End of training

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 1.5942937135696411,
-  "best_model_checkpoint": "detr-r101-cd45rb-8ah-6l-256d-4096ffn-correcetd\\checkpoint-92120",
-  "epoch": 20.0,
-  "global_step": 92120,
+  "best_metric": 1.5818963050842285,
+  "best_model_checkpoint": "detr-r101-cd45rb-8ah-6l-256d-4096ffn-correcetd\\checkpoint-115150",
+  "epoch": 25.0,
+  "global_step": 115150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -288,18 +288,88 @@
       "step": 92120
     },
     {
-      "epoch": 20.0,
-      "step": 92120,
-      "total_flos": 3.09958520212224e+20,
-      "train_loss": 2.1620497868778497,
-      "train_runtime": 79274.0231,
-      "train_samples_per_second": 4.647,
-      "train_steps_per_second": 1.162
+      "epoch": 21.0,
+      "learning_rate": 1.603821102909249e-06,
+      "loss": 2.0165,
+      "step": 96726
+    },
+    {
+      "epoch": 21.0,
+      "eval_loss": 1.6092338562011719,
+      "eval_runtime": 906.9743,
+      "eval_samples_per_second": 1.964,
+      "eval_steps_per_second": 0.246,
+      "step": 96726
+    },
+    {
+      "epoch": 22.0,
+      "learning_rate": 1.2039079461571863e-06,
+      "loss": 2.007,
+      "step": 101332
+    },
+    {
+      "epoch": 22.0,
+      "eval_loss": 1.5986328125,
+      "eval_runtime": 1255.6495,
+      "eval_samples_per_second": 1.418,
+      "eval_steps_per_second": 0.178,
+      "step": 101332
+    },
+    {
+      "epoch": 23.0,
+      "learning_rate": 8.039947894051238e-07,
+      "loss": 2.0009,
+      "step": 105938
+    },
+    {
+      "epoch": 23.0,
+      "eval_loss": 1.5931391716003418,
+      "eval_runtime": 1400.4232,
+      "eval_samples_per_second": 1.272,
+      "eval_steps_per_second": 0.159,
+      "step": 105938
+    },
+    {
+      "epoch": 24.0,
+      "learning_rate": 4.041684759009987e-07,
+      "loss": 1.992,
+      "step": 110544
+    },
+    {
+      "epoch": 24.0,
+      "eval_loss": 1.5898462533950806,
+      "eval_runtime": 1322.312,
+      "eval_samples_per_second": 1.347,
+      "eval_steps_per_second": 0.169,
+      "step": 110544
+    },
+    {
+      "epoch": 25.0,
+      "learning_rate": 4.342162396873643e-09,
+      "loss": 1.9769,
+      "step": 115150
+    },
+    {
+      "epoch": 25.0,
+      "eval_loss": 1.5818963050842285,
+      "eval_runtime": 1441.7733,
+      "eval_samples_per_second": 1.235,
+      "eval_steps_per_second": 0.155,
+      "step": 115150
+    },
+    {
+      "epoch": 25.0,
+      "step": 115150,
+      "total_flos": 3.874481502652799e+20,
+      "train_loss": 0.3997329824549501,
+      "train_runtime": 88532.2397,
+      "train_samples_per_second": 5.202,
+      "train_steps_per_second": 1.301
     }
   ],
-  "max_steps": 92120,
-  "num_train_epochs": 20,
-  "total_flos": 3.09958520212224e+20,
+  "max_steps": 115150,
+  "num_train_epochs": 25,
+  "total_flos": 3.874481502652799e+20,
   "trial_name": null,
   "trial_params": null
 }