End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.885
+      value: 0.945
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ 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: 0.3423
-- Accuracy: 0.885
+- Loss: 0.2078
+- Accuracy: 0.945
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 9.824561403508772,
+    "eval_accuracy": 0.945,
+    "eval_loss": 0.20781494677066803,
+    "eval_runtime": 59.5914,
+    "eval_samples_per_second": 3.356,
+    "eval_steps_per_second": 0.117,
+    "total_flos": 4.400504290055946e+17,
+    "train_loss": 0.2603792348078319,
+    "train_runtime": 15640.9233,
+    "train_samples_per_second": 1.151,
+    "train_steps_per_second": 0.009
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 9.824561403508772,
+    "eval_accuracy": 0.945,
+    "eval_loss": 0.20781494677066803,
+    "eval_runtime": 59.5914,
+    "eval_samples_per_second": 3.356,
+    "eval_steps_per_second": 0.117
+}

runs/Apr23_10-10-14_42ece461816d/events.out.tfevents.1713882724.42ece461816d.20321.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fbb84e500312f782a03653c7272057e3171510c7c1d6c4ee0f734a4c46eed6f
+size 411

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 9.824561403508772,
+    "total_flos": 4.400504290055946e+17,
+    "train_loss": 0.2603792348078319,
+    "train_runtime": 15640.9233,
+    "train_samples_per_second": 1.151,
+    "train_steps_per_second": 0.009
+}

