Training in progress, epoch 1

all_results.json

@@ -5,9 +5,9 @@
     "eval_runtime": 7.2006,
     "eval_samples_per_second": 35.275,
     "eval_steps_per_second": 1.111,
-    "total_flos": 3.397316574586798e+17,
-    "train_loss": 0.4178706164713259,
-    "train_runtime": 1783.0458,
-    "train_samples_per_second": 7.666,
-    "train_steps_per_second": 0.061
+    "total_flos": 1.1070360374520545e+18,
+    "train_loss": 0.5791551381692119,
+    "train_runtime": 3074.7974,
+    "train_samples_per_second": 14.485,
+    "train_steps_per_second": 0.113
 }

runs/Oct12_18-42-49_5fea15d368fa/1665608374.0010908/events.out.tfevents.1665608374.5fea15d368fa.94.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1771a9e6d9ca8aed1af4f7d606e5dc42889bc0e7c48ba99f29de8534e5fc0c5e
+size 5553

runs/Oct12_18-42-49_5fea15d368fa/events.out.tfevents.1665608373.5fea15d368fa.94.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:249affddb8e1e4f78183446c3f3c906e28c167751cf12a0caac1d0bb94fecfc8
+size 5133

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 6.0,
-    "total_flos": 3.397316574586798e+17,
-    "train_loss": 0.4178706164713259,
-    "train_runtime": 1783.0458,
-    "train_samples_per_second": 7.666,
-    "train_steps_per_second": 0.061
+    "total_flos": 1.1070360374520545e+18,
+    "train_loss": 0.5791551381692119,
+    "train_runtime": 3074.7974,
+    "train_samples_per_second": 14.485,
+    "train_steps_per_second": 0.113
 }

