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,
@@ -21,8 +21,8 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "q_proj",
     "v_proj",
+    "q_proj",
     "o_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cd9b52928ea87f2d2d81f115a9965152fc10b6a8980cf4ff5149cc1a29d4337
-size 69760376
+oid sha256:bbd7ab9af0a33d0ed0f45bb4030995ec229348a25acd077dbb73b85b57920596
+size 161510984

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 1024,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

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 sha256:6fd1e4e3be6c71d518efb37ce42b186c76d46c4b10511483ea46f050325ecd1f
+oid sha256:90daf7de51c063ad3074ac84d09de8bd17ed31f1aec20b91c3d3afe278f3785d
 size 5368