End of training

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 10.3972
+- Loss: 0.0913
 
 ## Model description
 
@@ -34,21 +34,21 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0002
+- learning_rate: 2e-05
 - train_batch_size: 5
 - eval_batch_size: 5
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 3.0
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 10.3972       | 1.0   | 116  | 10.3972         |
-| 10.3972       | 2.0   | 232  | 10.3972         |
-| 10.3972       | 3.0   | 348  | 10.3972         |
+| 0.1499        | 1.0   | 116  | 0.1287          |
+| 0.1106        | 2.0   | 232  | 0.1026          |
+| 0.0914        | 3.0   | 348  | 0.0913          |
 
 
 ### Framework versions

runs/Jul31_14-38-46_104-171-203-105/events.out.tfevents.1722436726.104-171-203-105.3393.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfa478e6b805d329b67a1aa4bcdb4694793036a2e79b2a9a7fbba1fc9d14a134
-size 6115
+oid sha256:cec6ea648ad44d9f67b6620cc554544498ad983703baecff7a6c0d7ec4c086b8
+size 6740