End of training

all_results.json

@@ -1,13 +1,13 @@
 {
-    "epoch": 2.97,
-    "eval_accuracy": 0.6172839506172839,
-    "eval_loss": 1.799244999885559,
-    "eval_runtime": 0.6311,
-    "eval_samples_per_second": 128.35,
-    "eval_steps_per_second": 33.276,
-    "total_flos": 2.8249710873624576e+16,
-    "train_loss": 1.9398403582365618,
-    "train_runtime": 40.5476,
-    "train_samples_per_second": 27.967,
-    "train_steps_per_second": 1.702
+    "epoch": 9.97,
+    "eval_accuracy": 0.9506172839506173,
+    "eval_loss": 0.5076120495796204,
+    "eval_runtime": 0.658,
+    "eval_samples_per_second": 123.091,
+    "eval_steps_per_second": 31.913,
+    "total_flos": 9.475214412238848e+16,
+    "train_loss": 0.5672112387159597,
+    "train_runtime": 101.9242,
+    "train_samples_per_second": 37.086,
+    "train_steps_per_second": 2.257
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 2.97,
-    "eval_accuracy": 0.6172839506172839,
-    "eval_loss": 1.799244999885559,
-    "eval_runtime": 0.6311,
-    "eval_samples_per_second": 128.35,
-    "eval_steps_per_second": 33.276
+    "epoch": 9.97,
+    "eval_accuracy": 0.9506172839506173,
+    "eval_loss": 0.5076120495796204,
+    "eval_runtime": 0.658,
+    "eval_samples_per_second": 123.091,
+    "eval_steps_per_second": 31.913
 }

runs/Dec11_08-56-27_24d728a6ec27/events.out.tfevents.1670749247.24d728a6ec27.73.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1497ee6aebc3489fd5b3325f5c7c23003af1e716107041c432e35f1d1b9b4fd1
+size 363

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 2.97,
-    "total_flos": 2.8249710873624576e+16,
-    "train_loss": 1.9398403582365618,
-    "train_runtime": 40.5476,
-    "train_samples_per_second": 27.967,
-    "train_steps_per_second": 1.702
+    "epoch": 9.97,
+    "total_flos": 9.475214412238848e+16,
+    "train_loss": 0.5672112387159597,
+    "train_runtime": 101.9242,
+    "train_samples_per_second": 37.086,
+    "train_steps_per_second": 2.257
 }

