outputs
This model is a fine-tuned version of bigscience/bloomz-3b on the FourthBrainGenAI/MarketMail-AI dataset.
Model description
bigscience/bloomz-3b
Intended uses & limitations
This model is for demonstration purpose
Training and evaluation data
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.001
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- 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: 20
- training_steps: 100
- mixed_precision_training: Native AMP
Training results
TrainOutput(global_step=100, training_loss=0.3372485587000847, metrics={'train_runtime': 522.2092, 'train_samples_per_second': 12.256, 'train_steps_per_second': 0.191, 'total_flos': 1.230954169199616e+16, 'train_loss': 0.3372485587000847, 'epoch': 100.0})
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3