metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
metrics:
- accuracy
base_model: mistralai/Mistral-7B-Instruct-v0.1
model-index:
- name: mistral_instruct_classify10k
results: []
mistral_instruct_classify10k
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4669
- F1 Micro: 0.5541
- F1 Macro: 0.4757
- Accuracy: 0.8606
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_steps: 0.03
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Micro | F1 Macro | Accuracy |
|---|---|---|---|---|---|---|
| 0.5713 | 1.0 | 1345 | 0.5121 | 0.5518 | 0.4780 | 0.8361 |
| 2.1107 | 2.0 | 2690 | 1.0088 | 0.5039 | 0.4158 | 0.7536 |
| 0.7897 | 3.0 | 4035 | 0.8093 | 0.4448 | 0.3756 | 0.6377 |
| 0.2022 | 4.0 | 5380 | 0.3706 | 0.5619 | 0.4837 | 0.8751 |
| 0.4403 | 5.0 | 6725 | 0.4996 | 0.5552 | 0.4811 | 0.8406 |
| 0.3214 | 6.0 | 8070 | 0.4669 | 0.5541 | 0.4757 | 0.8606 |
Framework versions
- PEFT 0.8.2
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2