ahmedgongi10/mistral_instruct_devops_expert1

README.md

@@ -16,7 +16,7 @@ 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.5531
+- Loss: 1.7356
 
 ## Model description
 
@@ -44,14 +44,16 @@ 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: 2
-- num_epochs: 10
+- num_epochs: 3
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.1277        | 9.91  | 540  | 1.5531          |
+| 1.7127        | 1.0   | 360  | 1.6831          |
+| 1.5565        | 2.0   | 720  | 1.6868          |
+| 1.3898        | 3.0   | 1080 | 1.7356          |
 
 
 ### Framework versions