metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: wvangils/DistilGPT2-Beatles-Lyrics-finetuned
model-index:
- name: DistilGPT2-Beatles-model
results: []
DistilGPT2-Beatles-model
This model is a fine-tuned version of wvangils/DistilGPT2-Beatles-Lyrics-finetuned on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.9446
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: 2
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1
- training_steps: 250
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.171 | 0.0 | 25 | 1.9776 |
| 2.1476 | 0.0 | 50 | 1.9749 |
| 2.1443 | 0.0 | 75 | 1.9618 |
| 2.1231 | 0.0 | 100 | 1.9567 |
| 2.1389 | 0.0 | 125 | 1.9535 |
| 2.1542 | 0.0 | 150 | 1.9507 |
| 2.107 | 0.01 | 175 | 1.9536 |
| 2.1268 | 0.01 | 200 | 1.9514 |
| 2.1264 | 0.01 | 225 | 1.9443 |
| 2.1182 | 0.01 | 250 | 1.9446 |
Framework versions
- PEFT 0.8.2
- Transformers 4.38.1
- Pytorch 1.13.1
- Datasets 2.17.0
- Tokenizers 0.15.2