End of training

README.md

@@ -0,0 +1,59 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: HuggingFaceTB/SmolVLM-Base
+tags:
+- base_model:adapter:HuggingFaceTB/SmolVLM-Base
+- lora
+- transformers
+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 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: 1
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 4
+- optimizer: Use OptimizerNames.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
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.18.0
+- Transformers 5.0.0.dev0
+- Pytorch 2.9.1+cu128
+- Datasets 4.4.1
+- Tokenizers 0.22.1

adapter_config.json

@@ -0,0 +1,49 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Idefics3ForConditionalGeneration",
+    "parent_library": "transformers.models.idefics3.modeling_idefics3"
+  },
+  "base_model_name_or_path": "HuggingFaceTB/SmolVLM-Base",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "up_proj",
+    "v_proj",
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_dora": true,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70daf17c16b74a92b084e068275c47d41061d4038ce1ccf174415cc86ea3a726
+size 45187904

runs/Nov25_19-53-59_blacc/events.out.tfevents.1764089639.blacc.6466.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:788d897dfe6e643c720dcd544746f3d9fb1bb1cdc5af47db7dc9ee64581bd391
+size 7994

runs/Nov25_19-54-50_blacc/events.out.tfevents.1764089690.blacc.6466.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12c6cef68ccec5dc26b9cda1a65d468e4860d5be3a8b1b75a3b66aec41591e8c
+size 7994

runs/Nov25_19-56-36_blacc/events.out.tfevents.1764089796.blacc.11118.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f283ca2f809c7aa5bddeefdb74a341ef36d75179bbea34dd3e98426918738f42
+size 7994

runs/Nov27_03-51-13_blacc/events.out.tfevents.1764204673.blacc.8551.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3654accb8e054ab66ab575c6488fca2a6d9188c67495fd13091b53b634ba0a30
+size 30905

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c35f089b62d668e79e8d433aae57f18ad46a4b34e47c2855e0654e700587fa0
+size 5201