chickens / README.md
joe611's picture
End of training
46ca4b1 verified
|
raw
history blame
2.79 kB
metadata
library_name: transformers
license: apache-2.0
base_model: facebook/detr-resnet-50
tags:
  - generated_from_trainer
model-index:
  - name: chickens
    results: []

chickens

This model is a fine-tuned version of facebook/detr-resnet-50 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3492

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 5e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • num_epochs: 30

Training results

Training Loss Epoch Step Validation Loss
No log 1.0 13 1.0881
No log 2.0 26 0.9358
1.0365 3.0 39 0.9215
1.0365 4.0 52 0.9268
0.9112 5.0 65 0.9596
0.9112 6.0 78 0.7592
0.8322 7.0 91 0.8089
0.8322 8.0 104 0.6614
0.8322 9.0 117 0.6783
0.6855 10.0 130 0.7351
0.6855 11.0 143 0.5850
0.6472 12.0 156 0.6359
0.6472 13.0 169 0.5550
0.6054 14.0 182 0.6118
0.6054 15.0 195 0.5439
0.6054 16.0 208 0.4656
0.5285 17.0 221 0.5055
0.5285 18.0 234 0.4901
0.5045 19.0 247 0.4484
0.5045 20.0 260 0.4110
0.4543 21.0 273 0.4308
0.4543 22.0 286 0.3917
0.4543 23.0 299 0.3521
0.434 24.0 312 0.3937
0.434 25.0 325 0.3454
0.4099 26.0 338 0.3603
0.4099 27.0 351 0.3589
0.3998 28.0 364 0.3548
0.3998 29.0 377 0.3474
0.3945 30.0 390 0.3492

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.1+cu121
  • Datasets 2.14.4
  • Tokenizers 0.19.1