Training in progress, step 500

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-small](https://huggingface.co/google/flan-t5-small) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8831
+- Loss: 0.0076
 
 ## Model description
 
@@ -47,16 +47,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 9.9609        | 1.0   | 15   | 3.7048          |
-| 3.2663        | 2.0   | 30   | 2.4982          |
-| 2.5394        | 3.0   | 45   | 1.7657          |
-| 1.6881        | 4.0   | 60   | 1.2883          |
-| 1.4200        | 5.0   | 75   | 1.0623          |
-| 1.1158        | 6.0   | 90   | 0.9751          |
-| 1.0128        | 7.0   | 105  | 0.9256          |
-| 0.9078        | 8.0   | 120  | 0.8989          |
-| 0.9097        | 9.0   | 135  | 0.8891          |
-| 0.8413        | 10.0  | 150  | 0.8831          |
+| 0.0696        | 1.0   | 57   | 0.0314          |
+| 0.0235        | 2.0   | 114  | 0.0152          |
+| 0.0153        | 3.0   | 171  | 0.0110          |
+| 0.0129        | 4.0   | 228  | 0.0110          |
+| 0.0117        | 5.0   | 285  | 0.0087          |
+| 0.0116        | 6.0   | 342  | 0.0084          |
+| 0.0121        | 7.0   | 399  | 0.0088          |
+| 0.0093        | 8.0   | 456  | 0.0078          |
+| 0.0102        | 9.0   | 513  | 0.0074          |
+| 0.0091        | 10.0  | 570  | 0.0076          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73dbe62d3d2b77ec568a9ac5f05d441bb5f422528ae0c0c495b51d041181ffce
+oid sha256:434d285f46e1a0ccc3392cc5bf2fdc6460a66672f5f97c7856baeb598231bece
 size 307867048