Training in progress, epoch 1

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "Qwen/Qwen2-1.5B-Instruct",
+  "base_model_name_or_path": "Qwen/Qwen2-7B-Instruct",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -21,9 +21,9 @@
   "revision": null,
   "target_modules": [
     "v_proj",
-    "o_proj",
     "k_proj",
-    "q_proj"
+    "q_proj",
+    "o_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:be084b2864a73c4b83caaba69a568d0d4dcbb80366f25984b0dbfc3639f3f9f8
-size 69760376
+oid sha256:ef64e7f61c6278300455b9ab503bb69978078f372f7d7edb22093b7ed61a04cf
+size 161510984

tokenizer_config.json

@@ -35,7 +35,7 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",
-  "model_max_length": 32768,
+  "model_max_length": 131072,
   "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 sha256:05d0190e2610db4b7d1e62551f98783c75fdb9d12c614c8789551b58ccfbf6f0
+oid sha256:6468c35a2684fbb6502e7283b841b08ffe4068eeeffe6a115df9b7fea8f68918
 size 5368