|
---
|
|
library_name: transformers
|
|
license: other
|
|
tags:
|
|
- freeze
|
|
model-index:
|
|
- name: phi3.5-pro-10-08
|
|
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. -->
|
|
|
|
# phi3.5-pro-10-08
|
|
|
|
This model is a fine-tuned version of [E:\mergekit\phi3.5-pro](https://huggingface.co/E:\mergekit\phi3.5-pro) on the Magpie_Qwen2_Pro_300k and the Magpie_Llama_3.1_Pro_MT_300k datasets.
|
|
It achieves the following results on the evaluation set:
|
|
- Loss: 0.8538
|
|
|
|
## 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: 2
|
|
- eval_batch_size: 2
|
|
- seed: 42
|
|
- gradient_accumulation_steps: 8
|
|
- total_train_batch_size: 16
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
|
- lr_scheduler_type: cosine
|
|
- training_steps: 1000
|
|
- mixed_precision_training: Native AMP
|
|
|
|
### Training results
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss |
|
|
|:-------------:|:------:|:----:|:---------------:|
|
|
| 0.7784 | 0.0080 | 100 | 0.8538 |
|
|
| 0.8605 | 0.0160 | 200 | 0.8538 |
|
|
| 0.8386 | 0.0240 | 300 | 0.8538 |
|
|
| 0.8201 | 0.0320 | 400 | 0.8538 |
|
|
| 0.8661 | 0.0400 | 500 | 0.8538 |
|
|
| 0.776 | 0.0480 | 600 | 0.8538 |
|
|
| 0.8377 | 0.0561 | 700 | 0.8538 |
|
|
| 0.8541 | 0.0641 | 800 | 0.8538 |
|
|
| 0.799 | 0.0721 | 900 | 0.8538 |
|
|
| 0.8146 | 0.0801 | 1000 | 0.8538 |
|
|
|
|
|
|
### Framework versions
|
|
|
|
- Transformers 4.45.0
|
|
- Pytorch 2.4.0+cu124
|
|
- Datasets 2.21.0
|
|
- Tokenizers 0.20.0
|
|
|
