ca-finetuned-phi-2
This model is a fine-tuned version of microsoft/phi-2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.5643
- Perplexity: 0.0000
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: 0.001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 32
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Perplexity |
---|---|---|---|---|
No log | 0.97 | 7 | 2.2352 | 0.0000 |
No log | 1.95 | 14 | 2.0164 | 0.0000 |
2.4567 | 2.92 | 21 | 1.8511 | 0.0000 |
2.4567 | 3.9 | 28 | 1.7391 | 0.0000 |
1.8517 | 4.87 | 35 | 1.6667 | 0.0000 |
1.8517 | 5.98 | 43 | 1.6059 | 0.0000 |
1.5627 | 6.96 | 50 | 1.5816 | 0.0000 |
1.5627 | 7.93 | 57 | 1.5672 | 0.0000 |
1.41 | 8.9 | 64 | 1.5650 | 0.0000 |
1.41 | 9.74 | 70 | 1.5643 | 0.0000 |
Framework versions
- PEFT 0.8.2
- Transformers 4.38.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.16.1
- Tokenizers 0.15.1
- Downloads last month
- 0
Model tree for lvcalucioli/ca-finetuned-phi-2
Base model
microsoft/phi-2