trainer_state.json

@@ -1,139 +1,283 @@
 {
-  "best_metric": 0.84251968503937,
-  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-woody/checkpoint-18",
+  "best_metric": 0.7321212121212122,
+  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-woody/checkpoint-174",
   "epoch": 6.0,
-  "global_step": 108,
+  "global_step": 348,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.56,
-      "learning_rate": 4.545454545454546e-05,
-      "loss": 0.6766,
+      "epoch": 0.17,
+      "learning_rate": 1.4285714285714285e-05,
+      "loss": 0.7055,
       "step": 10
     },
+    {
+      "epoch": 0.34,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 0.6683,
+      "step": 20
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 4.2857142857142856e-05,
+      "loss": 0.6516,
+      "step": 30
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.920127795527157e-05,
+      "loss": 0.6218,
+      "step": 40
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 4.76038338658147e-05,
+      "loss": 0.6197,
+      "step": 50
+    },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.84251968503937,
-      "eval_loss": 0.4541613459587097,
-      "eval_runtime": 127.7917,
-      "eval_samples_per_second": 1.988,
-      "eval_steps_per_second": 0.063,
-      "step": 18
+      "eval_accuracy": 0.6557575757575758,
+      "eval_loss": 0.6088702082633972,
+      "eval_runtime": 182.647,
+      "eval_samples_per_second": 4.517,
+      "eval_steps_per_second": 0.142,
+      "step": 58
     },
     {
-      "epoch": 1.11,
-      "learning_rate": 4.536082474226804e-05,
-      "loss": 0.4353,
-      "step": 20
+      "epoch": 1.03,
+      "learning_rate": 4.600638977635783e-05,
+      "loss": 0.6022,
+      "step": 60
     },
     {
-      "epoch": 1.67,
-      "learning_rate": 4.020618556701031e-05,
-      "loss": 0.4078,
-      "step": 30
+      "epoch": 1.21,
+      "learning_rate": 4.440894568690096e-05,
+      "loss": 0.6239,
+      "step": 70
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 4.2811501597444096e-05,
+      "loss": 0.6337,
+      "step": 80
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 4.1214057507987225e-05,
+      "loss": 0.6083,
+      "step": 90
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 3.9616613418530355e-05,
+      "loss": 0.6061,
+      "step": 100
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 3.8019169329073485e-05,
+      "loss": 0.5984,
+      "step": 110
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.84251968503937,
-      "eval_loss": 0.3917757272720337,
-      "eval_runtime": 8.3632,
-      "eval_samples_per_second": 30.371,
-      "eval_steps_per_second": 0.957,
-      "step": 36
+      "eval_accuracy": 0.7103030303030303,
+      "eval_loss": 0.5503384470939636,
+      "eval_runtime": 23.8635,
+      "eval_samples_per_second": 34.572,
+      "eval_steps_per_second": 1.09,
+      "step": 116
     },
     {
-      "epoch": 2.22,
-      "learning_rate": 3.5051546391752576e-05,
-      "loss": 0.4322,
-      "step": 40
+      "epoch": 2.07,
+      "learning_rate": 3.6421725239616614e-05,
+      "loss": 0.594,
+      "step": 120
     },
     {
-      "epoch": 2.78,
-      "learning_rate": 2.9896907216494846e-05,
-      "loss": 0.4251,
-      "step": 50
+      "epoch": 2.24,
+      "learning_rate": 3.482428115015975e-05,
+      "loss": 0.5911,
+      "step": 130
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 3.322683706070287e-05,
+      "loss": 0.5523,
+      "step": 140
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 3.162939297124601e-05,
+      "loss": 0.6095,
+      "step": 150
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 3.003194888178914e-05,
+      "loss": 0.5657,
+      "step": 160
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 2.843450479233227e-05,
+      "loss": 0.5664,
+      "step": 170
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.84251968503937,
-      "eval_loss": 0.3992865979671478,
-      "eval_runtime": 9.1867,
-      "eval_samples_per_second": 27.649,
-      "eval_steps_per_second": 0.871,
-      "step": 54
+      "eval_accuracy": 0.7321212121212122,
+      "eval_loss": 0.5392071008682251,
+      "eval_runtime": 23.9974,
+      "eval_samples_per_second": 34.379,
+      "eval_steps_per_second": 1.083,
+      "step": 174
     },
     {
-      "epoch": 3.33,
-      "learning_rate": 2.4742268041237116e-05,
-      "loss": 0.3791,
-      "step": 60
+      "epoch": 3.1,
+      "learning_rate": 2.68370607028754e-05,
+      "loss": 0.5752,
