|
--- |
|
license: mit |
|
base_model: gpt2 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: gpt2-XYZCompany-1000-steps |
|
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. --> |
|
|
|
# gpt2-XYZCompany-1000-steps |
|
|
|
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: 0.3082 |
|
|
|
## 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: 1e-05 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 1 |
|
- training_steps: 1000 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 0.4688 | 0.32 | 50 | 0.4117 | |
|
| 0.4546 | 0.63 | 100 | 0.3712 | |
|
| 0.3868 | 0.95 | 150 | 0.3539 | |
|
| 0.369 | 1.27 | 200 | 0.3427 | |
|
| 0.3572 | 1.58 | 250 | 0.3357 | |
|
| 0.344 | 1.9 | 300 | 0.3301 | |
|
| 0.343 | 2.22 | 350 | 0.3258 | |
|
| 0.348 | 2.53 | 400 | 0.3227 | |
|
| 0.3431 | 2.85 | 450 | 0.3194 | |
|
| 0.2994 | 3.16 | 500 | 0.3169 | |
|
| 0.3348 | 3.48 | 550 | 0.3155 | |
|
| 0.3177 | 3.8 | 600 | 0.3134 | |
|
| 0.32 | 4.11 | 650 | 0.3125 | |
|
| 0.318 | 4.43 | 700 | 0.3111 | |
|
| 0.3448 | 4.75 | 750 | 0.3102 | |
|
| 0.2903 | 5.06 | 800 | 0.3094 | |
|
| 0.3078 | 5.38 | 850 | 0.3088 | |
|
| 0.2993 | 5.7 | 900 | 0.3085 | |
|
| 0.3132 | 6.01 | 950 | 0.3083 | |
|
| 0.3262 | 6.33 | 1000 | 0.3082 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.32.1 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.17.1 |
|
- Tokenizers 0.13.2 |
|
|
