random_first_noditransitive_seed-42_1e-3

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

  • Loss: 3.4765
  • Accuracy: 0.3747

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
6.1723 0.9998 1495 4.6680 0.2657
4.6225 1.9997 2990 4.1969 0.3052
4.0268 2.9995 4485 3.9485 0.3257
3.8589 4.0 5981 3.7891 0.3402
3.631 4.9998 7476 3.6919 0.3500
3.5582 5.9997 8971 3.6250 0.3564
3.4406 6.9995 10466 3.5854 0.3608
3.4057 8.0 11962 3.5576 0.3640
3.3348 8.9998 13457 3.5365 0.3663
3.3147 9.9997 14952 3.5227 0.3682
3.2685 10.9995 16447 3.5096 0.3697
3.2552 12.0 17943 3.5064 0.3705
3.2239 12.9998 19438 3.4980 0.3716
3.2154 13.9997 20933 3.4910 0.3722
3.1913 14.9995 22428 3.4857 0.3729
3.1874 16.0 23924 3.4834 0.3736
3.1704 16.9998 25419 3.4794 0.3740
3.1669 17.9997 26914 3.4786 0.3743
3.1565 18.9995 28409 3.4768 0.3747
3.1505 19.9967 29900 3.4765 0.3747

Framework versions

  • Transformers 4.46.2
  • Pytorch 2.5.1+cu124
  • Datasets 3.2.0
  • Tokenizers 0.20.0
Downloads last month
12
Safetensors
Model size
0.1B params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Evaluation results