End of training

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: peft
 license: gemma
-base_model: google/paligemma2-3b-pt-448
+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_output
 
-This model is a fine-tuned version of [google/paligemma2-3b-pt-448](https://huggingface.co/google/paligemma2-3b-pt-448) 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
 
@@ -33,16 +33,16 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-06
-- train_batch_size: 1
+- learning_rate: 2e-05
+- train_batch_size: 3
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 8
-- total_train_batch_size: 8
+- total_train_batch_size: 24
 - 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: 50
+- num_epochs: 100
 
 ### Training results
 
@@ -50,7 +50,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- PEFT 0.13.2
-- Transformers 4.46.3
+- PEFT 0.14.0
+- Transformers 4.47.0
 - Pytorch 2.5.1+cu121
-- Tokenizers 0.20.3
+- Tokenizers 0.21.0

adapter_config.json

@@ -1,8 +1,10 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "google/paligemma2-3b-pt-448",
+  "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",
@@ -20,12 +23,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "k_proj",
-    "gate_proj",
-    "q_proj",
     "up_proj",
     "down_proj",
+    "gate_proj",
+    "q_proj",
+    "v_proj",
+    "k_proj",
     "o_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88b7f18590d5afb6a7e3239c1e11ddb2de72311a3fde154ee970b001ea8d7db2
+oid sha256:15b2df67b3e307fa02d658a592381f44ada0ef278391307f56ee6b8738a3bf70
 size 47584968

runs/Dec20_14-23-35_300e13238cef/events.out.tfevents.1734704620.300e13238cef.5584.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57adc5f17617d9e79d974fd129f9b8ce932dee6b03a67b49125c86dd546f2c30
+size 5789

runs/Dec20_14-27-08_300e13238cef/events.out.tfevents.1734704833.300e13238cef.5584.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc03a5374e4d617e0440a08761b4ac370399ad020ff642843dd1fe82cb75fe76
+size 10339

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb4c18602227f97b671ec64d6b076779edd9fdd23ef7c54174fe273231ee8441
+oid sha256:2076dfa69f6d9d4a60ea09580a0d4102ac1fb28cca4e91cfcf75362fccfa6ffc
 size 5304