base_model: Qwen/CodeQwen1.5-7B-Chat
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false
 
datasets:
  - path: /workspace/axolotl/vinh/PAL/input_output_qwen.json
    type: input_output
  - path: /workspace/axolotl/vinh/INSTRUCT/input_output_qwen.json
    type: input_output
dataset_prepared_path:
val_set_size: 0.05
eval_sample_packing: false
output_dir: /workspace/axolotl/vinh/Qwen_CodeQwen1.5-7B-Chat-lora-2024-07-01-02-04-03

sequence_len: 2048
sample_packing: false
pad_to_sequence_len: false

adapter: lora
lora_model_dir: 
lora_r: 64
lora_alpha: 128
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 128
micro_batch_size: 1
num_epochs: 3
optimizer: paged_adamw_32bit
lr_scheduler: cosine
learning_rate: 2e-4

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention: 
flash_attention: true
s2_attention:

loss_watchdog_threshold: 5.0
loss_watchdog_patience: 3

warmup_steps: 10
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 512
saves_per_epoch: 2
save_total_limit: 20
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config: