trust_remote_code: true
adapter: lora
base_model: deepseek-ai/DeepSeek-V2-Lite-Chat
bf16: auto
bnb_config_kwargs:
  # These are default values
  llm_int8_has_fp16_weight: false
  bnb_4bit_quant_type: nf4
  bnb_4bit_use_double_quant: true
dataset_processes: 32
datasets:
- path: ./train.jsonl
  type: chat_template
  field_messages: messages
gradient_accumulation_steps: 1
gradient_checkpointing: true
learning_rate: 0.0002
lisa_layers_attribute: model.layers
load_best_model_at_end: false
lora_alpha: 16
lora_dropout: 0.05
lora_r: 8
lora_target_modules:
- q_proj
- v_proj
- k_proj
- o_proj
- gate_proj
- down_proj
- up_proj
loraplus_lr_embedding: 1.0e-06
lr_scheduler: cosine
max_prompt_len: 1024
mean_resizing_embeddings: false
micro_batch_size: 1
num_epochs: 1.0
optimizer: adamw_bnb_8bit
output_dir: ./outputs/mymodel
pretrain_multipack_attn: true
pretrain_multipack_buffer_size: 10000
qlora_sharded_model_loading: false
ray_num_workers: 1
resources_per_worker:
  GPU: 1
sample_packing_bin_size: 200
sample_packing_group_size: 100000
save_only_model: false
save_safetensors: true
sequence_len: 4096
shuffle_merged_datasets: true
skip_prepare_dataset: false
strict: false
train_on_inputs: false
trl:
  log_completions: false
  ref_model_mixup_alpha: 0.9
  ref_model_sync_steps: 64
  sync_ref_model: false
  use_vllm: false
  vllm_device: auto
  vllm_dtype: auto
  vllm_gpu_memory_utilization: 0.9
use_ray: false
val_set_size: 0.0
weight_decay: 0.0

outputs/mymodel

This model is a fine-tuned version of deepseek-ai/DeepSeek-V2-Lite-Chat on the ./train.jsonl dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0002
train_batch_size: 1
eval_batch_size: 1
seed: 42
optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 27
num_epochs: 1.0

Training results

Framework versions

PEFT 0.14.0
Transformers 4.48.3
Pytorch 2.4.0+cu121
Datasets 3.2.0
Tokenizers 0.21.1

deevade/DeepSeek-V2-Lite-Chat-finetuned

outputs/mymodel

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

deevade/
DeepSeek-V2-Lite-Chat-finetuned