Upload 8 files

config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "google/vit-large-patch16-224",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "airplane",
+    "1": "automobile",
+    "2": "bird",
+    "3": "cat",
+    "4": "deer",
+    "5": "dog",
+    "6": "frog",
+    "7": "horse",
+    "8": "ship",
+    "9": "truck"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "airplane": 0,
+    "automobile": 1,
+    "bird": 2,
+    "cat": 3,
+    "deer": 4,
+    "dog": 5,
+    "frog": 6,
+    "horse": 7,
+    "ship": 8,
+    "truck": 9
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 16,
+  "num_channels": 3,
+  "num_hidden_layers": 24,
+  "patch_size": 16,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.2"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d4a8a5bc3967a7456510bde39786f606e2b493362bc1e1d096bc3e0fb4d4121
+size 2426725317

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
+  }
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a9e4729d92c7afbddecf6f47317c8c102e11d58136eeeee54a4c354729e6a48
+size 1213381421

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82bdb3348630fd0c85da6a17901be79efaea14773a56d2c79fe5b0074f9069a1
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dca64b7eac7a4fd7a01f82a1cef7a27f8eb0382f0849f1b5a8971bb8b96ca675
+size 627

trainer_state.json

@@ -0,0 +1,103 @@
+{
+  "best_metric": 0.9818,
+  "best_model_checkpoint": "fine-tune-vit-L-cifar10\\checkpoint-3520",
+  "epoch": 5.0,
+  "global_step": 3520,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00017159090909090908,
+      "loss": 0.5656,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9554,
+      "eval_loss": 0.13088831305503845,
+      "eval_runtime": 56.4271,
+      "eval_samples_per_second": 88.61,
+      "eval_steps_per_second": 1.4,
+      "step": 704
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.0001431818181818182,
+      "loss": 0.4167,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9664,
+      "eval_loss": 0.10773425549268723,
+      "eval_runtime": 55.2538,
+      "eval_samples_per_second": 90.492,
+      "eval_steps_per_second": 1.43,
+      "step": 1408
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 0.00011477272727272728,
+      "loss": 0.3517,
+      "step": 1500
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 8.636363636363637e-05,
+      "loss": 0.2912,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.976,
+      "eval_loss": 0.07570263743400574,
+      "eval_runtime": 55.5205,
+      "eval_samples_per_second": 90.057,
+      "eval_steps_per_second": 1.423,
+      "step": 2112
+    },
+    {
+      "epoch": 3.55,
+      "learning_rate": 5.7954545454545464e-05,
+      "loss": 0.2422,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9804,
+      "eval_loss": 0.06285750865936279,
+      "eval_runtime": 55.4687,
+      "eval_samples_per_second": 90.141,
+      "eval_steps_per_second": 1.424,
+      "step": 2816
+    },
+    {
+      "epoch": 4.26,
+      "learning_rate": 2.954545454545455e-05,
+      "loss": 0.1998,
+      "step": 3000
+    },
+    {
+      "epoch": 4.97,
+      "learning_rate": 1.1363636363636364e-06,
+      "loss": 0.1661,
+      "step": 3500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9818,
+      "eval_loss": 0.05650622025132179,
+      "eval_runtime": 56.1248,
+      "eval_samples_per_second": 89.087,
+      "eval_steps_per_second": 1.408,
+      "step": 3520
+    }
+  ],
+  "max_steps": 3520,
+  "num_train_epochs": 5,
+  "total_flos": 6.16368568144896e+19,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d53c2f15a036e4b0d0d3f89090a5b856f8c1be1ae0f761fd93917811ad17ab40
+size 3899