Edit model card

t5-small-ft-tr

This model is a fine-tuned version of google-t5/t5-small on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 3.3199

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: 4
  • eval_batch_size: 4
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 30

Training results

Training Loss Epoch Step Validation Loss
4.2085 1.0 1393 3.8282
3.9976 2.0 2786 3.7173
3.892 3.0 4179 3.6482
3.8259 4.0 5572 3.5999
3.7951 5.0 6965 3.5604
3.7541 6.0 8358 3.5299
3.7037 7.0 9751 3.5021
3.6603 8.0 11144 3.4786
3.6617 9.0 12537 3.4590
3.6191 10.0 13930 3.4417
3.6184 11.0 15323 3.4273
3.592 12.0 16716 3.4128
3.5782 13.0 18109 3.4017
3.5506 14.0 19502 3.3899
3.5519 15.0 20895 3.3798
3.5262 16.0 22288 3.3715
3.5087 17.0 23681 3.3651
3.509 18.0 25074 3.3558
3.5004 19.0 26467 3.3503
3.4775 20.0 27860 3.3449
3.4817 21.0 29253 3.3405
3.484 22.0 30646 3.3352
3.473 23.0 32039 3.3313
3.4625 24.0 33432 3.3292
3.4513 25.0 34825 3.3267
3.4564 26.0 36218 3.3239
3.4507 27.0 37611 3.3221
3.4385 28.0 39004 3.3211
3.452 29.0 40397 3.3202
3.4528 30.0 41790 3.3199

Framework versions

  • Transformers 4.43.4
  • Pytorch 1.13.1
  • Datasets 2.12.0
  • Tokenizers 0.19.1
Downloads last month
0
Safetensors
Model size
60.5M params
Tensor type
F32
·
Inference API
Unable to determine this model's library. Check the docs .

Model tree for aparajitha/t5-small-ft-tr

Base model

google-t5/t5-small
Finetuned
(1510)
this model