Training in progress, step 400

adapter_config.json

@@ -1,26 +1,34 @@
 {
+  "alpha_pattern": {},
   "auto_mapping": null,
   "base_model_name_or_path": "Qwen/Qwen2.5-0.5B",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
+  "layer_replication": null,
   "layers_pattern": null,
   "layers_to_transform": null,
+  "loftq_config": {},
   "lora_alpha": 256,
   "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
   "r": 128,
+  "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj",
-    "gate_proj",
-    "up_proj",
     "k_proj",
+    "o_proj",
+    "gate_proj",
+    "q_proj",
     "down_proj",
-    "o_proj"
+    "v_proj",
+    "up_proj"
   ],
-  "task_type": "CAUSAL_LM"
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c49223a0d1550ba7664593e2a68b858c40e8f465d4b44990732c750f7f786d19
+oid sha256:6e857cece1f271faa7222eee2f847e3ce6851cbb1c70ab0499af9f4f9ef7e9b0
 size 281587880

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef9f9c4ec8dc8ef81737756db109be659075addd53d2415359d306d4fc98b8dd
+oid sha256:935793d51a94086be2db454f4546a31b3804833bf28eb416c91350b96d028d54
 size 5947