mrm8488's picture
Update README.md
a1fd711
metadata
license: apache-2.0
base_model: unsloth/tinyllama-bnb-4bit
tags:
  - generated_from_trainer
datasets:
  - generator
model-index:
  - name: tinyllama-bnb-4bit-ft-codeAlpaca
    results: []

tinyllama-bnb-4bit-ft-codeAlpaca

This model is a fine-tuned version of unsloth/tinyllama-bnb-4bit on the generator dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7926

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: 2e-05
  • train_batch_size: 4
  • eval_batch_size: 8
  • seed: 3407
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss
1.1517 0.83 50 1.1598
0.9428 1.65 100 0.9327
0.8319 2.48 150 0.8448
0.8205 3.31 200 0.8102
0.7977 4.13 250 0.7966
0.763 4.96 300 0.7926

Framework versions

  • Transformers 4.37.0.dev0
  • Pytorch 2.1.0+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.0