Training in progress, step 10

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/on-planets/glm4-1v-8b/runs/ad4mye88) 
+[<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/on-planets/glm4-1v-8b/runs/z5hp2rsl) 
 
 
 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

@@ -25,17 +25,17 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
+    "v_proj",
     "q_proj",
+    "gate_up_proj",
+    "attn.proj",
     "o_proj",
-    "k_proj",
+    "up_proj",
+    "down_proj",
     "gate_proj",
     "qkv",
-    "up_proj",
-    "merger.proj",
-    "v_proj",
-    "gate_up_proj",
-    "attn.proj"
+    "k_proj",
+    "merger.proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f8f01b85acc9fdd2e532cbc2483f7e24013074889a8ee6a7d95497ca4cb75a3
+oid sha256:160498b090c81335fcfe5554d744d7d18229d90a4a6d917281fec358997f1926
 size 117320232

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cb34fbd5694acb2e2adb1e804f002ff21e90c41256b812c6efeee7f824ac5d3
+oid sha256:40dad4fba9b6f7a9d266261c01b97ad7dd9ef6342cdbdde39f88b69034e3429b
 size 6929