CoolFace
Modelpublic

yahyaahmed/tinyllama-lora-squad_4_3e-05_2_lora4_qk

sourceHugging Faceapache-2.0updated 1y agoView on Hugging Face
0likes14downloads
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. -->

tinyllama-lora-squad43e-052lora4_qk

This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-Chat-v1.0 on an unknown dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.0071

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: 3e-05
  • —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
  • —lrschedulerwarmup_steps: 100
  • —num_epochs: 2
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation Loss
3.68450.19984950.0120
0.01060.39959900.0097
0.00910.599314850.0088
0.00840.799019800.0080
0.00740.998824750.0077
0.00671.198529700.0076
0.00651.398334650.0073
0.00641.598139600.0072
0.00671.797844550.0071
0.00651.997649500.0071

Framework versions

  • —PEFT 0.16.0
  • —Transformers 4.53.2
  • —Pytorch 2.6.0+cu124
  • —Datasets 4.0.0
  • —Tokenizers 0.21.2