End of training

README.md

@@ -4,6 +4,7 @@ license: apache-2.0
 base_model: Qwen/Qwen2.5-7B-Instruct
 tags:
 - llama-factory
+- full
 - generated_from_trainer
 model-index:
 - name: a1_math_open2math
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # a1_math_open2math
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/a1_math_open2math dataset.
 
 ## Model description
 

all_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 5.0,
-    "total_flos": 1515609891143680.0,
-    "train_loss": 0.29405738967753614,
-    "train_runtime": 24654.457,
-    "train_samples_per_second": 6.409,
-    "train_steps_per_second": 0.05
+    "epoch": 4.982278481012658,
+    "total_flos": 2.312324413665575e+18,
+    "train_loss": 0.2930771143637537,
+    "train_runtime": 126133.8526,
+    "train_samples_per_second": 1.253,
+    "train_steps_per_second": 0.01
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 5.0,
-    "total_flos": 1515609891143680.0,
-    "train_loss": 0.29405738967753614,
-    "train_runtime": 24654.457,
-    "train_samples_per_second": 6.409,
-    "train_steps_per_second": 0.05
+    "epoch": 4.982278481012658,
+    "total_flos": 2.312324413665575e+18,
+    "train_loss": 0.2930771143637537,
+    "train_runtime": 126133.8526,
+    "train_samples_per_second": 1.253,
+    "train_steps_per_second": 0.01
 }