End of training

README.md

@@ -0,0 +1,53 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: HuggingFaceTB/SmolVLM-256M-Instruct
+tags:
+- generated_from_trainer
+model-index:
+- name: SmolVLM-256M-Instruct-manifestasi-v1
+  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-256M-Instruct-manifestasi-v1
+
+This model is a fine-tuned version of [HuggingFaceTB/SmolVLM-256M-Instruct](https://huggingface.co/HuggingFaceTB/SmolVLM-256M-Instruct) 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: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- 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
+
+### Framework versions
+
+- PEFT 0.15.2
+- Transformers 4.51.3
+- Pytorch 2.6.0+cu124
+- Datasets 3.6.0
+- Tokenizers 0.21.1

adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "Idefics3ForConditionalGeneration",
+    "parent_library": "transformers.models.idefics3.modeling_idefics3"
+  },
+  "base_model_name_or_path": "HuggingFaceTB/SmolVLM-256M-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "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": [
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "q_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09b09420aef8857b567f70abfc5fdc4bdca47c64da5e817166379bd80c674f8f
+size 11608320

runs/May15_00-01-26_a05e3dd23844/events.out.tfevents.1747267293.a05e3dd23844.3648.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3435640b67fae8453b7ac434ee9a62ba29e666de162284bc70287ad93c633bc5
+size 13516

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f070ea84910ea0887477b260e711ac246f5c511b128e68a635b132dcff4c5b30
+size 5368