Upload folder using huggingface_hub

checkpoint-8440/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "google/vit-base-patch16-224-in21k",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "REAL",
+    "1": "FAKE"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "FAKE": 1,
+    "REAL": 0
+  },
+  "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": "4.34.0"
+}

checkpoint-8440/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b583e1fdf5005c72375e1a3a5f75f6f98f02ea7b896b335ea250c58d7c4ceb4
+size 686568453

checkpoint-8440/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
+  }
+}

checkpoint-8440/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3ee9511c4aea31585701b13cc75639e26bb4437581af161244d4996fc509d57
+size 343268717

checkpoint-8440/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:675741f06bf0154188a79f5025905c62bfed9ad5666579ef8150b2dd8a73296f
+size 14575

checkpoint-8440/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39db12678132f9b7e5c5e223ce35b171c6743ec311ddf7d7ba16f4f26cdf58aa
+size 627

checkpoint-8440/trainer_state.json

@@ -0,0 +1,160 @@
+{
+  "best_metric": 0.05447809770703316,
+  "best_model_checkpoint": "ai_vs_real_image_detection/checkpoint-8440",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 8440,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3,
+      "learning_rate": 9.463647199046485e-06,
+      "loss": 0.2818,
+      "step": 500
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 8.867699642431467e-06,
+      "loss": 0.1106,
+      "step": 1000
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 8.27175208581645e-06,
+      "loss": 0.0871,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9599166666666666,
+      "eval_loss": 0.13126564025878906,
+      "eval_runtime": 108.7151,
+      "eval_samples_per_second": 110.38,
+      "eval_steps_per_second": 3.449,
+      "step": 1688
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 7.675804529201431e-06,
+      "loss": 0.0641,
+      "step": 2000
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 7.079856972586413e-06,
+      "loss": 0.0554,
+      "step": 2500
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 6.483909415971396e-06,
+      "loss": 0.0542,
+      "step": 3000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.97675,
+      "eval_loss": 0.06993511319160461,
+      "eval_runtime": 110.3278,
+      "eval_samples_per_second": 108.767,
+      "eval_steps_per_second": 3.399,
+      "step": 3376
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 5.887961859356377e-06,
+      "loss": 0.0448,
+      "step": 3500
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 5.2920143027413596e-06,
+      "loss": 0.0372,
+      "step": 4000
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 4.696066746126342e-06,
+      "loss": 0.0344,
+      "step": 4500
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 4.100119189511323e-06,
+      "loss": 0.031,
+      "step": 5000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9773333333333334,
+      "eval_loss": 0.06398669630289078,
+      "eval_runtime": 110.6996,
+      "eval_samples_per_second": 108.401,
+      "eval_steps_per_second": 3.388,
+      "step": 5064
+    },
+    {
+      "epoch": 3.26,
+      "learning_rate": 3.5041716328963056e-06,
+      "loss": 0.0252,
+      "step": 5500
+    },
+    {
+      "epoch": 3.55,
+      "learning_rate": 2.9082240762812874e-06,
+      "loss": 0.0226,
+      "step": 6000
+    },
+    {
+      "epoch": 3.85,
+      "learning_rate": 2.3122765196662693e-06,
+      "loss": 0.024,
+      "step": 6500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9770833333333333,
+      "eval_loss": 0.06279084086418152,
+      "eval_runtime": 110.8304,
+      "eval_samples_per_second": 108.274,
+      "eval_steps_per_second": 3.384,
+      "step": 6752
+    },
+    {
+      "epoch": 4.15,
+      "learning_rate": 1.7163289630512518e-06,
+      "loss": 0.019,
+      "step": 7000
+    },
+    {
+      "epoch": 4.44,
+      "learning_rate": 1.1203814064362336e-06,
+      "loss": 0.0171,
+      "step": 7500
+    },
+    {
+      "epoch": 4.74,
+      "learning_rate": 5.244338498212158e-07,
+      "loss": 0.0158,
+      "step": 8000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9804166666666667,
+      "eval_loss": 0.05447809770703316,
+      "eval_runtime": 108.5958,
+      "eval_samples_per_second": 110.502,
+      "eval_steps_per_second": 3.453,
+      "step": 8440
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8440,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 4.184567439187968e+19,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-8440/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:421bdc39b2ea43219c073f34e0d65a8548d36830f975957689c797414e940423
+size 4027

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "google/vit-base-patch16-224-in21k",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "REAL",
+    "1": "FAKE"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "FAKE": 1,
+    "REAL": 0
+  },
+  "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": "4.34.0"
+}

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:c3ee9511c4aea31585701b13cc75639e26bb4437581af161244d4996fc509d57
+size 343268717

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:421bdc39b2ea43219c073f34e0d65a8548d36830f975957689c797414e940423
+size 4027