Training in progress, step 44

adapter_config.json

@@ -3,6 +3,8 @@
   "auto_mapping": null,
   "base_model_name_or_path": "Qwen/Qwen2-0.5B",
   "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
@@ -11,6 +13,7 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 16,
+  "lora_bias": false,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -20,8 +23,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_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 sha256:2a620e25934e469a8b270a2f9922f02e86689b5183d54ffb886e6f878af58466
+oid sha256:5a0da76a15c3e0a0dcf3f88ee33d69448ccc91e71e1d8de2c0bb4f4dcc88b369
 size 8663400

tokenizer_config.json

@@ -35,6 +35,7 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
   "errors": "replace",
+  "extra_special_tokens": {},
   "model_max_length": 32768,
   "pad_token": "<|endoftext|>",
   "split_special_tokens": false,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7aa817f51616ea5d83274cea099ed8dd46559c4750e8d66315b5ce19c85397f1
-size 5688
+oid sha256:28344a9081919b6de86592f6eb5ee9bd3de7032c10be475bebcacf3dac1ce216
+size 5752