./wmc_v2_vit_base_wm811k_cls_contra_learning_0916_9cls

README.md

@@ -0,0 +1,96 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google/vit-base-patch16-224
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: wmc_v2_vit_base_wm811k_cls_contra_learning_0916_9cls
+  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. -->
+
+# wmc_v2_vit_base_wm811k_cls_contra_learning_0916_9cls
+
+This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1013
+- Accuracy: 0.9670
+- Precision: 0.9209
+- Recall: 0.8649
+- F1: 0.8808
+
+## 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: 2e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 0.3763        | 0.1079 | 100  | 0.9646          | 0.6825   | 0.1404    | 0.1291 | 0.1179 |
+| 0.2651        | 0.2158 | 200  | 0.6134          | 0.7668   | 0.3945    | 0.2648 | 0.2505 |
+| 0.1556        | 0.3237 | 300  | 0.2849          | 0.9183   | 0.6474    | 0.5500 | 0.5700 |
+| 0.1999        | 0.4316 | 400  | 0.2655          | 0.9021   | 0.7646    | 0.5318 | 0.5426 |
+| 0.1746        | 0.5395 | 500  | 0.2362          | 0.9086   | 0.7687    | 0.6036 | 0.6230 |
+| 0.1733        | 0.6474 | 600  | 0.2026          | 0.9509   | 0.7935    | 0.7895 | 0.7860 |
+| 0.1048        | 0.7553 | 700  | 0.1498          | 0.9563   | 0.8978    | 0.7432 | 0.7662 |
+| 0.1751        | 0.8632 | 800  | 0.1688          | 0.9495   | 0.8475    | 0.7802 | 0.7727 |
+| 0.1087        | 0.9711 | 900  | 0.1966          | 0.9220   | 0.8840    | 0.6922 | 0.6952 |
+| 0.1367        | 1.0790 | 1000 | 0.1605          | 0.9423   | 0.8138    | 0.8021 | 0.7573 |
+| 0.1251        | 1.1869 | 1100 | 0.1698          | 0.9313   | 0.7926    | 0.8010 | 0.7637 |
+| 0.1383        | 1.2948 | 1200 | 0.1252          | 0.9625   | 0.8940    | 0.8389 | 0.8525 |
+| 0.1173        | 1.4028 | 1300 | 0.1372          | 0.9476   | 0.8857    | 0.7698 | 0.7774 |
+| 0.1014        | 1.5107 | 1400 | 0.1104          | 0.9655   | 0.9173    | 0.8072 | 0.8257 |
+| 0.1073        | 1.6186 | 1500 | 0.1222          | 0.9651   | 0.8932    | 0.8670 | 0.8792 |
+| 0.1093        | 1.7265 | 1600 | 0.1270          | 0.9517   | 0.8591    | 0.8431 | 0.8316 |
+| 0.0832        | 1.8344 | 1700 | 0.1128          | 0.9645   | 0.9080    | 0.8533 | 0.8707 |
+| 0.0972        | 1.9423 | 1800 | 0.1040          | 0.9704   | 0.9309    | 0.8473 | 0.8744 |
+| 0.0771        | 2.0502 | 1900 | 0.1116          | 0.9602   | 0.8525    | 0.8643 | 0.8438 |
+| 0.1073        | 2.1581 | 2000 | 0.1096          | 0.9645   | 0.9117    | 0.8557 | 0.8684 |
+| 0.0997        | 2.2660 | 2100 | 0.1022          | 0.9708   | 0.9292    | 0.8826 | 0.9014 |
+| 0.089         | 2.3739 | 2200 | 0.1032          | 0.9691   | 0.9104    | 0.8785 | 0.8861 |
+| 0.0688        | 2.4818 | 2300 | 0.1046          | 0.9652   | 0.9195    | 0.8446 | 0.8638 |
+| 0.0894        | 2.5897 | 2400 | 0.0933          | 0.9727   | 0.9006    | 0.8957 | 0.8956 |
+| 0.0691        | 2.6976 | 2500 | 0.0929          | 0.9714   | 0.9093    | 0.8807 | 0.8886 |
+| 0.0903        | 2.8055 | 2600 | 0.1017          | 0.9666   | 0.9229    | 0.8679 | 0.8835 |
+| 0.0582        | 2.9134 | 2700 | 0.1013          | 0.9670   | 0.9209    | 0.8649 | 0.8808 |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.0+cu121
+- Datasets 3.0.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "google/vit-base-patch16-224",
+  "architectures": [
+    "ViTForClassificationAndContrastiveLearning"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "finetuning_task": "image-classification",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d63c81dfe4cbd6b323a552502628e7f68f452112349e595e5a7e3fcfea50a12
+size 345608060

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36630d9a91285b638b76cf43bee2aa39df28568eb4e31ac8eb974dcc1a97e540
+size 5240