axolotl-ai-cloud · NanoCode012 · Dec 4, 2023 · Oct 22, 2023 · Oct 22, 2023 · Oct 22, 2023
diff --git a/README.md b/README.md
@@ -659,7 +659,7 @@ wandb_mode: # "offline" to save run metadata locally and not sync to the server,
 wandb_project: # Your wandb project name
 wandb_entity: # A wandb Team name if using a Team
 wandb_watch:
-wandb_run_id: # Set the name of your wandb run
+wandb_name: # Set the name 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
 
 # Where to save the full-finetuned model to
@@ -952,7 +952,7 @@ wandb_mode:
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_run_id:
+wandb_name:
 wandb_log_model:
 ```
 

diff --git a/examples/cerebras/btlm-ft.yml b/examples/cerebras/btlm-ft.yml
@@ -35,7 +35,7 @@ lora_fan_in_fan_out:
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_run_id:
+wandb_name:
 wandb_log_model:
 
 output_dir: btlm-out

diff --git a/examples/cerebras/qlora.yml b/examples/cerebras/qlora.yml
@@ -24,7 +24,7 @@ lora_fan_in_fan_out:
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_run_id:
+wandb_name:
 wandb_log_model:
 output_dir: ./qlora-out
 batch_size: 4

diff --git a/examples/code-llama/13b/lora.yml b/examples/code-llama/13b/lora.yml
@@ -29,7 +29,7 @@ lora_fan_in_fan_out:
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_run_id:
+wandb_name:
 wandb_log_model:
 
 gradient_accumulation_steps: 4

diff --git a/examples/code-llama/13b/qlora.yml b/examples/code-llama/13b/qlora.yml
@@ -31,7 +31,7 @@ lora_fan_in_fan_out:
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_run_id:
+wandb_name:
 wandb_log_model:
 
 gradient_accumulation_steps: 4

diff --git a/examples/code-llama/34b/lora.yml b/examples/code-llama/34b/lora.yml
@@ -29,7 +29,7 @@ lora_fan_in_fan_out:
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_run_id:
+wandb_name:
 wandb_log_model:
 
 gradient_accumulation_steps: 4

diff --git a/examples/code-llama/34b/qlora.yml b/examples/code-llama/34b/qlora.yml
@@ -31,7 +31,7 @@ lora_fan_in_fan_out:
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_run_id:
+wandb_name:
 wandb_log_model:
 
 gradient_accumulation_steps: 4

diff --git a/examples/code-llama/7b/lora.yml b/examples/code-llama/7b/lora.yml
@@ -29,7 +29,7 @@ lora_fan_in_fan_out:
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_run_id:
+wandb_name:
 wandb_log_model:
 
 gradient_accumulation_steps: 4

diff --git a/examples/code-llama/7b/qlora.yml b/examples/code-llama/7b/qlora.yml
@@ -31,7 +31,7 @@ lora_fan_in_fan_out:
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_run_id:
+wandb_name:
 wandb_log_model:
 
 gradient_accumulation_steps: 4

diff --git a/examples/falcon/config-7b-lora.yml b/examples/falcon/config-7b-lora.yml
@@ -26,7 +26,7 @@ lora_fan_in_fan_out:
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_run_id:
+wandb_name:
 wandb_log_model:
 output_dir: ./falcon-7b
 batch_size: 2

diff --git a/examples/falcon/config-7b-qlora.yml b/examples/falcon/config-7b-qlora.yml
@@ -40,7 +40,7 @@ lora_fan_in_fan_out:
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_run_id:
+wandb_name:
 wandb_log_model:
 output_dir: ./qlora-out
 

diff --git a/examples/falcon/config-7b.yml b/examples/falcon/config-7b.yml
@@ -26,7 +26,7 @@ lora_fan_in_fan_out:
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_run_id:
+wandb_name:
 wandb_log_model:
 output_dir: ./falcon-7b
 batch_size: 2

diff --git a/examples/gptj/qlora.yml b/examples/gptj/qlora.yml
@@ -21,7 +21,7 @@ lora_fan_in_fan_out:
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_run_id:
+wandb_name:
 wandb_log_model:
 output_dir: ./qlora-out
 gradient_accumulation_steps: 2

diff --git a/examples/jeopardy-bot/config.yml b/examples/jeopardy-bot/config.yml
@@ -19,7 +19,7 @@ lora_fan_in_fan_out: false
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_run_id:
+wandb_name:
 wandb_log_model:
 output_dir: ./jeopardy-bot-7b
 gradient_accumulation_steps: 1

diff --git a/examples/llama-2/fft_optimized.yml b/examples/llama-2/fft_optimized.yml
