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 sha256:6841c5b005ac17ff533d5796c191990e0e8e5041b85003c67fdb3bdf37ff4ea2
+size 343372768

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": 0.5298666666666667,
+  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0500/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": Infinity,
+      "learning_rate": 0.0005,
+      "loss": 3.2565,
+      "step": 333
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.20613333333333334,
+      "eval_loss": 2.939532518386841,
+      "eval_runtime": 12.1432,
+      "eval_samples_per_second": 308.815,
+      "eval_steps_per_second": 4.859,
+      "step": 333
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0005,
+      "loss": 2.674,
+      "step": 666
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.3218666666666667,
+      "eval_loss": 2.506107807159424,
+      "eval_runtime": 12.2383,
+      "eval_samples_per_second": 306.415,
+      "eval_steps_per_second": 4.821,
+      "step": 666
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 8.53410816192627,
+      "learning_rate": 0.0005,
+      "loss": 2.2594,
+      "step": 999
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.3586666666666667,
+      "eval_loss": 2.3375556468963623,
+      "eval_runtime": 12.0955,
+      "eval_samples_per_second": 310.033,
+      "eval_steps_per_second": 4.878,
+      "step": 999
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 12.522454261779785,
+      "learning_rate": 0.0005,
+      "loss": 1.9483,
+      "step": 1332
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.43733333333333335,
+      "eval_loss": 2.031986713409424,
+      "eval_runtime": 11.8594,
+      "eval_samples_per_second": 316.206,
+      "eval_steps_per_second": 4.975,
+      "step": 1332
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0005,
+      "loss": 1.6697,
+      "step": 1665
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.48346666666666666,
+      "eval_loss": 1.8123379945755005,
+      "eval_runtime": 12.1646,
+      "eval_samples_per_second": 308.271,
+      "eval_steps_per_second": 4.85,
+      "step": 1665
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 20.4299259185791,
+      "learning_rate": 0.0005,
+      "loss": 1.4148,
+      "step": 1998
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.4901333333333333,
+      "eval_loss": 1.8386976718902588,
+      "eval_runtime": 12.0838,
+      "eval_samples_per_second": 310.332,
+      "eval_steps_per_second": 4.883,
+      "step": 1998
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 20.94927406311035,
+      "learning_rate": 0.0005,
+      "loss": 1.1505,
+      "step": 2331
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.508,
+      "eval_loss": 1.8421908617019653,
+      "eval_runtime": 11.9992,
+      "eval_samples_per_second": 312.521,
+      "eval_steps_per_second": 4.917,
+      "step": 2331
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 15.200113296508789,
+      "learning_rate": 0.0005,
+      "loss": 0.8885,
+      "step": 2664
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.5061333333333333,
+      "eval_loss": 1.8651669025421143,
+      "eval_runtime": 12.2064,
+      "eval_samples_per_second": 307.215,
+      "eval_steps_per_second": 4.834,
+      "step": 2664
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 24.23003578186035,
+      "learning_rate": 0.0005,
+      "loss": 0.6529,
+      "step": 2997
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.5298666666666667,
+      "eval_loss": 1.932701587677002,
+      "eval_runtime": 12.2412,
+      "eval_samples_per_second": 306.341,
+      "eval_steps_per_second": 4.82,
+      "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 sha256:81b1171eaf75257523853dbf8e1c1163a40c53d2a66d1e67f71f77fdfeb027d1
+size 5368