kinzoku99's picture
End of training
e38d8c5 verified
|
raw
history blame
No virus
3.2 kB
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: 0.9144

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
3.3969 1.0 6 2.7182
2.3315 2.0 12 1.9518
1.7958 3.0 18 1.6778
1.6131 4.0 24 1.5845
1.5584 5.0 30 1.5760
1.548 6.0 36 1.5781
1.5369 7.0 42 1.5516
1.5412 8.0 48 1.6085
1.5311 9.0 54 1.5398
1.5435 10.0 60 1.5587
1.5138 11.0 66 1.5452
1.5192 12.0 72 1.5345
1.4818 13.0 78 1.6037
1.4935 14.0 84 1.5391
1.4396 15.0 90 1.8690
1.4801 16.0 96 1.4349
1.4051 17.0 102 1.3765
1.3563 18.0 108 1.3655
1.3188 19.0 114 1.3211
1.3023 20.0 120 1.2695
1.259 21.0 126 1.2644
1.2366 22.0 132 1.2287
1.2252 23.0 138 1.1858
1.2205 24.0 144 1.1587
1.1593 25.0 150 1.1855
1.1639 26.0 156 1.1943
1.1617 27.0 162 1.1305
1.1493 28.0 168 1.0901
1.1031 29.0 174 1.0640
1.0901 30.0 180 1.0242
1.0582 31.0 186 1.0066
1.0423 32.0 192 0.9996
1.0239 33.0 198 0.9732
1.0151 34.0 204 0.9871
1.0452 35.0 210 0.9655
1.009 36.0 216 0.9411
0.9819 37.0 222 0.9342
0.9773 38.0 228 0.9235
0.9743 39.0 234 0.9175
0.9722 40.0 240 0.9144

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.1.1+cu121
  • Datasets 2.17.1
  • Tokenizers 0.15.2