Training in progress - step 500

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-0.6B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 512,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "q_proj",
+    "gate_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c60241d6077141e1793eabc09a982c9b0dee84dc7430f2ae5b07302e3f14f8a1
+size 323014520

config.json

@@ -161,9 +161,9 @@
   "label_smoothing": 0.0,
   "length_penalty": 1.0,
   "llm_dim": 1024,
-  "lora_alpha": 128,
+  "lora_alpha": 512,
   "lora_dropout": 0.05,
-  "lora_rank": 64,
+  "lora_rank": 128,
   "lora_target_modules": [
     "q_proj",
     "k_proj",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e47c1dad96a0b9e1a85a0a0545ce0fda86d3a8a26bccf2306db9e3de0d48abcc
+oid sha256:cb28f306452543d726f6b8bca86d372d5977856d41b3e7bdede3654852335727
 size 25172384