Upload folder using huggingface_hub

README.md

@@ -0,0 +1,42 @@
+
+---
+tags:
+- autotrain
+- image-classification
+widget:
+- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/tiger.jpg
+  example_title: Tiger
+- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/teapot.jpg
+  example_title: Teapot
+- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/palace.jpg
+  example_title: Palace
+datasets:
+- autotrain-vit-base-2/autotrain-data
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Image Classification
+
+## Validation Metricsg
+loss: 1.019775390625
+
+f1_macro: 0.6
+
+f1_micro: 0.75
+
+f1_weighted: 0.65
+
+precision_macro: 0.5555555555555555
+
+precision_micro: 0.75
+
+precision_weighted: 0.5833333333333333
+
+recall_macro: 0.6666666666666666
+
+recall_micro: 0.75
+
+recall_weighted: 0.75
+
+accuracy: 0.75

checkpoint-18/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "google/vit-base-patch16-224",
+  "_num_labels": 3,
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "11covered_with_a_quilt_and_only_the_head_exposed",
+    "1": "12covered_with_a_quilt_and_exposed_other_parts_of_the_body",
+    "2": "13has_nothing_to_do_with_11_and_12_above"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "11covered_with_a_quilt_and_only_the_head_exposed": 0,
+    "12covered_with_a_quilt_and_exposed_other_parts_of_the_body": 1,
+    "13has_nothing_to_do_with_11_and_12_above": 2
+  },
+  "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": "4.36.1"
+}

checkpoint-18/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24233972a8514bb0b6b5c162543c50d29e3276514bb8a405f94d5a265d6eec72
+size 343227052

checkpoint-18/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f978f751df2da7186260dcbd47e23457f4623112153ffb5659f5bfa4488e20d8
+size 686575034

checkpoint-18/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cc23527a4dcb91e6dbe6ae59d6b6ebacff1c319ca563a153911b9489f92fd26
+size 14180

checkpoint-18/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3f20bfc16e51685bd013a5fd8ab0cb541785bffa7ddc771a29458bf97bfc574
+size 1064

