 | 0.8071 | 0.1208 | 223 |
271
  | 0.8089 | 0.1194 | 0.8101 | 0.1195 | 224 |
 
272
 
273
 
274
  ### 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: 0.8081
18
  - Train Accuracy: 0.1194
19
+ - Validation Loss: 0.8311
20
+ - Validation Accuracy: 0.1184
21
+ - Epoch: 225
22
 
23
  ## Model description
24
 
 
269
  | 0.8095 | 0.1194 | 0.8340 | 0.1195 | 222 |
270
  | 0.8090 | 0.1194 | 0.8071 | 0.1208 | 223 |
271
  | 0.8089 | 0.1194 | 0.8101 | 0.1195 | 224 |
272
+ | 0.8081 | 0.1194 | 0.8311 | 0.1184 | 225 |
273
 
274
 
275
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:981761b6e9c8e867fd8656797994c76dbd96cbde3dcb59911d8a6e24865fb46c
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ed31efeee295f69df77f01d2b051c63ddfd3ef2f28e2dc8546dedc0cf594240
3
  size 499741936