Training in progress, step 10

adapter_config.json

@@ -1,11 +1,39 @@
 {
-  "adapter_type": "steering_vector_toggle",
-  "base_model": "unsloth/Qwen3-14B",
-  "layer_idx": 16,
-  "alpha": 256.0,
-  "hidden_size": 5120,
-  "steering_vector_path": "checkpoints/final/steering_vector.pt",
-  "approach": "toggle_based",
-  "memory_efficient": true,
-  "num_checkpoints": 160
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Qwen3-14B",
+  "bias": "none",
+  "corda_config": null,
+  "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": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "down_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "o_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": true
 }

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:500a9482d35400b31500dd1b580534e6a3c24e0de838f1c69d43a8be54b417f1
+size 513877864

special_tokens_map.json

@@ -21,5 +21,11 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|im_end|>"
+  "pad_token": {
+    "content": "<|vision_pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90550ebb7ce088ce5bc24596b1316d8d0aa741378a89d68198f482fb7d3cce4e
-size 11422929
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -232,7 +232,7 @@
   "errors": "replace",
   "extra_special_tokens": {},
   "model_max_length": 40960,
-  "pad_token": "<|im_end|>",
+  "pad_token": "<|vision_pad|>",
   "padding_side": "right",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb6de66e3fe852c1e00b5bef4ae321a94f547f2c407241301f03edce25795f2a
+size 5969