End of training

README.md

@@ -0,0 +1,57 @@
+---
+base_model: HuggingFaceM4/Idefics3-8B-Llama3
+library_name: peft
+license: apache-2.0
+tags:
+- generated_from_trainer
+model-index:
+- name: idefics3-llama-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. -->
+
+# idefics3-llama-vqav2
+
+This model is a fine-tuned version of [HuggingFaceM4/Idefics3-8B-Llama3](https://huggingface.co/HuggingFaceM4/Idefics3-8B-Llama3) 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: 0.0001
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 50
+- num_epochs: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.44.0.dev0
+- Pytorch 2.4.0
+- Datasets 2.21.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,37 @@
+{
+ "alpha_pattern": {},
+ "auto_mapping": {
+ "base_model_class": "Idefics3ForConditionalGeneration",
+ "parent_library": "transformers.models.idefics3.modeling_idefics3"
+ },
+ "base_model_name_or_path": "HuggingFaceM4/Idefics3-8B-Llama3",
+ "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": [
+ "o_proj",
+ "k_proj",
+ "q_proj",
+ "gate_proj",
+ "up_proj",
+ "down_proj",
+ "v_proj"
+ ],
+ "task_type": null,
+ "use_dora": false,
+ "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f875dd310a45eeeab0c18776412d631f49c999c159289fb1c5d5c84a7c4695da
+size 89947240

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:751e569262f5543099b96fa90b9eca72417638170e3e81380685f7d296ae3e6f
+size 5176