End of training

README.md

@@ -0,0 +1,51 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: HuggingFaceTB/SmolVLM-Base
+tags:
+- generated_from_trainer
+model-index:
+- name: SmolVLM-Base-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. -->
+
+# SmolVLM-Base-vqav2
+
+This model is a fine-tuned version of [HuggingFaceTB/SmolVLM-Base](https://huggingface.co/HuggingFaceTB/SmolVLM-Base) 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: 0.0001
+- train_batch_size: 72
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use paged_adamw_8bit 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: 50
+- num_epochs: 1
+
+### Framework versions
+
+- PEFT 0.14.0
+- Transformers 4.49.0
+- Pytorch 2.2.1
+- Datasets 3.3.2
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,40 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "Idefics3ForConditionalGeneration",
+    "parent_library": "transformers.models.idefics3.modeling_idefics3"
+  },
+  "base_model_name_or_path": "HuggingFaceTB/SmolVLM-Base",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "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_bias": false,
+  "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": [
+    "gate_proj",
+    "down_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "up_proj",
+    "q_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 sha256:460752af101c9343e78d0cd126e5210a48eb3e66db5688ecc35d9765853e6a58
+size 42220792

runs/Mar07_01-40-08_e7b0803fbb6b/events.out.tfevents.1741311615.e7b0803fbb6b.1189099.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6b3482fe24667fc3dba5de85c409ef77427901941a2dd56177e0f06ff2b3c30
+size 14291

runs/Mar07_16-39-33_e7b0803fbb6b/events.out.tfevents.1741365577.e7b0803fbb6b.2735626.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b85af05ad947c6d4b63d13321dd9a787df42d9e360631151dcf1eb9a91654815
+size 8472

runs/Mar07_16-39-33_e7b0803fbb6b/events.out.tfevents.1741365605.e7b0803fbb6b.2735626.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22b48cb1d1e067a036017a7f68d2ba15bb10e6dbebdd0933d189384e9ae3db76
+size 8472

runs/Mar07_16-55-42_e7b0803fbb6b/events.out.tfevents.1741366546.e7b0803fbb6b.2754248.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d9037523666611af348e8a334cae275ea420a0c746bb46e9cd4cf7fbf623449
+size 9526

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a8514445bfa7f5ed8450243ed396258e75f955cd6bb96dee590e4de662998ce
+size 5368