metadata
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: mistral-supervised
results: []
mistral-supervised
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.4161
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.8982 | 0.5889 | 500 | 4.6761 |
| 4.2609 | 1.1779 | 1000 | 3.9880 |
| 3.7225 | 1.7668 | 1500 | 3.6593 |
| 3.433 | 2.3557 | 2000 | 3.4856 |
| 3.2793 | 2.9446 | 2500 | 3.4161 |
Framework versions
- Transformers 4.43.3
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1