Training in progress, step 200

README.md

@@ -16,13 +16,6 @@ should probably proofread and complete it, then remove this comment. -->
 # daigram_detr_r50_albumentations
 
 This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) on the bpmn-shapes dataset.
-It achieves the following results on the evaluation set:
-- eval_loss: 4.1057
-- eval_runtime: 7.2682
-- eval_samples_per_second: 5.641
-- eval_steps_per_second: 0.826
-- epoch: 223.68
-- step: 4250
 
 ## Model description
 
@@ -51,7 +44,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.34.0
+- Transformers 4.34.1
 - Pytorch 2.0.1+cu118
 - Datasets 2.14.5
 - Tokenizers 0.14.1

config.json

@@ -58,7 +58,7 @@
   "position_embedding_type": "sine",
   "scale_embedding": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.34.0",
+  "transformers_version": "4.34.1",
   "use_pretrained_backbone": true,
   "use_timm_backbone": true
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87a6dd338dcf06fd17d01c14a61722e06d445f519bd644ff986c4e21c19de868
+oid sha256:679b121e8623be1fcffece61695ec93b6d8215597bae834320e76ff8ae1e09b8
 size 166620821

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:006b4afadc225a061e920d9eee10b78851c9f6c55f52d40708ac333e84c1365a
+oid sha256:a18794d9feda564befea04a2ba9d3ab025ad4007a5238b6bf62fbadac86999bd
 size 4091