Upload folder using huggingface_hub

lora/sft/README.md

@@ -0,0 +1,61 @@
+---
+base_model: THUDM/glm-4-9b-chat
+library_name: peft
+license: other
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: sft
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# sft
+
+This model is a fine-tuned version of [THUDM/glm-4-9b-chat](https://huggingface.co/THUDM/glm-4-9b-chat) on the formatted dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.5199
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.43.2
+- Pytorch 2.2.2+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

lora/sft/adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "THUDM/glm-4-9b-chat",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query_key_value",
+    "dense_h_to_4h",
+    "dense",
+    "dense_4h_to_h"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

lora/sft/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:830c3647e075857538ee6e0cf9629004590472edb43fe259103d0065050b6cd6
+size 84754200

lora/sft/added_tokens.json

@@ -0,0 +1,16 @@
+{
+  "<eop>": 151334,
+  "<sop>": 151333,
+  "<|assistant|>": 151337,
+  "<|begin_of_image|>": 151339,
+  "<|begin_of_video|>": 151341,
+  "<|end_of_image|>": 151340,
+  "<|end_of_video|>": 151342,
+  "<|endoftext|>": 151329,
+  "<|observation|>": 151338,
+  "<|system|>": 151335,
+  "<|user|>": 151336,
+  "[MASK]": 151330,
+  "[gMASK]": 151331,
+  "[sMASK]": 151332
+}

lora/sft/all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 0.9955555555555555,
+    "eval_loss": 1.5198827981948853,
+    "eval_runtime": 11.7693,
+    "eval_samples_per_second": 8.497,
+    "eval_steps_per_second": 8.497,
+    "total_flos": 1.2980476361834496e+16,
+    "train_loss": 1.7745797293526786,
+    "train_runtime": 341.4533,
+    "train_samples_per_second": 2.636,
+    "train_steps_per_second": 0.328
+}

lora/sft/checkpoint-112/README.md

@@ -0,0 +1,202 @@
+---
+base_model: THUDM/glm-4-9b-chat
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

lora/sft/checkpoint-112/adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "THUDM/glm-4-9b-chat",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query_key_value",
+    "dense_h_to_4h",
+    "dense",
+    "dense_4h_to_h"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

lora/sft/checkpoint-112/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:830c3647e075857538ee6e0cf9629004590472edb43fe259103d0065050b6cd6
+size 84754200

lora/sft/checkpoint-112/added_tokens.json

@@ -0,0 +1,16 @@
+{
+  "<eop>": 151334,
+  "<sop>": 151333,
+  "<|assistant|>": 151337,
+  "<|begin_of_image|>": 151339,
+  "<|begin_of_video|>": 151341,
+  "<|end_of_image|>": 151340,
+  "<|end_of_video|>": 151342,
+  "<|endoftext|>": 151329,
+  "<|observation|>": 151338,
+  "<|system|>": 151335,
+  "<|user|>": 151336,
+  "[MASK]": 151330,
+  "[gMASK]": 151331,
+  "[sMASK]": 151332
+}

lora/sft/checkpoint-112/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8846b93dcae5983ca52f2617bf8c1037f9e36dc656c50d11bdb8a17f9886378
+size 169679354

lora/sft/checkpoint-112/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244

lora/sft/checkpoint-112/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4fc31a656c2809f413c2392223b8c06a2006c5191ca89eebdb44beedb6ae4e7
+size 1064

