Training in progress, epoch 0

all_results.json

@@ -1,13 +1,13 @@
 {
-    "epoch": 9.73,
-    "eval_accuracy": 0.7272727272727273,
-    "eval_loss": 0.6321931481361389,
-    "eval_runtime": 5.5693,
-    "eval_samples_per_second": 23.702,
-    "eval_steps_per_second": 0.898,
-    "total_flos": 2.8567786371889766e+17,
-    "train_loss": 0.6456676854027642,
-    "train_runtime": 1051.9243,
-    "train_samples_per_second": 11.227,
-    "train_steps_per_second": 0.086
+    "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
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 9.73,
-    "eval_accuracy": 0.7272727272727273,
-    "eval_loss": 0.6321931481361389,
-    "eval_runtime": 5.5693,
-    "eval_samples_per_second": 23.702,
-    "eval_steps_per_second": 0.898
+    "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
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4f652eb7f5dba7f7403ed4940f204e2303af8a85925a7596a21f7b9665e6124
+oid sha256:a9ac478b76ae08c58cccf61527ab27ba693406c4feb993e3f897009f4c94e951
 size 110345908

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eaff7ef959a5de0ccb92404811b6aae31227f644993a4a312bab77b62554c238
+oid sha256:551d1bdb0e9ea1e87e437ec74e9b435f70538f93be8bb4ca1e628486fe3d85a1
 size 110397937

runs/Nov30_02-36-21_5327fa17b653/events.out.tfevents.1701313909.5327fa17b653.294.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72551607429dd262fdffc024289acb359e31578c1960c0fc42477df2ff7964b1
+size 411

runs/Nov30_05-39-29_26aa82926d21/events.out.tfevents.1701322776.26aa82926d21.160.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0193d3cb9bc11e9ec47fb4489babe0d9c271ff503e3525fe774fbb3750bdda2
+size 4869

runs/Nov30_19-21-04_9d5d42108d17/events.out.tfevents.1701372159.9d5d42108d17.324.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ace2fd88b704b315c767e7399a598c65beadb6ca57962d425f81d06646f66152
+size 5186

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 9.73,
-    "total_flos": 2.8567786371889766e+17,
-    "train_loss": 0.6456676854027642,
-    "train_runtime": 1051.9243,
-    "train_samples_per_second": 11.227,
-    "train_steps_per_second": 0.086
+    "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
 }

