gajanhcc007/colpali-g1000

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: peft
-license: apache-2.0
-base_model: vidore/ColSmolVLM-base
+license: gemma
+base_model: vidore/colpali-v1.2-hf
 tags:
 - generated_from_trainer
 model-index:
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # colpali_ufo
 
-This model is a fine-tuned version of [vidore/ColSmolVLM-base](https://huggingface.co/vidore/ColSmolVLM-base) on an unknown dataset.
+This model is a fine-tuned version of [vidore/colpali-v1.2-hf](https://huggingface.co/vidore/colpali-v1.2-hf) on an unknown dataset.
 
 ## Model description
 
@@ -34,16 +34,15 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 2
+- train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 8
+- 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: 3
-- mixed_precision_training: Native AMP
+- num_epochs: 1
 
 ### Training results
 
@@ -51,7 +50,8 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- PEFT 0.14.0
-- Transformers 4.49.0
+- PEFT 0.11.1
+- Transformers 4.50.0.dev0
 - Pytorch 2.5.1+cu124
+- Datasets 2.21.0
 - Tokenizers 0.21.0

adapter_config.json

@@ -1,13 +1,11 @@
 {
   "alpha_pattern": {},
   "auto_mapping": {
-    "base_model_class": "ColIdefics3",
-    "parent_library": "colpali_engine.models.idefics3.colidefics3.modeling_colidefics3"
+    "base_model_class": "ColPaliForRetrieval",
+    "parent_library": "transformers.models.colpali.modeling_colpali"
   },
-  "base_model_name_or_path": "vidore/ColSmolVLM-base",
+  "base_model_name_or_path": "vidore/colpali-v1.2-hf",
   "bias": "none",
-  "eva_config": null,
-  "exclude_modules": null,
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": "gaussian",
@@ -16,7 +14,6 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 8,
-  "lora_bias": false,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -26,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
+    "gate_proj",
     "v_proj",
     "down_proj",
-    "gate_proj",
     "o_proj",
-    "up_proj",
-    "k_proj",
-    "q_proj"
+    "q_proj",
+    "k_proj"
   ],
   "task_type": null,
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9b175eefd1915948058ef459f7a95057a9ec70c9aa75c5834b8d1e0d2a30de1
-size 42220792
+oid sha256:b47da99b739240599da87081ae55e706364676cfca625880f0994f36e57fa298
+size 45260040

runs/Mar03_13-55-06_d262a177bfae/events.out.tfevents.1741010111.d262a177bfae.975.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd6edfc2ffb8190da99752ae12dfdae4ad52f8ce89c81e278fd427913c07e80e
+size 7028

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65ab1c0a8d82377b964da64bd3d4c21d48b2e9b3a928c79650ccae9d861a3b5c
+oid sha256:d569c22b7f4d2e6ef0ff6225612f989e8dfec942cd0039b667a598e7d0276253
 size 5304