End of training

README.md

@@ -1,9 +1,11 @@
 ---
 base_model: Qwen/Qwen1.5-MoE-A2.7B
+datasets: HectorHe/math7k
 library_name: transformers
 model_name: Qwen1.5-MOE-aux-free-sft-math7k-1e-4-gamma
 tags:
 - generated_from_trainer
+- open-r1
 - trl
 - sft
 licence: license
@@ -11,7 +13,7 @@ licence: license
 
 # Model Card for Qwen1.5-MOE-aux-free-sft-math7k-1e-4-gamma
 
-This model is a fine-tuned version of [Qwen/Qwen1.5-MoE-A2.7B](https://huggingface.co/Qwen/Qwen1.5-MoE-A2.7B).
+This model is a fine-tuned version of [Qwen/Qwen1.5-MoE-A2.7B](https://huggingface.co/Qwen/Qwen1.5-MoE-A2.7B) on the [HectorHe/math7k](https://huggingface.co/datasets/HectorHe/math7k) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

config.json

@@ -33,7 +33,7 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.51.0",
-  "use_cache": false,
+  "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 151936
 }

training.log

@@ -439,3 +439,5 @@ weight_decay=0.0,
 2025-09-15 02:07:56 - INFO - __main__ -   model.layers.21.mlp: 60 experts, range=[-0.0312, 0.0312]
 2025-09-15 02:07:56 - INFO - __main__ -   model.layers.22.mlp: 60 experts, range=[-0.0312, 0.0312]
 2025-09-15 02:07:56 - INFO - __main__ -   model.layers.23.mlp: 60 experts, range=[-0.0312, 0.0312]
+2025-09-15 02:09:40 - INFO - __main__ - Model saved to /tmp/data/Qwen1.5-MOE/aux_free_sft/math7k/1e-4-gamma
+2025-09-15 02:09:40 - INFO - __main__ - Pushing to hub...