AaRaBiNoZa's picture
End of training
e73c489 verified
metadata
tags:
  - generated_from_trainer
model-index:
  - name: calculator_model_test
    results: []

calculator_model_test

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

  • Loss: 0.8108

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: 0.001
  • train_batch_size: 512
  • eval_batch_size: 512
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 40

Training results

Training Loss Epoch Step Validation Loss
3.3648 1.0 6 2.7465
2.3708 2.0 12 2.0172
1.8554 3.0 18 1.7507
1.6599 4.0 24 1.6101
1.5513 5.0 30 1.6004
1.5494 6.0 36 1.5314
1.5147 7.0 42 1.6012
1.5361 8.0 48 1.9344
1.5928 9.0 54 1.5257
1.5114 10.0 60 1.5045
1.457 11.0 66 1.4829
1.4053 12.0 72 1.4635
1.4049 13.0 78 1.4393
1.4052 14.0 84 1.3878
1.3437 15.0 90 1.3503
1.3226 16.0 96 1.3059
1.2817 17.0 102 1.2379
1.2255 18.0 108 1.1771
1.1717 19.0 114 1.2811
1.2039 20.0 120 1.3512
1.2312 21.0 126 1.2075
1.1481 22.0 132 1.0787
1.091 23.0 138 1.0809
1.0598 24.0 144 1.0479
1.0649 25.0 150 1.0148
1.0172 26.0 156 1.0194
1.0004 27.0 162 0.9618
0.9639 28.0 168 0.9565
0.9461 29.0 174 0.9197
0.9112 30.0 180 0.9280
0.9397 31.0 186 0.8850
0.8829 32.0 192 0.8936
0.8869 33.0 198 0.9086
0.8956 34.0 204 0.8656
0.8672 35.0 210 0.8579
0.8427 36.0 216 0.8305
0.8538 37.0 222 0.8312
0.83 38.0 228 0.8179
0.8411 39.0 234 0.8124
0.8238 40.0 240 0.8108

Framework versions

  • Transformers 4.38.1
  • Pytorch 2.1.0+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2