phi-1_5-lora-tuned-sft-dolly
This model is a fine-tuned version of microsoft/phi-1_5 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 2.4000
Model description
More information needed
Intended uses & limitations
More information needed
Hardware
Trained model on Intel Max 1550 GPU
Training and evaluation data
databricks/databricks-dolly-15k
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.05
- training_steps: 593
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
2.7868 | 0.8065 | 100 | 2.5808 |
2.547 | 1.6129 | 200 | 2.4670 |
2.4664 | 2.4194 | 300 | 2.4305 |
2.4586 | 3.2258 | 400 | 2.4108 |
2.4204 | 4.0323 | 500 | 2.4000 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.1.0.post0+cxx11.abi
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 10
Model tree for eduardo-alvarez/phi-1_5-lora-tuned-sft-dolly
Base model
microsoft/phi-1_5
Adapter
this model