End of training
Browse files
README.md
CHANGED
|
@@ -14,8 +14,6 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
# detr-resnet-50_finetuned_swny
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) on an unknown dataset.
|
| 17 |
-
It achieves the following results on the evaluation set:
|
| 18 |
-
- Loss: 1.7504
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
@@ -40,38 +38,15 @@ The following hyperparameters were used during training:
|
|
| 40 |
- seed: 42
|
| 41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
- lr_scheduler_type: linear
|
| 43 |
-
- num_epochs:
|
| 44 |
|
| 45 |
### Training results
|
| 46 |
|
| 47 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
-
|:-------------:|:-------:|:----:|:---------------:|
|
| 49 |
-
| 5.6587 | 4.7619 | 100 | 5.5964 |
|
| 50 |
-
| 4.3793 | 9.5238 | 200 | 3.8578 |
|
| 51 |
-
| 3.4828 | 14.2857 | 300 | 3.2121 |
|
| 52 |
-
| 2.8371 | 19.0476 | 400 | 2.6974 |
|
| 53 |
-
| 2.3745 | 23.8095 | 500 | 2.3697 |
|
| 54 |
-
| 2.0983 | 28.5714 | 600 | 2.0374 |
|
| 55 |
-
| 1.995 | 33.3333 | 700 | 2.0759 |
|
| 56 |
-
| 1.8153 | 38.0952 | 800 | 1.9295 |
|
| 57 |
-
| 1.7984 | 42.8571 | 900 | 1.8945 |
|
| 58 |
-
| 1.6725 | 47.6190 | 1000 | 1.8271 |
|
| 59 |
-
| 1.5961 | 52.3810 | 1100 | 1.8709 |
|
| 60 |
-
| 1.5454 | 57.1429 | 1200 | 1.8674 |
|
| 61 |
-
| 1.4977 | 61.9048 | 1300 | 1.8333 |
|
| 62 |
-
| 1.4575 | 66.6667 | 1400 | 1.8387 |
|
| 63 |
-
| 1.4784 | 71.4286 | 1500 | 1.8334 |
|
| 64 |
-
| 1.4698 | 76.1905 | 1600 | 1.7419 |
|
| 65 |
-
| 1.4335 | 80.9524 | 1700 | 1.8332 |
|
| 66 |
-
| 1.394 | 85.7143 | 1800 | 1.8329 |
|
| 67 |
-
| 1.3992 | 90.4762 | 1900 | 1.7304 |
|
| 68 |
-
| 1.3951 | 95.2381 | 2000 | 1.6899 |
|
| 69 |
-
| 1.3984 | 100.0 | 2100 | 1.7504 |
|
| 70 |
|
| 71 |
|
| 72 |
### Framework versions
|
| 73 |
|
| 74 |
-
- Transformers 4.41.
|
| 75 |
- Pytorch 2.3.0+cu121
|
| 76 |
- Datasets 2.19.1
|
| 77 |
- Tokenizers 0.19.1
|
|
|
|
| 14 |
# detr-resnet-50_finetuned_swny
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) on an unknown dataset.
|
|
|
|
|
|
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
|
|
| 38 |
- seed: 42
|
| 39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 40 |
- lr_scheduler_type: linear
|
| 41 |
+
- num_epochs: 510
|
| 42 |
|
| 43 |
### Training results
|
| 44 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
|
| 46 |
|
| 47 |
### Framework versions
|
| 48 |
|
| 49 |
+
- Transformers 4.41.1
|
| 50 |
- Pytorch 2.3.0+cu121
|
| 51 |
- Datasets 2.19.1
|
| 52 |
- Tokenizers 0.19.1
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 166657288
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5730540dd4b94ac4c4edda6175975a91ed1147f44863dc85d62e6750be28d50c
|
| 3 |
size 166657288
|
runs/Jun02_20-55-44_b35b9e50cd49/events.out.tfevents.1717361745.b35b9e50cd49.2917.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a7e414c7d9b4471f0cf085b9e44f3e591d4059472f03074e265a1b279dd1796
|
| 3 |
+
size 54797
|