Training in progress, epoch 0

all_results.json

@@ -1,13 +1,13 @@
 {
-    "epoch": 10.0,
-    "eval_accuracy": 0.7429906542056075,
-    "eval_loss": 0.6470456719398499,
-    "eval_runtime": 11.8351,
-    "eval_samples_per_second": 18.082,
-    "eval_steps_per_second": 0.591,
-    "total_flos": 4.772483236233216e+17,
-    "train_loss": 0.631834732691447,
-    "train_runtime": 2090.315,
-    "train_samples_per_second": 9.185,
-    "train_steps_per_second": 0.072
+    "epoch": 9.68,
+    "eval_accuracy": 0.7272727272727273,
+    "eval_loss": 0.6827457547187805,
+    "eval_runtime": 17.8634,
+    "eval_samples_per_second": 12.316,
+    "eval_steps_per_second": 0.392,
+    "total_flos": 4.7612977286482944e+17,
+    "train_loss": 0.6240748373667399,
+    "train_runtime": 3165.909,
+    "train_samples_per_second": 6.251,
+    "train_steps_per_second": 0.047
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 10.0,
-    "eval_accuracy": 0.7429906542056075,
-    "eval_loss": 0.6470456719398499,
-    "eval_runtime": 11.8351,
-    "eval_samples_per_second": 18.082,
-    "eval_steps_per_second": 0.591
+    "epoch": 9.68,
+    "eval_accuracy": 0.7272727272727273,
+    "eval_loss": 0.6827457547187805,
+    "eval_runtime": 17.8634,
+    "eval_samples_per_second": 12.316,
+    "eval_steps_per_second": 0.392
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:795d7fdfbf2c2c13acbb1b6d47d3945160d4f54d6a9c36f12c3ac128ff178056
+oid sha256:4a7379e8a0b9024c03ddc84ca54c44771da4b6b921aab03357917ea5a6217a00
 size 110345908

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eaff7ef959a5de0ccb92404811b6aae31227f644993a4a312bab77b62554c238
-size 110397937
+oid sha256:abe972a95fe34c7d0035a0ef86d6ef050cfad2ed110164fec7c8e5554c472707
+size 110398382

runs/Dec02_05-43-49_eaeadb71b15c/events.out.tfevents.1701495842.eaeadb71b15c.351.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebfba51551c3ccb150ef1d61b3dee189c502af122158771581288d112c3384bb
+size 5340

runs/Nov30_19-21-04_9d5d42108d17/events.out.tfevents.1701375355.9d5d42108d17.324.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88aa5d85c6470066b496f5eb7711e0d3b7a9d323c392f1dffec897df3efe7d46
+size 734

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 10.0,
-    "total_flos": 4.772483236233216e+17,
-    "train_loss": 0.631834732691447,
-    "train_runtime": 2090.315,
-    "train_samples_per_second": 9.185,
-    "train_steps_per_second": 0.072
+    "epoch": 9.68,
+    "total_flos": 4.7612977286482944e+17,
+    "train_loss": 0.6240748373667399,
+    "train_runtime": 3165.909,
+    "train_samples_per_second": 6.251,
+    "train_steps_per_second": 0.047
 }

trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.7429906542056075,
-  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-120",
-  "epoch": 10.0,
+  "best_metric": 0.7272727272727273,
+  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-93",
+  "epoch": 9.67741935483871,
   "eval_steps": 500,
   "global_step": 150,
   "is_hyper_param_search": false,
@@ -9,200 +9,200 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.67,
+      "epoch": 0.65,
       "learning_rate": 3.3333333333333335e-05,
-      "loss": 1.0627,
+      "loss": 1.1158,
       "step": 10
     },
     {
-      "epoch": 1.0,
-      "eval_accuracy": 0.5467289719626168,
-      "eval_loss": 0.9620130062103271,
-      "eval_runtime": 76.4881,
-      "eval_samples_per_second": 2.798,
-      "eval_steps_per_second": 0.092,
+      "epoch": 0.97,
+      "eval_accuracy": 0.5045454545454545,
+      "eval_loss": 0.9996662735939026,
+      "eval_runtime": 192.1374,
+      "eval_samples_per_second": 1.145,
+      "eval_steps_per_second": 0.036,
       "step": 15
     },
     {
-      "epoch": 1.33,
+      "epoch": 1.29,
       "learning_rate": 4.814814814814815e-05,
-      "loss": 0.9337,
+      "loss": 0.9619,
       "step": 20
     },
     {
-      "epoch": 2.0,
+      "epoch": 1.94,
       "learning_rate": 4.4444444444444447e-05,
-      "loss": 0.8137,
+      "loss": 0.8261,
       "step": 30
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.6588785046728972,
-      "eval_loss": 0.7779576778411865,
-      "eval_runtime": 11.4497,
-      "eval_samples_per_second": 18.691,
-      "eval_steps_per_second": 0.611,
-      "step": 30
+      "eval_accuracy": 0.5909090909090909,
+      "eval_loss": 0.9179713726043701,
+      "eval_runtime": 12.9002,
+      "eval_samples_per_second": 17.054,
+      "eval_steps_per_second": 0.543,
+      "step": 31
     },
     {
-      "epoch": 2.67,
+      "epoch": 2.58,
       "learning_rate": 4.074074074074074e-05,
-      "loss": 0.7516,
+      "loss": 0.7361,
       "step": 40
     },
     {
-      "epoch": 3.0,
-      "eval_accuracy": 0.6822429906542056,
-      "eval_loss": 0.7736912369728088,
-      "eval_runtime": 10.1149,
-      "eval_samples_per_second": 21.157,
-      "eval_steps_per_second": 0.692,
-      "step": 45
+      "epoch": 2.97,
+      "eval_accuracy": 0.65,
+      "eval_loss": 0.8046814203262329,
+      "eval_runtime": 12.6289,
+      "eval_samples_per_second": 17.42,
+      "eval_steps_per_second": 0.554,
+      "step": 46
     },
     {
-      "epoch": 3.33,
+      "epoch": 3.23,
       "learning_rate": 3.7037037037037037e-05,
-      "loss": 0.7407,
+      "loss": 0.695,
       "step": 50
     },
     {
-      "epoch": 4.0,
+      "epoch": 3.87,
       "learning_rate": 3.3333333333333335e-05,
-      "loss": 0.6395,
+      "loss": 0.6325,
       "step": 60
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.6869158878504673,
-      "eval_loss": 0.7195055484771729,
-      "eval_runtime": 11.3612,
-      "eval_samples_per_second": 18.836,
-      "eval_steps_per_second": 0.616,
-      "step": 60
+      "eval_accuracy": 0.6818181818181818,
+      "eval_loss": 0.7319933772087097,
+      "eval_runtime": 11.9267,
+      "eval_samples_per_second": 18.446,
+      "eval_steps_per_second": 0.587,
+      "step": 62
     },
     {
-      "epoch": 4.67,
+      "epoch": 4.52,
       "learning_rate": 2.962962962962963e-05,
-      "loss": 0.579,
+      "loss": 0.5946,
       "step": 70
     },
     {
-      "epoch": 5.0,
-      "eval_accuracy": 0.7149532710280374,
-      "eval_loss": 0.674180269241333,
-      "eval_runtime": 10.9381,
-      "eval_samples_per_second": 19.565,
-      "eval_steps_per_second": 0.64,
-      "step": 75
+      "epoch": 4.97,
+      "eval_accuracy": 0.6772727272727272,
+      "eval_loss": 0.7196129560470581,
+      "eval_runtime": 12.5354,
+      "eval_samples_per_second": 17.55,
+      "eval_steps_per_second": 0.558,
+      "step": 77
     },
     {
-      "epoch": 5.33,
+      "epoch": 5.16,
       "learning_rate": 2.5925925925925925e-05,
-      "loss": 0.5781,
+      "loss": 0.5746,
       "step": 80
     },
     {
-      "epoch": 6.0,
+      "epoch": 5.81,
       "learning_rate": 2.2222222222222223e-05,
-      "loss": 0.5505,
+      "loss": 0.5149,
