Edit model card

v3-starcoderbase1b-personal-copilot-A100-40GB-colab

This model is a fine-tuned version of bigcode/starcoderbase-1b on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: nan

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: 4
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 30
  • training_steps: 2000

Training results

Training Loss Epoch Step Validation Loss
0.0 0.05 100 nan
0.0 0.1 200 nan
0.0 0.15 300 nan
0.0 0.2 400 nan
0.0 0.25 500 nan
0.0 0.3 600 nan
0.0 0.35 700 nan
0.0 0.4 800 nan
0.0 0.45 900 nan
0.0 0.5 1000 nan
0.0 0.55 1100 nan
0.0 0.6 1200 nan
0.0 0.65 1300 nan
0.0 0.7 1400 nan
0.0 0.75 1500 nan
0.0 0.8 1600 nan
0.0 0.85 1700 nan
0.0 0.9 1800 nan
0.0 0.95 1900 nan
0.0 1.0 2000 nan

Framework versions

  • Transformers 4.38.0.dev0
  • Pytorch 2.1.0+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.1
Downloads last month
14
Safetensors
Model size
1.14B params
Tensor type
FP16
·
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 mkdir700/v3-starcoderbase1b-personal-copilot-A100-40GB-colab

Finetuned
(16)
this model