metadata
license: bigscience-bloom-rail-1.0
tags:
- generated_from_trainer
model-index:
- name: bloom-560m-finetuned-the-stack-brainfuck
results: []
widget:
- text: ' >+++++++++[<++++++++>-]<.>+++++++[<++++>-]<+.+++++++..+++.[-]>++++++++[<++++>-] <.>+++++++++++[<++++++++>-]<-.--------.+++.-[.>>+>+<<<-]>>>'
bloom-560m-finetuned-the-stack-brainfuck
This model is a fine-tuned version of bigscience/bloom-560m on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2112
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: 1
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.3877 | 0.1 | 200 | 1.8023 |
| 1.2576 | 0.19 | 400 | 1.7121 |
| 1.1452 | 0.29 | 600 | 1.5469 |
| 1.1503 | 0.39 | 800 | 1.6261 |
| 1.0287 | 0.48 | 1000 | 1.5097 |
| 1.0118 | 0.58 | 1200 | 1.4398 |
| 1.0466 | 0.67 | 1400 | 1.4267 |
| 0.9531 | 0.77 | 1600 | 1.4130 |
| 0.8891 | 0.87 | 1800 | 1.4026 |
| 0.9163 | 0.96 | 2000 | 1.4003 |
| 0.7207 | 1.06 | 2200 | 1.3758 |
| 0.7041 | 1.16 | 2400 | 1.3364 |
| 0.7065 | 1.25 | 2600 | 1.3095 |
| 0.7316 | 1.35 | 2800 | 1.2959 |
| 0.6817 | 1.45 | 3000 | 1.2682 |
| 0.6926 | 1.54 | 3200 | 1.2567 |
| 0.6511 | 1.64 | 3400 | 1.2416 |
| 0.6819 | 1.73 | 3600 | 1.2263 |
| 0.6422 | 1.83 | 3800 | 1.2206 |
| 0.6392 | 1.93 | 4000 | 1.2112 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.13.0+cu117
- Datasets 2.5.1
- Tokenizers 0.13.0