diff --git a/.nojekyll b/.nojekyll index ef2dcf1cd..8b207ffd3 100644 --- a/.nojekyll +++ b/.nojekyll @@ -1 +1 @@ -79e3fa9c \ No newline at end of file +1f397381 \ No newline at end of file diff --git a/docs/config.html b/docs/config.html index fcf378367..be4e8ed24 100644 --- a/docs/config.html +++ b/docs/config.html @@ -397,7 +397,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin datasets: # HuggingFace dataset repo | s3://,gs:// path | "json" for local dataset, make sure to fill data_files - path: vicgalle/alpaca-gpt4 - # The type of prompt to use for training. [alpaca, sharegpt, gpteacher, oasst, reflection] + # The type of prompt to use for training. [alpaca, gpteacher, oasst, reflection] type: alpaca # format | format:<prompt_style> (chat/instruct) | <prompt_strategies>.load_<load_fn> ds_type: # Optional[str] (json|arrow|parquet|text|csv) defines the datatype when path is a file data_files: # Optional[str] path to source data files @@ -406,434 +406,425 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin train_on_split: train # Optional[str] name of dataset split to load from revision: # Optional[str] The specific revision of the dataset to use when loading from the Hugging Face Hub. This can be a commit hash, tag, or branch name. If not specified, the latest version will be used. This parameter is ignored for local datasets. - # Optional[str] fastchat conversation type, only used with type: sharegpt - conversation: # Options (see Conversation 'name'): https://github.com/lm-sys/FastChat/blob/main/fastchat/conversation.py - field_human: # Optional[str]. Human key to use for conversation. - field_model: # Optional[str]. Assistant key to use for conversation. - # Add additional keys from your dataset as input or output roles - roles: - input: # Optional[List[str]]. These will be masked based on train_on_input - output: # Optional[List[str]]. - - # Custom user instruction prompt - - path: repo - type: - # The below are defaults. only set what's needed if you use a different column name. - system_prompt: "" - system_format: "{system}" - field_system: system - field_instruction: instruction - field_input: input - field_output: output + # Custom user instruction prompt + - path: repo + type: + # The below are defaults. only set what's needed if you use a different column name. + system_prompt: "" + system_format: "{system}" + field_system: system + field_instruction: instruction + field_input: input + field_output: output + + # Customizable to be single line or multi-line + # Use {instruction}/{input} as key to be replaced + # 'format' can include {input} + format: |- + User: {instruction} {input} + Assistant: + # 'no_input_format' cannot include {input} + no_input_format: "{instruction} " - # Customizable to be single line or multi-line - # Use {instruction}/{input} as key to be replaced - # 'format' can include {input} - format: |- - User: {instruction} {input} - Assistant: - # 'no_input_format' cannot include {input} - no_input_format: "{instruction} " - - # For `completion` datsets only, uses the provided field instead of `text` column - field: - - # Using chat template - - path: ... - # Set type to `chat_template` to use this strategy - type: chat_template - # Specify the name of the chat template to use - # The name of the chat template to use for training, following values are supported: - # - tokenizer_default: Uses the chat template that is available in the tokenizer_config.json. If the chat template is not available in the tokenizer, it will raise an error. This is the default. - # - alpaca/inst/chatml/gemma/cohere/llama3/phi_3/deepseek_v2/jamba: These chat templates are available in the axolotl codebase at src/axolotl/utils/chat_templates.py - # - tokenizer_default_fallback_*: where * is the name of the chat template to fallback to if the tokenizer does not have a chat template else default to tokenizer. E.g. tokenizer_default_fallback_chatml. - # - jinja: Uses a custom jinja template for the chat template. The custom jinja template should be provided in the chat_template_jinja field. - chat_template: tokenizer_default - # Custom jinja template for chat template. This will be only used if `chat_template` is set to `jinja` or empty (in which case chat_template is automatically set to `jinja`). - chat_template_jinja: - # The key in the data example that contains the messages. Default is "messages". - field_messages: messages - # The key in the message turn that contains the role. Default is "role". - message_field_role: role - # The key in the message turn that contains the content. Default is "content". - message_field_content: content - # Optional[Dict[str, List]]. Roles mapping for the messages. - roles: - user: ["human", "user"] - assistant: ["gpt", "assistant", "ai"] - system: ["system"] - - ## NOTE: Leaving the below empty will default to using the simple legacy tokenization strategy where only last message is trained on. - - # Optional[List[str]]. Roles to train on. The tokens from these roles will be considered for the loss. - roles_to_train: ["gpt", "assistant"] - # Optional[str]. Which EOS tokens to train on in the conversation. Possible values are: - # - all: train on all EOS tokens - # - turn: train on the EOS token at the end of each trainable turn - # - last: train on the last EOS token in the conversation - train_on_eos: last - # The key in the message turn that indicates via boolean whether tokens of a turn should be considered for training. Useful to selectively train on certain turns besides the `roles_to_train`. - message_field_training: training - # The key in the message turn that contains the training details. Useful to selectively train on certain tokens in a turn. - # The value of the key is a List[Dict] containing `begin_offset` (start character index in content), `end_offset` (end character index in content), and `train` (boolean whether to train). - # See example at `docs/dataset-formats/conversation.qmd` - message_field_training_detail: train_detail - - -# If false, the datasets will not be shuffled and will keep their original order in `datasets`. -# The same applies to the `test_datasets` option and the `pretraining_dataset` option. Default is true. -shuffle_merged_datasets: true - -# A list of one or more datasets to eval the model with. -# You can use either test_datasets, or val_set_size, but not both. -test_datasets: - - path: /workspace/data/eval.jsonl - ds_type: json - # You need to specify a split. For "json" datasets the default split is called "train". - split: train - type: completion - data_files: - - /workspace/data/eval.jsonl - -# use RL training: 'dpo', 'ipo', 'kto' -rl: -# whether to perform weighting if doing DPO training. Boolean. -dpo_use_weighting: - -# The name of the chat template to use for training, following values are supported: -# - tokenizer_default: Uses the chat template that is available in the tokenizer_config.json. If the chat template is not available in the tokenizer, it will raise an error. This is the default value. -# - alpaca/inst/chatml/gemma/cohere/llama3/phi_3/deepseek_v2/jamba: These chat templates are available in the axolotl codebase at src/axolotl/utils/chat_templates.py -# - tokenizer_default_fallback_*: where * is the name of the chat template to fallback to. E.g. tokenizer_default_fallback_chatml. This is useful when the chat template is not available in the tokenizer. -# - jinja: Uses a custom jinja template for the chat template. The custom jinja template should be provided in the chat_template_jinja field. -# The selected chat template will be saved to the tokenizer_config.json for easier inferencing -# Note: It is recommended to set train_on_inputs to true when using a chat template that is different from the model's default chat template. -chat_template: tokenizer_default -# custom jinja template for chat template. This will be only used if chat_template is set to `jinja` or `null` (in which case chat_template is automatically set to `jinja`). Default is null. -chat_template_jinja: null -# Changes the default system message -default_system_message: You are a helpful assistant. Please give a long and detailed answer. # Currently only supports chatml. -# Axolotl attempts to save the dataset as an arrow after packing the data together so -# subsequent training attempts load faster, relative path -dataset_prepared_path: data/last_run_prepared -# Push prepared dataset to hub -push_dataset_to_hub: # repo path -# The maximum number of processes to use while preprocessing your input dataset. This defaults to `os.cpu_count()` -# if not set. -dataset_processes: # defaults to os.cpu_count() if not set -# Keep dataset in memory while preprocessing -# Only needed if cached dataset is taking too much storage -dataset_keep_in_memory: -# push checkpoints to hub -hub_model_id: # private repo path to push finetuned model -# how to push checkpoints to hub -# https://huggingface.co/docs/transformers/v4.31.0/en/main_classes/trainer#transformers.TrainingArguments.hub_strategy -hub_strategy: -# Whether to use hf `use_auth_token` for loading datasets. Useful for fetching private datasets -# Required to be true when used in combination with `push_dataset_to_hub` -hf_use_auth_token: # boolean -# How much of the dataset to set aside as evaluation. 1 = 100%, 0.50 = 50%, etc. 0 for no eval. -val_set_size: 0.04 -# Num shards for whole dataset -dataset_shard_num: -# Index of shard to use for whole dataset -dataset_shard_idx: - -# The maximum length of an input to train with, this should typically be less than 2048 -# as most models have a token/context limit of 2048 -sequence_len: 2048 -# Pad inputs so each step uses constant sized buffers -# This will reduce memory fragmentation and may prevent OOMs, by re-using memory more efficiently -pad_to_sequence_len: -# Use efficient multi-packing with block diagonal attention and per sequence position_ids. Recommend set to 'true' -sample_packing: -# Set to 'false' if getting errors during eval with sample_packing on. -eval_sample_packing: -# You can set these packing optimizations AFTER starting a training at least once. -# The trainer will provide recommended values for these values. -sample_packing_eff_est: -total_num_tokens: -# Increasing the following values helps with packing, but usually only slightly (<%1.) -# The number of samples packed at a time. -sample_packing_group_size: 100000 -# The number of samples which can be packed into one sequence. Increase if using a large sequence_len with many short samples. -sample_packing_bin_size: 200 - -# Passed through to transformers when loading the model when launched without accelerate -# Use `sequential` when training w/ model parallelism to limit memory -device_map: -# Defines the max memory usage per gpu on the system. Passed through to transformers when loading the model. -max_memory: - -# If you want to use 'lora' or 'qlora' or leave blank to train all parameters in original model -adapter: lora -# If you already have a lora model trained that you want to load, put that here. -# This means after training, if you want to test the model, you should set this to the value of `output_dir`. -# Note that if you merge an adapter to the base model, a new subdirectory `merged` will be created under the `output_dir`. -lora_model_dir: - -# LoRA hyperparameters -# For more details about the following options, see: -# https://www.anyscale.com/blog/fine-tuning-llms-lora-or-full-parameter-an-in-depth-analysis-with-llama-2 -lora_r: 8 -lora_alpha: 16 -lora_dropout: 0.05 -lora_target_modules: - - q_proj - - v_proj -# - k_proj -# - o_proj -# - gate_proj -# - down_proj -# - up_proj -lora_target_linear: # If true, will target all linear modules -peft_layers_to_transform: # The layer indices to transform, otherwise, apply to all layers - -# If you added new tokens to the tokenizer, you may need to save some LoRA modules because they need to know the new tokens. -# For LLaMA and Mistral, you need to save `embed_tokens` and `lm_head`. It may vary for other models. -# `embed_tokens` converts tokens to embeddings, and `lm_head` converts embeddings to token probabilities. -# https://github.com/huggingface/peft/issues/334#issuecomment-1561727994 -lora_modules_to_save: -# - embed_tokens -# - lm_head - -lora_fan_in_fan_out: false - -# LoRA+ hyperparameters -# For more details about the following options, see: -# https://arxiv.org/abs/2402.12354 and `src/axolotl/core/train_builder.py` -loraplus_lr_ratio: # loraplus learning rate ratio lr_B / lr_A. Recommended value is 2^4. -loraplus_lr_embedding: # loraplus learning rate for lora embedding layers. Default value is 1e-6. - -peft: - # Configuration options for loftq initialization for LoRA - # https://huggingface.co/docs/peft/developer_guides/quantization#loftq-initialization - loftq_config: - loftq_bits: # typically 4 bits - -# ReLoRA configuration -# Must use either 'lora' or 'qlora' adapter, and does not support fsdp or deepspeed -relora_steps: # Number of steps per ReLoRA restart -relora_warmup_steps: # Number of per-restart warmup steps -relora_anneal_steps: # Number of anneal steps for each relora cycle -relora_prune_ratio: # threshold for optimizer magnitude when pruning -relora_cpu_offload: # True to perform lora weight merges on cpu during restarts, for modest gpu memory savings - -# wandb configuration if you're using it -# Make sure your `WANDB_API_KEY` environment variable is set (recommended) or you login to wandb with `wandb login`. -wandb_mode: # "offline" to save run metadata locally and not sync to the server, "disabled" to turn off wandb -wandb_project: # Your wandb project name -wandb_entity: # A wandb Team name if using a Team -wandb_watch: -wandb_name: # Set the name of your wandb run -wandb_run_id: # Set the ID of your wandb run -wandb_log_model: # "checkpoint" to log model to wandb Artifacts every `save_steps` or "end" to log only at the end of training - -# mlflow configuration if you're using it -mlflow_tracking_uri: # URI to mlflow -mlflow_experiment_name: # Your experiment name -mlflow_run_name: # Your run name -hf_mlflow_log_artifacts: # set to true to copy each saved checkpoint on each save to mlflow artifact registry - -# Comet configuration if you're using it -# Make sure your `COMET_API_KEY` environment variable is set (recommended) or you login to Comet with `comet login`. -# Check out our documentation for more details https://www.comet.com/docs/v2/api-and-sdk/python-sdk/reference/Experiment-Creation/#comet_ml.start -use_comet: # Enable or disable Comet integration. -comet_api_key: # API key for Comet. Recommended to set via `comet login`. -comet_workspace: # Workspace name in Comet. Defaults to the user's default workspace. -comet_project_name: # Project name in Comet. Defaults to Uncategorized. -comet_experiment_key: # Identifier for the experiment. Used to append data to an existing experiment or control the key of new experiments. Default to a random key. -comet_mode: # Create a new experiment ("create") or log to an existing one ("get"). Default ("get_or_create") auto-selects based on configuration. -comet_online: # Set to True to log data to Comet server, or False for offline storage. Default is True. -comet_experiment_config: # Dictionary for additional configuration settings, see the doc for more details. + # For `completion` datsets only, uses the provided field instead of `text` column + field: + + # Using chat template + - path: ... + # Set type to `chat_template` to use this strategy + type: chat_template + # Specify the name of the chat template to use + # The name of the chat template to use for training, following values are supported: + # - tokenizer_default: Uses the chat template that is available in the tokenizer_config.json. If the chat template is not available in the tokenizer, it will raise an error. This is the default. + # - alpaca/inst/chatml/gemma/cohere/llama3/phi_3/deepseek_v2/jamba: These chat templates are available in the axolotl codebase at src/axolotl/utils/chat_templates.py + # - tokenizer_default_fallback_*: where * is the name of the chat template to fallback to if the tokenizer does not have a chat template else default to tokenizer. E.g. tokenizer_default_fallback_chatml. + # - jinja: Uses a custom jinja template for the chat template. The custom jinja template