YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co/docs/hub/model-cards#model-card-metadata)
This model is a fine-tuned version of Mixtral-8x22B-Instruct-v0.1 on the mbpp dataset.
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training hyperparameters
The following hyperparameters were used during training:
method
- stage: sft
- finetuning_type: lora
- lora_target: all
- deepspeed: examples/deepspeed/ds_z3_offload_config.json
dataset
- dataset: mbpp
- template: mistral
- cutoff_len: 2048
- max_samples: 316
- overwrite_cache: true
- preprocessing_num_workers: 16
train
- per_device_train_batch_size: 1
- gradient_accumulation_steps: 2
- learning_rate: 1.0e-4
- num_train_epochs: 3
- lr_scheduler_type: cosine
- warmup_ratio: 0.1
- bf16: true
- ddp_timeout: 180000000
Framework versions
- PEFT 0.14.0
- Transformers 4.47.0
- Pytorch 2.5.1+cu124
- Datasets 2.14.6
- Tokenizers 0.21.0
wandb
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.