metadata
license: mit
library_name: peft
tags:
- generated_from_trainer
base_model: microsoft/phi-2
model-index:
- name: phi2-dolly-sum-finetune
results: []
phi2-dolly-sum-finetune
This model is a fine-tuned version of microsoft/phi-2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.0505
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: 2.5e-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1
- training_steps: 500
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.9329 | 0.05 | 25 | 2.4178 |
| 2.4832 | 0.09 | 50 | 2.1541 |
| 2.1688 | 0.14 | 75 | 2.0774 |
| 2.2247 | 0.18 | 100 | 2.0725 |
| 2.225 | 0.23 | 125 | 2.0652 |
| 2.2217 | 0.27 | 150 | 2.0635 |
| 2.2282 | 0.32 | 175 | 2.0611 |
| 2.1104 | 0.37 | 200 | 2.0608 |
| 2.1583 | 0.41 | 225 | 2.0569 |
| 2.1197 | 0.46 | 250 | 2.0565 |
| 2.1257 | 0.5 | 275 | 2.0559 |
| 2.0018 | 0.55 | 300 | 2.0512 |
| 2.0203 | 0.6 | 325 | 2.0546 |
| 2.1332 | 0.64 | 350 | 2.0519 |
| 2.1585 | 0.69 | 375 | 2.0503 |
| 2.1287 | 0.73 | 400 | 2.0510 |
| 2.1431 | 0.78 | 425 | 2.0515 |
| 2.1601 | 0.82 | 450 | 2.0522 |
| 2.088 | 0.87 | 475 | 2.0481 |
| 2.0462 | 0.92 | 500 | 2.0505 |
Framework versions
- PEFT 0.8.1
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1