End of training

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,75 @@
+---
+library_name: transformers
+license: gemma
+base_model: vidore/colpaligemma-3b-pt-448-base
+tags:
+- colpali
+- generated_from_trainer
+model-index:
+- name: finetune_colpali_v1_2-german_ver2-8bit
+  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. -->
+
+# finetune_colpali_v1_2-german_ver2-8bit
+
+This model is a fine-tuned version of [vidore/colpaligemma-3b-pt-448-base](https://huggingface.co/vidore/colpaligemma-3b-pt-448-base) on the German_docx dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1034
+- Model Preparation Time: 0.0101
+
+## 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: 4
+- 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: 10
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Model Preparation Time |
+|:-------------:|:------:|:----:|:---------------:|:----------------------:|
+| No log        | 0.0816 | 1    | 0.4123          | 0.0101                 |
+| 1.2101        | 0.8163 | 10   | 0.3859          | 0.0101                 |
+| 1.2237        | 1.6327 | 20   | 0.3079          | 0.0101                 |
+| 0.6883        | 2.4490 | 30   | 0.2464          | 0.0101                 |
+| 0.4804        | 3.2653 | 40   | 0.2011          | 0.0101                 |
+| 0.5187        | 4.0816 | 50   | 0.1792          | 0.0101                 |
+| 0.3899        | 4.8980 | 60   | 0.1563          | 0.0101                 |
+| 0.203         | 5.7143 | 70   | 0.1307          | 0.0101                 |
+| 0.1897        | 6.5306 | 80   | 0.0990          | 0.0101                 |
+| 0.3326        | 7.3469 | 90   | 0.1246          | 0.0101                 |
+| 0.3578        | 8.1633 | 100  | 0.1429          | 0.0101                 |
+| 0.3568        | 8.9796 | 110  | 0.1148          | 0.0101                 |
+| 0.1411        | 9.7959 | 120  | 0.1034          | 0.0101                 |
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.3.1
+- Datasets 3.1.0
+- Tokenizers 0.20.1

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "vidore/colpaligemma-3b-pt-448-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": 32,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(.*(language_model).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$|.*(custom_text_proj).*$)",
+  "task_type": "FEATURE_EXTRACTION",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6395b35b4ffc5ba30acbefe5465299ac7959c3590d58b96938fcfbd81cdd130
+size 157071680

preprocessor_config.json

@@ -0,0 +1,25 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "SiglipImageProcessor",
+  "image_seq_length": 1024,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "ColPaliProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 448,
+    "width": 448
+  }
+}

special_tokens_map.json

@@ -0,0 +1,39 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff84f53c290d0348c4e206da6094ef781cf8c0e482fec8b268a996b32257cfd
+size 34600975

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f959f38138aca0f64e025f0633730222ddacce9675e7b9e8d56fba2ce47d6a7
+size 5240