metadata
license: apache-2.0
base_model: mistralai/Mistral-7B-v0.1
tags:
- trl
- sft
- generated_from_trainer
library_name: peft
model-index:
- name: cimphony-clause
results: []
cimphony-clause
This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2086
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: 6
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 3
- total_train_batch_size: 18
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 4 | 0.1776 |
| No log | 2.0 | 8 | 0.1456 |
| 0.2059 | 3.0 | 12 | 0.1422 |
| 0.2059 | 4.0 | 16 | 0.1480 |
| 0.0478 | 5.0 | 20 | 0.1666 |
| 0.0478 | 6.0 | 24 | 0.1812 |
| 0.0478 | 7.0 | 28 | 0.1966 |
| 0.011 | 8.0 | 32 | 0.2063 |
| 0.011 | 9.0 | 36 | 0.2079 |
| 0.0054 | 10.0 | 40 | 0.2086 |
Framework versions
- PEFT 0.10.0
- Transformers 4.41.2
- Pytorch 2.1.2+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1