Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
metrics:
|
| 5 |
+
- accuracy
|
| 6 |
+
model-index:
|
| 7 |
+
- name: polish-gpt2-small-reviews-2024-01-14
|
| 8 |
+
results: []
|
| 9 |
+
license: mit
|
| 10 |
+
language:
|
| 11 |
+
- pl
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# polish-gpt2-small-reviews-2024-01-14
|
| 18 |
+
|
| 19 |
+
This model was trained from scratch on the None dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.4659
|
| 22 |
+
- Accuracy: 0.9627
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 2e-05
|
| 42 |
+
- train_batch_size: 4
|
| 43 |
+
- eval_batch_size: 4
|
| 44 |
+
- seed: 42
|
| 45 |
+
- gradient_accumulation_steps: 8
|
| 46 |
+
- total_train_batch_size: 32
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- num_epochs: 10
|
| 50 |
+
- mixed_precision_training: Native AMP
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 55 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
| 56 |
+
| 0.4049 | 1.0 | 3284 | 0.3351 | 0.8792 |
|
| 57 |
+
| 0.1885 | 2.0 | 6568 | 0.2625 | 0.9218 |
|
| 58 |
+
| 0.1182 | 3.0 | 9852 | 0.2583 | 0.9419 |
|
| 59 |
+
| 0.0825 | 4.0 | 13136 | 0.2886 | 0.9482 |
|
| 60 |
+
| 0.0586 | 5.0 | 16420 | 0.3343 | 0.9538 |
|
| 61 |
+
| 0.034 | 6.0 | 19704 | 0.3734 | 0.9595 |
|
| 62 |
+
| 0.0288 | 7.0 | 22988 | 0.4125 | 0.9599 |
|
| 63 |
+
| 0.0185 | 8.0 | 26273 | 0.4262 | 0.9626 |
|
| 64 |
+
| 0.0069 | 9.0 | 29557 | 0.4529 | 0.9622 |
|
| 65 |
+
| 0.0059 | 10.0 | 32840 | 0.4659 | 0.9627 |
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
### Framework versions
|
| 69 |
+
|
| 70 |
+
- Transformers 4.36.2
|
| 71 |
+
- Pytorch 2.1.2+cu121
|
| 72 |
+
- Datasets 2.16.1
|
| 73 |
+
- Tokenizers 0.15.0
|