CoolFace
Modelpublic

RichardErkhov/danielgombas_-_llama_1b_step2_batch_grad_v5-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes773downloads
Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama1bstep2batchgrad_v5 - GGUF

  • —Model creator: https://huggingface.co/danielgombas/
  • —Original model: https://huggingface.co/danielgombas/llama1bstep2batchgrad_v5/

Original model description: --- library_name: transformers tags:

  • —trl
  • —sft
  • —generatedfromtrainer model-index:
  • —name: llama1bstep2batchgrad_v5 results: [] ---

<!-- 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. -->

llama1bstep2batchgrad_v5

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.3613

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: 5e-05
  • —trainbatchsize: 8
  • —evalbatchsize: 40
  • —seed: 42
  • —gradientaccumulationsteps: 16
  • —totaltrainbatch_size: 128
  • —optimizer: Use adamwtorch with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
  • —lrschedulertype: linear
  • —num_epochs: 2

Training results

Training LossEpochStepValidation Loss
0.51040.5453500.5257
0.25761.09411000.3929
0.25141.63941500.3613

Framework versions

  • —Transformers 4.46.0
  • —Pytorch 2.1.0+cu118
  • —Datasets 3.0.2
  • —Tokenizers 0.20.1