End of training

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6561a03f12c42b7d9ef3f539bc378c5f48f19ff799b43b4034defb3ec835ba52
+oid sha256:6e678fa92eab62c06c943e42cef882fd7c3f8e6459a583f165ef05a3a2224ddb
 size 166616101

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 1.639158010482788,
-  "best_model_checkpoint": "detr-r50-cd45rb-8ah-6l-gelu-corrected\\checkpoint-46060",
-  "epoch": 10.0,
-  "global_step": 46060,
+  "best_metric": 1.5988867282867432,
+  "best_model_checkpoint": "detr-r50-cd45rb-8ah-6l-gelu-corrected\\checkpoint-87514",
+  "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": 8.803256478082562e+19,
-      "train_loss": 2.275937762904364,
-      "train_runtime": 29381.2037,
-      "train_samples_per_second": 6.27,
-      "train_steps_per_second": 1.568
+      "epoch": 11.0,
+      "learning_rate": 4.50293095961789e-06,
+      "loss": 2.1132,
+      "step": 50666
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 1.687514305114746,
+      "eval_runtime": 203.299,
+      "eval_samples_per_second": 8.76,
+      "eval_steps_per_second": 1.097,
+      "step": 50666
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 4.003039513677812e-06,
+      "loss": 2.1145,
+      "step": 55272
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 1.6863107681274414,
+      "eval_runtime": 203.0628,
+      "eval_samples_per_second": 8.771,
+      "eval_steps_per_second": 1.098,
+      "step": 55272
+    },
+    {
+      "epoch": 13.0,
+      "learning_rate": 3.5032566217976557e-06,
+      "loss": 2.0947,
+      "step": 59878
+    },
+    {
+      "epoch": 13.0,
+      "eval_loss": 1.6527632474899292,
+      "eval_runtime": 203.1785,
+      "eval_samples_per_second": 8.766,
+      "eval_steps_per_second": 1.098,
+      "step": 59878
+    },
+    {
+      "epoch": 14.0,
+      "learning_rate": 3.003582283977421e-06,
+      "loss": 2.0777,
+      "step": 64484
+    },
+    {
+      "epoch": 14.0,
+      "eval_loss": 1.666866660118103,
+      "eval_runtime": 202.7783,
+      "eval_samples_per_second": 8.783,
+      "eval_steps_per_second": 1.1,
+      "step": 64484
+    },
+    {
+      "epoch": 15.0,
+      "learning_rate": 2.5036908380373426e-06,
+      "loss": 2.0551,
+      "step": 69090
+    },
+    {
+      "epoch": 15.0,
+      "eval_loss": 1.6240596771240234,
+      "eval_runtime": 203.6325,
+      "eval_samples_per_second": 8.746,
+      "eval_steps_per_second": 1.095,
+      "step": 69090
+    },
+    {
+      "epoch": 16.0,
+      "learning_rate": 2.0037993920972645e-06,
+      "loss": 2.0567,
+      "step": 73696
+    },
+    {
+      "epoch": 16.0,
+      "eval_loss": 1.6240826845169067,
+      "eval_runtime": 203.7113,
+      "eval_samples_per_second": 8.743,
+      "eval_steps_per_second": 1.095,
+      "step": 73696
+    },
+    {
+      "epoch": 17.0,
+      "learning_rate": 1.504233608336952e-06,
+      "loss": 2.042,
+      "step": 78302
+    },
+    {
+      "epoch": 17.0,
+      "eval_loss": 1.6171499490737915,
+      "eval_runtime": 203.6475,
+      "eval_samples_per_second": 8.746,
+      "eval_steps_per_second": 1.095,
+      "step": 78302
+    },
+    {
+      "epoch": 18.0,
+      "learning_rate": 1.004233608336952e-06,
+      "loss": 2.0306,
+      "step": 82908
+    },
+    {
+      "epoch": 18.0,
+      "eval_loss": 1.6062376499176025,
+      "eval_runtime": 203.3215,
+      "eval_samples_per_second": 8.76,
+      "eval_steps_per_second": 1.097,
+      "step": 82908
+    },
+    {
+      "epoch": 19.0,
+      "learning_rate": 5.043421623968737e-07,
+      "loss": 2.015,
+      "step": 87514
+    },
+    {
+      "epoch": 19.0,
+      "eval_loss": 1.5988867282867432,
+      "eval_runtime": 203.4303,
+      "eval_samples_per_second": 8.755,
+      "eval_steps_per_second": 1.096,
+      "step": 87514
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 4.559270516717325e-09,
+      "loss": 2.0084,
+      "step": 92120
+    },
+    {
+      "epoch": 20.0,
+      "eval_loss": 1.599236011505127,
+      "eval_runtime": 202.2872,
+      "eval_samples_per_second": 8.804,
+      "eval_steps_per_second": 1.102,
+      "step": 92120
+    },
+    {
+      "epoch": 20.0,
+      "step": 92120,
+      "total_flos": 1.7606512956165125e+20,
+      "train_loss": 1.0303937374484369,
+      "train_runtime": 29465.5365,
+      "train_samples_per_second": 12.503,
+      "train_steps_per_second": 3.126
     }
   ],
-  "max_steps": 46060,
-  "num_train_epochs": 10,
-  "total_flos": 8.803256478082562e+19,
+  "max_steps": 92120,
+  "num_train_epochs": 20,
+  "total_flos": 1.7606512956165125e+20,
   "trial_name": null,
   "trial_params": null
 }