Hugging Face's logo

matthewdelorenzo
/
archgen-2b-v1

Text Generation
Transformers
Safetensors
codegen
generated_from_trainer
Eval Results
Inference Endpoints
Model card Files Community
archgen-2b-v1 / README.md
matthewdelorenzo's picture
matthewdelorenzo
Upload 16 files
c63c0f3 verified
preview code
|
raw history blame contribute delete
No virus
1.82 kB
metadata
license: bsd-3-clause
base_model: Salesforce/codegen-2B-nl
tags:
  - generated_from_trainer
datasets:
  - matthewdelorenzo/archgen
metrics:
  - accuracy
model-index:
  - name: output_llm
    results:
      - task:
          name: Causal Language Modeling
          type: text-generation
        dataset:
          name: matthewdelorenzo/archgen
          type: matthewdelorenzo/archgen
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8559900076029108

Visualize in Weights & Biases

output_llm

This model is a fine-tuned version of Salesforce/codegen-2B-nl on the matthewdelorenzo/archgen dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6558
  • Accuracy: 0.8560

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: 1
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • gradient_accumulation_steps: 32
  • total_train_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 1.0
  • mixed_precision_training: Native AMP

Training results

Framework versions

  • Transformers 4.41.0.dev0
  • Pytorch 2.3.0
  • Datasets 2.19.1
  • Tokenizers 0.19.1