metadata
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- trl
base_model: unsloth/mistral-7b-instruct-v0.2-bnb-4bit
Uploaded model
- Developed by: Angelectronic
- License: apache-2.0
- Finetuned from model : unsloth/mistral-7b-instruct-v0.2-bnb-4bit
This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.
Evaluation
- ViMMRC test set: 0.8475 accuracy
Training results
Training Loss | Accuracy | Step | Validation Loss |
---|---|---|---|
1.033500 | 0.771325 | 240 | 1.478651 |
0.852000 | 0.758621 | 480 | 1.475045 |
0.751200 | 0.751361 | 720 | 1.501176 |
0.668400 | 0.780399 | 960 | 1.543064 |
0.591600 | 0.796733 | 1200 | 1.567212 |
0.498200 | 0.785844 | 1440 | 1.607110 |
0.379600 | 0.796733 | 1680 | 1.643269 |
0.334200 | 0.771324 | 1920 | 1.661141 |
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 16
- eval_batch_size: 8
- seed: 3407
- gradient_accumulation_steps: 4
- eval_accumulation_steps: 4
- 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: 3
Framework versions
- PEFT 0.10.0
- Transformers 4.40.2
- Pytorch 2.3.0
- Datasets 2.19.1
- Tokenizers 0.19.1