Training in progress, epoch 1

all_results.json

@@ -1,13 +1,13 @@
 {
-    "epoch": 10.0,
+    "epoch": 20.0,
     "eval_accuracy": 1.0,
     "eval_loss": 0.5404492020606995,
     "eval_runtime": 0.0787,
     "eval_samples_per_second": 50.832,
     "eval_steps_per_second": 12.708,
-    "total_flos": 8699596145049600.0,
-    "train_loss": 0.20386319160461425,
-    "train_runtime": 41.2868,
-    "train_samples_per_second": 8.477,
-    "train_steps_per_second": 0.242
+    "total_flos": 1.73991922900992e+16,
+    "train_loss": 0.15340265035629272,
+    "train_runtime": 48.7906,
+    "train_samples_per_second": 14.347,
+    "train_steps_per_second": 0.41
 }

runs/Sep06_02-49-21_8a3aa9d02c1c/1662432936.4683797/events.out.tfevents.1662432936.8a3aa9d02c1c.69.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5165775fa9b52edd356ac81b99b9edbbc5a5d992f56842535f9287a290c719c
+size 5494

runs/Sep06_02-49-21_8a3aa9d02c1c/events.out.tfevents.1662432936.8a3aa9d02c1c.69.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c39f49f7b23d1e894bff63ace3a6f02330eef95725f434cea471aeb41ea81cd9
+size 4317

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 10.0,
-    "total_flos": 8699596145049600.0,
-    "train_loss": 0.20386319160461425,
-    "train_runtime": 41.2868,
-    "train_samples_per_second": 8.477,
-    "train_steps_per_second": 0.242
+    "epoch": 20.0,
+    "total_flos": 1.73991922900992e+16,
+    "train_loss": 0.15340265035629272,
+    "train_runtime": 48.7906,
+    "train_samples_per_second": 14.347,
+    "train_steps_per_second": 0.41
 }

