End of training

README.md

@@ -4,6 +4,7 @@ license: other
 base_model: Qwen/Qwen2.5-3B-Instruct
 tags:
 - llama-factory
+- full
 - generated_from_trainer
 model-index:
 - name: Qwen2.5-3B-Instruct-OT3-8K-R1-ML
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Qwen2.5-3B-Instruct-OT3-8K-R1-ML
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct) on the ot3_8k_r1_min_length dataset.
 
 ## Model description
 

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 432224790970368.0,
+    "train_loss": 0.5731080526353759,
+    "train_runtime": 83358.552,
+    "train_samples_per_second": 0.5,
+    "train_steps_per_second": 0.063
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 432224790970368.0,
+    "train_loss": 0.5731080526353759,
+    "train_runtime": 83358.552,
+    "train_samples_per_second": 0.5,
+    "train_steps_per_second": 0.063
+}