[LLM] Llama 3.1 finetuning

llm/llama-31-finetuning/configs/70B-lora.yaml

@@ -0,0 +1,99 @@
+# Config for multi-device LoRA in lora_finetune_distributed.py
+# using a Llama3.1 70B model
+#
+# This config assumes that you've run the following command before launching
+# this run:
+#   tune download meta-llama/Meta-Llama-3.1-70B-Instruct --output-dir /tmp/Meta-Llama-3.1-70B-Instruct --ignore-patterns "original/consolidated*"
+#
+# This config needs 8 GPUs to run
+#   tune run --nproc_per_node 8 lora_finetune_distributed --config llama3_1/70B_lora
+
+# Model Arguments
+model:
+  _component_: torchtune.models.llama3_1.lora_llama3_1_70b
+  lora_attn_modules: ['q_proj', 'k_proj', 'v_proj']
+  apply_lora_to_mlp: False
+  apply_lora_to_output: False
+  lora_rank: 16
+  lora_alpha: 32
+
+tokenizer:
+  _component_: torchtune.models.llama3.llama3_tokenizer
+  path: /tmp/Meta-Llama-3.1-70B-Instruct/original/tokenizer.model
+
+checkpointer:
+  _component_: torchtune.utils.FullModelHFCheckpointer
+  checkpoint_dir: /tmp/Meta-Llama-3.1-70B-Instruct/
+  checkpoint_files: [
+    model-00001-of-00030.safetensors,
+    model-00002-of-00030.safetensors,
+    model-00003-of-00030.safetensors,
+    model-00004-of-00030.safetensors,
+    model-00005-of-00030.safetensors,
+    model-00006-of-00030.safetensors,
+    model-00007-of-00030.safetensors,
+    model-00008-of-00030.safetensors,
+    model-00009-of-00030.safetensors,
+    model-00010-of-00030.safetensors,
+    model-00011-of-00030.safetensors,
+    model-00012-of-00030.safetensors,
+    model-00013-of-00030.safetensors,
+    model-00014-of-00030.safetensors,
+    model-00015-of-00030.safetensors,
+    model-00016-of-00030.safetensors,
+    model-00017-of-00030.safetensors,
+    model-00018-of-00030.safetensors,
+    model-00019-of-00030.safetensors,
+    model-00020-of-00030.safetensors,
+    model-00021-of-00030.safetensors,
+    model-00022-of-00030.safetensors,
+    model-00023-of-00030.safetensors,
+    model-00024-of-00030.safetensors,
+    model-00025-of-00030.safetensors,
+    model-00026-of-00030.safetensors,
+    model-00027-of-00030.safetensors,
+    model-00028-of-00030.safetensors,
+    model-00029-of-00030.safetensors,
+    model-00030-of-00030.safetensors,
+  ]
+  recipe_checkpoint: null
+  output_dir: /tmp/Meta-Llama-3.1-70B-Instruct/
+  model_type: LLAMA3
+resume_from_checkpoint: False
+
+# Dataset and Sampler
+dataset:
+  _component_: torchtune.datasets.alpaca_dataset
+seed: null
+shuffle: True
+batch_size: 2
+
+# Optimizer and Scheduler
+optimizer:
+  _component_: torch.optim.AdamW
+  weight_decay: 0.01
+  lr: 3e-4
+lr_scheduler:
+  _component_: torchtune.modules.get_cosine_schedule_with_warmup
+  num_warmup_steps: 100
+
+loss:
+  _component_: torch.nn.CrossEntropyLoss
+
+# Training
+epochs: 1
+max_steps_per_epoch: null
+gradient_accumulation_steps: 1
+
+# Logging
+output_dir: /tmp/lora_finetune_output
+metric_logger:
+  _component_: torchtune.utils.metric_logging.DiskLogger
+  log_dir: ${output_dir}
+log_every_n_steps: 1
+log_peak_memory_stats: False
+
+# Environment
+device: cuda
+dtype: bf16
+enable_activation_checkpointing: True

