CoolFace
Modelpublic

smangrul/tinyllama_lora_adcopy

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face
0likes51downloads
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. -->

tinyllamaloraadcopy

This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T on an unknown dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.8992

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: 0.0005
  • —trainbatchsize: 8
  • —evalbatchsize: 8
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: cosine
  • —lrschedulerwarmup_ratio: 0.1
  • —num_epochs: 10
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation Loss
0.93861.01290.8662
0.78212.02580.7954
0.52693.03870.7621
0.41214.05160.7183
0.21695.06450.7358
0.12066.07740.7757
0.0577.09030.8003
0.02918.010320.8342
0.00979.011610.8800
0.007710.012900.8992

Framework versions

  • —PEFT 0.7.2.dev0
  • —Transformers 4.37.0.dev0
  • —Pytorch 2.1.2+cu121
  • —Datasets 2.15.0
  • —Tokenizers 0.15.0