@@ -29,7 +29,7 @@ lora_fan_in_fan_out:
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_run_id:
+wandb_name:
 wandb_log_model:
 
 gradient_accumulation_steps: 1

diff --git a/examples/llama-2/gptq-lora.yml b/examples/llama-2/gptq-lora.yml
@@ -32,7 +32,7 @@ lora_target_linear:
 lora_fan_in_fan_out:
 wandb_project:
 wandb_watch:
-wandb_run_id:
+wandb_name:
 wandb_log_model:
 output_dir: ./model-out
 gradient_accumulation_steps: 1

diff --git a/examples/llama-2/lora.yml b/examples/llama-2/lora.yml
@@ -29,7 +29,7 @@ lora_fan_in_fan_out:
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_run_id:
+wandb_name:
 wandb_log_model:
 
 gradient_accumulation_steps: 4

diff --git a/examples/llama-2/qlora.yml b/examples/llama-2/qlora.yml
@@ -31,7 +31,7 @@ lora_fan_in_fan_out:
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_run_id:
+wandb_name:
 wandb_log_model:
 
 gradient_accumulation_steps: 4

diff --git a/examples/llama-2/relora.yml b/examples/llama-2/relora.yml
@@ -35,7 +35,7 @@ relora_cpu_offload: false
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_run_id:
+wandb_name:
 wandb_log_model:
 
 gradient_accumulation_steps: 4

diff --git a/examples/llama-2/tiny-llama.yml b/examples/llama-2/tiny-llama.yml
@@ -29,7 +29,7 @@ lora_fan_in_fan_out:
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_run_id:
+wandb_name:
 wandb_log_model:
 
 gradient_accumulation_steps: 4

diff --git a/examples/mistral/config.yml b/examples/mistral/config.yml
@@ -21,7 +21,7 @@ pad_to_sequence_len: true
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_run_id:
+wandb_name:
 wandb_log_model:
 
 gradient_accumulation_steps: 4

diff --git a/examples/mistral/qlora.yml b/examples/mistral/qlora.yml
@@ -38,7 +38,7 @@ lora_target_modules:
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_run_id:
+wandb_name:
 wandb_log_model:
 
 gradient_accumulation_steps: 4

diff --git a/examples/mpt-7b/config.yml b/examples/mpt-7b/config.yml
@@ -21,7 +21,7 @@ lora_fan_in_fan_out: false
 wandb_project: mpt-alpaca-7b
 wandb_entity:
 wandb_watch:
-wandb_run_id:
+wandb_name:
 wandb_log_model:
 output_dir: ./mpt-alpaca-7b
 gradient_accumulation_steps: 1

diff --git a/examples/openllama-3b/config.yml b/examples/openllama-3b/config.yml
@@ -23,7 +23,7 @@ lora_fan_in_fan_out:
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_run_id:
+wandb_name:
 wandb_log_model:
 output_dir: ./openllama-out
 gradient_accumulation_steps: 1

diff --git a/examples/openllama-3b/lora.yml b/examples/openllama-3b/lora.yml
@@ -29,7 +29,7 @@ lora_fan_in_fan_out:
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_run_id:
+wandb_name:
 wandb_log_model:
 output_dir: ./lora-out
 gradient_accumulation_steps: 1

diff --git a/examples/openllama-3b/qlora.yml b/examples/openllama-3b/qlora.yml
@@ -23,7 +23,7 @@ lora_fan_in_fan_out:
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_run_id:
+wandb_name:
 wandb_log_model:
 output_dir: ./qlora-out
 gradient_accumulation_steps: 1

diff --git a/examples/phi/phi-ft.yml b/examples/phi/phi-ft.yml
@@ -31,7 +31,7 @@ lora_fan_in_fan_out:
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_run_id:
+wandb_name:
 wandb_log_model:
 
 gradient_accumulation_steps: 1

diff --git a/examples/phi/phi-qlora.yml b/examples/phi/phi-qlora.yml
@@ -31,7 +31,7 @@ lora_fan_in_fan_out:
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_run_id:
+wandb_name:
 wandb_log_model:
 
 gradient_accumulation_steps: 1

diff --git a/examples/pythia-12b/config.yml b/examples/pythia-12b/config.yml
@@ -24,7 +24,7 @@ lora_fan_in_fan_out: true  # pythia/GPTNeoX lora specific
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_run_id:
+wandb_name:
 wandb_log_model:
 output_dir: ./pythia-12b
 gradient_accumulation_steps: 1

diff --git a/examples/pythia/lora.yml b/examples/pythia/lora.yml
@@ -18,7 +18,7 @@ lora_fan_in_fan_out: true  # pythia/GPTNeoX lora specific
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_run_id:
+wandb_name:
