Training in progress, epoch 1

adapter_config.json

@@ -18,22 +18,25 @@
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
-  "modules_to_save": null,
+  "modules_to_save": [
+    "lm_head",
+    "embed_tokens"
+  ],
   "peft_type": "LORA",
-  "r": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "down_proj",
+    "fc2",
+    "out_proj",
     "q_proj",
-    "fc1",
+    "o_proj",
     "up_proj",
-    "fc2",
+    "v_proj",
     "k_proj",
-    "gate_proj",
-    "out_proj",
-    "o_proj"
+    "down_proj",
+    "fc1",
+    "gate_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 sha256:155a4bb01587d3038cee3c89befca01ea0fcef2b276ab8adb454d55379670ccd
-size 77119048
+oid sha256:aabe8db5f15f6e15caa5a117bb409d41331f32f60f9eca2d5f8d42b7185bb01b
+size 2839126480

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_pan_and_scan": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Gemma3ImageProcessor",
+  "image_seq_length": 256,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "pan_and_scan_max_num_crops": null,
+  "pan_and_scan_min_crop_size": null,
+  "pan_and_scan_min_ratio_to_activate": null,
+  "processor_class": "Gemma3Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 896,
+    "width": 896
+  }
+}

processor_config.json

@@ -0,0 +1,4 @@
+{
+  "image_seq_length": 256,
+  "processor_class": "Gemma3Processor"
+}

runs/Jun10_08-45-28_7ea6724ade3d/events.out.tfevents.1749545132.7ea6724ade3d.5178.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70306e962a406f4172c546f1ebeafac5b676032a0258a621352c85bf45faa576
+size 15217

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6ec2659e52e3d1aa82505357493940039828c81360d681090c3082f1878052c
-size 33384822
+oid sha256:1ebf1915455f8237564395182c49e3c685cfe3533b3d50ec6d49ce65ec43c32e
+size 33384723

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7401f90eb773cc9c00a06a08c17cc6d2a4d0ff8f0e33cb38f98a760c5a5ab57c
-size 6097
+oid sha256:4482a7007a820b2911a5238e1c0c2bbfd2d189c47fe9f16b2f3d6244fe91f2fc
+size 5688