End of training

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: Qwen/Qwen3-1.7B
+base_model: Qwen/Qwen3-8B
 library_name: transformers
 model_name: cm_adapter
 tags:
@@ -11,7 +11,7 @@ licence: license
 
 # Model Card for cm_adapter
 
-This model is a fine-tuned version of [Qwen/Qwen3-1.7B](https://huggingface.co/Qwen/Qwen3-1.7B).
+This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -36,7 +36,7 @@ This model was trained with SFT.
 
 - TRL: 0.18.1
 - Transformers: 4.52.4
-- Pytorch: 2.5.1+cu121
+- Pytorch: 2.7.1
 - Datasets: 3.6.0
 - Tokenizers: 0.21.1
 

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "Qwen/Qwen3-1.7B",
+  "base_model_name_or_path": "Qwen/Qwen3-8B",
   "bias": "none",
   "corda_config": null,
   "eva_config": null,
@@ -24,12 +24,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
+    "q_proj",
     "v_proj",
-    "down_proj",
     "gate_proj",
+    "o_proj",
     "up_proj",
-    "q_proj"
+    "down_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:c7997a03bbcf90a0b63b6e7350bd1813021dc56ccb584bfd925926ad727f4c32
-size 64269832
+oid sha256:88ecfda7e503333ec0bc0046e813e37082b2a55f3b0f0633a328d7e74a925ea9
+size 162849256

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbebc83a66c33eec1fc8453c5394ee6d3809a5c27acb90d51a71567fbef5feb6
-size 5624
+oid sha256:69dd12af6b063a4bd155ac751bad13d8da2c0ad3eacf7b1610ce4f993ab9e887
+size 6033