metadata
license: mit
library_name: peft
tags:
- generated_from_trainer
base_model: microsoft/phi-2
model-index:
- name: customer_care_dialog_summary_phi_2
results: []
customer_care_dialog_summary_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: 1.6666
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: 5e-05
- train_batch_size: 4
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.0697 | 1.0 | 110 | 1.7888 |
| 1.7135 | 2.0 | 220 | 1.7248 |
| 1.6432 | 3.0 | 330 | 1.7010 |
| 1.6017 | 4.0 | 440 | 1.6930 |
| 1.5717 | 5.0 | 550 | 1.6772 |
| 1.5476 | 6.0 | 660 | 1.6707 |
| 1.525 | 7.0 | 770 | 1.6555 |
| 1.5091 | 8.0 | 880 | 1.6692 |
| 1.4935 | 9.0 | 990 | 1.6602 |
| 1.4816 | 10.0 | 1100 | 1.6666 |
Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.2.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0