End of training

README.md

@@ -14,6 +14,8 @@ should probably proofread and complete it, then remove this comment. -->
 # phi-1_5-finetuned-SQL-2
 
 This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7586
 
 ## Model description
 
@@ -33,15 +35,30 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 4
+- train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: cosine
-- num_epochs: 6
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- training_steps: 10000
 
 ### Training results
 
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 2.1598        | 3.2   | 1000  | 1.7484          |
+| 1.6682        | 6.4   | 2000  | 1.5604          |
+| 1.5154        | 9.6   | 3000  | 1.4110          |
+| 1.3766        | 12.8  | 4000  | 1.2735          |
+| 1.2458        | 16.0  | 5000  | 1.1389          |
+| 1.1176        | 19.2  | 6000  | 1.0163          |
+| 1.0093        | 22.4  | 7000  | 0.9195          |
+| 0.9166        | 25.6  | 8000  | 0.8406          |
+| 0.8448        | 28.8  | 9000  | 0.7828          |
+| 0.7928        | 32.0  | 10000 | 0.7586          |
 
 
 ### Framework versions