jjdd

README.md

@@ -1,7 +1,7 @@
 ---
-base_model: google/paligemma-3b-pt-224
 library_name: peft
 license: gemma
+base_model: google/paligemma2-3b-pt-224
 tags:
 - generated_from_trainer
 model-index:
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # paligemma_Graph_DESC_v2
 
-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.
+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.
 
 ## Model description
 
@@ -39,20 +39,16 @@ The following hyperparameters were used during training:
 - seed: 42
 - gradient_accumulation_steps: 8
 - total_train_batch_size: 16
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- 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: 2
 - mixed_precision_training: Native AMP
 
-### Training results
-
-
-
 ### Framework versions
 
-- PEFT 0.12.0
-- Transformers 4.44.0.dev0
-- Pytorch 2.1.2
-- Datasets 2.20.0
-- Tokenizers 0.19.1
+- PEFT 0.14.0
+- Transformers 4.47.1
+- Pytorch 2.4.1+cu121
+- Datasets 3.2.0
+- Tokenizers 0.21.0

adapter_config.json

@@ -1,8 +1,10 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "google/paligemma-3b-pt-224",
+  "base_model_name_or_path": "google/paligemma2-3b-pt-224",
   "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
@@ -11,6 +13,7 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 8,
+  "lora_bias": false,
   "lora_dropout": 0.0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -20,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "gate_proj",
+    "q_proj",
     "down_proj",
-    "up_proj",
-    "v_proj",
     "k_proj",
-    "q_proj"
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "up_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:b2b61f9f0a95393e773857a03de6b9eccd0a7c4ad40592e06f142e2f373b8aa3
-size 45258384
+oid sha256:cc19cf0a53f31a8353ed1eb2f888b2f1a4513a4d5a4f7e1af87c9c3ffcd1e166
+size 47584968

runs/Dec21_11-11-08_1e0cdd42fbb4/events.out.tfevents.1734779703.1e0cdd42fbb4.40.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04340ce29f8bbe7fc678b6c75f09d06ca9d100405e3ecf1fff5fa979a1db1f4f
+size 12669

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b3126221171ba0b50d7427655e54bc422d1c76e5a480c8e0c5721b0fd971d7a
-size 5176
+oid sha256:4d2189982d4286616101ee3d18e76ec97208749cd0a55bea1c81ba26b4a9b4aa
+size 5368