Upload 9 files

config.json

@@ -0,0 +1,79 @@
+{
+  "_name_or_path": "microsoft/beit-base-patch16-224",
+  "add_fpn": false,
+  "architectures": [
+    "BeitForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "auxiliary_channels": 256,
+  "auxiliary_concat_input": false,
+  "auxiliary_loss_weight": 0.4,
+  "auxiliary_num_convs": 1,
+  "drop_path_rate": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "faceswap",
+    "1": "real",
+    "2": "sfhq",
+    "3": "stable_diffusion",
+    "4": "thispersondoesnotexist"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "faceswap": 0,
+    "real": 1,
+    "sfhq": 2,
+    "stable_diffusion": 3,
+    "thispersondoesnotexist": 4
+  },
+  "layer_norm_eps": 1e-12,
+  "layer_scale_init_value": 0.1,
+  "model_type": "beit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "out_features": [
+    "stage12"
+  ],
+  "out_indices": [
+    12
+  ],
+  "patch_size": 16,
+  "pool_scales": [
+    1,
+    2,
+    3,
+    6
+  ],
+  "problem_type": "single_label_classification",
+  "reshape_hidden_states": true,
+  "semantic_loss_ignore_index": 255,
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4",
+    "stage5",
+    "stage6",
+    "stage7",
+    "stage8",
+    "stage9",
+    "stage10",
+    "stage11",
+    "stage12"
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.2",
+  "use_absolute_position_embeddings": false,
+  "use_auxiliary_head": true,
+  "use_mask_token": false,
+  "use_mean_pooling": true,
+  "use_relative_position_bias": true,
+  "use_shared_relative_position_bias": false,
+  "vocab_size": 8192
+}

gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:091dfb9ee437c743f08996c35e9a85b50dea43c4f2c08d1749f43b6a722e0f74
+size 343089556

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76f32410aad2b8fde67664100ba77b9206b7829ac98f873c32fd25ed980430bc
+size 686313082

preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": false,
+  "do_normalize": true,
+  "do_reduce_labels": false,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "BeitFeatureExtractor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30802ee6b802cf0755cac9a204b064ca9c552516d1e85cb6072aafc4ac576b5a
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14508328767fb35b822b09b625b1477a4ecbcb3c4dd224dd08a15bd502df0d95
+size 1064

