End of training

README.md

@@ -3,6 +3,8 @@ library_name: transformers
 license: other
 base_model: nvidia/mit-b0
 tags:
+- image-segmentation
+- vision
 - generated_from_trainer
 model-index:
 - name: segformer-finetuned-tt-1000-2k
@@ -14,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # segformer-finetuned-tt-1000-2k
 
-This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on an unknown dataset.
+This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the Saumya-Mundra/text255 dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.1042
 - Mean Iou: 0.4902

all_results.json

@@ -1,19 +1,19 @@
 {
-    "epoch": 16.0,
-    "eval_accuracy_no_text": 0.9789534698341376,
+    "epoch": 160.0,
+    "eval_accuracy_no_text": 0.9804176340737537,
     "eval_accuracy_text": NaN,
-    "eval_iou_no_text": 0.9789534698341376,
+    "eval_iou_no_text": 0.9804176340737537,
     "eval_iou_text": 0.0,
-    "eval_loss": 0.09761390835046768,
-    "eval_mean_accuracy": 0.9789534698341376,
-    "eval_mean_iou": 0.4894767349170688,
-    "eval_overall_accuracy": 0.9789534698341376,
-    "eval_runtime": 8.2529,
-    "eval_samples_per_second": 30.777,
-    "eval_steps_per_second": 3.877,
-    "total_flos": 2.80447288344576e+17,
-    "train_loss": 0.1418005952835083,
-    "train_runtime": 624.6204,
-    "train_samples_per_second": 25.616,
-    "train_steps_per_second": 3.202
+    "eval_loss": 0.10416771471500397,
+    "eval_mean_accuracy": 0.9804176340737537,
+    "eval_mean_iou": 0.49020881703687685,
+    "eval_overall_accuracy": 0.9804176340737537,
+    "eval_runtime": 8.3583,
+    "eval_samples_per_second": 30.389,
+    "eval_steps_per_second": 3.829,
+    "total_flos": 2.80447288344576e+18,
+    "train_loss": 0.01519945946931839,
+    "train_runtime": 1952.9271,
+    "train_samples_per_second": 81.928,
+    "train_steps_per_second": 10.241
 }

eval_results.json

@@ -1,14 +1,14 @@
 {
-    "epoch": 16.0,
-    "eval_accuracy_no_text": 0.9789534698341376,
+    "epoch": 160.0,
+    "eval_accuracy_no_text": 0.9804176340737537,
     "eval_accuracy_text": NaN,
-    "eval_iou_no_text": 0.9789534698341376,
+    "eval_iou_no_text": 0.9804176340737537,
     "eval_iou_text": 0.0,
-    "eval_loss": 0.09761390835046768,
-    "eval_mean_accuracy": 0.9789534698341376,
-    "eval_mean_iou": 0.4894767349170688,
-    "eval_overall_accuracy": 0.9789534698341376,
-    "eval_runtime": 8.2529,
-    "eval_samples_per_second": 30.777,
-    "eval_steps_per_second": 3.877
+    "eval_loss": 0.10416771471500397,
+    "eval_mean_accuracy": 0.9804176340737537,
+    "eval_mean_iou": 0.49020881703687685,
+    "eval_overall_accuracy": 0.9804176340737537,
+    "eval_runtime": 8.3583,
+    "eval_samples_per_second": 30.389,
+    "eval_steps_per_second": 3.829
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 16.0,
-    "total_flos": 2.80447288344576e+17,
-    "train_loss": 0.1418005952835083,
-    "train_runtime": 624.6204,
-    "train_samples_per_second": 25.616,
-    "train_steps_per_second": 3.202
+    "epoch": 160.0,
+    "total_flos": 2.80447288344576e+18,
+    "train_loss": 0.01519945946931839,
+    "train_runtime": 1952.9271,
+    "train_samples_per_second": 81.928,
+    "train_steps_per_second": 10.241
 }