metadata
tags:
- generated_from_trainer
model-index:
- name: bloom-560m-finetuned-liability-700_length-QA5
results: []
bloom-560m-finetuned-liability-700_length-QA5
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.9256
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: 3e-06
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.2939 | 0.98 | 29 | 1.5512 |
| 0.3478 | 2.0 | 59 | 1.5154 |
| 0.3055 | 2.98 | 88 | 1.4945 |
| 0.2324 | 4.0 | 118 | 1.5501 |
| 0.1853 | 4.98 | 147 | 1.7230 |
| 0.1676 | 6.0 | 177 | 1.7146 |
| 0.1483 | 6.98 | 206 | 1.8510 |
| 0.121 | 8.0 | 236 | 1.8573 |
| 0.1115 | 8.98 | 265 | 1.9207 |
| 0.0641 | 9.83 | 290 | 1.9256 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3