End of training

README.md

@@ -15,6 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
 # flan-t5-xl-spider-qpl-20240127
 
 This model is a fine-tuned version of [google/flan-t5-xl](https://huggingface.co/google/flan-t5-xl) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0582
+- Execution Accuracy: 0.0
 
 ## Model description
 
@@ -39,13 +42,18 @@ The following hyperparameters were used during training:
 - seed: 1
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 15
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Execution Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:------------------:|
-| No log        | 1.0   | 10   | 2.1365          | 0.0                |
+| Training Loss | Epoch | Step  | Validation Loss | Execution Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:------------------:|
+| 0.06          | 1.0   | 6555  | 0.0635          | 0.0                |
+| 0.0375        | 2.0   | 13110 | 0.0577          | 0.0                |
+| 0.0289        | 3.0   | 19665 | 0.0556          | 0.0                |
+| 0.0223        | 4.0   | 26220 | 0.0566          | 0.0                |
+| 0.0186        | 5.0   | 32775 | 0.0555          | 0.0                |
+| 0.015         | 6.0   | 39330 | 0.0582          | 0.0                |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dd685bac2c3761e70133ac6dc0bc2ce99dfba193a7d867ddcbf34f17a12c8f9
+oid sha256:748788b2ce5813eaf0f40b5c79e7918f2eab189b99fa6ffbbd5ac48a735f383e
 size 563765632

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f6ab97d824a1f70a3d8efee32cb1dd49550aa975f4eaec4c7986e1ec3018eae
+oid sha256:2fa248748b1bd19b9b60a04c17fca445859719572d4a98714e4ac39010314985
 size 4920