Training in progress, step 1

README.md

@@ -27,7 +27,7 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/ielts-science/huggingface/runs/2j3knxf9) 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/ielts-science/huggingface/runs/7af7s9gq) 
 
 
 This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).

adapter_config.json

@@ -29,13 +29,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "down_proj",
+    "up_proj",
+    "k_proj",
     "gate_proj",
-    "o_proj",
     "q_proj",
-    "k_proj",
-    "up_proj"
+    "v_proj",
+    "down_proj",
+    "o_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:deba35e0e587aa420f6b0141501528196114acfcadffb82c1a48a1ac50fc2ad5
+oid sha256:0f4f32b47401640185cde552d149163028219d3841d307139d2c9b25368cd74f
 size 66126768

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5434aab9cd2600c935e24641ebf68b4fd3ac64b1d4352233ee31e6e7dfae9307
+oid sha256:e7da30ed371923824ff6d38fcf5286a265972784473ee41d274ad933553ca239
 size 7825