sumitD/table-transformer-structure-recognition-v1.1-all-finetuned

README.md

@@ -15,6 +15,37 @@ should probably proofread and complete it, then remove this comment. -->
 # table-transformer-structure-recognition-v1.1-all-finetuned
 
 This model is a fine-tuned version of [microsoft/table-transformer-structure-recognition-v1.1-all](https://huggingface.co/microsoft/table-transformer-structure-recognition-v1.1-all) on the None dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 0.1912
+- eval_map: 0.8766
+- eval_map_50: 0.9434
+- eval_map_75: 0.9207
+- eval_map_small: -1.0
+- eval_map_medium: 0.6345
+- eval_map_large: 0.8754
+- eval_mar_1: 0.5409
+- eval_mar_10: 0.9214
+- eval_mar_100: 0.9519
+- eval_mar_small: -1.0
+- eval_mar_medium: 0.7107
+- eval_mar_large: 0.9517
+- eval_map_table: 0.9823
+- eval_mar_100_table: 0.9921
+- eval_map_table column: 0.957
+- eval_mar_100_table column: 0.9789
+- eval_map_table column header: 0.9225
+- eval_mar_100_table column header: 0.9648
+- eval_map_table projected row header: 0.7332
+- eval_mar_100_table projected row header: 0.9478
+- eval_map_table row: 0.9386
+- eval_mar_100_table row: 0.9734
+- eval_map_table spanning cell: 0.7258
+- eval_mar_100_table spanning cell: 0.8543
+- eval_runtime: 153.5358
+- eval_samples_per_second: 618.481
+- eval_steps_per_second: 19.331
+- epoch: 2.0
+- step: 47430
 
 ## Model description
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2add4ed387f250a330e2b5706faca3662825e4106cd6102a941f4431902f0d7
+oid sha256:5d50079bbe4187ad550d3ebcc0b3fbd0e5bc6469d985026a9419f21daddaf3f8
 size 115437156