HW3_bonus
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: 2.1196
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: 0.0005
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 64
- total_train_batch_size: 128
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
2.5258 | 0.13 | 10 | 2.4049 |
2.1578 | 0.26 | 20 | 2.2568 |
2.1059 | 0.38 | 30 | 2.1895 |
1.9871 | 0.51 | 40 | 2.1711 |
1.9926 | 0.64 | 50 | 2.1389 |
1.9699 | 0.77 | 60 | 2.1318 |
1.9185 | 0.9 | 70 | 2.1196 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.0
- Datasets 2.15.0
- Tokenizers 0.15.0
Unable to determine this model's library. Check the
docs
.