stuff

1991.yml

@@ -0,0 +1,295 @@
+base_model: Qwen/Qwen2.5-14B-Instruct
+model_type: AutoModelForCausalLM #nohup accelerate launch -m axolotl.cli.train /home/ubuntu/qwen2.5_14B.yml > training_output.log 2>&1 &
+tokenizer_type: AutoTokenizer
+trust_remote_code: true
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+datasets:
+  - path: tatsu-lab/alpaca
+    type: alpaca
+
+chat_template: chatml
+dataset_prepared_path:
+val_set_size: 0
+output_dir: ./outputs/out
+
+sequence_len: 2048
+sample_packing: true
+eval_sample_packing: true
+pad_to_sequence_len: true
+
+unfrozen_parameters:
+- ^lm_head.weight$
+- ^model.embed_tokens.weight$
+# input_layernorm layers
+- model.layers.0.input_layernorm
+- model.layers.1.input_layernorm
+- model.layers.2.input_layernorm
+- model.layers.3.input_layernorm
+- model.layers.4.input_layernorm
+- model.layers.5.input_layernorm
+- model.layers.6.input_layernorm
+- model.layers.7.input_layernorm
+- model.layers.8.input_layernorm
+- model.layers.9.input_layernorm
+- model.layers.10.input_layernorm
+- model.layers.11.input_layernorm
+- model.layers.12.input_layernorm
+- model.layers.13.input_layernorm
+- model.layers.14.input_layernorm
+- model.layers.15.input_layernorm
+- model.layers.16.input_layernorm
+- model.layers.17.input_layernorm
+- model.layers.18.input_layernorm
+- model.layers.19.input_layernorm
+- model.layers.20.input_layernorm
+- model.layers.21.input_layernorm
+- model.layers.22.input_layernorm
+- model.layers.23.input_layernorm
+# lm_head layers
+# mlp.down_proj layers
+- model.layers.1.mlp.down_proj
+- model.layers.35.mlp.down_proj
+- model.layers.38.mlp.down_proj
+- model.layers.37.mlp.down_proj
+- model.layers.36.mlp.down_proj
+- model.layers.15.mlp.down_proj
+- model.layers.11.mlp.down_proj
+- model.layers.12.mlp.down_proj
+- model.layers.34.mlp.down_proj
+- model.layers.44.mlp.down_proj
+- model.layers.45.mlp.down_proj
+- model.layers.9.mlp.down_proj
+- model.layers.41.mlp.down_proj
+- model.layers.33.mlp.down_proj
+- model.layers.43.mlp.down_proj
+- model.layers.40.mlp.down_proj
+- model.layers.13.mlp.down_proj
+- model.layers.8.mlp.down_proj
+- model.layers.39.mlp.down_proj
+- model.layers.10.mlp.down_proj
+- model.layers.14.mlp.down_proj
+- model.layers.16.mlp.down_proj
+- model.layers.31.mlp.down_proj
+- model.layers.32.mlp.down_proj
+# mlp.gate_proj layers
+- model.layers.1.mlp.gate_proj
+- model.layers.44.mlp.gate_proj
+- model.layers.46.mlp.gate_proj
+- model.layers.45.mlp.gate_proj
+- model.layers.43.mlp.gate_proj
+- model.layers.47.mlp.gate_proj
+- model.layers.42.mlp.gate_proj
+- model.layers.32.mlp.gate_proj
+- model.layers.27.mlp.gate_proj
+- model.layers.33.mlp.gate_proj
+- model.layers.28.mlp.gate_proj
+- model.layers.39.mlp.gate_proj
+- model.layers.41.mlp.gate_proj
+- model.layers.40.mlp.gate_proj
+- model.layers.30.mlp.gate_proj
+- model.layers.29.mlp.gate_proj
+- model.layers.31.mlp.gate_proj
+- model.layers.26.mlp.gate_proj
+- model.layers.37.mlp.gate_proj
+- model.layers.10.mlp.gate_proj
+- model.layers.38.mlp.gate_proj
+- model.layers.12.mlp.gate_proj
+- model.layers.36.mlp.gate_proj
+- model.layers.13.mlp.gate_proj
+# mlp.up_proj layers
+- model.layers.1.mlp.up_proj
+- model.layers.13.mlp.up_proj
+- model.layers.11.mlp.up_proj
+- model.layers.14.mlp.up_proj
+- model.layers.15.mlp.up_proj
+- model.layers.12.mlp.up_proj
+- model.layers.8.mlp.up_proj
+- model.layers.16.mlp.up_proj
+- model.layers.9.mlp.up_proj
+- model.layers.19.mlp.up_proj
+- model.layers.10.mlp.up_proj
+- model.layers.7.mlp.up_proj
+- model.layers.17.mlp.up_proj
+- model.layers.20.mlp.up_proj
+- model.layers.21.mlp.up_proj
+- model.layers.18.mlp.up_proj
+- model.layers.38.mlp.up_proj
+- model.layers.37.mlp.up_proj
+- model.layers.39.mlp.up_proj
+- model.layers.42.mlp.up_proj
+- model.layers.41.mlp.up_proj
+- model.layers.27.mlp.up_proj
+- model.layers.28.mlp.up_proj
+- model.layers.34.mlp.up_proj
+# model.norm layers
+# post_attention_layernorm layers
+- model.layers.0.post_attention_layernorm
+- model.layers.1.post_attention_layernorm
+- model.layers.2.post_attention_layernorm
+- model.layers.3.post_attention_layernorm
+- model.layers.4.post_attention_layernorm
+- model.layers.5.post_attention_layernorm
+- model.layers.6.post_attention_layernorm
+- model.layers.7.post_attention_layernorm
+- model.layers.8.post_attention_layernorm
+- model.layers.9.post_attention_layernorm
+- model.layers.10.post_attention_layernorm
+- model.layers.11.post_attention_layernorm
+- model.layers.12.post_attention_layernorm
+- model.layers.13.post_attention_layernorm
+- model.layers.14.post_attention_layernorm
+- model.layers.15.post_attention_layernorm
