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-008
 
-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: 0.0935
 - Accuracy: 0.9722

all_results.json

@@ -1,13 +1,13 @@
 {
-    "epoch": 23.285714285714285,
+    "epoch": 19.857142857142858,
     "eval_accuracy": 0.9722222222222222,
-    "eval_loss": 0.07812394201755524,
-    "eval_runtime": 0.6106,
-    "eval_samples_per_second": 58.961,
-    "eval_steps_per_second": 8.189,
-    "total_flos": 3.068073182851891e+17,
-    "train_loss": 0.1982296261404242,
-    "train_runtime": 182.696,
-    "train_samples_per_second": 9.579,
-    "train_steps_per_second": 0.192
+    "eval_loss": 0.09350258857011795,
+    "eval_runtime": 1.1276,
+    "eval_samples_per_second": 31.927,
+    "eval_steps_per_second": 4.434,
+    "total_flos": 2.6297770138730496e+17,
+    "train_loss": 0.000703394537170728,
+    "train_runtime": 205.6889,
+    "train_samples_per_second": 7.293,
+    "train_steps_per_second": 0.146
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 23.285714285714285,
+    "epoch": 19.857142857142858,
     "eval_accuracy": 0.9722222222222222,
-    "eval_loss": 0.07812394201755524,
-    "eval_runtime": 0.6106,
-    "eval_samples_per_second": 58.961,
-    "eval_steps_per_second": 8.189
+    "eval_loss": 0.09350258857011795,
+    "eval_runtime": 1.1276,
+    "eval_samples_per_second": 31.927,
+    "eval_steps_per_second": 4.434
 }

runs/Nov13_17-27-56_de5729e0f5b3/events.out.tfevents.1731519223.de5729e0f5b3.318.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1848c49d65fed5dfdf9e2afbcbedd17af06437ee085cda2f8577a60092743bf3
+size 722

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 23.285714285714285,
-    "total_flos": 3.068073182851891e+17,
-    "train_loss": 0.1982296261404242,
-    "train_runtime": 182.696,
-    "train_samples_per_second": 9.579,
-    "train_steps_per_second": 0.192
+    "epoch": 19.857142857142858,
+    "total_flos": 2.6297770138730496e+17,
+    "train_loss": 0.000703394537170728,
+    "train_runtime": 205.6889,
+    "train_samples_per_second": 7.293,
+    "train_steps_per_second": 0.146
 }

trainer_state.json

@@ -1,75 +1,75 @@
 {
-  "best_metric": 0.07812394201755524,
-  "best_model_checkpoint": "vit-large-patch16-224-dungeon-geo-morphs-008/checkpoint-20",
-  "epoch": 23.285714285714285,
+  "best_metric": 0.09350258857011795,
+  "best_model_checkpoint": "vit-large-patch16-224-dungeon-geo-morphs-008/checkpoint-30",
+  "epoch": 19.857142857142858,
   "eval_steps": 10,
-  "global_step": 35,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 6.571428571428571,
-      "grad_norm": 10.188948631286621,
-      "learning_rate": 1.6774193548387098e-05,
-      "loss": 0.6526,
+      "grad_norm": 0.04094718024134636,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 0.0018,
       "step": 10
     },
     {
       "epoch": 6.571428571428571,
       "eval_accuracy": 0.9722222222222222,
-      "eval_loss": 0.1925116628408432,
-      "eval_runtime": 0.5168,
-      "eval_samples_per_second": 69.66,
-      "eval_steps_per_second": 9.675,
+      "eval_loss": 0.11066238582134247,
+      "eval_runtime": 0.505,
+      "eval_samples_per_second": 71.287,
+      "eval_steps_per_second": 9.901,
       "step": 10
     },
     {
       "epoch": 13.285714285714286,
-      "grad_norm": 0.3271343410015106,
-      "learning_rate": 1.0322580645161291e-05,
-      "loss": 0.0388,
+      "grad_norm": 0.009387318976223469,
+      "learning_rate": 3.7037037037037037e-06,
+      "loss": 0.0002,
       "step": 20
     },
     {
       "epoch": 13.285714285714286,
       "eval_accuracy": 0.9722222222222222,
-      "eval_loss": 0.07812394201755524,
-      "eval_runtime": 0.5529,
-      "eval_samples_per_second": 65.108,
-      "eval_steps_per_second": 9.043,
+      "eval_loss": 0.10644031316041946,
+      "eval_runtime": 0.5796,
+      "eval_samples_per_second": 62.117,
+      "eval_steps_per_second": 8.627,
       "step": 20
     },
     {
       "epoch": 19.857142857142858,
-      "grad_norm": 0.0802752748131752,
-      "learning_rate": 3.870967741935484e-06,
-      "loss": 0.002,
+      "grad_norm": 0.008829403668642044,
+      "learning_rate": 0.0,
+      "loss": 0.0001,
       "step": 30
     },
     {
       "epoch": 19.857142857142858,
       "eval_accuracy": 0.9722222222222222,
-      "eval_loss": 0.0781446322798729,
-      "eval_runtime": 0.5935,
-      "eval_samples_per_second": 60.658,
-      "eval_steps_per_second": 8.425,
+      "eval_loss": 0.09350258857011795,
+      "eval_runtime": 0.5948,
+      "eval_samples_per_second": 60.523,
+      "eval_steps_per_second": 8.406,
       "step": 30
     },
     {
-      "epoch": 23.285714285714285,
-      "step": 35,
-      "total_flos": 3.068073182851891e+17,
-      "train_loss": 0.1982296261404242,
-      "train_runtime": 182.696,
-      "train_samples_per_second": 9.579,
-      "train_steps_per_second": 0.192
+      "epoch": 19.857142857142858,
+      "step": 30,
+      "total_flos": 2.6297770138730496e+17,
+      "train_loss": 0.000703394537170728,
+      "train_runtime": 205.6889,
+      "train_samples_per_second": 7.293,
+      "train_steps_per_second": 0.146
     }
   ],
   "logging_steps": 10,
-  "max_steps": 35,
+  "max_steps": 30,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 35,
+  "num_train_epochs": 30,
   "save_steps": 10,
   "stateful_callbacks": {
     "EarlyStoppingCallback": {
@@ -78,7 +78,7 @@
         "early_stopping_threshold": 0.01
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -92,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.068073182851891e+17,
+  "total_flos": 2.6297770138730496e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null