blip-MedTrinity-peft-1

README.md

@@ -1,7 +1,7 @@
 ---
-library_name: transformers
-license: mit
-base_model: gpt2
+library_name: peft
+license: bsd-3-clause
+base_model: Salesforce/blip-image-captioning-base
 tags:
 - generated_from_trainer
 model-index:
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # results
 
-This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
+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.
 
 ## Model description
 
@@ -35,14 +35,23 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
 - train_batch_size: 8
-- eval_batch_size: 8
+- eval_batch_size: 16
 - seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
 - 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
 - num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
 
 ### Framework versions
 
-- Transformers 4.48.3
-- Pytorch 2.5.1+cu124
-- Tokenizers 0.21.0
+- PEFT 0.14.0
+- Transformers 4.53.1
+- Pytorch 2.6.0+cu124
+- Datasets 3.6.0
+- Tokenizers 0.21.1

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "BlipForConditionalGeneration",
+    "parent_library": "transformers.models.blip.modeling_blip"
+  },
+  "base_model_name_or_path": "Salesforce/blip-image-captioning-base",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "qkv",
+    "value",
+    "key",
+    "query"
+  ],
+  "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:fc17514e2cb84add2753aeb95401b4e4a543ece35e8644aa44d84bd693812a10
+size 9463088

runs/Jul07_05-33-28_9cb0eddbcbad/events.out.tfevents.1751866409.9cb0eddbcbad.35.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8797d4d5a6bae3dfceeb21665840593f6ed5c4be97b2b32abc12647ef5789857
+size 5697

runs/Jul07_05-37-21_9cb0eddbcbad/events.out.tfevents.1751866700.9cb0eddbcbad.35.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc4fd4b3c66c0254417101051694472d6df979cf605c68a8dfe2fc8f5c17b07c
+size 5697

runs/Jul07_05-44-03_9cb0eddbcbad/events.out.tfevents.1751867045.9cb0eddbcbad.35.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2dabde39799d6a9b6e4212ac255d7884db3c3fa04b32c2101f83d8644593a63
+size 5697

runs/Jul07_05-44-42_9cb0eddbcbad/events.out.tfevents.1751867083.9cb0eddbcbad.35.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9239691e5afabd0c9973c4b2401b63954bb2874e04d9e56ff2e46109682b13d0
+size 6469

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a9f347ff47b4b7586130325d7764e7b8b6e1275d8cedc27cbe3446a28155e1a
-size 5304
+oid sha256:b4716299cc5b29265b2e49ec6c9763a0382574995077e87df67d0e85e7b6d712
+size 5368