Base Model

Dataset

Parameter

  • max_length: 1024
  • learning_rate: 1e-5
  • scheduler_type: WarmupCosineLR
  • num_train_epochs: 3
  • per_device_train_batch_size: 64
  • per_device_eval_batch_size: 64
  • gradient_accumulation_steps: 1
Downloads last month
2
Safetensors
Model size
4B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for kasys/Phi-3.5_CPT_ESCI-v0.2.1

Finetuned
(104)
this model