trainer_state.json

@@ -1,70 +1,181 @@
 {
-  "best_metric": 0.6172839506172839,
-  "best_model_checkpoint": "convnext-tiny-224-finetuned-eurosat-att-auto/checkpoint-69",
-  "epoch": 2.968421052631579,
-  "global_step": 69,
+  "best_metric": 0.9506172839506173,
+  "best_model_checkpoint": "convnext-tiny-224-finetuned-eurosat-att-auto/checkpoint-184",
+  "epoch": 9.968421052631578,
+  "global_step": 230,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.84,
-      "learning_rate": 3.951612903225806e-05,
-      "loss": 2.2191,
+      "learning_rate": 4.347826086956522e-05,
+      "loss": 1.5583,
       "step": 20
     },
     {
       "epoch": 0.97,
-      "eval_accuracy": 0.41975308641975306,
-      "eval_loss": 2.0644607543945312,
-      "eval_runtime": 0.5365,
-      "eval_samples_per_second": 150.987,
-      "eval_steps_per_second": 39.145,
+      "eval_accuracy": 0.7160493827160493,
+      "eval_loss": 1.6008388996124268,
+      "eval_runtime": 0.5509,
+      "eval_samples_per_second": 147.042,
+      "eval_steps_per_second": 38.122,
       "step": 23
     },
     {
       "epoch": 1.72,
-      "learning_rate": 2.338709677419355e-05,
-      "loss": 1.9791,
+      "learning_rate": 4.589371980676328e-05,
+      "loss": 1.2953,
       "step": 40
     },
     {
       "epoch": 1.97,
-      "eval_accuracy": 0.5925925925925926,
-      "eval_loss": 1.8730874061584473,
-      "eval_runtime": 0.5882,
-      "eval_samples_per_second": 137.703,
-      "eval_steps_per_second": 35.701,
+      "eval_accuracy": 0.7530864197530864,
+      "eval_loss": 1.2957005500793457,
+      "eval_runtime": 0.5979,
+      "eval_samples_per_second": 135.485,
+      "eval_steps_per_second": 35.126,
       "step": 46
     },
     {
       "epoch": 2.59,
-      "learning_rate": 7.258064516129033e-06,
-      "loss": 1.7559,
+      "learning_rate": 4.106280193236715e-05,
+      "loss": 0.9488,
       "step": 60
     },
     {
       "epoch": 2.97,
-      "eval_accuracy": 0.6172839506172839,
-      "eval_loss": 1.799244999885559,
-      "eval_runtime": 0.5742,
-      "eval_samples_per_second": 141.066,
-      "eval_steps_per_second": 36.573,
+      "eval_accuracy": 0.8148148148148148,
+      "eval_loss": 1.072020411491394,
+      "eval_runtime": 0.594,
+      "eval_samples_per_second": 136.355,
+      "eval_steps_per_second": 35.351,
       "step": 69
     },
     {
-      "epoch": 2.97,
-      "step": 69,
-      "total_flos": 2.8249710873624576e+16,
-      "train_loss": 1.9398403582365618,
-      "train_runtime": 40.5476,
-      "train_samples_per_second": 27.967,
-      "train_steps_per_second": 1.702
+      "epoch": 3.46,
+      "learning_rate": 3.6231884057971014e-05,
+      "loss": 0.7036,
+      "step": 80
+    },
+    {
+      "epoch": 3.97,
+      "eval_accuracy": 0.8641975308641975,
+      "eval_loss": 0.8964575529098511,
+      "eval_runtime": 0.579,
+      "eval_samples_per_second": 139.885,
+      "eval_steps_per_second": 36.267,
+      "step": 92
+    },
+    {
+      "epoch": 4.34,
+      "learning_rate": 3.140096618357488e-05,
+      "loss": 0.5446,
+      "step": 100
+    },
+    {
+      "epoch": 4.97,
+      "eval_accuracy": 0.9382716049382716,
+      "eval_loss": 0.7573724985122681,
+      "eval_runtime": 0.5915,
+      "eval_samples_per_second": 136.936,
+      "eval_steps_per_second": 35.502,
+      "step": 115
+    },
+    {
+      "epoch": 5.21,
+      "learning_rate": 2.6570048309178748e-05,
+      "loss": 0.4113,
+      "step": 120
+    },
+    {
+      "epoch": 5.97,
+      "eval_accuracy": 0.9382716049382716,
+      "eval_loss": 0.6521688103675842,
+      "eval_runtime": 0.6064,
+      "eval_samples_per_second": 133.581,
+      "eval_steps_per_second": 34.632,
+      "step": 138
+    },
+    {
+      "epoch": 6.08,
+      "learning_rate": 2.173913043478261e-05,
+      "loss": 0.3143,
+      "step": 140
+    },
+    {
+      "epoch": 6.93,
+      "learning_rate": 1.6908212560386476e-05,
+      "loss": 0.2259,
+      "step": 160
+    },
+    {
+      "epoch": 6.97,
+      "eval_accuracy": 0.9382716049382716,
+      "eval_loss": 0.572002649307251,
+      "eval_runtime": 0.5945,
+      "eval_samples_per_second": 136.243,
+      "eval_steps_per_second": 35.322,
+      "step": 161
+    },
+    {
+      "epoch": 7.8,
+      "learning_rate": 1.2077294685990338e-05,
+      "loss": 0.1863,
+      "step": 180
+    },
+    {
+      "epoch": 7.97,
+      "eval_accuracy": 0.9506172839506173,
+      "eval_loss": 0.5076120495796204,
+      "eval_runtime": 0.6943,
+      "eval_samples_per_second": 116.67,
+      "eval_steps_per_second": 30.248,
+      "step": 184
+    },
+    {
+      "epoch": 8.67,
+      "learning_rate": 7.246376811594203e-06,
+      "loss": 0.1443,
+      "step": 200
+    },
+    {
+      "epoch": 8.97,
+      "eval_accuracy": 0.9382716049382716,
+      "eval_loss": 0.4794546961784363,
+      "eval_runtime": 0.5986,
+      "eval_samples_per_second": 135.327,
+      "eval_steps_per_second": 35.085,
+      "step": 207
+    },
+    {
+      "epoch": 9.55,
+      "learning_rate": 2.4154589371980677e-06,
+      "loss": 0.1289,
+      "step": 220
+    },
+    {
+      "epoch": 9.97,
+      "eval_accuracy": 0.9382716049382716,
+      "eval_loss": 0.4685024619102478,
+      "eval_runtime": 0.6007,
+      "eval_samples_per_second": 134.835,
+      "eval_steps_per_second": 34.957,
+      "step": 230
+    },
+    {
+      "epoch": 9.97,
+      "step": 230,
+      "total_flos": 9.475214412238848e+16,
+      "train_loss": 0.5672112387159597,
+      "train_runtime": 101.9242,
+      "train_samples_per_second": 37.086,
+      "train_steps_per_second": 2.257
     }
   ],
-  "max_steps": 69,
-  "num_train_epochs": 3,
-  "total_flos": 2.8249710873624576e+16,
+  "max_steps": 230,
+  "num_train_epochs": 10,
+  "total_flos": 9.475214412238848e+16,
   "trial_name": null,
   "trial_params": null
 }