67 lines
1.6 KiB
YAML
67 lines
1.6 KiB
YAML
base_model: ai21labs/AI21-Jamba-1.5-Large
|
|
# optionally might have model_type or tokenizer_type
|
|
tokenizer_type: AutoTokenizer
|
|
# Automatically upload checkpoint and final model to HF
|
|
# hub_model_id: username/custom_model_name
|
|
|
|
load_in_4bit: true
|
|
use_tensorboard: true
|
|
chat_template: jamba
|
|
datasets:
|
|
- path: cgato/SlimOrcaDedupCleaned
|
|
type: chat_template
|
|
drop_system_message: true
|
|
field_messages: conversations
|
|
message_property_mappings:
|
|
role: from
|
|
content: value
|
|
|
|
dataset_prepared_path: last_run_prepared
|
|
val_set_size: 0.0
|
|
output_dir: jamba-large-fsdp-qlora-ft
|
|
save_safetensors: true
|
|
adapter: qlora
|
|
sequence_len: 2048
|
|
sample_packing: true
|
|
pad_to_sequence_len: true
|
|
|
|
lora_r: 16
|
|
lora_alpha: 16
|
|
lora_dropout: 0.05
|
|
lora_target_modules: [down_proj,gate_proj,in_proj,k_proj,o_proj,out_proj,q_proj,up_proj,v_proj,x_proj]
|
|
lora_target_linear: false
|
|
|
|
gradient_accumulation_steps: 4
|
|
micro_batch_size: 1
|
|
num_epochs: 2
|
|
optimizer: adamw_torch_fused
|
|
lr_scheduler: cosine
|
|
learning_rate: 0.00001
|
|
|
|
bf16: true
|
|
tf32: true
|
|
|
|
gradient_checkpointing: true
|
|
gradient_checkpointing_kwargs:
|
|
use_reentrant: true
|
|
logging_steps: 1
|
|
flash_attention: true
|
|
|
|
warmup_steps: 10
|
|
evals_per_epoch: 1
|
|
saves_per_epoch: 1
|
|
weight_decay: 0.0
|
|
fsdp:
|
|
- full_shard
|
|
- auto_wrap
|
|
fsdp_config:
|
|
fsdp_limit_all_gathers: true
|
|
fsdp_sync_module_states: true
|
|
fsdp_offload_params: false
|
|
fsdp_use_orig_params: false
|
|
fsdp_cpu_ram_efficient_loading: true
|
|
fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
|
|
fsdp_transformer_layer_cls_to_wrap: JambaAttentionDecoderLayer,JambaMambaDecoderLayer
|
|
fsdp_state_dict_type: FULL_STATE_DICT
|
|
fsdp_sharding_strategy: FULL_SHARD
|