Magneto/Paligemma_Image_Caption_Finetune

README.md

@@ -42,7 +42,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 2
-- num_epochs: 2
+- num_epochs: 1
 
 ### Training results
 

adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
     "k_proj",
     "o_proj",
-    "down_proj",
-    "q_proj",
     "v_proj",
+    "q_proj",
+    "gate_proj",
+    "down_proj",
     "up_proj"
   ],
   "task_type": "CAUSAL_LM",

runs/Jun03_13-30-35_e5c1ea114b39/events.out.tfevents.1717421436.e5c1ea114b39.35047.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74bf92333993fb66666ef6bda6e0b504a4b096f93210023b8e60ed4bd0a272d6
+size 6145

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7375c20682566eb856c40a685098e01aab24b1028dffef89505ce8f7994620bf
+oid sha256:65c74528289c1ba8e0b16679538c8fdf1838da6269865b1e308f3d2b2a102c8c
 size 5176