Training 2 complete

README.md

@@ -18,11 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.2629
-- Rouge1: 19.7332
-- Rouge2: 10.4613
-- Rougel: 18.6425
-- Rougelsum: 18.8116
+- Loss: 3.2197
+- Rouge1: 23.7209
+- Rouge2: 12.4611
+- Rougel: 22.745
+- Rougelsum: 22.8085
 
 ## Model description
 
@@ -53,14 +53,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
-| 9.1364        | 1.0   | 589  | 3.5408          | 14.3515 | 5.3824  | 14.2034 | 14.1358   |
-| 4.2365        | 2.0   | 1178 | 3.3891          | 17.8799 | 7.7088  | 17.1443 | 17.2266   |
-| 3.8171        | 3.0   | 1767 | 3.3303          | 21.0055 | 10.3132 | 19.9583 | 19.8408   |
-| 3.6164        | 4.0   | 2356 | 3.2909          | 19.7277 | 10.2522 | 18.6633 | 18.8049   |
-| 3.506         | 5.0   | 2945 | 3.2994          | 20.5969 | 10.5213 | 19.35   | 19.3436   |
-| 3.4122        | 6.0   | 3534 | 3.2715          | 18.2196 | 9.6013  | 17.1232 | 17.2425   |
-| 3.3635        | 7.0   | 4123 | 3.2582          | 19.0426 | 10.339  | 17.9558 | 18.1044   |
-| 3.3409        | 8.0   | 4712 | 3.2629          | 19.7332 | 10.4613 | 18.6425 | 18.8116   |
+| 3.2981        | 1.0   | 589  | 3.2505          | 21.3203 | 11.2834 | 20.3564 | 20.3812   |
+| 3.2017        | 2.0   | 1178 | 3.2563          | 21.5285 | 10.7337 | 20.7505 | 20.5952   |
+| 3.1031        | 3.0   | 1767 | 3.2636          | 23.6856 | 12.5802 | 22.6568 | 22.5633   |
+| 3.0303        | 4.0   | 2356 | 3.2242          | 23.4492 | 12.3205 | 22.3518 | 22.3521   |
+| 2.9808        | 5.0   | 2945 | 3.2281          | 24.2603 | 12.6434 | 23.1527 | 23.2443   |
+| 2.9519        | 6.0   | 3534 | 3.2146          | 24.5639 | 13.5995 | 23.8336 | 23.8418   |
+| 2.9125        | 7.0   | 4123 | 3.2226          | 23.9892 | 12.9918 | 23.3101 | 23.3465   |
+| 2.9058        | 8.0   | 4712 | 3.2197          | 23.7209 | 12.4611 | 22.745  | 22.8085   |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dcba117ece45442ec85a0e9f9885228a61490fa5c8a7d3746e02426358cc988
+oid sha256:debf5bbc5bc569c51b4f15873b4c45012e6467c38ccaa5a370a693dcf585ba02
 size 1200772613