Upload 9 files

README.md

@@ -16,12 +16,12 @@ 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: 1.4253
-- Rouge1: 41.573
+- Loss: 1.3199
+- Rouge1: 42.1053
 - Rouge2: 0.0
-- Rougel: 41.573
-- Rougelsum: 41.573
-- Gen Len: 6.0449
+- Rougel: 42.1053
+- Rougelsum: 42.1053
+- Gen Len: 5.8947
 
 ## Model description
 
@@ -52,16 +52,15 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2 | Rougel  | Rougelsum | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
-| No log        | 1.0   | 23   | 1.4488          | 39.3258 | 0.0    | 39.3258 | 39.3258   | 6.0562  |
-| No log        | 2.0   | 46   | 1.5261          | 43.8202 | 0.0    | 43.8202 | 43.8202   | 6.0562  |
-| No log        | 3.0   | 69   | 1.4502          | 42.6966 | 0.0    | 42.6966 | 42.6966   | 6.1236  |
-| No log        | 4.0   | 92   | 1.4279          | 40.4494 | 0.0    | 40.4494 | 40.4494   | 6.0337  |
-| No log        | 5.0   | 115  | 1.4253          | 41.573  | 0.0    | 41.573  | 41.573    | 6.0449  |
+| No log        | 1.0   | 49   | 1.5630          | 35.2632 | 0.0    | 35.2632 | 35.2632   | 5.7474  |
+| No log        | 2.0   | 98   | 1.3838          | 41.5789 | 0.0    | 41.5789 | 41.5789   | 5.9316  |
+| No log        | 3.0   | 147  | 1.3419          | 41.0526 | 0.0    | 41.0526 | 41.0526   | 5.8684  |
+| No log        | 4.0   | 196  | 1.3239          | 41.5789 | 0.0    | 41.5789 | 41.5789   | 5.8526  |
+| No log        | 5.0   | 245  | 1.3199          | 42.1053 | 0.0    | 42.1053 | 42.1053   | 5.8947  |
 
 
 ### Framework versions
 
 - Transformers 4.26.1
 - Pytorch 1.13.1+cu116
-- Datasets 2.9.0
 - Tokenizers 0.13.2

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656