metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: mistralai/Mistral-7B-Instruct-v0.2
model-index:
- name: Mistral-7B-Instruct-v0.2-binary_base03
results: []
Mistral-7B-Instruct-v0.2-binary_base03
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2790
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: 2.5e-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 5
- training_steps: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.5198 | 0.04 | 50 | 0.6078 |
| 0.5143 | 0.08 | 100 | 0.4729 |
| 0.4187 | 0.12 | 150 | 0.3775 |
| 0.3533 | 0.16 | 200 | 0.3413 |
| 0.3344 | 0.2 | 250 | 0.3247 |
| 0.322 | 0.24 | 300 | 0.3184 |
| 0.3129 | 0.28 | 350 | 0.3106 |
| 0.3062 | 0.32 | 400 | 0.3032 |
| 0.2985 | 0.36 | 450 | 0.2989 |
| 0.301 | 0.4 | 500 | 0.2949 |
| 0.2934 | 0.44 | 550 | 0.2933 |
| 0.2921 | 0.48 | 600 | 0.2914 |
| 0.2874 | 0.52 | 650 | 0.2882 |
| 0.2863 | 0.56 | 700 | 0.2875 |
| 0.284 | 0.6 | 750 | 0.2841 |
| 0.2841 | 0.64 | 800 | 0.2829 |
| 0.2797 | 0.68 | 850 | 0.2818 |
| 0.2815 | 0.72 | 900 | 0.2804 |
| 0.2835 | 0.76 | 950 | 0.2790 |
| 0.2777 | 0.8 | 1000 | 0.2790 |
Framework versions
- PEFT 0.7.2.dev0
- Transformers 4.37.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0