lora/sft/checkpoint-112/special_tokens_map.json

@@ -0,0 +1,32 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

lora/sft/checkpoint-112/tokenization_chatglm.py

@@ -0,0 +1,323 @@
+import regex as re
+import base64
+import os
+import json
+import tiktoken
+from torch import TensorType
+from typing import List, Optional, Union, Dict, Any
+from transformers import PreTrainedTokenizer
+from transformers.utils import logging, PaddingStrategy
+from transformers.tokenization_utils_base import EncodedInput, BatchEncoding
+
+
+class ChatGLM4Tokenizer(PreTrainedTokenizer):
+    vocab_files_names = {"vocab_file": "tokenizer.model"}
+    model_input_names = ["input_ids", "attention_mask", "position_ids"]
+
+    def __init__(
+            self,
+            vocab_file,
+            padding_side="left",
+            clean_up_tokenization_spaces=False,
+            encode_special_tokens=False,
+            **kwargs
+    ):
+        self.name = "GLM4Tokenizer"
+        self.vocab_file = vocab_file
+        pat_str = "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}{1,3}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+"
+        self.pat_str = re.compile(pat_str)
+        self.encode_special_tokens = encode_special_tokens
+
+        mergeable_ranks = {}
+        with open(vocab_file) as f:
+            for line in f:
+                token, rank = line.strip().split()
+                rank = int(rank)
+                token = base64.b64decode(token)
+                mergeable_ranks[token] = rank
+
+        self.mergeable_ranks = mergeable_ranks
+
+        self.tokenizer = tiktoken.Encoding(
+            name="my_tokenizer",
+            pat_str=pat_str,
+            mergeable_ranks=mergeable_ranks,
+            special_tokens={}
+        )
+        self.decoder = {rank: token for token, rank in mergeable_ranks.items()}
+        self.n_words = len(self.decoder)
+
+        super().__init__(
+            padding_side=padding_side,
+            clean_up_tokenization_spaces=clean_up_tokenization_spaces,
+            **kwargs
+        )
+
+    @property
+    def vocab_size(self):
+        return self.n_words
+
+    def get_vocab(self):
+        """ Returns vocab as a dict """
+        vocab = {self._convert_id_to_token(i): i for i in range(self.vocab_size)}
+        vocab.update(self.added_tokens_encoder)
+        return vocab
+
+    def convert_tokens_to_string(self, tokens: List[Union[bytes, str, int]]) -> str:
+        """
+        Converts a sequence of tokens in a single string.
+        """
+        text = ""
+        temp = b""
+        for t in tokens:
+            if isinstance(t, int):
+                t = chr(t)
+            if isinstance(t, str):
+                if temp:
+                    text += temp.decode("utf-8", errors="replace")
+            elif isinstance(t, bytes):
+                temp += t
+            else:
+                raise TypeError("token should only be of type int, bytes or str")
+        if temp:
+            text += temp.decode("utf-8", errors="replace")
+        return text
+
+    def _tokenize(self, text, **kwargs):
+        tokens = []
+        ids = self.tokenizer.encode(text)
+        for t in ids:
+            tokens.append(self.decoder[t])
+        return tokens
+
+    def _convert_token_to_id(self, token):
+        """ Converts a token (str) in an id using the vocab. """
+        return self.mergeable_ranks[token]
+
+    def _convert_id_to_token(self, index):
+        """Converts an index (integer) in a token (str) using the vocab."""
+        return self.decoder.get(index, "")
+
+    def save_vocabulary(self, save_directory, filename_prefix=None):
+        """
+        Save the vocabulary and special tokens file to a directory.
+
+        Args:
+            save_directory (`str`):
+                The directory in which to save the vocabulary.
+            filename_prefix (`str`, *optional*):
+                An optional prefix to add to the named of the saved files.
+
+        Returns:
+            `Tuple(str)`: Paths to the files saved.
+        """
+        if os.path.isdir(save_directory):
+            vocab_file = os.path.join(
+                save_directory, self.vocab_files_names["vocab_file"]
+            )
+        else:
+            vocab_file = save_directory
+
+        with open(self.vocab_file, 'rb') as fin:
+            proto_str = fin.read()
+
+        with open(vocab_file, "wb") as writer:
+            writer.write(proto_str)
+
+        return (vocab_file,)
+
+    def get_prefix_tokens(self):
+        prefix_tokens = [self.convert_tokens_to_ids("[gMASK]"), self.convert_tokens_to_ids("<sop>")]
+        return prefix_tokens
+
+    def build_single_message(self, role, metadata, message, tokenize=True):
+        assert role in ["system", "user", "assistant", "observation"], role
+        if tokenize:
+            role_tokens = [self.convert_tokens_to_ids(f"<|{role}|>")] + self.tokenizer.encode(f"{metadata}\n",
+                                                                                              disallowed_special=())
