---
library_name: peft
tags:
- generated_from_trainer
base_model: slplab/polyglot-ko-1.3b-pretrained-asd
model-index:
- name: pretrain-asd_w-cot_w-asd_text-features
  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-asd_w-cot_w-asd_text-features

This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2919

## 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: 3e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step  | Validation Loss |
|:-------------:|:------:|:-----:|:---------------:|
| 0.5331        | 0.1725 | 1000  | 0.3109          |
| 0.3076        | 0.3450 | 2000  | 0.3025          |
| 0.2963        | 0.5174 | 3000  | 0.3007          |
| 0.3008        | 0.6899 | 4000  | 0.2992          |
| 0.2969        | 0.8624 | 5000  | 0.2984          |
| 0.2956        | 1.0349 | 6000  | 0.2977          |
| 0.2943        | 1.2074 | 7000  | 0.3000          |
| 0.2973        | 1.3798 | 8000  | 0.2968          |
| 0.2927        | 1.5523 | 9000  | 0.2953          |
| 0.2949        | 1.7248 | 10000 | 0.2943          |
| 0.2915        | 1.8973 | 11000 | 0.2931          |
| 0.2897        | 2.0698 | 12000 | 0.2937          |
| 0.2885        | 2.2422 | 13000 | 0.2926          |
| 0.2945        | 2.4147 | 14000 | 0.2928          |
| 0.2907        | 2.5872 | 15000 | 0.2923          |
| 0.292         | 2.7597 | 16000 | 0.2922          |
| 0.2899        | 2.9322 | 17000 | 0.2919          |


### Framework versions

- PEFT 0.11.1
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1