metadata
base_model: distilbert/distilgpt2
library_name: peft
license: apache-2.0
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: tmp
results: []
tmp
This model is a fine-tuned version of distilbert/distilgpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.2922
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.5623 | 1.0 | 2337 | 2.3956 |
| 2.4776 | 2.0 | 4674 | 2.3410 |
| 2.4591 | 3.0 | 7011 | 2.3128 |
| 2.445 | 4.0 | 9348 | 2.2974 |
| 2.4492 | 5.0 | 11685 | 2.2922 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1