9f824ef76a
* simplify the example configs to be more minimal and less daunting * drop empty s2_attention from example yamls
54 lines
1.0 KiB
YAML
54 lines
1.0 KiB
YAML
base_model: google/gemma-2-2b
|
|
# optionally might have model_type or tokenizer_type
|
|
model_type: AutoModelForSequenceClassification
|
|
num_labels: 1
|
|
tokenizer_type: AutoTokenizer
|
|
# Automatically upload checkpoint and final model to HF
|
|
# hub_model_id: username/custom_model_name
|
|
strict: false
|
|
|
|
reward_model: true
|
|
chat_template: gemma
|
|
datasets:
|
|
- path: argilla/distilabel-intel-orca-dpo-pairs
|
|
type: bradley_terry.chat_template
|
|
val_set_size: 0.0
|
|
output_dir: ./outputs/out
|
|
remove_unused_columns: false
|
|
|
|
sequence_len: 2048
|
|
sample_packing: false
|
|
eval_sample_packing: false
|
|
pad_to_sequence_len: true
|
|
|
|
wandb_project:
|
|
wandb_entity:
|
|
wandb_watch:
|
|
wandb_name:
|
|
wandb_log_model:
|
|
|
|
|
|
gradient_accumulation_steps: 4
|
|
micro_batch_size: 2
|
|
num_epochs: 4
|
|
optimizer: adamw_bnb_8bit
|
|
lr_scheduler: cosine
|
|
learning_rate: 0.0002
|
|
|
|
bf16: true
|
|
fp16:
|
|
tf32: true
|
|
|
|
gradient_checkpointing: true
|
|
gradient_checkpointing_kwargs:
|
|
use_reentrant: false
|
|
resume_from_checkpoint:
|
|
logging_steps: 1
|
|
flash_attention: true
|
|
|
|
warmup_ratio: 0.1
|
|
evals_per_epoch:
|
|
saves_per_epoch: 1
|
|
weight_decay: 0.0
|
|
special_tokens:
|