|
--- |
|
license: mit |
|
base_model: openai-community/gpt2 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: financeLM_outputpath_final_model_15 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# financeLM_outputpath_final_model_15 |
|
|
|
This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.9396 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
| 1.6902 | 1.0 | 671 | 1.3422 | |
|
| 1.0644 | 2.0 | 1342 | 1.3353 | |
|
| 0.8371 | 3.0 | 2013 | 1.4028 | |
|
| 0.6842 | 4.0 | 2685 | 1.4639 | |
|
| 0.5775 | 5.0 | 3356 | 1.5597 | |
|
| 0.4967 | 6.0 | 4027 | 1.6722 | |
|
| 0.438 | 7.0 | 4698 | 1.7115 | |
|
| 0.3909 | 8.0 | 5370 | 1.7681 | |
|
| 0.3556 | 9.0 | 6041 | 1.8081 | |
|
| 0.3293 | 10.0 | 6712 | 1.8478 | |
|
| 0.3076 | 11.0 | 7383 | 1.8752 | |
|
| 0.2908 | 12.0 | 8055 | 1.8949 | |
|
| 0.2781 | 13.0 | 8726 | 1.9260 | |
|
| 0.2685 | 14.0 | 9397 | 1.9298 | |
|
| 0.2602 | 14.99 | 10065 | 1.9396 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.0 |
|
- Pytorch 2.1.2+cu121 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.14.1 |
|
|
