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
@@ -31,7 +32,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # vit-large-patch16-224-dungeon-geo-morphs-004
 
-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: 0.0895
 - Accuracy: 0.9444

all_results.json

@@ -1,13 +1,13 @@
 {
-    "epoch": 19.857142857142858,
+    "epoch": 20.0,
     "eval_accuracy": 0.9444444444444444,
-    "eval_loss": 0.0950346514582634,
-    "eval_runtime": 0.6537,
-    "eval_samples_per_second": 55.074,
-    "eval_steps_per_second": 7.649,
-    "total_flos": 2.6297770138730496e+17,
-    "train_loss": 0.2961386869351069,
-    "train_runtime": 192.5285,
-    "train_samples_per_second": 7.791,
-    "train_steps_per_second": 0.156
+    "eval_loss": 0.08948543667793274,
+    "eval_runtime": 0.601,
+    "eval_samples_per_second": 59.898,
+    "eval_steps_per_second": 8.319,
+    "total_flos": 2.7941380772401152e+17,
+    "train_loss": 0.3405552021094731,
+    "train_runtime": 211.545,
+    "train_samples_per_second": 8.438,
+    "train_steps_per_second": 0.165
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 19.857142857142858,
+    "epoch": 20.0,
     "eval_accuracy": 0.9444444444444444,
-    "eval_loss": 0.0950346514582634,
-    "eval_runtime": 0.6537,
-    "eval_samples_per_second": 55.074,
-    "eval_steps_per_second": 7.649
+    "eval_loss": 0.08948543667793274,
+    "eval_runtime": 0.601,
+    "eval_samples_per_second": 59.898,
+    "eval_steps_per_second": 8.319
 }

runs/Nov14_17-23-59_427600cacc83/events.out.tfevents.1731605336.427600cacc83.211.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9cb9f7feffb6f2d0d5a182fff7f080060f12593ca853dd2d587b565b226eff8
+size 405

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 19.857142857142858,
-    "total_flos": 2.6297770138730496e+17,
-    "train_loss": 0.2961386869351069,
-    "train_runtime": 192.5285,
-    "train_samples_per_second": 7.791,
-    "train_steps_per_second": 0.156
+    "epoch": 20.0,
+    "total_flos": 2.7941380772401152e+17,
+    "train_loss": 0.3405552021094731,
+    "train_runtime": 211.545,
+    "train_samples_per_second": 8.438,
+    "train_steps_per_second": 0.165
 }

trainer_state.json

@@ -1,75 +1,75 @@
 {
-  "best_metric": 0.0950346514582634,
+  "best_metric": 0.08948543667793274,
   "best_model_checkpoint": "vit-large-patch16-224-dungeon-geo-morphs-004/checkpoint-30",
-  "epoch": 19.857142857142858,
+  "epoch": 20.0,
   "eval_steps": 10,
-  "global_step": 30,
+  "global_step": 35,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 6.571428571428571,
-      "grad_norm": 15.927362442016602,
-      "learning_rate": 1.555555555555556e-05,
-      "loss": 0.7202,
+      "epoch": 5.714285714285714,
+      "grad_norm": 15.572179794311523,
+      "learning_rate": 1.6774193548387098e-05,
+      "loss": 0.8954,
       "step": 10
     },
     {
-      "epoch": 6.571428571428571,
+      "epoch": 5.714285714285714,
       "eval_accuracy": 0.9444444444444444,
-      "eval_loss": 0.2301517128944397,
-      "eval_runtime": 0.563,
-      "eval_samples_per_second": 63.947,
-      "eval_steps_per_second": 8.881,
+      "eval_loss": 0.3421071469783783,
+      "eval_runtime": 0.5133,
+      "eval_samples_per_second": 70.129,
+      "eval_steps_per_second": 9.74,
       "step": 10
     },
     {
-      "epoch": 13.285714285714286,
-      "grad_norm": 6.232780933380127,
-      "learning_rate": 8.148148148148148e-06,
-      "loss": 0.1296,
+      "epoch": 11.428571428571429,
+      "grad_norm": 8.270111083984375,
+      "learning_rate": 1.0322580645161291e-05,
+      "loss": 0.2087,
       "step": 20
     },
     {
-      "epoch": 13.285714285714286,
+      "epoch": 11.428571428571429,
       "eval_accuracy": 0.9444444444444444,
-      "eval_loss": 0.11305957287549973,
-      "eval_runtime": 0.6706,
-      "eval_samples_per_second": 53.684,
-      "eval_steps_per_second": 7.456,
+      "eval_loss": 0.14053164422512054,
+      "eval_runtime": 0.5592,
+      "eval_samples_per_second": 64.376,
+      "eval_steps_per_second": 8.941,
       "step": 20
     },
     {
-      "epoch": 19.857142857142858,
-      "grad_norm": 4.02134895324707,
-      "learning_rate": 7.407407407407407e-07,
-      "loss": 0.0385,
+      "epoch": 17.142857142857142,
+      "grad_norm": 6.16154146194458,
+      "learning_rate": 3.870967741935484e-06,
+      "loss": 0.062,
       "step": 30
     },
     {
-      "epoch": 19.857142857142858,
+      "epoch": 17.142857142857142,
       "eval_accuracy": 0.9444444444444444,
-      "eval_loss": 0.0950346514582634,
-      "eval_runtime": 0.5346,
-      "eval_samples_per_second": 67.341,
-      "eval_steps_per_second": 9.353,
+      "eval_loss": 0.08948543667793274,
+      "eval_runtime": 0.5801,
+      "eval_samples_per_second": 62.053,
+      "eval_steps_per_second": 8.619,
       "step": 30
     },
     {
-      "epoch": 19.857142857142858,
-      "step": 30,
-      "total_flos": 2.6297770138730496e+17,
-      "train_loss": 0.2961386869351069,
-      "train_runtime": 192.5285,
-      "train_samples_per_second": 7.791,
-      "train_steps_per_second": 0.156
+      "epoch": 20.0,
+      "step": 35,
+      "total_flos": 2.7941380772401152e+17,
+      "train_loss": 0.3405552021094731,
+      "train_runtime": 211.545,
+      "train_samples_per_second": 8.438,
+      "train_steps_per_second": 0.165
     }
   ],
   "logging_steps": 10,
-  "max_steps": 30,
+  "max_steps": 35,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 30,
+  "num_train_epochs": 35,
   "save_steps": 10,
   "stateful_callbacks": {
     "EarlyStoppingCallback": {
@@ -92,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.6297770138730496e+17,
+  "total_flos": 2.7941380772401152e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null