umt5-base-quechua-espanol-finetuned-model-v2

This model is a fine-tuned version of google/umt5-base on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.4914

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: 0.0002
  • train_batch_size: 22
  • eval_batch_size: 4
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: constant
  • num_epochs: 2

Training results

Training Loss Epoch Step Validation Loss
3.0956 0.2259 1000 2.5133
2.5227 0.4518 2000 2.1119
2.2631 0.6777 3000 1.8845
2.0653 0.9035 4000 1.7568
1.899 1.1294 5000 1.6684
1.8405 1.3553 6000 1.5924
1.7622 1.5812 7000 1.5415
1.7167 1.8071 8000 1.4914

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1
Downloads last month
98
Safetensors
Model size
592M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for ignaciovillanueva/umt5-base-quechua-espanol-finetuned-model-v2

Base model

google/umt5-base
Finetuned
(7)
this model