Merge branch 'main' into cj_tokenizer_default_prompt_template

docs/config.qmd

@@ -90,6 +90,7 @@ datasets:
     shards: # Optional[int] number of shards to split data into
     name: # Optional[str] name of dataset configuration to load
     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
@@ -314,6 +315,7 @@ wandb_log_model: # "checkpoint" to log model to wandb Artifacts every `save_step
 # 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
@@ -362,7 +364,7 @@ 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]
+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)