default_small_seed-42_1e-3

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

  • Loss: 3.1784
  • Accuracy: 0.4011

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
6.0083 0.9999 1504 4.4027 0.2935
3.9458 1.9998 3008 3.8998 0.3328
3.7061 2.9998 4512 3.6210 0.3566
3.42 3.9997 6016 3.4579 0.3718
3.3145 4.9996 7520 3.3636 0.3807
3.1945 5.9995 9024 3.3015 0.3869
3.1291 6.9994 10528 3.2621 0.3907
3.0787 8.0 12033 3.2364 0.3931
3.0267 8.9999 13537 3.2173 0.3952
3.0071 9.9998 15041 3.2058 0.3963
2.9617 10.9998 16545 3.1959 0.3980
2.9593 11.9997 18049 3.1934 0.3984
2.9165 12.9996 19553 3.1903 0.3991
2.9253 13.9995 21057 3.1875 0.3999
2.8847 14.9994 22561 3.1806 0.4003
2.9012 16.0 24066 3.1807 0.4002
2.8647 16.9999 25570 3.1764 0.4009
2.886 17.9998 27074 3.1780 0.4010
2.8512 18.9998 28578 3.1777 0.4015
2.8765 19.9983 30080 3.1784 0.4011

Framework versions

  • Transformers 4.46.2
  • Pytorch 2.5.1+cu124
  • Datasets 3.2.0
  • Tokenizers 0.20.0
Downloads last month
-
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