Training in progress, step 500

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "Qwen/Qwen2-7B-Instruct",
+  "base_model_name_or_path": "Qwen/Qwen2-1.5B-Instruct",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
     "v_proj",
-    "q_proj",
-    "o_proj"
+    "o_proj",
+    "k_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:240ade4b91815ec00e1dcc57e24cc05178b5bdafe1ebb4c7d7e139583553b592
-size 161510984
+oid sha256:ee82c10bf1840edca5c60190a590ed9779ff723588f85509e8b023b0e2351b72
+size 69760376

tokenizer_config.json

@@ -35,7 +35,7 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",
-  "model_max_length": 131072,
+  "model_max_length": 32768,
   "pad_token": "<|im_end|>",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9860f10377ca8056a6ec4ed3a7266140196ae7cd1189616819a32cabb4999e23
+oid sha256:05d0190e2610db4b7d1e62551f98783c75fdb9d12c614c8789551b58ccfbf6f0
 size 5368