CoolFace
Modelpublic

DeGrimer/finetune_rag_t_lite

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. -->

tmp

This model is a fine-tuned version of t-bank-ai/T-lite-instruct-0.1 on an unknown dataset. It achieves the following results on the evaluation set:

  • —Loss: 1.0736

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: 8e-06
  • —trainbatchsize: 1
  • —evalbatchsize: 1
  • —seed: 42
  • —gradientaccumulationsteps: 2
  • —totaltrainbatch_size: 2
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 3
  • —training_steps: 20

Training results

Training LossEpochStepValidation Loss
1.06580.000211.0817
0.94320.000421.0814
1.10060.000631.0809
0.88380.000841.0801
1.15280.001051.0793
0.88890.001261.0786
1.16550.001471.0780
1.00790.001681.0774
1.16850.001891.0768
1.16590.0020101.0763
1.13950.0022111.0758
0.94260.0024121.0753
0.97720.0026131.0750
1.37580.0028141.0746
0.70220.0030151.0743
1.57610.0032161.0741
1.28470.0034171.0739
1.15280.0036181.0737
0.83620.0038191.0736
0.90960.0040201.0736

Framework versions

  • —PEFT 0.13.2
  • —Transformers 4.45.2
  • —Pytorch 2.4.0
  • —Datasets 3.0.1
  • —Tokenizers 0.20.0