End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: facebook/detr-resnet-50-dc5
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: detr-resnet-50-dc5-fashionpedia-finetuned
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# detr-resnet-50-dc5-fashionpedia-finetuned
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [facebook/detr-resnet-50-dc5](https://huggingface.co/facebook/detr-resnet-50-dc5) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 3.2904
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 1e-05
|
| 39 |
+
- train_batch_size: 4
|
| 40 |
+
- eval_batch_size: 4
|
| 41 |
+
- seed: 42
|
| 42 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 43 |
+
- lr_scheduler_type: linear
|
| 44 |
+
- training_steps: 1000
|
| 45 |
+
- mixed_precision_training: Native AMP
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 51 |
+
| 4.7281 | 0.0438 | 50 | 4.3705 |
|
| 52 |
+
| 3.9353 | 0.0876 | 100 | 4.0499 |
|
| 53 |
+
| 4.5369 | 0.1315 | 150 | 3.8890 |
|
| 54 |
+
| 3.9156 | 0.1753 | 200 | 3.7630 |
|
| 55 |
+
| 3.6006 | 0.2191 | 250 | 3.6861 |
|
| 56 |
+
| 3.6562 | 0.2629 | 300 | 3.6110 |
|
| 57 |
+
| 3.7636 | 0.3067 | 350 | 3.5906 |
|
| 58 |
+
| 4.0293 | 0.3506 | 400 | 3.5405 |
|
| 59 |
+
| 3.533 | 0.3944 | 450 | 3.4906 |
|
| 60 |
+
| 3.1302 | 0.4382 | 500 | 3.4249 |
|
| 61 |
+
| 3.8257 | 0.4820 | 550 | 3.3910 |
|
| 62 |
+
| 2.9622 | 0.5259 | 600 | 3.3622 |
|
| 63 |
+
| 3.9213 | 0.5697 | 650 | 3.3310 |
|
| 64 |
+
| 4.4062 | 0.6135 | 700 | 3.3303 |
|
| 65 |
+
| 4.3076 | 0.6573 | 750 | 3.3105 |
|
| 66 |
+
| 4.0868 | 0.7011 | 800 | 3.3040 |
|
| 67 |
+
| 4.0639 | 0.7450 | 850 | 3.3076 |
|
| 68 |
+
| 4.7454 | 0.7888 | 900 | 3.2996 |
|
| 69 |
+
| 4.3044 | 0.8326 | 950 | 3.2935 |
|
| 70 |
+
| 3.9519 | 0.8764 | 1000 | 3.2904 |
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
### Framework versions
|
| 74 |
+
|
| 75 |
+
- Transformers 4.51.0
|
| 76 |
+
- Pytorch 2.6.0+cu124
|
| 77 |
+
- Datasets 3.5.0
|
| 78 |
+
- Tokenizers 0.21.1
|