End of training

README.md

@@ -4,6 +4,7 @@ library_name: peft
 license: llama3.1
 tags:
 - llama-factory
+- lora
 - generated_from_trainer
 model-index:
 - name: laaj_15k_label_only
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # laaj_15k_label_only
 
-This model is a fine-tuned version of [meta-llama/Llama-Guard-3-8B](https://huggingface.co/meta-llama/Llama-Guard-3-8B) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Llama-Guard-3-8B](https://huggingface.co/meta-llama/Llama-Guard-3-8B) on the beavertails_15k_ dataset.
 
 ## Model description
 

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 676226370502656.0,
+    "train_loss": 0.08742177106274499,
+    "train_runtime": 51369.7181,
+    "train_samples_per_second": 0.876,
+    "train_steps_per_second": 0.11
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 676226370502656.0,
+    "train_loss": 0.08742177106274499,
+    "train_runtime": 51369.7181,
+    "train_samples_per_second": 0.876,
+    "train_steps_per_second": 0.11
+}