trainer_state.json

@@ -0,0 +1,218 @@
+{
+  "best_metric": 0.945,
+  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat-leukemia-1000/checkpoint-114",
+  "epoch": 9.824561403508772,
+  "eval_steps": 500,
+  "global_step": 140,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.7017543859649122,
+      "grad_norm": 3.293278217315674,
+      "learning_rate": 3.571428571428572e-05,
+      "loss": 0.6899,
+      "step": 10
+    },
+    {
+      "epoch": 0.9824561403508771,
+      "eval_accuracy": 0.6,
+      "eval_loss": 0.6197624206542969,
+      "eval_runtime": 59.5649,
+      "eval_samples_per_second": 3.358,
+      "eval_steps_per_second": 0.118,
+      "step": 14
+    },
+    {
+      "epoch": 1.4035087719298245,
+      "grad_norm": 15.828011512756348,
+      "learning_rate": 4.761904761904762e-05,
+      "loss": 0.5494,
+      "step": 20
+    },
+    {
+      "epoch": 1.9649122807017543,
+      "eval_accuracy": 0.805,
+      "eval_loss": 0.40077194571495056,
+      "eval_runtime": 63.3088,
+      "eval_samples_per_second": 3.159,
+      "eval_steps_per_second": 0.111,
+      "step": 28
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 17.80167579650879,
+      "learning_rate": 4.3650793650793655e-05,
+      "loss": 0.4802,
+      "step": 30
+    },
+    {
+      "epoch": 2.807017543859649,
+      "grad_norm": 10.38412857055664,
+      "learning_rate": 3.968253968253968e-05,
+      "loss": 0.376,
+      "step": 40
+    },
+    {
+      "epoch": 2.9473684210526314,
+      "eval_accuracy": 0.815,
+      "eval_loss": 0.40858185291290283,
+      "eval_runtime": 61.4384,
+      "eval_samples_per_second": 3.255,
+      "eval_steps_per_second": 0.114,
+      "step": 42
+    },
+    {
+      "epoch": 3.5087719298245617,
+      "grad_norm": 13.256275177001953,
+      "learning_rate": 3.571428571428572e-05,
+      "loss": 0.2852,
+      "step": 50
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.81,
+      "eval_loss": 0.44540536403656006,
+      "eval_runtime": 59.681,
+      "eval_samples_per_second": 3.351,
+      "eval_steps_per_second": 0.117,
+      "step": 57
+    },
+    {
+      "epoch": 4.2105263157894735,
+      "grad_norm": 14.636404991149902,
+      "learning_rate": 3.1746031746031745e-05,
+      "loss": 0.2214,
+      "step": 60
+    },
+    {
+      "epoch": 4.912280701754386,
+      "grad_norm": 15.16395378112793,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 0.184,
+      "step": 70
+    },
+    {
+      "epoch": 4.982456140350877,
+      "eval_accuracy": 0.715,
+      "eval_loss": 0.8480778336524963,
+      "eval_runtime": 60.6095,
+      "eval_samples_per_second": 3.3,
+      "eval_steps_per_second": 0.115,
+      "step": 71
+    },
+    {
+      "epoch": 5.614035087719298,
+      "grad_norm": 20.521684646606445,
+      "learning_rate": 2.380952380952381e-05,
+      "loss": 0.183,
+      "step": 80
+    },
+    {
+      "epoch": 5.964912280701754,
+      "eval_accuracy": 0.94,
+      "eval_loss": 0.18698543310165405,
+      "eval_runtime": 62.558,
+      "eval_samples_per_second": 3.197,
+      "eval_steps_per_second": 0.112,
+      "step": 85
+    },
+    {
+      "epoch": 6.315789473684211,
+      "grad_norm": 22.951629638671875,
+      "learning_rate": 1.984126984126984e-05,
+      "loss": 0.1465,
+      "step": 90
+    },
+    {
+      "epoch": 6.947368421052632,
+      "eval_accuracy": 0.8,
+      "eval_loss": 0.7121139764785767,
+      "eval_runtime": 63.8208,
+      "eval_samples_per_second": 3.134,
+      "eval_steps_per_second": 0.11,
+      "step": 99
+    },
+    {
+      "epoch": 7.017543859649122,
+      "grad_norm": 23.46278190612793,
+      "learning_rate": 1.5873015873015872e-05,
+      "loss": 0.111,
+      "step": 100
+    },
+    {
+      "epoch": 7.719298245614035,
+      "grad_norm": 20.50105857849121,
+      "learning_rate": 1.1904761904761905e-05,
+      "loss": 0.1319,
+      "step": 110
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.945,
+      "eval_loss": 0.20781494677066803,
+      "eval_runtime": 59.8995,
+      "eval_samples_per_second": 3.339,
+      "eval_steps_per_second": 0.117,
+      "step": 114
+    },
+    {
+      "epoch": 8.421052631578947,
+      "grad_norm": 14.028729438781738,
+      "learning_rate": 7.936507936507936e-06,
+      "loss": 0.1054,
+      "step": 120
+    },
+    {
+      "epoch": 8.982456140350877,
+      "eval_accuracy": 0.885,
+      "eval_loss": 0.3320530354976654,
+      "eval_runtime": 60.1547,
+      "eval_samples_per_second": 3.325,
+      "eval_steps_per_second": 0.116,
+      "step": 128
+    },
+    {
+      "epoch": 9.12280701754386,
+      "grad_norm": 8.052062034606934,
+      "learning_rate": 3.968253968253968e-06,
+      "loss": 0.0852,
+      "step": 130
+    },
+    {
+      "epoch": 9.824561403508772,
+      "grad_norm": 9.103638648986816,
+      "learning_rate": 0.0,
+      "loss": 0.096,
+      "step": 140
+    },
+    {
+      "epoch": 9.824561403508772,
+      "eval_accuracy": 0.885,
+      "eval_loss": 0.3423093855381012,
+      "eval_runtime": 61.212,
+      "eval_samples_per_second": 3.267,
+      "eval_steps_per_second": 0.114,
+      "step": 140
+    },
+    {
+      "epoch": 9.824561403508772,
+      "step": 140,
+      "total_flos": 4.400504290055946e+17,
+      "train_loss": 0.2603792348078319,
+      "train_runtime": 15640.9233,
+      "train_samples_per_second": 1.151,
+      "train_steps_per_second": 0.009
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 140,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 4.400504290055946e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}