metadata
license: bigscience-bloom-rail-1.0
base_model: bigscience/bloom-560m
tags:
- generated_from_trainer
model-index:
- name: finetuned-model
results: []
finetuned-model
This model is a fine-tuned version of bigscience/bloom-560m on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 7.8626
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: 2e-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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 6 | 7.9789 |
| No log | 2.0 | 12 | 7.9410 |
| No log | 3.0 | 18 | 7.9208 |
| No log | 4.0 | 24 | 7.9045 |
| No log | 5.0 | 30 | 7.8931 |
| No log | 6.0 | 36 | 7.8828 |
| No log | 7.0 | 42 | 7.8742 |
| No log | 8.0 | 48 | 7.8679 |
| No log | 9.0 | 54 | 7.8640 |
| No log | 10.0 | 60 | 7.8626 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.13.3