|
--- |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- uonlp/CulturaX |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: gpt2+morf_u0-30-50-x_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: 0.39500633343599556 |
|
license: mit |
|
language: |
|
- en |
|
--- |
|
|
|
<!-- 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+morf_u0-30-50-x_cx-en_00000-00009_50k |
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on the uonlp/CulturaX en dataset. |
|
It achieves the following results on the evaluation set: |
|
|
|
- Loss: 3.3667 |
|
- Accuracy: 0.3950 |
|
|
|
## 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 | |
|
| :-----------: | :---: | :----: | :-------------: | :------: | |
|
| 4.3227 | 0.04 | 10000 | 4.2268 | 0.3161 | |
|
| 4.0305 | 0.07 | 20000 | 3.9455 | 0.3393 | |
|
| 3.8916 | 0.11 | 30000 | 3.8194 | 0.3502 | |
|
| 3.8104 | 0.15 | 40000 | 3.7340 | 0.3580 | |
|
| 3.7491 | 0.19 | 50000 | 3.6770 | 0.3633 | |
|
| 3.7062 | 0.22 | 60000 | 3.6288 | 0.3679 | |
|
| 3.6724 | 0.26 | 70000 | 3.5938 | 0.3714 | |
|
| 3.6399 | 0.3 | 80000 | 3.5652 | 0.3743 | |
|
| 3.6147 | 0.34 | 90000 | 3.5396 | 0.3768 | |
|
| 3.5946 | 0.37 | 100000 | 3.5158 | 0.3791 | |
|
| 3.5726 | 0.41 | 110000 | 3.4986 | 0.3809 | |
|
| 3.5631 | 0.45 | 120000 | 3.4819 | 0.3826 | |
|
| 3.5459 | 0.49 | 130000 | 3.4678 | 0.3842 | |
|
| 3.5304 | 0.52 | 140000 | 3.4535 | 0.3857 | |
|
| 3.5245 | 0.56 | 150000 | 3.4430 | 0.3867 | |
|
| 3.5124 | 0.6 | 160000 | 3.4329 | 0.3877 | |
|
| 3.501 | 0.63 | 170000 | 3.4223 | 0.3890 | |
|
| 3.4934 | 0.67 | 180000 | 3.4130 | 0.3901 | |
|
| 3.4863 | 0.71 | 190000 | 3.4042 | 0.3909 | |
|
| 3.4799 | 0.75 | 200000 | 3.3991 | 0.3914 | |
|
| 3.4682 | 0.78 | 210000 | 3.3909 | 0.3924 | |
|
| 3.4667 | 0.82 | 220000 | 3.3852 | 0.3930 | |
|
| 3.4564 | 0.86 | 230000 | 3.3790 | 0.3936 | |
|
| 3.4581 | 0.9 | 240000 | 3.3753 | 0.3941 | |
|
| 3.4553 | 0.93 | 250000 | 3.3710 | 0.3945 | |
|
| 3.4508 | 0.97 | 260000 | 3.3680 | 0.3949 | |
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.1 |
|
- Pytorch 2.1.2+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.1 |
