bloom-1b1-emailgen / README.md
pszemraj's picture
update model card README.md
12ca3b8
|
raw
history blame
1.47 kB
metadata
license: bigscience-bloom-rail-1.0
tags:
  - generated_from_trainer
model-index:
  - name: bloom-1b1-emailgen-v1
    results: []

bloom-1b1-emailgen-v1

This model is a fine-tuned version of bigscience/bloom-1b1 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.7396

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: 7e-05
  • train_batch_size: 2
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU
  • gradient_accumulation_steps: 64
  • 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: 0.03
  • num_epochs: 2.0

Training results

Training Loss Epoch Step Validation Loss
1.8465 1.0 256 1.8656
1.4903 2.0 512 1.7396

Framework versions

  • Transformers 4.25.0.dev0
  • Pytorch 1.13.0+cu117
  • Datasets 2.6.1
  • Tokenizers 0.13.1