End of training

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 6.885245901639344,
+    "eval_accuracy": 0.8804347826086957,
+    "eval_loss": 0.30945461988449097,
+    "eval_runtime": 205.9609,
+    "eval_samples_per_second": 9.38,
+    "eval_steps_per_second": 0.078,
+    "total_flos": 4.1785806114677883e+18,
+    "train_loss": 0.4162924766540527,
+    "train_runtime": 7056.8141,
+    "train_samples_per_second": 7.675,
+    "train_steps_per_second": 0.015
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.885245901639344,
+    "eval_accuracy": 0.8804347826086957,
+    "eval_loss": 0.30945461988449097,
+    "eval_runtime": 205.9609,
+    "eval_samples_per_second": 9.38,
+    "eval_steps_per_second": 0.078
+}

runs/Aug23_07-04-12_data-science-wbi/events.out.tfevents.1724403930.data-science-wbi

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3aa6156fa3fb9a6566c11729fcc8fecae596eda3b8ac5cf8e62fd4132b1bb50
+size 87

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.885245901639344,
+    "total_flos": 4.1785806114677883e+18,
+    "train_loss": 0.4162924766540527,
+    "train_runtime": 7056.8141,
+    "train_samples_per_second": 7.675,
+    "train_steps_per_second": 0.015
+}

trainer_state.json

@@ -0,0 +1,175 @@
+{
+  "best_metric": 0.8804347826086957,
+  "best_model_checkpoint": "swin-base-patch4-window7-224-in22k-construction_type/checkpoint-105",
+  "epoch": 6.885245901639344,
+  "eval_steps": 500,
+  "global_step": 105,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6557377049180327,
+      "grad_norm": 4.063533306121826,
+      "learning_rate": 4.545454545454546e-05,
+      "loss": 0.9839,
+      "step": 10
+    },
+    {
+      "epoch": 0.9836065573770492,
+      "eval_accuracy": 0.8183229813664596,
+      "eval_loss": 0.4599319398403168,
+      "eval_runtime": 281.6742,
+      "eval_samples_per_second": 6.859,
+      "eval_steps_per_second": 0.057,
+      "step": 15
+    },
+    {
+      "epoch": 1.3114754098360657,
+      "grad_norm": 2.286010265350342,
+      "learning_rate": 4.5212765957446815e-05,
+      "loss": 0.5207,
+      "step": 20
+    },
+    {
+      "epoch": 1.9672131147540983,
+      "grad_norm": 2.2137374877929688,
+      "learning_rate": 3.9893617021276594e-05,
+      "loss": 0.4167,
+      "step": 30
+    },
+    {
+      "epoch": 1.9672131147540983,
+      "eval_accuracy": 0.8628364389233955,
+      "eval_loss": 0.36054086685180664,
+      "eval_runtime": 204.4093,
+      "eval_samples_per_second": 9.452,
+      "eval_steps_per_second": 0.078,
+      "step": 30
+    },
+    {
+      "epoch": 2.6229508196721314,
+      "grad_norm": 2.0627264976501465,
+      "learning_rate": 3.4574468085106386e-05,
+      "loss": 0.3853,
+      "step": 40
+    },
+    {
+      "epoch": 2.9508196721311473,
+      "eval_accuracy": 0.8799171842650103,
+      "eval_loss": 0.32720068097114563,
+      "eval_runtime": 205.0098,
+      "eval_samples_per_second": 9.424,
+      "eval_steps_per_second": 0.078,
+      "step": 45
+    },
+    {
+      "epoch": 3.278688524590164,
+      "grad_norm": 1.9932682514190674,
+      "learning_rate": 2.925531914893617e-05,
+      "loss": 0.346,
+      "step": 50
+    },
+    {
+      "epoch": 3.9344262295081966,
+      "grad_norm": 2.1814448833465576,
+      "learning_rate": 2.393617021276596e-05,
+      "loss": 0.3302,
+      "step": 60
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8762939958592133,
+      "eval_loss": 0.32265299558639526,
+      "eval_runtime": 204.0571,
+      "eval_samples_per_second": 9.468,
+      "eval_steps_per_second": 0.078,
+      "step": 61
+    },
+    {
+      "epoch": 4.590163934426229,
+      "grad_norm": 2.4336397647857666,
+      "learning_rate": 1.8617021276595745e-05,
+      "loss": 0.3302,
+      "step": 70
+    },
+    {
+      "epoch": 4.983606557377049,
+      "eval_accuracy": 0.8752587991718427,
+      "eval_loss": 0.3269009292125702,
+      "eval_runtime": 204.1607,
+      "eval_samples_per_second": 9.463,
+      "eval_steps_per_second": 0.078,
+      "step": 76
+    },
+    {
+      "epoch": 5.245901639344262,
+      "grad_norm": 1.6803584098815918,
+      "learning_rate": 1.3297872340425532e-05,
+      "loss": 0.3058,
+      "step": 80
+    },
+    {
+      "epoch": 5.901639344262295,
+      "grad_norm": 2.46169376373291,
+      "learning_rate": 7.97872340425532e-06,
+      "loss": 0.3049,
+      "step": 90
+    },
+    {
+      "epoch": 5.967213114754099,
+      "eval_accuracy": 0.8799171842650103,
+      "eval_loss": 0.31380367279052734,
+      "eval_runtime": 204.6191,
+      "eval_samples_per_second": 9.442,
+      "eval_steps_per_second": 0.078,
+      "step": 91
+    },
+    {
+      "epoch": 6.557377049180328,
+      "grad_norm": 2.692831039428711,
+      "learning_rate": 2.6595744680851065e-06,
+      "loss": 0.2951,
+      "step": 100
+    },
+    {
+      "epoch": 6.885245901639344,
+      "eval_accuracy": 0.8804347826086957,
+      "eval_loss": 0.30945461988449097,
+      "eval_runtime": 204.9131,
+      "eval_samples_per_second": 9.428,
+      "eval_steps_per_second": 0.078,
+      "step": 105
+    },
+    {
+      "epoch": 6.885245901639344,
+      "step": 105,
+      "total_flos": 4.1785806114677883e+18,
+      "train_loss": 0.4162924766540527,
+      "train_runtime": 7056.8141,
+      "train_samples_per_second": 7.675,
+      "train_steps_per_second": 0.015
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 105,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "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": 4.1785806114677883e+18,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": null
+}