End of training

README.md

@@ -16,7 +16,7 @@ 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: 0.5627
+- Loss: 3.9226
 
 ## Model description
 
@@ -47,16 +47,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 7    | 3.4698          |
-| 3.8834        | 2.0   | 14   | 1.8878          |
-| 2.9004        | 3.0   | 21   | 1.4939          |
-| 2.9004        | 4.0   | 28   | 1.0909          |
-| 2.1926        | 5.0   | 35   | 0.8631          |
-| 1.7237        | 6.0   | 42   | 0.6799          |
-| 1.7237        | 7.0   | 49   | 0.6358          |
-| 1.482         | 8.0   | 56   | 0.6044          |
-| 1.3236        | 9.0   | 63   | 0.5749          |
-| 1.2312        | 10.0  | 70   | 0.5627          |
+| No log        | 1.0   | 7    | 26.6248         |
+| 32.1267       | 2.0   | 14   | 18.4799         |
+| 18.4028       | 3.0   | 21   | 9.9272          |
+| 18.4028       | 4.0   | 28   | 4.8353          |
+| 7.4967        | 5.0   | 35   | 4.4899          |
+| 4.8455        | 6.0   | 42   | 4.2977          |
+| 4.8455        | 7.0   | 49   | 4.1490          |
+| 4.4842        | 8.0   | 56   | 4.0375          |
+| 4.3206        | 9.0   | 63   | 3.9568          |
+| 4.1982        | 10.0  | 70   | 3.9226          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5db2674b332910df3222ba78afa5d58f507bd834122c1c9684fe60128dd48b28
+oid sha256:562b5ce58956c29267bd1c05f8e0ceb1a541aaaf441ecb272df6c95e46017f4b
 size 6655648