feat: add examples for deepcoder (#2517)
This commit is contained in:
58
examples/deepcoder/deepcoder-14B-preview-lora.yml
Normal file
58
examples/deepcoder/deepcoder-14B-preview-lora.yml
Normal file
@@ -0,0 +1,58 @@
|
|||||||
|
base_model: agentica-org/DeepCoder-14B-Preview
|
||||||
|
# Automatically upload checkpoint and final model to HF
|
||||||
|
# hub_model_id: username/custom_model_name
|
||||||
|
|
||||||
|
load_in_8bit: true
|
||||||
|
load_in_4bit: false
|
||||||
|
strict: false
|
||||||
|
|
||||||
|
datasets:
|
||||||
|
- path: fozziethebeat/alpaca_messages_2k_test
|
||||||
|
type: chat_template
|
||||||
|
field_messages: messages
|
||||||
|
message_property_mappings:
|
||||||
|
role: role
|
||||||
|
content: content
|
||||||
|
|
||||||
|
dataset_prepared_path:
|
||||||
|
val_set_size: 0.05
|
||||||
|
output_dir: ./outputs/lora-out
|
||||||
|
|
||||||
|
sequence_len: 4096
|
||||||
|
sample_packing: true
|
||||||
|
eval_sample_packing: false
|
||||||
|
pad_to_sequence_len: true
|
||||||
|
|
||||||
|
adapter: lora
|
||||||
|
lora_model_dir:
|
||||||
|
lora_r: 32
|
||||||
|
lora_alpha: 16
|
||||||
|
lora_dropout: 0.05
|
||||||
|
lora_target_linear: true
|
||||||
|
|
||||||
|
wandb_project:
|
||||||
|
wandb_entity:
|
||||||
|
wandb_watch:
|
||||||
|
wandb_name:
|
||||||
|
wandb_log_model:
|
||||||
|
|
||||||
|
gradient_accumulation_steps: 2
|
||||||
|
micro_batch_size: 2
|
||||||
|
num_epochs: 4
|
||||||
|
optimizer: adamw_bnb_8bit
|
||||||
|
lr_scheduler: cosine
|
||||||
|
learning_rate: 0.0002
|
||||||
|
|
||||||
|
bf16: auto
|
||||||
|
tf32: true
|
||||||
|
|
||||||
|
gradient_checkpointing: true
|
||||||
|
resume_from_checkpoint:
|
||||||
|
logging_steps: 1
|
||||||
|
flash_attention: true
|
||||||
|
|
||||||
|
warmup_steps: 10
|
||||||
|
evals_per_epoch: 1
|
||||||
|
saves_per_epoch: 1
|
||||||
|
weight_decay: 0.0
|
||||||
|
special_tokens:
|
||||||
Reference in New Issue
Block a user