metadata
license: mit
base_model: openai-community/gpt2
tags:
- generated_from_trainer
model-index:
- name: financeLM_outputpath_sa
results: []
financeLM_outputpath_sa
This model is a fine-tuned version of openai-community/gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.4027
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: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.2041 | 1.0 | 239 | 1.7449 |
| 1.5789 | 2.0 | 478 | 1.6901 |
| 1.3553 | 3.0 | 717 | 1.7043 |
| 1.1684 | 4.0 | 957 | 1.7492 |
| 1.0153 | 5.0 | 1196 | 1.8371 |
| 0.8759 | 6.0 | 1435 | 1.9329 |
| 0.762 | 7.0 | 1674 | 2.0288 |
| 0.6636 | 8.0 | 1914 | 2.1386 |
| 0.5889 | 9.0 | 2153 | 2.2152 |
| 0.5311 | 10.0 | 2392 | 2.2569 |
| 0.4837 | 11.0 | 2631 | 2.3196 |
| 0.4459 | 12.0 | 2871 | 2.3524 |
| 0.419 | 13.0 | 3110 | 2.3839 |
| 0.3996 | 14.0 | 3349 | 2.3953 |
| 0.3834 | 14.98 | 3585 | 2.4027 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.2+cu121
- Datasets 2.14.5
- Tokenizers 0.14.1