Tippawan/proof-reading-SeaLLM3-7B-Chat-3090-v3

base_model: SeaLLMs/SeaLLM3-7B-Chat
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false

datasets:
  - path: Tippawan/pr-v3
    type: sharegpt
    conversation: chatml
    field_messages: messages
chat_template: chatml
dataset_prepared_path:
val_set_size: 0.00 #editted 2
output_dir: ./outputs/outputs_name

sequence_len: 2048
sample_packing: false
eval_sample_packing: false
pad_to_sequence_len: false

push_to_hub: true
hub_model_id: Tippawan/proof-reading-SeaLLM3-7B-Chat-3090-v3  # Replace with your Hugging Face repo ID
use_auth_token: true  # Ensure you have set your Hugging Face API token in the environment
hub_private_repo: true  # Set to true if you want the repository to be private
hub_strategy: all_checkpoints
save_total_limit: 3
load_best_model_at_end: true

adapter: qlora
lora_model_dir:
lora_r: 16
lora_alpha: 32
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: proof-reading-SeaLLM3-7B-Chat-3090-v3
wandb_entity: 
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1 #editted 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
seed: 42
warmup_steps: 10
evals_per_epoch: 1
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens: