Training in progress, step 2000

adapter_config.json

@@ -3,7 +3,7 @@
   "alpha_pattern": {},
   "arrow_config": null,
   "auto_mapping": null,
-  "base_model_name_or_path": "Qwen/Qwen3-0.6B",
+  "base_model_name_or_path": null,
   "bias": "none",
   "corda_config": null,
   "ensure_weight_tying": false,
@@ -16,9 +16,9 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 128,
   "lora_bias": false,
-  "lora_dropout": 0.0,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8492345b1762cee01629ee589f91551b15ed7050fb203c8f919fc89131a4d75
+oid sha256:8a587ef502e10f6d043043c94ca4116d4eeb6340ebc4bc693dc9c72e6752fa4b
 size 36715216

config.json

@@ -282,8 +282,8 @@
   "label_smoothing": 0.0,
   "length_penalty": 1.0,
   "llm_dim": 1024,
-  "lora_alpha": 32,
-  "lora_dropout": 0.0,
+  "lora_alpha": 128,
+  "lora_dropout": 0.05,
   "lora_rank": 64,
   "lora_target_modules": [
     "q_proj",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0347348d2f9cd64839ab1875ed302a1e1c18f65a070a3643f044869e50d2dce4
+oid sha256:1063540454db7a2d8f22e28c4a5f1f2837a90898db9d936fdae454c11000b88e
 size 25172384