+- model.layers.16.post_attention_layernorm
+- model.layers.17.post_attention_layernorm
+- model.layers.18.post_attention_layernorm
+- model.layers.19.post_attention_layernorm
+- model.layers.20.post_attention_layernorm
+- model.layers.21.post_attention_layernorm
+- model.layers.22.post_attention_layernorm
+- model.layers.23.post_attention_layernorm
+# self_attn.k_proj layers
+- model.layers.47.self_attn.k_proj
+- model.layers.39.self_attn.k_proj
+- model.layers.41.self_attn.k_proj
+- model.layers.37.self_attn.k_proj
+- model.layers.35.self_attn.k_proj
+- model.layers.44.self_attn.k_proj
+- model.layers.38.self_attn.k_proj
+- model.layers.14.self_attn.k_proj
+- model.layers.7.self_attn.k_proj
+- model.layers.12.self_attn.k_proj
+- model.layers.11.self_attn.k_proj
+- model.layers.32.self_attn.k_proj
+- model.layers.10.self_attn.k_proj
+- model.layers.8.self_attn.k_proj
+- model.layers.9.self_attn.k_proj
+- model.layers.6.self_attn.k_proj
+- model.layers.45.self_attn.k_proj
+- model.layers.42.self_attn.k_proj
+- model.layers.5.self_attn.k_proj
+- model.layers.40.self_attn.k_proj
+- model.layers.33.self_attn.k_proj
+- model.layers.0.self_attn.k_proj
+- model.layers.34.self_attn.k_proj
+- model.layers.13.self_attn.k_proj
+# self_attn.o_proj layers
+- model.layers.12.self_attn.o_proj
+- model.layers.5.self_attn.o_proj
+- model.layers.14.self_attn.o_proj
+- model.layers.16.self_attn.o_proj
+- model.layers.20.self_attn.o_proj
+- model.layers.13.self_attn.o_proj
+- model.layers.11.self_attn.o_proj
+- model.layers.4.self_attn.o_proj
+- model.layers.6.self_attn.o_proj
+- model.layers.19.self_attn.o_proj
+- model.layers.7.self_attn.o_proj
+- model.layers.18.self_attn.o_proj
+- model.layers.8.self_attn.o_proj
+- model.layers.38.self_attn.o_proj
+- model.layers.15.self_attn.o_proj
+- model.layers.17.self_attn.o_proj
+- model.layers.9.self_attn.o_proj
+- model.layers.10.self_attn.o_proj
+- model.layers.21.self_attn.o_proj
+- model.layers.28.self_attn.o_proj
+- model.layers.32.self_attn.o_proj
+- model.layers.35.self_attn.o_proj
+- model.layers.39.self_attn.o_proj
+- model.layers.3.self_attn.o_proj
+# self_attn.q_proj layers
+- model.layers.1.self_attn.q_proj
+- model.layers.2.self_attn.q_proj
+- model.layers.3.self_attn.q_proj
+- model.layers.44.self_attn.q_proj
+- model.layers.29.self_attn.q_proj
+- model.layers.45.self_attn.q_proj
+- model.layers.43.self_attn.q_proj
+- model.layers.32.self_attn.q_proj
+- model.layers.38.self_attn.q_proj
+- model.layers.19.self_attn.q_proj
+- model.layers.42.self_attn.q_proj
+- model.layers.34.self_attn.q_proj
+- model.layers.36.self_attn.q_proj
+- model.layers.40.self_attn.q_proj
+- model.layers.26.self_attn.q_proj
+- model.layers.20.self_attn.q_proj
+- model.layers.39.self_attn.q_proj
+- model.layers.28.self_attn.q_proj
+- model.layers.35.self_attn.q_proj
+- model.layers.41.self_attn.q_proj
+- model.layers.33.self_attn.q_proj
+- model.layers.25.self_attn.q_proj
+- model.layers.30.self_attn.q_proj
+- model.layers.27.self_attn.q_proj
+# self_attn.v_proj layers
+- model.layers.0.self_attn.v_proj
+- model.layers.7.self_attn.v_proj
+- model.layers.39.self_attn.v_proj
+- model.layers.31.self_attn.v_proj
+- model.layers.15.self_attn.v_proj
+- model.layers.10.self_attn.v_proj
+- model.layers.32.self_attn.v_proj
+- model.layers.41.self_attn.v_proj
+- model.layers.6.self_attn.v_proj
+- model.layers.33.self_attn.v_proj
+- model.layers.42.self_attn.v_proj
+- model.layers.29.self_attn.v_proj
+- model.layers.14.self_attn.v_proj
+- model.layers.9.self_attn.v_proj
+- model.layers.35.self_attn.v_proj
+- model.layers.38.self_attn.v_proj
+- model.layers.13.self_attn.v_proj
+- model.layers.30.self_attn.v_proj
+- model.layers.5.self_attn.v_proj
+- model.layers.34.self_attn.v_proj
+- model.layers.28.self_attn.v_proj
+- model.layers.37.self_attn.v_proj
+- model.layers.27.self_attn.v_proj
+- model.layers.11.self_attn.v_proj
+# model.embed_tokens layers
+
+
+gradient_accumulation_steps: 2
+micro_batch_size: 2
+num_epochs: 3
+optimizer: adamw_torch_fused
+lr_scheduler: linear
+learning_rate: 5e-6
+
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16:
+tf32: false
+
+plugins:
+  - axolotl.integrations.liger.LigerPlugin
+liger_rope: true
+liger_rms_norm: true
+liger_swiglu: true
+liger_fused_linear_cross_entropy: true
+
+gradient_checkpointing: unsloth
+gradient_checkpointing_kwargs:
+  use_reentrant: false
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+warmup_steps: 10
+evals_per_epoch: 2
+saves_per_epoch: 1
+save_total_limit: 4
+debug:
+deepspeed: deepspeed_configs/zero3_bf16.json
+weight_decay: 0.05
+special_tokens:
+  eos_token: <|im_end|>

