Training in progress, step 1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/paligemma-3b-mix-224",
+  "bias": "none",
+  "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": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05c098e261910f9ac967848fdd5649e1003a99317dd2b2030c0378892aa6d34b
+size 45259216

runs/Jun26_12-01-45_aid-iad-bm-gpu4-8-ad1-004/events.out.tfevents.1719403372.aid-iad-bm-gpu4-8-ad1-004.761080.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64b600b9d4c1d5fb153bf6f1685af1c4801e70eda030626131a1aae915e6856c
+size 5247

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4728c3acde31421058c99f1e5bb1a2b5578f7c5e4c5b019e0cb66c80a701f4f6
+size 5176