|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: mistralai/Mistral-7B-v0.1 |
|
model-index: |
|
- name: mistral-dict-finetune |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# mistral-dict-finetune |
|
|
|
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.0971 |
|
|
|
## 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: 0.00025 |
|
- train_batch_size: 2 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 1 |
|
- training_steps: 150 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 0.5253 | 0.02 | 10 | 1.2809 | |
|
| 0.6095 | 0.04 | 20 | 1.3211 | |
|
| 0.6344 | 0.06 | 30 | 1.2456 | |
|
| 0.6884 | 0.08 | 40 | 1.2517 | |
|
| 0.8843 | 0.1 | 50 | 1.1908 | |
|
| 1.1089 | 0.12 | 60 | 1.1586 | |
|
| 1.1403 | 0.14 | 70 | 1.1397 | |
|
| 1.1651 | 0.16 | 80 | 1.1363 | |
|
| 1.2073 | 0.18 | 90 | 1.1258 | |
|
| 1.1118 | 0.2 | 100 | 1.1154 | |
|
| 1.0701 | 0.22 | 110 | 1.1106 | |
|
| 1.1988 | 0.24 | 120 | 1.1064 | |
|
| 1.1405 | 0.26 | 130 | 1.1029 | |
|
| 1.0875 | 0.28 | 140 | 1.0986 | |
|
| 1.1385 | 0.3 | 150 | 1.0971 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.10.1.dev0 |
|
- Transformers 4.40.0.dev0 |
|
- Pytorch 2.1.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |