Edit model card

umt5-small-finetuned-umt5-poemV1

This model is a fine-tuned version of google/umt5-small on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: nan

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: 2e-05
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
No log 1.0 282 nan
0.0 2.0 564 nan
0.0 3.0 846 nan
0.0 4.0 1128 nan
0.0 5.0 1410 nan
0.0 6.0 1692 nan
0.0 7.0 1974 nan
0.0 8.0 2256 nan
0.0 9.0 2538 nan
0.0 10.0 2820 nan

Framework versions

  • Transformers 4.40.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1
Downloads last month
2
Safetensors
Model size
307M params
Tensor type
F32
·
Inference API
This model can be loaded on Inference API (serverless).

Finetuned from