rotated_maps

README.md

@@ -24,7 +24,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 1.0
+      value: 0.875
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -34,8 +34,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the rotated_maps dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1515
-- Accuracy: 1.0
+- Loss: 0.5177
+- Accuracy: 0.875
 
 ## Model description
 
@@ -67,7 +67,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.0386        | 12.5  | 100  | 0.1515          | 1.0      |
+| 0.1009        | 12.5  | 100  | 0.5177          | 0.875    |
 
 
 ### Framework versions

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 15.0,
-    "eval_accuracy": 1.0,
-    "eval_loss": 0.1515045166015625,
-    "eval_runtime": 0.092,
-    "eval_samples_per_second": 76.101,
-    "eval_steps_per_second": 10.872,
-    "total_flos": 4.417241350846464e+16,
-    "train_loss": 0.08117741694053014,
-    "train_runtime": 27.1137,
-    "train_samples_per_second": 21.023,
-    "train_steps_per_second": 4.426
+    "eval_accuracy": 0.875,
+    "eval_loss": 0.5177230834960938,
+    "eval_runtime": 0.1273,
+    "eval_samples_per_second": 62.83,
+    "eval_steps_per_second": 7.854,
+    "total_flos": 4.64972773773312e+16,
+    "train_loss": 0.45015646318594615,
+    "train_runtime": 30.2968,
+    "train_samples_per_second": 19.804,
+    "train_steps_per_second": 3.961
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 15.0,
-    "eval_accuracy": 1.0,
-    "eval_loss": 0.1515045166015625,
-    "eval_runtime": 0.092,
-    "eval_samples_per_second": 76.101,
-    "eval_steps_per_second": 10.872
+    "eval_accuracy": 0.875,
+    "eval_loss": 0.5177230834960938,
+    "eval_runtime": 0.1273,
+    "eval_samples_per_second": 62.83,
+    "eval_steps_per_second": 7.854
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec300bee5b7dde99c4801ee26ecb64e50738f69095e1b8d86fbc34f204f96153
+oid sha256:624e1b227a433f765e4f11185a40c7bb3c8df1343071ee4c8ee0e1e20a8d84e1
 size 343239356

runs/Oct29_20-25-38_3e04bab4dd1f/events.out.tfevents.1730233547.3e04bab4dd1f.943.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bed54ae20228aceff93dd0913002cfc7cba4052841e376c2c8ae424d5e3d23f
+size 8300

runs/Oct29_20-25-38_3e04bab4dd1f/events.out.tfevents.1730233581.3e04bab4dd1f.943.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:315ced64c36dfa9ca028f47f5703e599bc4491b6b7dcef04ada114fa0ebb8da0
+size 405

