Oysiyl/colqwen-ft-ufo

README.md

@@ -0,0 +1,57 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: vidore/colqwen2-base
+tags:
+- generated_from_trainer
+model-index:
+- name: colqwen_ufo
+  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. -->
+
+# colqwen_ufo
+
+This model is a fine-tuned version of [vidore/colqwen2-base](https://huggingface.co/vidore/colqwen2-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: 5e-05
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Use 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: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.49.0
+- Pytorch 2.2.1+cu121
+- Datasets 3.3.1
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "ColQwen2",
+    "parent_library": "colpali_engine.models.qwen2.colqwen2.modeling_colqwen2"
+  },
+  "base_model_name_or_path": "vidore/colqwen2-base",
+  "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",
+    "q_proj",
+    "v_proj",
+    "down_proj",
+    "gate_proj",
+    "up_proj",
+    "k_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 sha256:0866271f3e8b6bb68736d119a984aa6a56e1fb7604ccf70240c5596e2408feb6
+size 18623184

runs/Feb19_20-36-07_ip-10-192-11-235/events.out.tfevents.1739997375.ip-10-192-11-235.1754.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e01beee100be8cc7a26a36de163a6d076f101b9f402dcf05d1664539979327c
+size 5537

runs/Feb19_20-39-08_ip-10-192-11-235/events.out.tfevents.1739997555.ip-10-192-11-235.1754.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d5eacbd600888adba2c03075d406cc80f6872ce2c030cc1aab2f0749532cb6c
+size 5537

runs/Feb20_18-52-22_ip-10-192-12-79/events.out.tfevents.1740077695.ip-10-192-12-79.114078.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86cf8ffd54d27e7edfe967a6c74db79b64ab95d2bd234e218167fed9d5994d7a
+size 5531

runs/Feb20_19-25-08_ip-10-192-12-165/events.out.tfevents.1740079515.ip-10-192-12-165.13014.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:067d5110200b6af9a001cd24a85342fd2d60830fe8d458b79c24895e409e6f1e
+size 7122

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5ca25670196f835e6ad1a8cc2d51b088e6e581c3ad86ff5ff99486ced83317c
+size 5304