Upload folder using huggingface_hub

checkpoint-12705/config.json

@@ -0,0 +1,124 @@
+{
+  "_name_or_path": "dima806/cat_breed_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": "Abyssinian",
+    "1": "American Bobtail",
+    "2": "American Curl",
+    "3": "American Shorthair",
+    "4": "Applehead Siamese",
+    "5": "Balinese",
+    "6": "Bengal",
+    "7": "Birman",
+    "8": "Bombay",
+    "9": "British Shorthair",
+    "10": "Burmese",
+    "11": "Calico",
+    "12": "Cornish Rex",
+    "13": "Devon Rex",
+    "14": "Dilute Calico",
+    "15": "Dilute Tortoiseshell",
+    "16": "Domestic Long Hair",
+    "17": "Domestic Medium Hair",
+    "18": "Domestic Short Hair",
+    "19": "Egyptian Mau",
+    "20": "Exotic Shorthair",
+    "21": "Extra-Toes Cat - Hemingway Polydactyl",
+    "22": "Havana",
+    "23": "Himalayan",
+    "24": "Japanese Bobtail",
+    "25": "Maine Coon",
+    "26": "Manx",
+    "27": "Munchkin",
+    "28": "Nebelung",
+    "29": "Norwegian Forest",
+    "30": "Oriental Short Hair",
+    "31": "Persian",
+    "32": "Ragamuffin",
+    "33": "Ragdoll",
+    "34": "Russian Blue",
+    "35": "Scottish Fold",
+    "36": "Siamese",
+    "37": "Siberian",
+    "38": "Snowshoe",
+    "39": "Sphynx",
+    "40": "Tabby",
+    "41": "Tiger",
+    "42": "Tonkinese",
+    "43": "Torbie",
+    "44": "Tortoiseshell",
+    "45": "Turkish Angora",
+    "46": "Turkish Van",
+    "47": "Tuxedo"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Abyssinian": 0,
+    "American Bobtail": 1,
+    "American Curl": 2,
+    "American Shorthair": 3,
+    "Applehead Siamese": 4,
+    "Balinese": 5,
+    "Bengal": 6,
+    "Birman": 7,
+    "Bombay": 8,
+    "British Shorthair": 9,
+    "Burmese": 10,
+    "Calico": 11,
+    "Cornish Rex": 12,
+    "Devon Rex": 13,
+    "Dilute Calico": 14,
+    "Dilute Tortoiseshell": 15,
+    "Domestic Long Hair": 16,
+    "Domestic Medium Hair": 17,
+    "Domestic Short Hair": 18,
+    "Egyptian Mau": 19,
+    "Exotic Shorthair": 20,
+    "Extra-Toes Cat - Hemingway Polydactyl": 21,
+    "Havana": 22,
+    "Himalayan": 23,
+    "Japanese Bobtail": 24,
+    "Maine Coon": 25,
+    "Manx": 26,
+    "Munchkin": 27,
+    "Nebelung": 28,
+    "Norwegian Forest": 29,
+    "Oriental Short Hair": 30,
+    "Persian": 31,
+    "Ragamuffin": 32,
+    "Ragdoll": 33,
+    "Russian Blue": 34,
+    "Scottish Fold": 35,
+    "Siamese": 36,
+    "Siberian": 37,
+    "Snowshoe": 38,
+    "Sphynx": 39,
+    "Tabby": 40,
+    "Tiger": 41,
+    "Tonkinese": 42,
+    "Torbie": 43,
+    "Tortoiseshell": 44,
+    "Turkish Angora": 45,
+    "Turkish Van": 46,
+    "Tuxedo": 47
+  },
+  "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": "4.44.0"
+}

checkpoint-12705/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63b8a8b92cd1bc9a5ed6f1db877ea8c070ecc294f47c06c4935b510d576c8031
+size 343365480

checkpoint-12705/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c23f489c9a1fd8dfe616d89a26d283840716e56f3d631bf34ea2160a5da8ea78
+size 686851461

