metadata
license: mit
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: microsoft/phi-2
model-index:
- name: output_dir
results: []
output_dir
This model is a fine-tuned version of microsoft/phi-2 on the SAMSUM (summarization) dataset. It achieves the following results on the evaluation set:
- Loss: 1.8001
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: 0.0001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.8411 | 0.4 | 368 | 1.8439 |
| 1.6179 | 0.8 | 736 | 1.8187 |
| 1.5641 | 1.2 | 1104 | 1.8084 |
| 2.2357 | 1.6 | 1472 | 1.8017 |
| 1.388 | 2.0 | 1840 | 1.8001 |
Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2