should be provided in the chat_template_jinja field. + chat_template: tokenizer_default + # Custom jinja template for chat template. This will be only used if `chat_template` is set to `jinja` or empty (in which case chat_template is automatically set to `jinja`). + chat_template_jinja: + # The key in the data example that contains the messages. Default is "messages". + field_messages: messages + # The key in the message turn that contains the role. Default is "role". + message_field_role: role + # The key in the message turn that contains the content. Default is "content". + message_field_content: content + # Optional[Dict[str, List]]. Roles mapping for the messages. + roles: + user: ["human", "user"] + assistant: ["gpt", "assistant", "ai"] + system: ["system"] + + ## NOTE: Leaving the below empty will default to using the simple legacy tokenization strategy where only last message is trained on. + + # Optional[List[str]]. Roles to train on. The tokens from these roles will be considered for the loss. + roles_to_train: ["gpt", "assistant"] + # Optional[str]. Which EOS tokens to train on in the conversation. Possible values are: + # - all: train on all EOS tokens + # - turn: train on the EOS token at the end of each trainable turn + # - last: train on the last EOS token in the conversation + train_on_eos: last + # The key in the message turn that indicates via boolean whether tokens of a turn should be considered for training. Useful to selectively train on certain turns besides the `roles_to_train`. + message_field_training: training + # The key in the message turn that contains the training details. Useful to selectively train on certain tokens in a turn. + # The value of the key is a List[Dict] containing `begin_offset` (start character index in content), `end_offset` (end character index in content), and `train` (boolean whether to train). + # See example at `docs/dataset-formats/conversation.qmd` + message_field_training_detail: train_detail + + +# If false, the datasets will not be shuffled and will keep their original order in `datasets`. +# The same applies to the `test_datasets` option and the `pretraining_dataset` option. Default is true. +shuffle_merged_datasets: true + +# A list of one or more datasets to eval the model with. +# You can use either test_datasets, or val_set_size, but not both. +test_datasets: + - path: /workspace/data/eval.jsonl + ds_type: json + # You need to specify a split. For "json" datasets the default split is called "train". + split: train + type: completion + data_files: + - /workspace/data/eval.jsonl + +# use RL training: 'dpo', 'ipo', 'kto' +rl: +# whether to perform weighting if doing DPO training. Boolean. +dpo_use_weighting: + +# The name of the chat template to use for training, following values are supported: +# - tokenizer_default: Uses the chat template that is available in the tokenizer_config.json. If the chat template is not available in the tokenizer, it will raise an error. This is the default value. +# - alpaca/inst/chatml/gemma/cohere/llama3/phi_3/deepseek_v2/jamba: These chat templates are available in the axolotl codebase at src/axolotl/utils/chat_templates.py +# - tokenizer_default_fallback_*: where * is the name of the chat template to fallback to. E.g. tokenizer_default_fallback_chatml. This is useful when the chat template is not available in the tokenizer. +# - jinja: Uses a custom jinja template for the chat template. The custom jinja template should be provided in the chat_template_jinja field. +# The selected chat template will be saved to the tokenizer_config.json for easier inferencing +# Note: It is recommended to set train_on_inputs to true when using a chat template that is different from the model's default chat template. +chat_template: tokenizer_default +# custom jinja template for chat template. This will be only used if chat_template is set to `jinja` or `null` (in which case chat_template is automatically set to `jinja`). Default is null. +chat_template_jinja: null +# Changes the default system message +default_system_message: You are a helpful assistant. Please give a long and detailed answer. # Currently only supports chatml. +# Axolotl attempts to save the dataset as an arrow after packing the data together so +# subsequent training attempts load faster, relative path +dataset_prepared_path: data/last_run_prepared +# Push prepared dataset to hub +push_dataset_to_hub: # repo path +# The maximum number of processes to use while preprocessing your input dataset. This defaults to `os.cpu_count()` +# if not set. +dataset_processes: # defaults to os.cpu_count() if not set +# Keep dataset in memory while preprocessing +# Only needed if cached dataset is taking too much storage +dataset_keep_in_memory: +# push checkpoints to hub +hub_model_id: # private repo path to push finetuned model +# how to push checkpoints to hub +# https://huggingface.co/docs/transformers/v4.31.0/en/main_classes/trainer#transformers.TrainingArguments.hub_strategy +hub_strategy: +# Whether to use hf `use_auth_token` for loading datasets. Useful for fetching private datasets +# Required to be true when used in combination with `push_dataset_to_hub` +hf_use_auth_token: # boolean +# How much of the dataset to set aside as evaluation. 1 = 100%, 0.50 = 50%, etc. 0 for no eval. +val_set_size: 0.04 +# Num shards for whole dataset +dataset_shard_num: +# Index of shard to use for whole dataset +dataset_shard_idx: + +# The maximum length of an input to train with, this should typically be less than 2048 +# as most models have a token/context limit of 2048 +sequence_len: 2048 +# Pad inputs so each step uses constant sized buffers +# This will reduce memory fragmentation and may prevent OOMs, by re-using memory more efficiently +pad_to_sequence_len: +# Use efficient multi-packing with block diagonal attention and per sequence position_ids. Recommend set to 'true' +sample_packing: +# Set to 'false' if getting errors during eval with sample_packing on. +eval_sample_packing: +# You can set these packing optimizations AFTER starting a training at least once. +# The trainer will provide recommended values for these values. +sample_packing_eff_est: +total_num_tokens: +# Increasing the following values helps with packing, but usually only slightly (<%1.) +# The number of samples packed at a time. +sample_packing_group_size: 100000 +# The number of samples which can be packed into one sequence. Increase if using a large sequence_len with many short samples. +sample_packing_bin_size: 200 + +# Passed through to transformers when loading the model when launched without accelerate +# Use `sequential` when training w/ model parallelism to limit memory +device_map: +# Defines the max memory usage per gpu on the system. Passed through to transformers when loading the model. +max_memory: + +# If you want to use 'lora' or 'qlora' or leave blank to train all parameters in original model +adapter: lora +# If you already have a lora model trained that you want to load, put that here. +# This means after training, if you want to test the model, you should set this to the value of `output_dir`. +# Note that if you merge an adapter to the base model, a new subdirectory `merged` will be created under the `output_dir`. +lora_model_dir: + +# LoRA hyperparameters +# For more details about the following options, see: +# https://www.anyscale.com/blog/fine-tuning-llms-lora-or-full-parameter-an-in-depth-analysis-with-llama-2 +lora_r: 8 +lora_alpha: 16 +lora_dropout: 0.05 +lora_target_modules: + - q_proj + - v_proj +# - k_proj +# - o_proj +# - gate_proj +# - down_proj +# - up_proj +lora_target_linear: # If true, will target all linear modules +peft_layers_to_transform: # The layer indices to transform, otherwise, apply to all layers + +# If you added new tokens to the tokenizer, you may need to save some LoRA modules because they need to know the new tokens. +# For LLaMA and Mistral, you need to save `embed_tokens` and `lm_head`. It may vary for other models. +# `embed_tokens` converts tokens to embeddings, and `lm_head` converts embeddings to token probabilities. +# https://github.com/huggingface/peft/issues/334#issuecomment-1561727994 +lora_modules_to_save: +# - embed_tokens +# - lm_head + +lora_fan_in_fan_out: false + +# LoRA+ hyperparameters +# For more details about the following options, see: +# https://arxiv.org/abs/2402.12354 and `src/axolotl/core/train_builder.py` +loraplus_lr_ratio: # loraplus learning rate ratio lr_B / lr_A. Recommended value is 2^4. +loraplus_lr_embedding: # loraplus learning rate for lora embedding layers. Default value is 1e-6. + +peft: + # Configuration options for loftq initialization for LoRA + # https://huggingface.co/docs/peft/developer_guides/quantization#loftq-initialization + loftq_config: + loftq_bits: # typically 4 bits + +# ReLoRA configuration +# Must use either 'lora' or 'qlora' adapter, and does not support fsdp or deepspeed +relora_steps: # Number of steps per ReLoRA restart +relora_warmup_steps: # Number of per-restart warmup steps +relora_anneal_steps: # Number of anneal steps for each relora cycle +relora_prune_ratio: # threshold for optimizer magnitude when pruning +relora_cpu_offload: # True to perform lora weight merges on cpu during restarts, for modest gpu memory savings + +# wandb configuration if you're using it +# Make sure your `WANDB_API_KEY` environment variable is set (recommended) or you login to wandb with `wandb login`. +wandb_mode: # "offline" to save run metadata locally and not sync to the server, "disabled" to turn off wandb +wandb_project: # Your wandb project name +wandb_entity: # A wandb Team name if using a Team +wandb_watch: +wandb_name: # Set the name of your wandb run +wandb_run_id: # Set the ID of your wandb run +wandb_log_model: # "checkpoint" to log model to wandb Artifacts every `save_steps` or "end" to log only at the end of training + +# mlflow configuration if you're using it +mlflow_tracking_uri: # URI to mlflow +mlflow_experiment_name: # Your experiment name +mlflow_run_name: # Your run name +hf_mlflow_log_artifacts: # set to true to copy each saved checkpoint on each save to mlflow artifact registry + +# Comet configuration if you're using it +# Make sure your `COMET_API_KEY` environment variable is set (recommended) or you login to Comet with `comet login`. +# Check out our documentation for more details https://www.comet.com/docs/v2/api-and-sdk/python-sdk/reference/Experiment-Creation/#comet_ml.start +use_comet: # Enable or disable Comet integration. +comet_api_key: # API key for Comet. Recommended to set via `comet login`. +comet_workspace: # Workspace name in Comet. Defaults to the user's default workspace. +comet_project_name: # Project name in Comet. Defaults to Uncategorized. +comet_experiment_key: # Identifier for the experiment. Used to append data to an existing experiment or control the key of new experiments. Default to a random key. +comet_mode: # Create a new experiment ("create") or log to an existing one ("get"). Default ("get_or_create") auto-selects based on configuration. +comet_online: # Set to True to log data to Comet server, or False for offline storage. Default is True. +comet_experiment_config: # Dictionary for additional configuration settings, see the doc for more details. + +# Where to save the full-finetuned model to +output_dir: ./completed-model + +# Whether to use torch.compile and which backend to use +torch_compile: # bool +torch_compile_backend: # Optional[str] + +# Training hyperparameters -# Where to save the full-finetuned model to -output_dir: ./completed-model - -# Whether to use torch.compile and which backend to use -torch_compile: # bool -torch_compile_backend: # Optional[str] - -# Training hyperparameters - -# If greater than 1, backpropagation will be skipped and the gradients will be accumulated for the given number of steps. -gradient_accumulation_steps: 1 -# The number of samples to include in each batch. This is the number of samples sent to each GPU. -# Batch size per gpu = micro_batch_size * gradient_accumulation_steps -micro_batch_size: 2 -eval_batch_size: -num_epochs: 4 -warmup_steps: 100 # cannot use with warmup_ratio -warmup_ratio: 0.05 # cannot use with warmup_steps -learning_rate: 0.00003 -lr_quadratic_warmup: -logging_steps: -eval_steps: # Leave empty to eval at each epoch, integers for every N steps. decimal for fraction of total steps -evals_per_epoch: # number of times per epoch to run evals, mutually exclusive with eval_steps -save_strategy: # Set to `"no"` to skip checkpoint saves -save_steps: # Leave empty to save at each epoch -saves_per_epoch: # number of times per epoch to save a checkpoint, mutually exclusive with save_steps -save_total_limit: # Checkpoints saved at a time -# Maximum number of iterations to train for. It precedes num_epochs which means that -# if both are set, num_epochs will not be guaranteed. -# e.g., when 1 epoch is 1000 steps => `num_epochs: 2` and `max_steps: 100` will train for 100 steps -max_steps: - -eval_table_size: # Approximate number of predictions sent to wandb depending on batch size. Enabled above 0. Default is 0 -eval_max_new_tokens: # Total number of tokens generated for predictions sent to wandb. Default is 128 -eval_causal_lm_metrics: # HF evaluate metrics used during evaluation. Default is ["sacrebleu", "comet", "ter", "chrf", "perplexity"] - -loss_watchdog_threshold: # High loss value, indicating the learning has broken down (a good estimate is ~2 times the loss at the start of training) -loss_watchdog_patience: # Number of high-loss steps in a row before the trainer aborts (default: 3) - -# Save model as safetensors (require safetensors package) -save_safetensors: - -# Whether to mask out or include the human's prompt from the training labels -train_on_inputs: false -# Group similarly sized data to minimize padding. -# May be slower to start, as it must download and sort the entire dataset. -# Note that training loss may have an oscillating pattern with this enabled. -group_by_length: false - -# Whether to use gradient checkpointing https://huggingface.co/docs/transformers/v4.18.0/en/performance#gradient-checkpointing -gradient_checkpointing: false -# additional kwargs to pass to the trainer for gradient checkpointing -# gradient_checkpointing_kwargs: -# use_reentrant: true - -# Stop training after this many evaluation losses have increased in a row -# https://huggingface.co/transformers/v4.2.2/_modules/transformers/trainer_callback.html#EarlyStoppingCallback -early_stopping_patience: 3 +# If greater than 1, backpropagation will be skipped and the gradients will be accumulated for the given number of steps. +gradient_accumulation_steps: 1 +# The number of samples to include in each batch. This is the number of samples sent to each GPU. +# Batch size per gpu = micro_batch_size * gradient_accumulation_steps +micro_batch_size: 2 +eval_batch_size: +num_epochs: 4 +warmup_steps: 100 # cannot use with warmup_ratio +warmup_ratio: 0.05 # cannot use with warmup_steps +learning_rate: 0.00003 +lr_quadratic_warmup: +logging_steps: +eval_steps: # Leave empty to eval at each epoch, integers for every N steps. decimal for fraction of total steps +evals_per_epoch: # number of times per epoch to run evals, mutually exclusive with eval_steps +save_strategy: # Set to `"no"` to skip checkpoint saves +save_steps: # Leave empty to save at each epoch +saves_per_epoch: # number of times per epoch to save a checkpoint, mutually exclusive with save_steps +save_total_limit: # Checkpoints saved at a time +# Maximum number of iterations to train for. It precedes num_epochs which means that +# if both are set, num_epochs will not be guaranteed. +# e.g., when 1 epoch is 1000 steps => `num_epochs: 2` and `max_steps: 100` will train for 100 steps +max_steps: + +eval_table_size: # Approximate number of predictions sent to wandb depending on batch size. Enabled above 0. Default is 0 +eval_max_new_tokens: # Total number of tokens generated for predictions sent to wandb. Default is 128 +eval_causal_lm_metrics: # HF evaluate metrics used during evaluation. Default is ["sacrebleu", "comet", "ter", "chrf", "perplexity"] + +loss_watchdog_threshold: # High loss value, indicating the learning has broken down (a good estimate is ~2 times the loss at the start of