End of training

README.md

@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [ybelkada/flan-t5-xl-sharded-bf16](https://huggingface.co/ybelkada/flan-t5-xl-sharded-bf16) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6981
+- Loss: 0.2061
 
 ## Model description
 
@@ -40,13 +40,17 @@ 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_ratio: 0.1
-- num_epochs: 1
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.1992        | 0.9   | 200  | 0.6981          |
+| 2.6993        | 0.9   | 200  | 0.3786          |
+| 0.4329        | 1.8   | 400  | 0.2510          |
+| 0.3233        | 2.7   | 600  | 0.2303          |
+| 0.3008        | 3.6   | 800  | 0.2150          |
+| 0.2763        | 4.5   | 1000 | 0.2061          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95b8c78b93af0b95298afaa4fae23ff80e8caa1e4de5d4a00dc9b468718ada89
+oid sha256:0c02ebb16c738937984b2d36123a9f3513c01d9ed1d8385baa6853a22afc125f
 size 37855242

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd151eac8d7b566d10a89925afa6ee361853d92a38b4132a8524587f8cef76e2
+oid sha256:2767bae1f857b8913ebe0924795203fb366a8ab25cb9c0ad7b6269c507b4c520
 size 5112