metadata
license: apache-2.0
base_model: bn22/Mistral-7B-Instruct-v0.1-sharded
tags:
- generated_from_trainer
model-index:
- name: results
results: []
results
This model is a fine-tuned version of bn22/Mistral-7B-Instruct-v0.1-sharded on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.9447
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: 0.0002
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- training_steps: 600
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.4418 | 0.07 | 100 | 2.2922 |
| 2.1884 | 0.15 | 200 | 2.1105 |
| 2.0871 | 0.22 | 300 | 2.0371 |
| 2.011 | 0.29 | 400 | 1.9835 |
| 1.9346 | 0.37 | 500 | 1.9517 |
| 1.9721 | 0.44 | 600 | 1.9447 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.0
- Datasets 2.11.0
- Tokenizers 0.15.0