llm/llama-31-finetuning/configs/8B-lora.yaml

@@ -0,0 +1,83 @@
+# Config for multi-device LoRA finetuning in lora_finetune_distributed.py
+# using a Llama3.1 8B Instruct model
+#
+# This config assumes that you've run the following command before launching
+# this run:
+#   tune download meta-llama/Meta-Llama-3.1-8B-Instruct --output-dir /tmp/Meta-Llama-3.1-8B-Instruct --ignore-patterns "original/consolidated.00.pth"
+#
+# To launch on 2 devices, run the following command from root:
+#   tune run --nproc_per_node 2 lora_finetune_distributed --config llama3_1/8B_lora
+#
+# You can add specific overrides through the command line. For example
+# to override the checkpointer directory while launching training
+# you can run:
+#   tune run --nproc_per_node 2 lora_finetune_distributed --config llama3_1/8B_lora checkpointer.checkpoint_dir=<YOUR_CHECKPOINT_DIR>
+#
+# This config works best when the model is being fine-tuned on 2+ GPUs.
+# For single device LoRA finetuning please use 8B_lora_single_device.yaml
+# or 8B_qlora_single_device.yaml
+
+# Tokenizer
+tokenizer:
+  _component_: torchtune.models.llama3.llama3_tokenizer
+  path: /tmp/Meta-Llama-3.1-8B-Instruct/original/tokenizer.model
+
+# Model Arguments
+model:
+  _component_: torchtune.models.llama3_1.lora_llama3_1_8b
+  lora_attn_modules: ['q_proj', 'v_proj']
+  apply_lora_to_mlp: False
+  apply_lora_to_output: False
+  lora_rank: 8
+  lora_alpha: 16
+
+checkpointer:
+  _component_: torchtune.utils.FullModelHFCheckpointer
+  checkpoint_dir: /tmp/Meta-Llama-3.1-8B-Instruct/
+  checkpoint_files: [
+    model-00001-of-00004.safetensors,
+    model-00002-of-00004.safetensors,
+    model-00003-of-00004.safetensors,
+    model-00004-of-00004.safetensors
+  ]
+  recipe_checkpoint: null
+  output_dir: /tmp/Meta-Llama-3.1-8B-Instruct/
+  model_type: LLAMA3
+resume_from_checkpoint: False
+
+# Dataset and Sampler
+dataset:
+  _component_: torchtune.datasets.alpaca_cleaned_dataset
+seed: null
+shuffle: True
+batch_size: 2
+
+# Optimizer and Scheduler
+optimizer:
+  _component_: torch.optim.AdamW
+  weight_decay: 0.01
+  lr: 3e-4
+lr_scheduler:
+  _component_: torchtune.modules.get_cosine_schedule_with_warmup
+  num_warmup_steps: 100
+
+loss:
+  _component_: torch.nn.CrossEntropyLoss
+
+# Training
+epochs: 1
+max_steps_per_epoch: null
+gradient_accumulation_steps: 32
+
+# Logging
+output_dir: /tmp/lora_finetune_output
+metric_logger:
+  _component_: torchtune.utils.metric_logging.DiskLogger
+  log_dir: ${output_dir}
+log_every_n_steps: 1
+log_peak_memory_stats: False
+
+# Environment
+device: cuda
+dtype: bf16
+enable_activation_checkpointing: False

llm/llama-31-finetuning/lora.yaml

@@ -0,0 +1,58 @@
+# LoRA finetuning Meta Llama-3.1 on any of your own infra.
+#
+# Usage:
+#
+#  HF_TOKEN=xxx sky launch lora.yaml -c llama31 --env HF_TOKEN
+#
+# To finetune a 70B model:  
+#
+#  HF_TOKEN=xxx sky launch lora.yaml -c llama31-70 --env HF_TOKEN --env MODEL_SIZE=70B
+
+envs:
+  MODEL_SIZE: 8B
+  HF_TOKEN:
+  DATASET: "yahma/alpaca-cleaned"
+  # Change this to your own checkpoint bucket
+  CHECKPOINT_BUCKET_NAME: sky-llama-31-checkpoints
+
+
+resources:
+  accelerators: A100:8
+  disk_tier: best
+  use_spot: true
+
+file_mounts:
+  /configs: ./configs
+  /output:
+    name: $CHECKPOINT_BUCKET_NAME
+    mode: MOUNT
+    # Optionally, specify the store to enforce to use one of the stores below:
+    #   r2/azure/gcs/s3/cos
+    # store: r2
+
+setup: |
+  pip install torch torchvision
+
+  # Install torch tune from source for the latest Llama-3.1 model
+  pip install git+https://github.com/pytorch/torchtune.git@58255001bd0b1e3a81a6302201024e472af05379
+  # pip install torchtune
+
+  tune download meta-llama/Meta-Llama-3.1-${MODEL_SIZE}-Instruct \
+    --hf-token $HF_TOKEN \
+    --output-dir /tmp/Meta-Llama-3.1-${MODEL_SIZE}-Instruct \
+    --ignore-patterns "original/consolidated*"
+
+run: |
+  tune run --nproc_per_node $SKYPILOT_NUM_GPUS_PER_NODE \
+    lora_finetune_distributed \
+    --config /configs/${MODEL_SIZE}-lora.yaml \
+    dataset.source=$DATASET
+
+  # Remove the checkpoint files to save space, LoRA serving only needs the
+  # adapter files.
+  rm /tmp/Meta-Llama-3.1-${MODEL_SIZE}-Instruct/*.pt
+  rm /tmp/Meta-Llama-3.1-${MODEL_SIZE}-Instruct/*.safetensors
+
+  mkdir -p /output/$MODEL_SIZE-lora
+  rsync -Pavz /tmp/Meta-Llama-3.1-${MODEL_SIZE}-Instruct /output/$MODEL_SIZE-lora
+  cp -r /tmp/lora_finetune_output /output/$MODEL_SIZE-lora/