Training in progress, epoch 0

adapter_config.json

@@ -1,8 +1,11 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "OpenGVLab/InternVL3_5-1B",
+  "base_model_name_or_path": "OpenGVLab/InternVL3_5-1B-HF",
   "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
@@ -11,24 +14,29 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 32,
+  "lora_bias": false,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
+  "qalora_group_size": 16,
   "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "down_proj",
     "q_proj",
-    "up_proj",
-    "v_proj",
+    "k_proj",
+    "gate_proj",
     "o_proj",
-    "k_proj"
+    "v_proj",
+    "up_proj",
+    "down_proj"
   ],
+  "target_parameters": null,
   "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
   "use_dora": false,
+  "use_qalora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24b2b9da6f8e216e1c9fe55ac59cddde3b1e48297da5648a64de5d04afa1eec0
-size 40428048
+oid sha256:751aa57c18861264ac5b6a4001537ef373adec790e026a8369d3259fea73e1e2
+size 49887496