training complete

README.md

@@ -15,7 +15,7 @@ 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4144
+- Loss: 0.3056
 
 ## Model description
 
@@ -41,36 +41,24 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- num_epochs: 10
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 18.6942       | 0.42  | 20   | 15.2678         |
-| 18.8039       | 0.83  | 40   | 13.9778         |
-| 16.8802       | 1.25  | 60   | 11.9079         |
-| 14.6576       | 1.67  | 80   | 9.4440          |
-| 12.5812       | 2.08  | 100  | 7.7483          |
-| 10.3758       | 2.5   | 120  | 7.0654          |
-| 8.0084        | 2.92  | 140  | 6.0787          |
-| 6.4748        | 3.33  | 160  | 4.9378          |
-| 5.5363        | 3.75  | 180  | 4.4125          |
-| 4.8288        | 4.17  | 200  | 4.0494          |
-| 4.3356        | 4.58  | 220  | 3.7350          |
-| 3.863         | 5.0   | 240  | 3.3543          |
-| 3.5341        | 5.42  | 260  | 3.0297          |
-| 3.1401        | 5.83  | 280  | 2.6883          |
-| 2.8039        | 6.25  | 300  | 2.3282          |
-| 2.4826        | 6.67  | 320  | 1.9990          |
-| 2.1485        | 7.08  | 340  | 1.6831          |
-| 1.8229        | 7.5   | 360  | 1.3760          |
-| 1.5307        | 7.92  | 380  | 1.1124          |
-| 1.2462        | 8.33  | 400  | 0.8750          |
-| 0.9948        | 8.75  | 420  | 0.7026          |
-| 0.8475        | 9.17  | 440  | 0.5729          |
-| 0.6563        | 9.58  | 460  | 0.4803          |
-| 0.4579        | 10.0  | 480  | 0.4144          |
+| 0.5231        | 0.42  | 20   | 0.4133          |
+| 0.4702        | 0.83  | 40   | 0.4094          |
+| 0.4898        | 1.25  | 60   | 0.4028          |
+| 0.4596        | 1.67  | 80   | 0.3933          |
+| 0.4597        | 2.08  | 100  | 0.3822          |
+| 0.3879        | 2.5   | 120  | 0.3714          |
+| 0.3861        | 2.92  | 140  | 0.3606          |
+| 0.3689        | 3.33  | 160  | 0.3495          |
+| 0.3574        | 3.75  | 180  | 0.3377          |
+| 0.3272        | 4.17  | 200  | 0.3257          |
+| 0.2981        | 4.58  | 220  | 0.3157          |
+| 0.3075        | 5.0   | 240  | 0.3056          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd6624a94d4ab177cbff284f8fcef6ded3e539f855554dc2b5f6fec538421fb9
+oid sha256:bff7316580b7948e72dca86954e69c7014219e584601436f1e7ff46f29ac7bd9
 size 307867048

runs/Nov17_12-41-24_aad6f3b7c3e4/events.out.tfevents.1700224890.aad6f3b7c3e4.296.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2f919268ea5f18aef0476644f01ae3d4de04c4fd693a6e2353978f0d1b1e9f1
+size 12457

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a882479aa7d9cc93106e94ee184d9c494c948f6ec260d541d4006bbb13d025f6
+oid sha256:f185fff7f531cee1368aead790c02b50a9e43f08113b06bd77dc41daf32a28df
 size 4600