opt-peter-2.7B / README.md
pszemraj's picture
Update README.md
71e37d7
|
raw
history blame
1.39 kB
metadata
license: other
tags:
  - generated_from_trainer
model-index:
  - name: opt-2pt7b-ps_DS-msgs_Ep-3_Bs-8
    results: []

pszemraj/opt-peter-2.7B

This model is a fine-tuned version of facebook/opt-2.7b on about 80k whatsapp/text messages (mine). Please use responsibly :)

Model description

More information needed

Intended uses & limitations

The base model has a custom license which propogates to this one. Most importantly, it cannot be used commercially. Read more here: facebook/opt-2.7b

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 4e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 128
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.01
  • num_epochs: 3

Training results

Framework versions

  • Transformers 4.19.2
  • Pytorch 1.10.0+cu113
  • Datasets 2.2.2
  • Tokenizers 0.12.1