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: 0.8182
-- Rouge1: 55.6522
-- Rouge2: 47.9592
-- Rougel: 56.0248
-- Rougelsum: 56.7702
-- Gen Len: 13.8571
+- Loss: 0.2842
+- Rouge1: 64.1043
+- Rouge2: 39.0476
+- Rougel: 60.3628
+- Rougelsum: 60.9297
+- Gen Len: 14.5714
 
 ## 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    | 2.4417          | 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 |
+| No log        | 1.0   | 8    | 2.0867          | 15.5226 | 0.0     | 11.4409 | 11.4409   | 15.5714 |
+| No log        | 2.0   | 16   | 1.1098          | 21.0884 | 0.0     | 20.5782 | 20.7483   | 17.0    |
+| No log        | 3.0   | 24   | 0.6635          | 52.381  | 21.4286 | 51.9728 | 52.381    | 11.0    |
+| No log        | 4.0   | 32   | 0.5018          | 52.8571 | 29.5238 | 51.7007 | 52.381    | 11.5714 |
+| No log        | 5.0   | 40   | 0.4491          | 56.7347 | 28.5714 | 53.1293 | 53.5828   | 12.7143 |
+| No log        | 6.0   | 48   | 0.3894          | 60.4535 | 38.5714 | 57.7551 | 57.8685   | 13.8571 |
+| No log        | 7.0   | 56   | 0.3616          | 60.4535 | 38.5714 | 57.7551 | 57.8685   | 14.0    |
+| No log        | 8.0   | 64   | 0.3140          | 64.1043 | 39.0476 | 60.3628 | 60.9297   | 14.5714 |
+| No log        | 9.0   | 72   | 0.2880          | 64.1043 | 39.0476 | 60.3628 | 60.9297   | 14.5714 |
+| No log        | 10.0  | 80   | 0.2842          | 64.1043 | 39.0476 | 60.3628 | 60.9297   | 14.5714 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf971ccb3d106493e7ee7d3b7be316955ede4dd9932a5b3453444143bdd18529
+oid sha256:2453be168d327d54dde73612ab58e93721261354b9ad686a3110f6d4d4611b6a
 size 307867048

runs/Dec14_11-25-48_13b4eec0012a/events.out.tfevents.1702553160.13b4eec0012a.247.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c3999c4f17df46bf4401a53ac63d15a5378b452910a6630692ca8f226f2e8b0
+size 10809

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:428ece369627cc88a088f03aa84a2851d49bf3e65c4c62c4a920fce5bc01dbaf
+oid sha256:58789ea0615c35016045bd1993b69d07628c6e6228fa7495f5d8b7bd122397c7
 size 4728