+      "step": 180
     },
     {
-      "epoch": 3.89,
-      "learning_rate": 1.9587628865979382e-05,
-      "loss": 0.3648,
-      "step": 70
+      "epoch": 3.28,
+      "learning_rate": 2.523961661341853e-05,
+      "loss": 0.5534,
+      "step": 190
+    },
+    {
+      "epoch": 3.45,
+      "learning_rate": 2.364217252396166e-05,
+      "loss": 0.5642,
+      "step": 200
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 2.2044728434504794e-05,
+      "loss": 0.5334,
+      "step": 210
+    },
+    {
+      "epoch": 3.79,
+      "learning_rate": 2.0447284345047924e-05,
+      "loss": 0.5655,
+      "step": 220
+    },
+    {
+      "epoch": 3.97,
+      "learning_rate": 1.8849840255591057e-05,
+      "loss": 0.5645,
+      "step": 230
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.8385826771653543,
-      "eval_loss": 0.37160149216651917,
-      "eval_runtime": 8.9616,
-      "eval_samples_per_second": 28.343,
-      "eval_steps_per_second": 0.893,
-      "step": 72
+      "eval_accuracy": 0.7260606060606061,
+      "eval_loss": 0.5387520790100098,
+      "eval_runtime": 23.7899,
+      "eval_samples_per_second": 34.679,
+      "eval_steps_per_second": 1.093,
+      "step": 232
     },
     {
-      "epoch": 4.44,
-      "learning_rate": 1.4432989690721649e-05,
-      "loss": 0.3798,
-      "step": 80
+      "epoch": 4.14,
+      "learning_rate": 1.7252396166134186e-05,
+      "loss": 0.5588,
+      "step": 240
+    },
+    {
+      "epoch": 4.31,
+      "learning_rate": 1.565495207667732e-05,
+      "loss": 0.5342,
+      "step": 250
+    },
+    {
+      "epoch": 4.48,
+      "learning_rate": 1.4057507987220447e-05,
+      "loss": 0.5535,
+      "step": 260
+    },
+    {
+      "epoch": 4.66,
+      "learning_rate": 1.2460063897763578e-05,
+      "loss": 0.5549,
+      "step": 270
+    },
+    {
+      "epoch": 4.83,
+      "learning_rate": 1.086261980830671e-05,
+      "loss": 0.5266,
+      "step": 280
     },
     {
       "epoch": 5.0,
-      "learning_rate": 9.278350515463918e-06,
-      "loss": 0.3474,
-      "step": 90
+      "learning_rate": 9.265175718849841e-06,
+      "loss": 0.5467,
+      "step": 290
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.8346456692913385,
-      "eval_loss": 0.38020509481430054,
-      "eval_runtime": 7.3986,
-      "eval_samples_per_second": 34.331,
-      "eval_steps_per_second": 1.081,
-      "step": 90
+      "eval_accuracy": 0.7321212121212122,
+      "eval_loss": 0.5143269300460815,
+      "eval_runtime": 23.8629,
+      "eval_samples_per_second": 34.573,
+      "eval_steps_per_second": 1.09,
+      "step": 290
     },
     {
-      "epoch": 5.56,
-      "learning_rate": 4.123711340206186e-06,
-      "loss": 0.367,
-      "step": 100
+      "epoch": 5.17,
+      "learning_rate": 7.66773162939297e-06,
+      "loss": 0.5335,
+      "step": 300
+    },
+    {
+      "epoch": 5.34,
+      "learning_rate": 6.070287539936103e-06,
+      "loss": 0.558,
+      "step": 310
+    },
+    {
+      "epoch": 5.52,
+      "learning_rate": 4.472843450479233e-06,
+      "loss": 0.5368,
+      "step": 320
+    },
+    {
+      "epoch": 5.69,
+      "learning_rate": 2.8753993610223644e-06,
+      "loss": 0.5366,
+      "step": 330
+    },
+    {
+      "epoch": 5.86,
+      "learning_rate": 1.2779552715654952e-06,
+      "loss": 0.5316,
+      "step": 340
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.8346456692913385,
-      "eval_loss": 0.3757024109363556,
-      "eval_runtime": 8.8054,
-      "eval_samples_per_second": 28.846,
-      "eval_steps_per_second": 0.909,
-      "step": 108
+      "eval_accuracy": 0.7296969696969697,
+      "eval_loss": 0.5135210156440735,
+      "eval_runtime": 23.6834,
+      "eval_samples_per_second": 34.834,
+      "eval_steps_per_second": 1.098,
+      "step": 348
     },
     {
       "epoch": 6.0,
-      "step": 108,
-      "total_flos": 3.397316574586798e+17,
-      "train_loss": 0.4178706164713259,
-      "train_runtime": 1783.0458,
-      "train_samples_per_second": 7.666,
-      "train_steps_per_second": 0.061
+      "step": 348,
+      "total_flos": 1.1070360374520545e+18,
+      "train_loss": 0.5791551381692119,
+      "train_runtime": 3074.7974,
+      "train_samples_per_second": 14.485,
+      "train_steps_per_second": 0.113
     }
   ],
-  "max_steps": 108,
+  "max_steps": 348,
   "num_train_epochs": 6,
-  "total_flos": 3.397316574586798e+17,
+  "total_flos": 1.1070360374520545e+18,
   "trial_name": null,
   "trial_params": null
 }