End of training

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "total_flos": 0.0,
+    "train_loss": 0.7672463009754816,
+    "train_runtime": 43.8376,
+    "train_samples_per_second": 34.765,
+    "train_steps_per_second": 2.19
+}

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "google/vit-base-patch16-224-in21k",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "corgi",
+    "1": "husky",
+    "2": "shibu inu"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "corgi": "0",
+    "husky": "1",
+    "shibu inu": "2"
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.12.3"
+}

preprocessor_config.json

@@ -0,0 +1,17 @@
+{
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "ViTFeatureExtractor",
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "size": 224
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:979fa7819df9c11e638b3ba4376f62034376242d26d0ea718612d9d5157e4d11
+size 343282929

runs/Nov09_20-51-42_70506a7f64af/1636491109.8043528/events.out.tfevents.1636491109.70506a7f64af.361.17

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8969f64697b5a13ed7d5bc4b2937ee9e4c3dfde887f7cecc457f9f01607cd549
+size 4532

runs/Nov09_20-51-42_70506a7f64af/events.out.tfevents.1636491109.70506a7f64af.361.16

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:583f05f1c60128305ef90907875791e380fb5fe4d3d4fddecfd3d0099f957d51
+size 6170

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "total_flos": 0.0,
+    "train_loss": 0.7672463009754816,
+    "train_runtime": 43.8376,
+    "train_samples_per_second": 34.765,
+    "train_steps_per_second": 2.19
+}

trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "global_step": 96,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.42,
+      "learning_rate": 2e-05,
+      "loss": 1.0914,
+      "step": 10
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 2e-05,
+      "loss": 1.0328,
+      "step": 20
+    },
+    {
+      "epoch": 1.0,
+      "eval_acc": 0.746268630027771,
+      "eval_loss": 0.9441611170768738,
+      "eval_runtime": 0.8959,
+      "eval_samples_per_second": 74.785,
+      "eval_steps_per_second": 5.581,
+      "step": 24
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 2e-05,
+      "loss": 0.9558,
+      "step": 30
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 2e-05,
+      "loss": 0.8742,
+      "step": 40
+    },
+    {
+      "epoch": 2.0,
+      "eval_acc": 0.9402984976768494,
+      "eval_loss": 0.7099391222000122,
+      "eval_runtime": 0.9063,
+      "eval_samples_per_second": 73.928,
+      "eval_steps_per_second": 5.517,
+      "step": 48
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 2e-05,
+      "loss": 0.7474,
+      "step": 50
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 2e-05,
+      "loss": 0.6858,
+      "step": 60
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 2e-05,
+      "loss": 0.6451,
+      "step": 70
+    },
+    {
+      "epoch": 3.0,
+      "eval_acc": 0.9402984976768494,
+      "eval_loss": 0.5049594044685364,
+      "eval_runtime": 0.9206,
+      "eval_samples_per_second": 72.776,
+      "eval_steps_per_second": 5.431,
+      "step": 72
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 2e-05,
+      "loss": 0.5587,
+      "step": 80
+    },
+    {
+      "epoch": 3.75,
+      "learning_rate": 2e-05,
+      "loss": 0.508,
+      "step": 90
+    },
+    {
+      "epoch": 4.0,
+      "eval_acc": 0.9402984976768494,
+      "eval_loss": 0.37610408663749695,
+      "eval_runtime": 0.911,
+      "eval_samples_per_second": 73.547,
+      "eval_steps_per_second": 5.489,
+      "step": 96
+    },
+    {
+      "epoch": 4.0,
+      "step": 96,
+      "total_flos": 0.0,
+      "train_loss": 0.7672463009754816,
+      "train_runtime": 43.8376,
+      "train_samples_per_second": 34.765,
+      "train_steps_per_second": 2.19
+    }
+  ],
+  "max_steps": 96,
+  "num_train_epochs": 4,
+  "total_flos": 0.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8ad915302f9c4b601a71c9de43a75496cc703b8f6cfc70984999a2af109bd24
+size 2863