+            message_tokens = self.tokenizer.encode(message, disallowed_special=())
+            tokens = role_tokens + message_tokens
+            return tokens
+        else:
+            return str(f"<|{role}|>{metadata}\n{message}")
+
+    # Use Jinja Template in tokenizer_config.json
+    # def apply_chat_template(
+    #         self,
+    #         conversation: Union[List[Dict[str, str]], List[List[Dict[str, str]]], "Conversation"],
+    #         add_generation_prompt: bool = False,
+    #         tokenize: bool = True,
+    #         padding: bool = False,
+    #         truncation: bool = False,
+    #         max_length: Optional[int] = None,
+    #         return_tensors: Optional[Union[str, TensorType]] = None,
+    #         return_dict: bool = False,
+    #         tokenizer_kwargs: Optional[Dict[str, Any]] = None,
+    #         add_special_tokens: bool = True,
+    #         **kwargs,
+    # ) -> Union[str, List[int], List[str], List[List[int]], BatchEncoding]:
+    #
+    #     if return_dict and not tokenize:
+    #         raise ValueError(
+    #             "`return_dict=True` is incompatible with `tokenize=False`, because there is no dict "
+    #             "of tokenizer outputs to return."
+    #         )
+    #
+    #     def handle_single_conversation(conversation):
+    #         input_ids = self.get_prefix_tokens() if add_special_tokens else []
+    #         input_message = "[gMASK]<sop>" if add_special_tokens else ""
+    #         for item in conversation:
+    #             if item.get("tools"):
+    #                 tools = item["tools"]
+    #                 content = "你是一个名为 GhatGLM 的人工智能助手。你是基于智谱AI训练的语言模型 GLM-4 模型开发的，你的任务是针对用户的问题和要求提供适当的答复和支持。"
+    #                 content += "\n\n# 可用工具"
+    #                 for tool in tools:
+    #                     if tool["type"] == "function":
+    #                         function = tool["function"]
+    #                         content += f"\n\n## {function['name']}\n\n{json.dumps(function, ensure_ascii=False, indent=4)}"
+    #                         content += "\n在调用上述函数时，请使用 Json 格式表示调用的参数。"
+    #                     elif tool["type"] == "python":
+    #                         content += "\n\n## python\n\n当你向 `python` 发送包含 Python 代码的消息时，该代码将会在一个有状态的 Jupyter notebook 环境中执行。\n`python` 返回代码执行的输出，或在执行 60 秒后返回超时。\n`/mnt/data` 将会持久化存储你的文件。在此会话中，`python` 无法访问互联网。不要使用 `python` 进行任何网络请求或者在线 API 调用，这些在线内容的访问将不会成功。"
+    #                     elif tool["type"] == "simple_browser":
+    #                         content += "\n\n## simple_browser\n\n你可以使用 `simple_browser` 工具。该工具支持以下函数：\n`search(query: str, recency_days: int)`：使用搜索引擎进行查询并显示结果，可以使用 `recency_days` 参数控制搜索内容的时效性。\n`mclick(ids: list[int])`：获取一系列指定 id 的页面内容。每次调用时，须选择3-10个页面。选择多个角度的页面，同时尽可能选择可信任的信息来源。考虑到部分页面是无法加载的，你也可以多打开一些可能有用的页面而不用担心内容过多。\n`open_url(url: str)`：打开指定的 URL。\n\n使用 `【{引用 id}†{引用文本}】` 来引用内容。\n\n操作步骤：1. 使用 `search` 来获得信息列表; 2. 使用 `mclick` 来获取指定 ID 页面的内容; 3. 根据获得的内容进行回复。在回复中应当引用信息来源。\n 如果用户提供了 URL，也可以用 `open_url` 直接打开页面。\n如果初次搜索结果没有找到合适的信息，也可以再次使用 `search` 进行搜索。"
+    #                     elif tool["type"] == "cogview":
+    #                         content += "\n\n## cogview\n\n如果用户的请求中包含了对图像的描述，你可以使用 `cogview` 来生成图像并展示给用户。你需要向 `cogview` 发送图像描述，规则：\n- 发送给 `cogview` 的消息必须使用英语。用户的中文描述必须完全翻译为英语。\n- 应当尽可能详细地描述图像生成的需求，需求描述约 100 英文单词。\n- 保持用户原始描述的意图。不要虚构内容或者没见过的人物。\n- 如无特殊说明，所在地为中国，持有中国立场并遵循中国社会主义价值观。"
+    #                     else:
+    #                         raise NotImplementedError(f"Unknown tool type {tool['type']}")
+    #                 input = self.build_single_message("system", "", content, tokenize=tokenize)
+    #                 if tokenize:
+    #                     input_ids.extend(input)
+    #                 else:
+    #                     input_message += input
+    #             if item["content"]:
+    #                 input = self.build_single_message(
+    #                     item["role"],
+    #                     item.get("metadata", ""),
+    #                     item["content"],
+    #                     tokenize=tokenize
+    #                 )
+    #                 if tokenize:
+    #                     input_ids.extend(input)
+    #                 else:
+    #                     input_message += input
+    #         if add_generation_prompt:
+    #             if tokenize:
+    #                 input_ids.extend([self.convert_tokens_to_ids("<|assistant|>")])
+    #             else:
+    #                 input_message += "<|assistant|>"
+    #         return input_ids if tokenize else input_message
+    #
+    #     # Main logic to handle different conversation formats
+    #     if isinstance(conversation, list) and all(isinstance(i, dict) for i in conversation):
+    #         result = handle_single_conversation(conversation)
+    #     elif isinstance(conversation, list) and all(isinstance(i, list) for i in conversation):
+    #         result = [handle_single_conversation(c) for c in conversation]