trainer_state.json

@@ -1,172 +1,208 @@
 {
-  "best_metric": 0.7272727272727273,
-  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-83",
-  "epoch": 9.72972972972973,
+  "best_metric": 0.7429906542056075,
+  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-120",
+  "epoch": 10.0,
   "eval_steps": 500,
-  "global_step": 90,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.97,
-      "eval_accuracy": 0.4621212121212121,
-      "eval_loss": 1.0291072130203247,
-      "eval_runtime": 38.7664,
-      "eval_samples_per_second": 3.405,
-      "eval_steps_per_second": 0.129,
-      "step": 9
-    },
-    {
-      "epoch": 1.08,
-      "learning_rate": 4.938271604938271e-05,
-      "loss": 1.0954,
+      "epoch": 0.67,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 1.0627,
       "step": 10
     },
     {
-      "epoch": 1.95,
-      "eval_accuracy": 0.6136363636363636,
-      "eval_loss": 0.8322019577026367,
-      "eval_runtime": 6.218,
-      "eval_samples_per_second": 21.229,
-      "eval_steps_per_second": 0.804,
-      "step": 18
+      "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,
+      "step": 15
     },
     {
-      "epoch": 2.16,
-      "learning_rate": 4.3209876543209875e-05,
-      "loss": 0.8859,
+      "epoch": 1.33,
+      "learning_rate": 4.814814814814815e-05,
+      "loss": 0.9337,
       "step": 20
     },
     {
-      "epoch": 2.92,
-      "eval_accuracy": 0.6363636363636364,
-      "eval_loss": 0.7933622598648071,
-      "eval_runtime": 5.5171,
-      "eval_samples_per_second": 23.926,
-      "eval_steps_per_second": 0.906,
-      "step": 27
+      "epoch": 2.0,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.8137,
+      "step": 30
     },
     {
-      "epoch": 3.24,
-      "learning_rate": 3.7037037037037037e-05,
-      "loss": 0.7328,
+      "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
     },
+    {
+      "epoch": 2.67,
+      "learning_rate": 4.074074074074074e-05,
+      "loss": 0.7516,
+      "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": 3.33,
+      "learning_rate": 3.7037037037037037e-05,
+      "loss": 0.7407,
+      "step": 50
+    },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.6742424242424242,
-      "eval_loss": 0.7151352763175964,
-      "eval_runtime": 6.9052,
-      "eval_samples_per_second": 19.116,
-      "eval_steps_per_second": 0.724,
-      "step": 37
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.6395,
+      "step": 60
     },
     {
-      "epoch": 4.32,
-      "learning_rate": 3.08641975308642e-05,
-      "loss": 0.6285,
-      "step": 40
+      "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
     },
     {
-      "epoch": 4.97,
-      "eval_accuracy": 0.6060606060606061,
-      "eval_loss": 0.7613763809204102,
-      "eval_runtime": 6.2935,
-      "eval_samples_per_second": 20.974,
-      "eval_steps_per_second": 0.794,
-      "step": 46
+      "epoch": 4.67,
+      "learning_rate": 2.962962962962963e-05,
+      "loss": 0.579,
+      "step": 70
     },
     {
-      "epoch": 5.41,
-      "learning_rate": 2.4691358024691357e-05,
-      "loss": 0.5817,
-      "step": 50
+      "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": 5.33,
+      "learning_rate": 2.5925925925925925e-05,
+      "loss": 0.5781,
+      "step": 80
     },
     {
-      "epoch": 5.95,
-      "eval_accuracy": 0.6439393939393939,
-      "eval_loss": 0.7581026554107666,
-      "eval_runtime": 5.3759,
-      "eval_samples_per_second": 24.554,
-      "eval_steps_per_second": 0.93,
-      "step": 55
+      "epoch": 6.0,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 0.5505,
+      "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
     },
     {
-      "epoch": 6.49,
+      "epoch": 6.67,
       "learning_rate": 1.8518518518518518e-05,
-      "loss": 0.5145,
-      "step": 60
+      "loss": 0.5312,
+      "step": 100
     },
     {
-      "epoch": 6.92,
-      "eval_accuracy": 0.7121212121212122,
-      "eval_loss": 0.6607750654220581,
-      "eval_runtime": 6.827,
-      "eval_samples_per_second": 19.335,
-      "eval_steps_per_second": 0.732,
-      "step": 64
+      "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": 7.57,
-      "learning_rate": 1.2345679012345678e-05,
-      "loss": 0.4899,
-      "step": 70
+      "epoch": 7.33,
+      "learning_rate": 1.4814814814814815e-05,
+      "loss": 0.4709,
+      "step": 110
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.6893939393939394,
-      "eval_loss": 0.6711231470108032,
-      "eval_runtime": 5.4387,
-      "eval_samples_per_second": 24.271,
-      "eval_steps_per_second": 0.919,
-      "step": 74
+      "learning_rate": 1.1111111111111112e-05,
+      "loss": 0.4793,
+      "step": 120
     },
     {
-      "epoch": 8.65,
-      "learning_rate": 6.172839506172839e-06,
-      "loss": 0.4372,
-      "step": 80
+      "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
     },
     {
-      "epoch": 8.97,
-      "eval_accuracy": 0.7272727272727273,
-      "eval_loss": 0.6321931481361389,
-      "eval_runtime": 6.1539,
-      "eval_samples_per_second": 21.45,
-      "eval_steps_per_second": 0.812,
-      "step": 83
+      "epoch": 8.67,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 0.4443,
+      "step": 130
     },
     {
-      "epoch": 9.73,
-      "learning_rate": 0.0,
-      "loss": 0.4452,
-      "step": 90
+      "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": 9.73,
-      "eval_accuracy": 0.7121212121212122,
-      "eval_loss": 0.6398604512214661,
-      "eval_runtime": 6.4193,
-      "eval_samples_per_second": 20.563,
-      "eval_steps_per_second": 0.779,
-      "step": 90
+      "epoch": 9.33,
+      "learning_rate": 3.7037037037037037e-06,
+      "loss": 0.4335,
+      "step": 140
     },
     {
-      "epoch": 9.73,
-      "step": 90,
-      "total_flos": 2.8567786371889766e+17,
-      "train_loss": 0.6456676854027642,
-      "train_runtime": 1051.9243,
-      "train_samples_per_second": 11.227,
-      "train_steps_per_second": 0.086
+      "epoch": 10.0,
+      "learning_rate": 0.0,
+      "loss": 0.4685,
+      "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,
+      "step": 150
+    },
+    {
+      "epoch": 10.0,
+      "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
     }
   ],
   "logging_steps": 10,
-  "max_steps": 90,
+  "max_steps": 150,
   "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 2.8567786371889766e+17,
+  "total_flos": 4.772483236233216e+17,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d83f4ba9a02cd15381b3fc9b8e15a2e8e344ad4850ea94ae1368ab4386f16a6
+oid sha256:0a4f481a36c89204aeedde5377a22a9258ae5a4b142e7198e15e3fa361842a5b
 size 4664