5lang-sample_16epochs

This model is a fine-tuned version of google/byt5-small on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2553

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: 5e-05
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Use adamw_torch_fused 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: 500
  • num_epochs: 16

Training results

Training Loss Epoch Step Validation Loss
2.696 1.0 625 0.7126
0.7798 2.0 1250 0.5027
0.5664 3.0 1875 0.4304
0.4072 4.0 2500 0.3728
0.3556 5.0 3125 0.3360
0.3152 6.0 3750 0.3085
0.2783 7.0 4375 0.2828
0.2325 8.0 5000 0.2754
0.2119 9.0 5625 0.2718
0.1994 10.0 6250 0.2614
0.1884 11.0 6875 0.2586
0.1693 12.0 7500 0.2554
0.158 13.0 8125 0.2532
0.1562 14.0 8750 0.2559
0.1517 15.0 9375 0.2561
0.1475 16.0 10000 0.2553

Framework versions

  • Transformers 4.57.1
  • Pytorch 2.9.1+cu128
  • Datasets 4.4.1
  • Tokenizers 0.22.1
Downloads last month
3
Safetensors
Model size
0.3B params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for livles/5lang-sample_16epochs

Finetuned
(348)
this model