llama-3.2-3b-it-finetuned_mind2web

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: meta-llama/Llama-3.2-1B-Instruct
+base_model: meta-llama/Llama-3.2-3B-Instruct
 library_name: peft
 license: llama3.2
 tags:
@@ -14,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama_finetune_mind2web
 
-This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.6648
+- Loss: 4.3766
 
 ## Model description
 
@@ -48,9 +48,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 7.566         | 1.0   | 505  | 5.1133          |
-| 4.9889        | 2.0   | 1010 | 4.7279          |
-| 4.7964        | 3.0   | 1515 | 4.6648          |
+| 7.5048        | 1.0   | 505  | 4.6510          |
+| 4.6129        | 2.0   | 1010 | 4.4311          |
+| 4.4755        | 3.0   | 1515 | 4.3766          |
 
 
 ### Framework versions