---
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: 0.2825705030042804
---

<!-- 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 |
|:-------------:|:------:|:-----:|:---------------:|:--------:|
| No log        | 0.0002 | 1     | 10.7642         | 0.0134   |
| No log        | 0.0004 | 2     | 10.6236         | 0.0387   |
| No log        | 0.0007 | 4     | 10.4466         | 0.0420   |
| No log        | 0.0015 | 8     | 10.2538         | 0.0441   |
| No log        | 0.0029 | 16    | 10.0488         | 0.0442   |
| No log        | 0.0058 | 32    | 9.6781          | 0.0525   |
| No log        | 0.0117 | 64    | 9.0249          | 0.0649   |
| No log        | 0.0233 | 128   | 8.2151          | 0.0849   |
| No log        | 0.0466 | 256   | 7.2851          | 0.1097   |
| 7.6369        | 0.0933 | 512   | 6.4273          | 0.1299   |
| 6.0229        | 0.1866 | 1024  | 5.6962          | 0.1612   |
| 5.2064        | 0.3732 | 2048  | 5.0830          | 0.1898   |
| 4.6324        | 0.7464 | 4096  | 4.5923          | 0.2237   |
| 4.4846        | 1.0    | 5488  | 4.4230          | 0.2390   |
| 4.2266        | 1.4927 | 8192  | 4.2292          | 0.2592   |
| 4.1079        | 2.0    | 10976 | 4.1156          | 0.2717   |
| 3.9841        | 2.9854 | 16384 | 4.0274          | 0.2826   |
| 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