End of training

README.md

@@ -4,6 +4,7 @@ license: apache-2.0
 base_model: Qwen/Qwen3-8B
 tags:
 - llama-factory
+- full
 - generated_from_trainer
 model-index:
 - name: VeriThoughts-Reasoning-7B-Qwen3-Test
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # VeriThoughts-Reasoning-7B-Qwen3-Test
 
-This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on an unknown dataset.
+This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the reasoning_dataset dataset.
 
 ## Model description
 

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 146165521711104.0,
+    "train_loss": 0.3971822352996513,
+    "train_runtime": 6153.7064,
+    "train_samples_per_second": 0.781,
+    "train_steps_per_second": 0.098
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 146165521711104.0,
+    "train_loss": 0.3971822352996513,
+    "train_runtime": 6153.7064,
+    "train_samples_per_second": 0.781,
+    "train_steps_per_second": 0.098
+}