Model save

README.md

@@ -0,0 +1,79 @@
+---
+library_name: transformers
+license: bsd-3-clause
+base_model: Salesforce/blip-image-captioning-base
+tags:
+- generated_from_trainer
+model-index:
+- name: BLIP_Captioning
+  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_Captioning
+
+This model is a fine-tuned version of [Salesforce/blip-image-captioning-base](https://huggingface.co/Salesforce/blip-image-captioning-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0201
+
+## 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: 0.0001
+- train_batch_size: 2
+- eval_batch_size: 1
+- seed: 42
+- 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: 1000
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss |
+|:-------------:|:------:|:-----:|:---------------:|
+| 0.047         | 0.0446 | 500   | 0.0336          |
+| 0.0379        | 0.0892 | 1000  | 0.0419          |
+| 0.0285        | 0.1339 | 1500  | 0.0247          |
+| 0.0247        | 0.1785 | 2000  | 0.0254          |
+| 0.0244        | 0.2231 | 2500  | 0.0238          |
+| 0.0242        | 0.2677 | 3000  | 0.0240          |
+| 0.0239        | 0.3124 | 3500  | 0.0234          |
+| 0.0243        | 0.3570 | 4000  | 0.0235          |
+| 0.0502        | 0.4016 | 4500  | 0.0350          |
+| 0.0236        | 0.4462 | 5000  | 0.0227          |
+| 0.0228        | 0.4909 | 5500  | 0.0228          |
+| 0.0225        | 0.5355 | 6000  | 0.0249          |
+| 0.0232        | 0.5801 | 6500  | 0.0846          |
+| 0.0222        | 0.6247 | 7000  | 0.0223          |
+| 0.023         | 0.6693 | 7500  | 0.0213          |
+| 0.0217        | 0.7140 | 8000  | 0.0211          |
+| 0.0212        | 0.7586 | 8500  | 0.0210          |
+| 0.0213        | 0.8032 | 9000  | 0.0207          |
+| 0.0217        | 0.8478 | 9500  | 0.0204          |
+| 0.0203        | 0.8925 | 10000 | 0.0208          |
+| 0.0205        | 0.9371 | 10500 | 0.0206          |
+| 0.0207        | 0.9817 | 11000 | 0.0201          |
+
+
+### Framework versions
+
+- Transformers 4.55.4
+- Pytorch 2.1.2+cu121
+- Tokenizers 0.21.4

config.json

@@ -0,0 +1,52 @@
+{
+  "architectures": [
+    "BlipForConditionalGeneration"
+  ],
+  "image_text_hidden_size": 256,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "label_smoothing": 0.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "blip",
+  "projection_dim": 512,
+  "text_config": {
+    "attention_probs_dropout_prob": 0.0,
+    "encoder_hidden_size": 768,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 768,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "label_smoothing": 0.0,
+    "layer_norm_eps": 1e-12,
+    "max_position_embeddings": 512,
+    "model_type": "blip_text_model",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 12,
+    "projection_dim": 768,
+    "torch_dtype": "float32",
+    "use_cache": true,
+    "vocab_size": 30524
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.4",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "dropout": 0.0,
+    "hidden_act": "gelu",
+    "hidden_size": 768,
+    "image_size": 384,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "layer_norm_eps": 1e-05,
+    "model_type": "blip_vision_model",
+    "num_attention_heads": 12,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "patch_size": 16,
+    "projection_dim": 512,
+    "torch_dtype": "float32"
+  }
+}

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": "4.55.4"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:910352d541ff0955c2e646747f6066bb9180d6abe6227fc097c1e2551527d8fb
+size 989717056

preprocessor_config.json

@@ -0,0 +1,24 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": 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
+  }
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,63 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "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 sha256:157c46f7e208b51deb4a2b331aeb445b9d2a1a4154abe3e89faa1f677e787d68
+size 5560