🤠

README.md

@@ -1,3 +1,73 @@
 ---
-license: wtfpl
+license: apache-2.0
+tags:
+- image-classification
+- vision
+- generated_from_trainer
+datasets:
+- imagefolder
+metrics:
+- accuracy
+model-index:
+- name: outputs
+  results:
+  - task:
+      name: Image Classification
+      type: image-classification
+    dataset:
+      name: imagefolder
+      type: imagefolder
+      config: default
+      split: train
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8571428571428571
 ---
+
+<!-- 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. -->
+
+# Cowboy Hat emoji 🤠 (Western)
+
+This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5372
+- Accuracy: 0.8571
+
+## Model description
+
+When you want to know if an art is 🤠 or not 🤠.
+
+## Intended uses & limitations
+
+filter gelbooru data on 🤠 or not 🤠
+
+## Training and evaluation data
+
+Selected 72 images of 🤠 and not 🤠.
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+Works OK. Needs more finetuning.
+
+### Framework versions
+
+- Transformers 4.30.0.dev0
+- Pytorch 1.13.1+cu117
+- Datasets 2.12.0
+- Tokenizers 0.13.3

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.8571428571428571,
+    "eval_loss": 0.537242591381073,
+    "eval_runtime": 1.4402,
+    "eval_samples_per_second": 14.582,
+    "eval_steps_per_second": 2.083,
+    "train_loss": 0.5724380493164063,
+    "train_runtime": 25.85,
+    "train_samples_per_second": 13.81,
+    "train_steps_per_second": 1.741
+}

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "google/vit-base-patch16-224-in21k",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "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": "not_western",
+    "1": "western"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "not_western": "0",
+    "western": "1"
+  },
+  "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": "4.30.0.dev0"
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.8571428571428571,
+    "eval_loss": 0.537242591381073,
+    "eval_runtime": 1.4402,
+    "eval_samples_per_second": 14.582,
+    "eval_steps_per_second": 2.083
+}

preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "ViTImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f820f1f2576997b6a31a625789757927367756647cb988e7a143be3eb6411c5f
+size 343268717

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.5724380493164063,
+    "train_runtime": 25.85,
+    "train_samples_per_second": 13.81,
+    "train_steps_per_second": 1.741
+}

trainer_state.json

@@ -0,0 +1,25 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 45,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.0,
+      "step": 45,
+      "total_flos": 2.7664640292409344e+16,
+      "train_loss": 0.5724380493164063,
+      "train_runtime": 25.85,
+      "train_samples_per_second": 13.81,
+      "train_steps_per_second": 1.741
+    }
+  ],
+  "max_steps": 45,
+  "num_train_epochs": 3,
+  "total_flos": 2.7664640292409344e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17eb5b0411fa90a36e2a5ef3742fb9c9089bfe617f2b308d17876d66bfad9ba6
+size 3899