metadata
license: mit
base_model: gpt2
tags:
- generated_from_trainer
model-index:
- name: redit_gpt_v3
results: []
redit_gpt_v3
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.7931
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: 0.0001
- train_batch_size: 32
- eval_batch_size: 64
- 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_ratio: 0.1
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.9986 | 358 | 5.6208 |
| No log | 2.0 | 717 | 5.1240 |
| 5.5313 | 2.9986 | 1075 | 4.9075 |
| 5.5313 | 4.0 | 1434 | 4.8096 |
| 5.5313 | 4.9930 | 1790 | 4.7931 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1