Model save

README.md

@@ -6,6 +6,8 @@ tags:
 - sft
 - generated_from_trainer
 base_model: meta-llama/Meta-Llama-3-8B-Instruct
+datasets:
+- generator
 model-index:
 - name: Llama3-stanford-encyclopedia-philosophy-QA
   results: []
@@ -16,7 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Llama3-stanford-encyclopedia-philosophy-QA
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.9202
 
 ## Model description
 
@@ -46,6 +50,20 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_ratio: 0.03
 - num_epochs: 3
 
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.9641        | 0.3529 | 15   | 1.9525          |
+| 1.9096        | 0.7059 | 30   | 1.9184          |
+| 1.8421        | 1.0588 | 45   | 1.9071          |
+| 1.7913        | 1.4118 | 60   | 1.8996          |
+| 1.7812        | 1.7647 | 75   | 1.8928          |
+| 1.6468        | 2.1176 | 90   | 1.9158          |
+| 1.5843        | 2.4706 | 105  | 1.9286          |
+| 1.5829        | 2.8235 | 120  | 1.9202          |
+
+
 ### Framework versions
 
 - PEFT 0.10.0