metadata
license: mit
base_model: gpt2
tags:
- generated_from_trainer
model-index:
- name: 4_bar_lmd_clean_custom_epochs10
results: []
4_bar_lmd_clean_custom_epochs10
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0103
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: 48
- eval_batch_size: 32
- seed: 1
- gradient_accumulation_steps: 2
- total_train_batch_size: 96
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.01
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.7474 | 3.92 | 5000 | 1.1705 |
| 1.1177 | 7.85 | 10000 | 1.0103 |
Framework versions
- Transformers 4.36.0
- Pytorch 2.1.0
- Datasets 2.15.0
- Tokenizers 0.15.1