metadata
tags:
- generated_from_trainer
datasets:
- uonlp/CulturaX
metrics:
- accuracy
model-index:
- name: gpt2_cx-en_00000-00009_50k
results:
- task:
name: Causal Language Modeling
type: text-generation
dataset:
name: uonlp/CulturaX en
type: uonlp/CulturaX
args: en
metrics:
- name: Accuracy
type: accuracy
value: 0.36165373273858764
gpt2_cx-en_00000-00009_50k
This model is a fine-tuned version of on the uonlp/CulturaX en dataset. It achieves the following results on the evaluation set:
- Loss: 3.5834
- Accuracy: 0.3617
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 |
---|---|---|---|---|
4.586 | 0.04 | 10000 | 4.4977 | 0.2821 |
4.2706 | 0.08 | 20000 | 4.1928 | 0.3058 |
4.1189 | 0.12 | 30000 | 4.0469 | 0.3179 |
4.0314 | 0.16 | 40000 | 3.9610 | 0.3253 |
3.9704 | 0.2 | 50000 | 3.8977 | 0.3311 |
3.923 | 0.24 | 60000 | 3.8486 | 0.3353 |
3.888 | 0.28 | 70000 | 3.8084 | 0.3390 |
3.8529 | 0.32 | 80000 | 3.7777 | 0.3423 |
3.832 | 0.36 | 90000 | 3.7526 | 0.3446 |
3.8102 | 0.4 | 100000 | 3.7277 | 0.3470 |
3.7876 | 0.44 | 110000 | 3.7073 | 0.3490 |
3.7686 | 0.48 | 120000 | 3.6922 | 0.3506 |
3.7585 | 0.52 | 130000 | 3.6750 | 0.3522 |
3.7459 | 0.56 | 140000 | 3.6620 | 0.3535 |
3.7378 | 0.6 | 150000 | 3.6501 | 0.3545 |
3.7181 | 0.64 | 160000 | 3.6385 | 0.3559 |
3.7139 | 0.68 | 170000 | 3.6293 | 0.3568 |
3.6958 | 0.72 | 180000 | 3.6201 | 0.3578 |
3.6872 | 0.76 | 190000 | 3.6122 | 0.3585 |
3.6888 | 0.8 | 200000 | 3.6060 | 0.3592 |
3.6765 | 0.84 | 210000 | 3.6001 | 0.3599 |
3.6734 | 0.88 | 220000 | 3.5945 | 0.3604 |
3.6669 | 0.92 | 230000 | 3.5891 | 0.3611 |
3.6696 | 0.96 | 240000 | 3.5856 | 0.3614 |
Framework versions
- Transformers 4.37.1
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1