README.md

metadata

base_model: dmis-lab/selfbiorag_7b
tags:
  - alignment-handbook
  - trl
  - sft
  - generated_from_trainer
  - trl
  - sft
  - generated_from_trainer
datasets:
  - HuggingFaceH4/deita-10k-v0-sft
model-index:
  - name: selfbiorag-7b-1e-6-wo-kqa_golden-iter-sft-step1_lr
    results: []

selfbiorag-7b-1e-6-wo-kqa_golden-iter-sft-step1_lr

This model is a fine-tuned version of dmis-lab/selfbiorag_7b on the HuggingFaceH4/deita-10k-v0-sft dataset. It achieves the following results on the evaluation set:

• Loss: 1.3816

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: 1e-06
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• total_eval_batch_size: 16
• 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

Training Loss	Epoch	Step	Validation Loss
1.438	0.91	5	1.4282
1.3992	2.0	11	1.3832
1.3839	2.73	15	1.3816

Framework versions

• Transformers 4.39.0.dev0
• Pytorch 2.1.2
• Datasets 2.14.6
• Tokenizers 0.15.2