Training in progress, epoch 0

all_results.json

@@ -6,8 +6,8 @@
     "eval_samples_per_second": 65.819,
     "eval_steps_per_second": 2.106,
     "total_flos": 1.0405550045270016e+18,
-    "train_loss": 2.9593473706926616,
-    "train_runtime": 590.8235,
-    "train_samples_per_second": 22.849,
-    "train_steps_per_second": 0.178
+    "train_loss": 2.9546848569597515,
+    "train_runtime": 605.4022,
+    "train_samples_per_second": 22.299,
+    "train_steps_per_second": 0.173
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caff2b9d1d22df2a576c9a32e374a5232a73b2a2fd26808782f901b89550f230
+oid sha256:7c1289032da88897cd882d9c306444318a2ea5552252457e2d9780b389209ce9
 size 343573229

runs/Jul27_08-11-15_b65b7ae3d286/events.out.tfevents.1690445479.b65b7ae3d286.307.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da480688e790eeb797bd8d93d5e291cf8b94406cdcb8a25f30837a98beefe3fc
+size 9760

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.98,
     "total_flos": 1.0405550045270016e+18,
-    "train_loss": 2.9593473706926616,
-    "train_runtime": 590.8235,
-    "train_samples_per_second": 22.849,
-    "train_steps_per_second": 0.178
+    "train_loss": 2.9546848569597515,
+    "train_runtime": 605.4022,
+    "train_samples_per_second": 22.299,
+    "train_steps_per_second": 0.173
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.85,
+  "best_metric": 0.86,
   "best_model_checkpoint": "vit-base-patch16-224-in21k-finetuned-eurosat/checkpoint-105",
   "epoch": 2.978723404255319,
   "global_step": 105,
@@ -10,98 +10,98 @@
     {
       "epoch": 0.28,
       "learning_rate": 4.545454545454546e-05,
-      "loss": 4.5706,
+      "loss": 4.5362,
       "step": 10
     },
     {
       "epoch": 0.57,
       "learning_rate": 4.5212765957446815e-05,
-      "loss": 4.0661,
+      "loss": 4.0222,
       "step": 20
     },
     {
       "epoch": 0.85,
       "learning_rate": 3.9893617021276594e-05,
-      "loss": 3.5038,
+      "loss": 3.4758,
       "step": 30
     },
     {
       "epoch": 0.99,
-      "eval_accuracy": 0.776,
-      "eval_loss": 3.120776891708374,
-      "eval_runtime": 8.0104,
-      "eval_samples_per_second": 62.419,
-      "eval_steps_per_second": 1.997,
+      "eval_accuracy": 0.82,
+      "eval_loss": 3.1076748371124268,
+      "eval_runtime": 7.2667,
+      "eval_samples_per_second": 68.807,
+      "eval_steps_per_second": 2.202,
       "step": 35
     },
     {
       "epoch": 1.13,
       "learning_rate": 3.4574468085106386e-05,
-      "loss": 3.1206,
+      "loss": 3.1322,
       "step": 40
     },
     {
       "epoch": 1.42,
       "learning_rate": 2.925531914893617e-05,
-      "loss": 2.8404,
+      "loss": 2.8806,
       "step": 50
     },
     {
       "epoch": 1.7,
       "learning_rate": 2.393617021276596e-05,
-      "loss": 2.6347,
+      "loss": 2.63,
       "step": 60
     },
     {
       "epoch": 1.99,
       "learning_rate": 1.8617021276595745e-05,
-      "loss": 2.4515,
+      "loss": 2.4504,
       "step": 70
     },
     {
       "epoch": 1.99,
-      "eval_accuracy": 0.842,
-      "eval_loss": 2.3798251152038574,
-      "eval_runtime": 7.4885,
-      "eval_samples_per_second": 66.769,
-      "eval_steps_per_second": 2.137,
+      "eval_accuracy": 0.852,
+      "eval_loss": 2.367713451385498,
+      "eval_runtime": 7.8654,
+      "eval_samples_per_second": 63.57,
+      "eval_steps_per_second": 2.034,
       "step": 70
     },
     {
       "epoch": 2.27,
       "learning_rate": 1.3297872340425532e-05,
-      "loss": 2.3263,
+      "loss": 2.3387,
       "step": 80
     },
     {
       "epoch": 2.55,
       "learning_rate": 7.97872340425532e-06,
-      "loss": 2.2567,
+      "loss": 2.2457,
       "step": 90
     },
     {
       "epoch": 2.84,
       "learning_rate": 2.6595744680851065e-06,
-      "loss": 2.1903,
+      "loss": 2.212,
       "step": 100
     },
     {
       "epoch": 2.98,
-      "eval_accuracy": 0.85,
-      "eval_loss": 2.189312219619751,
-      "eval_runtime": 7.6989,
-      "eval_samples_per_second": 64.945,
-      "eval_steps_per_second": 2.078,
+      "eval_accuracy": 0.86,
+      "eval_loss": 2.1622867584228516,
+      "eval_runtime": 7.7962,
+      "eval_samples_per_second": 64.134,
+      "eval_steps_per_second": 2.052,
       "step": 105
     },
     {
       "epoch": 2.98,
       "step": 105,
       "total_flos": 1.0405550045270016e+18,
-      "train_loss": 2.9593473706926616,
-      "train_runtime": 590.8235,
-      "train_samples_per_second": 22.849,
-      "train_steps_per_second": 0.178
+      "train_loss": 2.9546848569597515,
+      "train_runtime": 605.4022,
+      "train_samples_per_second": 22.299,
+      "train_steps_per_second": 0.173
     }
   ],
   "max_steps": 105,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f82fd429502b1180a668c87ad054492abeff1fdba9c1d77672c1b9046dd773d
-size 4027
+oid sha256:4dbf2beb5284ac3169f4fd86adc63bfc3aebf33d3c4a3a1d1de4fa9a9ca32fd1
+size 4155