Rename recipe

2026-08-16 10:22:56 +08:00 · 2023-11-10 10:49:13 +00:00
parent 64f1834e01
commit a0b8d49424
6 changed files with 15 additions and 16 deletions
@@ -12,18 +12,18 @@ See below for commands to train these models using either DeepSpeed ZeRO-3 or Lo

 ```shell
 # Step 1 - SFT
-ACCELERATE_LOG_LEVEL=info accelerate launch --config_file recipes/accelerate_configs/deepspeed_zero3.yaml scripts/run_sft.py recipes/zephyr-7b/sft/config_full.yaml
+ACCELERATE_LOG_LEVEL=info accelerate launch --config_file recipes/accelerate_configs/deepspeed_zero3.yaml scripts/run_sft.py recipes/zephyr-7b-beta/sft/config_full.yaml

 # Step 2 - DPO
-ACCELERATE_LOG_LEVEL=info accelerate launch --config_file recipes/accelerate_configs/deepspeed_zero3.yaml scripts/run_dpo.py recipes/zephyr-7b/dpo/config_full.yaml
+ACCELERATE_LOG_LEVEL=info accelerate launch --config_file recipes/accelerate_configs/deepspeed_zero3.yaml scripts/run_dpo.py recipes/zephyr-7b-beta/beta/beta/beta/dpo/config_full.yaml
 ```

 ## LoRA training examples

 ```shell
 # Step 1 - SFT
-ACCELERATE_LOG_LEVEL=info accelerate launch --config_file recipes/accelerate_configs/multi_gpu.yaml --num_processes=1 scripts/run_sft.py recipes/zephyr-7b/sft/config_lora.yaml
+ACCELERATE_LOG_LEVEL=info accelerate launch --config_file recipes/accelerate_configs/multi_gpu.yaml --num_processes=1 scripts/run_sft.py recipes/zephyr-7b-beta/beta/sft/config_lora.yaml

 # Step 2 - DPO
-ACCELERATE_LOG_LEVEL=info accelerate launch --config_file recipes/accelerate_configs/multi_gpu.yaml --num_processes=1 scripts/run_dpo.py recipes/zephyr-7b/dpo/config_lora.yaml
+ACCELERATE_LOG_LEVEL=info accelerate launch --config_file recipes/accelerate_configs/multi_gpu.yaml --num_processes=1 scripts/run_dpo.py recipes/zephyr-7b-beta/dpo/config_lora.yaml
 ```
@@ -26,7 +26,6 @@ preprocessing_num_workers: 12
 bf16: true
 beta: 0.1
 do_eval: true
-ddp_find_unused_parameters: true
 evaluation_strategy: epoch
 eval_steps: 100
 gradient_accumulation_steps: 32
@@ -3,7 +3,7 @@ model_name_or_path: mistralai/Mistral-7B-v0.1
 torch_dtype: auto
 use_flash_attention_2: true

-# LORA
+# LoRA arguments
 use_peft: true
 lora_r: 64
 lora_alpha: 16
@@ -27,7 +27,6 @@ bf16: true
 do_eval: true
 evaluation_strategy: epoch
 gradient_accumulation_steps: 128
-ddp_find_unused_parameters: true
 gradient_checkpointing: true
 gradient_checkpointing_kwargs:
  use_reentrant: False
@@ -50,5 +49,4 @@ report_to:
 - tensorboard
 save_strategy: "no"
 save_total_limit: null
-seed: 42
-tf32: true
+seed: 42
@@ -6,7 +6,7 @@
 In the handbook, we provide three main ways to align LLMs for chat:

 - Full fine-tuning on a multi-GPU machine with DeepSpeed ZeRO-3 (tested on an 8 x A100 (80GB) node).
- LoRA fine-tuning on a single consumer 24GB GPU (tested on a RTX 4090).
+- LoRA or QLoRA fine-tuning on a single consumer 24GB GPU (tested on a RTX 4090).
 - LoRA fine-tuning on a multi-GPU machine with DeepSpeed ZeRO-3 (tested on a 2 x A100s (80GB)).

 In practice, we find comparable performance for both full and LoRA fine-tuning, with the latter having the advantage of producing small adapter weights that are fast to upload and download from the Hugging Face Hub. Here's the two general commands to fine-tune your models:
@@ -22,16 +22,18 @@ ACCELERATE_LOG_LEVEL=info accelerate launch --config_file recipes/accelerate_con
 ACCELERATE_LOG_LEVEL=info accelerate launch --config_file recipes/accelerate_configs/deepspeed_zero3.yaml --num_processes={num_gpus} scripts/run_{task}.py recipes/{model_name}/{task}/config_lora.yaml
 ```

-Here `{task}` refers to type of training you wish to run (SFT, DPO, etc), while `{model_name}` refers to the choice of recipe in the `recipes/` directory. For example, to replicate Zephyr 7B you can run:
+Here `{task}` refers to type of training you wish to run (SFT, DPO, etc), while `{model_name}` refers to the choice of recipe in the `recipes` directory. For example, to replicate Zephyr-7B-β you can run:

 ```shell
 # Step 1 - train SFT policy
-ACCELERATE_LOG_LEVEL=info accelerate launch --config_file recipes/accelerate_configs/deepspeed_zero3.yaml scripts/run_sft.py recipes/zephyr-7b/sft/config_full.yaml
+ACCELERATE_LOG_LEVEL=info accelerate launch --config_file recipes/accelerate_configs/deepspeed_zero3.yaml scripts/run_sft.py recipes/zephyr-7b-beta/sft/config_full.yaml

 # Step 2 - align with DPO
-ACCELERATE_LOG_LEVEL=info accelerate launch --config_file recipes/accelerate_configs/deepspeed_zero3.yaml scripts/run_dpo.py recipes/zephyr-7b/dpo/config_full.yaml
+ACCELERATE_LOG_LEVEL=info accelerate launch --config_file recipes/accelerate_configs/deepspeed_zero3.yaml scripts/run_dpo.py recipes/zephyr-7b-beta/dpo/config_full.yaml
 ```

+** 💡 Tip:** If you scale the up/down the number of GPUs, we recommend also scaling up the per-device batch size or number of gradient accumulation steps to keep the global batch size constant (and thus replicate our results).
+
 By default, these scripts will push each model to your Hugging Face Hub username, i.e. `{username}/{model_name}-{task}`. You can override the parameters in each YAML config by appending them to the command as follows:

 ```shell
@@ -56,9 +58,9 @@ sbatch --job-name=handbook_{task} --nodes=1 recipes/launch.slurm {model_name} {t
 Here `{model_name}` and `{task}` are defined as above, while `{precision}` refers to the type of training (full vs LoRA) and `{accelerator}` refers to the choice of 🤗 Accelerate config in `recipes/accelerate_configs`. Here's a concrete example to run SFT on 1 node of 8 GPUs:

 ```shell
-sbatch --job-name=handbook_sft --nodes=1 recipes/launch.slurm zephyr-7b sft full deepspeed_zero3
+sbatch --job-name=handbook_sft --nodes=1 recipes/launch.slurm zephyr-7b-beta sft full deepspeed_zero3
 ```

-You can scale the number of nodes by increasing the `--nodes` flag; in these cases we recommend also scaling up the per-device batch size or number of gradient accumulation steps to keep the global batch size constant (and thus replicate our results).
+You can scale the number of nodes by increasing the `--nodes` flag.

-**Note:** the configuration in `recipes/launch.slurm` is optimised for the Hugging Face Compute Cluster and may require tweaking to be adapted to your own compute nodes.
+**⚠️ Note:** the configuration in `recipes/launch.slurm` is optimised for the Hugging Face Compute Cluster and may require tweaking to be adapted to your own compute nodes.