NLI-Lora-Fine-Tuning-10K-ALBERT
This model is a fine-tuned version of Alireza1044/albert-base-v2-mnli on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5040
- Accuracy: 0.8087
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 | 0.5855 | 0.7969 |
0.6904 | 2.0 | 624 | 0.5286 | 0.7992 |
0.6904 | 3.0 | 936 | 0.5205 | 0.8010 |
0.5659 | 4.0 | 1248 | 0.5168 | 0.8021 |
0.5529 | 5.0 | 1560 | 0.5128 | 0.8042 |
0.5529 | 6.0 | 1872 | 0.5096 | 0.8054 |
0.5459 | 7.0 | 2184 | 0.5071 | 0.8076 |
0.5459 | 8.0 | 2496 | 0.5055 | 0.8081 |
0.5319 | 9.0 | 2808 | 0.5044 | 0.8086 |
0.5319 | 10.0 | 3120 | 0.5040 | 0.8087 |
Framework versions
- PEFT 0.9.1.dev0
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 5
Model tree for m4faisal/NLI-Lora-Fine-Tuning-10K-ALBERT
Base model
Alireza1044/albert-base-v2-mnli
Adapter
this model