End of training

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: peft
 license: gemma
-base_model: google/paligemma2-3b-pt-224
+base_model: google/paligemma2-10b-pt-224
 tags:
 - generated_from_trainer
 model-index:
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # finetuned_paligemma2_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/paligemma2-10b-pt-224](https://huggingface.co/google/paligemma2-10b-pt-224) on an unknown dataset.
 
 ## Model description
 
@@ -37,9 +37,9 @@ The following hyperparameters were used during training:
 - train_batch_size: 3
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 5
-- total_train_batch_size: 15
-- optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 12
+- optimizer: Use adamw_hf 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: 150
@@ -52,6 +52,6 @@ The following hyperparameters were used during training:
 
 - PEFT 0.14.0
 - Transformers 4.47.1
-- Pytorch 2.2.2+cu121
+- Pytorch 2.5.1+cu121
 - Datasets 3.2.0
 - Tokenizers 0.21.0

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/paligemma2-10b-pt-224",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
@@ -23,16 +23,16 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "o_proj",
+    "lora_megnitude_vector",
     "v_proj",
-    "k_proj",
     "down_proj",
-    "lora_megnitude_vector",
+    "o_proj",
+    "gate_proj",
     "up_proj",
-    "gate_proj"
+    "k_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
-  "use_dora": true,
+  "use_dora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc32b2d802f1350daa58160c548a8cf696af2f01b13cffb743c329948d3f4975
-size 50821720
+oid sha256:e665b6da20addd901b82421a662d77ee436804decb7d88fb76434f24893f021d
+size 114121264

runs/Dec26_23-02-43_6d5fcf09ec9f/events.out.tfevents.1735254163.6d5fcf09ec9f.7637.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e428b0c76b4033d924e390c33d322984fd37a38017d29f1e115b63d8fbf1223d
+size 5836

runs/Dec26_23-07-02_6d5fcf09ec9f/events.out.tfevents.1735254423.6d5fcf09ec9f.12348.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4450b509ce9e1046dc82f6066f2802f6f2d4a7c8628b37f16de6d186680368ca
+size 4184

runs/Dec26_23-08-18_6d5fcf09ec9f/events.out.tfevents.1735254498.6d5fcf09ec9f.12830.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f70a4a50e1976a173bbd2217b2a7d124ffcf3b5bbfc45e48a00288d5b3ae8cbc
+size 22485

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65fb7c9c2bbe97824e43c756000a70c85e558c4d730775968e97a7ddf3ae29c5
+oid sha256:a2786f2b12eac92c733de0303062835d15883e56fc81d96a762b8846ebc0544f
 size 5368