End of training

README.md

@@ -32,7 +32,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2522
+- Loss: 0.3943
 - Accuracy: 1.0
 
 ## Model description

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 1.0,
+    "eval_loss": 0.39433449506759644,
+    "eval_runtime": 2.1956,
+    "eval_samples_per_second": 6.376,
+    "eval_steps_per_second": 0.455,
+    "total_flos": 3.082142634246144e+16,
+    "train_loss": 0.48003435134887695,
+    "train_runtime": 259.245,
+    "train_samples_per_second": 4.783,
+    "train_steps_per_second": 0.039
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 1.0,
+    "eval_loss": 0.39433449506759644,
+    "eval_runtime": 2.1956,
+    "eval_samples_per_second": 6.376,
+    "eval_steps_per_second": 0.455
+}

runs/May26_22-38-01_1144702afd64/events.out.tfevents.1716763348.1144702afd64.287.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91fec531bd181f8176d78dcc5cb8a8a75c2e7cc2bba10444b901a046130072ec
+size 405

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "total_flos": 3.082142634246144e+16,
+    "train_loss": 0.48003435134887695,
+    "train_runtime": 259.245,
+    "train_samples_per_second": 4.783,
+    "train_steps_per_second": 0.039
+}

trainer_state.json

@@ -0,0 +1,139 @@
+{
+  "best_metric": 1.0,
+  "best_model_checkpoint": "swin-tiny-patch4-window7-224-Mid-NonMidMarket-Classification/checkpoint-5",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 10,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.21428571428571427,
+      "eval_loss": 0.8506087064743042,
+      "eval_runtime": 7.3051,
+      "eval_samples_per_second": 1.916,
+      "eval_steps_per_second": 0.137,
+      "step": 1
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5714285714285714,
+      "eval_loss": 0.7153599858283997,
+      "eval_runtime": 1.9543,
+      "eval_samples_per_second": 7.164,
+      "eval_steps_per_second": 0.512,
+      "step": 2
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7857142857142857,
+      "eval_loss": 0.5852259993553162,
+      "eval_runtime": 1.8648,
+      "eval_samples_per_second": 7.508,
+      "eval_steps_per_second": 0.536,
+      "step": 3
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9285714285714286,
+      "eval_loss": 0.4751197397708893,
+      "eval_runtime": 2.0294,
+      "eval_samples_per_second": 6.899,
+      "eval_steps_per_second": 0.493,
+      "step": 4
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.39433449506759644,
+      "eval_runtime": 1.9372,
+      "eval_samples_per_second": 7.227,
+      "eval_steps_per_second": 0.516,
+      "step": 5
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.337693989276886,
+      "eval_runtime": 2.2949,
+      "eval_samples_per_second": 6.1,
+      "eval_steps_per_second": 0.436,
+      "step": 6
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.29677438735961914,
+      "eval_runtime": 1.9456,
+      "eval_samples_per_second": 7.196,
+      "eval_steps_per_second": 0.514,
+      "step": 7
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.271878719329834,
+      "eval_runtime": 2.8241,
+      "eval_samples_per_second": 4.957,
+      "eval_steps_per_second": 0.354,
+      "step": 8
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.25762152671813965,
+      "eval_runtime": 1.8834,
+      "eval_samples_per_second": 7.433,
+      "eval_steps_per_second": 0.531,
+      "step": 9
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 2.779751777648926,
+      "learning_rate": 0.0,
+      "loss": 0.48,
+      "step": 10
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.25221019983291626,
+      "eval_runtime": 1.8914,
+      "eval_samples_per_second": 7.402,
+      "eval_steps_per_second": 0.529,
+      "step": 10
+    },
+    {
+      "epoch": 10.0,
+      "step": 10,
+      "total_flos": 3.082142634246144e+16,
+      "train_loss": 0.48003435134887695,
+      "train_runtime": 259.245,
+      "train_samples_per_second": 4.783,
+      "train_steps_per_second": 0.039
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 10,
+  "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": 3.082142634246144e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}