Initial model upload

checkpoint-8965/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": "4.47.0"
+}

checkpoint-8965/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:789fc6b6e0e13db4399e372a02a1b6e9a16daba7c21e097bdea97d82f03b2aeb
+size 343223968

checkpoint-8965/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c75afa5cf7958c18855d3c2e64fcf42204202812796337c2df3d638929de3b14
+size 686568890

checkpoint-8965/preprocessor_config.json

@@ -0,0 +1,23 @@
+{
+  "do_convert_rgb": null,
+  "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-8965/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ec28ea0c416565eeac14a0e9c944f185ac250f4ed4bd15c84ff77ed78ba9301
+size 14244

checkpoint-8965/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a54ce6a70c8d29c4256c95d9b111cf8772fb4806a81a5b8549c462c110ca1e88
+size 1064

checkpoint-8965/trainer_state.json

@@ -0,0 +1,251 @@
+{
+  "best_metric": 0.36695095896720886,
+  "best_model_checkpoint": "deepfake_faces_vit/checkpoint-8965",
+  "epoch": 11.0,
+  "eval_steps": 500,
+  "global_step": 8965,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6134969325153374,
+      "grad_norm": 9.73007869720459,
+      "learning_rate": 9.537512846865365e-07,
+      "loss": 0.4289,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8100644369438478,
+      "eval_loss": 0.43108952045440674,
+      "eval_runtime": 29.5331,
+      "eval_samples_per_second": 110.351,
+      "eval_steps_per_second": 13.815,
+      "step": 815
+    },
+    {
+      "epoch": 1.2269938650306749,
+      "grad_norm": 5.347096920013428,
+      "learning_rate": 9.023638232271325e-07,
+      "loss": 0.4061,
+      "step": 1000
+    },
+    {
+      "epoch": 1.8404907975460123,
+      "grad_norm": 9.34152889251709,
+      "learning_rate": 8.509763617677287e-07,
+      "loss": 0.3857,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.822951825713409,
+      "eval_loss": 0.40853503346443176,
+      "eval_runtime": 27.4579,
+      "eval_samples_per_second": 118.691,
+      "eval_steps_per_second": 14.859,
+      "step": 1630
+    },
+    {
+      "epoch": 2.4539877300613497,
+      "grad_norm": 5.006694316864014,
+      "learning_rate": 7.995889003083247e-07,
+      "loss": 0.3592,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8275544645596808,
+      "eval_loss": 0.3940746486186981,
+      "eval_runtime": 29.4468,
+      "eval_samples_per_second": 110.674,
+      "eval_steps_per_second": 13.855,
+      "step": 2445
+    },
+    {
+      "epoch": 3.067484662576687,
+      "grad_norm": 9.202957153320312,
+      "learning_rate": 7.482014388489208e-07,
+      "loss": 0.3519,
+      "step": 2500
+    },
+    {
+      "epoch": 3.6809815950920246,
+      "grad_norm": 7.183080673217773,
+      "learning_rate": 6.968139773895169e-07,
+      "loss": 0.3307,
+      "step": 3000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8306228904571955,
+      "eval_loss": 0.38576722145080566,
+      "eval_runtime": 26.6498,
+      "eval_samples_per_second": 122.29,
+      "eval_steps_per_second": 15.31,
+      "step": 3260
+    },
+    {
+      "epoch": 4.294478527607362,
+      "grad_norm": 11.383119583129883,
+      "learning_rate": 6.454265159301129e-07,
+      "loss": 0.3216,
+      "step": 3500
+    },
+    {
+      "epoch": 4.9079754601226995,
+      "grad_norm": 4.364112377166748,
+      "learning_rate": 5.940390544707091e-07,
+      "loss": 0.3079,
+      "step": 4000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8373734274317275,
+      "eval_loss": 0.3753877580165863,
+      "eval_runtime": 28.0806,
+      "eval_samples_per_second": 116.059,
+      "eval_steps_per_second": 14.53,
+      "step": 4075
+    },
+    {
+      "epoch": 5.521472392638037,
+      "grad_norm": 5.054851055145264,
