pandyamarut/ByteDance-SeedCoder-LoRA

adapter: lora
base_model: ByteDance-Seed/Seed-Coder-8B-Instruct
bf16: true
dataset_prepared_path: last_run_prepared

# Dataset configuration for instruction/input/output format
datasets:
- chat_template: tokenizer_default
  field_messages: messages
  message_field_content: content
  message_field_role: role
  path: data_clean.jsonl
  roles:
    assistant:
    - assistant
    system:
    - system
    user:
    - user
  type: chat_template

debug: null
deepspeed: /osmosis/zero2.json
early_stopping_patience: null
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
group_by_length: false
learning_rate: 0.0001
liger_fused_linear_cross_entropy: true
liger_glu_activation: true
liger_layer_norm: true
liger_rms_norm: true
liger_rope: true
load_in_4bit: false
load_in_8bit: false
logging_steps: 1
lora_alpha: 64
lora_dropout: 0.05
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lr_scheduler: cosine
max_grad_norm: 1
micro_batch_size: 4
model_type: AutoModelForCausalLM
num_epochs: 1
optimizer: adamw_torch
output_dir: ./lora-sout-SC-highseq-len
pad_to_sequence_len: true
plugins:
- axolotl.integrations.liger.LigerPlugin
resume_from_checkpoint: null
sample_packing: false
save_steps: 60
save_total_limit: 100
sequence_len: 8192
# special_tokens:
#   eos_token: <|im_end|>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.0
wandb_entity: test-aa
wandb_project: seedcoder
wandb_log_model: null
wandb_name: No-mods-seedcoder-low-gas-high-seq-len
wandb_watch: null
warmup_ratio: 0.05
weight_decay: 0.0
xformers_attention: null