training) +loss_watchdog_patience: # Number of high-loss steps in a row before the trainer aborts (default: 3) + +# Save model as safetensors (require safetensors package) +save_safetensors: + +# Whether to mask out or include the human's prompt from the training labels +train_on_inputs: false +# Group similarly sized data to minimize padding. +# May be slower to start, as it must download and sort the entire dataset. +# Note that training loss may have an oscillating pattern with this enabled. +group_by_length: false + +# Whether to use gradient checkpointing https://huggingface.co/docs/transformers/v4.18.0/en/performance#gradient-checkpointing +gradient_checkpointing: false +# additional kwargs to pass to the trainer for gradient checkpointing +# gradient_checkpointing_kwargs: +# use_reentrant: true + +# Stop training after this many evaluation losses have increased in a row +# https://huggingface.co/transformers/v4.2.2/_modules/transformers/trainer_callback.html#EarlyStoppingCallback +early_stopping_patience: 3 + +# Specify a scheduler and kwargs to use with the optimizer +lr_scheduler: # 'one_cycle' | 'log_sweep' | empty for cosine +lr_scheduler_kwargs: +cosine_min_lr_ratio: # decay lr to some percentage of the peak lr, e.g. cosine_min_lr_ratio=0.1 for 10% of peak lr +cosine_constant_lr_ratio: # freeze lr at some percentage of the step, e.g. cosine_constant_lr_ratio=0.8 means start cosine_min_lr at 80% of training step (https://arxiv.org/pdf/2308.04014.pdf) + +# For one_cycle optim +lr_div_factor: # Learning rate div factor -# Specify a scheduler and kwargs to use with the optimizer -lr_scheduler: # 'one_cycle' | 'log_sweep' | empty for cosine -lr_scheduler_kwargs: -cosine_min_lr_ratio: # decay lr to some percentage of the peak lr, e.g. cosine_min_lr_ratio=0.1 for 10% of peak lr -cosine_constant_lr_ratio: # freeze lr at some percentage of the step, e.g. cosine_constant_lr_ratio=0.8 means start cosine_min_lr at 80% of training step (https://arxiv.org/pdf/2308.04014.pdf) - -# For one_cycle optim -lr_div_factor: # Learning rate div factor - -# Specify optimizer -# Valid values are driven by the Transformers OptimizerNames class, see: -# https://github.com/huggingface/transformers/blob/95b374952dc27d8511541d6f5a4e22c9ec11fb24/src/transformers/training_args.py#L134 -# -# Note that not all optimizers may be available in your environment, ex: 'adamw_anyprecision' is part of -# torchdistx, 'adamw_bnb_8bit' is part of bnb.optim.Adam8bit, etc. When in doubt, it is recommended to start with the optimizer used -# in the examples/ for your model and fine-tuning use case. -# -# Valid values for 'optimizer' include: -# - adamw_hf -# - adamw_torch -# - adamw_torch_fused -# - adamw_torch_xla -# - adamw_apex_fused -# - adafactor -# - adamw_anyprecision -# - sgd -# - adagrad -# - adamw_bnb_8bit -# - lion_8bit -# - lion_32bit -# - paged_adamw_32bit -# - paged_adamw_8bit -# - paged_lion_32bit -# - paged_lion_8bit -# - galore_adamw -# - galore_adamw_8bit -# - galore_adafactor -# - galore_adamw_layerwise -# - galore_adamw_8bit_layerwise -# - galore_adafactor_layerwise -optimizer: -# Dictionary of arguments to pass to the optimizer -optim_args: -# For Galore Optimizers the following optim_args are available -# rank: # type: int -# update_proj_gap # type: int -# scale # type: float -# proj_type: # type: str, default = std - -# The target modules to optimize, i.e. the module names that you would like to train, right now this is used only for GaLore algorithm -optim_target_modules: -# - self_attn # for llama -# - mlp +# Specify optimizer +# Valid values are driven by the Transformers OptimizerNames class, see: +# https://github.com/huggingface/transformers/blob/95b374952dc27d8511541d6f5a4e22c9ec11fb24/src/transformers/training_args.py#L134 +# +# Note that not all optimizers may be available in your environment, ex: 'adamw_anyprecision' is part of +# torchdistx, 'adamw_bnb_8bit' is part of bnb.optim.Adam8bit, etc. When in doubt, it is recommended to start with the optimizer used +# in the examples/ for your model and fine-tuning use case. +# +# Valid values for 'optimizer' include: +# - adamw_hf +# - adamw_torch +# - adamw_torch_fused +# - adamw_torch_xla +# - adamw_apex_fused +# - adafactor +# - adamw_anyprecision +# - sgd +# - adagrad +# - adamw_bnb_8bit +# - lion_8bit +# - lion_32bit +# - paged_adamw_32bit +# - paged_adamw_8bit +# - paged_lion_32bit +# - paged_lion_8bit +# - galore_adamw +# - galore_adamw_8bit +# - galore_adafactor +# - galore_adamw_layerwise +# - galore_adamw_8bit_layerwise +# - galore_adafactor_layerwise +optimizer: +# Dictionary of arguments to pass to the optimizer +optim_args: +# For Galore Optimizers the following optim_args are available +# rank: # type: int +# update_proj_gap # type: int +# scale # type: float +# proj_type: # type: str, default = std + +# The target modules to optimize, i.e. the module names that you would like to train, right now this is used only for GaLore algorithm +optim_target_modules: +# - self_attn # for llama +# - mlp + +# Specify weight decay +weight_decay: +# adamw hyperparams +adam_beta1: +adam_beta2: +adam_epsilon: +# Gradient clipping max norm +max_grad_norm: -# Specify weight decay -weight_decay: -# adamw hyperparams -adam_beta1: -adam_beta2: -adam_epsilon: -# Gradient clipping max norm -max_grad_norm: - -# Augmentation techniques -# NEFT https://arxiv.org/abs/2310.05914, set this to a number (paper default is 5) to add noise to embeddings -# currently only supported on Llama and Mistral -neftune_noise_alpha: - -# Whether to bettertransformers -flash_optimum: -# Whether to use xformers attention patch https://github.com/facebookresearch/xformers: -xformers_attention: -# Whether to use flash attention patch https://github.com/Dao-AILab/flash-attention: -flash_attention: -flash_attn_cross_entropy: # Whether to use flash-attention cross entropy implementation - advanced use only -flash_attn_rms_norm: # Whether to use flash-attention rms norm implementation - advanced use only -flash_attn_fuse_qkv: # Whether to fuse QKV into a single operation -flash_attn_fuse_mlp: # Whether to fuse part of the MLP into a single operation -# Whether to use scaled-dot-product attention -# https://pytorch.org/docs/stable/generated/torch.nn.functional.scaled_dot_product_attention.html -sdp_attention: -# Shifted-sparse attention (only llama) - https://arxiv.org/pdf/2309.12307.pdf -s2_attention: -# Resume from a specific checkpoint dir -resume_from_checkpoint: -# If resume_from_checkpoint isn't set and you simply want it to start where it left off. -# Be careful with this being turned on between different models. -auto_resume_from_checkpoints: false - -# Don't mess with this, it's here for accelerate and torchrun -local_rank: - -# Add or change special tokens. -# If you add tokens here, you don't need to add them to the `tokens` list. -special_tokens: - # bos_token: "<s>" - # eos_token: "</s>" - # unk_token: "<unk>" - # pad_token: "[PAD]" - -# Add extra tokens. -tokens: - -# FSDP -fsdp: -fsdp_config: - -# Deepspeed config path. e.g., deepspeed_configs/zero3.json -deepspeed: - -# Advanced DDP Arguments -ddp_timeout: -ddp_bucket_cap_mb: -ddp_broadcast_buffers: +# Augmentation techniques +# NEFT https://arxiv.org/abs/2310.05914, set this to a number (paper default is 5) to add noise to embeddings +# currently only supported on Llama and Mistral +neftune_noise_alpha: + +# Whether to bettertransformers +flash_optimum: +# Whether to use xformers attention patch https://github.com/facebookresearch/xformers: +xformers_attention: +# Whether to use flash attention patch https://github.com/Dao-AILab/flash-attention: +flash_attention: +flash_attn_cross_entropy: # Whether to use flash-attention cross entropy implementation - advanced use only +flash_attn_rms_norm: # Whether to use flash-attention rms norm implementation - advanced use only +flash_attn_fuse_qkv: # Whether to fuse QKV into a single operation +flash_attn_fuse_mlp: # Whether to fuse part of the MLP into a single operation +# Whether to use scaled-dot-product attention +# https://pytorch.org/docs/stable/generated/torch.nn.functional.scaled_dot_product_attention.html +sdp_attention: +# Shifted-sparse attention (only llama) - https://arxiv.org/pdf/2309.12307.pdf +s2_attention: +# Resume from a specific checkpoint dir +resume_from_checkpoint: +# If resume_from_checkpoint isn't set and you simply want it to start where it left off. +# Be careful with this being turned on between different models. +auto_resume_from_checkpoints: false + +# Don't mess with this, it's here for accelerate and torchrun +local_rank: + +# Add or change special tokens. +# If you add tokens here, you don't need to add them to the `tokens` list. +special_tokens: + # bos_token: "<s>" + # eos_token: "</s>" + # unk_token: "<unk>" + # pad_token: "[PAD]" + +# Add extra tokens. +tokens: + +# FSDP +fsdp: +fsdp_config: + +# Deepspeed config path. e.g., deepspeed_configs/zero3.json +deepspeed: + +# Advanced DDP Arguments +ddp_timeout: +ddp_bucket_cap_mb: +ddp_broadcast_buffers: + +# Path to torch distx for optim 'adamw_anyprecision' +torchdistx_path: + +# Set to HF dataset for type: 'completion' for streaming instead of pre-tokenize +pretraining_dataset: + +# Debug mode +debug: -# Path to torch distx for optim 'adamw_anyprecision' -torchdistx_path: +# Seed +seed: -# Set to HF dataset for type: 'completion' for streaming instead of pre-tokenize -pretraining_dataset: - -# Debug mode -debug: - -# Seed -seed: - -# Allow overwrite yml config using from cli -strict: +# Allow overwrite yml config using from cli +strict: diff --git a/docs/dataset-formats/conversation.html b/docs/dataset-formats/conversation.html index 1f04865e7..826ac5fd1 100644 --- a/docs/dataset-formats/conversation.html +++ b/docs/dataset-formats/conversation.html @@ -295,10 +295,6 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
data.jsonl
{"conversations": [{"role": "...", "value": "..."}]}data.jsonl
{"conversations": [{"role": "...", "content": "..."}]}{"conversations": [{"role": "...", "content": "..."}]}See config.qmd for full configs and supported templates.
datasets:
- - path: ...
- type: chat_templatedatasets:
+ - path: ...
+ type: chat_templategemma chat template to override the tokenizer_config.json’s chat template on OpenAI messages format, training on all assistant messages.chat_template: gemma # this overwrites the tokenizer's chat_template
-datasets:
- - path: ...
- type: chat_template
- roles_to_train: ["assistant"]chat_template: gemma # this overwrites the tokenizer's chat_template
+datasets:
+ - path: ...
+ type: chat_template
+ roles_to_train: ["assistant"]chatml as fallback if the former’s chat template does not exist, on OpenAI messages format, training on all assistant messages.chat_template: tokenizer_default_fallback_chatml # this overwrites the tokenizer's chat_template
-datasets:
- - path: ...
- type: chat_template
- roles_to_train: ["assistant"]chat_template: tokenizer_default_fallback_chatml # this overwrites the tokenizer's chat_template
+datasets:
+ - path: ...
+ type: chat_template
+ roles_to_train: ["assistant"]# chat_template: jinja # `jinja` will be implied if the `chat_template_jinja` is set and this field is empty
-chat_template_jinja: "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'system') %}{{'<|system|>' + '\n' + message['content'] + '<|end|>' + '\n'}}{% elif (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif message['role'] == 'assistant' %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}"
-
-datasets:
- - path: ...
- type: chat_template
- roles_to_train: ["assistant"]# chat_template: jinja # `jinja` will be implied if the `chat_template_jinja` is set and this field is empty
+chat_template_jinja: "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'system') %}{{'<|system|>' + '\n' + message['content'] + '<|end|>' + '\n'}}{% elif (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif message['role'] == 'assistant' %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}"
+
+datasets:
+ - path: ...
+ type: chat_template
+ roles_to_train: ["assistant"]data.jsonl
{
- "conversations": [
- {"from": "system", "value": "You are an AI assistant.", "train": false},
- {"from": "human", "value": "Hello", "train": false},
- {"from": "assistant", "value": "Hello", "train": true},
- {"from": "human", "value": "How are you?", "train": true},
- {
- "from": "assistant",
- "value": "I'm doing very well, thank you!",
- "train_detail": [
- {"begin_offset": 0, "end_offset": 8, "train": false},
- {"begin_offset": 9, "end_offset": 18, "train": true},
- {"begin_offset": 19, "end_offset": 30, "train": false},
- ],
- },
- {
- "from": "human",
- "value": "I'm doing very well, thank you!",
- "train": true,
- },
- {"from": "assistant", "value": "Hi there!", "train": true}
- ]
-}{
+ "conversations": [
+ {"from": "system", "value": "You are an AI assistant.", "train": false},
+ {"from": "human", "value": "Hello", "train": false},
+ {"from": "assistant", "value": "Hello", "train": true},
+ {"from": "human", "value": "How are you?", "train": true},
+ {
+ "from": "assistant",
+ "value": "I'm doing very well, thank you!",
+ "train_detail": [
+ {"begin_offset": 0, "end_offset": 8, "train": false},
+ {"begin_offset": 9, "end_offset": 18, "train": true},
+ {"begin_offset": 19, "end_offset": 30, "train": false},
+ ],
+ },
+ {
+ "from": "human",
+ "value": "I'm doing very well, thank you!",
+ "train": true,
+ },
+ {"from": "assistant", "value": "Hi there!", "train": true}
+ ]
+}The configuration would look like:
-datasets:
- - path: ...
- type: chat_template
- chat_template: tokenizer_default
- field_messages: conversations
- message_field_role: from
- message_field_content: value
- roles_to_train: []
- train_on_eos: turn
- message_field_training: train
- message_field_training_detail: train_detaildatasets:
+ - path: ...
+ type: chat_template
+ chat_template: tokenizer_default
+ field_messages: conversations
+ message_field_role: from
+ message_field_content: value
+ roles_to_train: []
+ train_on_eos: turn
+ message_field_training: train
+ message_field_training_detail: train_detailTip: It is not necessary to use both message_field_training and message_field_training_detail at a time.
loading
load_in_4bit: true
load_in_8bit: true
diff --git a/search.json b/search.json
index 998c7ec31..79b59e0e9 100644
--- a/search.json
+++ b/search.json
@@ -34,7 +34,7 @@
"href": "index.html#advanced-setup",
"title": "Axolotl",
"section": "Advanced Setup",
