CoolFace
Modelpublic

srilekha27/english-telugu-colloquial-translator

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
0likes4downloads
Model Card

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

english-telugu-colloquial-translator

This model is a fine-tuned version of unsloth/mistral-7b-bnb-4bit on the None dataset. It achieves the following results on the evaluation set:

  • —Loss: 8.7783

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: 0.0003
  • —trainbatchsize: 4
  • —evalbatchsize: 4
  • —seed: 42
  • —optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
  • —lrschedulertype: linear
  • —num_epochs: 10
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation Loss
No log0.428.7783
No log0.848.7783
No log1.268.7783
No log1.688.7783
No log2.0108.7783
No log2.4128.7783
No log2.8148.7783
No log3.2168.7783
No log3.6188.7783
No log4.0208.7783
No log4.4228.7783
No log4.8248.7783
No log5.2268.7783
No log5.6288.7783
No log6.0308.7783
No log6.4328.7783
No log6.8348.7783
No log7.2368.7783
No log7.6388.7783
No log8.0408.7783
No log8.4428.7783
No log8.8448.7783
No log9.2468.7783
No log9.6488.7783
No log10.0508.7783

Framework versions

  • —PEFT 0.14.0
  • —Transformers 4.48.3
  • —Pytorch 2.6.0+cu124
  • —Datasets 3.3.1
  • —Tokenizers 0.21.0