ganse/word_wizards_final_bart

README.md

@@ -17,11 +17,11 @@ should 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 the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.0509
-- Rouge1: 0.2716
-- Rouge2: 0.0759
-- Rougel: 0.2222
-- Rougelsum: 0.2222
+- Loss: 1.2484
+- Rouge1: 0.2698
+- Rouge2: 0.2581
+- Rougel: 0.2698
+- Rougelsum: 0.2698
 - Gen Len: 20.0
 
 ## Model description
@@ -54,10 +54,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| No log        | 1.0   | 3    | 2.5357          | 0.1842 | 0.1081 | 0.1579 | 0.1579    | 20.0    |
-| No log        | 2.0   | 6    | 2.2193          | 0.1842 | 0.1081 | 0.1579 | 0.1579    | 20.0    |
-| No log        | 3.0   | 9    | 2.1043          | 0.1842 | 0.1081 | 0.1579 | 0.1579    | 20.0    |
-| No log        | 4.0   | 12   | 2.0509          | 0.2716 | 0.0759 | 0.2222 | 0.2222    | 20.0    |
+| No log        | 1.0   | 3    | 1.6226          | 0.0826 | 0.0    | 0.0661 | 0.0661    | 20.0    |
+| No log        | 2.0   | 6    | 1.4712          | 0.256  | 0.2439 | 0.256  | 0.256     | 20.0    |
+| No log        | 3.0   | 9    | 1.3444          | 0.2698 | 0.2581 | 0.2698 | 0.2698    | 20.0    |
+| No log        | 4.0   | 12   | 1.2484          | 0.2698 | 0.2581 | 0.2698 | 0.2698    | 20.0    |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:310f28456c706e2eab8c6490b8affae203bc5a2c1567b6be39eddb0438c53251
+oid sha256:03aaef8e9ff231dce1a5677f7e97e285ce5d8e830cfb1c8214f8416b9998b8a8
 size 557912620

runs/Dec07_03-16-10_122418b4c9bd/events.out.tfevents.1701918971.122418b4c9bd.12256.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8e92c38ad6a647a39200787ef95794dc3b781c603d46a25ea011e34b7941d0d
+size 7810

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d324227caced320126a1819851f286fe6da1dab28baf8683d9d4a8faf64ee17a
+oid sha256:b896f1b77dcfab0e569d9bc306370554a375bfa1aa9c3a95232997649ec04307
 size 4728