End of training

README.md

@@ -0,0 +1,54 @@
+---
+license: apache-2.0
+base_model: dandelin/vilt-b32-mlm
+tags:
+- generated_from_trainer
+datasets:
+- coco_vqa_small_dataset
+model-index:
+- name: vilt_finetuned_1_epoch
+  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. -->
+
+# vilt_finetuned_1_epoch
+
+This model is a fine-tuned version of [dandelin/vilt-b32-mlm](https://huggingface.co/dandelin/vilt-b32-mlm) on the coco_vqa_small_dataset 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: 1
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.40.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,105 @@
+{
+  "_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": "room",
+    "1": "united states",
+    "2": "airport",
+    "3": "australia",
+    "4": "usa",
+    "5": "windows",
+    "6": "home",
+    "7": "fridge",
+    "8": "in car",
+    "9": "park",
+    "10": "england",
+    "11": "on sidewalk",
+    "12": "nothing",
+    "13": "mouse",
+    "14": "sun",
+    "15": "smile",
+    "16": "refrigerator",
+    "17": "british",
+    "18": "freezer",
+    "19": "hotel",
+    "20": "car",
+    "21": "indoors",
+    "22": "woods",
+    "23": "buildings",
+    "24": "uk",
+    "25": "nowhere",
+    "26": "cows",
+    "27": "dog",
+    "28": "bus",
+    "29": "america",
+    "30": "living room",
+    "31": "ground",
+    "32": "us",
+    "33": "inside",
+    "34": "yes",
+    "35": "hallway"
+  },
+  "image_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "airport": 2,
+    "america": 29,
+    "australia": 3,
+    "british": 17,
+    "buildings": 23,
+    "bus": 28,
+    "car": 20,
+    "cows": 26,
+    "dog": 27,
+    "england": 10,
+    "freezer": 18,
+    "fridge": 7,
+    "ground": 31,
+    "hallway": 35,
+    "home": 6,
+    "hotel": 19,
+    "in car": 8,
+    "indoors": 21,
+    "inside": 33,
+    "living room": 30,
+    "mouse": 13,
+    "nothing": 12,
+    "nowhere": 25,
+    "on sidewalk": 11,
+    "park": 9,
+    "refrigerator": 16,
+    "room": 0,
+    "smile": 15,
+    "sun": 14,
+    "uk": 24,
+    "united states": 1,
+    "us": 32,
+    "usa": 4,
+    "windows": 5,
+    "woods": 22,
+    "yes": 34
+  },
+  "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": "4.40.2",
+  "type_vocab_size": 2,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1512877cb4d279a64120eb9b8088a9eccc63773d1e65e1b4d1db8a939276b104
+size 451363200

preprocessor_config.json

@@ -0,0 +1,40 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "size_divisor",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "do_pad",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "ViltImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "ViltProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 384
+  },
+  "size_divisor": 32
+}

runs/May15_22-11-23_arg10/events.out.tfevents.1715782287.arg10.562.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61e05d819d772fc4ce8bc2bf11a5403d35679e8a7056a79962d1678807ef8986
+size 37049

runs/May15_22-15-28_arg10/events.out.tfevents.1715782530.arg10.699.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:358a8864d045eb0447465674e18e563c2859423c1a68768a08e3729a2b6f378c
+size 32808

runs/May15_22-49-26_arg10/events.out.tfevents.1715784567.arg10.914.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20621fdd92aab8c32dcd95b577b8768c24c4de6668eb271f9ac5cf589fbc2f73
+size 37256

runs/May15_23-11-11_arg10/events.out.tfevents.1715785875.arg10.1066.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4264351d0983a5e6f28d7f45d67b94a89925938401983a640869df61d6170dd9
+size 6468

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 +1,56 @@
+{
+  "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_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 40,
+  "pad_token": "[PAD]",
+  "processor_class": "ViltProcessor",
+  "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 sha256:07909c8c4b1adb31814a93953935b79eac6ba42176c872efdddaed8dfb3ce4b0
+size 5048