|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- trl |
|
- sft |
|
- unsloth |
|
- generated_from_trainer |
|
base_model: unsloth/mistral-7b-instruct-v0.2-bnb-4bit |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: mistral_wikitable_FV |
|
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_wikitable_FV |
|
|
|
This model is a fine-tuned version of [unsloth/mistral-7b-instruct-v0.2-bnb-4bit](https://huggingface.co/unsloth/mistral-7b-instruct-v0.2-bnb-4bit) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3567 |
|
- Rouge1: 0.8764 |
|
- Rougel: 0.8720 |
|
|
|
## 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: 1e-05 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 1 |
|
- seed: 3407 |
|
- gradient_accumulation_steps: 16 |
|
- total_train_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 5 |
|
- num_epochs: 6 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rougel | |
|
|:-------------:|:------:|:----:|:---------------:|:------:|:------:| |
|
| 0.5561 | 0.9984 | 156 | 0.4506 | 0.8474 | 0.8405 | |
|
| 0.4761 | 1.9968 | 312 | 0.4096 | 0.8636 | 0.8575 | |
|
| 0.3846 | 2.9952 | 468 | 0.3823 | 0.8693 | 0.8648 | |
|
| 0.3334 | 4.0 | 625 | 0.3666 | 0.8741 | 0.8697 | |
|
| 0.3367 | 4.9984 | 781 | 0.3566 | 0.8773 | 0.8729 | |
|
| 0.298 | 5.9904 | 936 | 0.3567 | 0.8764 | 0.8720 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.11.1 |
|
- Transformers 4.41.2 |
|
- Pytorch 2.2.0 |
|
- Datasets 2.16.0 |
|
- Tokenizers 0.19.1 |
