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
9c1d05e
•
1 Parent(s): 9e7c03c

Training in progress epoch 392

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: 0.7319
18
  - Train Accuracy: 0.1214
19
- - Validation Loss: 0.8042
20
- - Validation Accuracy: 0.1203
21
- - Epoch: 391
22
 
23
  ## Model description
24
 
@@ -436,6 +436,7 @@ The following hyperparameters were used during training:
436
  | 0.7334 | 0.1214 | 0.8193 | 0.1215 | 389 |
437
  | 0.7319 | 0.1214 | 0.7788 | 0.1208 | 390 |
438
  | 0.7319 | 0.1214 | 0.8042 | 0.1203 | 391 |
 
439
 
440
 
441
  ### 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: 0.7315
18
  - Train Accuracy: 0.1214
19
+ - Validation Loss: 0.7935
20
+ - Validation Accuracy: 0.1211
21
+ - Epoch: 392
22
 
23
  ## Model description
24
 
 
436
  | 0.7334 | 0.1214 | 0.8193 | 0.1215 | 389 |
437
  | 0.7319 | 0.1214 | 0.7788 | 0.1208 | 390 |
438
  | 0.7319 | 0.1214 | 0.8042 | 0.1203 | 391 |
439
+ | 0.7315 | 0.1214 | 0.7935 | 0.1211 | 392 |
440
 
441
 
442
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2062a0e34e4c97f0b04848dfa7e5d09351bdf8192aeaf95cb26042295c60010c
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18c1087693a8d898837760dba8bdcf671f183ca99ce185f398b108cfd3664c89
3
  size 499741936