Model save

README.md

@@ -18,10 +18,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [ministral/Ministral-3b-instruct](https://huggingface.co/ministral/Ministral-3b-instruct) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.6892
-- Model Preparation Time: 0.0125
-- Accuracy: 0.5202
-- Perplexity: 14.7202
+- Loss: 2.2631
+- Model Preparation Time: 0.0126
+- Accuracy: 0.5672
+- Perplexity: 9.6125
 
 ## Model description
 
@@ -48,14 +48,16 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 4
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 3
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch  | Step  | Validation Loss | Model Preparation Time | Accuracy | Perplexity |
 |:-------------:|:------:|:-----:|:---------------:|:----------------------:|:--------:|:----------:|
-| 2.8172        | 1.0000 | 30564 | 2.6892          | 0.0125                 | 0.5202   | 14.7202    |
+| 2.3634        | 1.0    | 30565 | 2.3471          | 0.0126                 | 0.5535   | 10.4554    |
+| 2.381         | 2.0    | 61130 | 2.2835          | 0.0126                 | 0.5619   | 9.8107     |
+| 2.3067        | 2.9999 | 91692 | 2.2631          | 0.0126                 | 0.5672   | 9.6125     |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c88f9cc9a98b2977689f1c3a7463ad238e06eb2303ad3bd4e8df78b8e8c5f941
+oid sha256:1bc69c1c2ce8b7887e34b511d0fcbd825f5454a5b3b2aa114fafb50999c76ee3
 size 11935008

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33c132f516d11637882cd935e90238237d00ed8e00f75f31b5c9c8639b8bf23f
+oid sha256:d89d1d2162cf22cfc9742266df0a7957fcd54c7d01b3d3773e949b56a3ac7287
 size 5432