vladjr
/

bart-base-teste2

Text2Text Generation

generated_from_keras_callback

Inference Endpoints

Model card Files Files and versions Community

vladjr commited on Oct 12, 2023

Commit

463ccd9

•

1 Parent(s): fe50ecc

Training in progress epoch 6

Files changed (2) hide show

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

README.md CHANGED Viewed

@@ -15,9 +15,9 @@ 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: 0.0136
-- Validation Loss: 0.0165
-- Epoch: 5
 ## Model description
@@ -49,6 +49,7 @@ The following hyperparameters were used during training:
 | 0.0206     | 0.0133          | 3     |
 | 0.0157     | 0.0250          | 4     |
 | 0.0136     | 0.0165          | 5     |
 ### 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: 0.0112
+- Validation Loss: 0.0169
+- Epoch: 6
 ## Model description
 | 0.0206     | 0.0133          | 3     |
 | 0.0157     | 0.0250          | 4     |
 | 0.0136     | 0.0165          | 5     |
+| 0.0112     | 0.0169          | 6     |
 ### Framework versions

tf_model.h5 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ca317ab325cc90ee6b1e91817d16e063f69b45c1b1eeec83f531864bcddcd5a
 size 558172300

 version https://git-lfs.github.com/spec/v1
+oid sha256:ea5c23e71a6979e1d8472806c3972c4c06e4c6dbdf44b4da9933e4678f663186
 size 558172300