uplimit-project-3-phi-1.5
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: 0.0000
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 |
---|---|---|---|
0.0 | 0.1 | 200 | 0.0000 |
0.0 | 0.2 | 400 | 0.0000 |
0.0 | 0.3 | 600 | 0.0000 |
0.0 | 0.4 | 800 | 0.0000 |
0.0 | 0.5 | 1000 | 0.0000 |
0.0 | 0.6 | 1200 | 0.0000 |
0.0 | 0.7 | 1400 | 0.0000 |
0.0 | 0.8 | 1600 | 0.0000 |
0.0 | 0.9 | 1800 | 0.0000 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
Model tree for aleidolf/uplimit-project-3-phi-1.5
Base model
microsoft/phi-1_5
Finetuned
this model