dmitrijsk's picture
End of training
6d87ad1
metadata
license: bigscience-bloom-rail-1.0
base_model: bigscience/bloomz-3b
tags:
  - generated_from_trainer
model-index:
  - name: blooms-3b-rick-trainer
    results: []

blooms-3b-rick-trainer

This model is a fine-tuned version of bigscience/bloomz-3b on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 3.5774

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: 5e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 2

Training results

Training Loss Epoch Step Validation Loss
3.5704 1.0 7 3.6198
3.467 2.0 14 3.5774

Framework versions

  • Transformers 4.32.0.dev0
  • Pytorch 2.0.1+cu117
  • Datasets 2.14.4
  • Tokenizers 0.13.3