trl-lib_-_qwen1.5-0.5b-sft-awq

Quantization made by Richard Erkhov.

Github

Discord

Request more models

qwen1.5-0.5b-sft - AWQ

• Model creator: https://huggingface.co/trl-lib/
• Original model: https://huggingface.co/trl-lib/qwen1.5-0.5b-sft/

Original model description:

license: other base_model: Qwen/Qwen1.5-0.5B tags:

• alignment-handbook
• generated_from_trainer datasets:
• HuggingFaceH4/deita-6k-v0-sft model-index:
• name: qwen-1.5-0.5b-sft-v1.0 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-1.5-0.5b-sft-v1.0

This model is a fine-tuned version of Qwen/Qwen1.5-0.5B on the HuggingFaceH4/deita-6k-v0-sft dataset. It achieves the following results on the evaluation set:

• Loss: 1.2566

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
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• total_train_batch_size: 128
• total_eval_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3

Training results

Framework versions

• Transformers 4.39.0.dev0
• Pytorch 2.1.2+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1