- "text": "Advanced Setup\n\nEnvironment\n\nDocker\ndocker run --gpus '\"all\"' --rm -it winglian/axolotl:main-latest\nOr run on the current files for development:\ndocker compose up -d\n\n[!Tip] If you want to debug axolotl or prefer to use Docker as your development environment, see the debugging guide’s section on Docker.\n\n\n\nDocker advanced\n\nA more powerful Docker command to run would be this:\ndocker run --privileged --gpus '\"all\"' --shm-size 10g --rm -it --name axolotl --ipc=host --ulimit memlock=-1 --ulimit stack=67108864 --mount type=bind,src=\"${PWD}\",target=/workspace/axolotl -v ${HOME}/.cache/huggingface:/root/.cache/huggingface winglian/axolotl:main-latest\nIt additionally: * Prevents memory issues when running e.g. deepspeed (e.g. you could hit SIGBUS/signal 7 error) through --ipc and --ulimit args. * Persists the downloaded HF data (models etc.) and your modifications to axolotl code through --mount/-v args. * The --name argument simply makes it easier to refer to the container in vscode (Dev Containers: Attach to Running Container...) or in your terminal. * The --privileged flag gives all capabilities to the container. * The --shm-size 10g argument increases the shared memory size. Use this if you see exitcode: -7 errors using deepspeed.\nMore information on nvidia website\n\n\n\nConda/Pip venv\n\nInstall python >=3.10\nInstall pytorch stable https://pytorch.org/get-started/locally/\nInstall Axolotl along with python dependencies bash pip3 install packaging pip3 install -e '.[flash-attn,deepspeed]'\n(Optional) Login to Huggingface to use gated models/datasets. bash huggingface-cli login Get the token at huggingface.co/settings/tokens\n\n\n\nCloud GPU\nFor cloud GPU providers that support docker images, use winglian/axolotl-cloud:main-latest\n\non Latitude.sh use this direct link\non JarvisLabs.ai use this direct link\non RunPod use this direct link\n\n\n\nBare Metal Cloud GPU\n\nLambdaLabs\n\n\nClick to Expand\n\n\nInstall python\n\nsudo apt update\nsudo apt install -y python3.10\n\nsudo update-alternatives --install /usr/bin/python python /usr/bin/python3.10 1\nsudo update-alternatives --config python # pick 3.10 if given option\npython -V # should be 3.10\n\nInstall pip\n\nwget https://bootstrap.pypa.io/get-pip.py\npython get-pip.py\n\nInstall Pytorch https://pytorch.org/get-started/locally/\nFollow instructions on quickstart.\nRun\n\npip3 install protobuf==3.20.3\npip3 install -U --ignore-installed requests Pillow psutil scipy\n\nSet path\n\nexport LD_LIBRARY_PATH=/usr/lib/x86_64-linux-gnu:$LD_LIBRARY_PATH\n\n\n\nGCP\n\n\nClick to Expand\n\nUse a Deeplearning linux OS with cuda and pytorch installed. Then follow instructions on quickstart.\nMake sure to run the below to uninstall xla.\npip uninstall -y torch_xla[tpu]\n\n\n\n\nWindows\nPlease use WSL or Docker!\n\n\nMac\nUse the below instead of the install method in QuickStart.\npip3 install -e '.'\nMore info: mac.md\n\n\nGoogle Colab\nPlease use this example notebook.\n\n\nLaunching on public clouds via SkyPilot\nTo launch on GPU instances (both on-demand and spot instances) on 7+ clouds (GCP, AWS, Azure, OCI, and more), you can use SkyPilot:\npip install \"skypilot-nightly[gcp,aws,azure,oci,lambda,kubernetes,ibm,scp]\" # choose your clouds\nsky check\nGet the example YAMLs of using Axolotl to finetune mistralai/Mistral-7B-v0.1:\ngit clone https://github.com/skypilot-org/skypilot.git\ncd skypilot/llm/axolotl\nUse one command to launch:\n# On-demand\nHF_TOKEN=xx sky launch axolotl.yaml --env HF_TOKEN\n\n# Managed spot (auto-recovery on preemption)\nHF_TOKEN=xx BUCKET=<unique-name> sky spot launch axolotl-spot.yaml --env HF_TOKEN --env BUCKET\n\n\nLaunching on public clouds via dstack\nTo launch on GPU instance (both on-demand and spot instances) on public clouds (GCP, AWS, Azure, Lambda Labs, TensorDock, Vast.ai, and CUDO), you can use dstack.\nWrite a job description in YAML as below:\n# dstack.yaml\ntype: task\n\nimage: winglian/axolotl-cloud:main-20240429-py3.11-cu121-2.2.2\n\nenv:\n - HUGGING_FACE_HUB_TOKEN\n - WANDB_API_KEY\n\ncommands:\n - accelerate launch -m axolotl.cli.train config.yaml\n\nports:\n - 6006\n\nresources:\n gpu:\n memory: 24GB..\n count: 2\nthen, simply run the job with dstack run command. Append --spot option if you want spot instance. dstack run command will show you the instance with cheapest price across multi cloud services:\npip install dstack\nHUGGING_FACE_HUB_TOKEN=xxx WANDB_API_KEY=xxx dstack run . -f dstack.yaml # --spot\nFor further and fine-grained use cases, please refer to the official dstack documents and the detailed description of axolotl example on the official repository.\n\n\n\nDataset\nAxolotl supports a variety of dataset formats. It is recommended to use a JSONL. The schema of the JSONL depends upon the task and the prompt template you wish to use. Instead of a JSONL, you can also use a HuggingFace dataset with columns for each JSONL field.\nSee the documentation for more information on how to use different dataset formats.\n\n\nConfig\nSee examples for quick start. It is recommended to duplicate and modify to your needs. The most important options are:\n\nmodel\nbase_model: ./llama-7b-hf # local or huggingface repo\nNote: The code will load the right architecture.\ndataset\ndatasets:\n # huggingface repo\n - path: vicgalle/alpaca-gpt4\n type: alpaca\n\n # huggingface repo with specific configuration/subset\n - path: EleutherAI/pile\n name: enron_emails\n type: completion # format from earlier\n field: text # Optional[str] default: text, field to use for completion data\n\n # huggingface repo with multiple named configurations/subsets\n - path: bigcode/commitpackft\n name:\n - ruby\n - python\n - typescript\n type: ... # unimplemented custom format\n\n # fastchat conversation (deprecation soon, use chat_template https://axolotl-ai-cloud.github.io/axolotl/docs/dataset-formats/conversation.html#chat_template)\n # See 'conversation' options: https://github.com/lm-sys/FastChat/blob/main/fastchat/conversation.py\n - path: ...\n type: sharegpt\n conversation: chatml # default: vicuna_v1.1\n\n # local\n - path: data.jsonl # or json\n ds_type: json # see other options below\n type: alpaca\n\n # dataset with splits, but no train split\n - path: knowrohit07/know_sql\n type: context_qa.load_v2\n train_on_split: validation\n\n # loading from s3 or gcs\n # s3 creds will be loaded from the system default and gcs only supports public access\n - path: s3://path_to_ds # Accepts folder with arrow/parquet or file path like above. Supports s3, gcs.\n ...\n\n # Loading Data From a Public URL\n # - The file format is `json` (which includes `jsonl`) by default. For different formats, adjust the `ds_type` option accordingly.\n - path: https://some.url.com/yourdata.jsonl # The URL should be a direct link to the file you wish to load. URLs must use HTTPS protocol, not HTTP.\n ds_type: json # this is the default, see other options below.\nloading\nload_in_4bit: true\nload_in_8bit: true\n\nbf16: auto # require >=ampere, auto will detect if your GPU supports this and choose automatically.\nfp16: # leave empty to use fp16 when bf16 is 'auto'. set to false if you want to fallback to fp32\ntf32: true # require >=ampere\n\nbfloat16: true # require >=ampere, use instead of bf16 when you don't want AMP (automatic mixed precision)\nfloat16: true # use instead of fp16 when you don't want AMP\nNote: Repo does not do 4-bit quantization.\nlora\nadapter: lora # 'qlora' or leave blank for full finetune\nlora_r: 8\nlora_alpha: 16\nlora_dropout: 0.05\nlora_target_modules:\n - q_proj\n - v_proj\n\n\nAll Config Options\nSee these docs for all config options.\n\n\n\nTrain\nRun\naccelerate launch -m axolotl.cli.train your_config.yml\n\n[!TIP] You can also reference a config file that is hosted on a public URL, for example accelerate launch -m axolotl.cli.train https://yourdomain.com/your_config.yml\n\n\nPreprocess dataset\nYou can optionally pre-tokenize dataset with the following before finetuning. This is recommended for large datasets.\n\nSet dataset_prepared_path: to a local folder for saving and loading pre-tokenized dataset.\n(Optional): Set push_dataset_to_hub: hf_user/repo to push it to Huggingface.\n(Optional): Use --debug to see preprocessed examples.\n\npython -m axolotl.cli.preprocess your_config.yml\n\n\nMulti-GPU\nBelow are the options available in axolotl for training with multiple GPUs. Note that DeepSpeed is the recommended multi-GPU option currently because FSDP may experience loss instability.\n\nDeepSpeed\nDeepspeed is an optimization suite for multi-gpu systems allowing you to train much larger models than you might typically be able to fit into your GPU’s VRAM. More information about the various optimization types for deepspeed is available at https://huggingface.co/docs/accelerate/main/en/usage_guides/deepspeed#what-is-integrated\nWe provide several default deepspeed JSON configurations for ZeRO stage 1, 2, and 3.\ndeepspeed: deepspeed_configs/zero1.json\naccelerate launch -m axolotl.cli.train examples/llama-2/config.yml --deepspeed deepspeed_configs/zero1.json\n\n\nFSDP\n\nllama FSDP\n\nfsdp:\n - full_shard\n - auto_wrap\nfsdp_config:\n fsdp_offload_params: true\n fsdp_state_dict_type: FULL_STATE_DICT\n fsdp_transformer_layer_cls_to_wrap: LlamaDecoderLayer\n\n\nFSDP + QLoRA\nAxolotl supports training with FSDP and QLoRA, see these docs for more information.\n\n\nWeights & Biases Logging\nMake sure your WANDB_API_KEY environment variable is set (recommended) or you login to wandb with wandb login.\n\nwandb options\n\nwandb_mode:\nwandb_project:\nwandb_entity:\nwandb_watch:\nwandb_name:\nwandb_log_model:\n\n\nComet Logging\nMake sure your COMET_API_KEY environment variable is set (recommended) or you login to wandb with comet login.\n\nwandb options\n\nuse_comet:\ncomet_api_key:\ncomet_workspace:\ncomet_project_name:\ncomet_experiment_key:\ncomet_mode:\ncomet_online:\ncomet_experiment_config:\n\n\nSpecial Tokens\nIt is important to have special tokens like delimiters, end-of-sequence, beginning-of-sequence in your tokenizer’s vocabulary. This will help you avoid tokenization issues and help your model train better. You can do this in axolotl like this:\nspecial_tokens:\n bos_token: \"<s>\"\n eos_token: \"</s>\"\n unk_token: \"<unk>\"\ntokens: # these are delimiters\n - \"<|im_start|>\"\n - \"<|im_end|>\"\nWhen you include these tokens in your axolotl config, axolotl adds these tokens to the tokenizer’s vocabulary.\n\n\nLiger Kernel\nLiger Kernel: Efficient Triton Kernels for LLM Training\nhttps://github.com/linkedin/Liger-Kernel\nLiger (LinkedIn GPU Efficient Runtime) Kernel is a collection of Triton kernels designed specifically for LLM training. It can effectively increase multi-GPU training throughput by 20% and reduces memory usage by 60%. The Liger Kernel composes well and is compatible with both FSDP and Deepspeed.\nplugins:\n - axolotl.integrations.liger.LigerPlugin\nliger_rope: true\nliger_rms_norm: true\nliger_glu_activation: true\nliger_layer_norm: true\nliger_fused_linear_cross_entropy: true\n\n\n\n\nInference Playground\nAxolotl allows you to load your model in an interactive terminal playground for quick experimentation. The config file is the same config file used for training.\nPass the appropriate flag to the inference command, depending upon what kind of model was trained:\n\nPretrained LORA:\npython -m axolotl.cli.inference examples/your_config.yml --lora_model_dir=\"./lora-output-dir\"\nFull weights finetune:\npython -m axolotl.cli.inference examples/your_config.yml --base_model=\"./completed-model\"\nFull weights finetune w/ a prompt from a text file:\ncat /tmp/prompt.txt | python -m axolotl.cli.inference examples/your_config.yml \\\n --base_model=\"./completed-model\" --prompter=None --load_in_8bit=True\n– With gradio hosting\npython -m axolotl.cli.inference examples/your_config.yml --gradio\n\nPlease use --sample_packing False if you have it on and receive the error similar to below:\n\nRuntimeError: stack expects each tensor to be equal size, but got [1, 32, 1, 128] at entry 0 and [1, 32, 8, 128] at entry 1\n\n\n\nMerge LORA to base\nThe following command will merge your LORA adapater with your base model. You can optionally pass the argument --lora_model_dir to specify the directory where your LORA adapter was saved, otherwhise, this will be inferred from output_dir in your axolotl config file. The merged model is saved in the sub-directory {lora_model_dir}/merged.\npython3 -m axolotl.cli.merge_lora your_config.yml --lora_model_dir=\"./completed-model\"\nYou may need to use the gpu_memory_limit and/or lora_on_cpu config options to avoid running out of memory. If you still run out of CUDA memory, you can try to merge in system RAM with\nCUDA_VISIBLE_DEVICES=\"\" python3 -m axolotl.cli.merge_lora ...\nalthough this will be very slow, and using the config options above are recommended instead.",
+ "text": "Advanced Setup\n\nEnvironment\n\nDocker\ndocker run --gpus '\"all\"' --rm -it winglian/axolotl:main-latest\nOr run on the current files for development:\ndocker compose up -d\n\n[!Tip] If you want to debug axolotl or prefer to use Docker as your development environment, see the debugging guide’s section on Docker.\n\n\n\nDocker advanced\n\nA more powerful Docker command to run would be this:\ndocker run --privileged --gpus '\"all\"' --shm-size 10g --rm -it --name axolotl --ipc=host --ulimit memlock=-1 --ulimit stack=67108864 --mount type=bind,src=\"${PWD}\",target=/workspace/axolotl -v ${HOME}/.cache/huggingface:/root/.cache/huggingface winglian/axolotl:main-latest\nIt additionally: * Prevents memory issues when running e.g. deepspeed (e.g. you could hit SIGBUS/signal 7 error) through --ipc and --ulimit args. * Persists the downloaded HF data (models etc.) and your modifications to axolotl code through --mount/-v args. * The --name argument simply makes it easier to refer to the container in vscode (Dev Containers: Attach to Running Container...) or in your terminal. * The --privileged flag gives all capabilities to the container. * The --shm-size 10g argument increases the shared memory size. Use this if you see exitcode: -7 errors using deepspeed.\nMore information on nvidia website\n\n\n\nConda/Pip venv\n\nInstall python >=3.10\nInstall pytorch stable https://pytorch.org/get-started/locally/\nInstall Axolotl along with python dependencies bash pip3 install packaging pip3 install -e '.[flash-attn,deepspeed]'\n(Optional) Login to Huggingface to use gated models/datasets. bash huggingface-cli login Get the token at huggingface.co/settings/tokens\n\n\n\nCloud GPU\nFor cloud GPU providers that support docker images, use winglian/axolotl-cloud:main-latest\n\non Latitude.sh use this direct link\non JarvisLabs.ai use this direct link\non RunPod use this direct link\n\n\n\nBare Metal Cloud GPU\n\nLambdaLabs\n\n\nClick to Expand\n\n\nInstall python\n\nsudo apt update\nsudo apt install -y python3.10\n\nsudo update-alternatives --install /usr/bin/python python /usr/bin/python3.10 1\nsudo update-alternatives --config python # pick 3.10 if given option\npython -V # should be 3.10\n\nInstall pip\n\nwget https://bootstrap.pypa.io/get-pip.py\npython get-pip.py\n\nInstall Pytorch https://pytorch.org/get-started/locally/\nFollow instructions on quickstart.\nRun\n\npip3 install protobuf==3.20.3\npip3 install -U --ignore-installed requests Pillow psutil scipy\n\nSet path\n\nexport LD_LIBRARY_PATH=/usr/lib/x86_64-linux-gnu:$LD_LIBRARY_PATH\n\n\n\nGCP\n\n\nClick to Expand\n\nUse a Deeplearning linux OS with cuda and pytorch installed. Then follow instructions on quickstart.\nMake sure to run the below to uninstall xla.\npip uninstall -y torch_xla[tpu]\n\n\n\n\nWindows\nPlease use WSL or Docker!\n\n\nMac\nUse the below instead of the install method in QuickStart.\npip3 install -e '.'\nMore info: mac.md\n\n\nGoogle Colab\nPlease use this example notebook.\n\n\nLaunching on public clouds via SkyPilot\nTo launch on GPU instances (both on-demand and spot instances) on 7+ clouds (GCP, AWS, Azure, OCI, and more), you can use SkyPilot:\npip install \"skypilot-nightly[gcp,aws,azure,oci,lambda,kubernetes,ibm,scp]\" # choose your clouds\nsky check\nGet the example YAMLs of using Axolotl to finetune mistralai/Mistral-7B-v0.1:\ngit clone https://github.com/skypilot-org/skypilot.git\ncd skypilot/llm/axolotl\nUse one command to launch:\n# On-demand\nHF_TOKEN=xx sky launch axolotl.yaml --env HF_TOKEN\n\n# Managed spot (auto-recovery on preemption)\nHF_TOKEN=xx BUCKET=<unique-name> sky spot launch axolotl-spot.yaml --env HF_TOKEN --env BUCKET\n\n\nLaunching on public clouds via dstack\nTo launch on GPU instance (both on-demand and spot instances) on public clouds (GCP, AWS, Azure, Lambda Labs, TensorDock, Vast.ai, and CUDO), you can use dstack.\nWrite a job description in YAML as below:\n# dstack.yaml\ntype: task\n\nimage: winglian/axolotl-cloud:main-20240429-py3.11-cu121-2.2.2\n\nenv:\n - HUGGING_FACE_HUB_TOKEN\n - WANDB_API_KEY\n\ncommands:\n - accelerate launch -m axolotl.cli.train config.yaml\n\nports:\n - 6006\n\nresources:\n gpu:\n memory: 24GB..\n count: 2\nthen, simply run the job with dstack run command. Append --spot option if you want spot instance. dstack run command will show you the instance with cheapest price across multi cloud services:\npip install dstack\nHUGGING_FACE_HUB_TOKEN=xxx WANDB_API_KEY=xxx dstack run . -f dstack.yaml # --spot\nFor further and fine-grained use cases, please refer to the official dstack documents and the detailed description of axolotl example on the official repository.\n\n\n\nDataset\nAxolotl supports a variety of dataset formats. It is recommended to use a JSONL. The schema of the JSONL depends upon the task and the prompt template you wish to use. Instead of a JSONL, you can also use a HuggingFace dataset with columns for each JSONL field.\nSee the documentation for more information on how to use different dataset formats.\n\n\nConfig\nSee examples for quick start. It is recommended to duplicate and modify to your needs. The most important options are:\n\nmodel\nbase_model: ./llama-7b-hf # local or huggingface repo\nNote: The code will load the right architecture.