qing-yao's picture
Model save
574b40f verified
|
raw
history blame
2.58 kB
metadata
library_name: transformers
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: baseline_seed-42_1e-3
    results: []

baseline_seed-42_1e-3

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 3.1495
  • Accuracy: 0.4121

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: 32
  • eval_batch_size: 64
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 32000
  • num_epochs: 20.0
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy
3.6536 1.0 17459 3.6063 0.3536
3.4313 2.0 34918 3.3959 0.3757
3.2641 3.0 52377 3.2704 0.3901
3.1763 4.0 69836 3.2136 0.3968
3.1125 5.0 87295 3.1768 0.4015
3.0607 6.0 104754 3.1599 0.4039
3.0231 7.0 122213 3.1423 0.4063
2.986 8.0 139672 3.1343 0.4077
2.9519 9.0 157131 3.1277 0.4090
2.9272 10.0 174590 3.1228 0.4100
2.9034 11.0 192049 3.1221 0.4106
2.8763 12.0 209508 3.1221 0.4111
2.851 13.0 226967 3.1256 0.4114
2.8383 14.0 244426 3.1238 0.4119
2.8084 15.0 261885 3.1268 0.4121
2.7877 16.0 279344 3.1320 0.4121
2.7651 17.0 296803 3.1339 0.4122
2.7424 18.0 314262 3.1409 0.4121
2.7208 19.0 331721 3.1441 0.4121
2.7009 20.0 349180 3.1495 0.4121

Framework versions

  • Transformers 4.45.1
  • Pytorch 2.4.1+cu121
  • Datasets 2.19.1
  • Tokenizers 0.20.0