chickens / README.md
joe611's picture
End of training
306ecf2 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: 0.2124

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 23 0.9087
1.1031 2.0 46 0.8311
0.9027 3.0 69 0.6971
0.7561 4.0 92 0.5537
0.7561 5.0 115 0.4770
0.6238 6.0 138 0.4349
0.5385 7.0 161 0.3924
0.4759 8.0 184 0.3603
0.4759 9.0 207 0.3261
0.4367 10.0 230 0.3306
0.4199 11.0 253 0.3442
0.3988 12.0 276 0.2995
0.3988 13.0 299 0.3219
0.3887 14.0 322 0.2768
0.3808 15.0 345 0.2574
0.3673 16.0 368 0.2715
0.3354 17.0 391 0.3126
0.3354 18.0 414 0.2536
0.3347 19.0 437 0.2362
0.3287 20.0 460 0.2539
0.3325 21.0 483 0.2341
0.3325 22.0 506 0.2173
0.3196 23.0 529 0.2180
0.3091 24.0 552 0.2166
0.3111 25.0 575 0.2264
0.3111 26.0 598 0.2070
0.2983 27.0 621 0.2177
0.2946 28.0 644 0.2080
0.3068 29.0 667 0.2113
0.2933 30.0 690 0.2124

Framework versions

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