Training in progress, step 10

README.md

@@ -1,18 +1,18 @@
 ---
-base_model: unsloth/Qwen3-4B-unsloth-bnb-4bit
+base_model: unsloth/Qwen3-1.7B-unsloth-bnb-4bit
 library_name: transformers
 model_name: smart-emergency-grpo
 tags:
 - generated_from_trainer
 - unsloth
-- grpo
 - trl
+- grpo
 licence: license
 ---
 
 # Model Card for smart-emergency-grpo
 
-This model is a fine-tuned version of [unsloth/Qwen3-4B-unsloth-bnb-4bit](https://huggingface.co/unsloth/Qwen3-4B-unsloth-bnb-4bit).
+This model is a fine-tuned version of [unsloth/Qwen3-1.7B-unsloth-bnb-4bit](https://huggingface.co/unsloth/Qwen3-1.7B-unsloth-bnb-4bit).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

adapter_config.json

@@ -7,7 +7,7 @@
     "parent_library": "transformers.models.qwen3.modeling_qwen3",
     "unsloth_fixed": true
   },
-  "base_model_name_or_path": "unsloth/Qwen3-4B-unsloth-bnb-4bit",
+  "base_model_name_or_path": "unsloth/Qwen3-1.7B-unsloth-bnb-4bit",
   "bias": "none",
   "corda_config": null,
   "ensure_weight_tying": false,
@@ -34,13 +34,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "down_proj",
-    "gate_proj",
     "v_proj",
+    "o_proj",
     "k_proj",
+    "gate_proj",
+    "down_proj",
     "q_proj",
-    "o_proj"
+    "up_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:e66882ce5e8ea97c7d9bb909d1348ae5c1b776a897b1b224bb2317adeea6f729
-size 132187888
+oid sha256:932b61a20c5b78ee61c932e84155a3c6bf1fea8a48a19c2857501b2471aacc34
+size 69782384

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e3891a59089fdc7b05df276eddb9638706c9215c28a4e8f5db6693c2217a2ea
+oid sha256:2b96489e9994db0566c3f6f6d74088be1436a13f4cc4986b0ecdd1bed3fbc3f2
 size 7377