metadata
license: bigscience-bloom-rail-1.0
library_name: peft
tags:
- generated_from_trainer
base_model: vlsp-2023-vllm/hoa-1b4
model-index:
- name: hoa-1b4_model_kaggle_time_March9th_format
results: []
hoa-1b4_model_kaggle_time_March9th_format
This model is a fine-tuned version of vlsp-2023-vllm/hoa-1b4 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0275
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: 4e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 465 | 0.1374 |
| 0.4597 | 2.0 | 930 | 0.0718 |
| 0.0993 | 3.0 | 1395 | 0.0513 |
| 0.0658 | 4.0 | 1860 | 0.0427 |
| 0.0474 | 5.0 | 2325 | 0.0391 |
| 0.0391 | 6.0 | 2790 | 0.0356 |
| 0.0374 | 7.0 | 3255 | 0.0317 |
| 0.0323 | 8.0 | 3720 | 0.0296 |
| 0.0317 | 9.0 | 4185 | 0.0284 |
| 0.0299 | 10.0 | 4650 | 0.0275 |
Framework versions
- PEFT 0.9.0
- Transformers 4.38.1
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.2