trollek/danube2-1.8b-openhermes

<|im_start|>user
{{instruction}}<|im_end|>
<|im_start|>assistant
{{response}}<|im_end|>

### model
model_name_or_path: danube2-base-chatml

### method
stage: sft
do_train: true
finetuning_type: full
use_badam: true
badam_switch_mode: ascending
badam_switch_interval: 50
badam_verbose: 1
badam_start_block: 10
seed: 720

### dataset
dataset: openhermes_unfiltered
template: ninja_chatml
cutoff_len: 8192
overwrite_cache: false
preprocessing_num_workers: 12

### output
output_dir: openhermes-chatml-badam
logging_steps: 5
save_steps: 1
save_strategy: epoch
plot_loss: true
overwrite_output_dir: false

### train
per_device_train_batch_size: 2
gradient_accumulation_steps: 8
learning_rate: 0.00001
num_train_epochs: 1
lr_scheduler_type: constant_with_warmup
warmup_ratio: 0.01
bf16: true
flash_attn: fa2

### eval
val_size: 0.01
per_device_eval_batch_size: 1
eval_strategy: steps
eval_steps: 2000

### model
model_name_or_path: openhermes-chatml-badam

### method
stage: sft
do_train: true
finetuning_type: lora
lora_target: all
loraplus_lr_ratio: 16.0
lora_rank: 8
lora_alpha: 16
use_unsloth: true
quantization_bit: 4
upcast_layernorm: true
seed: 3141

### dataset
dataset: openhermes_unfiltered
template: hermes_chatml
cutoff_len: 8192
overwrite_cache: false
preprocessing_num_workers: 12

### output
output_dir: openhermes-chatml-badam/loraplus
logging_steps: 1
save_steps: 1
save_strategy: epoch
plot_loss: true
overwrite_output_dir: false

### train
per_device_train_batch_size: 4
gradient_accumulation_steps: 4
learning_rate: 0.0001
num_train_epochs: 1.0
lr_scheduler_type: cosine
warmup_ratio: 0.01
bf16: true
flash_attn: fa2
#neftune_noise_alpha: 5

### eval
val_size: 0.02
per_device_eval_batch_size: 1
eval_strategy: steps
eval_steps: 1000