nodative_cf_seed-42_1e-3

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

  • Loss: 3.1523
  • Accuracy: 0.4041

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
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 256
  • optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • 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
6.0249 0.9998 1490 4.3937 0.2955
4.3282 1.9997 2980 3.8788 0.3354
3.6854 2.9995 4470 3.5978 0.3592
3.5059 4.0 5961 3.4388 0.3741
3.2809 4.9998 7451 3.3407 0.3833
3.2045 5.9997 8941 3.2826 0.3889
3.0978 6.9995 10431 3.2422 0.3927
3.0597 8.0 11922 3.2173 0.3956
2.9976 8.9998 13412 3.2001 0.3977
2.9746 9.9997 14902 3.1847 0.3986
2.9359 10.9995 16392 3.1759 0.4004
2.9174 12.0 17883 3.1750 0.4005
2.8938 12.9998 19373 3.1686 0.4015
2.8805 13.9997 20863 3.1650 0.4021
2.8649 14.9995 22353 3.1609 0.4027
2.8544 16.0 23844 3.1605 0.4027
2.8457 16.9998 25334 3.1597 0.4032
2.8338 17.9997 26824 3.1591 0.4032
2.8332 18.9995 28314 3.1558 0.4036
2.8205 19.9966 29800 3.1523 0.4041

Framework versions

  • Transformers 4.46.2
  • Pytorch 2.5.1+cu124
  • Datasets 3.2.0
  • Tokenizers 0.20.0
Downloads last month
1
Safetensors
Model size
0.1B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support