Gemma

recipes/configs/gemma/2B_full.yaml

@@ -0,0 +1,86 @@
+# Config for multi-device full finetuning in full_finetune_distributed.py
+# using a gemma 2B model
+#
+# This config assumes that you've run the following command before launching
+# this run:
+#   tune download --repo-id google/gemma-2b \
+#   --hf-token <HF_TOKEN> \
+#   --output-dir /tmp/gemma2
+#
+# To launch on 4 devices, run the following command from root:
+#   tune --nnodes 1 --nproc_per_node 4 full_finetune_distributed \
+#   --config gemma/2B_full \
+#
+# You can add specific overrides through the command line. For example
+# to override the checkpointer directory while launching training
+# you can run:
+#   tune --nnodes 1 --nproc_per_node 4 full_finetune_distributed \
+#   --config gemma/2B_full \
+#   checkpointer.checkpoint_dir=<YOUR_CHECKPOINT_DIR>
+#
+# This config works only when the model is being fine-tuned on 2+ GPUs.
+
+
+# Tokenizer
+tokenizer:
+  _component_: torchtune.models.gemma.gemma_tokenizer
+  path: /tmp/gemma/tokenizer.model
+
+# Dataset
+dataset:
+  _component_: torchtune.datasets.alpaca_dataset
+  train_on_input: True
+seed: null
+shuffle: True
+
+# Model Arguments
+model:
+  _component_: torchtune.models.gemma.gemma_2b
+
+checkpointer:
+  _component_: torchtune.utils.FullModelHFCheckpointer
+  checkpoint_dir: /tmp/gemma/
+  checkpoint_files: [
+    model-00001-of-00002.safetensors,
+    model-00002-of-00002.safetensors,
+  ]
+  recipe_checkpoint: null
+  output_dir: /tmp/gemma
+  model_type: GEMMA
+share_weights:
+  share_weights: True
+  weight_tying_config: {
+    "output": "tok_embeddings"
+  }
+resume_from_checkpoint: False
+
+# Fine-tuning arguments
+batch_size: 2
+epochs: 3
+optimizer:
+  _component_: torch.optim.AdamW
+  lr: 2e-5
+loss:
+  _component_: torch.nn.CrossEntropyLoss
+max_steps_per_epoch: null
+gradient_accumulation_steps: 1
+
+
+# Training env
+device: cuda
+
+# Distributed
+cpu_offload: False
+
+# 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-gemma-finetune
+log_every_n_steps: null