metadata
base_model: mistralai/Mistral-7B-Instruct-v0.2
library_name: peft
license: apache-2.0
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: results_3
results: []
results_3
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: 1.4783
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: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 7
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.5669 | 0.7143 | 5 | 1.9836 |
| 1.7321 | 1.4286 | 10 | 1.5707 |
| 1.2965 | 2.1429 | 15 | 1.3547 |
| 1.027 | 2.8571 | 20 | 1.3522 |
| 0.7281 | 3.5714 | 25 | 1.3416 |
| 0.7364 | 4.2857 | 30 | 1.3577 |
| 0.7055 | 5.0 | 35 | 1.4064 |
| 0.5305 | 5.7143 | 40 | 1.4535 |
| 0.56 | 6.4286 | 45 | 1.4710 |
Framework versions
- PEFT 0.13.2
- Transformers 4.45.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.1