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-mt-10
results: []
Phi-3.5-MultiCap-mt-10
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: 0.6691
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.0255 | 0.5109 | 50 | 0.9995 |
| 0.7489 | 1.0217 | 100 | 0.7879 |
| 0.7483 | 1.5326 | 150 | 0.7377 |
| 0.7314 | 2.0434 | 200 | 0.7159 |
| 0.7247 | 2.5543 | 250 | 0.7031 |
| 0.7219 | 3.0651 | 300 | 0.6948 |
| 0.681 | 3.5760 | 350 | 0.6894 |
| 0.6678 | 4.0868 | 400 | 0.6843 |
| 0.6784 | 4.5977 | 450 | 0.6808 |
| 0.6606 | 5.1086 | 500 | 0.6782 |
| 0.6982 | 5.6194 | 550 | 0.6763 |
| 0.6524 | 6.1303 | 600 | 0.6742 |
| 0.655 | 6.6411 | 650 | 0.6728 |
| 0.6483 | 7.1520 | 700 | 0.6715 |
| 0.6707 | 7.6628 | 750 | 0.6710 |
| 0.6334 | 8.1737 | 800 | 0.6703 |
| 0.6521 | 8.6845 | 850 | 0.6698 |
| 0.6356 | 9.1954 | 900 | 0.6694 |
| 0.6232 | 9.7063 | 950 | 0.6691 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1