metadata
base_model: microsoft/Phi-3.5-mini-instruct
library_name: peft
license: mit
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: Phi-3.5-MultiCap-tool-embedding-3
results: []
Phi-3.5-MultiCap-tool-embedding-3
This model is a fine-tuned version of microsoft/Phi-3.5-mini-instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5221
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: 0.0001
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.8799 | 0.2256 | 50 | 0.8806 |
| 0.6125 | 0.4512 | 100 | 0.6177 |
| 0.5659 | 0.6768 | 150 | 0.5733 |
| 0.6125 | 0.9024 | 200 | 0.5550 |
| 0.5402 | 1.1280 | 250 | 0.5448 |
| 0.5299 | 1.3536 | 300 | 0.5378 |
| 0.4997 | 1.5792 | 350 | 0.5331 |
| 0.549 | 1.8049 | 400 | 0.5296 |
| 0.5361 | 2.0305 | 450 | 0.5268 |
| 0.4821 | 2.2561 | 500 | 0.5249 |
| 0.5274 | 2.4817 | 550 | 0.5234 |
| 0.5344 | 2.7073 | 600 | 0.5227 |
| 0.546 | 2.9329 | 650 | 0.5221 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1