End of training

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: peft
 license: gemma
-base_model: google/paligemma2-3b-pt-224
+base_model: google/paligemma-3b-pt-224
 tags:
 - generated_from_trainer
 model-index:
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # finetuned_paligemma_blackjack
 
-This model is a fine-tuned version of [google/paligemma2-3b-pt-224](https://huggingface.co/google/paligemma2-3b-pt-224) on an unknown dataset.
+This model is a fine-tuned version of [google/paligemma-3b-pt-224](https://huggingface.co/google/paligemma-3b-pt-224) on an unknown dataset.
 
 ## Model description
 
@@ -34,15 +34,15 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 6
-- eval_batch_size: 6
+- train_batch_size: 4
+- eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 3
-- total_train_batch_size: 18
+- total_train_batch_size: 12
 - optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 2
-- num_epochs: 50
+- num_epochs: 10
 
 ### Training results
 

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "google/paligemma2-3b-pt-224",
+  "base_model_name_or_path": "google/paligemma-3b-pt-224",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "q_proj",
     "v_proj",
-    "down_proj",
+    "o_proj",
     "k_proj",
-    "gate_proj",
-    "o_proj"
+    "down_proj",
+    "q_proj",
+    "up_proj",
+    "gate_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:f6b9b22decdd1ef0c965a40b883d72a83e0ac61130a12129c7cddf1843c739ff
-size 47584968
+oid sha256:bd68959c2531c02be28c2389adae5638895a01d99f08e7b8b9536149d5074e81
+size 45258384

runs/Dec14_21-39-10_ml-ubuntu/events.out.tfevents.1734212358.ml-ubuntu.2437523.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b87d47e11992fa1a0c7684493944e82f4e09ad1501c66cfbe1ea4feccccf6cd
+size 4184

runs/Dec14_21-53-57_ml-ubuntu/events.out.tfevents.1734213238.ml-ubuntu.2839262.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d104d40302d71e6c357cea5ada597cbf298a939b5a890147d8ecb41ec19d778e
+size 4184

runs/Dec14_21-55-51_ml-ubuntu/events.out.tfevents.1734213352.ml-ubuntu.2881180.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b78103e70ec7df274de3324eef042d113e7c1764bd001a6f39970a10526807ab
+size 7256

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d32aa38b159632ba657fc6c4f6b5ee58ea518dcb6b76eb5709b82a30be934e14
+oid sha256:cff7efc3c77541312c390ddb9653326c73dc9e3464d743e644f14ea7b90a2b12
 size 5304