End of training

README.md

@@ -17,12 +17,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0064
-- Rouge1: 48.6395
-- Rouge2: 26.1905
-- Rougel: 47.7211
-- Rougelsum: 48.1633
-- Gen Len: 10.5714
+- Loss: 0.8182
+- Rouge1: 55.6522
+- Rouge2: 47.9592
+- Rougel: 56.0248
+- Rougelsum: 56.7702
+- Gen Len: 13.8571
 
 ## Model description
 
@@ -53,16 +53,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
-| No log        | 1.0   | 8    | 2.5594          | 10.2165 | 0.0     | 9.9567  | 10.2165   | 11.0    |
-| No log        | 2.0   | 16   | 2.0407          | 25.7143 | 14.2857 | 25.7143 | 25.7143   | 6.0     |
-| No log        | 3.0   | 24   | 1.7822          | 46.0317 | 33.3333 | 46.0317 | 45.7143   | 11.7143 |
-| No log        | 4.0   | 32   | 1.5058          | 50.3401 | 32.8571 | 49.1156 | 49.932    | 11.0    |
-| No log        | 5.0   | 40   | 1.2425          | 48.6395 | 26.1905 | 47.7211 | 48.1633   | 11.7143 |
-| No log        | 6.0   | 48   | 1.1249          | 52.8912 | 33.3333 | 52.2109 | 52.2109   | 13.4286 |
-| No log        | 7.0   | 56   | 1.0713          | 41.7687 | 21.4286 | 40.9524 | 41.7687   | 9.7143  |
-| No log        | 8.0   | 64   | 1.0475          | 46.1224 | 21.4286 | 45.1701 | 45.4422   | 10.1429 |
-| No log        | 9.0   | 72   | 1.0154          | 43.8095 | 16.6667 | 42.7211 | 42.9932   | 10.7143 |
-| No log        | 10.0  | 80   | 1.0064          | 48.6395 | 26.1905 | 47.7211 | 48.1633   | 10.5714 |
+| No log        | 1.0   | 8    | 2.4417          | 24.2887 | 11.7436 | 24.2887 | 24.0166   | 15.2857 |
+| No log        | 2.0   | 16   | 1.7097          | 26.6667 | 15.5388 | 26.6667 | 25.7143   | 13.2857 |
+| No log        | 3.0   | 24   | 1.4098          | 43.1844 | 20.9524 | 43.3613 | 43.6424   | 9.8571  |
+| No log        | 4.0   | 32   | 1.1681          | 45.1247 | 30.4762 | 45.941  | 46.5586   | 13.0    |
+| No log        | 5.0   | 40   | 1.0326          | 44.131  | 31.4286 | 45.1847 | 45.2674   | 13.1429 |
+| No log        | 6.0   | 48   | 0.9399          | 54.7826 | 42.4263 | 55.0238 | 55.6937   | 14.7143 |
+| No log        | 7.0   | 56   | 0.8863          | 61.9255 | 52.7211 | 61.9255 | 62.1739   | 14.0    |
+| No log        | 8.0   | 64   | 0.8449          | 61.9255 | 52.7211 | 61.9255 | 62.1739   | 14.0    |
+| No log        | 9.0   | 72   | 0.8303          | 55.6522 | 47.9592 | 56.0248 | 56.7702   | 13.8571 |
+| No log        | 10.0  | 80   | 0.8182          | 55.6522 | 47.9592 | 56.0248 | 56.7702   | 13.8571 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf626a11861b9965737b34222a931cc0b246f7676fb38d6a1bdebb6218967175
+oid sha256:bf971ccb3d106493e7ee7d3b7be316955ede4dd9932a5b3453444143bdd18529
 size 307867048

runs/Dec14_08-03-28_cb0c8c88b1c1/events.out.tfevents.1702541028.cb0c8c88b1c1.396.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9947e0d6aada801e263969618e7c6763258d443336d4cc2a4777427a281cbe67
+size 10809

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d201fcae9071d8f202b1f02da6b5990fbe3200d35b22750145f519e5317d30e
-size 4792
+oid sha256:428ece369627cc88a088f03aa84a2851d49bf3e65c4c62c4a920fce5bc01dbaf
+size 4728