KostiuchenkoArtem
/

bart_base_large

text2text-generation

generated_from_keras_callback

Model card Files Files and versions

KostiuchenkoArtem commited on May 21, 2023

Commit

8840169

·

1 Parent(s): 6b6ad56

Training in progress epoch 3

Files changed (2) hide show

README.md +4 -3
tf_model.h5 +1 -1

README.md CHANGED Viewed

@@ -14,9 +14,9 @@ probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 2.4377
-- Validation Loss: 2.4095
-- Epoch: 2
 ## Model description
@@ -45,6 +45,7 @@ The following hyperparameters were used during training:
 | 2.7502     | 2.4418          | 0     |
 | 2.5512     | 2.4306          | 1     |
 | 2.4377     | 2.4095          | 2     |
 ### Framework versions

 This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Train Loss: 2.3445
+- Validation Loss: 2.4043
+- Epoch: 3
 ## Model description
 | 2.7502     | 2.4418          | 0     |
 | 2.5512     | 2.4306          | 1     |
 | 2.4377     | 2.4095          | 2     |
+| 2.3445     | 2.4043          | 3     |
 ### Framework versions

tf_model.h5 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:add6f289b9a26eb9e744e7514c5e279c900be3b5debce1be66bfb62ebd5e6ffd
 size 558172300

 version https://git-lfs.github.com/spec/v1
+oid sha256:4bf6c6f79384af1f7f05f7e4740789c60efbcdc9484aef1d6e8d0c029730222c
 size 558172300