Training in progress, step 5

README.md

@@ -26,7 +26,7 @@ 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/micdonald/huggingface/runs/podtx771) 
+[<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/micdonald/huggingface/runs/vti5tdur) 
 
 
 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": [
-    "up_proj",
-    "gate_proj",
     "q_proj",
     "k_proj",
+    "up_proj",
+    "gate_proj",
+    "o_proj",
     "down_proj",
-    "v_proj",
-    "o_proj"
+    "v_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:a58240fedc4073a7b3c796507ecd3341f813f2e02fd72b88de04158aa6b6c789
+oid sha256:6a669128a72146420411e81327621aa9ec84bf3d780668b056a33f20fd155190
 size 167832240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a929e0f36547840c40406528167dcfe4fbdbc7dcf179bef933b7ccc3cf0c607
+oid sha256:e59cf36e265f5facceac70404328f2d5de6d257ce94a3c466f02c45f47beff3b
 size 7160