output
This model is a fine-tuned version of microsoft/phi-1_5 on the scitldr dataset. It achieves the following results on the evaluation set:
- Loss: 2.5343
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: 0.001
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
2.5534 | 0.1 | 200 | 2.5963 |
2.5771 | 0.2 | 400 | 2.5892 |
2.5311 | 0.3 | 600 | 2.5792 |
2.5859 | 0.4 | 800 | 2.5705 |
2.543 | 0.5 | 1000 | 2.5573 |
2.5801 | 0.6 | 1200 | 2.5516 |
2.5461 | 0.7 | 1400 | 2.5468 |
2.5237 | 0.8 | 1600 | 2.5398 |
2.5794 | 0.9 | 1800 | 2.5343 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
Model tree for retroam/output
Base model
microsoft/phi-1_5