End of training

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 1.122222661972046,
-  "best_model_checkpoint": "detr-r50-cd45rb-8ah-4l-1cost\\checkpoint-46060",
-  "epoch": 10.0,
-  "global_step": 46060,
+  "best_metric": 1.0859479904174805,
+  "best_model_checkpoint": "detr-r50-cd45rb-8ah-4l-1cost\\checkpoint-92120",
+  "epoch": 20.0,
+  "global_step": 92120,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -148,18 +148,158 @@
       "step": 46060
     },
     {
-      "epoch": 10.0,
-      "step": 46060,
-      "total_flos": 7.575060159014402e+19,
-      "train_loss": 1.5399620039588309,
-      "train_runtime": 28443.8043,
-      "train_samples_per_second": 6.476,
-      "train_steps_per_second": 1.619
+      "epoch": 11.0,
+      "learning_rate": 4.502496743378202e-07,
+      "loss": 1.4579,
+      "step": 50666
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 1.1178261041641235,
+      "eval_runtime": 201.3314,
+      "eval_samples_per_second": 8.846,
+      "eval_steps_per_second": 1.108,
+      "step": 50666
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 4.0027138514980457e-07,
+      "loss": 1.4529,
+      "step": 55272
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 1.1085678339004517,
+      "eval_runtime": 200.8718,
+      "eval_samples_per_second": 8.866,
+      "eval_steps_per_second": 1.11,
+      "step": 55272
+    },
+    {
+      "epoch": 13.0,
+      "learning_rate": 3.5028224055579677e-07,
+      "loss": 1.4397,
+      "step": 59878
+    },
+    {
+      "epoch": 13.0,
+      "eval_loss": 1.103363275527954,
+      "eval_runtime": 203.7656,
+      "eval_samples_per_second": 8.74,
+      "eval_steps_per_second": 1.094,
+      "step": 59878
+    },
+    {
+      "epoch": 14.0,
+      "learning_rate": 3.003039513677811e-07,
+      "loss": 1.4366,
+      "step": 64484
+    },
+    {
+      "epoch": 14.0,
+      "eval_loss": 1.0989503860473633,
+      "eval_runtime": 200.8632,
+      "eval_samples_per_second": 8.867,
+      "eval_steps_per_second": 1.11,
+      "step": 64484
+    },
+    {
+      "epoch": 15.0,
+      "learning_rate": 2.503256621797655e-07,
+      "loss": 1.425,
+      "step": 69090
+    },
+    {
+      "epoch": 15.0,
+      "eval_loss": 1.0942606925964355,
+      "eval_runtime": 201.1548,
+      "eval_samples_per_second": 8.854,
+      "eval_steps_per_second": 1.109,
+      "step": 69090
+    },
+    {
+      "epoch": 16.0,
+      "learning_rate": 2.003473729917499e-07,
+      "loss": 1.4252,
+      "step": 73696
+    },
+    {
+      "epoch": 16.0,
+      "eval_loss": 1.0911729335784912,
+      "eval_runtime": 200.7701,
+      "eval_samples_per_second": 8.871,
+      "eval_steps_per_second": 1.111,
+      "step": 73696
+    },
+    {
+      "epoch": 17.0,
+      "learning_rate": 1.5035822839774206e-07,
+      "loss": 1.4215,
+      "step": 78302
+    },
+    {
+      "epoch": 17.0,
+      "eval_loss": 1.088094711303711,
+      "eval_runtime": 202.7396,
+      "eval_samples_per_second": 8.785,
+      "eval_steps_per_second": 1.1,
+      "step": 78302
+    },
+    {
+      "epoch": 18.0,
+      "learning_rate": 1.0037993920972644e-07,
+      "loss": 1.4188,
+      "step": 82908
+    },
+    {
+      "epoch": 18.0,
+      "eval_loss": 1.0874948501586914,
+      "eval_runtime": 200.0402,
+      "eval_samples_per_second": 8.903,
+      "eval_steps_per_second": 1.115,
+      "step": 82908
+    },
+    {
+      "epoch": 19.0,
+      "learning_rate": 5.0390794615718624e-08,
+      "loss": 1.4133,
+      "step": 87514
+    },
+    {
+      "epoch": 19.0,
+      "eval_loss": 1.0869966745376587,
+      "eval_runtime": 200.3439,
+      "eval_samples_per_second": 8.89,
+      "eval_steps_per_second": 1.113,
+      "step": 87514
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 4.1250542770299607e-10,
+      "loss": 1.4152,
+      "step": 92120
+    },
+    {
+      "epoch": 20.0,
+      "eval_loss": 1.0859479904174805,
+      "eval_runtime": 200.8626,
+      "eval_samples_per_second": 8.867,
+      "eval_steps_per_second": 1.11,
+      "step": 92120
+    },
+    {
+      "epoch": 20.0,
+      "step": 92120,
+      "total_flos": 1.5150120318028805e+20,
+      "train_loss": 0.7153063927740312,
+      "train_runtime": 28368.5894,
+      "train_samples_per_second": 12.987,
+      "train_steps_per_second": 3.247
     }
   ],
-  "max_steps": 46060,
-  "num_train_epochs": 10,
-  "total_flos": 7.575060159014402e+19,
+  "max_steps": 92120,
+  "num_train_epochs": 20,
+  "total_flos": 1.5150120318028805e+20,
   "trial_name": null,
   "trial_params": null
 }