End of training

README.md

@@ -19,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [unsloth/llama-3.2-1b-instruct-bnb-4bit](https://huggingface.co/unsloth/llama-3.2-1b-instruct-bnb-4bit) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.9095
+- Loss: 1.8254
 
 ## Model description
 
@@ -39,14 +39,14 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 8
+- train_batch_size: 4
 - eval_batch_size: 8
 - seed: 3407
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 32
+- total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 50
+- lr_scheduler_warmup_steps: 100
 - num_epochs: 1
 - mixed_precision_training: Native AMP
 
@@ -54,9 +54,12 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 2.0803        | 0.3185 | 50   | 2.0749          |
-| 1.945         | 0.6369 | 100  | 1.9421          |
-| 1.9269        | 0.9554 | 150  | 1.9095          |
+| 1.8725        | 0.1594 | 50   | 1.9015          |
+| 1.8203        | 0.3187 | 100  | 1.8936          |
+| 1.766         | 0.4781 | 150  | 1.8729          |
+| 1.8071        | 0.6375 | 200  | 1.8494          |
+| 1.7771        | 0.7968 | 250  | 1.8358          |
+| 1.8222        | 0.9562 | 300  | 1.8254          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c1ab30a34e03a626b146eb47fa07c2530fc22c29f852827809ad2fb9a328747
+oid sha256:6ac7cfb78eb08b39cbe63df18394693b950a8c621294f2d4093c357e68b35939
 size 45118424