metadata
license: mit
base_model: gpt2
tags:
- generated_from_trainer
model-index:
- name: gpt2-ds
results: []
gpt2-ds
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 6.5115
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 7.9456 | 0.08 | 10 | 7.6166 |
| 7.4919 | 0.16 | 20 | 7.3649 |
| 7.3086 | 0.24 | 30 | 7.1963 |
| 7.1312 | 0.32 | 40 | 7.0145 |
| 6.9745 | 0.4 | 50 | 6.8656 |
| 6.8648 | 0.48 | 60 | 6.7427 |
| 6.7591 | 0.56 | 70 | 6.6575 |
| 6.6745 | 0.64 | 80 | 6.5982 |
| 6.6597 | 0.72 | 90 | 6.5550 |
| 6.6284 | 0.8 | 100 | 6.5302 |
| 6.5895 | 0.88 | 110 | 6.5159 |
| 6.5568 | 0.96 | 120 | 6.5115 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1