RichardErkhov/danielgombas_-_llama_1b_step2_batch_v3-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama1bstep2batchv3 - GGUF

• —Model creator: https://huggingface.co/danielgombas/
• —Original model: https://huggingface.co/danielgombas/llama1bstep2batchv3/

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

• —trl
• —sft
• —generatedfromtrainer model-index:
• —name: llama1bstep2batchv3 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. -->

llama1bstep2batchv3

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

• —Loss: 0.3241

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: 4
• —evalbatchsize: 40
• —seed: 42
• —gradientaccumulationsteps: 4
• —totaltrainbatch_size: 16
• —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

Framework versions

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