rel-cl-lstm-3

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

  • Loss: 3.9834

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: 32
  • eval_batch_size: 32
  • seed: 3
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • training_steps: 3052726

Training results

Training Loss Epoch Step Validation Loss
4.8333 0.03 76319 4.7955
4.5414 1.03 152638 4.5069
4.3958 0.03 228957 4.3693
4.3064 1.03 305276 4.2841
4.2412 0.03 381595 4.2253
4.1888 1.03 457914 4.1822
4.1518 0.03 534233 4.1503
4.1231 1.03 610552 4.1251
4.0901 0.03 686871 4.1043
4.0684 1.03 763190 4.0883
4.0494 0.03 839509 4.0748
4.0311 1.03 915828 4.0629
4.0094 0.03 992147 4.0531
3.9984 1.03 1068466 4.0447
3.9843 0.03 1144785 4.0374
3.9745 1.03 1221104 4.0315
3.9639 0.03 1297424 4.0246
3.9518 1.03 1373744 4.0196
3.9425 0.03 1450064 4.0152
3.9366 1.03 1526384 4.0120
3.9314 0.03 1602704 4.0092
3.9281 1.03 1679024 4.0062
3.9248 0.03 1755344 4.0037
3.9168 1.03 1831664 4.0010
3.9081 0.03 1907984 3.9989
3.9019 1.03 1984304 3.9969
3.8948 0.03 2060624 3.9948
3.891 1.03 2136944 3.9935
3.8871 0.03 2213264 3.9923
3.8802 1.03 2289584 3.9913
3.8797 0.03 2365904 3.9902
3.8769 1.03 2442224 3.9892
3.8733 0.03 2518544 3.9886
3.8671 1.03 2594864 3.9875
3.8637 0.03 2671184 3.9867
3.8642 1.03 2747504 3.9858
3.8642 0.03 2823824 3.9848
3.8653 1.03 2900144 3.9842
3.8671 0.03 2976464 3.9836
3.8639 0.02 3052726 3.9834

Framework versions

  • Transformers 4.33.3
  • Pytorch 2.0.1
  • Datasets 2.12.0
  • Tokenizers 0.13.3
Downloads last month
36
Inference API
Unable to determine this model’s pipeline type. Check the docs .