End of training

README.md

@@ -0,0 +1,60 @@
+---
+library_name: peft
+license: gemma
+base_model: google/paligemma2-3b-pt-896
+tags:
+- base_model:adapter:google/paligemma2-3b-pt-896
+- lora
+- transformers
+pipeline_tag: text-generation
+model-index:
+- name: paligemma_vqav2
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# paligemma_vqav2
+
+This model is a fine-tuned version of [google/paligemma2-3b-pt-896](https://huggingface.co/google/paligemma2-3b-pt-896) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 4
+- optimizer: Use OptimizerNames.ADAMW_TORCH 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
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.17.1
+- Transformers 4.57.0.dev0
+- Pytorch 2.8.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.22.0

adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/paligemma2-3b-pt-896",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 8,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "gate_proj",
+    "up_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9bf74a974b414bce91d43265135ae5291c5e676dc33305dd1ef42e3a595db47
+size 47585944

runs/Sep10_07-46-59_0302-dsm2-prxmx70028/events.out.tfevents.1757490428.0302-dsm2-prxmx70028.11511.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8107341aaf78e2d5229282c3bb8a53e533bf8a3b5b1ba2c50050350975c4be9e
+size 6742

runs/Sep10_07-51-14_0302-dsm2-prxmx70028/events.out.tfevents.1757490681.0302-dsm2-prxmx70028.11511.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6264670698edfe988cfda49142d48880ce9b4e4c33dd0a4fc9cac33b863a2185
+size 6742

runs/Sep10_07-52-41_0302-dsm2-prxmx70028/events.out.tfevents.1757490766.0302-dsm2-prxmx70028.11511.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c723c5e87df18b65d076e9ab84ef4f4a24a112cc044c80a3c65dbad1da4717d
+size 7090

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2c758bd2746428b62a63c3a31ab785631cb070dc51876416a75fbc99b55884f
+size 5777