metadata
license: other
base_model: microsoft/phi-1_5
tags:
- generated_from_trainer
datasets:
- scitldr
model-index:
- name: uplimit-project-3-phi-1.5
results: []
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: 2.5352
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 |
|---|---|---|---|
| 2.5539 | 0.1 | 200 | 2.5942 |
| 2.5712 | 0.2 | 400 | 2.5944 |
| 2.5304 | 0.3 | 600 | 2.5755 |
| 2.5846 | 0.4 | 800 | 2.5669 |
| 2.5448 | 0.5 | 1000 | 2.5576 |
| 2.5776 | 0.6 | 1200 | 2.5535 |
| 2.5513 | 0.7 | 1400 | 2.5471 |
| 2.5291 | 0.8 | 1600 | 2.5403 |
| 2.5782 | 0.9 | 1800 | 2.5352 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1