Edit model card

selfbiorag-7b-wo-live_qa-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: 1.1582

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
1.2659 0.91 5 1.2054
1.0094 2.0 11 1.1690
0.8249 2.73 15 1.1582

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.1.2+cu121
  • Datasets 2.14.6
  • Tokenizers 0.15.2
Downloads last month
19
Safetensors
Model size
6.74B params
Tensor type
BF16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for Minbyul/selfbiorag-7b-wo-live_qa-iter-sft-step1

Finetuned
(23)
this model

Dataset used to train Minbyul/selfbiorag-7b-wo-live_qa-iter-sft-step1