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": 42.5944,
+    "train_samples_per_second": 35.779,
+    "train_steps_per_second": 2.254
+}

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"
+}

pytorch_model.bin

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

runs/Nov09_20-39-33_70506a7f64af/1636490380.517445/events.out.tfevents.1636490380.70506a7f64af.361.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d349235864bdc454b86da77af432f93f5c2a24bbb491a445539a1ce1f58ada5
+size 4528

runs/Nov09_20-39-33_70506a7f64af/events.out.tfevents.1636490380.70506a7f64af.361.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80f76d8564b4ecd80de585d56340e6a43344cdaa5f62dab61c8bdc7b2b1fec95
+size 6166

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "total_flos": 0.0,
+    "train_loss": 0.7672463009754816,
+    "train_runtime": 42.5944,
+    "train_samples_per_second": 35.779,
+    "train_steps_per_second": 2.254
+}

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": 0.857,
+      "eval_samples_per_second": 78.18,
+      "eval_steps_per_second": 5.834,
+      "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": 0.8562,
+      "eval_samples_per_second": 78.255,
+      "eval_steps_per_second": 5.84,
+      "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": 0.8709,
+      "eval_samples_per_second": 76.935,
+      "eval_steps_per_second": 5.741,
+      "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": 0.8617,
+      "eval_samples_per_second": 77.756,
+      "eval_steps_per_second": 5.803,
+      "step": 96
+    },
+    {
+      "epoch": 4.0,
+      "step": 96,
+      "total_flos": 0.0,
+      "train_loss": 0.7672463009754816,
+      "train_runtime": 42.5944,
+      "train_samples_per_second": 35.779,
+      "train_steps_per_second": 2.254
+    }
+  ],
+  "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 sha256:6ded504200ed97c8596525b9b070918b298cb5cf5eadbab1a46f4df15698945f
+size 2863