trainer_state.json

@@ -0,0 +1,242 @@
+{
+  "best_metric": 0.9493333333333334,
+  "best_model_checkpoint": "./beit_finetuned\\checkpoint-1314",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1314,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1141552511415525,
+      "grad_norm": 8.857061386108398,
+      "learning_rate": 4.8173515981735164e-05,
+      "loss": 1.0756,
+      "step": 50
+    },
+    {
+      "epoch": 0.228310502283105,
+      "grad_norm": 6.956742286682129,
+      "learning_rate": 4.6270928462709285e-05,
+      "loss": 0.8313,
+      "step": 100
+    },
+    {
+      "epoch": 0.3424657534246575,
+      "grad_norm": 25.718080520629883,
+      "learning_rate": 4.452054794520548e-05,
+      "loss": 0.7164,
+      "step": 150
+    },
+    {
+      "epoch": 0.45662100456621,
+      "grad_norm": 14.741324424743652,
+      "learning_rate": 4.26179604261796e-05,
+      "loss": 0.6739,
+      "step": 200
+    },
+    {
+      "epoch": 0.5707762557077626,
+      "grad_norm": 8.193249702453613,
+      "learning_rate": 4.071537290715373e-05,
+      "loss": 0.6212,
+      "step": 250
+    },
+    {
+      "epoch": 0.684931506849315,
+      "grad_norm": 18.06510353088379,
+      "learning_rate": 3.881278538812785e-05,
+      "loss": 0.4952,
+      "step": 300
+    },
+    {
+      "epoch": 0.7990867579908676,
+      "grad_norm": 8.87159252166748,
+      "learning_rate": 3.691019786910198e-05,
+      "loss": 0.4409,
+      "step": 350
+    },
+    {
+      "epoch": 0.91324200913242,
+      "grad_norm": 2.9289777278900146,
+      "learning_rate": 3.50076103500761e-05,
+      "loss": 0.4377,
+      "step": 400
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8773333333333333,
+      "eval_loss": 0.36529314517974854,
+      "eval_runtime": 83.9644,
+      "eval_samples_per_second": 17.865,
+      "eval_steps_per_second": 1.12,
+      "step": 438
+    },
+    {
+      "epoch": 1.0273972602739727,
+      "grad_norm": 1.1098586320877075,
+      "learning_rate": 3.310502283105023e-05,
+      "loss": 0.2894,
+      "step": 450
+    },
+    {
+      "epoch": 1.1415525114155252,
+      "grad_norm": 17.91949462890625,
+      "learning_rate": 3.120243531202435e-05,
+      "loss": 0.2204,
+      "step": 500
+    },
+    {
+      "epoch": 1.2557077625570776,
+      "grad_norm": 3.071772575378418,
+      "learning_rate": 2.929984779299848e-05,
+      "loss": 0.1716,
+      "step": 550
+    },
+    {
+      "epoch": 1.36986301369863,
+      "grad_norm": 1.6142654418945312,
+      "learning_rate": 2.7397260273972603e-05,
+      "loss": 0.1754,
+      "step": 600
+    },
+    {
+      "epoch": 1.4840182648401825,
+      "grad_norm": 25.471872329711914,
+      "learning_rate": 2.549467275494673e-05,
+      "loss": 0.2025,
+      "step": 650
+    },
+    {
+      "epoch": 1.5981735159817352,
+      "grad_norm": 3.1595094203948975,
+      "learning_rate": 2.359208523592085e-05,
+      "loss": 0.2487,
+      "step": 700
+    },
+    {
+      "epoch": 1.7123287671232876,
+      "grad_norm": 3.188368797302246,
+      "learning_rate": 2.1689497716894976e-05,
+      "loss": 0.1964,
+      "step": 750
+    },
+    {
+      "epoch": 1.82648401826484,
+      "grad_norm": 0.5533382296562195,
+      "learning_rate": 1.97869101978691e-05,
+      "loss": 0.109,
+      "step": 800
+    },
+    {
+      "epoch": 1.9406392694063928,
+      "grad_norm": 15.678669929504395,
+      "learning_rate": 1.7884322678843227e-05,
+      "loss": 0.1221,
+      "step": 850
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8986666666666666,
+      "eval_loss": 0.3740909695625305,
+      "eval_runtime": 85.0571,
+      "eval_samples_per_second": 17.635,
+      "eval_steps_per_second": 1.105,
+      "step": 876
+    },
+    {
+      "epoch": 2.0547945205479454,
+      "grad_norm": 5.463280200958252,
+      "learning_rate": 1.5981735159817352e-05,
+      "loss": 0.1046,
+      "step": 900
+    },
+    {
+      "epoch": 2.1689497716894977,
+      "grad_norm": 14.793232917785645,
+      "learning_rate": 1.4079147640791476e-05,
+      "loss": 0.0534,
+      "step": 950
+    },
+    {
+      "epoch": 2.2831050228310503,
+      "grad_norm": 5.250246524810791,
+      "learning_rate": 1.2176560121765601e-05,
+      "loss": 0.02,
+      "step": 1000
+    },
+    {
+      "epoch": 2.3972602739726026,
+      "grad_norm": 22.0667667388916,
+      "learning_rate": 1.0273972602739726e-05,
+      "loss": 0.0274,
+      "step": 1050
+    },
+    {
+      "epoch": 2.5114155251141552,
+      "grad_norm": 4.051002025604248,
+      "learning_rate": 8.37138508371385e-06,
+      "loss": 0.0312,
+      "step": 1100
+    },
+    {
+      "epoch": 2.625570776255708,
+      "grad_norm": 1.257653832435608,
+      "learning_rate": 6.468797564687975e-06,
+      "loss": 0.0213,
+      "step": 1150
+    },
+    {
+      "epoch": 2.73972602739726,
+      "grad_norm": 3.783207654953003,
+      "learning_rate": 4.566210045662101e-06,
+      "loss": 0.0392,
+      "step": 1200
+    },
+    {
+      "epoch": 2.853881278538813,
+      "grad_norm": 0.03894606605172157,
+      "learning_rate": 2.663622526636225e-06,
+      "loss": 0.0378,
+      "step": 1250
+    },
+    {
+      "epoch": 2.968036529680365,
+      "grad_norm": 10.792261123657227,
+      "learning_rate": 7.610350076103501e-07,
+      "loss": 0.0187,
+      "step": 1300
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9493333333333334,
+      "eval_loss": 0.18020151555538177,
+      "eval_runtime": 85.2028,
+      "eval_samples_per_second": 17.605,
+      "eval_steps_per_second": 1.103,
+      "step": 1314
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 1314,
+  "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": 1.626679997171712e+18,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21e3ab9073c6fce128dd434fb3b9b5ac50875b385a6cdc19b22dc10901a6b90a
+size 5304