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/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.3714
+- Loss: 8.0201
 - Accuracy: 0.0980
 
 ## Model description

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 22.86,
+    "eval_accuracy": 0.09803921568627451,
+    "eval_loss": 8.020079612731934,
+    "eval_runtime": 1.0016,
+    "eval_samples_per_second": 50.918,
+    "eval_steps_per_second": 1.997,
+    "train_loss": 6.031261348724366,
+    "train_runtime": 124.0067,
+    "train_samples_per_second": 65.48,
+    "train_steps_per_second": 0.323
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 22.86,
+    "eval_accuracy": 0.09803921568627451,
+    "eval_loss": 8.020079612731934,
+    "eval_runtime": 1.0016,
+    "eval_samples_per_second": 50.918,
+    "eval_steps_per_second": 1.997
+}

runs/Jun17_10-52-28_DESKTOP-SKBE9FB/events.out.tfevents.1718643277.DESKTOP-SKBE9FB.1840.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0a4cd22232d8f2608098e1152bbb06d5687757bcfd90cc62bc1bdad4190fd3c
+size 405

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 22.86,
+    "train_loss": 6.031261348724366,
+    "train_runtime": 124.0067,
+    "train_samples_per_second": 65.48,
+    "train_steps_per_second": 0.323
+}

trainer_state.json

@@ -0,0 +1,261 @@
+{
+  "best_metric": 0.09803921568627451,
+  "best_model_checkpoint": "swinv2-tiny-patch4-window8-256-ve-Ub\\checkpoint-1",
+  "epoch": 22.857142857142858,
+  "eval_steps": 500,
+  "global_step": 40,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.57,
+      "eval_accuracy": 0.09803921568627451,
+      "eval_loss": 8.020079612731934,
+      "eval_runtime": 0.9165,
+      "eval_samples_per_second": 55.645,
+      "eval_steps_per_second": 2.182,
+      "step": 1
+    },
+    {
+      "epoch": 1.71,
+      "eval_accuracy": 0.09803921568627451,
+      "eval_loss": 8.004411697387695,
+      "eval_runtime": 0.7005,
+      "eval_samples_per_second": 72.805,
+      "eval_steps_per_second": 2.855,
+      "step": 3
+    },
+    {
+      "epoch": 2.86,
+      "eval_accuracy": 0.09803921568627451,
+      "eval_loss": 7.930569648742676,
+      "eval_runtime": 0.7161,
+      "eval_samples_per_second": 71.215,
+      "eval_steps_per_second": 2.793,
+      "step": 5
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.09803921568627451,
+      "eval_loss": 7.77127742767334,
+      "eval_runtime": 0.7123,
+      "eval_samples_per_second": 71.602,
+      "eval_steps_per_second": 2.808,
+      "step": 7
+    },
+    {
+      "epoch": 4.57,
+      "eval_accuracy": 0.09803921568627451,
+      "eval_loss": 7.651132583618164,
+      "eval_runtime": 0.6843,
+      "eval_samples_per_second": 74.53,
+      "eval_steps_per_second": 2.923,
+      "step": 8
+    },
+    {
+      "epoch": 5.71,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 7.7785,
+      "step": 10
+    },
+    {
+      "epoch": 5.71,
+      "eval_accuracy": 0.09803921568627451,
+      "eval_loss": 7.365252494812012,
+      "eval_runtime": 0.7228,
+      "eval_samples_per_second": 70.557,
+      "eval_steps_per_second": 2.767,
+      "step": 10
+    },
+    {
+      "epoch": 6.86,
+      "eval_accuracy": 0.09803921568627451,
+      "eval_loss": 7.024637699127197,
+      "eval_runtime": 0.7167,
+      "eval_samples_per_second": 71.16,
+      "eval_steps_per_second": 2.791,
+      "step": 12
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.09803921568627451,
+      "eval_loss": 6.641313076019287,
+      "eval_runtime": 0.7094,
+      "eval_samples_per_second": 71.894,
+      "eval_steps_per_second": 2.819,
+      "step": 14
+    },
+    {
+      "epoch": 8.57,
+      "eval_accuracy": 0.09803921568627451,
+      "eval_loss": 6.466968059539795,
+      "eval_runtime": 0.6864,
+      "eval_samples_per_second": 74.298,
+      "eval_steps_per_second": 2.914,
+      "step": 15
+    },
+    {
+      "epoch": 9.71,
+      "eval_accuracy": 0.09803921568627451,
+      "eval_loss": 6.132067680358887,
+      "eval_runtime": 0.6833,
+      "eval_samples_per_second": 74.642,
+      "eval_steps_per_second": 2.927,
+      "step": 17