\ndataset\ndatasets:\n # huggingface repo\n - path: vicgalle/alpaca-gpt4\n type: alpaca\n\n # huggingface repo with specific configuration/subset\n - path: EleutherAI/pile\n name: enron_emails\n type: completion # format from earlier\n field: text # Optional[str] default: text, field to use for completion data\n\n # huggingface repo with multiple named configurations/subsets\n - path: bigcode/commitpackft\n name:\n - ruby\n - python\n - typescript\n type: ... # unimplemented custom format\n\n # chat_template https://axolotl-ai-cloud.github.io/axolotl/docs/dataset-formats/conversation.html#chat_template\n - path: ...\n type: chat_template\n chat_template: chatml # defaults to tokenizer's chat_template\n\n # local\n - path: data.jsonl # or json\n ds_type: json # see other options below\n type: alpaca\n\n # dataset with splits, but no train split\n - path: knowrohit07/know_sql\n type: context_qa.load_v2\n train_on_split: validation\n\n # loading from s3 or gcs\n # s3 creds will be loaded from the system default and gcs only supports public access\n - path: s3://path_to_ds # Accepts folder with arrow/parquet or file path like above. Supports s3, gcs.\n ...\n\n # Loading Data From a Public URL\n # - The file format is `json` (which includes `jsonl`) by default. For different formats, adjust the `ds_type` option accordingly.\n - path: https://some.url.com/yourdata.jsonl # The URL should be a direct link to the file you wish to load. URLs must use HTTPS protocol, not HTTP.\n ds_type: json # this is the default, see other options below.\nloading\nload_in_4bit: true\nload_in_8bit: true\n\nbf16: auto # require >=ampere, auto will detect if your GPU supports this and choose automatically.\nfp16: # leave empty to use fp16 when bf16 is 'auto'. set to false if you want to fallback to fp32\ntf32: true # require >=ampere\n\nbfloat16: true # require >=ampere, use instead of bf16 when you don't want AMP (automatic mixed precision)\nfloat16: true # use instead of fp16 when you don't want AMP\nNote: Repo does not do 4-bit quantization.\nlora\nadapter: lora # 'qlora' or leave blank for full finetune\nlora_r: 8\nlora_alpha: 16\nlora_dropout: 0.05\nlora_target_modules:\n - q_proj\n - v_proj\n\n\nAll Config Options\nSee these docs for all config options.\n\n\n\nTrain\nRun\naccelerate launch -m axolotl.cli.train your_config.yml\n\n[!TIP] You can also reference a config file that is hosted on a public URL, for example accelerate launch -m axolotl.cli.train https://yourdomain.com/your_config.yml\n\n\nPreprocess dataset\nYou can optionally pre-tokenize dataset with the following before finetuning. This is recommended for large datasets.\n\nSet dataset_prepared_path: to a local folder for saving and loading pre-tokenized dataset.\n(Optional): Set push_dataset_to_hub: hf_user/repo to push it to Huggingface.\n(Optional): Use --debug to see preprocessed examples.\n\npython -m axolotl.cli.preprocess your_config.yml\n\n\nMulti-GPU\nBelow are the options available in axolotl for training with multiple GPUs. Note that DeepSpeed is the recommended multi-GPU option currently because FSDP may experience loss instability.\n\nDeepSpeed\nDeepspeed is an optimization suite for multi-gpu systems allowing you to train much larger models than you might typically be able to fit into your GPU’s VRAM. More information about the various optimization types for deepspeed is available at https://huggingface.co/docs/accelerate/main/en/usage_guides/deepspeed#what-is-integrated\nWe provide several default deepspeed JSON configurations for ZeRO stage 1, 2, and 3.\ndeepspeed: deepspeed_configs/zero1.json\naccelerate launch -m axolotl.cli.train examples/llama-2/config.yml --deepspeed deepspeed_configs/zero1.json\n\n\nFSDP\n\nllama FSDP\n\nfsdp:\n - full_shard\n - auto_wrap\nfsdp_config:\n fsdp_offload_params: true\n fsdp_state_dict_type: FULL_STATE_DICT\n fsdp_transformer_layer_cls_to_wrap: LlamaDecoderLayer\n\n\nFSDP + QLoRA\nAxolotl supports training with FSDP and QLoRA, see these docs for more information.\n\n\nWeights & Biases Logging\nMake sure your WANDB_API_KEY environment variable is set (recommended) or you login to wandb with wandb login.\n\nwandb options\n\nwandb_mode:\nwandb_project:\nwandb_entity:\nwandb_watch:\nwandb_name:\nwandb_log_model:\n\n\nComet Logging\nMake sure your COMET_API_KEY environment variable is set (recommended) or you login to wandb with comet login.\n\nwandb options\n\nuse_comet:\ncomet_api_key:\ncomet_workspace:\ncomet_project_name:\ncomet_experiment_key:\ncomet_mode:\ncomet_online:\ncomet_experiment_config:\n\n\nSpecial Tokens\nIt is important to have special tokens like delimiters, end-of-sequence, beginning-of-sequence in your tokenizer’s vocabulary. This will help you avoid tokenization issues and help your model train better. You can do this in axolotl like this:\nspecial_tokens:\n bos_token: \"<s>\"\n eos_token: \"</s>\"\n unk_token: \"<unk>\"\ntokens: # these are delimiters\n - \"<|im_start|>\"\n - \"<|im_end|>\"\nWhen you include these tokens in your axolotl config, axolotl adds these tokens to the tokenizer’s vocabulary.\n\n\nLiger Kernel\nLiger Kernel: Efficient Triton Kernels for LLM Training\nhttps://github.com/linkedin/Liger-Kernel\nLiger (LinkedIn GPU Efficient Runtime) Kernel is a collection of Triton kernels designed specifically for LLM training. It can effectively increase multi-GPU training throughput by 20% and reduces memory usage by 60%. The Liger Kernel composes well and is compatible with both FSDP and Deepspeed.\nplugins:\n - axolotl.integrations.liger.LigerPlugin\nliger_rope: true\nliger_rms_norm: true\nliger_glu_activation: true\nliger_layer_norm: true\nliger_fused_linear_cross_entropy: true\n\n\n\n\nInference Playground\nAxolotl allows you to load your model in an interactive terminal playground for quick experimentation. The config file is the same config file used for training.\nPass the appropriate flag to the inference command, depending upon what kind of model was trained:\n\nPretrained LORA:\npython -m axolotl.cli.inference examples/your_config.yml --lora_model_dir=\"./lora-output-dir\"\nFull weights finetune:\npython -m axolotl.cli.inference examples/your_config.yml --base_model=\"./completed-model\"\nFull weights finetune w/ a prompt from a text file:\ncat /tmp/prompt.txt | python -m axolotl.cli.inference examples/your_config.yml \\\n --base_model=\"./completed-model\" --prompter=None --load_in_8bit=True\n– With gradio hosting\npython -m axolotl.cli.inference examples/your_config.yml --gradio\n\nPlease use --sample_packing False if you have it on and receive the error similar to below:\n\nRuntimeError: stack expects each tensor to be equal size, but got [1, 32, 1, 128] at entry 0 and [1, 32, 8, 128] at entry 1\n\n\n\nMerge LORA to base\nThe following command will merge your LORA adapater with your base model. You can optionally pass the argument --lora_model_dir to specify the directory where your LORA adapter was saved, otherwhise, this will be inferred from output_dir in your axolotl config file. The merged model is saved in the sub-directory {lora_model_dir}/merged.\npython3 -m axolotl.cli.merge_lora your_config.yml --lora_model_dir=\"./completed-model\"\nYou may need to use the gpu_memory_limit and/or lora_on_cpu config options to avoid running out of memory. If you still run out of CUDA memory, you can try to merge in system RAM with\nCUDA_VISIBLE_DEVICES=\"\" python3 -m axolotl.cli.merge_lora ...\nalthough this will be very slow, and using the config options above are recommended instead.",
"crumbs": [
"Home"
]
@@ -699,7 +699,7 @@
"href": "docs/dataset-formats/conversation.html",
"title": "Conversation",
"section": "",
- "text": "UPDATE: ShareGPT is being deprecated in the next release. Please see chat_template section below.\nconversations where from is human/gpt. (optional: first row with role system to override default system prompt)\n\n\ndata.jsonl\n\n{\"conversations\": [{\"from\": \"...\", \"value\": \"...\"}]}\n\nNote: type: sharegpt opens special configs: - conversation: enables conversions to many Conversation types. Refer to the ‘name’ here for options. - roles: allows you to specify the roles for input and output. This is useful for datasets with custom roles such as tool etc to support masking. - field_human: specify the key to use instead of human in the conversation. - field_model: specify the key to use instead of gpt in the conversation.\ndatasets:\n path: ...\n type: sharegpt\n\n conversation: # Options (see Conversation 'name'): https://github.com/lm-sys/FastChat/blob/main/fastchat/conversation.py\n field_human: # Optional[str]. Human key to use for conversation.\n field_model: # Optional[str]. Assistant key to use for conversation.\n # Add additional keys from your dataset as input or output roles\n roles:\n input: # Optional[List[str]]. These will be masked based on train_on_input\n output: # Optional[List[str]].",
+ "text": "IMPORTANT: ShareGPT is deprecated!. Please see chat_template section below.",
"crumbs": [
"Dataset Formats",
"Conversation"
@@ -710,7 +710,7 @@
"href": "docs/dataset-formats/conversation.html#sharegpt",
"title": "Conversation",
"section": "",
- "text": "UPDATE: ShareGPT is being deprecated in the next release. Please see chat_template section below.\nconversations where from is human/gpt. (optional: first row with role system to override default system prompt)\n\n\ndata.jsonl\n\n{\"conversations\": [{\"from\": \"...\", \"value\": \"...\"}]}\n\nNote: type: sharegpt opens special configs: - conversation: enables conversions to many Conversation types. Refer to the ‘name’ here for options. - roles: allows you to specify the roles for input and output. This is useful for datasets with custom roles such as tool etc to support masking. - field_human: specify the key to use instead of human in the conversation. - field_model: specify the key to use instead of gpt in the conversation.\ndatasets:\n path: ...\n type: sharegpt\n\n conversation: # Options (see Conversation 'name'): https://github.com/lm-sys/FastChat/blob/main/fastchat/conversation.py\n field_human: # Optional[str]. Human key to use for conversation.\n field_model: # Optional[str]. Assistant key to use for conversation.\n # Add additional keys from your dataset as input or output roles\n roles:\n input: # Optional[List[str]]. These will be masked based on train_on_input\n output: # Optional[List[str]].",
+ "text": "IMPORTANT: ShareGPT is deprecated!. Please see chat_template section below.",
"crumbs": [
"Dataset Formats",
"Conversation"
@@ -727,50 +727,6 @@
"Conversation"
]
},
- {
- "objectID": "docs/dataset-formats/conversation.html#sharegpt.load_role",
- "href": "docs/dataset-formats/conversation.html#sharegpt.load_role",
- "title": "Conversation",
- "section": "sharegpt.load_role",
- "text": "sharegpt.load_role\nconversations where role is used instead of from\n\n\ndata.jsonl\n\n{\"conversations\": [{\"role\": \"...\", \"value\": \"...\"}]}",
- "crumbs": [
- "Dataset Formats",
- "Conversation"
- ]
- },
- {
- "objectID": "docs/dataset-formats/conversation.html#sharegpt.load_guanaco",
- "href": "docs/dataset-formats/conversation.html#sharegpt.load_guanaco",
- "title": "Conversation",
- "section": "sharegpt.load_guanaco",
- "text": "sharegpt.load_guanaco\nconversations where from is prompter assistant instead of default sharegpt\n\n\ndata.jsonl\n\n{\"conversations\": [{\"from\": \"...\", \"value\": \"...\"}]}",
- "crumbs": [
- "Dataset Formats",
- "Conversation"
- ]
- },
- {
- "objectID": "docs/dataset-formats/conversation.html#sharegpt.load_ultrachat",
- "href": "docs/dataset-formats/conversation.html#sharegpt.load_ultrachat",
- "title": "Conversation",
- "section": "sharegpt.load_ultrachat",
- "text": "sharegpt.load_ultrachat\nconversations where the turns field is ‘messages’, human is ‘user’ and gpt is ‘assistant’.\n\n\ndata.jsonl\n\n{\"messages\": [{\"user\": \"...\", \"assistant\": \"...\"}]}",
- "crumbs": [
- "Dataset Formats",
- "Conversation"
- ]
- },
- {
- "objectID": "docs/dataset-formats/conversation.html#sharegpt_jokes",
- "href": "docs/dataset-formats/conversation.html#sharegpt_jokes",
- "title": "Conversation",
- "section": "sharegpt_jokes",
- "text": "sharegpt_jokes\ncreates a chat where bot is asked to tell a joke, then explain why the joke is funny\n\n\ndata.jsonl\n\n{\"conversations\": [{\"title\": \"...\", \"text\": \"...\", \"explanation\": \"...\"}]}",
- "crumbs": [
- "Dataset Formats",
- "Conversation"
- ]
- },
{
"objectID": "docs/dataset-formats/conversation.html#chat_template",
"href": "docs/dataset-formats/conversation.html#chat_template",
@@ -798,7 +754,7 @@
"href": "docs/config.html",
"title": "Config options",
"section": "",
- "text": "# This is the huggingface model that contains *.pt, *.safetensors, or *.bin files\n# This can also be a relative path to a model on disk\nbase_model: ./llama-7b-hf\n# You can specify an ignore pattern if the model repo contains more than 1 model type (*.pt, etc)\nbase_model_ignore_patterns:\n# If the base_model repo on hf hub doesn't include configuration .json files,\n# You can set that here, or leave this empty to default to base_model\nbase_model_config: ./llama-7b-hf\n# You can specify to choose a specific model revision from huggingface hub\nrevision_of_model:\n# Optional tokenizer configuration path in case you want to use a different tokenizer\n# than the one defined in the base model\ntokenizer_config:\n# If you want to specify the type of model to load, AutoModelForCausalLM is a good choice too\nmodel_type: AutoModelForCausalLM\n# Corresponding tokenizer for the model AutoTokenizer is a good choice\ntokenizer_type: AutoTokenizer\n# Trust remote code for untrusted source\ntrust_remote_code:\n# use_fast option for tokenizer loading from_pretrained, default to True\ntokenizer_use_fast:\n# Whether to use the legacy tokenizer setting, defaults to True\ntokenizer_legacy:\n# Resize the model embeddings when new tokens are added to multiples of 32\n# This is reported to improve training speed on some models\nresize_token_embeddings_to_32x:\n\n# (Internal use only)\n# Used to identify which the model is based on\nis_falcon_derived_model:\nis_llama_derived_model:\nis_qwen_derived_model:\n# Please note that if you set this to true, `padding_side` will be set to \"left\" by default\nis_mistral_derived_model:\n\n# optional overrides to the base model configuration\noverrides_of_model_config:\n # RoPE Scaling https://github.com/huggingface/transformers/pull/24653\n rope_scaling:\n type: # linear | dynamic\n factor: # float\n\n# optional overrides to the bnb 4bit quantization configuration\n# https://huggingface.co/docs/transformers/main/main_classes/quantization#transformers.BitsAndBytesConfig\nbnb_config_kwargs:\n # These are default values\n llm_int8_has_fp16_weight: false\n bnb_4bit_quant_type: nf4\n bnb_4bit_use_double_quant: true\n\n\n# Whether you are training a 4-bit GPTQ quantized model\ngptq: true\n\n# This will attempt to quantize the model down to 8 bits and use adam 8 bit optimizer\nload_in_8bit: true\n# Use bitsandbytes 4 bit\nload_in_4bit:\n\n# Use CUDA bf16\nbf16: true # bool or 'full' for `bf16_full_eval`. require >=ampere\n# Use CUDA fp16\nfp16: true\n# Use CUDA tf32\ntf32: true # require >=ampere\n\n# No AMP (automatic mixed precision)\nbfloat16: true # require >=ampere\nfloat16: true\n\n# Limit the memory for all available GPUs to this amount (if an integer, expressed in gigabytes); default: unset\ngpu_memory_limit: 20GiB\n# Do the LoRA/PEFT loading on CPU -- this is required if the base model is so large it takes up most or all of the available GPU VRAM, e.g. during a model and LoRA merge\nlora_on_cpu: true\n\n# A list of one or more datasets to finetune the model with\ndatasets:\n # HuggingFace dataset repo | s3://,gs:// path | \"json\" for local dataset, make sure to fill data_files\n - path: vicgalle/alpaca-gpt4\n # The type of prompt to use for training. [alpaca, sharegpt, gpteacher, oasst, reflection]\n type: alpaca # format | format:<prompt_style> (chat/instruct) | <prompt_strategies>.load_<load_fn>\n ds_type: # Optional[str] (json|arrow|parquet|text|csv) defines the datatype when path is a file\n data_files: # Optional[str] path to source data files\n shards: # Optional[int] number of shards to split data into\n name: # Optional[str] name of dataset configuration to load\n train_on_split: train # Optional[str] name of dataset split to load from\n revision: # Optional[str] The specific revision of the dataset to use when loading from the Hugging Face Hub. This can be a commit hash, tag, or branch name. If not specified, the latest version will be used. This parameter is ignored for local datasets.