|
--- |
|
license: mit |
|
base_model: Toflamus/GPT-2_para3M |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: Output |
|
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. --> |
|
|
|
# Output |
|
|
|
This model is a fine-tuned version of [Toflamus/GPT-2_para3M](https://huggingface.co/Toflamus/GPT-2_para3M) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 5.9785 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 128 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 100 |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 7.6797 | 0.27 | 100 | 7.0355 | |
|
| 6.9842 | 0.55 | 200 | 6.6754 | |
|
| 6.7517 | 0.82 | 300 | 6.5074 | |
|
| 6.6145 | 1.09 | 400 | 6.3942 | |
|
| 6.5294 | 1.37 | 500 | 6.3043 | |
|
| 6.4228 | 1.64 | 600 | 6.2332 | |
|
| 6.3582 | 1.91 | 700 | 6.1772 | |
|
| 6.3 | 2.19 | 800 | 6.1279 | |
|
| 6.2841 | 2.46 | 900 | 6.0878 | |
|
| 6.2103 | 2.73 | 1000 | 6.0572 | |
|
| 6.1908 | 3.01 | 1100 | 6.0325 | |
|
| 6.1733 | 3.28 | 1200 | 6.0132 | |
|
| 6.1383 | 3.55 | 1300 | 5.9991 | |
|
| 6.149 | 3.83 | 1400 | 5.9901 | |
|
| 6.1383 | 4.1 | 1500 | 5.9836 | |
|
| 6.1155 | 4.37 | 1600 | 5.9800 | |
|
| 6.1275 | 4.65 | 1700 | 5.9788 | |
|
| 6.1257 | 4.92 | 1800 | 5.9785 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.32.0 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.4 |
|
- Tokenizers 0.13.2 |
|
|