d4niel92's picture
End of training
3107ca6
---
license: other
base_model: microsoft/phi-1_5
tags:
- generated_from_trainer
datasets:
- scitldr
model-index:
- name: uplimit-project-3-phi-1.5
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# uplimit-project-3-phi-1.5
This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) on the scitldr dataset.
It achieves the following results on the evaluation set:
- Loss: 2.6003
## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 2.5556 | 0.1 | 200 | 2.6490 |
| 2.5751 | 0.2 | 400 | 2.6454 |
| 2.5295 | 0.3 | 600 | 2.6411 |
| 2.5819 | 0.4 | 800 | 2.6267 |
| 2.5413 | 0.5 | 1000 | 2.6250 |
| 2.5792 | 0.6 | 1200 | 2.6133 |
| 2.5506 | 0.7 | 1400 | 2.6101 |
| 2.5251 | 0.8 | 1600 | 2.6036 |
| 2.5799 | 0.9 | 1800 | 2.6003 |
### Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1