noditrans_cf_seed-21_1e-3

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

  • Loss: 3.5127
  • Accuracy: 0.3628

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: 21
  • 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
6.0804 0.9999 1507 4.5211 0.2799
4.1312 1.9998 3014 4.0918 0.3113
3.9336 2.9998 4521 3.8782 0.3272
3.7 3.9997 6028 3.7471 0.3391
3.6094 4.9996 7535 3.6646 0.3459
3.5019 5.9995 9042 3.6233 0.3497
3.4403 6.9994 10549 3.5813 0.3543
3.3905 8.0 12057 3.5711 0.3552
3.3435 8.9999 13564 3.5508 0.3569
3.3235 9.9998 15071 3.5320 0.3595
3.2827 10.9998 16578 3.5402 0.3593
3.2784 11.9997 18085 3.5183 0.3613
3.2418 12.9996 19592 3.5320 0.3600
3.2468 13.9995 21099 3.5169 0.3614
3.2131 14.9994 22606 3.5156 0.3622
3.2253 16.0 24114 3.5136 0.3623
3.1932 16.9999 25621 3.5065 0.3627
3.2109 17.9998 27128 3.5170 0.3615
3.1806 18.9998 28635 3.5112 0.3627
3.2002 19.9983 30140 3.5127 0.3628

Framework versions

  • Transformers 4.46.2
  • Pytorch 2.5.1+cu124
  • Datasets 3.2.0
  • Tokenizers 0.20.0
Downloads last month
3
Safetensors
Model size
110M params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support