checkpoint-12705/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-12705/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae31f6d7401c6a9094fff331acecfe45969d6298c11be19de2747e598772dd17
+size 14575

checkpoint-12705/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf55a5da2276b7534d8153631c0fcdf3e8887e15240ea11a4f10ae7a7c154943
+size 627

checkpoint-12705/trainer_state.json

@@ -0,0 +1,258 @@
+{
+  "best_metric": 0.9717448353767395,
+  "best_model_checkpoint": "cat_breed_image_detection/checkpoint-12705",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 12705,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.19677292404565133,
+      "grad_norm": 9.636006355285645,
+      "learning_rate": 7.715527459502173e-07,
+      "loss": 0.9268,
+      "step": 500
+    },
+    {
+      "epoch": 0.39354584809130266,
+      "grad_norm": 11.014582633972168,
+      "learning_rate": 7.399446858949032e-07,
+      "loss": 0.9256,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5903187721369539,
+      "grad_norm": 7.918747901916504,
+      "learning_rate": 7.08336625839589e-07,
+      "loss": 0.9215,
+      "step": 1500
+    },
+    {
+      "epoch": 0.7870916961826053,
+      "grad_norm": 11.053488731384277,
+      "learning_rate": 6.76728565784275e-07,
+      "loss": 0.9333,
+      "step": 2000
+    },
+    {
+      "epoch": 0.9838646202282566,
+      "grad_norm": 6.248382568359375,
+      "learning_rate": 6.451205057289608e-07,
+      "loss": 0.9281,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7275243578387954,
+      "eval_loss": 0.9933186173439026,
+      "eval_model_preparation_time": 0.0056,
+      "eval_runtime": 1315.6624,
+      "eval_samples_per_second": 82.38,
+      "eval_steps_per_second": 2.574,
+      "step": 2541
+    },
+    {
+      "epoch": 1.1806375442739079,
+      "grad_norm": 10.584348678588867,
+      "learning_rate": 6.135124456736468e-07,
+      "loss": 0.92,
+      "step": 3000
+    },
+    {
+      "epoch": 1.3774104683195592,
+      "grad_norm": 12.109768867492676,
+      "learning_rate": 5.819043856183327e-07,
+      "loss": 0.9081,
+      "step": 3500
+    },
+    {
+      "epoch": 1.5741833923652107,
+      "grad_norm": 8.714140892028809,
+      "learning_rate": 5.502963255630185e-07,
+      "loss": 0.9172,
+      "step": 4000
+    },
+    {
+      "epoch": 1.770956316410862,
+      "grad_norm": 11.591988563537598,
+      "learning_rate": 5.186882655077045e-07,
+      "loss": 0.9055,
+      "step": 4500
+    },
+    {
+      "epoch": 1.9677292404565132,
+      "grad_norm": 7.582597255706787,
+      "learning_rate": 4.870802054523904e-07,
+      "loss": 0.9151,
+      "step": 5000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7300155004428698,
+      "eval_loss": 0.9875085353851318,
+      "eval_model_preparation_time": 0.0056,
+      "eval_runtime": 1225.0709,
+      "eval_samples_per_second": 88.472,
+      "eval_steps_per_second": 2.765,
+      "step": 5082
+    },
+    {
+      "epoch": 2.1645021645021645,
+      "grad_norm": 10.563714027404785,
+      "learning_rate": 4.5547214539707617e-07,
+      "loss": 0.8938,
+      "step": 5500
+    },
+    {
+      "epoch": 2.3612750885478158,
+      "grad_norm": 10.767172813415527,
+      "learning_rate": 4.238640853417621e-07,
+      "loss": 0.9077,
+      "step": 6000
+    },
+    {
+      "epoch": 2.558048012593467,
+      "grad_norm": 11.555209159851074,
+      "learning_rate": 3.92256025286448e-07,
+      "loss": 0.9014,
+      "step": 6500
+    },
+    {
+      "epoch": 2.7548209366391183,
+      "grad_norm": 20.711454391479492,
+      "learning_rate": 3.606479652311339e-07,
