NLI-Lora-Fine-Tuning-10K
This model is a fine-tuned version of albert-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8405
- Accuracy: 0.6071
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 | 1.0533 | 0.4667 |
| 1.0642 | 2.0 | 624 | 1.0234 | 0.5033 |
| 1.0642 | 3.0 | 936 | 0.9616 | 0.5467 |
| 1.0052 | 4.0 | 1248 | 0.9010 | 0.5795 |
| 0.9162 | 5.0 | 1560 | 0.8750 | 0.5876 |
| 0.9162 | 6.0 | 1872 | 0.8606 | 0.5959 |
| 0.8817 | 7.0 | 2184 | 0.8512 | 0.6019 |
| 0.8817 | 8.0 | 2496 | 0.8452 | 0.6051 |
| 0.8618 | 9.0 | 2808 | 0.8416 | 0.6071 |
| 0.8551 | 10.0 | 3120 | 0.8405 | 0.6071 |
Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 3
Model tree for m4faisal/NLI-Lora-Fine-Tuning-10K
Base model
albert/albert-base-v2