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 sha256:0fea40885a6c2e787c5beb7f703cb09caca23652d4ad326526950215f1dc01c6
+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 +1,161 @@
+{
+  "best_metric": 0.8986666666666666,
+  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0657/checkpoints/checkpoint-2664",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 2664,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.2736525535583496,
+      "learning_rate": 8.657457896300791e-05,
+      "loss": 1.6592,
+      "step": 333
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7538666666666667,
+      "eval_loss": 0.8866291046142578,
+      "eval_runtime": 7.2246,
+      "eval_samples_per_second": 519.062,
+      "eval_steps_per_second": 8.167,
+      "step": 333
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": Infinity,
+      "learning_rate": 7.685730736804761e-05,
+      "loss": 0.5448,
+      "step": 666
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8026666666666666,
+      "eval_loss": 0.6555348038673401,
+      "eval_runtime": 7.7161,
+      "eval_samples_per_second": 485.999,
+      "eval_steps_per_second": 7.646,
+      "step": 666
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.9496603608131409,
+      "learning_rate": 6.226977039554153e-05,
+      "loss": 0.3214,
+      "step": 999
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8632,
+      "eval_loss": 0.45658496022224426,
+      "eval_runtime": 7.8016,
+      "eval_samples_per_second": 480.671,
+      "eval_steps_per_second": 7.563,
+      "step": 999
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.4970409870147705,
+      "learning_rate": 4.505306743117272e-05,
+      "loss": 0.187,
+      "step": 1332
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8749333333333333,
+      "eval_loss": 0.4338541626930237,
+      "eval_runtime": 7.7252,
+      "eval_samples_per_second": 485.422,
+      "eval_steps_per_second": 7.637,
+      "step": 1332
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.13811548054218292,
+      "learning_rate": 2.7828285431465317e-05,
+      "loss": 0.1065,
+      "step": 1665
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8816,
+      "eval_loss": 0.4089241027832031,
+      "eval_runtime": 7.2869,
+      "eval_samples_per_second": 514.622,
+      "eval_steps_per_second": 8.097,
+      "step": 1665
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.3568909764289856,
+      "learning_rate": 1.3217741312837138e-05,
+      "loss": 0.0518,
+      "step": 1998
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8930666666666667,
+      "eval_loss": 0.39138007164001465,
+      "eval_runtime": 7.3498,
+      "eval_samples_per_second": 510.218,
+      "eval_steps_per_second": 8.027,
+      "step": 1998
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.19655214250087738,
+      "learning_rate": 3.4457579724370674e-06,
+      "loss": 0.0286,
+      "step": 2331
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8936,
+      "eval_loss": 0.4012141823768616,
+      "eval_runtime": 7.4317,
+      "eval_samples_per_second": 504.593,
+      "eval_steps_per_second": 7.939,
+      "step": 2331
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.3163028657436371,
+      "learning_rate": 3.12905914479078e-11,
+      "loss": 0.0184,
+      "step": 2664
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8986666666666666,
+      "eval_loss": 0.3862427771091461,
+      "eval_runtime": 7.1478,
+      "eval_samples_per_second": 524.638,
+      "eval_steps_per_second": 8.254,
+      "step": 2664
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2664,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "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": 1.317930564980736e+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 sha256:85c5cb14452dfa6941ce0982f967fbcc01acee9a4455def5bb3dd0e1ca73a971
+size 5368