+    #     elif hasattr(conversation, "messages"):
+    #         result = handle_single_conversation(conversation.messages)
+    #     else:
+    #         raise ValueError("Invalid conversation format")
+    #
+    #     if tokenize:
+    #         output = self.batch_encode_plus(
+    #             [result] if isinstance(result[0], int) else result,
+    #             padding=padding,
+    #             truncation=truncation,
+    #             max_length=max_length,
+    #             return_tensors=return_tensors,
+    #             is_split_into_words=True,
+    #             add_special_tokens=False
+    #         )
+    #         if return_dict:
+    #             return output
+    #         else:
+    #             return output["input_ids"]
+    #     else:
+    #         return result
+
+    def build_inputs_with_special_tokens(
+            self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
+    ) -> List[int]:
+        """
+        Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and
+        adding special tokens. A BERT sequence has the following format:
+
+        - single sequence: `[CLS] X [SEP]`
+        - pair of sequences: `[CLS] A [SEP] B [SEP]`
+
+        Args:
+            token_ids_0 (`List[int]`):
+                List of IDs to which the special tokens will be added.
+            token_ids_1 (`List[int]`, *optional*):
+                Optional second list of IDs for sequence pairs.
+
+        Returns:
+            `List[int]`: List of [input IDs](../glossary#input-ids) with the appropriate special tokens.
+        """
+        prefix_tokens = self.get_prefix_tokens()
+        token_ids_0 = prefix_tokens + token_ids_0
+        if token_ids_1 is not None:
+            token_ids_0 = token_ids_0 + token_ids_1 + [self.convert_tokens_to_ids("<eos>")]
+        return token_ids_0
+
+    def _pad(
+            self,
+            encoded_inputs: Union[Dict[str, EncodedInput], BatchEncoding],
+            max_length: Optional[int] = None,
+            padding_strategy: PaddingStrategy = PaddingStrategy.DO_NOT_PAD,
+            pad_to_multiple_of: Optional[int] = None,
+            return_attention_mask: Optional[bool] = None,
+    ) -> dict:
+        """
+        Pad encoded inputs (on left/right and up to predefined length or max length in the batch)
+
+        Args:
+            encoded_inputs:
+                Dictionary of tokenized inputs (`List[int]`) or batch of tokenized inputs (`List[List[int]]`).
+            max_length: maximum length of the returned list and optionally padding length (see below).
+                Will truncate by taking into account the special tokens.
+            padding_strategy: PaddingStrategy to use for padding.
+
+                - PaddingStrategy.LONGEST Pad to the longest sequence in the batch
+                - PaddingStrategy.MAX_LENGTH: Pad to the max length (default)
+                - PaddingStrategy.DO_NOT_PAD: Do not pad
+                The tokenizer padding sides are defined in self.padding_side:
+
+                    - 'left': pads on the left of the sequences
+                    - 'right': pads on the right of the sequences
+            pad_to_multiple_of: (optional) Integer if set will pad the sequence to a multiple of the provided value.
+                This is especially useful to enable the use of Tensor Core on NVIDIA hardware with compute capability
+                `>= 7.5` (Volta).
+            return_attention_mask:
+                (optional) Set to False to avoid returning attention mask (default: set to model specifics)
+        """
+        # Load from model defaults
+        assert self.padding_side == "left"
+
+        required_input = encoded_inputs[self.model_input_names[0]]
+        seq_length = len(required_input)
+
+        if padding_strategy == PaddingStrategy.LONGEST:
+            max_length = len(required_input)
+
+        if max_length is not None and pad_to_multiple_of is not None and (max_length % pad_to_multiple_of != 0):
+            max_length = ((max_length // pad_to_multiple_of) + 1) * pad_to_multiple_of
+
+        needs_to_be_padded = padding_strategy != PaddingStrategy.DO_NOT_PAD and len(required_input) != max_length
+
+        # Initialize attention mask if not present.
+        if "attention_mask" not in encoded_inputs:
+            encoded_inputs["attention_mask"] = [1] * seq_length
+
+        if "position_ids" not in encoded_inputs:
+            encoded_inputs["position_ids"] = list(range(seq_length))
+
+        if needs_to_be_padded:
+            difference = max_length - len(required_input)
+
+            if "attention_mask" in encoded_inputs:
+                encoded_inputs["attention_mask"] = [0] * difference + encoded_inputs["attention_mask"]
+            if "position_ids" in encoded_inputs:
+                encoded_inputs["position_ids"] = [0] * difference + encoded_inputs["position_ids"]
+            encoded_inputs[self.model_input_names[0]] = [self.pad_token_id] * difference + required_input
+
+        return encoded_inputs

