|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- trl |
|
- sft |
|
- unsloth |
|
- translation |
|
- generated_from_trainer |
|
base_model: unsloth/mistral-7b-bnb-4bit |
|
model-index: |
|
- name: MistralAI_iwslt15_10000_2 |
|
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. --> |
|
|
|
# MistralAI_iwslt15_10000_2 |
|
|
|
This model is a fine-tuned version of [unsloth/mistral-7b-bnb-4bit](https://huggingface.co/unsloth/mistral-7b-bnb-4bit) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.0438 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 4269 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 32 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 1 |
|
- num_epochs: 2 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.1684 | 0.32 | 100 | 1.0926 | |
|
| 1.0883 | 0.64 | 200 | 1.0701 | |
|
| 1.0672 | 0.96 | 300 | 1.0498 | |
|
| 0.9315 | 1.28 | 400 | 1.0547 | |
|
| 0.8973 | 1.6 | 500 | 1.0495 | |
|
| 0.8831 | 1.92 | 600 | 1.0438 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.10.0 |
|
- Transformers 4.39.3 |
|
- Pytorch 2.2.2+cu121 |
|
- Datasets 2.16.0 |
|
- Tokenizers 0.15.2 |
