robinsmits's picture
Update README.md
d5d6eb1
|
raw
history blame
2.19 kB
metadata
license: cc-by-nc-4.0
inference: false
datasets:
  - BramVanroy/alpaca-cleaned-dutch
base_model: DAMO-NLP-MT/polylm-1.7b
tags:
  - generated_from_trainer
  - alpaca
  - Transformers
  - PolyLM
  - text-generation-inference
model-index:
  - name: polylm_1.7b_ft_alpaca_clean_dutch
    results: []
language:
  - nl
library_name: peft
pipeline_tag: text-generation

polylm_1.7b_ft_alpaca_clean_dutch

This model is a fine-tuned version of DAMO-NLP-MT/polylm-1.7b on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.8174

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: 0.0002
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 64
  • num_epochs: 2

Training results

Training Loss Epoch Step Validation Loss
2.0693 0.16 128 2.0915
2.0029 0.33 256 2.0195
2.0006 0.49 384 1.9779
1.933 0.66 512 1.9409
1.9532 0.82 640 1.9217
1.8959 0.99 768 1.8978
1.8237 1.15 896 1.8838
1.8218 1.32 1024 1.8693
1.8072 1.48 1152 1.8521
1.8103 1.65 1280 1.8395
1.8275 1.81 1408 1.8266
1.7902 1.98 1536 1.8174

Framework versions

  • Transformers 4.31.0
  • Pytorch 2.0.1+cu118
  • Datasets 2.13.1
  • Tokenizers 0.13.3
  • PEFT 0.4.0