src/axolotl/core/trainer_builder.py

@@ -895,13 +895,13 @@ class AxolotlTrainer(SchedulerMixin, Trainer):
         for key, value in metrics.items():
             self._stored_metrics[train_eval][key].append(value)
 
-    def _save_checkpoint(self, model, trial, metrics=None):
+    def _save_checkpoint(self, model, trial):
         # make sure the checkpoint dir exists, since trainer is flakey
         checkpoint_folder = f"{PREFIX_CHECKPOINT_DIR}-{self.state.global_step}"
         run_dir = self._get_output_dir(trial=trial)
         output_dir = os.path.join(run_dir, checkpoint_folder)
         os.makedirs(output_dir, exist_ok=True)
-        return super()._save_checkpoint(model, trial, metrics=metrics)
+        return super()._save_checkpoint(model, trial)
 
 
 class AxolotlMambaTrainer(AxolotlTrainer):

src/axolotl/monkeypatch/multipack.py

@@ -27,15 +27,18 @@ SUPPORTED_MULTIPACK_MODEL_TYPES = [
 ]
 
 
-def patch_for_multipack(model_type, model_name=None, is_remote_code=False):
+# def patch_for_multipack(model_type, model_name=None, is_remote_code=False):
+def patch_for_multipack(model_type, model_name=None, has_remote_code=False):
     if model_type == "gemmoe":
         patch_remote(model_name, ".configuration_gemmoe", ".modeling_gemmoe")
     elif model_type == "deepseek_v2":
         patch_remote(model_name, ".configuration_deepseek", ".modeling_deepseek")
-    elif hasattr(transformers, "modeling_flash_attention_utils") and not is_remote_code:
-        transformers.modeling_flash_attention_utils._get_unpad_data = (  # pylint: disable=protected-access
-            get_unpad_data
-        )
+    # elif hasattr(transformers, "modeling_flash_attention_utils") and not is_remote_code:
+    elif hasattr(transformers, "modeling_flash_attention_utils"):
+        if not has_remote_code:
+            transformers.modeling_flash_attention_utils._get_unpad_data = (  # pylint: disable=protected-access
+                get_unpad_data
+            )
         if model_type == "mixtral" and is_deepspeed_zero3_enabled():
             patch_mixtral_moe_forward_zero3()
         return

src/axolotl/utils/models.py

@@ -394,10 +394,15 @@ class ModelLoader:
             and self.cfg.flash_attention
             and self.cfg.sample_packing
         ):
+            has_remote_code = (
+                "auto_map" in self.model_config
+                and self.model_type in self.model_config["auto_map"]
+            )
+
             patch_for_multipack(
                 self.cfg.model_config_type,
                 model_name=self.cfg.base_model,
-                is_remote_code=self.cfg.trust_remote_code,
+                has_remote_code=has_remote_code,
             )
 
             if self.cfg.is_llama_derived_model: