Upload folder using huggingface_hub

config.json

@@ -0,0 +1,134 @@
+{
+  "_name_or_path": "facebook/vit-mae-base",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "decoder_hidden_size": 512,
+  "decoder_intermediate_size": 2048,
+  "decoder_num_attention_heads": 16,
+  "decoder_num_hidden_layers": 8,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17",
+    "18": "LABEL_18",
+    "19": "LABEL_19",
+    "20": "LABEL_20",
+    "21": "LABEL_21",
+    "22": "LABEL_22",
+    "23": "LABEL_23",
+    "24": "LABEL_24",
+    "25": "LABEL_25",
+    "26": "LABEL_26",
+    "27": "LABEL_27",
+    "28": "LABEL_28",
+    "29": "LABEL_29",
+    "30": "LABEL_30",
+    "31": "LABEL_31",
+    "32": "LABEL_32",
+    "33": "LABEL_33",
+    "34": "LABEL_34",
+    "35": "LABEL_35",
+    "36": "LABEL_36",
+    "37": "LABEL_37",
+    "38": "LABEL_38",
+    "39": "LABEL_39",
+    "40": "LABEL_40",
+    "41": "LABEL_41",
+    "42": "LABEL_42",
+    "43": "LABEL_43",
+    "44": "LABEL_44",
+    "45": "LABEL_45",
+    "46": "LABEL_46",
+    "47": "LABEL_47",
+    "48": "LABEL_48",
+    "49": "LABEL_49"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "LABEL_18": 18,
+    "LABEL_19": 19,
+    "LABEL_2": 2,
+    "LABEL_20": 20,
+    "LABEL_21": 21,
+    "LABEL_22": 22,
+    "LABEL_23": 23,
+    "LABEL_24": 24,
+    "LABEL_25": 25,
+    "LABEL_26": 26,
+    "LABEL_27": 27,
+    "LABEL_28": 28,
+    "LABEL_29": 29,
+    "LABEL_3": 3,
+    "LABEL_30": 30,
+    "LABEL_31": 31,
+    "LABEL_32": 32,
+    "LABEL_33": 33,
+    "LABEL_34": 34,
+    "LABEL_35": 35,
+    "LABEL_36": 36,
+    "LABEL_37": 37,
+    "LABEL_38": 38,
+    "LABEL_39": 39,
+    "LABEL_4": 4,
+    "LABEL_40": 40,
+    "LABEL_41": 41,
+    "LABEL_42": 42,
+    "LABEL_43": 43,
+    "LABEL_44": 44,
+    "LABEL_45": 45,
+    "LABEL_46": 46,
+    "LABEL_47": 47,
+    "LABEL_48": 48,
+    "LABEL_49": 49,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_eps": 1e-12,
+  "mask_ratio": 0.75,
+  "model_type": "vit",
+  "norm_pix_loss": false,
+  "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"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cf92f4fd3f04fa31fb9f5fcad9a2fdf31951cd018aff3c790b17753bffc9230
+size 343372744

preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "ViTImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

trainer_state.json

@@ -0,0 +1,177 @@
+{
+  "best_metric": 0.8797333333333334,
+  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0269/checkpoints/checkpoint-2997",
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 2997,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.7857272624969482,
+      "learning_rate": 8.003003003003004e-05,
+      "loss": 1.3687,
+      "step": 333
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7906666666666666,
+      "eval_loss": 0.707594096660614,
+      "eval_runtime": 4.161,
+      "eval_samples_per_second": 901.217,
+      "eval_steps_per_second": 14.179,
+      "step": 333
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.9791254997253418,
+      "learning_rate": 7.003003003003004e-05,
+      "loss": 0.4585,
+      "step": 666
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8288,
+      "eval_loss": 0.557952344417572,
+      "eval_runtime": 3.9087,
+      "eval_samples_per_second": 959.394,
+      "eval_steps_per_second": 15.094,
+      "step": 666
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.9436779022216797,
+      "learning_rate": 6.003003003003003e-05,
+      "loss": 0.2532,
+      "step": 999
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8496,
+      "eval_loss": 0.5063246488571167,
+      "eval_runtime": 4.0115,
+      "eval_samples_per_second": 934.817,
+      "eval_steps_per_second": 14.708,
+      "step": 999
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.09931182116270065,
+      "learning_rate": 5.003003003003004e-05,
+      "loss": 0.1396,
+      "step": 1332
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8690666666666667,
+      "eval_loss": 0.45184609293937683,
+      "eval_runtime": 4.0795,
+      "eval_samples_per_second": 919.228,
+      "eval_steps_per_second": 14.463,
+      "step": 1332
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.042947668582201004,
+      "learning_rate": 4.003003003003003e-05,
+      "loss": 0.0765,
+      "step": 1665
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8725333333333334,
+      "eval_loss": 0.48188066482543945,
+      "eval_runtime": 3.9041,
+      "eval_samples_per_second": 960.538,
+      "eval_steps_per_second": 15.112,
+      "step": 1665
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": Infinity,
+      "learning_rate": 3.0060060060060065e-05,
+      "loss": 0.0389,
+      "step": 1998
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8584,
+      "eval_loss": 0.5618187785148621,
+      "eval_runtime": 4.6531,
+      "eval_samples_per_second": 805.922,
+      "eval_steps_per_second": 12.68,
+      "step": 1998
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.0476762130856514,
+      "learning_rate": 2.0060060060060062e-05,
+      "loss": 0.0162,
+      "step": 2331
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8712,
+      "eval_loss": 0.5057010650634766,
+      "eval_runtime": 5.2876,
+      "eval_samples_per_second": 709.21,
+      "eval_steps_per_second": 11.158,
+      "step": 2331
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.017669668421149254,
+      "learning_rate": 1.0060060060060061e-05,
+      "loss": 0.0056,
+      "step": 2664
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.876,
+      "eval_loss": 0.48914003372192383,
+      "eval_runtime": 4.7658,
+      "eval_samples_per_second": 786.855,
+      "eval_steps_per_second": 12.38,
+      "step": 2664
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.061433542519807816,
+      "learning_rate": 6.006006006006006e-08,
+      "loss": 0.0027,
+      "step": 2997
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8797333333333334,
+      "eval_loss": 0.48338672518730164,
+      "eval_runtime": 4.2371,
+      "eval_samples_per_second": 885.034,
+      "eval_steps_per_second": 13.925,
+      "step": 2997
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2997,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "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": 1.482671885603328e+19,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00059ef9b2a3bc7652d28c2a743661871deaf8362b3719b401aa6a389b9e3b5a
+size 5368