|
--- |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- uonlp/CulturaX |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: gpt2+ts_cx-cs_00000-00019_50k |
|
results: |
|
- task: |
|
name: Causal Language Modeling |
|
type: text-generation |
|
dataset: |
|
name: uonlp/CulturaX cs |
|
type: uonlp/CulturaX |
|
args: cs |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.39971894120768026 |
|
license: mit |
|
language: |
|
- cs |
|
--- |
|
|
|
<!-- 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+ts_cx-cs_00000-00019_50k |
|
|
|
This model is a fine-tuned version of [](https://huggingface.co./) on the uonlp/CulturaX cs dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 3.4399 |
|
- Accuracy: 0.3997 |
|
|
|
## 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: 5e-05 |
|
- train_batch_size: 64 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 1.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:------:|:---------------:|:--------:| |
|
| 4.6338 | 0.04 | 10000 | 4.5133 | 0.2968 | |
|
| 4.2588 | 0.07 | 20000 | 4.1531 | 0.3284 | |
|
| 4.0955 | 0.11 | 30000 | 3.9906 | 0.3432 | |
|
| 3.9884 | 0.15 | 40000 | 3.8866 | 0.3530 | |
|
| 3.914 | 0.18 | 50000 | 3.8144 | 0.3601 | |
|
| 3.8563 | 0.22 | 60000 | 3.7592 | 0.3656 | |
|
| 3.8136 | 0.25 | 70000 | 3.7137 | 0.3701 | |
|
| 3.7762 | 0.29 | 80000 | 3.6766 | 0.3740 | |
|
| 3.7481 | 0.33 | 90000 | 3.6468 | 0.3773 | |
|
| 3.7199 | 0.36 | 100000 | 3.6194 | 0.3800 | |
|
| 3.6886 | 0.4 | 110000 | 3.5967 | 0.3824 | |
|
| 3.677 | 0.44 | 120000 | 3.5789 | 0.3843 | |
|
| 3.6611 | 0.47 | 130000 | 3.5600 | 0.3863 | |
|
| 3.6442 | 0.51 | 140000 | 3.5443 | 0.3879 | |
|
| 3.6285 | 0.55 | 150000 | 3.5313 | 0.3894 | |
|
| 3.6126 | 0.58 | 160000 | 3.5176 | 0.3910 | |
|
| 3.6051 | 0.62 | 170000 | 3.5063 | 0.3921 | |
|
| 3.5946 | 0.65 | 180000 | 3.4957 | 0.3933 | |
|
| 3.5883 | 0.69 | 190000 | 3.4858 | 0.3944 | |
|
| 3.5789 | 0.73 | 200000 | 3.4788 | 0.3951 | |
|
| 3.5693 | 0.76 | 210000 | 3.4702 | 0.3963 | |
|
| 3.5584 | 0.8 | 220000 | 3.4632 | 0.3970 | |
|
| 3.5546 | 0.84 | 230000 | 3.4574 | 0.3977 | |
|
| 3.5434 | 0.87 | 240000 | 3.4520 | 0.3983 | |
|
| 3.5447 | 0.91 | 250000 | 3.4473 | 0.3988 | |
|
| 3.5353 | 0.95 | 260000 | 3.4427 | 0.3993 | |
|
| 3.5382 | 0.98 | 270000 | 3.4402 | 0.3997 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.1 |
|
- Pytorch 2.1.2+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.1 |
