metadata
license: bigscience-bloom-rail-1.0
base_model: bigscience/bloomz-560m
tags:
- generated_from_trainer
model-index:
- name: bloomz-560m_fine_lr5e-05_bs4_epoch20_wd0.01
results: []
bloomz-560m_fine_lr5e-05_bs4_epoch20_wd0.01
This model is a fine-tuned version of bigscience/bloomz-560m on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 11.2503
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: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 20
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
3.6412 | 1.0 | 157 | 3.6601 |
2.5683 | 2.0 | 314 | 4.5891 |
1.8204 | 3.0 | 471 | 5.0154 |
2.5022 | 4.0 | 628 | 5.6442 |
1.6245 | 5.0 | 785 | 6.2936 |
0.8665 | 6.0 | 942 | 6.3147 |
0.6814 | 7.0 | 1099 | 6.6231 |
0.4828 | 8.0 | 1256 | 6.6090 |
0.4391 | 9.0 | 1413 | 6.3674 |
0.3401 | 10.0 | 1570 | 7.1139 |
0.3278 | 11.0 | 1727 | 7.1027 |
0.289 | 12.0 | 1884 | 7.4807 |
0.2523 | 13.0 | 2041 | 7.6643 |
0.2347 | 14.0 | 2198 | 8.2786 |
0.2127 | 15.0 | 2355 | 8.5955 |
0.2141 | 16.0 | 2512 | 9.5416 |
0.1931 | 17.0 | 2669 | 9.5192 |
0.1823 | 18.0 | 2826 | 10.4644 |
0.1702 | 19.0 | 2983 | 10.9266 |
0.1603 | 20.0 | 3140 | 11.2503 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.0.1
- Datasets 2.16.1
- Tokenizers 0.15.0