End of training

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 2.070624589920044,
-  "best_model_checkpoint": "detr-r50-cd45rb-2ah-6l\\checkpoint-23030",
-  "epoch": 5.0,
-  "global_step": 23030,
+  "best_metric": 1.9501873254776,
+  "best_model_checkpoint": "detr-r50-cd45rb-2ah-6l\\checkpoint-46060",
+  "epoch": 10.0,
+  "global_step": 46060,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -78,18 +78,88 @@
       "step": 23030
     },
     {
-      "epoch": 5.0,
-      "step": 23030,
-      "total_flos": 4.401655508016e+19,
-      "train_loss": 2.908882859992401,
-      "train_runtime": 15260.3368,
-      "train_samples_per_second": 6.036,
-      "train_steps_per_second": 1.509
+      "epoch": 6.0,
+      "learning_rate": 4.0041250542770305e-06,
+      "loss": 2.5992,
+      "step": 27636
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 2.0398733615875244,
+      "eval_runtime": 206.6619,
+      "eval_samples_per_second": 8.618,
+      "eval_steps_per_second": 1.079,
+      "step": 27636
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 3.00412505427703e-06,
+      "loss": 2.5376,
+      "step": 32242
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 1.999878168106079,
+      "eval_runtime": 202.5511,
+      "eval_samples_per_second": 8.793,
+      "eval_steps_per_second": 1.101,
+      "step": 32242
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 2.0045592705167173e-06,
+      "loss": 2.4979,
+      "step": 36848
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 1.996376872062683,
+      "eval_runtime": 206.6396,
+      "eval_samples_per_second": 8.619,
+      "eval_steps_per_second": 1.079,
+      "step": 36848
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 1.0049934867564047e-06,
+      "loss": 2.4669,
+      "step": 41454
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 1.9711166620254517,
+      "eval_runtime": 201.9711,
+      "eval_samples_per_second": 8.818,
+      "eval_steps_per_second": 1.104,
+      "step": 41454
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 5.210594876248372e-09,
+      "loss": 2.447,
+      "step": 46060
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 1.9501873254776,
+      "eval_runtime": 205.7415,
+      "eval_samples_per_second": 8.656,
+      "eval_steps_per_second": 1.084,
+      "step": 46060
+    },
+    {
+      "epoch": 10.0,
+      "step": 46060,
+      "total_flos": 8.803311016032e+19,
+      "train_loss": 1.2548531721531697,
+      "train_runtime": 14767.0616,
+      "train_samples_per_second": 12.474,
+      "train_steps_per_second": 3.119
     }
   ],
-  "max_steps": 23030,
-  "num_train_epochs": 5,
-  "total_flos": 4.401655508016e+19,
+  "max_steps": 46060,
+  "num_train_epochs": 10,
+  "total_flos": 8.803311016032e+19,
   "trial_name": null,
   "trial_params": null
 }