+    },
+    {
+      "epoch": 10.86,
+      "eval_accuracy": 0.09803921568627451,
+      "eval_loss": 5.835997104644775,
+      "eval_runtime": 0.7199,
+      "eval_samples_per_second": 70.846,
+      "eval_steps_per_second": 2.778,
+      "step": 19
+    },
+    {
+      "epoch": 11.43,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 6.5357,
+      "step": 20
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.09803921568627451,
+      "eval_loss": 5.574275970458984,
+      "eval_runtime": 0.6885,
+      "eval_samples_per_second": 74.079,
+      "eval_steps_per_second": 2.905,
+      "step": 21
+    },
+    {
+      "epoch": 12.57,
+      "eval_accuracy": 0.09803921568627451,
+      "eval_loss": 5.455224514007568,
+      "eval_runtime": 0.667,
+      "eval_samples_per_second": 76.457,
+      "eval_steps_per_second": 2.998,
+      "step": 22
+    },
+    {
+      "epoch": 13.71,
+      "eval_accuracy": 0.09803921568627451,
+      "eval_loss": 5.236710548400879,
+      "eval_runtime": 0.6751,
+      "eval_samples_per_second": 75.541,
+      "eval_steps_per_second": 2.962,
+      "step": 24
+    },
+    {
+      "epoch": 14.86,
+      "eval_accuracy": 0.09803921568627451,
+      "eval_loss": 5.04180383682251,
+      "eval_runtime": 0.6855,
+      "eval_samples_per_second": 74.395,
+      "eval_steps_per_second": 2.917,
+      "step": 26
+    },
+    {
+      "epoch": 16.0,
+      "eval_accuracy": 0.09803921568627451,
+      "eval_loss": 4.870639324188232,
+      "eval_runtime": 0.6928,
+      "eval_samples_per_second": 73.616,
+      "eval_steps_per_second": 2.887,
+      "step": 28
+    },
+    {
+      "epoch": 16.57,
+      "eval_accuracy": 0.09803921568627451,
+      "eval_loss": 4.793884754180908,
+      "eval_runtime": 0.7006,
+      "eval_samples_per_second": 72.795,
+      "eval_steps_per_second": 2.855,
+      "step": 29
+    },
+    {
+      "epoch": 17.14,
+      "learning_rate": 1.388888888888889e-05,
+      "loss": 5.2494,
+      "step": 30
+    },
+    {
+      "epoch": 17.71,
+      "eval_accuracy": 0.09803921568627451,
+      "eval_loss": 4.659574031829834,
+      "eval_runtime": 0.6877,
+      "eval_samples_per_second": 74.158,
+      "eval_steps_per_second": 2.908,
+      "step": 31
+    },
+    {
+      "epoch": 18.86,
+      "eval_accuracy": 0.09803921568627451,
+      "eval_loss": 4.550791263580322,
+      "eval_runtime": 0.6971,
+      "eval_samples_per_second": 73.163,
+      "eval_steps_per_second": 2.869,
+      "step": 33
+    },
+    {
+      "epoch": 20.0,
+      "eval_accuracy": 0.09803921568627451,
+      "eval_loss": 4.467587471008301,
+      "eval_runtime": 0.7059,
+      "eval_samples_per_second": 72.247,
+      "eval_steps_per_second": 2.833,
+      "step": 35
+    },
+    {
+      "epoch": 20.57,
+      "eval_accuracy": 0.09803921568627451,
+      "eval_loss": 4.435560703277588,
+      "eval_runtime": 0.6994,
+      "eval_samples_per_second": 72.923,
+      "eval_steps_per_second": 2.86,
+      "step": 36
+    },
+    {
+      "epoch": 21.71,
+      "eval_accuracy": 0.09803921568627451,
+      "eval_loss": 4.3906331062316895,
+      "eval_runtime": 0.6833,
+      "eval_samples_per_second": 74.635,
+      "eval_steps_per_second": 2.927,
+      "step": 38
+    },
+    {
+      "epoch": 22.86,
+      "learning_rate": 0.0,
+      "loss": 4.5614,
+      "step": 40
+    },
+    {
+      "epoch": 22.86,
+      "eval_accuracy": 0.09803921568627451,
+      "eval_loss": 4.371392250061035,
+      "eval_runtime": 0.685,
+      "eval_samples_per_second": 74.456,
+      "eval_steps_per_second": 2.92,
+      "step": 40
+    },
+    {
+      "epoch": 22.86,
+      "step": 40,
+      "total_flos": 1.5155335319519232e+17,
+      "train_loss": 6.031261348724366,
+      "train_runtime": 124.0067,
+      "train_samples_per_second": 65.48,
+      "train_steps_per_second": 0.323
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 40,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 40,
+  "save_steps": 500,
+  "total_flos": 1.5155335319519232e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}