End of training

README.md

@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.7939
+- Loss: 0.2368
 
 ## Model description
 
@@ -39,24 +39,26 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
+- learning_rate: 0.0005
 - train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.3
-- num_epochs: 5
+- num_epochs: 7
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 3    | 2.6773          |
-| No log        | 2.0   | 6    | 2.3213          |
-| No log        | 3.0   | 9    | 1.9551          |
-| 2.5229        | 4.0   | 12   | 1.8233          |
-| 2.5229        | 5.0   | 15   | 1.7939          |
+| No log        | 1.0   | 6    | 1.2601          |
+| 1.906         | 2.0   | 12   | 0.7329          |
+| 1.906         | 3.0   | 18   | 0.4273          |
+| 0.9496        | 4.0   | 24   | 0.2872          |
+| 0.7822        | 5.0   | 30   | 0.2423          |
+| 0.7822        | 6.0   | 36   | 0.2370          |
+| 0.6482        | 7.0   | 42   | 0.2368          |
 
 
 ### Framework versions