Upload RT-DETRv2 voucher classifier

README.md

@@ -58,32 +58,21 @@ This model is a fine-tuned version of [PekingU/rtdetr_v2_r101vd](https://hugging
 
 ### Performance Metrics
 
+**Metric Definitions:**
+
+- **mAP (mean Average Precision)**: Overall performance metric averaged across all classes and IoU thresholds (0.0-1.0, higher is better)
+- **mAP@50**: mAP calculated at IoU threshold 0.5 - more lenient, measures if objects are found in roughly correct location  
+- **mAP@75**: mAP calculated at IoU threshold 0.75 - more strict, requires precise bounding box localization
+- **IoU (Intersection over Union)**: Overlap between predicted and ground truth bounding boxes
+
+**Performance Ranges:**
+- 0.9+: Excellent
+- 0.8-0.9: Very Good  
+- 0.7-0.8: Good
+- 0.5-0.7: Fair
+- <0.5: Poor (needs improvement)
+
 **Final Evaluation Results:**
-**Overall Detection Performance:**
-- **mAP**: 0.0000
-- **mAP@50**: 0.0000
-- **mAP@75**: 0.0000
-
-**Per-Class Average Precision:**
-- **Digital invoices**: 0.0000 (needs improvement)
-- **Fisico receipts**: 0.0000 (needs improvement)
-- **Tesoreria receipts**: 0.0000 (needs improvement)
-
-**Model Confidence:**
-- **Digital invoices mean confidence**: 0.7044 (moderate)
-- **Fisico receipts mean confidence**: 0.5937 (low)
-- **Tesoreria receipts mean confidence**: 0.5683 (low)
-
-**Performance by Object Size:**
-- **Small objects**: 0.0000
-- **Medium objects**: -1.0000
-- **Large objects**: 0.0000
-
-**Evaluation Dataset:**
-- **Digital invoices**: 157 samples (28.5%)
-- **Fisico receipts**: 261 samples (47.4%)
-- **Tesoreria receipts**: 133 samples (24.1%)
-- **Total evaluation samples**: 551
 
 **Model Configuration:**
 - **Base model**: PekingU/rtdetr_v2_r101vd
@@ -98,15 +87,15 @@ This model is a fine-tuned version of [PekingU/rtdetr_v2_r101vd](https://hugging
 - **RAM**: 83.5 GB
 - **GPU configuration**: A100 optimized
 
-**Training Time**: 0.0 minutes
+**Training Time**: 0.6 minutes
 
 **Training Summary:**
-- **Final training loss**: 0.0000
+- **Final training loss**: 1361.9480
 
 
 ### MLflow Tracking
 
-- **MLflow Run ID**: b7fca7191e0c4de6883f809c8d3f4e0c
+- **MLflow Run ID**: 65eb62e7fd564f99981143809773def8
 - **MLflow Experiment**: RT-DETRv2_Voucher_Classification
 
 

checkpoint-22/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69b28fe57a922174a0ca53143ea940ed65381a18183eb24b9e30c384d25ab987
+oid sha256:41bcea9c8faca4547536af694dd5ad4a304153763de5c5d40387fb9d71bedb70
 size 306699044

checkpoint-22/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bcad52220dd23a1885b5af2e16f71a71179b5d33098b7fd435dfcae79ae9b5a
+oid sha256:443919119e128db40e45a79d6a18a299f9ef64236143bc3b0a00dc2b02f890c4
 size 611580433

checkpoint-22/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e283f3b7429fe38aad89505a2aceea49c6a5d524038138df0c101fb544e9aac
+oid sha256:ee47b52e482bd2dc4e70d1d92d8db4b33fc8cc8bb349a91709c9f357b574e2d1
 size 5368

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69b28fe57a922174a0ca53143ea940ed65381a18183eb24b9e30c384d25ab987
+oid sha256:41bcea9c8faca4547536af694dd5ad4a304153763de5c5d40387fb9d71bedb70
 size 306699044

runs/Aug14_00-08-42_9db0f8c974d2/events.out.tfevents.1755130123.9db0f8c974d2.91164.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98d25d95362299af66d8224db094bd64647151b9f37e98fed010630d17a98975
+size 7402

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f43a86a855e867f8fe16e877dace7e2697fb959d7d8b2bd57cbf3aba3493ead
+oid sha256:ee47b52e482bd2dc4e70d1d92d8db4b33fc8cc8bb349a91709c9f357b574e2d1
 size 5368