random_first_datives_seed-42_1e-3

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

  • Loss: 3.3644
  • Accuracy: 0.3778

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
6.2642 1.0 1731 4.5519 0.2722
4.3675 2.0 3462 4.0802 0.3075
3.9677 3.0 5193 3.8310 0.3286
3.832 4.0 6924 3.6886 0.3424
3.6544 5.0 8655 3.6002 0.3507
3.5548 6.0 10386 3.5555 0.3547
3.4849 7.0 12117 3.5217 0.3581
3.4337 8.0 13848 3.4956 0.3609
3.3926 9.0 15579 3.4885 0.3620
3.37 10.0 17310 3.4666 0.3640
3.3518 11.0 19041 3.4662 0.3643
3.3042 12.0 20772 3.4562 0.3655
3.2997 13.0 22503 3.4451 0.3669
3.2979 14.0 24234 3.4461 0.3671
3.2648 15.0 25965 3.4455 0.3669
3.2516 16.0 27696 3.4412 0.3674
3.264 17.0 29427 3.4405 0.3675
3.271 18.0 31158 3.4360 0.3676
3.2386 19.0 32889 3.4024 0.3719
3.1078 20.0 34620 3.3644 0.3778

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