See axolotl config

axolotl version: 0.4.0

yaml

1base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T 2model_type: LlamaForCausalLM 3tokenizer_type: LlamaTokenizer 4 5load_in_8bit: true 6load_in_4bit: false 7strict: false 8 9datasets: 10 - path: kareemamrr/databricks-dolly-4.5k 11 type: alpaca 12dataset_prepared_path: 13val_set_size: 0.05 14output_dir: ./outputs/lora-out 15 16sequence_len: 4096 17sample_packing: true 18eval_sample_packing: false 19pad_to_sequence_len: true 20 21adapter: lora 22lora_model_dir: 23lora_r: 16 24lora_alpha: 16 25lora_dropout: 0.5 26lora_target_linear: true 27lora_fan_in_fan_out: 28 29# wandb_project: tinyllama-dolly-axolotl 30# wandb_entity: kamr54 31 32hub_model_id: kareemamrr/tinyllama-1.1B_dolly-4.5k_lora 33 34gradient_accumulation_steps: 4 35micro_batch_size: 2 36num_epochs: 4 37optimizer: adamw_bnb_8bit 38lr_scheduler: 39learning_rate: 0.0004 40 41train_on_inputs: false 42group_by_length: false 43bf16: auto 44fp16: 45tf32: false 46 47gradient_checkpointing: true 48early_stopping_patience: 49resume_from_checkpoint: 50local_rank: 51logging_steps: 1 52xformers_attention: 53flash_attention: true 54 55warmup_steps: 10 56evals_per_epoch: 4 57saves_per_epoch: 1 58debug: 59deepspeed: 60weight_decay: 0.0 61fsdp: 62fsdp_config: 63special_tokens:

tinyllama-1.1B_dolly-4.5k_lora

• Loss: 1.7650

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

• learning_rate: 0.0004
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 10
• num_epochs: 4

Training results

Framework versions

• PEFT 0.10.0
• Transformers 4.40.2
• Pytorch 2.1.2+cu118
• Datasets 2.19.1
• Tokenizers 0.19.1