Training in progress, epoch 1

all_results.json

@@ -1,13 +1,13 @@
 {
-    "epoch": 9.68,
+    "epoch": 9.86,
     "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
+    "total_flos": 5.6934233607250944e+17,
+    "train_loss": 0.5934536351097954,
+    "train_runtime": 3636.0539,
+    "train_samples_per_second": 6.383,
+    "train_steps_per_second": 0.05
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0577cf535e14b88023a09678bec663f802b5c1e351e31f6b885ec5eb232c2666
+oid sha256:b1b356d3ade5868426b9a47603b57228a41bbf23f4d14a0234c463ff8de58b0c
 size 110345908

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:897438d4b1654499fda5dea6bc338ce3be122cfea1c97e10bd33aa14890b068d
-size 110397937
+oid sha256:abe972a95fe34c7d0035a0ef86d6ef050cfad2ed110164fec7c8e5554c472707
+size 110398382

runs/Dec03_17-11-15_3d49df9d5602/events.out.tfevents.1701623552.3d49df9d5602.1983.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2bce387d7c3d5292fe6189bd31ecca1f143c5687c97dfc8473585f8202dd19d
+size 5811

train_results.json

@@ -1,8 +1,8 @@
 {
-    "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
+    "epoch": 9.86,
+    "total_flos": 5.6934233607250944e+17,
+    "train_loss": 0.5934536351097954,
+    "train_runtime": 3636.0539,
+    "train_samples_per_second": 6.383,
+    "train_steps_per_second": 0.05
 }

