Training in progress, epoch 1

adapter_config.json

@@ -13,7 +13,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 4,
   "lora_bias": false,
   "lora_dropout": 0.1,
   "megatron_config": null,
@@ -24,13 +24,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "k_proj",
-    "q_proj",
-    "up_proj",
+    "o_proj",
     "down_proj",
+    "k_proj",
+    "v_proj",
     "gate_proj",
-    "o_proj"
+    "up_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:603e13be47aaa467d938f19454c7da03545f2192955c9f348700c15e7f43e32f
+oid sha256:8fd9b74c8b64954b8770f45ba78513a708fe4a0faf22b1bb9672db60025d345c
 size 13093200

runs/May20_10-26-42_a7435d519f39/events.out.tfevents.1747736830.a7435d519f39.2140.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c39897051a5e69b95425c91730627c1e424b61a0ee9e518f220488771456884
+size 4184

tokenizer_config.json

@@ -51335,7 +51335,7 @@
     "image_token": "<image_soft_token>"
   },
   "image_token": "<image_soft_token>",
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 128,
   "pad_token": "<pad>",
   "processor_class": "Gemma3Processor",
   "sp_model_kwargs": null,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6d2ec19c7375b0a7a90d32ce3631167b9d9780bbdeedc09c24450ca03e8ccb9
-size 6097
+oid sha256:8e3056b15e9125de2ce03e8987f5a82f10171a1cec36f73cd81da4f2f0241a92
+size 5688