dungeon-geo-morphs

README.md

@@ -3,6 +3,7 @@ library_name: transformers
 license: apache-2.0
 base_model: google/vit-large-patch16-224
 tags:
+- image-classification
 - generated_from_trainer
 datasets:
 - imagefolder
@@ -15,7 +16,7 @@ model-index:
       name: Image Classification
       type: image-classification
     dataset:
-      name: imagefolder
+      name: dungeon-geo-morphs
       type: imagefolder
       config: default
       split: validation
@@ -23,7 +24,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.9839285714285714
+      value: 0.9875
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,10 +32,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # vit-large-patch16-224-dungeon-geo-morphs-0-4-30Nov24-005
 
-This model is a fine-tuned version of [google/vit-large-patch16-224](https://huggingface.co/google/vit-large-patch16-224) on the imagefolder dataset.
+This model is a fine-tuned version of [google/vit-large-patch16-224](https://huggingface.co/google/vit-large-patch16-224) on the dungeon-geo-morphs dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1032
-- Accuracy: 0.9839
+- Loss: 0.1439
+- Accuracy: 0.9875
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 35.45454545454545,
+    "eval_accuracy": 0.9875,
+    "eval_loss": 0.14392714202404022,
+    "eval_runtime": 8.2841,
+    "eval_samples_per_second": 67.6,
+    "eval_steps_per_second": 8.45,
+    "total_flos": 7.012786101918106e+17,
+    "train_loss": 0.5004434317350388,
+    "train_runtime": 641.4666,
+    "train_samples_per_second": 5.051,
+    "train_steps_per_second": 0.125
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 35.45454545454545,
+    "eval_accuracy": 0.9875,
+    "eval_loss": 0.14392714202404022,
+    "eval_runtime": 8.2841,
+    "eval_samples_per_second": 67.6,
+    "eval_steps_per_second": 8.45
+}

runs/Nov30_11-42-55_c631b2c2f854/events.out.tfevents.1732967741.c631b2c2f854.485.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fca0f3e0d5f4aad7388470b7f2181678098859b0e5f63d0563ed1ad06fec9144
+size 405

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 35.45454545454545,
+    "total_flos": 7.012786101918106e+17,
+    "train_loss": 0.5004434317350388,
+    "train_runtime": 641.4666,
+    "train_samples_per_second": 5.051,
+    "train_steps_per_second": 0.125
+}

trainer_state.json

@@ -0,0 +1,170 @@
+{
+  "best_metric": 0.9875,
+  "best_model_checkpoint": "vit-large-patch16-224-dungeon-geo-morphs-0-4-30Nov24-005/checkpoint-60",
+  "epoch": 35.45454545454545,
+  "eval_steps": 10,
+  "global_step": 80,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 4.363636363636363,
+      "grad_norm": 24.60907745361328,
+      "learning_rate": 9.861111111111112e-06,
+      "loss": 1.5645,
+      "step": 10
+    },
+    {
+      "epoch": 4.363636363636363,
+      "eval_accuracy": 0.525,
+      "eval_loss": 1.2976471185684204,
+      "eval_runtime": 7.6522,
+      "eval_samples_per_second": 73.182,
+      "eval_steps_per_second": 9.148,
+      "step": 10
+    },
+    {
+      "epoch": 8.727272727272727,
+      "grad_norm": 38.15880584716797,
+      "learning_rate": 8.472222222222223e-06,
+      "loss": 1.0147,
+      "step": 20
+    },
+    {
+      "epoch": 8.727272727272727,
+      "eval_accuracy": 0.8392857142857143,
+      "eval_loss": 0.7672407031059265,
+      "eval_runtime": 8.3987,
+      "eval_samples_per_second": 66.677,
+      "eval_steps_per_second": 8.335,
+      "step": 20
+    },
+    {
+      "epoch": 13.272727272727273,
+      "grad_norm": 17.74706268310547,
+      "learning_rate": 7.083333333333335e-06,
+      "loss": 0.5992,
+      "step": 30
+    },
+    {
+      "epoch": 13.272727272727273,
+      "eval_accuracy": 0.9446428571428571,
+      "eval_loss": 0.4469510614871979,
+      "eval_runtime": 7.2106,
+      "eval_samples_per_second": 77.664,
+      "eval_steps_per_second": 9.708,
+      "step": 30
+    },
+    {
+      "epoch": 17.636363636363637,
+      "grad_norm": 13.495892524719238,
+      "learning_rate": 5.833333333333334e-06,
+      "loss": 0.343,
+      "step": 40
+    },
+    {
+      "epoch": 17.636363636363637,
+      "eval_accuracy": 0.9589285714285715,
+      "eval_loss": 0.29256269335746765,
+      "eval_runtime": 8.3922,
+      "eval_samples_per_second": 66.729,
+      "eval_steps_per_second": 8.341,
+      "step": 40
+    },
+    {
+      "epoch": 22.181818181818183,
+      "grad_norm": 14.16152572631836,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 0.2065,
+      "step": 50
+    },
+    {
+      "epoch": 22.181818181818183,
+      "eval_accuracy": 0.9785714285714285,
+      "eval_loss": 0.19798338413238525,
+      "eval_runtime": 7.1418,
+      "eval_samples_per_second": 78.412,
+      "eval_steps_per_second": 9.801,
+      "step": 50
+    },
+    {
+      "epoch": 26.545454545454547,
+      "grad_norm": 11.846973419189453,
+      "learning_rate": 3.055555555555556e-06,
+      "loss": 0.1286,
+      "step": 60
+    },
+    {
+      "epoch": 26.545454545454547,
+      "eval_accuracy": 0.9875,
+      "eval_loss": 0.14392714202404022,
+      "eval_runtime": 8.2847,
+      "eval_samples_per_second": 67.595,
+      "eval_steps_per_second": 8.449,
+      "step": 60
+    },
+    {
+      "epoch": 31.09090909090909,
+      "grad_norm": 6.959174633026123,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.082,
+      "step": 70
+    },
+    {
+      "epoch": 31.09090909090909,
+      "eval_accuracy": 0.9857142857142858,
+      "eval_loss": 0.1140705794095993,
+      "eval_runtime": 7.6557,
+      "eval_samples_per_second": 73.148,
+      "eval_steps_per_second": 9.143,
+      "step": 70
+    },
+    {
+      "epoch": 35.45454545454545,
+      "grad_norm": 8.776320457458496,
+      "learning_rate": 2.7777777777777776e-07,
+      "loss": 0.0649,
+      "step": 80
+    },
+    {
+      "epoch": 35.45454545454545,
+      "eval_accuracy": 0.9839285714285714,
+      "eval_loss": 0.10324299335479736,
+      "eval_runtime": 7.8656,
+      "eval_samples_per_second": 71.196,
+      "eval_steps_per_second": 8.899,
+      "step": 80
+    },
+    {
+      "epoch": 35.45454545454545,
+      "step": 80,
+      "total_flos": 7.012786101918106e+17,
+      "train_loss": 0.5004434317350388,
+      "train_runtime": 641.4666,
+      "train_samples_per_second": 5.051,
+      "train_steps_per_second": 0.125
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 80,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 40,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.012786101918106e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}