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-new
results: []
Phi-3.5-MultiCap-mt-new
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: 0.6661
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: 4
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.8401 | 0.5109 | 50 | 0.8176 |
| 0.6779 | 1.0217 | 100 | 0.7203 |
| 0.6889 | 1.5326 | 150 | 0.6930 |
| 0.6861 | 2.0434 | 200 | 0.6800 |
| 0.6797 | 2.5543 | 250 | 0.6723 |
| 0.6801 | 3.0651 | 300 | 0.6683 |
| 0.6439 | 3.5760 | 350 | 0.6661 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.2
- Pytorch 2.4.1+cu124
- Datasets 3.0.0
- Tokenizers 0.19.1