End of training

trainer_state.json

@@ -0,0 +1,165 @@
+{
+  "best_metric": 2.734494686126709,
+  "best_model_checkpoint": "detr-resnet50-cd45rb/checkpoint-2178",
+  "epoch": 10.0,
+  "global_step": 2420,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 9e-05,
+      "loss": 3.8886,
+      "step": 242
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.8753762245178223,
+      "eval_runtime": 31.2211,
+      "eval_samples_per_second": 3.203,
+      "eval_steps_per_second": 0.416,
+      "step": 242
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 8e-05,
+      "loss": 3.6406,
+      "step": 484
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.795649528503418,
+      "eval_runtime": 11.7067,
+      "eval_samples_per_second": 8.542,
+      "eval_steps_per_second": 1.11,
+      "step": 484
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 7e-05,
+      "loss": 3.6109,
+      "step": 726
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.8411974906921387,
+      "eval_runtime": 11.282,
+      "eval_samples_per_second": 8.864,
+      "eval_steps_per_second": 1.152,
+      "step": 726
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 6e-05,
+      "loss": 3.5724,
+      "step": 968
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.7905938625335693,
+      "eval_runtime": 11.8045,
+      "eval_samples_per_second": 8.471,
+      "eval_steps_per_second": 1.101,
+      "step": 968
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 5e-05,
+      "loss": 3.5492,
+      "step": 1210
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 2.7472944259643555,
+      "eval_runtime": 11.7153,
+      "eval_samples_per_second": 8.536,
+      "eval_steps_per_second": 1.11,
+      "step": 1210
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4e-05,
+      "loss": 3.5595,
+      "step": 1452
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 2.7593834400177,
+      "eval_runtime": 11.588,
+      "eval_samples_per_second": 8.63,
+      "eval_steps_per_second": 1.122,
+      "step": 1452
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 3e-05,
+      "loss": 3.5249,
+      "step": 1694
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 2.7395966053009033,
+      "eval_runtime": 11.6919,
+      "eval_samples_per_second": 8.553,
+      "eval_steps_per_second": 1.112,
+      "step": 1694
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 2e-05,
+      "loss": 3.524,
+      "step": 1936
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 2.756193161010742,
+      "eval_runtime": 11.5397,
+      "eval_samples_per_second": 8.666,
+      "eval_steps_per_second": 1.127,
+      "step": 1936
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 1e-05,
+      "loss": 3.4908,
+      "step": 2178
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 2.734494686126709,
+      "eval_runtime": 11.5952,
+      "eval_samples_per_second": 8.624,
+      "eval_steps_per_second": 1.121,
+      "step": 2178
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0,
+      "loss": 3.5149,
+      "step": 2420
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 2.741795539855957,
+      "eval_runtime": 11.3597,
+      "eval_samples_per_second": 8.803,
+      "eval_steps_per_second": 1.144,
+      "step": 2420
+    },
+    {
+      "epoch": 10.0,
+      "step": 2420,
+      "total_flos": 4.6164408869376e+18,
+      "train_loss": 3.587586029304946,
+      "train_runtime": 3403.4382,
+      "train_samples_per_second": 2.838,
+      "train_steps_per_second": 0.711
+    }
+  ],
+  "max_steps": 2420,
+  "num_train_epochs": 10,
+  "total_flos": 4.6164408869376e+18,
+  "trial_name": null,
+  "trial_params": null
+}