metadata
license: apache-2.0
base_model: studio-ousia/mluke-base
tags:
- generated_from_trainer
model-index:
- name: exp_acha_mluke_base_1e_4_warmpup_02
results: []
exp_acha_mluke_base_1e_4_warmpup_02
This model is a fine-tuned version of studio-ousia/mluke-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2797
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: 0.0001
- train_batch_size: 16
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.2
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.3661 | 1.0 | 208 | 0.4168 |
| 0.4296 | 2.0 | 416 | 0.7619 |
| 0.4223 | 3.0 | 624 | 0.3506 |
| 0.3795 | 4.0 | 832 | 0.3102 |
| 0.4992 | 5.0 | 1040 | 0.5101 |
| 0.4629 | 6.0 | 1248 | 0.4456 |
| 0.406 | 7.0 | 1456 | 0.4701 |
| 0.3229 | 8.0 | 1664 | 0.3865 |
| 0.262 | 9.0 | 1872 | 0.3046 |
| 0.3361 | 10.0 | 2080 | 0.2797 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1