End of training

all_results.json

@@ -1,8 +1,13 @@
 {
-    "epoch": 3.0,
-    "total_flos": 8.611768290817843e+16,
-    "train_loss": 1.5117597579956055,
-    "train_runtime": 274.4095,
-    "train_samples_per_second": 4.056,
-    "train_steps_per_second": 0.033
+    "epoch": 20.0,
+    "eval_accuracy": 0.6666666666666666,
+    "eval_loss": 0.933845043182373,
+    "eval_runtime": 5.652,
+    "eval_samples_per_second": 7.431,
+    "eval_steps_per_second": 0.354,
+    "total_flos": 5.741178860545229e+17,
+    "train_loss": 0.9606220165888468,
+    "train_runtime": 2002.1855,
+    "train_samples_per_second": 3.706,
+    "train_steps_per_second": 0.03
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 20.0,
+    "eval_accuracy": 0.6666666666666666,
+    "eval_loss": 0.933845043182373,
+    "eval_runtime": 5.652,
+    "eval_samples_per_second": 7.431,
+    "eval_steps_per_second": 0.354
+}

runs/Apr01_10-58-45_b000f2de1a15/events.out.tfevents.1711971202.b000f2de1a15.5893.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:508839f3076b473057443fe59c934877e58892379bdb9f176b5e8cd99760ecc0
+size 405

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.0,
-    "total_flos": 8.611768290817843e+16,
-    "train_loss": 1.5117597579956055,
-    "train_runtime": 274.4095,
-    "train_samples_per_second": 4.056,
-    "train_steps_per_second": 0.033
+    "epoch": 20.0,
+    "total_flos": 5.741178860545229e+17,
+    "train_loss": 0.9606220165888468,
+    "train_runtime": 2002.1855,
+    "train_samples_per_second": 3.706,
+    "train_steps_per_second": 0.03
 }