+      "learning_rate": 5.426515930113052e-07,
+      "loss": 0.298,
+      "step": 4500
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8382939552009819,
+      "eval_loss": 0.37101876735687256,
+      "eval_runtime": 29.1733,
+      "eval_samples_per_second": 111.712,
+      "eval_steps_per_second": 13.985,
+      "step": 4890
+    },
+    {
+      "epoch": 6.134969325153374,
+      "grad_norm": 13.362000465393066,
+      "learning_rate": 4.912641315519013e-07,
+      "loss": 0.2844,
+      "step": 5000
+    },
+    {
+      "epoch": 6.748466257668712,
+      "grad_norm": 11.542821884155273,
+      "learning_rate": 4.398766700924974e-07,
+      "loss": 0.2747,
+      "step": 5500
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8419760662779994,
+      "eval_loss": 0.370534747838974,
+      "eval_runtime": 29.1054,
+      "eval_samples_per_second": 111.972,
+      "eval_steps_per_second": 14.018,
+      "step": 5705
+    },
+    {
+      "epoch": 7.361963190184049,
+      "grad_norm": 11.590359687805176,
+      "learning_rate": 3.8848920863309354e-07,
+      "loss": 0.2667,
+      "step": 6000
+    },
+    {
+      "epoch": 7.975460122699387,
+      "grad_norm": 10.857077598571777,
+      "learning_rate": 3.371017471736896e-07,
+      "loss": 0.266,
+      "step": 6500
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8425897514575023,
+      "eval_loss": 0.36838075518608093,
+      "eval_runtime": 28.7074,
+      "eval_samples_per_second": 113.525,
+      "eval_steps_per_second": 14.212,
+      "step": 6520
+    },
+    {
+      "epoch": 8.588957055214724,
+      "grad_norm": 6.882222652435303,
+      "learning_rate": 2.857142857142857e-07,
+      "loss": 0.2558,
+      "step": 7000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.844430806996011,
+      "eval_loss": 0.36847400665283203,
+      "eval_runtime": 26.9443,
+      "eval_samples_per_second": 120.953,
+      "eval_steps_per_second": 15.142,
+      "step": 7335
+    },
+    {
+      "epoch": 9.202453987730062,
+      "grad_norm": 18.27613639831543,
+      "learning_rate": 2.343268242548818e-07,
+      "loss": 0.2518,
+      "step": 7500
+    },
+    {
+      "epoch": 9.815950920245399,
+      "grad_norm": 35.016822814941406,
+      "learning_rate": 1.829393627954779e-07,
+      "loss": 0.2466,
+      "step": 8000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.8459650199447684,
+      "eval_loss": 0.3689593970775604,
+      "eval_runtime": 29.6071,
+      "eval_samples_per_second": 110.075,
+      "eval_steps_per_second": 13.78,
+      "step": 8150
+    },
+    {
+      "epoch": 10.429447852760736,
+      "grad_norm": 5.033447742462158,
+      "learning_rate": 1.31551901336074e-07,
+      "loss": 0.2403,
+      "step": 8500
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.8459650199447684,
+      "eval_loss": 0.36695095896720886,
+      "eval_runtime": 29.5956,
+      "eval_samples_per_second": 110.118,
+      "eval_steps_per_second": 13.786,
+      "step": 8965
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 9780,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 12,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.2220673038005027e+19,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-8965/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:161bc882c30c7de46868214d00462c336f43f255ae07d98705ad8d24205b13ce
+size 5240

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": "4.47.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:789fc6b6e0e13db4399e372a02a1b6e9a16daba7c21e097bdea97d82f03b2aeb
+size 343223968

preprocessor_config.json

@@ -0,0 +1,23 @@
+{
+  "do_convert_rgb": null,
+  "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 sha256:161bc882c30c7de46868214d00462c336f43f255ae07d98705ad8d24205b13ce
+size 5240