Model save

README.md

@@ -0,0 +1,57 @@
+---
+library_name: peft
+license: llama3.2
+base_model: meta-llama/Llama-3.2-11B-Vision
+tags:
+- generated_from_trainer
+model-index:
+- name: lora
+  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. -->
+
+# lora
+
+This model is a fine-tuned version of [meta-llama/Llama-3.2-11B-Vision](https://huggingface.co/meta-llama/Llama-3.2-11B-Vision) 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: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 2
+- num_epochs: 2
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.13.2
+- Transformers 4.45.2
+- Pytorch 2.3.1
+- Datasets 3.0.1
+- Tokenizers 0.20.1

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "MllamaForConditionalGeneration",
+    "parent_library": "transformers.models.mllama.modeling_mllama"
+  },
+  "base_model_name_or_path": "meta-llama/Llama-3.2-11B-Vision",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": "gaussian",
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 8,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "gate_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "task_type": null,
+  "use_dora": true,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a6026aa23f3497dc6f6531b20bedfa8db4d82d4ed40342ab820017ba9c675ea
+size 125866776

runs/Oct21_18-15-19_209-20-158-74/events.out.tfevents.1729534549.209-20-158-74.2585.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae65c27b0231de15144b886d196d836dff1134b9ff45c6f044b1db8411f0b99e
+size 10551

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d12f3ccd5f35783e0919f758e768d645274a37d19984ab1f7babda134e9315f
+size 5176