fix save method of adapter_model.bin

src/llmtuner/webui/locales.py

@@ -287,16 +287,6 @@ LOCALES = {
             "info": "是否启用 FP16 或 BF16 混合精度训练。"
         }
     },
-    "padding_side": {
-        "en": {
-            "label": "Padding side",
-            "info": "The side on which the model should have padding applied."
-        },
-        "zh": {
-            "label": "填充位置",
-            "info": "使用左填充或右填充。"
-        }
-    },
     "lora_tab": {
         "en": {
             "label": "LoRA configurations"

src/llmtuner/webui/runner.py

@@ -8,11 +8,11 @@ from transformers.trainer import TRAINING_ARGS_NAME
 from typing import Any, Dict, Generator, List, Tuple
 
 from llmtuner.extras.callbacks import LogCallback
-from llmtuner.extras.constants import DEFAULT_MODULE
+from llmtuner.extras.constants import DEFAULT_MODULE, TRAINING_STAGES
 from llmtuner.extras.logging import LoggerHandler
 from llmtuner.extras.misc import torch_gc
 from llmtuner.tuner import run_exp
-from llmtuner.webui.common import get_model_path, get_save_dir
+from llmtuner.webui.common import get_model_path, get_save_dir, load_config
 from llmtuner.webui.locales import ALERTS
 from llmtuner.webui.utils import gen_cmd, get_eval_results, update_process_bar
 
@@ -87,7 +87,6 @@ class Runner:
         save_steps: int,
         warmup_steps: int,
         compute_type: str,
-        padding_side: str,
         lora_rank: int,
         lora_dropout: float,
         lora_target: str,
@@ -98,21 +97,25 @@ class Runner:
     ) -> Tuple[str, str, List[str], str, Dict[str, Any]]:
         if checkpoints:
             checkpoint_dir = ",".join(
-                [os.path.join(get_save_dir(model_name), finetuning_type, ckpt) for ckpt in checkpoints]
+                [get_save_dir(model_name, finetuning_type, ckpt) for ckpt in checkpoints]
             )
         else:
             checkpoint_dir = None
 
-        output_dir = os.path.join(get_save_dir(model_name), finetuning_type, output_dir)
+        output_dir = get_save_dir(model_name, finetuning_type, output_dir)
+
+        user_config = load_config()
+        cache_dir = user_config.get("cache_dir", None)
 
         args = dict(
-            stage="sft",
+            stage=TRAINING_STAGES[training_stage],
             model_name_or_path=get_model_path(model_name),
             do_train=True,
-            overwrite_cache=True,
+            overwrite_cache=False,
+            cache_dir=cache_dir,
             checkpoint_dir=checkpoint_dir,
             finetuning_type=finetuning_type,
-            quantization_bit=int(quantization_bit) if quantization_bit and quantization_bit != "None" else None,
+            quantization_bit=int(quantization_bit) if quantization_bit in ["8", "4"] else None,
             template=template,
             system_prompt=system_prompt,
             dataset_dir=dataset_dir,
@@ -129,30 +132,22 @@ class Runner:
             logging_steps=logging_steps,
             save_steps=save_steps,
             warmup_steps=warmup_steps,
-            padding_side=padding_side,
             lora_rank=lora_rank,
             lora_dropout=lora_dropout,
             lora_target=lora_target or DEFAULT_MODULE.get(model_name.split("-")[0], "q_proj,v_proj"),
-            resume_lora_training=resume_lora_training,
+            resume_lora_training=(
+                False if TRAINING_STAGES[training_stage] in ["rm", "ppo", "dpo"] else resume_lora_training
+            ),
             output_dir=output_dir
         )
         args[compute_type] = True
 
-        if training_stage == "Reward Modeling":
-            args["stage"] = "rm"
-            args["resume_lora_training"] = False
-        elif training_stage == "PPO":
-            args["stage"] = "ppo"
-            args["resume_lora_training"] = False
+        if args["stage"] == "ppo":
             args["reward_model"] = reward_model
-            args["padding_side"] = "left"
             val_size = 0
-        elif training_stage == "DPO":
-            args["stage"] = "dpo"
-            args["resume_lora_training"] = False
+
+        if args["stage"] == "dpo":
             args["dpo_beta"] = dpo_beta
-        elif training_stage == "Pre-Training":
-            args["stage"] = "pt"
 
         if val_size > 1e-6:
             args["val_size"] = val_size
@@ -181,22 +176,26 @@ class Runner:
     ) -> Tuple[str, str, List[str], str, Dict[str, Any]]:
         if checkpoints:
             checkpoint_dir = ",".join(
-                [os.path.join(get_save_dir(model_name), finetuning_type, checkpoint) for checkpoint in checkpoints]
+                [get_save_dir(model_name, finetuning_type, ckpt) for ckpt in checkpoints]
             )
-            output_dir = os.path.join(get_save_dir(model_name), finetuning_type, "eval_" + "_".join(checkpoints))
+            output_dir = get_save_dir(model_name, finetuning_type, "eval_" + "_".join(checkpoints))
         else:
             checkpoint_dir = None
-            output_dir = os.path.join(get_save_dir(model_name), finetuning_type, "eval_base")
+            output_dir = get_save_dir(model_name, finetuning_type, "eval_base")
+
+        user_config = load_config()
+        cache_dir = user_config.get("cache_dir", None)
 
