Training in progress, step 500

adapter_config.json

@@ -0,0 +1,34 @@
+{
+ "alpha_pattern": {},
+ "auto_mapping": null,
+ "base_model_name_or_path": "google/paligemma-3b-pt-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": 8,
+ "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": [
+ "o_proj",
+ "q_proj",
+ "up_proj",
+ "v_proj",
+ "gate_proj",
+ "down_proj",
+ "k_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:f0d957948a3e1437f8bf7f4710da4199d275eedb5aa0cb77e79ac51ae2fea260
+size 90454136

runs/Jul15_14-54-24_talworks/events.out.tfevents.1721022864.talworks.78606.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cec2e3ad51af816fca2d21dd865bcaa0bcfaaac332929d5e6cbf237da25b23a3
+size 7853

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46c6aed5689faaa5ab7fcdfbac205146c092d04f6c91c0ea7025bbe1f9ae71d2
+size 5240