---
library_name: transformers
language:
- zh
- en
base_model: ai_challenger-epoch-1
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: pretrain_zh_en_ai_challenger_output
  results: []
---

<!-- 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. -->

# pretrain_zh_en_ai_challenger_output

This model is a fine-tuned version of [ai_challenger-epoch-1](https://huggingface.co/ai_challenger-epoch-1) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4557
- Bleu: 27.0414
- Meteor: 0.5451
- Gen Len: 15.2255

## 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: 2024
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0

### Training results

| Training Loss | Epoch | Step   | Validation Loss | Bleu    | Meteor | Gen Len |
|:-------------:|:-----:|:------:|:---------------:|:-------:|:------:|:-------:|
| 1.6733        | 1.0   | 156250 | 1.5656          | 25.9104 | 0.5364 | 15.4366 |
| 1.6415        | 2.0   | 312500 | 1.5193          | 26.7033 | 0.5449 | 15.6291 |
| 1.5831        | 3.0   | 468750 | 1.4901          | 27.2345 | 0.5479 | 15.5704 |
| 1.5352        | 4.0   | 625000 | 1.4695          | 27.7312 | 0.5521 | 15.528  |
| 1.4946        | 5.0   | 781250 | 1.4557          | 27.9356 | 0.5543 | 15.548  |


### Framework versions

- Transformers 4.45.2
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1