End of training

all_results.json

@@ -1,13 +1,13 @@
 {
-    "epoch": 3.0,
-    "eval_accuracy": 1.0,
-    "eval_loss": 0.541394829750061,
-    "eval_runtime": 0.2681,
-    "eval_samples_per_second": 18.649,
-    "eval_steps_per_second": 3.73,
-    "total_flos": 3206422579175424.0,
-    "train_loss": 0.2824457089106242,
-    "train_runtime": 11.3219,
-    "train_samples_per_second": 11.394,
-    "train_steps_per_second": 0.265
+    "epoch": 2.96,
+    "eval_accuracy": 0.8710801393728222,
+    "eval_loss": 0.3399865925312042,
+    "eval_runtime": 4.1257,
+    "eval_samples_per_second": 69.563,
+    "eval_steps_per_second": 2.181,
+    "total_flos": 1.9045723068223488e+17,
+    "train_loss": 0.657797618707021,
+    "train_runtime": 145.8955,
+    "train_samples_per_second": 53.113,
+    "train_steps_per_second": 0.411
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.0,
-    "eval_accuracy": 1.0,
-    "eval_loss": 0.541394829750061,
-    "eval_runtime": 0.2681,
-    "eval_samples_per_second": 18.649,
-    "eval_steps_per_second": 3.73
+    "epoch": 2.96,
+    "eval_accuracy": 0.8710801393728222,
+    "eval_loss": 0.3399865925312042,
+    "eval_runtime": 4.1257,
+    "eval_samples_per_second": 69.563,
+    "eval_steps_per_second": 2.181
 }

runs/Apr08_12-28-18_90600695b4f6/events.out.tfevents.1712579455.90600695b4f6.424.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cc40f8b4bca792e8fbced46149a3d458393cfd165500ade4d9c5441d0278c94
+size 405

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.0,
-    "total_flos": 3206422579175424.0,
-    "train_loss": 0.2824457089106242,
-    "train_runtime": 11.3219,
-    "train_samples_per_second": 11.394,
-    "train_steps_per_second": 0.265
+    "epoch": 2.96,
+    "total_flos": 1.9045723068223488e+17,
+    "train_loss": 0.657797618707021,
+    "train_runtime": 145.8955,
+    "train_samples_per_second": 53.113,
+    "train_steps_per_second": 0.411
 }

trainer_state.json

@@ -1,56 +1,98 @@
 {
-  "best_metric": 1.0,
-  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-2",
-  "epoch": 3.0,
+  "best_metric": 0.8710801393728222,
+  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-60",
+  "epoch": 2.962962962962963,
   "eval_steps": 500,
-  "global_step": 3,
+  "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": 0.2,
-      "eval_loss": 0.7171379923820496,
-      "eval_runtime": 0.288,
-      "eval_samples_per_second": 17.359,
-      "eval_steps_per_second": 3.472,
-      "step": 1
-    },
-    {
-      "epoch": 2.0,
-      "eval_accuracy": 1.0,
-      "eval_loss": 0.541394829750061,
-      "eval_runtime": 0.2716,
-      "eval_samples_per_second": 18.413,
-      "eval_steps_per_second": 3.683,
-      "step": 2
-    },
-    {
-      "epoch": 3.0,
-      "eval_accuracy": 1.0,
-      "eval_loss": 0.4680565893650055,
-      "eval_runtime": 0.3396,
-      "eval_samples_per_second": 14.723,
-      "eval_steps_per_second": 2.945,
-      "step": 3
-    },
-    {
-      "epoch": 3.0,
-      "step": 3,
-      "total_flos": 3206422579175424.0,
-      "train_loss": 0.2824457089106242,
-      "train_runtime": 11.3219,
-      "train_samples_per_second": 11.394,
-      "train_steps_per_second": 0.265
+      "epoch": 0.49,
+      "grad_norm": 9.358732223510742,
+      "learning_rate": 4.62962962962963e-05,
+      "loss": 1.259,
+      "step": 10
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 11.161949157714844,
+      "learning_rate": 3.7037037037037037e-05,
+      "loss": 0.8451,
+      "step": 20
+    },
+    {
+      "epoch": 0.99,
+      "eval_accuracy": 0.7874564459930313,
+      "eval_loss": 0.5740640163421631,
+      "eval_runtime": 4.4336,
+      "eval_samples_per_second": 64.733,
+      "eval_steps_per_second": 2.03,
+      "step": 20
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 13.122177124023438,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 0.581,
+      "step": 30
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 10.2821044921875,
+      "learning_rate": 1.8518518518518518e-05,
+      "loss": 0.4621,
+      "step": 40
+    },
+    {
+      "epoch": 1.98,
+      "eval_accuracy": 0.8048780487804879,
+      "eval_loss": 0.45788925886154175,
+      "eval_runtime": 4.1854,
+      "eval_samples_per_second": 68.572,
+      "eval_steps_per_second": 2.15,
+      "step": 40
+    },
+    {
+      "epoch": 2.47,
+      "grad_norm": 12.540511131286621,
+      "learning_rate": 9.259259259259259e-06,
+      "loss": 0.4259,
+      "step": 50
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 6.045067310333252,
+      "learning_rate": 0.0,
+      "loss": 0.3736,
+      "step": 60
+    },
+    {
+      "epoch": 2.96,
+      "eval_accuracy": 0.8710801393728222,
+      "eval_loss": 0.3399865925312042,
+      "eval_runtime": 4.397,
+      "eval_samples_per_second": 65.272,
+      "eval_steps_per_second": 2.047,
+      "step": 60
+    },
+    {
+      "epoch": 2.96,
+      "step": 60,
+      "total_flos": 1.9045723068223488e+17,
+      "train_loss": 0.657797618707021,
+      "train_runtime": 145.8955,
+      "train_samples_per_second": 53.113,
+      "train_steps_per_second": 0.411
     }
   ],
   "logging_steps": 10,
-  "max_steps": 3,
+  "max_steps": 60,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 3206422579175424.0,
+  "total_flos": 1.9045723068223488e+17,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null