stealth-rag-v1

<!-- 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. -->

stealth-rag-v1

This model is a fine-tuned version of jan-hq/stealth-v1.3 on the jan-hq/rag_dataset_1200_binarized, the jan-hq/rag_dataset_12000_binarized, the jan-hq/rag_hallucination_dataset_1000_binarized, the jan-hq/rag_full_20000_binarized, the jan-hq/bagel_sft_binarized, the jan-hq/dolphin_binarized and the jan-hq/openhermes_binarized datasets. It achieves the following results on the evaluation set:

• Loss: 1.3883

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: 2
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• gradient_accumulation_steps: 16
• total_train_batch_size: 64
• total_eval_batch_size: 8
• 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

• PEFT 0.7.1
• Transformers 4.36.2
• Pytorch 2.1.2+cu121
• Datasets 2.14.6
• Tokenizers 0.15.0