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
Downloads last month
21
Safetensors
Model size
631M params
Tensor type
F32
BF16
U8
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for mrm8488/tinyllama-bnb-4bit-ft-codeAlpaca

Quantized
(150)
this model