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: 2.4488
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 |
|---|---|---|---|
| 2.4056 | 0.1 | 200 | 2.4951 |
| 2.4108 | 0.2 | 400 | 2.4877 |
| 2.3732 | 0.3 | 600 | 2.4823 |
| 2.4148 | 0.4 | 800 | 2.4741 |
| 2.3768 | 0.5 | 1000 | 2.4746 |
| 2.4095 | 0.6 | 1200 | 2.4632 |
| 2.3931 | 0.7 | 1400 | 2.4600 |
| 2.3644 | 0.8 | 1600 | 2.4500 |
| 2.4092 | 0.9 | 1800 | 2.4488 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.1.0
- Datasets 2.14.5
- Tokenizers 0.14.1
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model's library.
Model tree for jessica-ecosia/uplimit-project-3-phi-1.5
Base model
microsoft/phi-1_5