Ir para o conteúdo
ModelListadosExterno
Baixar

Phonebabylm Phone Deu Eng Sequential Interleaved

Trained with trainclm.py, a Hugging Face Accelerate causal-LM training script (no Trainer).

TipoOtherVersãoRevision 4570ba0Dnota

Fonte do modelo

Tipo
Other
Tamanho do arquivo
326 MB
Versão
vRevision 4570ba0
Atualizado
26 de set. de 2026
Downloads
72
Tarefas
Geração de texto
Fonte
Hugging Face

Descrição da fonte

nikitastheo/phonebabylm-phone-deu-eng-sequential_interleaved

Trained with train_clm.py, a Hugging Face Accelerate causal-LM training script (no Trainer).

Training details

  • Base config: gpt_base_config.json
  • Tokenizer: nikitastheo/phonelm-phone-deu-eng-tokenizer
  • Max steps: 30000
  • Learning rate: 0.0001
  • LR scheduler: linear
  • Warmup steps: 3000
  • Batch size (per device): 32
  • Gradient accumulation steps: 1
  • Total train batch size: 32
  • Language switch steps: 10000

Fontes

1 fonte
Hugging FacePrimárioVersão 4570ba0cb69f35cdc6a7ffc4dd151a3581e20c51
huggingface.co/nikitastheo/phonebabylm-phone-deu-eng-sequential_interleaved/tree/4570ba0cb69f35cdc6a7ffc4dd151a3581e20c51

Verificado 26 de set.

Artefatos de modelo

1 artefato

model.safetensors

safetensors · 326 MB · SHA-256 a4ac61b4935c…f61f · Hugging Face

Baixar

Trechos de fonte

2 trechos

--- tags: - causal-lm - text-generation library_name: transformers --- # nikitastheo/phonebabylm-phone-deu-eng-sequential_interleaved Trained with train_clm.py, a Hugging Face Accelerate causal-LM training script (no `Trainer`). ## Training details - **Base config**: `gpt_base_config.json` - **Tokenizer**: `nikitastheo/phonelm-phone-deu-eng-tokenizer` - **Max steps**: 30000 - **Learning rate**: 0.0001 - **LR scheduler**: linear - **Warmup steps**: 3000 - **Batch size (per device)**: 32 - **Gradient accumulation steps**: 1 - **Total train batch size**: 32 - **Language switch steps**: 10000

Source context: 72 downloads · 0 likes · Pipeline text-generation · Library transformers · Repo nikitastheo/phonebabylm-phone-deu-eng-sequential_interleaved