\n\n # Optional[str] fastchat conversation type, only used with type: sharegpt\n conversation: # Options (see Conversation 'name'): https://github.com/lm-sys/FastChat/blob/main/fastchat/conversation.py\n field_human: # Optional[str]. Human key to use for conversation.\n field_model: # Optional[str]. Assistant key to use for conversation.\n # Add additional keys from your dataset as input or output roles\n roles:\n input: # Optional[List[str]]. These will be masked based on train_on_input\n output: # Optional[List[str]].\n\n # Custom user instruction prompt\n - path: repo\n type:\n # The below are defaults. only set what's needed if you use a different column name.\n system_prompt: \"\"\n system_format: \"{system}\"\n field_system: system\n field_instruction: instruction\n field_input: input\n field_output: output\n\n # Customizable to be single line or multi-line\n # Use {instruction}/{input} as key to be replaced\n # 'format' can include {input}\n format: |-\n User: {instruction} {input}\n Assistant:\n # 'no_input_format' cannot include {input}\n no_input_format: \"{instruction} \"\n\n # For `completion` datsets only, uses the provided field instead of `text` column\n field:\n\n # Using chat template\n - path: ...\n # Set type to `chat_template` to use this strategy\n type: chat_template\n # Specify the name of the chat template to use\n # The name of the chat template to use for training, following values are supported:\n # - tokenizer_default: Uses the chat template that is available in the tokenizer_config.json. If the chat template is not available in the tokenizer, it will raise an error. This is the default.\n # - alpaca/inst/chatml/gemma/cohere/llama3/phi_3/deepseek_v2/jamba: These chat templates are available in the axolotl codebase at src/axolotl/utils/chat_templates.py\n # - tokenizer_default_fallback_*: where * is the name of the chat template to fallback to if the tokenizer does not have a chat template else default to tokenizer. E.g. tokenizer_default_fallback_chatml.\n # - jinja: Uses a custom jinja template for the chat template. The custom jinja template should be provided in the chat_template_jinja field.\n chat_template: tokenizer_default\n # Custom jinja template for chat template. This will be only used if `chat_template` is set to `jinja` or empty (in which case chat_template is automatically set to `jinja`).\n chat_template_jinja:\n # The key in the data example that contains the messages. Default is \"messages\".\n field_messages: messages\n # The key in the message turn that contains the role. Default is \"role\".\n message_field_role: role\n # The key in the message turn that contains the content. Default is \"content\".\n message_field_content: content\n # Optional[Dict[str, List]]. Roles mapping for the messages.\n roles:\n user: [\"human\", \"user\"]\n assistant: [\"gpt\", \"assistant\", \"ai\"]\n system: [\"system\"]\n\n ## NOTE: Leaving the below empty will default to using the simple legacy tokenization strategy where only last message is trained on.\n\n # Optional[List[str]]. Roles to train on. The tokens from these roles will be considered for the loss.\n roles_to_train: [\"gpt\", \"assistant\"]\n # Optional[str]. Which EOS tokens to train on in the conversation. Possible values are:\n # - all: train on all EOS tokens\n # - turn: train on the EOS token at the end of each trainable turn\n # - last: train on the last EOS token in the conversation\n train_on_eos: last\n # The key in the message turn that indicates via boolean whether tokens of a turn should be considered for training. Useful to selectively train on certain turns besides the `roles_to_train`.\n message_field_training: training\n # The key in the message turn that contains the training details. Useful to selectively train on certain tokens in a turn.\n # The value of the key is a List[Dict] containing `begin_offset` (start character index in content), `end_offset` (end character index in content), and `train` (boolean whether to train).\n # See example at `docs/dataset-formats/conversation.qmd`\n message_field_training_detail: train_detail\n\n\n# If false, the datasets will not be shuffled and will keep their original order in `datasets`.\n# The same applies to the `test_datasets` option and the `pretraining_dataset` option. Default is true.\nshuffle_merged_datasets: true\n\n# A list of one or more datasets to eval the model with.\n# You can use either test_datasets, or val_set_size, but not both.\ntest_datasets:\n - path: /workspace/data/eval.jsonl\n ds_type: json\n # You need to specify a split. For \"json\" datasets the default split is called \"train\".\n split: train\n type: completion\n data_files:\n - /workspace/data/eval.jsonl\n\n# use RL training: 'dpo', 'ipo', 'kto'\nrl:\n# whether to perform weighting if doing DPO training. Boolean.\ndpo_use_weighting:\n\n# The name of the chat template to use for training, following values are supported:\n# - tokenizer_default: Uses the chat template that is available in the tokenizer_config.json. If the chat template is not available in the tokenizer, it will raise an error. This is the default value.\n# - alpaca/inst/chatml/gemma/cohere/llama3/phi_3/deepseek_v2/jamba: These chat templates are available in the axolotl codebase at src/axolotl/utils/chat_templates.py\n# - tokenizer_default_fallback_*: where * is the name of the chat template to fallback to. E.g. tokenizer_default_fallback_chatml. This is useful when the chat template is not available in the tokenizer.\n# - jinja: Uses a custom jinja template for the chat template. The custom jinja template should be provided in the chat_template_jinja field.\n# The selected chat template will be saved to the tokenizer_config.json for easier inferencing\n# Note: It is recommended to set train_on_inputs to true when using a chat template that is different from the model's default chat template.\nchat_template: tokenizer_default\n# custom jinja template for chat template. This will be only used if chat_template is set to `jinja` or `null` (in which case chat_template is automatically set to `jinja`). Default is null.\nchat_template_jinja: null\n# Changes the default system message\ndefault_system_message: You are a helpful assistant. Please give a long and detailed answer. # Currently only supports chatml.\n# Axolotl attempts to save the dataset as an arrow after packing the data together so\n# subsequent training attempts load faster, relative path\ndataset_prepared_path: data/last_run_prepared\n# Push prepared dataset to hub\npush_dataset_to_hub: # repo path\n# The maximum number of processes to use while preprocessing your input dataset. This defaults to `os.cpu_count()`\n# if not set.\ndataset_processes: # defaults to os.cpu_count() if not set\n# Keep dataset in memory while preprocessing\n# Only needed if cached dataset is taking too much storage\ndataset_keep_in_memory:\n# push checkpoints to hub\nhub_model_id: # private repo path to push finetuned model\n# how to push checkpoints to hub\n# https://huggingface.co/docs/transformers/v4.31.0/en/main_classes/trainer#transformers.TrainingArguments.hub_strategy\nhub_strategy:\n# Whether to use hf `use_auth_token` for loading datasets. Useful for fetching private datasets\n# Required to be true when used in combination with `push_dataset_to_hub`\nhf_use_auth_token: # boolean\n# How much of the dataset to set aside as evaluation. 1 = 100%, 0.50 = 50%, etc. 0 for no eval.\nval_set_size: 0.04\n# Num shards for whole dataset\ndataset_shard_num:\n# Index of shard to use for whole dataset\ndataset_shard_idx:\n\n# The maximum length of an input to train with, this should typically be less than 2048\n# as most models have a token/context limit of 2048\nsequence_len: 2048\n# Pad inputs so each step uses constant sized buffers\n# This will reduce memory fragmentation and may prevent OOMs, by re-using memory more efficiently\npad_to_sequence_len:\n# Use efficient multi-packing with block diagonal attention and per sequence position_ids. Recommend set to 'true'\nsample_packing:\n# Set to 'false' if getting errors during eval with sample_packing on.\neval_sample_packing:\n# You can set these packing optimizations AFTER starting a training at least once.\n# The trainer will provide recommended values for these values.\nsample_packing_eff_est:\ntotal_num_tokens:\n# Increasing the following values helps with packing, but usually only slightly (<%1.)\n# The number of samples packed at a time.\nsample_packing_group_size: 100000\n# The number of samples which can be packed into one sequence. Increase if using a large sequence_len with many short samples.\nsample_packing_bin_size: 200\n\n# Passed through to transformers when loading the model when launched without accelerate\n# Use `sequential` when training w/ model parallelism to limit memory\ndevice_map:\n# Defines the max memory usage per gpu on the system. Passed through to transformers when loading the model.\nmax_memory:\n\n# If you want to use 'lora' or 'qlora' or leave blank to train all parameters in original model\nadapter: lora\n# If you already have a lora model trained that you want to load, put that here.\n# This means after training, if you want to test the model, you should set this to the value of `output_dir`.\n# Note that if you merge an adapter to the base model, a new subdirectory `merged` will be created under the `output_dir`.\nlora_model_dir:\n\n# LoRA hyperparameters\n# For more details about the following options, see:\n# https://www.anyscale.com/blog/fine-tuning-llms-lora-or-full-parameter-an-in-depth-analysis-with-llama-2\nlora_r: 8\nlora_alpha: 16\nlora_dropout: 0.05\nlora_target_modules:\n - q_proj\n - v_proj\n# - k_proj\n# - o_proj\n# - gate_proj\n# - down_proj\n# - up_proj\nlora_target_linear: # If true, will target all linear modules\npeft_layers_to_transform: # The layer indices to transform, otherwise, apply to all layers\n\n# If you added new tokens to the tokenizer, you may need to save some LoRA modules because they need to know the new tokens.\n# For LLaMA and Mistral, you need to save `embed_tokens` and `lm_head`. It may vary for other models.\n# `embed_tokens` converts tokens to embeddings, and `lm_head` converts embeddings to token probabilities.\n# https://github.com/huggingface/peft/issues/334#issuecomment-1561727994\nlora_modules_to_save:\n# - embed_tokens\n# - lm_head\n\nlora_fan_in_fan_out: false\n\n# LoRA+ hyperparameters\n# For more details about the following options, see:\n# https://arxiv.org/abs/2402.12354 and `src/axolotl/core/train_builder.py`\nloraplus_lr_ratio: # loraplus learning rate ratio lr_B / lr_A. Recommended value is 2^4.\nloraplus_lr_embedding: # loraplus learning rate for lora embedding layers. Default value is 1e-6.\n\npeft:\n # Configuration options for loftq initialization for LoRA\n # https://huggingface.co/docs/peft/developer_guides/quantization#loftq-initialization\n loftq_config:\n loftq_bits: # typically 4 bits\n\n# ReLoRA configuration\n# Must use either 'lora' or 'qlora' adapter, and does not support fsdp or deepspeed\nrelora_steps: # Number of steps per ReLoRA restart\nrelora_warmup_steps: # Number of per-restart warmup steps\nrelora_anneal_steps: # Number of anneal steps for each relora cycle\nrelora_prune_ratio: # threshold for optimizer magnitude when pruning\nrelora_cpu_offload: # True to perform lora weight merges on cpu during restarts, for modest gpu memory savings\n\n# wandb configuration if you're using it\n# Make sure your `WANDB_API_KEY` environment variable is set (recommended) or you login to wandb with `wandb login`.\nwandb_mode: # \"offline\" to save run metadata locally and not sync to the server, \"disabled\" to turn off wandb\nwandb_project: # Your wandb project name\nwandb_entity: # A wandb Team name if using a Team\nwandb_watch:\nwandb_name: # Set the name of your wandb run\nwandb_run_id: # Set the ID of your wandb run\nwandb_log_model: # \"checkpoint\" to log model to wandb Artifacts every `save_steps` or \"end\" to log only at the end of training\n\n# mlflow configuration if you're using it\nmlflow_tracking_uri: # URI to mlflow\nmlflow_experiment_name: # Your experiment name\nmlflow_run_name: # Your run name\nhf_mlflow_log_artifacts: # set to true to copy each saved checkpoint on each save to mlflow artifact registry\n\n# Comet configuration if you're using it\n# Make sure your `COMET_API_KEY` environment variable is set (recommended) or you login to Comet with `comet login`.\n# Check out our documentation for more details https://www.comet.com/docs/v2/api-and-sdk/python-sdk/reference/Experiment-Creation/#comet_ml.start\nuse_comet: # Enable or disable Comet integration.\ncomet_api_key: # API key for Comet. Recommended to set via `comet login`.\ncomet_workspace: # Workspace name in Comet. Defaults to the user's default workspace.\ncomet_project_name: # Project name in Comet. Defaults to Uncategorized.\ncomet_experiment_key: # Identifier for the experiment. Used to append data to an existing experiment or control the key of new experiments. Default to a random key.\ncomet_mode: # Create a new experiment (\"create\") or log to an existing one (\"get\"). Default (\"get_or_create\") auto-selects based on configuration.\ncomet_online: # Set to True to log data to Comet server, or False for offline storage. Default is True.\ncomet_experiment_config: # Dictionary for additional configuration settings, see the doc for more details.\n\n# Where to save the full-finetuned model to\noutput_dir: ./completed-model\n\n# Whether to use torch.compile and which backend to use\ntorch_compile: # bool\ntorch_compile_backend: # Optional[str]\n\n# Training hyperparameters\n\n# If greater than 1, backpropagation will be skipped and the gradients will be accumulated for the given number of steps.\ngradient_accumulation_steps: 1\n# The number of samples to include in each batch. This is the number of samples sent to each GPU.\n# Batch size per gpu = micro_batch_size * gradient_accumulation_steps\nmicro_batch_size: 2\neval_batch_size:\nnum_epochs: 4\nwarmup_steps: 100 # cannot use with warmup_ratio\nwarmup_ratio: 0.05 # cannot use with warmup_steps\nlearning_rate: 0.00003\nlr_quadratic_warmup:\nlogging_steps:\neval_steps: # Leave empty to eval at each epoch, integers for every N steps. decimal for fraction of total steps\nevals_per_epoch: # number of times per epoch to run evals, mutually exclusive with eval_steps\nsave_strategy: # Set to `\"no\"` to skip checkpoint saves\nsave_steps: # Leave empty to save at each epoch\nsaves_per_epoch: # number of times per epoch to save a checkpoint, mutually exclusive with save_steps\nsave_total_limit: # Checkpoints saved at a time\n# Maximum number of iterations to train for. It precedes num_epochs which means that\n# if both are set, num_epochs will not be guaranteed.\n# e.g., when 1 epoch is 1000 steps => `num_epochs: 2` and `max_steps: 100` will train for 100 steps\nmax_steps:\n\neval_table_size: # Approximate number of predictions sent to wandb depending on batch size. Enabled above 0. Default is 0\neval_max_new_tokens: # Total number of tokens generated for predictions sent to wandb. Default is 128\neval_causal_lm_metrics: # HF evaluate metrics used during evaluation. Default is [\"sacrebleu\", \"comet\", \"ter\", \"chrf\", \"perplexity\"]\n\nloss_watchdog_threshold: # High loss value, indicating the learning has broken down (a good estimate is ~2 times the loss at the start of training)\nloss_watchdog_patience: # Number of high-loss steps in a row before the trainer aborts (default: 3)\n\n# Save model as safetensors (require safetensors package)\nsave_safetensors:\n\n# Whether to mask out or include the human's prompt from the training labels\ntrain_on_inputs: false\n# Group similarly sized data to minimize padding.\n# May be slower to start, as it must download and sort the entire dataset.