End of training

README.md

@@ -0,0 +1,57 @@
+---
+library_name: peft
+license: gemma
+base_model: google/paligemma2-3b-pt-224
+tags:
+- generated_from_trainer
+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-224](https://huggingface.co/google/paligemma2-3b-pt-224) on the None 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_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: 5
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.14.0
+- Transformers 4.48.0.dev0
+- Pytorch 2.5.1+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "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,
+  "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",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "k_proj",
+    "down_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0249f7177eedf010f42932d9ec634f1c039e5ae5c0e67f17c07c07c1c6c388b4
+size 47584968

runs/Jan03_15-46-52_ip-172-31-15-216/events.out.tfevents.1735919259.ip-172-31-15-216.13131.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f0ff60aebe47cf755ee8a8df85042622e2070821537388a3959a0ac79fb1246
+size 5767

runs/Jan03_15-51-24_ip-172-31-15-216/events.out.tfevents.1735919508.ip-172-31-15-216.13131.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e8054cf84e3df0815c17187c7f047be72b0ff27e44a8219ba17b6f0822875a2
+size 5767

runs/Jan03_15-56-39_ip-172-31-15-216/events.out.tfevents.1735919808.ip-172-31-15-216.13131.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81ed51d541bc6d79b587223bdedc9998a833bfc4fccc3d15d497b4a2879be342
+size 5767

runs/Jan03_15-58-13_ip-172-31-15-216/events.out.tfevents.1735919899.ip-172-31-15-216.13131.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d52f3c3ddb443de13157cfd21e67cfcad62fdb8114ebdf7b63254a53623a65e0
+size 6115

runs/Jan03_15-59-56_ip-172-31-15-216/events.out.tfevents.1735920003.ip-172-31-15-216.13131.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4e8066c61354a5fe598b452cd927d32021f6bcd7d958074514847aec6dcac73
+size 6115

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78a729f7deee1a05b4429c93394d00b849e95d73248ac49a30c8a57688e59c85
+size 5304