metadata
license: mit
library_name: peft
tags:
- generated_from_trainer
base_model: microsoft/phi-2
model-index:
- name: peft_phi_2
results: []
peft_phi_2
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: nan
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: 0.005
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.4514 | 1.0 | 287 | 6.5988 |
| 0.0 | 2.0 | 574 | nan |
| 0.0 | 3.0 | 861 | nan |
Framework versions
- PEFT 0.11.2.dev0
- Transformers 4.42.4
- Pytorch 2.1.2
- Datasets 2.19.2
- Tokenizers 0.19.1