End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.9322033898305084
+      value: 0.9152542372881356
 ---
 
 <!-- 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: 0.2078
-- Accuracy: 0.9322
+- Loss: 0.2906
+- Accuracy: 0.9153
 
 ## Model description
 
@@ -67,14 +67,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 0.94  | 4    | 0.2574          | 0.9153   |
-| No log        | 1.88  | 8    | 0.2333          | 0.9153   |
-| 0.1896        | 2.82  | 12   | 0.2078          | 0.9322   |
+| No log        | 0.94  | 4    | 0.4790          | 0.7458   |
+| No log        | 1.88  | 8    | 0.3245          | 0.8644   |
+| 0.4186        | 2.82  | 12   | 0.2906          | 0.9153   |
 
 
 ### Framework versions
 
-- Transformers 4.38.1
+- Transformers 4.38.2
 - Pytorch 2.1.0+cu121
-- Datasets 2.17.1
+- Datasets 2.18.0
 - Tokenizers 0.15.2

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 2.82,
-    "eval_accuracy": 0.9322033898305084,
-    "eval_loss": 0.20782968401908875,
-    "eval_runtime": 3.4548,
-    "eval_samples_per_second": 17.078,
-    "eval_steps_per_second": 0.579,
+    "eval_accuracy": 0.9152542372881356,
+    "eval_loss": 0.29061949253082275,
+    "eval_runtime": 3.4295,
+    "eval_samples_per_second": 17.204,
+    "eval_steps_per_second": 0.583,
     "total_flos": 3.7283983478784e+16,
-    "train_loss": 0.17616023744146028,
-    "train_runtime": 116.4895,
-    "train_samples_per_second": 13.546,
-    "train_steps_per_second": 0.103
+    "train_loss": 0.3904288361469905,
+    "train_runtime": 118.5728,
+    "train_samples_per_second": 13.308,
+    "train_steps_per_second": 0.101
 }

config.json

@@ -55,7 +55,7 @@
     "stage4"
   ],
   "torch_dtype": "float32",
-  "transformers_version": "4.38.1",
+  "transformers_version": "4.38.2",
   "use_absolute_embeddings": false,
   "window_size": 7
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.82,
-    "eval_accuracy": 0.9322033898305084,
-    "eval_loss": 0.20782968401908875,
-    "eval_runtime": 3.4548,
-    "eval_samples_per_second": 17.078,
-    "eval_steps_per_second": 0.579
+    "eval_accuracy": 0.9152542372881356,
+    "eval_loss": 0.29061949253082275,
+    "eval_runtime": 3.4295,
+    "eval_samples_per_second": 17.204,
+    "eval_steps_per_second": 0.583
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:960b69ae11e813d40983d4dfb37a715a0c94dee88654a5adc0793770b26dc166
+oid sha256:ab1e5ceaf0b9ba83085a3c12f1c1e1a34678b3bb0d4b3dbc619653839b3a425d
 size 110342832

runs/Mar04_16-16-46_1982b302d4fe/events.out.tfevents.1709569365.1982b302d4fe.4995.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d12eec743abc8b007aa9a31f5d81d3d129468f8805a9ec87e8a862fd09d19eeb
+size 6537

runs/Mar04_16-16-46_1982b302d4fe/events.out.tfevents.1709569487.1982b302d4fe.4995.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d63e3166d03441b4a7c3310d91c2999ac9976b643cf295c02eece0874fa395e4
+size 405

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.82,
     "total_flos": 3.7283983478784e+16,
-    "train_loss": 0.17616023744146028,
-    "train_runtime": 116.4895,
-    "train_samples_per_second": 13.546,
-    "train_steps_per_second": 0.103
+    "train_loss": 0.3904288361469905,
+    "train_runtime": 118.5728,
+    "train_samples_per_second": 13.308,
+    "train_steps_per_second": 0.101
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.9322033898305084,
+  "best_metric": 0.9152542372881356,
   "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-12",
   "epoch": 2.8235294117647056,
   "eval_steps": 500,
@@ -10,46 +10,46 @@
   "log_history": [
     {
       "epoch": 0.94,
-      "eval_accuracy": 0.9152542372881356,
-      "eval_loss": 0.2573569416999817,
-      "eval_runtime": 3.3955,
-      "eval_samples_per_second": 17.376,
-      "eval_steps_per_second": 0.589,
+      "eval_accuracy": 0.7457627118644068,
+      "eval_loss": 0.478995680809021,
+      "eval_runtime": 3.3638,
+      "eval_samples_per_second": 17.54,
+      "eval_steps_per_second": 0.595,
       "step": 4
     },
     {
       "epoch": 1.88,
-      "eval_accuracy": 0.9152542372881356,
-      "eval_loss": 0.2333347201347351,
-      "eval_runtime": 4.3391,
-      "eval_samples_per_second": 13.597,
-      "eval_steps_per_second": 0.461,
+      "eval_accuracy": 0.864406779661017,
+      "eval_loss": 0.32449179887771606,
+      "eval_runtime": 3.4489,
+      "eval_samples_per_second": 17.107,
+      "eval_steps_per_second": 0.58,
       "step": 8
     },
     {
       "epoch": 2.35,
-      "grad_norm": 11.989400863647461,
+      "grad_norm": 4.969060897827148,
       "learning_rate": 1e-05,
-      "loss": 0.1896,
+      "loss": 0.4186,
       "step": 10
     },
     {
       "epoch": 2.82,
-      "eval_accuracy": 0.9322033898305084,
-      "eval_loss": 0.20782968401908875,
-      "eval_runtime": 3.6448,
-      "eval_samples_per_second": 16.188,
-      "eval_steps_per_second": 0.549,
+      "eval_accuracy": 0.9152542372881356,
+      "eval_loss": 0.29061949253082275,
+      "eval_runtime": 4.2268,
+      "eval_samples_per_second": 13.959,
+      "eval_steps_per_second": 0.473,
       "step": 12
     },
     {
       "epoch": 2.82,
       "step": 12,
       "total_flos": 3.7283983478784e+16,
-      "train_loss": 0.17616023744146028,
-      "train_runtime": 116.4895,
-      "train_samples_per_second": 13.546,
-      "train_steps_per_second": 0.103
+      "train_loss": 0.3904288361469905,
+      "train_runtime": 118.5728,
+      "train_samples_per_second": 13.308,
+      "train_steps_per_second": 0.101
     }
   ],
   "logging_steps": 10,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfe922973277a05a1e3c19748fc5c7a7792ad637191bc46dedb245c844f2d7ef
+oid sha256:a408e0a2d736d7be5b89505174e6352b11fc031469813334a7f6e3ad78aa6e03
 size 4984