         args = dict(
             stage="sft",
             model_name_or_path=get_model_path(model_name),
             do_eval=True,
-            overwrite_cache=True,
+            overwrite_cache=False,
             predict_with_generate=True,
+            cache_dir=cache_dir,
             checkpoint_dir=checkpoint_dir,
             finetuning_type=finetuning_type,
-            quantization_bit=int(quantization_bit) if quantization_bit and quantization_bit != "None" else None,
+            quantization_bit=int(quantization_bit) if quantization_bit in ["8", "4"] else None,
             template=template,
             system_prompt=system_prompt,
             dataset_dir=dataset_dir,

src/llmtuner/webui/utils.py

@@ -3,10 +3,9 @@ import json
 import gradio as gr
 import matplotlib.figure
 import matplotlib.pyplot as plt
-from typing import TYPE_CHECKING, Any, Dict, Generator, List, Tuple
+from typing import TYPE_CHECKING, Any, Dict, Generator, List, Optional, Tuple
 from datetime import datetime
 
-from llmtuner.dsets.utils import EXT2TYPE
 from llmtuner.extras.ploting import smooth
 from llmtuner.tuner import export_model
 from llmtuner.webui.common import get_model_path, get_save_dir, DATA_CONFIG
@@ -37,6 +36,7 @@ def get_time() -> str:
 def can_preview(dataset_dir: str, dataset: list) -> Dict[str, Any]:
     with open(os.path.join(dataset_dir, DATA_CONFIG), "r", encoding="utf-8") as f:
         dataset_info = json.load(f)
+
     if (
         len(dataset) > 0
         and "file_name" in dataset_info[dataset[0]]
@@ -47,25 +47,26 @@ def can_preview(dataset_dir: str, dataset: list) -> Dict[str, Any]:
         return gr.update(interactive=False)
 
 
-def get_preview(dataset_dir: str, dataset: list) -> Tuple[int, list, Dict[str, Any]]:
+def get_preview(
+    dataset_dir: str, dataset: list, start: Optional[int] = 0, end: Optional[int] = 2
+) -> Tuple[int, list, Dict[str, Any]]:
     with open(os.path.join(dataset_dir, DATA_CONFIG), "r", encoding="utf-8") as f:
         dataset_info = json.load(f)
-    data_file = dataset_info[dataset[0]]["file_name"]
-    data = []
-    data_format = EXT2TYPE.get(data_file.split(".")[-1], None)
-    if data_format == "text":
-        with open(os.path.join(dataset_dir, data_file), "r", encoding="utf-8") as f:
-            for line in f:
-                data.append(line.strip())
-    elif data_format == "json":
-        with open(os.path.join(dataset_dir, data_file), "r", encoding="utf-8") as f:
+
+    data_file: str = dataset_info[dataset[0]]["file_name"]
+    with open(os.path.join(dataset_dir, data_file), "r", encoding="utf-8") as f:
+        if data_file.endswith(".json"):
             data = json.load(f)
-    return len(data), data[:2], gr.update(visible=True)
+        elif data_file.endswith(".jsonl"):
+            data = [json.loads(line) for line in f]
+        else:
+            data = [line for line in f]
+    return len(data), data[start:end], gr.update(visible=True)
 
 
 def can_quantize(finetuning_type: str) -> Dict[str, Any]:
     if finetuning_type != "lora":
-        return gr.update(value="", interactive=False)
+        return gr.update(value="None", interactive=False)
     else:
         return gr.update(interactive=True)
 
@@ -73,7 +74,7 @@ def can_quantize(finetuning_type: str) -> Dict[str, Any]:
 def gen_cmd(args: Dict[str, Any]) -> str:
     if args.get("do_train", None):
         args["plot_loss"] = True
-    cmd_lines = ["CUDA_VISIBLE_DEVICES=0 python "]
+    cmd_lines = ["CUDA_VISIBLE_DEVICES=0 python src/train_bash.py "]
     for k, v in args.items():
         if v is not None and v != "":
             cmd_lines.append("    --{} {} ".format(k, str(v)))
@@ -89,7 +90,7 @@ def get_eval_results(path: os.PathLike) -> str:
 
 
 def gen_plot(base_model: str, finetuning_type: str, output_dir: str) -> matplotlib.figure.Figure:
-    log_file = os.path.join(get_save_dir(base_model), finetuning_type, output_dir, "trainer_log.jsonl")
+    log_file = get_save_dir(base_model, finetuning_type, output_dir, "trainer_log.jsonl")
     if not os.path.isfile(log_file):
         return None
 
@@ -138,7 +139,7 @@ def save_model(
         return
 
     checkpoint_dir = ",".join(
-            [os.path.join(get_save_dir(model_name), finetuning_type, checkpoint) for checkpoint in checkpoints]
+            [get_save_dir(model_name, finetuning_type, ckpt) for ckpt in checkpoints]
         )
 
     if not save_dir: