sade-adrien's picture
Update README.md
b40233b
|
raw
history blame
2.23 kB
---
license: apache-2.0
base_model: mistralai/Mistral-7B-Instruct-v0.1
tags:
- generated_from_trainer
model-index:
- name: Mistral-7B-Instruct-v0.1-LC-PI-.5
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. -->
# Mistral-7B-Instruct-v0.1-LC-PI-.5
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.9295
## Model description
This model is a fine-tuning of Mistral-7B-Instruct-v0.1.
This FT was using a Position Interpolation factor of 0.5 (Linear RoPE scaling).
Please note that the RoPE scaling factor should be determined by L/L' where L is the pre-training max context length and L' is the new max context length. In our case, we are just making experiments (and for us we would have had L/L' = 8096/7200 > 1 which did not require any PI scaling).
## Intended uses & limitations
More information needed
## Training and evaluation data
Data is a 9k sample from the RedPajama datset. The context is <=7200 with a decreasing exponential distribution of scale 1500.
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 32
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 20
- training_steps: 300
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.163 | 0.18 | 50 | 2.0175 |
| 2.1576 | 0.36 | 100 | 1.9574 |
| 2.0073 | 0.55 | 150 | 1.9391 |
| 1.8824 | 0.73 | 200 | 1.9320 |
| 2.0718 | 0.91 | 250 | 1.9298 |
| 1.9498 | 1.09 | 300 | 1.9295 |
### Framework versions
- Transformers 4.34.1
- Pytorch 2.0.0+cu117
- Datasets 2.14.6
- Tokenizers 0.14.1