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_formulas
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # a1_math_formulas
 
-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_formulas dataset.
 
 ## Model description
 

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.982278481012658,
-    "total_flos": 2.2387422629367644e+18,
-    "train_loss": 0.26373260683887373,
-    "train_runtime": 64181.8261,
-    "train_samples_per_second": 2.462,
-    "train_steps_per_second": 0.019
+    "total_flos": 2.090332464318251e+18,
+    "train_loss": 0.24650180314977962,
+    "train_runtime": 35345.5491,
+    "train_samples_per_second": 4.47,
+    "train_steps_per_second": 0.035
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.982278481012658,
-    "total_flos": 2.2387422629367644e+18,
-    "train_loss": 0.26373260683887373,
-    "train_runtime": 64181.8261,
-    "train_samples_per_second": 2.462,
-    "train_steps_per_second": 0.019
+    "total_flos": 2.090332464318251e+18,
+    "train_loss": 0.24650180314977962,
+    "train_runtime": 35345.5491,
+    "train_samples_per_second": 4.47,
+    "train_steps_per_second": 0.035
 }