ft-vilt-b32-mlm

README.md

@@ -0,0 +1,55 @@
+---
+license: apache-2.0
+base_model: dandelin/vilt-b32-mlm
+tags:
+- generated_from_trainer
+datasets:
+- vqa
+model-index:
+- name: ft-vilt-b32-mlm
+  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. -->
+
+# ft-vilt-b32-mlm
+
+This model is a fine-tuned version of [dandelin/vilt-b32-mlm](https://huggingface.co/dandelin/vilt-b32-mlm) on the vqa 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: 8
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 20
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.0.0
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,79 @@
+{
+  "_name_or_path": "dandelin/vilt-b32-mlm",
+  "architectures": [
+    "ViltForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "chopsticks",
+    "1": "picnic table",
+    "2": "yes",
+    "3": "boy",
+    "4": "crossing",
+    "5": "resting",
+    "6": "gray",
+    "7": "table",
+    "8": "4",
+    "9": "skateboard",
+    "10": "1",
+    "11": "at table",
+    "12": "green",
+    "13": "brown",
+    "14": "tired",
+    "15": "down",
+    "16": "watching",
+    "17": "walking",
+    "18": "10",
+    "19": "ice cream",
+    "20": "air",
+    "21": "shrimp",
+    "22": "no"
+  },
+  "image_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "1": 10,
+    "10": 18,
+    "4": 8,
+    "air": 20,
+    "at table": 11,
+    "boy": 3,
+    "brown": 13,
+    "chopsticks": 0,
+    "crossing": 4,
+    "down": 15,
+    "gray": 6,
+    "green": 12,
+    "ice cream": 19,
+    "no": 22,
+    "picnic table": 1,
+    "resting": 5,
+    "shrimp": 21,
+    "skateboard": 9,
+    "table": 7,
+    "tired": 14,
+    "walking": 17,
+    "watching": 16,
+    "yes": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "max_image_length": -1,
+  "max_position_embeddings": 40,
+  "modality_type_vocab_size": 2,
+  "model_type": "vilt",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "num_images": -1,
+  "patch_size": 32,
+  "qkv_bias": true,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 2,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8452601832466d911ad0081c723e70caf78bc575be2bbebc0d2fd46c4b122e0
+size 451283276

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee30d3fef0442816d77578e30edae42b09d1ce8f779d3d001b8c7bfe5cbc7c70
+size 4155