RichardErkhov/amy011872_-_LawToken-1.5B-baseline-awq

Quantization made by Richard Erkhov.

Github

Discord

Request more models

LawToken-1.5B-baseline - AWQ

• Model creator: https://huggingface.co/amy011872/
• Original model: https://huggingface.co/amy011872/LawToken-1.5B-baseline/

Original model description:

license: apache-2.0 base_model: Qwen/Qwen2-1.5B tags: - trl - sft - generated_from_trainer datasets: - generator model-index: - name: LawToken-1.5B-baseline results: []

LawToken-1.5B-baseline

This model is a fine-tuned version of Qwen/Qwen2-1.5B on the generator dataset. It achieves the following results on the evaluation set:

• Loss: 0.7613

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: 0.0001
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• total_train_batch_size: 16
• total_eval_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 0.03
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
0.9956	0.27	10000	0.9392
0.8306	0.54	20000	0.8382
0.7346	0.8	30000	0.7613

Framework versions

• Transformers 4.38.2
• Pytorch 2.3.0a0+ebedce2
• Datasets 2.19.1
• Tokenizers 0.15.2