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-noSW
results: []
Mistral-7B-Instruct-v0.1-LC-PI-.5-noSW
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.8995
Model description
This model is a fine-tuning of Mistral-7B-Instruct-v0.1. This FT was done with full attention (removing the 4k SWA). 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 = 7200/8096 > 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: 0.0001
- 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 |
|---|---|---|---|
| 2.1056 | 0.18 | 50 | 1.9680 |
| 2.1266 | 0.36 | 100 | 1.9213 |
| 1.978 | 0.55 | 150 | 1.9084 |
| 1.8576 | 0.73 | 200 | 1.9022 |
| 2.0311 | 0.91 | 250 | 1.8999 |
| 1.9197 | 1.09 | 300 | 1.8995 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.0.0+cu117
- Datasets 2.14.6
- Tokenizers 0.14.1