End of training

README.md

@@ -17,11 +17,11 @@ 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: 0.0455
-- Rouge1: 93.7107
-- Rouge2: 87.4214
-- Rougel: 93.7107
-- Rougelsum: 93.7107
+- Loss: 0.1109
+- Rouge1: 78.7129
+- Rouge2: 57.4257
+- Rougel: 78.7129
+- Rougelsum: 78.7129
 - Gen Len: 3.0
 
 ## Model description
@@ -53,10 +53,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
-| No log | 1.0 | 318 | 0.0494 | 93.5535 | 87.1069 | 93.5535 | 93.5535 | 3.0 |
-| 0.0889 | 2.0 | 636 | 0.0468 | 93.5535 | 87.1069 | 93.5535 | 93.5535 | 3.0 |
-| 0.0889 | 3.0 | 954 | 0.0447 | 94.4182 | 88.8365 | 94.4182 | 94.4182 | 3.0 |
-| 0.0448 | 4.0 | 1272 | 0.0455 | 93.7107 | 87.4214 | 93.7107 | 93.7107 | 3.0 |
+| No log | 1.0 | 51 | 0.1385 | 75.7426 | 51.4851 | 75.7426 | 75.7426 | 3.0 |
+| No log | 2.0 | 102 | 0.1108 | 80.198 | 60.396 | 80.198 | 80.198 | 3.0 |
+| No log | 3.0 | 153 | 0.1127 | 77.7228 | 55.4455 | 77.7228 | 77.7228 | 3.0 |
+| No log | 4.0 | 204 | 0.1109 | 78.7129 | 57.4257 | 78.7129 | 78.7129 | 3.0 |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e67660aaf5e7a3b0a854848f0b9f012c0b7aab356dfc1112c4b7c12b3425e6b2
+oid sha256:00c83132abb0e3413a3374f034d655569bbefe49deff6912c51f34944cea9fdb
 size 307907906