+      "loss": 0.9067,
+      "step": 7000
+    },
+    {
+      "epoch": 2.9515938606847696,
+      "grad_norm": 11.440732955932617,
+      "learning_rate": 3.290399051758198e-07,
+      "loss": 0.8894,
+      "step": 7500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7311503542958371,
+      "eval_loss": 0.9776839017868042,
+      "eval_model_preparation_time": 0.0056,
+      "eval_runtime": 1391.2353,
+      "eval_samples_per_second": 77.905,
+      "eval_steps_per_second": 2.435,
+      "step": 7623
+    },
+    {
+      "epoch": 3.1483667847304213,
+      "grad_norm": 9.768436431884766,
+      "learning_rate": 2.974318451205057e-07,
+      "loss": 0.8961,
+      "step": 8000
+    },
+    {
+      "epoch": 3.3451397087760726,
+      "grad_norm": 11.650525093078613,
+      "learning_rate": 2.658237850651916e-07,
+      "loss": 0.9053,
+      "step": 8500
+    },
+    {
+      "epoch": 3.541912632821724,
+      "grad_norm": 8.362442970275879,
+      "learning_rate": 2.342157250098775e-07,
+      "loss": 0.8899,
+      "step": 9000
+    },
+    {
+      "epoch": 3.738685556867375,
+      "grad_norm": 9.931063652038574,
+      "learning_rate": 2.026076649545634e-07,
+      "loss": 0.8822,
+      "step": 9500
+    },
+    {
+      "epoch": 3.9354584809130264,
+      "grad_norm": 9.28101921081543,
+      "learning_rate": 1.709996048992493e-07,
+      "loss": 0.891,
+      "step": 10000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7320176409802185,
+      "eval_loss": 0.9737523198127747,
+      "eval_model_preparation_time": 0.0056,
+      "eval_runtime": 1242.2984,
+      "eval_samples_per_second": 87.245,
+      "eval_steps_per_second": 2.726,
+      "step": 10164
+    },
+    {
+      "epoch": 4.132231404958677,
+      "grad_norm": 8.689752578735352,
+      "learning_rate": 1.393915448439352e-07,
+      "loss": 0.8878,
+      "step": 10500
+    },
+    {
+      "epoch": 4.329004329004329,
+      "grad_norm": 7.7662224769592285,
+      "learning_rate": 1.077834847886211e-07,
+      "loss": 0.8791,
+      "step": 11000
+    },
+    {
+      "epoch": 4.525777253049981,
+      "grad_norm": 10.417122840881348,
+      "learning_rate": 7.617542473330699e-08,
+      "loss": 0.8847,
+      "step": 11500
+    },
+    {
+      "epoch": 4.7225501770956315,
+      "grad_norm": 10.2011137008667,
+      "learning_rate": 4.4567364677992886e-08,
+      "loss": 0.8956,
+      "step": 12000
+    },
+    {
+      "epoch": 4.919323101141283,
+      "grad_norm": 10.344655990600586,
+      "learning_rate": 1.2959304622678783e-08,
+      "loss": 0.8829,
+      "step": 12500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7323590197815175,
+      "eval_loss": 0.9717448353767395,
+      "eval_model_preparation_time": 0.0056,
+      "eval_runtime": 1227.7961,
+      "eval_samples_per_second": 88.275,
+      "eval_steps_per_second": 2.759,
+      "step": 12705
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 12705,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 6.301765894857818e+19,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-12705/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0ccd77f73df11a1333f963ab6437406025cd7af5d1fcfd30d1c335f7e202d63
+size 4667

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae08e577606eeef2b66632cb52d3ed3f9cdb59bca00aac0af10979498ee66c3e
+oid sha256:63b8a8b92cd1bc9a5ed6f1db877ea8c070ecc294f47c06c4935b510d576c8031
 size 343365480

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad3477ddc7ea3a5c3236c20065dd22f24f5262766b2c91e1cd0f8c8389a1871c
+oid sha256:c0ccd77f73df11a1333f963ab6437406025cd7af5d1fcfd30d1c335f7e202d63
 size 4667