Upload folder using huggingface_hub

checkpoint-7998/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "dima806/deepfake_vs_real_image_detection",
+  "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": "4.45.2"
+}

checkpoint-7998/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aea2a191c0c835da20ce666c521582d1a8e9f62f0c0c2843acaeb7b7166a8e72
+size 343223968

checkpoint-7998/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e82eb4b63699037cd3bc1dd397cf2b60f8ba7dc07656da05ecfbc0728a331a28
+size 686568890

checkpoint-7998/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-7998/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20bae3f2bc4aa6fb562ff7618eb05f3142a2ad0c068643ba295141ed61f83604
+size 14244

checkpoint-7998/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f055a8f548ddd7c7aee91deb4607debd6093552dd7605ae7bd42f517dee034df
+size 1064

checkpoint-7998/trainer_state.json

@@ -0,0 +1,168 @@
+{
+  "best_metric": 0.2657858431339264,
+  "best_model_checkpoint": "deepfake_vs_real_image_detection/checkpoint-7998",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 7998,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.18754688672168043,
+      "grad_norm": 3.8869080543518066,
+      "learning_rate": 9.43381982888777e-07,
+      "loss": 0.9437,
+      "step": 500
+    },
+    {
+      "epoch": 0.37509377344336087,
+      "grad_norm": 5.849929332733154,
+      "learning_rate": 8.804730749874182e-07,
+      "loss": 0.5025,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5626406601650412,
+      "grad_norm": 10.627140045166016,
+      "learning_rate": 8.175641670860593e-07,
+      "loss": 0.4137,
+      "step": 1500
+    },
+    {
+      "epoch": 0.7501875468867217,
+      "grad_norm": 6.05531644821167,
+      "learning_rate": 7.546552591847005e-07,
+      "loss": 0.3563,
+      "step": 2000
+    },
+    {
+      "epoch": 0.9377344336084021,
+      "grad_norm": 7.301521301269531,
+      "learning_rate": 6.917463512833417e-07,
+      "loss": 0.3179,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8625868284533544,
+      "eval_loss": 0.3228318393230438,
+      "eval_model_preparation_time": 0.0055,
+      "eval_runtime": 634.6946,
+      "eval_samples_per_second": 89.594,
+      "eval_steps_per_second": 11.201,
+      "step": 2666
+    },
+    {
+      "epoch": 1.1252813203300824,
+      "grad_norm": 7.1418375968933105,
+      "learning_rate": 6.288374433819828e-07,
+      "loss": 0.2951,
+      "step": 3000
+    },
+    {
+      "epoch": 1.312828207051763,
+      "grad_norm": 12.518142700195312,
+      "learning_rate": 5.65928535480624e-07,
+      "loss": 0.2749,
+      "step": 3500
+    },
+    {
+      "epoch": 1.5003750937734432,
+      "grad_norm": 7.537821292877197,
+      "learning_rate": 5.030196275792652e-07,
+      "loss": 0.2542,
+      "step": 4000
+    },
+    {
+      "epoch": 1.6879219804951238,
+      "grad_norm": 8.785564422607422,
+      "learning_rate": 4.4011071967790636e-07,
+      "loss": 0.2496,
+      "step": 4500
+    },
+    {
+      "epoch": 1.8754688672168043,
+      "grad_norm": 8.230996131896973,
+      "learning_rate": 3.7720181177654754e-07,
+      "loss": 0.2347,
+      "step": 5000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8783962015299394,
+      "eval_loss": 0.28315049409866333,
+      "eval_model_preparation_time": 0.0055,
+      "eval_runtime": 618.5578,
+      "eval_samples_per_second": 91.932,
+      "eval_steps_per_second": 11.493,
+      "step": 5332
+    },
+    {
+      "epoch": 2.0630157539384846,
+      "grad_norm": 8.427594184875488,
+      "learning_rate": 3.142929038751887e-07,
+      "loss": 0.2317,
+      "step": 5500
+    },
+    {
+      "epoch": 2.250562640660165,
+      "grad_norm": 7.748924732208252,
+      "learning_rate": 2.5138399597382987e-07,
+      "loss": 0.2347,
+      "step": 6000
+    },
+    {
+      "epoch": 2.4381095273818456,
+      "grad_norm": 8.576868057250977,
+      "learning_rate": 1.8847508807247105e-07,
+      "loss": 0.2228,
+      "step": 6500
+    },
+    {
+      "epoch": 2.625656414103526,
+      "grad_norm": 6.261688709259033,
+      "learning_rate": 1.2556618017111224e-07,
+      "loss": 0.2153,
+      "step": 7000
+    },
+    {
+      "epoch": 2.813203300825206,
+      "grad_norm": 10.823939323425293,
+      "learning_rate": 6.26572722697534e-08,
+      "loss": 0.2143,
+      "step": 7500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8868196605996659,
+      "eval_loss": 0.2657858431339264,
+      "eval_model_preparation_time": 0.0055,
+      "eval_runtime": 609.2124,
+      "eval_samples_per_second": 93.342,
+      "eval_steps_per_second": 11.669,
+      "step": 7998
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7998,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.982950271446756e+19,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-7998/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be28f94bda083846811f1ec60f1f7943d3113cc3593577a5b73f47357e488f5d
+size 5176

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "dima806/deepfake_vs_real_image_detection",
+  "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": "4.45.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aea2a191c0c835da20ce666c521582d1a8e9f62f0c0c2843acaeb7b7166a8e72
+size 343223968

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:be28f94bda083846811f1ec60f1f7943d3113cc3593577a5b73f47357e488f5d
+size 5176