\n# Note that training loss may have an oscillating pattern with this enabled.\ngroup_by_length: false\n\n# Whether to use gradient checkpointing https://huggingface.co/docs/transformers/v4.18.0/en/performance#gradient-checkpointing\ngradient_checkpointing: false\n# additional kwargs to pass to the trainer for gradient checkpointing\n# gradient_checkpointing_kwargs:\n# use_reentrant: true\n\n# Stop training after this many evaluation losses have increased in a row\n# https://huggingface.co/transformers/v4.2.2/_modules/transformers/trainer_callback.html#EarlyStoppingCallback\nearly_stopping_patience: 3\n\n# Specify a scheduler and kwargs to use with the optimizer\nlr_scheduler: # 'one_cycle' | 'log_sweep' | empty for cosine\nlr_scheduler_kwargs:\ncosine_min_lr_ratio: # decay lr to some percentage of the peak lr, e.g. cosine_min_lr_ratio=0.1 for 10% of peak lr\ncosine_constant_lr_ratio: # freeze lr at some percentage of the step, e.g. cosine_constant_lr_ratio=0.8 means start cosine_min_lr at 80% of training step (https://arxiv.org/pdf/2308.04014.pdf)\n\n# For one_cycle optim\nlr_div_factor: # Learning rate div factor\n\n# Specify optimizer\n# Valid values are driven by the Transformers OptimizerNames class, see:\n# https://github.com/huggingface/transformers/blob/95b374952dc27d8511541d6f5a4e22c9ec11fb24/src/transformers/training_args.py#L134\n#\n# Note that not all optimizers may be available in your environment, ex: 'adamw_anyprecision' is part of\n# torchdistx, 'adamw_bnb_8bit' is part of bnb.optim.Adam8bit, etc. When in doubt, it is recommended to start with the optimizer used\n# in the examples/ for your model and fine-tuning use case.\n#\n# Valid values for 'optimizer' include:\n# - adamw_hf\n# - adamw_torch\n# - adamw_torch_fused\n# - adamw_torch_xla\n# - adamw_apex_fused\n# - adafactor\n# - adamw_anyprecision\n# - sgd\n# - adagrad\n# - adamw_bnb_8bit\n# - lion_8bit\n# - lion_32bit\n# - paged_adamw_32bit\n# - paged_adamw_8bit\n# - paged_lion_32bit\n# - paged_lion_8bit\n# - galore_adamw\n# - galore_adamw_8bit\n# - galore_adafactor\n# - galore_adamw_layerwise\n# - galore_adamw_8bit_layerwise\n# - galore_adafactor_layerwise\noptimizer:\n# Dictionary of arguments to pass to the optimizer\noptim_args:\n# For Galore Optimizers the following optim_args are available\n# rank: # type: int\n# update_proj_gap # type: int\n# scale # type: float\n# proj_type: # type: str, default = std\n\n# The target modules to optimize, i.e. the module names that you would like to train, right now this is used only for GaLore algorithm\noptim_target_modules:\n# - self_attn # for llama\n# - mlp\n\n# Specify weight decay\nweight_decay:\n# adamw hyperparams\nadam_beta1:\nadam_beta2:\nadam_epsilon:\n# Gradient clipping max norm\nmax_grad_norm:\n\n# Augmentation techniques\n# NEFT https://arxiv.org/abs/2310.05914, set this to a number (paper default is 5) to add noise to embeddings\n# currently only supported on Llama and Mistral\nneftune_noise_alpha:\n\n# Whether to bettertransformers\nflash_optimum:\n# Whether to use xformers attention patch https://github.com/facebookresearch/xformers:\nxformers_attention:\n# Whether to use flash attention patch https://github.com/Dao-AILab/flash-attention:\nflash_attention:\nflash_attn_cross_entropy: # Whether to use flash-attention cross entropy implementation - advanced use only\nflash_attn_rms_norm: # Whether to use flash-attention rms norm implementation - advanced use only\nflash_attn_fuse_qkv: # Whether to fuse QKV into a single operation\nflash_attn_fuse_mlp: # Whether to fuse part of the MLP into a single operation\n# Whether to use scaled-dot-product attention\n# https://pytorch.org/docs/stable/generated/torch.nn.functional.scaled_dot_product_attention.html\nsdp_attention:\n# Shifted-sparse attention (only llama) - https://arxiv.org/pdf/2309.12307.pdf\ns2_attention:\n# Resume from a specific checkpoint dir\nresume_from_checkpoint:\n# If resume_from_checkpoint isn't set and you simply want it to start where it left off.\n# Be careful with this being turned on between different models.\nauto_resume_from_checkpoints: false\n\n# Don't mess with this, it's here for accelerate and torchrun\nlocal_rank:\n\n# Add or change special tokens.\n# If you add tokens here, you don't need to add them to the `tokens` list.\nspecial_tokens:\n # bos_token: \"<s>\"\n # eos_token: \"</s>\"\n # unk_token: \"<unk>\"\n # pad_token: \"[PAD]\"\n\n# Add extra tokens.\ntokens:\n\n# FSDP\nfsdp:\nfsdp_config:\n\n# Deepspeed config path. e.g., deepspeed_configs/zero3.json\ndeepspeed:\n\n# Advanced DDP Arguments\nddp_timeout:\nddp_bucket_cap_mb:\nddp_broadcast_buffers:\n\n# Path to torch distx for optim 'adamw_anyprecision'\ntorchdistx_path:\n\n# Set to HF dataset for type: 'completion' for streaming instead of pre-tokenize\npretraining_dataset:\n\n# Debug mode\ndebug:\n\n# Seed\nseed:\n\n# Allow overwrite yml config using from cli\nstrict:",
+ "text": "# This is the huggingface model that contains *.pt, *.safetensors, or *.bin files\n# This can also be a relative path to a model on disk\nbase_model: ./llama-7b-hf\n# You can specify an ignore pattern if the model repo contains more than 1 model type (*.pt, etc)\nbase_model_ignore_patterns:\n# If the base_model repo on hf hub doesn't include configuration .json files,\n# You can set that here, or leave this empty to default to base_model\nbase_model_config: ./llama-7b-hf\n# You can specify to choose a specific model revision from huggingface hub\nrevision_of_model:\n# Optional tokenizer configuration path in case you want to use a different tokenizer\n# than the one defined in the base model\ntokenizer_config:\n# If you want to specify the type of model to load, AutoModelForCausalLM is a good choice too\nmodel_type: AutoModelForCausalLM\n# Corresponding tokenizer for the model AutoTokenizer is a good choice\ntokenizer_type: AutoTokenizer\n# Trust remote code for untrusted source\ntrust_remote_code:\n# use_fast option for tokenizer loading from_pretrained, default to True\ntokenizer_use_fast:\n# Whether to use the legacy tokenizer setting, defaults to True\ntokenizer_legacy:\n# Resize the model embeddings when new tokens are added to multiples of 32\n# This is reported to improve training speed on some models\nresize_token_embeddings_to_32x:\n\n# (Internal use only)\n# Used to identify which the model is based on\nis_falcon_derived_model:\nis_llama_derived_model:\nis_qwen_derived_model:\n# Please note that if you set this to true, `padding_side` will be set to \"left\" by default\nis_mistral_derived_model:\n\n# optional overrides to the base model configuration\noverrides_of_model_config:\n # RoPE Scaling https://github.com/huggingface/transformers/pull/24653\n rope_scaling:\n type: # linear | dynamic\n factor: # float\n\n# optional overrides to the bnb 4bit quantization configuration\n# https://huggingface.co/docs/transformers/main/main_classes/quantization#transformers.BitsAndBytesConfig\nbnb_config_kwargs:\n # These are default values\n llm_int8_has_fp16_weight: false\n bnb_4bit_quant_type: nf4\n bnb_4bit_use_double_quant: true\n\n\n# Whether you are training a 4-bit GPTQ quantized model\ngptq: true\n\n# This will attempt to quantize the model down to 8 bits and use adam 8 bit optimizer\nload_in_8bit: true\n# Use bitsandbytes 4 bit\nload_in_4bit:\n\n# Use CUDA bf16\nbf16: true # bool or 'full' for `bf16_full_eval`. require >=ampere\n# Use CUDA fp16\nfp16: true\n# Use CUDA tf32\ntf32: true # require >=ampere\n\n# No AMP (automatic mixed precision)\nbfloat16: true # require >=ampere\nfloat16: true\n\n# Limit the memory for all available GPUs to this amount (if an integer, expressed in gigabytes); default: unset\ngpu_memory_limit: 20GiB\n# Do the LoRA/PEFT loading on CPU -- this is required if the base model is so large it takes up most or all of the available GPU VRAM, e.g. during a model and LoRA merge\nlora_on_cpu: true\n\n# A list of one or more datasets to finetune the model with\ndatasets:\n # HuggingFace dataset repo | s3://,gs:// path | \"json\" for local dataset, make sure to fill data_files\n - path: vicgalle/alpaca-gpt4\n # The type of prompt to use for training. [alpaca, gpteacher, oasst, reflection]\n type: alpaca # format | format:<prompt_style> (chat/instruct) | <prompt_strategies>.load_<load_fn>\n ds_type: # Optional[str] (json|arrow|parquet|text|csv) defines the datatype when path is a file\n data_files: # Optional[str] path to source data files\n shards: # Optional[int] number of shards to split data into\n name: # Optional[str] name of dataset configuration to load\n train_on_split: train # Optional[str] name of dataset split to load from\n revision: # Optional[str] The specific revision of the dataset to use when loading from the Hugging Face Hub. This can be a commit hash, tag, or branch name. If not specified, the latest version will be used. This parameter is ignored for local datasets.\n\n # Custom user instruction prompt\n - path: repo\n type:\n # The below are defaults. only set what's needed if you use a different column name.\n system_prompt: \"\"\n system_format: \"{system}\"\n field_system: system\n field_instruction: instruction\n field_input: input\n field_output: output\n\n # Customizable to be single line or multi-line\n # Use {instruction}/{input} as key to be replaced\n # 'format' can include {input}\n format: |-\n User: {instruction} {input}\n Assistant:\n # 'no_input_format' cannot include {input}\n no_input_format: \"{instruction} \"\n\n # For `completion` datsets only, uses the provided field instead of `text` column\n field:\n\n # Using chat template\n - path: ...\n # Set type to `chat_template` to use this strategy\n type: chat_template\n # Specify the name of the chat template to use\n # The name of the chat template to use for training, following values are supported:\n # - tokenizer_default: Uses the chat template that is available in the tokenizer_config.json. If the chat template is not available in the tokenizer, it will raise an error. This is the default.\n # - alpaca/inst/chatml/gemma/cohere/llama3/phi_3/deepseek_v2/jamba: These chat templates are available in the axolotl codebase at src/axolotl/utils/chat_templates.py\n # - tokenizer_default_fallback_*: where * is the name of the chat template to fallback to if the tokenizer does not have a chat template else default to tokenizer. E.g. tokenizer_default_fallback_chatml.\n # - jinja: Uses a custom jinja template for the chat template. The custom jinja template should be provided in the chat_template_jinja field.\n chat_template: tokenizer_default\n # Custom jinja template for chat template. This will be only used if `chat_template` is set to `jinja` or empty (in which case chat_template is automatically set to `jinja`).\n chat_template_jinja:\n # The key in the data example that contains the messages. Default is \"messages\".\n field_messages: messages\n # The key in the message turn that contains the role. Default is \"role\".\n message_field_role: role\n # The key in the message turn that contains the content. Default is \"content\".\n message_field_content: content\n # Optional[Dict[str, List]]. Roles mapping for the messages.\n roles:\n user: [\"human\", \"user\"]\n assistant: [\"gpt\", \"assistant\", \"ai\"]\n system: [\"system\"]\n\n ## NOTE: Leaving the below empty will default to using the simple legacy tokenization strategy where only last message is trained on.\n\n # Optional[List[str]]. Roles to train on. The tokens from these roles will be considered for the loss.\n roles_to_train: [\"gpt\", \"assistant\"]\n # Optional[str]. Which EOS tokens to train on in the conversation. Possible values are:\n # - all: train on all EOS tokens\n # - turn: train on the EOS token at the end of each trainable turn\n # - last: train on the last EOS token in the conversation\n train_on_eos: last\n # The key in the message turn that indicates via boolean whether tokens of a turn should be considered for training. Useful to selectively train on certain turns besides the `roles_to_train`.\n message_field_training: training\n # The key in the message turn that contains the training details. Useful to selectively train on certain tokens in a turn.\n # The value of the key is a List[Dict] containing `begin_offset` (start character index in content), `end_offset` (end character index in content), and `train` (boolean whether to train).\n # See example at `docs/dataset-formats/conversation.qmd`\n message_field_training_detail: train_detail\n\n\n# If false, the datasets will not be shuffled and will keep their original order in `datasets`.\n# The same applies to the `test_datasets` option and the `pretraining_dataset` option. Default is true.\nshuffle_merged_datasets: true\n\n# A list of one or more datasets to eval the model with.\n# You can use either test_datasets, or val_set_size, but not both.\ntest_datasets:\n - path: /workspace/data/eval.jsonl\n ds_type: json\n # You need to specify a split. For \"json\" datasets the default split is called \"train\".\n split: train\n type: completion\n data_files:\n - /workspace/data/eval.jsonl\n\n# use RL training: 'dpo', 'ipo', 'kto'\nrl:\n# whether to perform weighting if doing DPO training. Boolean.\ndpo_use_weighting:\n\n# The name of the chat template to use for training, following values are supported:\n# - tokenizer_default: Uses the chat template that is available in the tokenizer_config.json. If the chat template is not available in the tokenizer, it will raise an error. This is the default value.\n# - alpaca/inst/chatml/gemma/cohere/llama3/phi_3/deepseek_v2/jamba: These chat templates are available in the axolotl codebase at src/axolotl/utils/chat_templates.py\n# - tokenizer_default_fallback_*: where * is the name of the chat template to fallback to. E.g. tokenizer_default_fallback_chatml. This is useful when the chat template is not available in the tokenizer.\n# - jinja: Uses a custom jinja template for the chat template. The custom jinja template should be provided in the chat_template_jinja field.\n# The selected chat template will be saved to the tokenizer_config.json for easier inferencing\n# Note: It is recommended to set train_on_inputs to true when using a chat template that is different from the model's default chat template.\nchat_template: tokenizer_default\n# custom jinja template for chat template. This will be only used if chat_template is set to `jinja` or `null` (in which case chat_template is automatically set to `jinja`). Default is null.\nchat_template_jinja: null\n# Changes the default system message\ndefault_system_message: You are a helpful assistant. Please give a long and detailed answer. # Currently only supports chatml.\n# Axolotl attempts to save the dataset as an arrow after packing the data together so\n# subsequent training attempts load faster, relative path\ndataset_prepared_path: data/last_run_prepared\n# Push prepared dataset to hub\npush_dataset_to_hub: # repo path\n# The maximum number of processes to use while preprocessing your input dataset. This defaults to `os.cpu_count()`\n# if not set.\ndataset_processes: # defaults to os.cpu_count() if not set\n# Keep dataset in memory while preprocessing\n# Only needed if cached dataset is taking too much storage\ndataset_keep_in_memory:\n# push checkpoints to hub\nhub_model_id: # private repo path to push finetuned model\n# how to push checkpoints to hub\n# https://huggingface.co/docs/transformers/v4.31.0/en/main_classes/trainer#transformers.TrainingArguments.hub_strategy\nhub_strategy:\n# Whether to use hf `use_auth_token` for loading datasets. Useful for fetching private datasets\n# Required to be true when used in combination with `push_dataset_to_hub`\nhf_use_auth_token: # boolean\n# How much of the dataset to set aside as evaluation. 1 = 100%, 0.50 = 50%, etc. 0 for no eval.\nval_set_size: 0.04\n# Num shards for whole dataset\ndataset_shard_num:\n# Index of shard to use for whole dataset\ndataset_shard_idx:\n\n# The maximum length of an input to train with, this should typically be less than 2048\n# as most models have a token/context limit of 2048\nsequence_len: 2048\n# Pad inputs so each step uses constant sized buffers\n# This will reduce memory fragmentation and may prevent OOMs, by re-using memory more efficiently\npad_to_sequence_len:\n# Use efficient multi-packing with block diagonal attention and per sequence position_ids. Recommend set to 'true'\nsample_packing:\n# Set to 'false' if getting errors during eval with sample_packing on.