checkpoint-18/trainer_state.json

@@ -0,0 +1,291 @@
+{
+  "best_metric": 1.019775390625,
+  "best_model_checkpoint": "autotrain-vit-base-2/checkpoint-18",
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 18,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0,
+      "loss": 1.0986,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 5e-05,
+      "loss": 1.0986,
+      "step": 2
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5,
+      "eval_f1_macro": 0.26666666666666666,
+      "eval_f1_micro": 0.5,
+      "eval_f1_weighted": 0.4,
+      "eval_loss": 1.0986328125,
+      "eval_precision_macro": 0.2222222222222222,
+      "eval_precision_micro": 0.5,
+      "eval_precision_weighted": 0.3333333333333333,
+      "eval_recall_macro": 0.3333333333333333,
+      "eval_recall_micro": 0.5,
+      "eval_recall_weighted": 0.5,
+      "eval_runtime": 0.1241,
+      "eval_samples_per_second": 32.227,
+      "eval_steps_per_second": 8.057,
+      "step": 2
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.0001,
+      "loss": 1.0986,
+      "step": 3
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 9.444444444444444e-05,
+      "loss": 1.0999,
+      "step": 4
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5,
+      "eval_f1_macro": 0.2222222222222222,
+      "eval_f1_micro": 0.5,
+      "eval_f1_weighted": 0.3333333333333333,
+      "eval_loss": 1.086669921875,
+      "eval_precision_macro": 0.16666666666666666,
+      "eval_precision_micro": 0.5,
+      "eval_precision_weighted": 0.25,
+      "eval_recall_macro": 0.3333333333333333,
+      "eval_recall_micro": 0.5,
+      "eval_recall_weighted": 0.5,
+      "eval_runtime": 0.1558,
+      "eval_samples_per_second": 25.675,
+      "eval_steps_per_second": 6.419,
+      "step": 4
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 8.888888888888889e-05,
+      "loss": 1.0785,
+      "step": 5
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 8.333333333333334e-05,
+      "loss": 1.0745,
+      "step": 6
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.75,
+      "eval_f1_macro": 0.6,
+      "eval_f1_micro": 0.75,
+      "eval_f1_weighted": 0.65,
+      "eval_loss": 1.07421875,
+      "eval_precision_macro": 0.5555555555555555,
+      "eval_precision_micro": 0.75,
+      "eval_precision_weighted": 0.5833333333333333,
+      "eval_recall_macro": 0.6666666666666666,
+      "eval_recall_micro": 0.75,
+      "eval_recall_weighted": 0.75,
+      "eval_runtime": 0.1106,
+      "eval_samples_per_second": 36.166,
+      "eval_steps_per_second": 9.042,
+      "step": 6
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 7.777777777777778e-05,
+      "loss": 1.0503,
+      "step": 7
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 7.222222222222222e-05,
+      "loss": 1.033,
+      "step": 8
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.75,
+      "eval_f1_macro": 0.6,
+      "eval_f1_micro": 0.75,
+      "eval_f1_weighted": 0.65,
+      "eval_loss": 1.061279296875,
+      "eval_precision_macro": 0.5555555555555555,
+      "eval_precision_micro": 0.75,
+      "eval_precision_weighted": 0.5833333333333333,
+      "eval_recall_macro": 0.6666666666666666,
+      "eval_recall_micro": 0.75,
+      "eval_recall_weighted": 0.75,
+      "eval_runtime": 0.145,
+      "eval_samples_per_second": 27.586,
+      "eval_steps_per_second": 6.897,
+      "step": 8
+    },
+    {
+      "epoch": 4.5,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 1.0021,
+      "step": 9
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 1.0374,
+      "step": 10
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.75,
+      "eval_f1_macro": 0.6,
+      "eval_f1_micro": 0.75,
+      "eval_f1_weighted": 0.65,
+      "eval_loss": 1.05322265625,
+      "eval_precision_macro": 0.5555555555555555,
+      "eval_precision_micro": 0.75,
+      "eval_precision_weighted": 0.5833333333333333,
+      "eval_recall_macro": 0.6666666666666666,
+      "eval_recall_micro": 0.75,
+      "eval_recall_weighted": 0.75,
+      "eval_runtime": 0.1047,
+      "eval_samples_per_second": 38.192,
+      "eval_steps_per_second": 9.548,
+      "step": 10
+    },
+    {
+      "epoch": 5.5,
+      "learning_rate": 6.111111111111112e-05,
+      "loss": 1.0021,
+      "step": 11
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 5.555555555555556e-05,
+      "loss": 0.9912,
+      "step": 12
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.75,
+      "eval_f1_macro": 0.6,
+      "eval_f1_micro": 0.75,
+      "eval_f1_weighted": 0.65,
+      "eval_loss": 1.0400390625,
+      "eval_precision_macro": 0.5555555555555555,
+      "eval_precision_micro": 0.75,
+      "eval_precision_weighted": 0.5833333333333333,
+      "eval_recall_macro": 0.6666666666666666,
+      "eval_recall_micro": 0.75,
+      "eval_recall_weighted": 0.75,
+      "eval_runtime": 0.1544,
+      "eval_samples_per_second": 25.903,
+      "eval_steps_per_second": 6.476,
+      "step": 12
+    },
+    {
+      "epoch": 6.5,
+      "learning_rate": 5e-05,
+      "loss": 0.969,
+      "step": 13
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.9684,
+      "step": 14
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.75,
+      "eval_f1_macro": 0.6,
+      "eval_f1_micro": 0.75,
+      "eval_f1_weighted": 0.65,
+      "eval_loss": 1.031494140625,
+      "eval_precision_macro": 0.5555555555555555,
+      "eval_precision_micro": 0.75,
+      "eval_precision_weighted": 0.5833333333333333,
+      "eval_recall_macro": 0.6666666666666666,
+      "eval_recall_micro": 0.75,
+      "eval_recall_weighted": 0.75,
+      "eval_runtime": 0.1058,
+      "eval_samples_per_second": 37.811,
+      "eval_steps_per_second": 9.453,
+      "step": 14
+    },
+    {
+      "epoch": 7.5,
+      "learning_rate": 3.888888888888889e-05,
+      "loss": 0.9493,
+      "step": 15
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.9297,
+      "step": 16
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.75,
+      "eval_f1_macro": 0.6,
+      "eval_f1_micro": 0.75,
+      "eval_f1_weighted": 0.65,
+      "eval_loss": 1.024658203125,
+      "eval_precision_macro": 0.5555555555555555,
+      "eval_precision_micro": 0.75,
+      "eval_precision_weighted": 0.5833333333333333,
+      "eval_recall_macro": 0.6666666666666666,
+      "eval_recall_micro": 0.75,
+      "eval_recall_weighted": 0.75,
+      "eval_runtime": 0.1145,
+      "eval_samples_per_second": 34.936,
+      "eval_steps_per_second": 8.734,
+      "step": 16
+    },
+    {
+      "epoch": 8.5,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 0.9229,
+      "step": 17
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 0.9038,
+      "step": 18
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.75,
+      "eval_f1_macro": 0.6,
+      "eval_f1_micro": 0.75,
+      "eval_f1_weighted": 0.65,
+      "eval_loss": 1.019775390625,
+      "eval_precision_macro": 0.5555555555555555,
+      "eval_precision_micro": 0.75,
+      "eval_precision_weighted": 0.5833333333333333,
+      "eval_recall_macro": 0.6666666666666666,
+      "eval_recall_micro": 0.75,
+      "eval_recall_weighted": 0.75,
+      "eval_runtime": 0.1741,
+      "eval_samples_per_second": 22.98,
+      "eval_steps_per_second": 5.745,
+      "step": 18
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 20,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 8369209888284672.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-18/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:845903e28a5cefa036825ea55ac382dad13e5d9b0e38e31e71cdbd7e7f9dc075
+size 4664

