|
--- |
|
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 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# Phi-3.5-MultiCap-mt |
|
|
|
This model is a fine-tuned version of [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7569 |
|
|
|
## 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: 2 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 1.4288 | 0.1533 | 15 | 1.3449 | |
|
| 1.0894 | 0.3065 | 30 | 1.1240 | |
|
| 0.9541 | 0.4598 | 45 | 0.9830 | |
|
| 0.9216 | 0.6130 | 60 | 0.8949 | |
|
| 0.8675 | 0.7663 | 75 | 0.8414 | |
|
| 0.8007 | 0.9195 | 90 | 0.8108 | |
|
| 0.8205 | 1.0728 | 105 | 0.7919 | |
|
| 0.7864 | 1.2261 | 120 | 0.7794 | |
|
| 0.7983 | 1.3793 | 135 | 0.7705 | |
|
| 0.7784 | 1.5326 | 150 | 0.7641 | |
|
| 0.744 | 1.6858 | 165 | 0.7595 | |
|
| 0.7765 | 1.8391 | 180 | 0.7569 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.0+cu124 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
