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-wo-kqa_golden-iter-sft-step1
    results: []

selfbiorag-7b-wo-kqa_golden-iter-sft-step1

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: 1.0452

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: 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
1.2821	0.91	5	1.1136
0.9973	2.0	11	1.0571
0.82	2.73	15	1.0452

Framework versions

Transformers 4.38.2
Pytorch 2.1.2+cu121
Datasets 2.14.6
Tokenizers 0.15.2