|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: ms-32maps_nonalpha-ds |
|
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. --> |
|
|
|
# ms-32maps_nonalpha-ds |
|
|
|
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 5.9255 |
|
|
|
## 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: 0.0005 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 10 |
|
- num_epochs: 1 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 6.2444 | 0.04 | 100 | 6.1360 | |
|
| 6.1152 | 0.08 | 200 | 6.1151 | |
|
| 6.1139 | 0.13 | 300 | 6.0946 | |
|
| 6.0576 | 0.17 | 400 | 6.0382 | |
|
| 6.0133 | 0.21 | 500 | 6.0101 | |
|
| 6.0049 | 0.25 | 600 | 5.9972 | |
|
| 5.9919 | 0.3 | 700 | 5.9890 | |
|
| 5.9839 | 0.34 | 800 | 5.9841 | |
|
| 5.9875 | 0.38 | 900 | 5.9783 | |
|
| 5.9712 | 0.42 | 1000 | 5.9717 | |
|
| 5.9775 | 0.47 | 1100 | 5.9656 | |
|
| 5.9668 | 0.51 | 1200 | 5.9597 | |
|
| 5.955 | 0.55 | 1300 | 5.9553 | |
|
| 5.9445 | 0.59 | 1400 | 5.9495 | |
|
| 5.95 | 0.64 | 1500 | 5.9439 | |
|
| 5.939 | 0.68 | 1600 | 5.9416 | |
|
| 5.9345 | 0.72 | 1700 | 5.9378 | |
|
| 5.9396 | 0.76 | 1800 | 5.9336 | |
|
| 5.9414 | 0.8 | 1900 | 5.9303 | |
|
| 5.9262 | 0.85 | 2000 | 5.9283 | |
|
| 5.9365 | 0.89 | 2100 | 5.9266 | |
|
| 5.937 | 0.93 | 2200 | 5.9258 | |
|
| 5.9251 | 0.97 | 2300 | 5.9255 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.30.2 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.13.1 |
|
- Tokenizers 0.13.3 |
|
|
