RichardErkhov/

OwenArli_-_ArliAI-Llama-3-8B-Dolfin-v0.2-Instruct-gguf

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

{{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>

{{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

{{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|>

{{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

base_model: /home/owen/models/Meta-Llama-3-8B-Instruct
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
  
train_on_inputs: false
group_by_length: false
load_in_8bit: false
load_in_4bit: true
strict: false
sequence_len: 4096
bf16: true
fp16: false
tf32: false
flash_attention: true

# Data
datasets:
  - path: /home/owen/datasets/cleaned-dolphin201-sharegpt2-uuid-improved.jsonl
    type:
      field_instruction: input
      field_output: output
      format: "<|start_header_id|>user<|end_header_id|>\n\n{instruction}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n"
      no_input_format: "<|start_header_id|>user<|end_header_id|>\n\n{instruction}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n"
    
warmup_steps: 10
dataset_prepared_path: ./last_run_prepared

# Iterations
num_epochs: 1
saves_per_epoch: 4

# Evaluation
val_set_size: 0.01
eval_table_size:
eval_table_max_new_tokens:
eval_sample_packing: false
evals_per_epoch: 4

# LoRA
output_dir: ./qlora-out
adapter: qlora
lora_model_dir:
lora_r: 64
lora_alpha: 128
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
lora_target_modules:
save_safetensors: true

# Sampling
sample_packing: true
pad_to_sequence_len: true

# Batching
gradient_accumulation_steps: 32
micro_batch_size: 2
gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: true

# wandb
wandb_mode: # "offline" to save run metadata locally and not sync to the server, "disabled" to turn off wandb
wandb_project: llama-3-8b-instruct-dolphin-q
wandb_entity: # A wandb Team name if using a Team
wandb_watch:
wandb_name: 64-128-4096-1ep-v0.2
wandb_run_id: # Set the ID of your wandb run
wandb_log_model: # "checkpoint" to log model to wandb Artifacts every `save_steps` or "end" to log only at the end of training

# Optimizer
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

# Misc
early_stopping_patience:
resume_from_checkpoint:
logging_steps: 1
debug:
deepspeed: /home/owen/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.1
special_tokens:
   pad_token: <|end_of_text|>