\neval_sample_packing:\n# You can set these packing optimizations AFTER starting a training at least once.\n# The trainer will provide recommended values for these values.\nsample_packing_eff_est:\ntotal_num_tokens:\n# Increasing the following values helps with packing, but usually only slightly (<%1.)\n# The number of samples packed at a time.\nsample_packing_group_size: 100000\n# The number of samples which can be packed into one sequence. Increase if using a large sequence_len with many short samples.\nsample_packing_bin_size: 200\n\n# Passed through to transformers when loading the model when launched without accelerate\n# Use `sequential` when training w/ model parallelism to limit memory\ndevice_map:\n# Defines the max memory usage per gpu on the system. Passed through to transformers when loading the model.\nmax_memory:\n\n# If you want to use 'lora' or 'qlora' or leave blank to train all parameters in original model\nadapter: lora\n# If you already have a lora model trained that you want to load, put that here.\n# This means after training, if you want to test the model, you should set this to the value of `output_dir`.\n# Note that if you merge an adapter to the base model, a new subdirectory `merged` will be created under the `output_dir`.\nlora_model_dir:\n\n# LoRA hyperparameters\n# For more details about the following options, see:\n# https://www.anyscale.com/blog/fine-tuning-llms-lora-or-full-parameter-an-in-depth-analysis-with-llama-2\nlora_r: 8\nlora_alpha: 16\nlora_dropout: 0.05\nlora_target_modules:\n - q_proj\n - v_proj\n# - k_proj\n# - o_proj\n# - gate_proj\n# - down_proj\n# - up_proj\nlora_target_linear: # If true, will target all linear modules\npeft_layers_to_transform: # The layer indices to transform, otherwise, apply to all layers\n\n# If you added new tokens to the tokenizer, you may need to save some LoRA modules because they need to know the new tokens.\n# For LLaMA and Mistral, you need to save `embed_tokens` and `lm_head`. It may vary for other models.\n# `embed_tokens` converts tokens to embeddings, and `lm_head` converts embeddings to token probabilities.\n# https://github.com/huggingface/peft/issues/334#issuecomment-1561727994\nlora_modules_to_save:\n# - embed_tokens\n# - lm_head\n\nlora_fan_in_fan_out: false\n\n# LoRA+ hyperparameters\n# For more details about the following options, see:\n# https://arxiv.org/abs/2402.12354 and `src/axolotl/core/train_builder.py`\nloraplus_lr_ratio: # loraplus learning rate ratio lr_B / lr_A. Recommended value is 2^4.\nloraplus_lr_embedding: # loraplus learning rate for lora embedding layers. Default value is 1e-6.\n\npeft:\n # Configuration options for loftq initialization for LoRA\n # https://huggingface.co/docs/peft/developer_guides/quantization#loftq-initialization\n loftq_config:\n loftq_bits: # typically 4 bits\n\n# ReLoRA configuration\n# Must use either 'lora' or 'qlora' adapter, and does not support fsdp or deepspeed\nrelora_steps: # Number of steps per ReLoRA restart\nrelora_warmup_steps: # Number of per-restart warmup steps\nrelora_anneal_steps: # Number of anneal steps for each relora cycle\nrelora_prune_ratio: # threshold for optimizer magnitude when pruning\nrelora_cpu_offload: # True to perform lora weight merges on cpu during restarts, for modest gpu memory savings\n\n# wandb configuration if you're using it\n# Make sure your `WANDB_API_KEY` environment variable is set (recommended) or you login to wandb with `wandb login`.\nwandb_mode: # \"offline\" to save run metadata locally and not sync to the server, \"disabled\" to turn off wandb\nwandb_project: # Your wandb project name\nwandb_entity: # A wandb Team name if using a Team\nwandb_watch:\nwandb_name: # Set the name of your wandb run\nwandb_run_id: # Set the ID of your wandb run\nwandb_log_model: # \"checkpoint\" to log model to wandb Artifacts every `save_steps` or \"end\" to log only at the end of training\n\n# mlflow configuration if you're using it\nmlflow_tracking_uri: # URI to mlflow\nmlflow_experiment_name: # Your experiment name\nmlflow_run_name: # Your run name\nhf_mlflow_log_artifacts: # set to true to copy each saved checkpoint on each save to mlflow artifact registry\n\n# Comet configuration if you're using it\n# Make sure your `COMET_API_KEY` environment variable is set (recommended) or you login to Comet with `comet login`.\n# Check out our documentation for more details https://www.comet.com/docs/v2/api-and-sdk/python-sdk/reference/Experiment-Creation/#comet_ml.start\nuse_comet: # Enable or disable Comet integration.\ncomet_api_key: # API key for Comet. Recommended to set via `comet login`.\ncomet_workspace: # Workspace name in Comet. Defaults to the user's default workspace.\ncomet_project_name: # Project name in Comet. Defaults to Uncategorized.\ncomet_experiment_key: # Identifier for the experiment. Used to append data to an existing experiment or control the key of new experiments. Default to a random key.\ncomet_mode: # Create a new experiment (\"create\") or log to an existing one (\"get\"). Default (\"get_or_create\") auto-selects based on configuration.\ncomet_online: # Set to True to log data to Comet server, or False for offline storage. Default is True.\ncomet_experiment_config: # Dictionary for additional configuration settings, see the doc for more details.\n\n# Where to save the full-finetuned model to\noutput_dir: ./completed-model\n\n# Whether to use torch.compile and which backend to use\ntorch_compile: # bool\ntorch_compile_backend: # Optional[str]\n\n# Training hyperparameters\n\n# If greater than 1, backpropagation will be skipped and the gradients will be accumulated for the given number of steps.\ngradient_accumulation_steps: 1\n# The number of samples to include in each batch. This is the number of samples sent to each GPU.\n# Batch size per gpu = micro_batch_size * gradient_accumulation_steps\nmicro_batch_size: 2\neval_batch_size:\nnum_epochs: 4\nwarmup_steps: 100 # cannot use with warmup_ratio\nwarmup_ratio: 0.05 # cannot use with warmup_steps\nlearning_rate: 0.00003\nlr_quadratic_warmup:\nlogging_steps:\neval_steps: # Leave empty to eval at each epoch, integers for every N steps. decimal for fraction of total steps\nevals_per_epoch: # number of times per epoch to run evals, mutually exclusive with eval_steps\nsave_strategy: # Set to `\"no\"` to skip checkpoint saves\nsave_steps: # Leave empty to save at each epoch\nsaves_per_epoch: # number of times per epoch to save a checkpoint, mutually exclusive with save_steps\nsave_total_limit: # Checkpoints saved at a time\n# Maximum number of iterations to train for. It precedes num_epochs which means that\n# if both are set, num_epochs will not be guaranteed.\n# e.g., when 1 epoch is 1000 steps => `num_epochs: 2` and `max_steps: 100` will train for 100 steps\nmax_steps:\n\neval_table_size: # Approximate number of predictions sent to wandb depending on batch size. Enabled above 0. Default is 0\neval_max_new_tokens: # Total number of tokens generated for predictions sent to wandb. Default is 128\neval_causal_lm_metrics: # HF evaluate metrics used during evaluation. Default is [\"sacrebleu\", \"comet\", \"ter\", \"chrf\", \"perplexity\"]\n\nloss_watchdog_threshold: # High loss value, indicating the learning has broken down (a good estimate is ~2 times the loss at the start of training)\nloss_watchdog_patience: # Number of high-loss steps in a row before the trainer aborts (default: 3)\n\n# Save model as safetensors (require safetensors package)\nsave_safetensors:\n\n# Whether to mask out or include the human's prompt from the training labels\ntrain_on_inputs: false\n# Group similarly sized data to minimize padding.\n# May be slower to start, as it must download and sort the entire dataset.\n# Note that training loss may have an oscillating pattern with this enabled.\ngroup_by_length: false\n\n# Whether to use gradient checkpointing https://huggingface.co/docs/transformers/v4.18.0/en/performance#gradient-checkpointing\ngradient_checkpointing: false\n# additional kwargs to pass to the trainer for gradient checkpointing\n# gradient_checkpointing_kwargs:\n# use_reentrant: true\n\n# Stop training after this many evaluation losses have increased in a row\n# https://huggingface.co/transformers/v4.2.2/_modules/transformers/trainer_callback.html#EarlyStoppingCallback\nearly_stopping_patience: 3\n\n# Specify a scheduler and kwargs to use with the optimizer\nlr_scheduler: # 'one_cycle' | 'log_sweep' | empty for cosine\nlr_scheduler_kwargs:\ncosine_min_lr_ratio: # decay lr to some percentage of the peak lr, e.g. cosine_min_lr_ratio=0.1 for 10% of peak lr\ncosine_constant_lr_ratio: # freeze lr at some percentage of the step, e.g. cosine_constant_lr_ratio=0.8 means start cosine_min_lr at 80% of training step (https://arxiv.org/pdf/2308.04014.pdf)\n\n# For one_cycle optim\nlr_div_factor: # Learning rate div factor\n\n# Specify optimizer\n# Valid values are driven by the Transformers OptimizerNames class, see:\n# https://github.com/huggingface/transformers/blob/95b374952dc27d8511541d6f5a4e22c9ec11fb24/src/transformers/training_args.py#L134\n#\n# Note that not all optimizers may be available in your environment, ex: 'adamw_anyprecision' is part of\n# torchdistx, 'adamw_bnb_8bit' is part of bnb.optim.Adam8bit, etc. When in doubt, it is recommended to start with the optimizer used\n# in the examples/ for your model and fine-tuning use case.\n#\n# Valid values for 'optimizer' include:\n# - adamw_hf\n# - adamw_torch\n# - adamw_torch_fused\n# - adamw_torch_xla\n# - adamw_apex_fused\n# - adafactor\n# - adamw_anyprecision\n# - sgd\n# - adagrad\n# - adamw_bnb_8bit\n# - lion_8bit\n# - lion_32bit\n# - paged_adamw_32bit\n# - paged_adamw_8bit\n# - paged_lion_32bit\n# - paged_lion_8bit\n# - galore_adamw\n# - galore_adamw_8bit\n# - galore_adafactor\n# - galore_adamw_layerwise\n# - galore_adamw_8bit_layerwise\n# - galore_adafactor_layerwise\noptimizer:\n# Dictionary of arguments to pass to the optimizer\noptim_args:\n# For Galore Optimizers the following optim_args are available\n# rank: # type: int\n# update_proj_gap # type: int\n# scale # type: float\n# proj_type: # type: str, default = std\n\n# The target modules to optimize, i.e. the module names that you would like to train, right now this is used only for GaLore algorithm\noptim_target_modules:\n# - self_attn # for llama\n# - mlp\n\n# Specify weight decay\nweight_decay:\n# adamw hyperparams\nadam_beta1:\nadam_beta2:\nadam_epsilon:\n# Gradient clipping max norm\nmax_grad_norm:\n\n# Augmentation techniques\n# NEFT https://arxiv.org/abs/2310.05914, set this to a number (paper default is 5) to add noise to embeddings\n# currently only supported on Llama and Mistral\nneftune_noise_alpha:\n\n# Whether to bettertransformers\nflash_optimum:\n# Whether to use xformers attention patch https://github.com/facebookresearch/xformers:\nxformers_attention:\n# Whether to use flash attention patch https://github.com/Dao-AILab/flash-attention:\nflash_attention:\nflash_attn_cross_entropy: # Whether to use flash-attention cross entropy implementation - advanced use only\nflash_attn_rms_norm: # Whether to use flash-attention rms norm implementation - advanced use only\nflash_attn_fuse_qkv: # Whether to fuse QKV into a single operation\nflash_attn_fuse_mlp: # Whether to fuse part of the MLP into a single operation\n# Whether to use scaled-dot-product attention\n# https://pytorch.org/docs/stable/generated/torch.nn.functional.scaled_dot_product_attention.html\nsdp_attention:\n# Shifted-sparse attention (only llama) - https://arxiv.org/pdf/2309.12307.pdf\ns2_attention:\n# Resume from a specific checkpoint dir\nresume_from_checkpoint:\n# If resume_from_checkpoint isn't set and you simply want it to start where it left off.\n# Be careful with this being turned on between different models.\nauto_resume_from_checkpoints: false\n\n# Don't mess with this, it's here for accelerate and torchrun\nlocal_rank:\n\n# Add or change special tokens.\n# If you add tokens here, you don't need to add them to the `tokens` list.\nspecial_tokens:\n # bos_token: \"<s>\"\n # eos_token: \"</s>\"\n # unk_token: \"<unk>\"\n # pad_token: \"[PAD]\"\n\n# Add extra tokens.\ntokens:\n\n# FSDP\nfsdp:\nfsdp_config:\n\n# Deepspeed config path. e.g., deepspeed_configs/zero3.json\ndeepspeed:\n\n# Advanced DDP Arguments\nddp_timeout:\nddp_bucket_cap_mb:\nddp_broadcast_buffers:\n\n# Path to torch distx for optim 'adamw_anyprecision'\ntorchdistx_path:\n\n# Set to HF dataset for type: 'completion' for streaming instead of pre-tokenize\npretraining_dataset:\n\n# Debug mode\ndebug:\n\n# Seed\nseed:\n\n# Allow overwrite yml config using from cli\nstrict:",
"crumbs": [
"Reference",
"Config options"
diff --git a/sitemap.xml b/sitemap.xml
index d8725e351..bc83ce0b2 100644
--- a/sitemap.xml
+++ b/sitemap.xml
@@ -2,110 +2,110 @@
https://axolotl-ai-cloud.github.io/axolotl/index.html
- 2024-11-08T16:30:44.918Z
+ 2024-11-08T18:46:01.147Z
https://axolotl-ai-cloud.github.io/axolotl/examples/colab-notebooks/colab-axolotl-example.html
- 2024-11-08T16:30:44.906Z
+ 2024-11-08T18:46:01.135Z
https://axolotl-ai-cloud.github.io/axolotl/docs/amd_hpc.html
- 2024-11-08T16:30:44.906Z
+ 2024-11-08T18:46:01.131Z
https://axolotl-ai-cloud.github.io/axolotl/docs/multipack.html
- 2024-11-08T16:30:44.906Z
+ 2024-11-08T18:46:01.135Z
https://axolotl-ai-cloud.github.io/axolotl/docs/fsdp_qlora.html
- 2024-11-08T16:30:44.906Z
+ 2024-11-08T18:46:01.131Z
https://axolotl-ai-cloud.github.io/axolotl/docs/batch_vs_grad.html
- 2024-11-08T16:30:44.906Z
+ 2024-11-08T18:46:01.131Z
https://axolotl-ai-cloud.github.io/axolotl/docs/multimodal.html
- 2024-11-08T16:30:44.906Z
+ 2024-11-08T18:46:01.135Z
https://axolotl-ai-cloud.github.io/axolotl/docs/unsloth.html
- 2024-11-08T16:30:44.906Z
+ 2024-11-08T18:46:01.135Z
https://axolotl-ai-cloud.github.io/axolotl/docs/dataset-formats/index.html
- 2024-11-08T16:30:44.906Z
+ 2024-11-08T18:46:01.131Z
https://axolotl-ai-cloud.github.io/axolotl/docs/dataset-formats/pretraining.html
- 2024-11-08T16:30:44.906Z
+ 2024-11-08T18:46:01.131Z
https://axolotl-ai-cloud.github.io/axolotl/docs/dataset-formats/inst_tune.html
- 2024-11-08T16:30:44.906Z
+ 2024-11-08T18:46:01.131Z
https://axolotl-ai-cloud.github.io/axolotl/docs/debugging.html
- 2024-11-08T16:30:44.906Z
+ 2024-11-08T18:46:01.131Z
https://axolotl-ai-cloud.github.io/axolotl/docs/faq.html
- 2024-11-08T16:30:44.906Z
+ 2024-11-08T18:46:01.131Z
https://axolotl-ai-cloud.github.io/axolotl/TODO.html
- 2024-11-08T16:30:44.902Z
+ 2024-11-08T18:46:01.131Z
https://axolotl-ai-cloud.github.io/axolotl/FAQS.html
- 2024-11-08T16:30:44.902Z
+ 2024-11-08T18:46:01.131Z
https://axolotl-ai-cloud.github.io/axolotl/docs/multi-node.html
- 2024-11-08T16:30:44.906Z
+ 2024-11-08T18:46:01.135Z
https://axolotl-ai-cloud.github.io/axolotl/docs/mac.html
- 2024-11-08T16:30:44.906Z
+ 2024-11-08T18:46:01.135Z
https://axolotl-ai-cloud.github.io/axolotl/docs/dataset-formats/tokenized.html
- 2024-11-08T16:30:44.906Z
+ 2024-11-08T18:46:01.131Z
https://axolotl-ai-cloud.github.io/axolotl/docs/dataset-formats/conversation.html
- 2024-11-08T16:30:44.906Z
+ 2024-11-08T18:46:01.131Z
https://axolotl-ai-cloud.github.io/axolotl/docs/dataset-formats/template_free.html
- 2024-11-08T16:30:44.906Z
+ 2024-11-08T18:46:01.131Z
https://axolotl-ai-cloud.github.io/axolotl/docs/config.html
- 2024-11-08T16:30:44.906Z
+ 2024-11-08T18:46:01.131Z
https://axolotl-ai-cloud.github.io/axolotl/docs/rlhf.html
- 2024-11-08T16:30:44.906Z
+ 2024-11-08T18:46:01.135Z
https://axolotl-ai-cloud.github.io/axolotl/docs/torchao.html
- 2024-11-08T16:30:44.906Z
+ 2024-11-08T18:46:01.135Z
https://axolotl-ai-cloud.github.io/axolotl/docs/dataset_preprocessing.html
- 2024-11-08T16:30:44.906Z
+ 2024-11-08T18:46:01.131Z
https://axolotl-ai-cloud.github.io/axolotl/docs/input_output.html
- 2024-11-08T16:30:44.906Z
+ 2024-11-08T18:46:01.135Z
https://axolotl-ai-cloud.github.io/axolotl/docs/nccl.html
- 2024-11-08T16:30:44.906Z
+ 2024-11-08T18:46:01.135Z
https://axolotl-ai-cloud.github.io/axolotl/src/axolotl/integrations/LICENSE.html
- 2024-11-08T16:30:44.918Z
+ 2024-11-08T18:46:01.147Z