Training in progress, epoch 2

adapter_config.json

@@ -1,28 +1,34 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "stabilityai/stable-diffusion-3-medium-diffusers",
+  "base_model_name_or_path": "google/paligemma-3b-pt-224",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
-  "init_lora_weights": "gaussian",
+  "init_lora_weights": true,
   "layer_replication": null,
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 4,
+  "lora_alpha": 8,
   "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 4,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "to_k",
-    "to_q",
-    "to_v",
-    "to_out.0"
+    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj",
+    "v_proj",
+    "q_proj"
   ],
+  "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:f75d6a80d3644d9beee51010c8c8fd89fa36b950b532d3e4ff8a13413f328581
+oid sha256:0628106f6b498600cd7fcbf8670d61ccdf6f16af1f358e12922106beadaac4b0
 size 45258384