From 777265a185391354b49ddba7877de7a8f4f8b86f Mon Sep 17 00:00:00 2001
From: Kaiyu Yang <kaiyuy@meta.com>
Date: Tue, 2 Jul 2024 18:27:20 +0000
Subject: [PATCH] add torchtune

---
 torchtune/confs/llama3-8B_full.yaml | 77 +++++++++++++++++++++++++++++
 1 file changed, 77 insertions(+)
 create mode 100644 torchtune/confs/llama3-8B_full.yaml

diff --git a/torchtune/confs/llama3-8B_full.yaml b/torchtune/confs/llama3-8B_full.yaml
new file mode 100644
index 0000000..d2d060d
--- /dev/null
+++ b/torchtune/confs/llama3-8B_full.yaml
@@ -0,0 +1,77 @@
+# Config for multi-device full finetuning in full_finetune_distributed.py
+# using a Llama3 8B model
+#
+# This config assumes that you've run the following command before launching
+# this run:
+#   tune download meta-llama/Meta-Llama-3-8B --output-dir /tmp/Meta-Llama-3-8B --hf-token <HF_TOKEN>
+#
+# To launch on 4 devices, run the following command from root:
+#   tune run --nproc_per_node 4 full_finetune_distributed --config llama3/8B_full
+#
+# 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 4 full_finetune_distributed --config llama3/8B_full checkpointer.checkpoint_dir=<YOUR_CHECKPOINT_DIR>
+#
+# This config works best when the model is being fine-tuned on 2+ GPUs.
+# Single device full finetuning requires more memory optimizations. It's
+# best to use 8B_full_single_device.yaml for those cases
+
+
+# Tokenizer
+tokenizer:
+  _component_: torchtune.models.llama3.llama3_tokenizer
+  path: /tmp/Meta-Llama-3-8B/original/tokenizer.model
+
+# Dataset
+dataset:
+  _component_: torchtune.datasets.alpaca_dataset
+  train_on_input: True
+seed: null
+shuffle: True
+
+# Model Arguments
+model:
+  _component_: torchtune.models.llama3.llama3_8b
+
+checkpointer:
+  _component_: torchtune.utils.FullModelMetaCheckpointer
+  checkpoint_dir: /tmp/Meta-Llama-3-8B/original/
+  checkpoint_files: [
+    consolidated.00.pth
+  ]
+  recipe_checkpoint: null
+  output_dir: /tmp/Meta-Llama-3-8B/
+  model_type: LLAMA3
+resume_from_checkpoint: False
+
+# Fine-tuning arguments
+batch_size: 2
+epochs: 3
+
+optimizer:
+  _component_: torch.optim.AdamW
+  lr: 2e-5
+  foreach: False
+
+loss:
+  _component_: torch.nn.CrossEntropyLoss
+max_steps_per_epoch: null
+gradient_accumulation_steps: 1
+
+
+# Training env
+device: cuda
+
+# Memory management
+enable_activation_checkpointing: True
+
+# Reduced precision
+dtype: bf16
+
+# Logging
+metric_logger:
+  _component_: torchtune.utils.metric_logging.DiskLogger
+  log_dir: ${output_dir}
+output_dir: /tmp/alpaca-llama3-finetune
+log_every_n_steps: null