metadata
base_model: microsoft/Phi-3.5-mini-instruct
library_name: peft
license: mit
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: outputs
results: []
outputs
This model is a fine-tuned version of microsoft/Phi-3.5-mini-instruct on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2249
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-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 20
- training_steps: 100
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.979 | 0.5882 | 5 | 2.1552 |
| 1.5649 | 1.1765 | 10 | 1.7044 |
| 1.5355 | 1.7647 | 15 | 1.3163 |
| 0.9301 | 2.3529 | 20 | 1.0521 |
| 0.7935 | 2.9412 | 25 | 0.9929 |
| 0.6411 | 3.5294 | 30 | 0.9735 |
| 0.6521 | 4.1176 | 35 | 0.9699 |
| 0.4867 | 4.7059 | 40 | 0.9812 |
| 0.6112 | 5.2941 | 45 | 1.0029 |
| 0.5041 | 5.8824 | 50 | 1.1055 |
| 0.4784 | 6.4706 | 55 | 1.0859 |
| 0.3787 | 7.0588 | 60 | 1.1113 |
| 0.2676 | 7.6471 | 65 | 1.3963 |
| 0.3066 | 8.2353 | 70 | 1.2249 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1