jaimik69/blip-finetuned-100

README.md

@@ -0,0 +1,51 @@
+---
+license: bsd-3-clause
+base_model: Salesforce/blip-vqa-base
+tags:
+- generated_from_trainer
+model-index:
+- name: blip_finetuned
+  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. -->
+
+# blip_finetuned
+
+This model is a fine-tuned version of [Salesforce/blip-vqa-base](https://huggingface.co/Salesforce/blip-vqa-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
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 20
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu118
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "Salesforce/blip-vqa-base",
+  "architectures": [
+    "BlipForQuestionAnswering"
+  ],
+  "image_text_hidden_size": 256,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "blip",
+  "projection_dim": 512,
+  "text_config": {
+    "initializer_factor": 1.0,
+    "model_type": "blip_text_model",
+    "num_attention_heads": 12
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "vision_config": {
+    "dropout": 0.0,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "model_type": "blip_vision_model",
+    "num_channels": 3
+  }
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 30522,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.35.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdfa2b8193c1bd76a556c86bb3e7baf7e9d14357fdfa78c8700a1e4f6d45e5b0
+size 1538792184

preprocessor_config.json

@@ -0,0 +1,26 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "BlipImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "BlipProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 384,
+    "width": 384
+  },
+  "size_divisor": 32
+}

runs/Nov29_01-44-45_944f6ffe8dd5/events.out.tfevents.1701222319.944f6ffe8dd5.740.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3d2ff29a673954ffcfdc149524332e851b2c893d1064e49607c68ee73ce2539
+size 4199

runs/Nov29_01-44-45_944f6ffe8dd5/events.out.tfevents.1701222334.944f6ffe8dd5.740.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6d5efdc478baee6a0db002ed161bef5b912bea522248be48da05f45eace8e7f
+size 8310

runs/Nov29_01-44-45_944f6ffe8dd5/events.out.tfevents.1701222826.944f6ffe8dd5.740.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c1b33b349aadc3209a23af88a069d88334293a84f961727f6978dabe56e2c69
+size 4199

runs/Nov29_01-56-06_944f6ffe8dd5/events.out.tfevents.1701222967.944f6ffe8dd5.740.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f7469ef28a8c4e84ac778ede690f65b6fe51a42ad4a391d5a5afc225a0deb56
+size 4547

runs/Nov29_01-56-06_944f6ffe8dd5/events.out.tfevents.1701224280.944f6ffe8dd5.740.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f597fdf73f68490d729970098d5c5507c61758726d72da1f172ddb1181429518
+size 4184

runs/Nov29_02-19-22_944f6ffe8dd5/events.out.tfevents.1701224365.944f6ffe8dd5.10086.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93926502dc83782929d4820b2066905f9727eae6fdcbd6060640bdae4e610538
+size 4701

runs/Nov29_02-19-22_944f6ffe8dd5/events.out.tfevents.1701226813.944f6ffe8dd5.10086.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fca0804ccb0dc99f6f3ce689c0be3f76fa47848cf487482381a2a12b047b159a
+size 4184

runs/Nov29_02-19-22_944f6ffe8dd5/events.out.tfevents.1701226876.944f6ffe8dd5.10086.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d95a3f4cb318983748b3f345538a313836ec51f75be2ffe4b8041b912df3012
+size 4184

runs/Nov29_03-02-07_944f6ffe8dd5/events.out.tfevents.1701226928.944f6ffe8dd5.20712.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6982e0d7551720775df5d54bb8370102eeaaf2427c5c21ad52afd0d5e913f56e
+size 6117

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "processor_class": "BlipProcessor",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86d1f63ec4d4e816caaa3fcd243e1add0934fba2b08b94810cecaf6edb2a82c1
+size 4536