End of training

README.md

@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2863
+- Loss: 1.3549
 - Accuracy: 0.5
 
 ## Model description

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.5,
+    "eval_loss": 1.3549420833587646,
+    "eval_runtime": 2.557,
+    "eval_samples_per_second": 20.337,
+    "eval_steps_per_second": 0.782,
+    "total_flos": 7.743817889611776e+16,
+    "train_loss": 1.3487067699432373,
+    "train_runtime": 107.726,
+    "train_samples_per_second": 22.093,
+    "train_steps_per_second": 0.186
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.5,
+    "eval_loss": 1.3549420833587646,
+    "eval_runtime": 2.557,
+    "eval_samples_per_second": 20.337,
+    "eval_steps_per_second": 0.782
+}

runs/Jun16_19-27-05_3d474309800c/events.out.tfevents.1718566311.3d474309800c.4675.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96029cde1e5e60e94fd27de665461942b9eb599cc1808d0ae3098c129a8c9ffc
+size 405

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "total_flos": 7.743817889611776e+16,
+    "train_loss": 1.3487067699432373,
+    "train_runtime": 107.726,
+    "train_samples_per_second": 22.093,
+    "train_steps_per_second": 0.186
+}

trainer_state.json

@@ -0,0 +1,146 @@
+{
+  "best_metric": 0.5,
+  "best_model_checkpoint": "swinv2-tiny-patch4-window8-256-dmae-humeda-1/checkpoint-12",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 20,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.34615384615384615,
+      "eval_loss": 1.5475995540618896,
+      "eval_runtime": 0.9663,
+      "eval_samples_per_second": 53.813,
+      "eval_steps_per_second": 2.07,
+      "step": 2
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.46153846153846156,
+      "eval_loss": 1.4060213565826416,
+      "eval_runtime": 0.9187,
+      "eval_samples_per_second": 56.602,
+      "eval_steps_per_second": 2.177,
+      "step": 4
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.4423076923076923,
+      "eval_loss": 1.4221522808074951,
+      "eval_runtime": 0.9084,
+      "eval_samples_per_second": 57.241,
+      "eval_steps_per_second": 2.202,
+      "step": 6
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.4230769230769231,
+      "eval_loss": 1.4011189937591553,
+      "eval_runtime": 0.9197,
+      "eval_samples_per_second": 56.539,
+      "eval_steps_per_second": 2.175,
+      "step": 8
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 4.191273212432861,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 1.4158,
+      "step": 10
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.46153846153846156,
+      "eval_loss": 1.376419186592102,
+      "eval_runtime": 1.2608,
+      "eval_samples_per_second": 41.243,
+      "eval_steps_per_second": 1.586,
+      "step": 10
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5,
+      "eval_loss": 1.3549420833587646,
+      "eval_runtime": 0.9055,
+      "eval_samples_per_second": 57.426,
+      "eval_steps_per_second": 2.209,
+      "step": 12
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.5,
+      "eval_loss": 1.3301607370376587,
+      "eval_runtime": 0.9301,
+      "eval_samples_per_second": 55.911,
+      "eval_steps_per_second": 2.15,
+      "step": 14
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.5,
+      "eval_loss": 1.3073081970214844,
+      "eval_runtime": 0.957,
+      "eval_samples_per_second": 54.338,
+      "eval_steps_per_second": 2.09,
+      "step": 16
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.5,
+      "eval_loss": 1.2922947406768799,
+      "eval_runtime": 0.9636,
+      "eval_samples_per_second": 53.965,
+      "eval_steps_per_second": 2.076,
+      "step": 18
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 5.915622234344482,
+      "learning_rate": 0.0,
+      "loss": 1.2817,
+      "step": 20
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.5,
+      "eval_loss": 1.28629732131958,
+      "eval_runtime": 1.2408,
+      "eval_samples_per_second": 41.91,
+      "eval_steps_per_second": 1.612,
+      "step": 20
+    },
+    {
+      "epoch": 10.0,
+      "step": 20,
+      "total_flos": 7.743817889611776e+16,
+      "train_loss": 1.3487067699432373,
+      "train_runtime": 107.726,
+      "train_samples_per_second": 22.093,
+      "train_steps_per_second": 0.186
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 20,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": 7.743817889611776e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}