Tweaks

README.md

@@ -12,7 +12,7 @@ The Alignment Handbook aims to fill that gap by providing the community with a s
 
 ## News 🗞️
 
-* November 10, 2023: We release all the training code to replicate Zephyr 7B 🪁!
+* November 10, 2023: We release all the training code to replicate Zephyr-7b-β 🪁!
 
 ## Links 🔗
 

recipes/zephyr-7b-beta/dpo/config_lora.yaml

@@ -2,7 +2,7 @@
 model_name_or_path: alignment-handbook/zephyr-7b-sft-lora
 torch_dtype: auto
 
-# LORA
+# LoRA arguments
 use_peft: true
 lora_r: 64
 lora_alpha: 16

recipes/zephyr-7b-beta/sft/config_full.yaml

@@ -32,7 +32,7 @@ output_dir: data/zephyr-7b-sft-full
 overwrite_output_dir: true
 per_device_eval_batch_size: 16
 per_device_train_batch_size: 32
-push_to_hub: True
+push_to_hub: true
 remove_unused_columns: true
 report_to:
 - tensorboard

recipes/zephyr-7b-beta/sft/config_lora.yaml

@@ -44,7 +44,7 @@ output_dir: data/zephyr-7b-sft-lora
 overwrite_output_dir: true
 per_device_eval_batch_size: 8
 per_device_train_batch_size: 4
-push_to_hub: True
+push_to_hub: true
 report_to:
 - tensorboard
 save_strategy: "no"

scripts/README.md

@@ -32,7 +32,7 @@ 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 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).
+** 💡 Tip:** If you scale 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:
 

tests/fixtures/config_sft_full.yaml

@@ -32,7 +32,7 @@ output_dir: data/zephyr-7b-sft-full
 overwrite_output_dir: true
 per_device_eval_batch_size: 16
 per_device_train_batch_size: 32
-push_to_hub: True
+push_to_hub: true
 remove_unused_columns: true
 report_to:
 - tensorboard