|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
base_model: albert/albert-base-v2 |
|
model-index: |
|
- name: NLI-Lora-Fine-Tuning-10K-ALBERTA |
|
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. --> |
|
|
|
# NLI-Lora-Fine-Tuning-10K-ALBERTA |
|
|
|
This model is a fine-tuned version of [albert/albert-base-v2](https://huggingface.co/albert/albert-base-v2) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.8439 |
|
- Accuracy: 0.6063 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 32 |
|
- 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 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| No log | 1.0 | 312 | 1.0562 | 0.4551 | |
|
| 1.0762 | 2.0 | 624 | 1.0236 | 0.4995 | |
|
| 1.0762 | 3.0 | 936 | 0.9603 | 0.5361 | |
|
| 1.0075 | 4.0 | 1248 | 0.9053 | 0.5671 | |
|
| 0.9178 | 5.0 | 1560 | 0.8796 | 0.5823 | |
|
| 0.9178 | 6.0 | 1872 | 0.8649 | 0.5934 | |
|
| 0.8859 | 7.0 | 2184 | 0.8551 | 0.5977 | |
|
| 0.8859 | 8.0 | 2496 | 0.8488 | 0.6033 | |
|
| 0.8632 | 9.0 | 2808 | 0.8450 | 0.6057 | |
|
| 0.8543 | 10.0 | 3120 | 0.8439 | 0.6063 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.9.0 |
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