trainer_state.json

@@ -1,52 +1,241 @@
 {
-  "best_metric": 0.40476190476190477,
-  "best_model_checkpoint": "beit-base-patch16-224-pt22k-finetuned-eurosat/checkpoint-9",
-  "epoch": 3.0,
-  "global_step": 9,
+  "best_metric": 0.6666666666666666,
+  "best_model_checkpoint": "beit-base-patch16-224-pt22k-finetuned-eurosat/checkpoint-24",
+  "epoch": 20.0,
+  "global_step": 60,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.2857142857142857,
-      "eval_loss": 1.473257303237915,
-      "eval_runtime": 5.627,
-      "eval_samples_per_second": 7.464,
-      "eval_steps_per_second": 0.355,
+      "eval_accuracy": 0.30952380952380953,
+      "eval_loss": 1.3656748533248901,
+      "eval_runtime": 4.7483,
+      "eval_samples_per_second": 8.845,
+      "eval_steps_per_second": 0.421,
       "step": 3
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.2857142857142857,
-      "eval_loss": 1.384506344795227,
-      "eval_runtime": 5.2378,
-      "eval_samples_per_second": 8.019,
-      "eval_steps_per_second": 0.382,
+      "eval_accuracy": 0.42857142857142855,
+      "eval_loss": 1.1965879201889038,
+      "eval_runtime": 5.7114,
+      "eval_samples_per_second": 7.354,
+      "eval_steps_per_second": 0.35,
       "step": 6
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.40476190476190477,
-      "eval_loss": 1.3418488502502441,
-      "eval_runtime": 5.4291,
-      "eval_samples_per_second": 7.736,
-      "eval_steps_per_second": 0.368,
+      "eval_accuracy": 0.4523809523809524,
+      "eval_loss": 1.107600212097168,
+      "eval_runtime": 4.8432,
+      "eval_samples_per_second": 8.672,
+      "eval_steps_per_second": 0.413,
       "step": 9
     },
     {
-      "epoch": 3.0,
-      "step": 9,
-      "total_flos": 8.611768290817843e+16,
-      "train_loss": 1.5117597579956055,
-      "train_runtime": 274.4095,
-      "train_samples_per_second": 4.056,
-      "train_steps_per_second": 0.033
+      "epoch": 3.33,
+      "learning_rate": 4.62962962962963e-05,
+      "loss": 1.2696,
+      "step": 10
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5714285714285714,
+      "eval_loss": 1.0716592073440552,
+      "eval_runtime": 5.6422,
+      "eval_samples_per_second": 7.444,
+      "eval_steps_per_second": 0.354,
+      "step": 12
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5238095238095238,
+      "eval_loss": 0.9948052763938904,
+      "eval_runtime": 5.0495,
+      "eval_samples_per_second": 8.318,
+      "eval_steps_per_second": 0.396,
+      "step": 15
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5,
+      "eval_loss": 1.0701154470443726,
+      "eval_runtime": 4.8895,
+      "eval_samples_per_second": 8.59,
+      "eval_steps_per_second": 0.409,
+      "step": 18
+    },
+    {
+      "epoch": 6.67,
+      "learning_rate": 3.7037037037037037e-05,
+      "loss": 1.0945,
+      "step": 20
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.5,
+      "eval_loss": 0.9919558763504028,
+      "eval_runtime": 4.8666,
+      "eval_samples_per_second": 8.63,
+      "eval_steps_per_second": 0.411,
+      "step": 21
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.6666666666666666,
+      "eval_loss": 0.933845043182373,
+      "eval_runtime": 4.7955,
+      "eval_samples_per_second": 8.758,
+      "eval_steps_per_second": 0.417,
+      "step": 24
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.5714285714285714,
+      "eval_loss": 0.9605352282524109,
+      "eval_runtime": 4.8458,
+      "eval_samples_per_second": 8.667,
+      "eval_steps_per_second": 0.413,
+      "step": 27
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 0.9538,
+      "step": 30
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.6190476190476191,
+      "eval_loss": 0.928451418876648,
+      "eval_runtime": 5.4278,
+      "eval_samples_per_second": 7.738,
+      "eval_steps_per_second": 0.368,
+      "step": 30
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.5714285714285714,
+      "eval_loss": 0.9112913012504578,
+      "eval_runtime": 4.9223,
+      "eval_samples_per_second": 8.533,
+      "eval_steps_per_second": 0.406,
+      "step": 33
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.6190476190476191,
+      "eval_loss": 0.8413514494895935,
+      "eval_runtime": 4.9452,
+      "eval_samples_per_second": 8.493,
+      "eval_steps_per_second": 0.404,
+      "step": 36
+    },
+    {
+      "epoch": 13.0,
+      "eval_accuracy": 0.5476190476190477,
+      "eval_loss": 0.9422200322151184,
+      "eval_runtime": 4.7763,
+      "eval_samples_per_second": 8.793,
+      "eval_steps_per_second": 0.419,
+      "step": 39
+    },
+    {
+      "epoch": 13.33,
+      "learning_rate": 1.8518518518518518e-05,
+      "loss": 0.8646,
+      "step": 40
+    },
+    {
+      "epoch": 14.0,
+      "eval_accuracy": 0.6428571428571429,
+      "eval_loss": 0.8164998292922974,
+      "eval_runtime": 4.7422,
+      "eval_samples_per_second": 8.857,
+      "eval_steps_per_second": 0.422,
+      "step": 42
+    },
+    {
+      "epoch": 15.0,
+      "eval_accuracy": 0.5238095238095238,
+      "eval_loss": 0.9582035541534424,
+      "eval_runtime": 5.1656,
+      "eval_samples_per_second": 8.131,
+      "eval_steps_per_second": 0.387,
+      "step": 45
+    },
+    {
+      "epoch": 16.0,
+      "eval_accuracy": 0.6190476190476191,
+      "eval_loss": 0.8548088073730469,
+      "eval_runtime": 4.9211,
+      "eval_samples_per_second": 8.535,
+      "eval_steps_per_second": 0.406,
+      "step": 48
+    },
+    {
+      "epoch": 16.67,
+      "learning_rate": 9.259259259259259e-06,
+      "loss": 0.8082,
+      "step": 50
+    },
+    {
+      "epoch": 17.0,
+      "eval_accuracy": 0.6190476190476191,
+      "eval_loss": 0.8567562103271484,
+      "eval_runtime": 4.8635,
+      "eval_samples_per_second": 8.636,
+      "eval_steps_per_second": 0.411,
+      "step": 51
+    },
+    {
+      "epoch": 18.0,
+      "eval_accuracy": 0.5476190476190477,
+      "eval_loss": 0.8791553974151611,
+      "eval_runtime": 5.6088,
+      "eval_samples_per_second": 7.488,
+      "eval_steps_per_second": 0.357,
+      "step": 54
+    },
+    {
+      "epoch": 19.0,
+      "eval_accuracy": 0.5476190476190477,
+      "eval_loss": 0.8818988800048828,
+      "eval_runtime": 5.6414,
+      "eval_samples_per_second": 7.445,
+      "eval_steps_per_second": 0.355,
+      "step": 57
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 0.0,
+      "loss": 0.7731,
+      "step": 60
+    },
+    {
+      "epoch": 20.0,
+      "eval_accuracy": 0.5714285714285714,
+      "eval_loss": 0.8454474210739136,
+      "eval_runtime": 8.0511,
+      "eval_samples_per_second": 5.217,
+      "eval_steps_per_second": 0.248,
+      "step": 60
+    },
+    {
+      "epoch": 20.0,
+      "step": 60,
+      "total_flos": 5.741178860545229e+17,
+      "train_loss": 0.9606220165888468,
+      "train_runtime": 2002.1855,
+      "train_samples_per_second": 3.706,
+      "train_steps_per_second": 0.03
     }
   ],
-  "max_steps": 9,
-  "num_train_epochs": 3,
-  "total_flos": 8.611768290817843e+16,
+  "max_steps": 60,
+  "num_train_epochs": 20,
+  "total_flos": 5.741178860545229e+17,
   "trial_name": null,
   "trial_params": null
 }