       "step": 90
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.7242990654205608,
-      "eval_loss": 0.6525578498840332,
-      "eval_runtime": 10.1857,
-      "eval_samples_per_second": 21.01,
-      "eval_steps_per_second": 0.687,
-      "step": 90
+      "eval_accuracy": 0.7272727272727273,
+      "eval_loss": 0.6827457547187805,
+      "eval_runtime": 12.8605,
+      "eval_samples_per_second": 17.107,
+      "eval_steps_per_second": 0.544,
+      "step": 93
     },
     {
-      "epoch": 6.67,
+      "epoch": 6.45,
       "learning_rate": 1.8518518518518518e-05,
-      "loss": 0.5312,
+      "loss": 0.5083,
       "step": 100
     },
     {
-      "epoch": 7.0,
-      "eval_accuracy": 0.7289719626168224,
-      "eval_loss": 0.6616000533103943,
-      "eval_runtime": 11.5076,
-      "eval_samples_per_second": 18.596,
-      "eval_steps_per_second": 0.608,
-      "step": 105
+      "epoch": 6.97,
+      "eval_accuracy": 0.6954545454545454,
+      "eval_loss": 0.6906238198280334,
+      "eval_runtime": 12.5065,
+      "eval_samples_per_second": 17.591,
+      "eval_steps_per_second": 0.56,
+      "step": 108
     },
     {
-      "epoch": 7.33,
+      "epoch": 7.1,
       "learning_rate": 1.4814814814814815e-05,
-      "loss": 0.4709,
+      "loss": 0.4835,
       "step": 110
     },
     {
-      "epoch": 8.0,
+      "epoch": 7.74,
       "learning_rate": 1.1111111111111112e-05,
-      "loss": 0.4793,
+      "loss": 0.4316,
       "step": 120
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.7429906542056075,
-      "eval_loss": 0.6470456719398499,
-      "eval_runtime": 10.8132,
-      "eval_samples_per_second": 19.791,
-      "eval_steps_per_second": 0.647,
-      "step": 120
+      "eval_accuracy": 0.7090909090909091,
+      "eval_loss": 0.6681076288223267,
+      "eval_runtime": 12.7742,
+      "eval_samples_per_second": 17.222,
+      "eval_steps_per_second": 0.548,
+      "step": 124
     },
     {
-      "epoch": 8.67,
+      "epoch": 8.39,
       "learning_rate": 7.4074074074074075e-06,
-      "loss": 0.4443,
+      "loss": 0.4214,
       "step": 130
     },
     {
-      "epoch": 9.0,
-      "eval_accuracy": 0.7383177570093458,
-      "eval_loss": 0.6374843716621399,
-      "eval_runtime": 11.7851,
-      "eval_samples_per_second": 18.158,
-      "eval_steps_per_second": 0.594,
-      "step": 135
+      "epoch": 8.97,
+      "eval_accuracy": 0.7090909090909091,
+      "eval_loss": 0.6699694395065308,
+      "eval_runtime": 12.8762,
+      "eval_samples_per_second": 17.086,
+      "eval_steps_per_second": 0.544,
+      "step": 139
     },
     {
-      "epoch": 9.33,
+      "epoch": 9.03,
       "learning_rate": 3.7037037037037037e-06,
-      "loss": 0.4335,
+      "loss": 0.4551,
       "step": 140
     },
     {
-      "epoch": 10.0,
+      "epoch": 9.68,
       "learning_rate": 0.0,
-      "loss": 0.4685,
+      "loss": 0.4096,
       "step": 150
     },
     {
-      "epoch": 10.0,
-      "eval_accuracy": 0.7289719626168224,
-      "eval_loss": 0.6419404745101929,
-      "eval_runtime": 11.0308,
-      "eval_samples_per_second": 19.4,
-      "eval_steps_per_second": 0.635,
+      "epoch": 9.68,
+      "eval_accuracy": 0.7090909090909091,
+      "eval_loss": 0.6670935153961182,
+      "eval_runtime": 12.1565,
+      "eval_samples_per_second": 18.097,
+      "eval_steps_per_second": 0.576,
       "step": 150
     },
     {
-      "epoch": 10.0,
+      "epoch": 9.68,
       "step": 150,
-      "total_flos": 4.772483236233216e+17,
-      "train_loss": 0.631834732691447,
-      "train_runtime": 2090.315,
-      "train_samples_per_second": 9.185,
-      "train_steps_per_second": 0.072
+      "total_flos": 4.7612977286482944e+17,
+      "train_loss": 0.6240748373667399,
+      "train_runtime": 3165.909,
+      "train_samples_per_second": 6.251,
+      "train_steps_per_second": 0.047
     }
   ],
   "logging_steps": 10,
   "max_steps": 150,
   "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 4.772483236233216e+17,
+  "total_flos": 4.7612977286482944e+17,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a4f481a36c89204aeedde5377a22a9258ae5a4b142e7198e15e3fa361842a5b
+oid sha256:1210178898209e43a21f0315525493ed9643984df32cad3c848f6cee94f214bb
 size 4664