Edit model card

stablelm-2-1.6-disticoder-v0.1

This model is a fine-tuned version of stabilityai/stablelm-2-1_6b on the argilla/DistiCoder-dpo-binarized dataset. It achieves the following results on the evaluation set:

  • Loss: 1.1315

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: 5e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 4
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 128
  • total_eval_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss
1.7319 0.44 5 1.5441
1.3425 0.89 10 1.2968
1.1709 1.33 15 1.2151
1.0994 1.78 20 1.1605
1.0287 2.22 25 1.1382
1.0303 2.67 30 1.1315

Framework versions

  • Transformers 4.37.2
  • Pytorch 2.1.1+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.2
Downloads last month
10
Safetensors
Model size
1.64B params
Tensor type
BF16
·
Inference Examples
Inference API (serverless) does not yet support model repos that contain custom code.

Model tree for plaguss/stablelm-2-1_6-sft-disticoder-v01

Finetuned
(6)
this model
Adapters
1 model