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "google/vit-base-patch16-224",
+  "_num_labels": 3,
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "11covered_with_a_quilt_and_only_the_head_exposed",
+    "1": "12covered_with_a_quilt_and_exposed_other_parts_of_the_body",
+    "2": "13has_nothing_to_do_with_11_and_12_above"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "11covered_with_a_quilt_and_only_the_head_exposed": 0,
+    "12covered_with_a_quilt_and_exposed_other_parts_of_the_body": 1,
+    "13has_nothing_to_do_with_11_and_12_above": 2
+  },
+  "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": "4.36.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24233972a8514bb0b6b5c162543c50d29e3276514bb8a405f94d5a265d6eec72
+size 343227052

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
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:845903e28a5cefa036825ea55ac382dad13e5d9b0e38e31e71cdbd7e7f9dc075
+size 4664

training_params.json

@@ -0,0 +1,29 @@
+{
+    "data_path": "autotrain-vit-base-2/autotrain-data",
+    "model": "google/vit-base-patch16-224",
+    "username": "ZhaoYoujia",
+    "lr": 0.0001,
+    "epochs": 10,
+    "batch_size": 8,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 1,
+    "optimizer": "adamw_torch",
+    "scheduler": "linear",
+    "weight_decay": 0.0,
+    "max_grad_norm": 1.0,
+    "seed": 42,
+    "train_split": "train",
+    "valid_split": "validation",
+    "logging_steps": -1,
+    "project_name": "autotrain-vit-base-2",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "save_strategy": "epoch",
+    "push_to_hub": true,
+    "repo_id": "ZhaoYoujia/autotrain-vit-base-2",
+    "evaluation_strategy": "epoch",
+    "image_column": "autotrain_image",
+    "target_column": "autotrain_label",
+    "log": "none"
+}