End of training

README.md

@@ -3,6 +3,7 @@ library_name: transformers
 base_model: AI-MO/Qwen2.5-Math-7B-Instruct-formal-prover-ft-v7.1-020425-CSFT
 tags:
 - llama-factory
+- full
 - generated_from_trainer
 model-index:
 - name: Qwen2.5-Math-7B-Instruct-formal-prover-ft-v8-090425-CSFT
@@ -14,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Qwen2.5-Math-7B-Instruct-formal-prover-ft-v8-090425-CSFT
 
-This model is a fine-tuned version of [AI-MO/Qwen2.5-Math-7B-Instruct-formal-prover-ft-v7.1-020425-CSFT](https://huggingface.co/AI-MO/Qwen2.5-Math-7B-Instruct-formal-prover-ft-v7.1-020425-CSFT) on an unknown dataset.
+This model is a fine-tuned version of [AI-MO/Qwen2.5-Math-7B-Instruct-formal-prover-ft-v7.1-020425-CSFT](https://huggingface.co/AI-MO/Qwen2.5-Math-7B-Instruct-formal-prover-ft-v7.1-020425-CSFT) on the formal-prover-ft-v8-090425 dataset.
 
 ## Model description
 

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 769456799612928.0,
+    "train_loss": 0.17196391693531612,
+    "train_runtime": 18817.4017,
+    "train_samples_per_second": 1.247,
+    "train_steps_per_second": 0.078
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 769456799612928.0,
+    "train_loss": 0.17196391693531612,
+    "train_runtime": 18817.4017,
+    "train_samples_per_second": 1.247,
+    "train_steps_per_second": 0.078
+}