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 15.0,
-    "total_flos": 4.417241350846464e+16,
-    "train_loss": 0.08117741694053014,
-    "train_runtime": 27.1137,
-    "train_samples_per_second": 21.023,
-    "train_steps_per_second": 4.426
+    "total_flos": 4.64972773773312e+16,
+    "train_loss": 0.45015646318594615,
+    "train_runtime": 30.2968,
+    "train_samples_per_second": 19.804,
+    "train_steps_per_second": 3.961
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.1515045166015625,
+  "best_metric": 0.5177230834960938,
   "best_model_checkpoint": "vit-base-patch16-224-in21k-rotated-dungeons-v3/checkpoint-100",
   "epoch": 15.0,
   "eval_steps": 100,
@@ -10,105 +10,105 @@
   "log_history": [
     {
       "epoch": 1.25,
-      "grad_norm": 0.588030219078064,
+      "grad_norm": 2.4491872787475586,
       "learning_rate": 0.00018333333333333334,
-      "loss": 0.2001,
+      "loss": 1.7253,
       "step": 10
     },
     {
       "epoch": 2.5,
-      "grad_norm": 0.40187984704971313,
+      "grad_norm": 2.151639461517334,
       "learning_rate": 0.0001666666666666667,
-      "loss": 0.2121,
+      "loss": 1.2096,
       "step": 20
     },
     {
       "epoch": 3.75,
-      "grad_norm": 0.26918885111808777,
+      "grad_norm": 1.7387666702270508,
       "learning_rate": 0.00015000000000000001,
-      "loss": 0.1179,
+      "loss": 0.8385,
       "step": 30
     },
     {
       "epoch": 5.0,
-      "grad_norm": 0.2864986062049866,
+      "grad_norm": 1.5225492715835571,
       "learning_rate": 0.00013333333333333334,
-      "loss": 0.0755,
+      "loss": 0.4285,
       "step": 40
     },
     {
       "epoch": 6.25,
-      "grad_norm": 0.20267005264759064,
+      "grad_norm": 0.6194241046905518,
       "learning_rate": 0.00011666666666666668,
-      "loss": 0.0641,
+      "loss": 0.322,
       "step": 50
     },
     {
       "epoch": 7.5,
-      "grad_norm": 0.24064351618289948,
+      "grad_norm": 0.9321300387382507,
       "learning_rate": 0.0001,
-      "loss": 0.0523,
+      "loss": 0.1986,
       "step": 60
     },
     {
       "epoch": 8.75,
-      "grad_norm": 0.15450333058834076,
+      "grad_norm": 0.4772986173629761,
       "learning_rate": 8.333333333333334e-05,
-      "loss": 0.0487,
+      "loss": 0.1683,
       "step": 70
     },
     {
       "epoch": 10.0,
-      "grad_norm": 0.3064187467098236,
+      "grad_norm": 0.4312579929828644,
       "learning_rate": 6.666666666666667e-05,
-      "loss": 0.0447,
+      "loss": 0.1219,
       "step": 80
     },
     {
       "epoch": 11.25,
-      "grad_norm": 0.23561660945415497,
+      "grad_norm": 0.34619101881980896,
       "learning_rate": 5e-05,
-      "loss": 0.043,
+      "loss": 0.1029,
       "step": 90
     },
     {
       "epoch": 12.5,
-      "grad_norm": 0.19291207194328308,
+      "grad_norm": 0.330285906791687,
       "learning_rate": 3.3333333333333335e-05,
-      "loss": 0.0386,
+      "loss": 0.1009,
       "step": 100
     },
     {
       "epoch": 12.5,
-      "eval_accuracy": 1.0,
-      "eval_loss": 0.1515045166015625,
-      "eval_runtime": 0.0635,
-      "eval_samples_per_second": 110.175,
-      "eval_steps_per_second": 15.739,
+      "eval_accuracy": 0.875,
+      "eval_loss": 0.5177230834960938,
+      "eval_runtime": 0.0932,
+      "eval_samples_per_second": 85.814,
+      "eval_steps_per_second": 10.727,
       "step": 100
     },
     {
       "epoch": 13.75,
-      "grad_norm": 0.14135047793388367,
+      "grad_norm": 0.5117152333259583,
       "learning_rate": 1.6666666666666667e-05,
-      "loss": 0.0402,
+      "loss": 0.0982,
       "step": 110
     },
     {
       "epoch": 15.0,
-      "grad_norm": 0.2867968678474426,
+      "grad_norm": 0.43090176582336426,
       "learning_rate": 0.0,
-      "loss": 0.037,
+      "loss": 0.0872,
       "step": 120
     },
     {
       "epoch": 15.0,
       "step": 120,
-      "total_flos": 4.417241350846464e+16,
-      "train_loss": 0.08117741694053014,
-      "train_runtime": 27.1137,
-      "train_samples_per_second": 21.023,
-      "train_steps_per_second": 4.426
+      "total_flos": 4.64972773773312e+16,
+      "train_loss": 0.45015646318594615,
+      "train_runtime": 30.2968,
+      "train_samples_per_second": 19.804,
+      "train_steps_per_second": 3.961
     }
   ],
   "logging_steps": 10,
@@ -128,7 +128,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.417241350846464e+16,
+  "total_flos": 4.64972773773312e+16,
   "train_batch_size": 5,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c92f29ff6847d0e143af11ce92e7c695b999cab35edef2863bd027c51ded0a06
+oid sha256:0fb2cc2648216541e9edbb969fa04031be3e7fa72f8bc658c167a01a32d323e1
 size 5240