metadata
license: mit
base_model: gpt2
tags:
- generated_from_trainer
model-index:
- name: reuters-gpt2-text-gen
results: []
reuters-gpt2-text-gen
This model is a trained from-scratch gpt2 model on the Reuters dataset. It achieves the following results on the evaluation set:
- Loss: 4.8502
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: 0.0005
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.2539 | 1.0 | 234 | 4.8502 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3