valstu/colpali-hockey-ft-0.1

README.md

@@ -0,0 +1,57 @@
+---
+library_name: peft
+license: gemma
+base_model: vidore/colpali-v1.3-hf
+tags:
+- generated_from_trainer
+model-index:
+- name: colpali-hockey-ft-0.1
+  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. -->
+
+# colpali-hockey-ft-0.1
+
+This model is a fine-tuned version of [vidore/colpali-v1.3-hf](https://huggingface.co/vidore/colpali-v1.3-hf) 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: 5e-05
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Use OptimizerNames.ADAMW_TORCH 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: 100
+- num_epochs: 2
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.48.1
+- Pytorch 2.5.1+cu121
+- Datasets 3.2.0
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "ColPaliForRetrieval",
+    "parent_library": "transformers.models.colpali.modeling_colpali"
+  },
+  "base_model_name_or_path": "vidore/colpali-v1.3-hf",
+  "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",
+    "gate_proj",
+    "down_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj",
+    "up_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 sha256:900b8ea2360a60ddb2d14114c84c943d1f923f5f2d3e47e873fc2602a7ff53e4
+size 45260040

runs/Jan26_14-10-25_3d19c42928ff/events.out.tfevents.1737900631.3d19c42928ff.3758.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0e84b41927d77fabd50e06df238d6559f866a593b1c541af46f32a0820dd8d5
+size 11459

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bad48c07a070332ecbcd8d8832553ee018e6632c8ef4af7519d773061a9c8c84
+size 5304