CodePhi-3-mini-4k-instruct-appsloraN1k
This model is a fine-tuned version of microsoft/Phi-3-mini-4k-instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6440
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: 5e-06
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- training_steps: 1000
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.5745 | 0.1 | 100 | 0.6791 |
0.6382 | 0.2 | 200 | 0.6637 |
0.6357 | 0.3 | 300 | 0.6558 |
0.5793 | 0.4 | 400 | 0.6507 |
0.607 | 0.5 | 500 | 0.6472 |
0.592 | 0.6 | 600 | 0.6451 |
0.5959 | 0.7 | 700 | 0.6442 |
0.5586 | 0.8 | 800 | 0.6440 |
0.571 | 0.9 | 900 | 0.6439 |
0.5259 | 1.0 | 1000 | 0.6440 |
Framework versions
- PEFT 0.11.0
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 0
Model tree for AdnanRiaz107/CodePhi-3-mini-4k-instruct-appsloraN1k
Base model
microsoft/Phi-3-mini-4k-instruct
Adapter
this model