metadata
license: apache-2.0
base_model: EleutherAI/pythia-70m
tags:
- generated_from_trainer
model-index:
- name: polish_wikipedia_model
results: []
polish_wikipedia_model
This model is a fine-tuned version of EleutherAI/pythia-70m on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0319
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: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 133 | 0.4322 |
| No log | 2.0 | 266 | 0.3766 |
| No log | 3.0 | 399 | 0.3599 |
| 0.4669 | 4.0 | 532 | 0.3247 |
| 0.4669 | 5.0 | 665 | 0.2830 |
| 0.4669 | 6.0 | 798 | 0.2628 |
| 0.4669 | 7.0 | 931 | 0.2573 |
| 0.3481 | 8.0 | 1064 | 0.2443 |
| 0.3481 | 9.0 | 1197 | 0.1904 |
| 0.3481 | 10.0 | 1330 | 0.1799 |
| 0.3481 | 11.0 | 1463 | 0.1475 |
| 0.2502 | 12.0 | 1596 | 0.1292 |
| 0.2502 | 13.0 | 1729 | 0.1168 |
| 0.2502 | 14.0 | 1862 | 0.1103 |
| 0.2502 | 15.0 | 1995 | 0.0989 |
| 0.1572 | 16.0 | 2128 | 0.0890 |
| 0.1572 | 17.0 | 2261 | 0.0736 |
| 0.1572 | 18.0 | 2394 | 0.0672 |
| 0.1007 | 19.0 | 2527 | 0.0592 |
| 0.1007 | 20.0 | 2660 | 0.0550 |
| 0.1007 | 21.0 | 2793 | 0.0517 |
| 0.1007 | 22.0 | 2926 | 0.0497 |
| 0.0674 | 23.0 | 3059 | 0.0458 |
| 0.0674 | 24.0 | 3192 | 0.0421 |
| 0.0674 | 25.0 | 3325 | 0.0394 |
| 0.0674 | 26.0 | 3458 | 0.0378 |
| 0.0491 | 27.0 | 3591 | 0.0357 |
| 0.0491 | 28.0 | 3724 | 0.0337 |
| 0.0491 | 29.0 | 3857 | 0.0323 |
| 0.0491 | 30.0 | 3990 | 0.0319 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1