End of training

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 4.701754385964913,
+    "eval_accuracy": 0.975,
+    "eval_loss": 0.0948040708899498,
+    "eval_runtime": 12.9458,
+    "eval_samples_per_second": 15.449,
+    "eval_steps_per_second": 0.541,
+    "total_flos": 2.107905659338752e+17,
+    "train_loss": 2.1127685138157437,
+    "train_runtime": 1664.7726,
+    "train_samples_per_second": 5.406,
+    "train_steps_per_second": 0.042
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.701754385964913,
+    "eval_accuracy": 0.975,
+    "eval_loss": 0.0948040708899498,
+    "eval_runtime": 12.9458,
+    "eval_samples_per_second": 15.449,
+    "eval_steps_per_second": 0.541
+}

runs/Jan05_15-09-25_593e2597c9a8/events.out.tfevents.1736091461.593e2597c9a8.912.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8dc42b7208b2b9b2075baba79033f4a621e7235d0708bf80b125ecf5710e3b7
+size 405

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.701754385964913,
+    "total_flos": 2.107905659338752e+17,
+    "train_loss": 2.1127685138157437,
+    "train_runtime": 1664.7726,
+    "train_samples_per_second": 5.406,
+    "train_steps_per_second": 0.042
+}

trainer_state.json

@@ -0,0 +1,136 @@
+{
+  "best_metric": 0.975,
+  "best_model_checkpoint": "Swin-Transformer-Pro-Passport-Orientation-Classifier/checkpoint-70",
+  "epoch": 4.701754385964913,
+  "eval_steps": 500,
+  "global_step": 70,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.7017543859649122,
+      "grad_norm": 18.05853843688965,
+      "learning_rate": 4.761904761904762e-05,
+      "loss": 5.0594,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.745,
+      "eval_loss": 0.6023613810539246,
+      "eval_runtime": 106.6771,
+      "eval_samples_per_second": 1.875,
+      "eval_steps_per_second": 0.066,
+      "step": 15
+    },
+    {
+      "epoch": 1.3508771929824561,
+      "grad_norm": 20.55156707763672,
+      "learning_rate": 3.968253968253968e-05,
+      "loss": 2.7384,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 13.169713973999023,
+      "learning_rate": 3.1746031746031745e-05,
+      "loss": 2.0855,
+      "step": 30
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.89,
+      "eval_loss": 0.3376832604408264,
+      "eval_runtime": 13.4877,
+      "eval_samples_per_second": 14.828,
+      "eval_steps_per_second": 0.519,
+      "step": 30
+    },
+    {
+      "epoch": 2.7017543859649122,
+      "grad_norm": 16.93358039855957,
+      "learning_rate": 2.380952380952381e-05,
+      "loss": 1.7551,
+      "step": 40
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.94,
+      "eval_loss": 0.17310231924057007,
+      "eval_runtime": 13.5804,
+      "eval_samples_per_second": 14.727,
+      "eval_steps_per_second": 0.515,
+      "step": 45
+    },
+    {
+      "epoch": 3.3508771929824563,
+      "grad_norm": 14.565256118774414,
+      "learning_rate": 1.5873015873015872e-05,
+      "loss": 1.1734,
+      "step": 50
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 23.54315185546875,
+      "learning_rate": 7.936507936507936e-06,
+      "loss": 1.0192,
+      "step": 60
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.97,
+      "eval_loss": 0.10304895043373108,
+      "eval_runtime": 13.5715,
+      "eval_samples_per_second": 14.737,
+      "eval_steps_per_second": 0.516,
+      "step": 60
+    },
+    {
+      "epoch": 4.701754385964913,
+      "grad_norm": 13.321975708007812,
+      "learning_rate": 0.0,
+      "loss": 0.9583,
+      "step": 70
+    },
+    {
+      "epoch": 4.701754385964913,
+      "eval_accuracy": 0.975,
+      "eval_loss": 0.0948040708899498,
+      "eval_runtime": 14.111,
+      "eval_samples_per_second": 14.173,
+      "eval_steps_per_second": 0.496,
+      "step": 70
+    },
+    {
+      "epoch": 4.701754385964913,
+      "step": 70,
+      "total_flos": 2.107905659338752e+17,
+      "train_loss": 2.1127685138157437,
+      "train_runtime": 1664.7726,
+      "train_samples_per_second": 5.406,
+      "train_steps_per_second": 0.042
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 70,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.107905659338752e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}