|
--- |
|
library_name: transformers |
|
base_model: bowphs/pythia-70m-multi |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- bowphs/europarl_parallel |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: debugging |
|
results: |
|
- task: |
|
name: Causal Language Modeling |
|
type: text-generation |
|
dataset: |
|
name: bowphs/europarl_parallel |
|
type: bowphs/europarl_parallel |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.2825701437173418 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# debugging |
|
|
|
This model is a fine-tuned version of [bowphs/pythia-70m-multi](https://huggingface.co/bowphs/pythia-70m-multi) on the bowphs/europarl_parallel dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 4.0273 |
|
- Accuracy: 0.2826 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
- lr_scheduler_type: linear |
|
- num_epochs: 3.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:| |
|
| 4.4846 | 1.0 | 5488 | 4.4230 | 0.2390 | |
|
| 4.1079 | 2.0 | 10976 | 4.1156 | 0.2717 | |
|
| 3.9841 | 3.0 | 16464 | 4.0273 | 0.2826 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.48.0.dev0 |
|
- Pytorch 2.5.1+cu124 |
|
- Datasets 3.2.0 |
|
- Tokenizers 0.21.0 |
|
|
