End of training

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.99,
+    "train_loss": 0.9566538672977024,
+    "train_runtime": 16896.1488,
+    "train_samples_per_second": 1.709,
+    "train_steps_per_second": 0.013
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.99,
+    "train_loss": 0.9566538672977024,
+    "train_runtime": 16896.1488,
+    "train_samples_per_second": 1.709,
+    "train_steps_per_second": 0.013
+}

trainer_state.json

@@ -0,0 +1,211 @@
+{
+  "best_metric": 0.9979227253842958,
+  "best_model_checkpoint": "vit-base-patch16-224-in21k-Smart_Tour_CarioVersion\\checkpoint-150",
+  "epoch": 2.990033222591362,
+  "eval_steps": 500,
+  "global_step": 225,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.9199802875518799,
+      "learning_rate": 2.173913043478261e-05,
+      "loss": 2.6968,
+      "step": 10
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 1.0731828212738037,
+      "learning_rate": 4.347826086956522e-05,
+      "loss": 2.514,
+      "step": 20
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.129557490348816,
+      "learning_rate": 4.826732673267327e-05,
+      "loss": 2.2023,
+      "step": 30
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 1.1548207998275757,
+      "learning_rate": 4.57920792079208e-05,
+      "loss": 1.8253,
+      "step": 40
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.141477346420288,
+      "learning_rate": 4.331683168316832e-05,
+      "loss": 1.5296,
+      "step": 50
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.0975979566574097,
+      "learning_rate": 4.0841584158415844e-05,
+      "loss": 1.2621,
+      "step": 60
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 1.1613612174987793,
+      "learning_rate": 3.8366336633663367e-05,
+      "loss": 1.0618,
+      "step": 70
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9842127129206482,
+      "eval_loss": 0.8608944416046143,
+      "eval_runtime": 556.5393,
+      "eval_samples_per_second": 4.325,
+      "eval_steps_per_second": 0.137,
+      "step": 75
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 1.0027191638946533,
+      "learning_rate": 3.589108910891089e-05,
+      "loss": 0.8985,
+      "step": 80
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 1.0154672861099243,
+      "learning_rate": 3.341584158415842e-05,
+      "loss": 0.7635,
+      "step": 90
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 1.0417600870132446,
+      "learning_rate": 3.094059405940594e-05,
+      "loss": 0.7196,
+      "step": 100
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 0.8144603371620178,
+      "learning_rate": 2.8465346534653464e-05,
+      "loss": 0.6409,
+      "step": 110
+    },
+    {
+      "epoch": 1.59,
+      "grad_norm": 0.8676450848579407,
+      "learning_rate": 2.5990099009900993e-05,
+      "loss": 0.5916,
+      "step": 120
+    },
+    {
+      "epoch": 1.73,
+      "grad_norm": 1.0389797687530518,
+      "learning_rate": 2.3514851485148515e-05,
+      "loss": 0.5408,
+      "step": 130
+    },
+    {
+      "epoch": 1.86,
+      "grad_norm": 0.9222360849380493,
+      "learning_rate": 2.103960396039604e-05,
+      "loss": 0.5145,
+      "step": 140
+    },
+    {
+      "epoch": 1.99,
+      "grad_norm": 0.7808237671852112,
+      "learning_rate": 1.8564356435643564e-05,
+      "loss": 0.4871,
+      "step": 150
+    },
+    {
+      "epoch": 1.99,
+      "eval_accuracy": 0.9979227253842958,
+      "eval_loss": 0.4369741976261139,
+      "eval_runtime": 321.3421,
+      "eval_samples_per_second": 7.49,
+      "eval_steps_per_second": 0.237,
+      "step": 150
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 0.7686122059822083,
+      "learning_rate": 1.608910891089109e-05,
+      "loss": 0.4781,
+      "step": 160
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 0.7780303955078125,
+      "learning_rate": 1.3613861386138616e-05,
+      "loss": 0.4613,
+      "step": 170
+    },
+    {
+      "epoch": 2.39,
+      "grad_norm": 0.7087822556495667,
+      "learning_rate": 1.113861386138614e-05,
+      "loss": 0.4609,
+      "step": 180
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 0.6575062870979309,
+      "learning_rate": 8.663366336633663e-06,
+      "loss": 0.4268,
+      "step": 190
+    },
+    {
+      "epoch": 2.66,
+      "grad_norm": 0.6254608035087585,
+      "learning_rate": 6.1881188118811885e-06,
+      "loss": 0.4067,
+      "step": 200
+    },
+    {
+      "epoch": 2.79,
+      "grad_norm": 0.835518479347229,
+      "learning_rate": 3.7128712871287128e-06,
+      "loss": 0.4191,
+      "step": 210
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 0.7507413029670715,
+      "learning_rate": 1.2376237623762377e-06,
+      "loss": 0.4088,
+      "step": 220
+    },
+    {
+      "epoch": 2.99,
+      "eval_accuracy": 0.9979227253842958,
+      "eval_loss": 0.37498676776885986,
+      "eval_runtime": 288.7355,
+      "eval_samples_per_second": 8.336,
+      "eval_steps_per_second": 0.263,
+      "step": 225
+    },
+    {
+      "epoch": 2.99,
+      "step": 225,
+      "total_flos": 2.2312543250646835e+18,
+      "train_loss": 0.9566538672977024,
+      "train_runtime": 16896.1488,
+      "train_samples_per_second": 1.709,
+      "train_steps_per_second": 0.013
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 225,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 2.2312543250646835e+18,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}