Last active
October 6, 2024 14:25
-
-
Save almugabo/d1ae25cd86c1e60ed610995e01fe4037 to your computer and use it in GitHub Desktop.
TorchTune recipe config
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| ## to make it easier to work with the paths in torchtune | |
| path_model_downloaded: /home/mike/_torch_tune/_xmodel_downloaded/MetaLlama-3.1-8B | |
| path_model_finetuned: /home/mike/_torch_tune/_xmodel_finetuned/MetaLlama-3.1-8B_finetuned | |
| # Tokenizer | |
| tokenizer: | |
| _component_: torchtune.models.llama3.llama3_tokenizer | |
| path: ${path_model_downloaded}/original/tokenizer.model | |
| max_seq_len: 2048 | |
| # Dataset | |
| # Dataset | |
| dataset: | |
| _component_: torchtune.datasets.text_completion_dataset | |
| source: json | |
| data_files: /home/mike/data_infrastructure/text_monolingual_train.json | |
| column: text | |
| split: train | |
| seed: null | |
| shuffle: True | |
| # Model Arguments | |
| model: | |
| _component_: torchtune.models.llama3_1.llama3_1_8b | |
| checkpointer: | |
| _component_: torchtune.training.FullModelHFCheckpointer | |
| checkpoint_dir: ${path_model_downloaded} | |
| 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: ${path_model_finetuned} | |
| model_type: LLAMA3 | |
| resume_from_checkpoint: False | |
| # Fine-tuning arguments | |
| batch_size: 2 | |
| epochs: 1 | |
| optimizer: | |
| _component_: bitsandbytes.optim.PagedAdamW8bit | |
| lr: 2e-5 | |
| loss: | |
| _component_: torchtune.modules.loss.CEWithChunkedOutputLoss | |
| max_steps_per_epoch: null | |
| gradient_accumulation_steps: 1 | |
| optimizer_in_bwd: True | |
| compile: False # set it to True for better memory and performance | |
| # Training environment | |
| device: cuda | |
| # Memory management | |
| enable_activation_checkpointing: True | |
| # Reduced precision | |
| dtype: bf16 | |
| # Logging | |
| metric_logger: | |
| _component_: torchtune.training.metric_logging.DiskLogger | |
| log_dir: ${path_model_finetuned}/logs | |
| output_dir: ${path_model_finetuned} | |
| log_every_n_steps: 1 | |
| log_peak_memory_stats: False | |
| # Profiler (disabled) | |
| profiler: | |
| _component_: torchtune.training.setup_torch_profiler | |
| enabled: False | |
| #Output directory of trace artifacts | |
| output_dir: ${path_model_finetuned}/profiling_outputs | |
| #`torch.profiler.ProfilerActivity` types to trace | |
| cpu: True | |
| cuda: True | |
| #trace options passed to `torch.profiler.profile` | |
| profile_memory: True | |
| with_stack: False | |
| record_shapes: True | |
| with_flops: False | |
| # `torch.profiler.schedule` options: | |
| # wait_steps -> wait, warmup_steps -> warmup, active_steps -> active, num_cycles -> repeat | |
| wait_steps: 1 | |
| warmup_steps: 2 | |
| active_steps: 1 | |
| num_cycles: 1 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment