metadata
license: mit
base_model: EleutherAI/gpt-neo-125M
tags:
- generated_from_trainer
datasets:
- daily_dialog
model-index:
- name: gpt-neo-daily-dialog
results: []
gpt-neo-daily-dialog
This model is a fine-tuned version of EleutherAI/gpt-neo-125M on the daily_dialog dataset. It achieves the following results on the evaluation set:
- Loss: 2.3630
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: 3e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.5578 | 0.1799 | 500 | 2.5389 |
| 2.4489 | 0.3598 | 1000 | 2.4848 |
| 2.4904 | 0.5397 | 1500 | 2.4453 |
| 2.3967 | 0.7196 | 2000 | 2.4236 |
| 2.4108 | 0.8994 | 2500 | 2.4042 |
| 2.2683 | 1.0793 | 3000 | 2.3939 |
| 2.2068 | 1.2592 | 3500 | 2.3849 |
| 2.2195 | 1.4391 | 4000 | 2.3798 |
| 2.2381 | 1.6190 | 4500 | 2.3709 |
| 2.241 | 1.7989 | 5000 | 2.3647 |
| 2.2108 | 1.9788 | 5500 | 2.3630 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1