mirror of
https://github.com/nomic-ai/gpt4all
synced 2024-11-06 09:20:33 +00:00
31 lines
470 B
YAML
31 lines
470 B
YAML
# model/tokenizer
|
|
model_name: # add model here
|
|
tokenizer_name: # add model here
|
|
gradient_checkpointing: true
|
|
save_name: # CHANGE
|
|
|
|
# dataset
|
|
streaming: false
|
|
num_proc: 64
|
|
dataset_path: # update
|
|
max_length: 1024
|
|
batch_size: 32
|
|
|
|
# train dynamics
|
|
lr: 5.0e-5
|
|
eval_every: 800
|
|
eval_steps: 100
|
|
save_every: 800
|
|
output_dir: # CHANGE
|
|
checkpoint: null
|
|
lora: false
|
|
warmup_steps: 100
|
|
num_epochs: 2
|
|
|
|
# logging
|
|
wandb: true
|
|
wandb_entity: # update
|
|
wandb_project_name: # update
|
|
seed: 42
|
|
|