trainer_state.json

@@ -1,121 +1,217 @@
 {
-  "best_metric": 1.0,
-  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-vosap/checkpoint-1",
-  "epoch": 10.0,
-  "global_step": 10,
+  "best_metric": 0.75,
+  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-vosap/checkpoint-11",
+  "epoch": 20.0,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 1.0,
-      "eval_loss": 0.5404492020606995,
-      "eval_runtime": 0.0625,
-      "eval_samples_per_second": 64.034,
-      "eval_steps_per_second": 16.008,
+      "eval_accuracy": 0.5,
+      "eval_loss": 0.6076761484146118,
+      "eval_runtime": 0.0775,
+      "eval_samples_per_second": 51.64,
+      "eval_steps_per_second": 12.91,
       "step": 1
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 1.0,
-      "eval_loss": 0.4876060485839844,
-      "eval_runtime": 0.0737,
-      "eval_samples_per_second": 54.286,
-      "eval_steps_per_second": 13.571,
+      "eval_accuracy": 0.5,
+      "eval_loss": 0.5957173705101013,
+      "eval_runtime": 0.0821,
+      "eval_samples_per_second": 48.732,
+      "eval_steps_per_second": 12.183,
       "step": 2
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 1.0,
-      "eval_loss": 0.44556379318237305,
-      "eval_runtime": 0.0672,
-      "eval_samples_per_second": 59.503,
-      "eval_steps_per_second": 14.876,
+      "eval_accuracy": 0.5,
+      "eval_loss": 0.6553595662117004,
+      "eval_runtime": 0.0814,
+      "eval_samples_per_second": 49.141,
+      "eval_steps_per_second": 12.285,
       "step": 3
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 1.0,
-      "eval_loss": 0.41716501116752625,
-      "eval_runtime": 0.0654,
-      "eval_samples_per_second": 61.169,
-      "eval_steps_per_second": 15.292,
+      "eval_accuracy": 0.25,
+      "eval_loss": 0.7486120462417603,
+      "eval_runtime": 0.092,
+      "eval_samples_per_second": 43.462,
+      "eval_steps_per_second": 10.866,
       "step": 4
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 1.0,
-      "eval_loss": 0.3770451843738556,
-      "eval_runtime": 0.0686,
-      "eval_samples_per_second": 58.32,
-      "eval_steps_per_second": 14.58,
+      "eval_accuracy": 0.25,
+      "eval_loss": 0.8207159042358398,
+      "eval_runtime": 0.0849,
+      "eval_samples_per_second": 47.103,
+      "eval_steps_per_second": 11.776,
       "step": 5
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 1.0,
-      "eval_loss": 0.3442598283290863,
-      "eval_runtime": 0.0676,
-      "eval_samples_per_second": 59.13,
-      "eval_steps_per_second": 14.783,
+      "eval_accuracy": 0.25,
+      "eval_loss": 0.8213469386100769,
+      "eval_runtime": 0.0786,
+      "eval_samples_per_second": 50.921,
+      "eval_steps_per_second": 12.73,
       "step": 6
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 1.0,
-      "eval_loss": 0.32264935970306396,
-      "eval_runtime": 0.0634,
-      "eval_samples_per_second": 63.066,
-      "eval_steps_per_second": 15.767,
+      "eval_accuracy": 0.5,
+      "eval_loss": 0.7957496643066406,
+      "eval_runtime": 0.1037,
+      "eval_samples_per_second": 38.557,
+      "eval_steps_per_second": 9.639,
       "step": 7
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 1.0,
-      "eval_loss": 0.3132918179035187,
-      "eval_runtime": 0.0661,
-      "eval_samples_per_second": 60.478,
-      "eval_steps_per_second": 15.12,
+      "eval_accuracy": 0.5,
+      "eval_loss": 0.7098022699356079,
+      "eval_runtime": 0.0873,
+      "eval_samples_per_second": 45.794,
+      "eval_steps_per_second": 11.449,
       "step": 8
     },
     {
       "epoch": 9.0,
-      "eval_accuracy": 1.0,
-      "eval_loss": 0.30815836787223816,
-      "eval_runtime": 0.0661,
-      "eval_samples_per_second": 60.509,
-      "eval_steps_per_second": 15.127,
+      "eval_accuracy": 0.5,
+      "eval_loss": 0.6372093558311462,
+      "eval_runtime": 0.0953,
+      "eval_samples_per_second": 41.99,
+      "eval_steps_per_second": 10.497,
       "step": 9
     },
     {
       "epoch": 10.0,
-      "learning_rate": 0.0,
-      "loss": 0.2039,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 0.2113,
       "step": 10
     },
     {
       "epoch": 10.0,
-      "eval_accuracy": 1.0,
-      "eval_loss": 0.30541735887527466,
-      "eval_runtime": 0.0689,
-      "eval_samples_per_second": 58.029,
-      "eval_steps_per_second": 14.507,
+      "eval_accuracy": 0.5,
+      "eval_loss": 0.5358340740203857,
+      "eval_runtime": 0.085,
+      "eval_samples_per_second": 47.079,
+      "eval_steps_per_second": 11.77,
       "step": 10
     },
     {
-      "epoch": 10.0,
-      "step": 10,
-      "total_flos": 8699596145049600.0,
-      "train_loss": 0.20386319160461425,
-      "train_runtime": 41.2868,
-      "train_samples_per_second": 8.477,
-      "train_steps_per_second": 0.242
+      "epoch": 11.0,
+      "eval_accuracy": 0.75,
+      "eval_loss": 0.48944157361984253,
+      "eval_runtime": 0.0964,
+      "eval_samples_per_second": 41.48,
+      "eval_steps_per_second": 10.37,
+      "step": 11
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.75,
+      "eval_loss": 0.4506962299346924,
+      "eval_runtime": 0.111,
+      "eval_samples_per_second": 36.02,
+      "eval_steps_per_second": 9.005,
+      "step": 12
+    },
+    {
+      "epoch": 13.0,
+      "eval_accuracy": 0.75,
+      "eval_loss": 0.43113046884536743,
+      "eval_runtime": 0.0817,
+      "eval_samples_per_second": 48.933,
+      "eval_steps_per_second": 12.233,
+      "step": 13
+    },
+    {
+      "epoch": 14.0,
+      "eval_accuracy": 0.75,
+      "eval_loss": 0.4339416027069092,
+      "eval_runtime": 0.1033,
+      "eval_samples_per_second": 38.72,
+      "eval_steps_per_second": 9.68,
+      "step": 14
+    },
+    {
+      "epoch": 15.0,
+      "eval_accuracy": 0.75,
+      "eval_loss": 0.46003320813179016,
+      "eval_runtime": 0.0837,
+      "eval_samples_per_second": 47.81,
+      "eval_steps_per_second": 11.952,
+      "step": 15
+    },
+    {
+      "epoch": 16.0,
+      "eval_accuracy": 0.5,
+      "eval_loss": 0.49817201495170593,
+      "eval_runtime": 0.1026,
+      "eval_samples_per_second": 38.983,
+      "eval_steps_per_second": 9.746,
+      "step": 16
+    },
+    {
+      "epoch": 17.0,
+      "eval_accuracy": 0.5,
+      "eval_loss": 0.5298565626144409,
+      "eval_runtime": 0.0879,
+      "eval_samples_per_second": 45.53,
+      "eval_steps_per_second": 11.383,
+      "step": 17
+    },
+    {
+      "epoch": 18.0,
+      "eval_accuracy": 0.5,
+      "eval_loss": 0.5602237582206726,
+      "eval_runtime": 0.0988,
+      "eval_samples_per_second": 40.497,
+      "eval_steps_per_second": 10.124,
+      "step": 18
+    },
+    {
+      "epoch": 19.0,
+      "eval_accuracy": 0.5,
+      "eval_loss": 0.5776747465133667,
+      "eval_runtime": 0.0845,
+      "eval_samples_per_second": 47.319,
+      "eval_steps_per_second": 11.83,
+      "step": 19
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 0.0,
+      "loss": 0.0955,
+      "step": 20
+    },
+    {
+      "epoch": 20.0,
+      "eval_accuracy": 0.5,
+      "eval_loss": 0.5813302993774414,
+      "eval_runtime": 0.101,
+      "eval_samples_per_second": 39.589,
+      "eval_steps_per_second": 9.897,
+      "step": 20
+    },
+    {
+      "epoch": 20.0,
+      "step": 20,
+      "total_flos": 1.73991922900992e+16,
+      "train_loss": 0.15340265035629272,
+      "train_runtime": 48.7906,
+      "train_samples_per_second": 14.347,
+      "train_steps_per_second": 0.41
     }
   ],
-  "max_steps": 10,
-  "num_train_epochs": 10,
-  "total_flos": 8699596145049600.0,
+  "max_steps": 20,
+  "num_train_epochs": 20,
+  "total_flos": 1.73991922900992e+16,
   "trial_name": null,
   "trial_params": null
 }