End of training

README.md

@@ -3,7 +3,7 @@ license: gemma
 library_name: peft
 tags:
 - generated_from_trainer
-base_model: google/paligemma-3b-pt-224
+base_model: google/paligemma-3b-mix-224
 model-index:
 - name: paligemma_vqav2
   results: []
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # paligemma_vqav2
 
-This model is a fine-tuned version of [google/paligemma-3b-pt-224](https://huggingface.co/google/paligemma-3b-pt-224) on the None dataset.
+This model is a fine-tuned version of [google/paligemma-3b-mix-224](https://huggingface.co/google/paligemma-3b-mix-224) on the None dataset.
 
 ## Model description
 

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "google/paligemma-3b-pt-224",
+  "base_model_name_or_path": "google/paligemma-3b-mix-224",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
+    "o_proj",
     "v_proj",
-    "up_proj",
-    "down_proj",
+    "gate_proj",
     "k_proj",
+    "up_proj",
     "q_proj",
-    "o_proj"
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29365ccedb9f1392dc8561d103d95526cf2563646c641663eb245389a3bca88b
+oid sha256:47788e0e113805a9ada0b28dd24cad06ae15aec097bf173d37fde7a551130d5c
 size 45258384

runs/Jun07_18-20-20_amanali/events.out.tfevents.1717766425.amanali.2826301.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6611687010d019ff50138bdc4fc96e8dd98a77bdc80297256bdc1ce5037514bd
+size 6710

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76628232e028f26f763508e2d79d1db1b077407bf83f712d5baf16e19e125d2d
+oid sha256:073c69930f37b88e96199fd967d759f008a07da483a93fb0da365ff07a799c8c
 size 4667