Hugging Face's logo

Adzka
/
test-fine-tune

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
test-fine-tune / README.md
Adzka's picture
Adzka
Model save
b59b726 verified
preview code
|
raw
history blame
1.7 kB
metadata
license: mit
base_model: aisingapore/sea-lion-7b-instruct
tags:
  - generated_from_trainer
model-index:
  - name: test-fine-tune
    results: []
library_name: peft

test-fine-tune

This model is a fine-tuned version of aisingapore/sea-lion-7b-instruct on the None dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

The following bitsandbytes quantization config was used during training:

  • quant_method: QuantizationMethod.BITS_AND_BYTES
  • _load_in_8bit: False
  • _load_in_4bit: True
  • llm_int8_threshold: 6.0
  • llm_int8_skip_modules: None
  • llm_int8_enable_fp32_cpu_offload: False
  • llm_int8_has_fp16_weight: False
  • bnb_4bit_quant_type: fp4
  • bnb_4bit_use_double_quant: False
  • bnb_4bit_compute_dtype: float32
  • bnb_4bit_quant_storage: uint8
  • load_in_4bit: True
  • load_in_8bit: False

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 2e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3
  • mixed_precision_training: Native AMP

Training results

Framework versions

  • PEFT 0.5.0
  • Transformers 4.39.1
  • Pytorch 2.1.0+cu121
  • Datasets 2.14.5
  • Tokenizers 0.15.2