RichardErkhov/trl-lib_-_qwen1.5-1.8b-sft-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

qwen1.5-1.8b-sft - GGUF

• —Model creator: https://huggingface.co/trl-lib/
• —Original model: https://huggingface.co/trl-lib/qwen1.5-1.8b-sft/

Original model description: --- license: other base_model: Qwen/Qwen1.5-1.8B tags:

• —alignment-handbook
• —generatedfromtrainer datasets:
• —HuggingFaceH4/deita-6k-v0-sft model-index:
• —name: qwen-1.5-1.8b-sft-v0.0 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. -->

qwen-1.5-1.8b-sft-v0.0

This model is a fine-tuned version of Qwen/Qwen1.5-1.8B on the HuggingFaceH4/deita-6k-v0-sft dataset. It achieves the following results on the evaluation set:

• —Loss: 1.0886

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: 2e-05
• —trainbatchsize: 16
• —evalbatchsize: 8
• —seed: 42
• —distributed_type: multi-GPU
• —num_devices: 8
• —totaltrainbatch_size: 128
• —totalevalbatch_size: 64
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: cosine
• —lrschedulerwarmup_ratio: 0.1
• —num_epochs: 3

Training results

Framework versions

• —Transformers 4.38.2
• —Pytorch 2.1.2+cu121
• —Datasets 2.16.1
• —Tokenizers 0.15.1