Hugging Face's logo

thorirhrafn
/
gpt1B_domar_finetune

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
gpt1B_domar_finetune / README.md
thorirhrafn's picture
thorirhrafn
End of training
7d9d109 verified
preview code
|
raw
history blame contribute delete
1.67 kB
metadata
license: apache-2.0
library_name: peft
tags:
  - generated_from_trainer
base_model: AI-Sweden-Models/gpt-sw3-1.3b
model-index:
  - name: gpt1B_domar_finetune
    results: []

gpt1B_domar_finetune

This model is a fine-tuned version of AI-Sweden-Models/gpt-sw3-1.3b on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.8420

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-05
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss
0.91 0.79 200 0.8529
0.7817 1.59 400 0.8483
0.9032 2.38 600 0.8458
0.8597 3.18 800 0.8439
0.8052 3.97 1000 0.8421
0.723 4.77 1200 0.8420

Framework versions

  • PEFT 0.8.2
  • Transformers 4.38.1
  • Pytorch 2.2.0+cu118
  • Datasets 2.17.1
  • Tokenizers 0.15.2