 wandb_log_model:
 output_dir: ./lora-alpaca-pythia
 gradient_accumulation_steps: 1

diff --git a/examples/qwen/lora.yml b/examples/qwen/lora.yml
@@ -31,7 +31,7 @@ lora_fan_in_fan_out:
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_run_id:
+wandb_name:
 wandb_log_model:
 
 gradient_accumulation_steps: 4

diff --git a/examples/qwen/qlora.yml b/examples/qwen/qlora.yml
@@ -31,7 +31,7 @@ lora_fan_in_fan_out:
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_run_id:
+wandb_name:
 wandb_log_model:
 
 gradient_accumulation_steps: 4

diff --git a/examples/redpajama/config-3b.yml b/examples/redpajama/config-3b.yml
@@ -22,7 +22,7 @@ lora_fan_in_fan_out: false
 wandb_project: redpajama-alpaca-3b
 wandb_entity:
 wandb_watch:
-wandb_run_id:
+wandb_name:
 wandb_log_model:
 output_dir: ./redpajama-alpaca-3b
 batch_size: 4

diff --git a/examples/replit-3b/config-lora.yml b/examples/replit-3b/config-lora.yml
@@ -21,7 +21,7 @@ lora_fan_in_fan_out:
 wandb_project: lora-replit
 wandb_entity:
 wandb_watch:
-wandb_run_id:
+wandb_name:
 wandb_log_model:
 output_dir: ./lora-replit
 batch_size: 8

diff --git a/examples/xgen-7b/xgen-7b-8k-qlora.yml b/examples/xgen-7b/xgen-7b-8k-qlora.yml
@@ -38,7 +38,7 @@ lora_fan_in_fan_out:
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_run_id:
+wandb_name:
 wandb_log_model:
 output_dir: ./qlora-out
 

diff --git a/src/axolotl/core/trainer_builder.py b/src/axolotl/core/trainer_builder.py
@@ -643,7 +643,7 @@ def build(self, total_num_steps):
         training_arguments_kwargs["group_by_length"] = self.cfg.group_by_length
         training_arguments_kwargs["report_to"] = "wandb" if self.cfg.use_wandb else None
         training_arguments_kwargs["run_name"] = (
-            self.cfg.wandb_run_id if self.cfg.use_wandb else None
+            self.cfg.wandb_name if self.cfg.use_wandb else None
         )
         training_arguments_kwargs["optim"] = (
             self.cfg.optimizer if self.cfg.optimizer else "adamw_hf"

diff --git a/src/axolotl/utils/config.py b/src/axolotl/utils/config.py
@@ -397,6 +397,13 @@ def validate_config(cfg):
             "Gradient checkpointing is broken for Qwen models for transformers>=4.35.0, except main branch."
         )
 
+    if cfg.wandb_run_id and not cfg.wandb_name:
+        cfg.wandb_name = cfg.wandb_run_id
+
+        LOG.warning(
+            "wandb_run_id sets the ID of the run. If you would like to set the name, please use wandb_name instead."
+        )
+
     # TODO
     # MPT 7b
     # https://github.com/facebookresearch/bitsandbytes/issues/25

diff --git a/src/axolotl/utils/wandb_.py b/src/axolotl/utils/wandb_.py
@@ -2,20 +2,20 @@
 
 import os
 
+from axolotl.utils.dict import DictDefault
 
-def setup_wandb_env_vars(cfg):
-    if cfg.wandb_mode and cfg.wandb_mode == "offline":
-        os.environ["WANDB_MODE"] = cfg.wandb_mode
-    elif cfg.wandb_project and len(cfg.wandb_project) > 0:
-        os.environ["WANDB_PROJECT"] = cfg.wandb_project
+
+def setup_wandb_env_vars(cfg: DictDefault):
+    for key in cfg.keys():
+        if key.startswith("wandb_"):
+            value = cfg.get(key, "")
+
+            if value and isinstance(value, str) and len(value) > 0:
+                os.environ[key.upper()] = value
+
+    # Enable wandb if project name is present
+    if cfg.wandb_project and len(cfg.wandb_project) > 0:
         cfg.use_wandb = True
-        if cfg.wandb_entity and len(cfg.wandb_entity) > 0:
-            os.environ["WANDB_ENTITY"] = cfg.wandb_entity
-        if cfg.wandb_watch and len(cfg.wandb_watch) > 0:
-            os.environ["WANDB_WATCH"] = cfg.wandb_watch
-        if cfg.wandb_log_model and len(cfg.wandb_log_model) > 0:
-            os.environ["WANDB_LOG_MODEL"] = cfg.wandb_log_model
-        if cfg.wandb_run_id and len(cfg.wandb_run_id) > 0:
-            os.environ["WANDB_RUN_ID"] = cfg.wandb_run_id
+        os.environ.pop("WANDB_DISABLED", None)  # Remove if present
     else:
         os.environ["WANDB_DISABLED"] = "true"