Shrunk learning rate

README.md

@@ -18,11 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5633
-- Rouge1: 70.9016
-- Rouge2: 60.7375
-- Rougel: 54.2243
-- Rougelsum: 58.491
+- Loss: 0.3711
+- Rouge1: 64.5245
+- Rouge2: 53.1381
+- Rougel: 47.3234
+- Rougelsum: 51.2042
 
 ## Model description
 
@@ -41,7 +41,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5.6e-05
+- learning_rate: 5.6e-06
 - train_batch_size: 4
 - eval_batch_size: 4
 - seed: 42
@@ -53,10 +53,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
-| 0.1042        | 1.0   | 389  | 0.4854          | 69.7999 | 59.5837 | 52.6002 | 57.1183   |
-| 0.0803        | 2.0   | 778  | 0.4980          | 69.7759 | 59.0227 | 51.7915 | 56.3797   |
-| 0.0458        | 3.0   | 1167 | 0.5126          | 71.0291 | 60.7734 | 53.5909 | 57.7722   |
-| 0.0213        | 4.0   | 1556 | 0.5633          | 70.9016 | 60.7375 | 54.2243 | 58.491    |
+| 0.4228        | 1.0   | 389  | 0.3821          | 57.8993 | 45.4774 | 41.9455 | 44.9012   |
+| 0.321         | 2.0   | 778  | 0.3641          | 61.5071 | 49.6584 | 45.5774 | 48.3601   |
+| 0.2764        | 3.0   | 1167 | 0.3689          | 63.7295 | 52.1907 | 46.827  | 50.3726   |
+| 0.2504        | 4.0   | 1556 | 0.3711          | 64.5245 | 53.1381 | 47.3234 | 51.2042   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f8f9bde1c318486d81190b013b09d64ad246f859040e583fc0d935b2ce59d15
+oid sha256:18b06836dbd72e01e642e92768c91e1903eef60bbcb2ec2544f6abd1bb330a02
 size 1625422896

runs/Feb08_15-21-39_0f69a279724d/events.out.tfevents.1707405749.0f69a279724d.4494.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e93074f8434db308a6561ce059d090de27db11d15b755330c46dc19c90fcee96
+size 8294

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe24ef9f767584732eb976250eafbd6631cc9e4116a4b2cfcbf1ad9af0de3daf
-size 4728
+oid sha256:8b185d3b25b3bc45db7154959030819fd168c7d876545d35c8414b5911f9c7a0
+size 4792