trainer_state.json

@@ -1,208 +1,226 @@
 {
-  "best_metric": 0.7272727272727273,
-  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-93",
-  "epoch": 9.67741935483871,
+  "best_metric": 0.7713178294573644,
+  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-109",
+  "epoch": 9.863013698630137,
   "eval_steps": 500,
-  "global_step": 150,
+  "global_step": 180,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.65,
-      "learning_rate": 3.3333333333333335e-05,
-      "loss": 1.1158,
+      "epoch": 0.55,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 1.047,
       "step": 10
     },
     {
-      "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": 0.99,
+      "eval_accuracy": 0.6666666666666666,
+      "eval_loss": 0.8237752318382263,
+      "eval_runtime": 230.1882,
+      "eval_samples_per_second": 1.121,
+      "eval_steps_per_second": 0.039,
+      "step": 18
     },
     {
-      "epoch": 1.29,
-      "learning_rate": 4.814814814814815e-05,
-      "loss": 0.9619,
+      "epoch": 1.1,
+      "learning_rate": 4.938271604938271e-05,
+      "loss": 0.9215,
       "step": 20
     },
     {
-      "epoch": 1.94,
-      "learning_rate": 4.4444444444444447e-05,
-      "loss": 0.8261,
+      "epoch": 1.64,
+      "learning_rate": 4.62962962962963e-05,
+      "loss": 0.7685,
       "step": 30
     },
     {
-      "epoch": 2.0,
-      "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": 1.97,
+      "eval_accuracy": 0.6705426356589147,
+      "eval_loss": 0.7295451760292053,
+      "eval_runtime": 13.1153,
+      "eval_samples_per_second": 19.672,
+      "eval_steps_per_second": 0.686,
+      "step": 36
     },
     {
-      "epoch": 2.58,
-      "learning_rate": 4.074074074074074e-05,
-      "loss": 0.7361,
+      "epoch": 2.19,
+      "learning_rate": 4.3209876543209875e-05,
+      "loss": 0.7415,
       "step": 40
     },
     {
-      "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": 3.23,
-      "learning_rate": 3.7037037037037037e-05,
-      "loss": 0.695,
+      "epoch": 2.74,
+      "learning_rate": 4.012345679012346e-05,
+      "loss": 0.7036,
       "step": 50
     },
     {
-      "epoch": 3.87,
-      "learning_rate": 3.3333333333333335e-05,
-      "loss": 0.6325,
-      "step": 60
+      "epoch": 2.96,
+      "eval_accuracy": 0.6976744186046512,
+      "eval_loss": 0.679406464099884,
+      "eval_runtime": 12.8867,
+      "eval_samples_per_second": 20.021,
+      "eval_steps_per_second": 0.698,
+      "step": 54
     },
     {
-      "epoch": 4.0,
-      "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": 3.29,
+      "learning_rate": 3.7037037037037037e-05,
+      "loss": 0.673,
+      "step": 60
     },
     {
-      "epoch": 4.52,
-      "learning_rate": 2.962962962962963e-05,
-      "loss": 0.5946,
+      "epoch": 3.84,
+      "learning_rate": 3.395061728395062e-05,
+      "loss": 0.6215,
       "step": 70
     },
     {
-      "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": 4.0,
+      "eval_accuracy": 0.7093023255813954,
+      "eval_loss": 0.6780354976654053,
+      "eval_runtime": 13.3784,
+      "eval_samples_per_second": 19.285,
+      "eval_steps_per_second": 0.673,
+      "step": 73
     },
     {
-      "epoch": 5.16,
-      "learning_rate": 2.5925925925925925e-05,
-      "loss": 0.5746,
+      "epoch": 4.38,
+      "learning_rate": 3.08641975308642e-05,
+      "loss": 0.5791,
       "step": 80
     },
     {
-      "epoch": 5.81,
-      "learning_rate": 2.2222222222222223e-05,
-      "loss": 0.5149,
+      "epoch": 4.93,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 0.5409,
       "step": 90
     },
     {
-      "epoch": 6.0,
-      "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": 4.99,
+      "eval_accuracy": 0.751937984496124,
+      "eval_loss": 0.5863576531410217,
+      "eval_runtime": 13.0111,
+      "eval_samples_per_second": 19.829,
+      "eval_steps_per_second": 0.692,
+      "step": 91
     },
     {
-      "epoch": 6.45,
-      "learning_rate": 1.8518518518518518e-05,
-      "loss": 0.5083,
+      "epoch": 5.48,
+      "learning_rate": 2.4691358024691357e-05,
+      "loss": 0.5165,
       "step": 100
     },
     {
-      "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": 5.97,
+      "eval_accuracy": 0.7713178294573644,
+      "eval_loss": 0.5343179702758789,
+      "eval_runtime": 13.0683,
+      "eval_samples_per_second": 19.742,
+      "eval_steps_per_second": 0.689,
+      "step": 109
     },
     {
-      "epoch": 7.1,
-      "learning_rate": 1.4814814814814815e-05,
-      "loss": 0.4835,
+      "epoch": 6.03,
+      "learning_rate": 2.1604938271604937e-05,
+      "loss": 0.5124,
       "step": 110
     },
     {
-      "epoch": 7.74,
-      "learning_rate": 1.1111111111111112e-05,
-      "loss": 0.4316,
+      "epoch": 6.58,
+      "learning_rate": 1.8518518518518518e-05,
+      "loss": 0.4803,
       "step": 120
     },
     {
-      "epoch": 8.0,
-      "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": 6.96,
+      "eval_accuracy": 0.7325581395348837,
+      "eval_loss": 0.6034355759620667,
+      "eval_runtime": 13.1989,
+      "eval_samples_per_second": 19.547,
+      "eval_steps_per_second": 0.682,
+      "step": 127
     },
     {
-      "epoch": 8.39,
-      "learning_rate": 7.4074074074074075e-06,
-      "loss": 0.4214,
+      "epoch": 7.12,
+      "learning_rate": 1.54320987654321e-05,
+      "loss": 0.4476,
       "step": 130
     },
     {
-      "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": 7.67,
+      "learning_rate": 1.2345679012345678e-05,
+      "loss": 0.4328,
+      "step": 140
     },
     {
-      "epoch": 9.03,
-      "learning_rate": 3.7037037037037037e-06,
-      "loss": 0.4551,
-      "step": 140
+      "epoch": 8.0,
+      "eval_accuracy": 0.7325581395348837,
+      "eval_loss": 0.6063434481620789,
+      "eval_runtime": 12.5526,
+      "eval_samples_per_second": 20.553,
+      "eval_steps_per_second": 0.717,
+      "step": 146
     },
     {
-      "epoch": 9.68,
-      "learning_rate": 0.0,
-      "loss": 0.4096,
+      "epoch": 8.22,
+      "learning_rate": 9.259259259259259e-06,
+      "loss": 0.4438,
       "step": 150
     },
     {
-      "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": 8.77,
+      "learning_rate": 6.172839506172839e-06,
+      "loss": 0.4125,
+      "step": 160
     },
     {
-      "epoch": 9.68,
-      "step": 150,
-      "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
+      "epoch": 8.99,
+      "eval_accuracy": 0.7558139534883721,
+      "eval_loss": 0.581466794013977,
+      "eval_runtime": 13.212,
+      "eval_samples_per_second": 19.528,
+      "eval_steps_per_second": 0.681,
+      "step": 164
+    },
+    {
+      "epoch": 9.32,
+      "learning_rate": 3.0864197530864196e-06,
+      "loss": 0.4161,
+      "step": 170
+    },
+    {
+      "epoch": 9.86,
+      "learning_rate": 0.0,
+      "loss": 0.4237,
+      "step": 180
+    },
+    {
+      "epoch": 9.86,
+      "eval_accuracy": 0.7713178294573644,
+      "eval_loss": 0.5587521195411682,
+      "eval_runtime": 12.6148,
+      "eval_samples_per_second": 20.452,
+      "eval_steps_per_second": 0.713,
+      "step": 180
+    },
+    {
+      "epoch": 9.86,
+      "step": 180,
+      "total_flos": 5.6934233607250944e+17,
+      "train_loss": 0.5934536351097954,
+      "train_runtime": 3636.0539,
+      "train_samples_per_second": 6.383,
+      "train_steps_per_second": 0.05
     }
   ],
   "logging_steps": 10,
-  "max_steps": 150,
+  "max_steps": 180,
   "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 4.7612977286482944e+17,
+  "total_flos": 5.6934233607250944e+17,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1210178898209e43a21f0315525493ed9643984df32cad3c848f6cee94f214bb
+oid sha256:c9f9571a673d92db3deb89cd1e7237a21c96d3d324567e1449792efa4e6eee62
 size 4664