metadata
base_model: mistralai/Mistral-7B-v0.1
library_name: peft
license: apache-2.0
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: lc_v7_all
results: []
lc_v7_all
This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.4816
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: 2e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.3131 | 1.0 | 919 | 1.5000 |
| 1.5413 | 2.0 | 1838 | 1.4873 |
| 1.3715 | 3.0 | 2757 | 1.4834 |
| 1.5193 | 4.0 | 3676 | 1.4822 |
| 1.3544 | 5.0 | 4595 | 1.4814 |
| 1.3155 | 6.0 | 5514 | 1.4815 |
| 1.2591 | 7.0 | 6433 | 1.4816 |
| 1.4263 | 8.0 | 7352 | 1.4815 |
| 1.4298 | 9.0 | 8271 | 1.4817 |
| 1.4252 | 10.0 | 9190 | 1.4816 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.1.0+cu118
- Datasets 2.20.0
- Tokenizers 0.19.1