cheaptrix/TokenizerTestingMTSUFall2024SoftwareEngineering-Removed members in datasaet with empty text boxes; Used new tokenizer lengths for the input and output; and used the new combined dataset of Senate and House bills and summaries.

README.md

@@ -18,12 +18,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.5834
-- Rouge1: 0.2719
-- Rouge2: 0.2175
-- Rougel: 0.2629
-- Rougelsum: 0.2629
-- Gen Len: 18.9753
+- Loss: 1.5198
+- Rouge1: 0.2778
+- Rouge2: 0.2234
+- Rougel: 0.2686
+- Rougelsum: 0.2686
+- Gen Len: 18.9697
 
 ## Model description
 
@@ -55,10 +55,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step  | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
 |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| 1.8415        | 1.0   | 12975 | 1.6850          | 0.2704 | 0.2117 | 0.2604 | 0.2604    | 18.9826 |
-| 1.7849        | 2.0   | 25950 | 1.6190          | 0.2713 | 0.2159 | 0.2621 | 0.262     | 18.9747 |
-| 1.7692        | 3.0   | 38925 | 1.5916          | 0.2718 | 0.2172 | 0.2628 | 0.2627    | 18.9762 |
-| 1.74          | 4.0   | 51900 | 1.5834          | 0.2719 | 0.2175 | 0.2629 | 0.2629    | 18.9753 |
+| 1.8333        | 1.0   | 12429 | 1.6354          | 0.2717 | 0.2139 | 0.262  | 0.262     | 18.9751 |
+| 1.7368        | 2.0   | 24858 | 1.5610          | 0.2763 | 0.2208 | 0.267  | 0.267     | 18.9735 |
+| 1.6978        | 3.0   | 37287 | 1.5291          | 0.2777 | 0.2227 | 0.2683 | 0.2682    | 18.9699 |
+| 1.7008        | 4.0   | 49716 | 1.5198          | 0.2778 | 0.2234 | 0.2686 | 0.2686    | 18.9697 |
 
 
 ### Framework versions

runs/Oct07_21-02-25_75d052a1e97f/events.out.tfevents.1728334946.75d052a1e97f.6094.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fef9b6fd61860da836d48563efeb93bb2f63afa8ef7c893b1d97fd7b9de3a1d5
-size 28767
+oid sha256:f18235d0d8d67befe810e6a6d2b8e61362fa4c00ff7c2e318aafd993f116d594
+size 29662