ativilambit/neu-faq

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-base](https://huggingface.co/google/flan-t5-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8470
-- Rouge1: 0.2057
-- Rouge2: 0.1147
-- Rougel: 0.1782
-- Rougelsum: 0.1958
+- Loss: 0.2242
+- Rouge1: 0.2012
+- Rouge2: 0.1143
+- Rougel: 0.1704
+- Rougelsum: 0.1885
 
 ## Model description
 
@@ -52,18 +52,18 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
-| No log        | 1.0   | 17   | 1.2660          | 0.1999 | 0.1058 | 0.1703 | 0.1847    |
-| No log        | 2.0   | 34   | 1.1230          | 0.2144 | 0.1178 | 0.1823 | 0.2017    |
-| No log        | 3.0   | 51   | 1.0869          | 0.2106 | 0.1181 | 0.1870 | 0.2010    |
-| No log        | 4.0   | 68   | 0.9919          | 0.2110 | 0.1205 | 0.1883 | 0.2036    |
-| No log        | 5.0   | 85   | 1.0286          | 0.2009 | 0.1078 | 0.1749 | 0.1935    |
-| No log        | 6.0   | 102  | 0.9935          | 0.2042 | 0.1096 | 0.1775 | 0.1958    |
-| No log        | 7.0   | 119  | 0.9676          | 0.2132 | 0.1231 | 0.1887 | 0.2068    |
-| No log        | 8.0   | 136  | 0.9297          | 0.2062 | 0.1155 | 0.1824 | 0.1992    |
-| No log        | 9.0   | 153  | 0.9009          | 0.2101 | 0.1181 | 0.1853 | 0.2027    |
-| No log        | 10.0  | 170  | 0.8658          | 0.2088 | 0.1179 | 0.1840 | 0.2021    |
-| No log        | 11.0  | 187  | 0.8495          | 0.2061 | 0.1146 | 0.1791 | 0.1972    |
-| No log        | 11.76 | 200  | 0.8470          | 0.2057 | 0.1147 | 0.1782 | 0.1958    |
+| No log        | 1.0   | 17   | 5.3687          | 0.1823 | 0.0899 | 0.1478 | 0.1616    |
+| No log        | 2.0   | 34   | 3.0748          | 0.1903 | 0.0931 | 0.1539 | 0.1741    |
+| No log        | 3.0   | 51   | 1.5007          | 0.1654 | 0.0620 | 0.1273 | 0.1507    |
+| No log        | 4.0   | 68   | 0.5415          | 0.1570 | 0.0597 | 0.1153 | 0.1389    |
+| No log        | 5.0   | 85   | 0.3232          | 0.1538 | 0.0702 | 0.1152 | 0.1377    |
+| No log        | 6.0   | 102  | 0.2662          | 0.1668 | 0.0704 | 0.1298 | 0.1467    |
+| No log        | 7.0   | 119  | 0.2379          | 0.1667 | 0.0684 | 0.1283 | 0.1475    |
+| No log        | 8.0   | 136  | 0.2296          | 0.1865 | 0.0911 | 0.1498 | 0.1720    |
+| No log        | 9.0   | 153  | 0.2266          | 0.2040 | 0.1084 | 0.1662 | 0.1860    |
+| No log        | 10.0  | 170  | 0.2238          | 0.2031 | 0.1136 | 0.1689 | 0.1877    |
+| No log        | 11.0  | 187  | 0.2239          | 0.2012 | 0.1148 | 0.1704 | 0.1885    |
+| No log        | 11.76 | 200  | 0.2242          | 0.2012 | 0.1143 | 0.1704 | 0.1885    |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c48518b2bc8a61f9580f0d9bd8d44309c1100914131190a60630e99f09d85bf
+oid sha256:d616a60ffd3542e2ebf93ccae79e7b3887851de6ad904e4e27d13b004659643b
 size 990404917

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90a771eede72cf7c25000c2104809583c9883f8ccd6b21ca61651ea218fdcc3a
+oid sha256:ff1097c45aeb3dccaf6bad4564f800ddf052353749006f59683051ec142a590c
 size 4155