lora/sft/checkpoint-112/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a493598071550244b2ee7f26118f3edec2150b9dfa967929a99052ac83fe716
+size 2623634

lora/sft/checkpoint-112/tokenizer_config.json

@@ -0,0 +1,148 @@
+{
+  "added_tokens_decoder": {
+    "151329": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151330": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151331": {
+      "content": "[gMASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151332": {
+      "content": "[sMASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151333": {
+      "content": "<sop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151334": {
+      "content": "<eop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151335": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151336": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151337": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151338": {
+      "content": "<|observation|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151339": {
+      "content": "<|begin_of_image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151340": {
+      "content": "<|end_of_image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151341": {
+      "content": "<|begin_of_video|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151342": {
+      "content": "<|end_of_video|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>"
+  ],
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_chatglm.ChatGLM4Tokenizer",
+      null
+    ]
+  },
+  "chat_template": "{{ '[gMASK]<sop>' }}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|system|>\n' + system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|user|>\n' + content + '<|assistant|>' }}{% elif message['role'] == 'assistant' %}{{ '\n' + content }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 128000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "remove_space": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "ChatGLM4Tokenizer"
+}

lora/sft/checkpoint-112/trainer_state.json

@@ -0,0 +1,110 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9955555555555555,
+  "eval_steps": 500,
+  "global_step": 112,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 7.216278553009033,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 2.4521,
+      "step": 10
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 5.572214603424072,
+      "learning_rate": 9.842915805643156e-06,
+      "loss": 2.1638,
+      "step": 20
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 2.498288631439209,
+      "learning_rate": 9.221639627510076e-06,
+      "loss": 1.9103,
+      "step": 30
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 3.3242993354797363,
+      "learning_rate": 8.18711994874345e-06,
+      "loss": 1.7952,
+      "step": 40
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 2.2792470455169678,
+      "learning_rate": 6.840622763423391e-06,
+      "loss": 1.6722,
+      "step": 50
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 2.598036289215088,
+      "learning_rate": 5.3139525976465675e-06,
+      "loss": 1.6154,
+      "step": 60
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 2.531435489654541,
+      "learning_rate": 3.756550564175727e-06,
+      "loss": 1.6036,
+      "step": 70
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 2.560697317123413,
+      "learning_rate": 2.320866025105016e-06,
+      "loss": 1.5899,
+      "step": 80
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.3769493103027344,
+      "learning_rate": 1.1474337861210543e-06,
+      "loss": 1.6193,
+      "step": 90
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 2.1420528888702393,
+      "learning_rate": 3.511175705587433e-07,
+      "loss": 1.569,
+      "step": 100
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 1.8092883825302124,
+      "learning_rate": 9.866357858642206e-09,
+      "loss": 1.5909,
+      "step": 110
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 112,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2980476361834496e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

lora/sft/checkpoint-112/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a91a4ed932e171381acdd219106313852fe2612831e5273940b143e95ee3af6f
+size 5304

lora/sft/eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 0.9955555555555555,
+    "eval_loss": 1.5198827981948853,
+    "eval_runtime": 11.7693,
+    "eval_samples_per_second": 8.497,
+    "eval_steps_per_second": 8.497
+}

lora/sft/special_tokens_map.json

@@ -0,0 +1,32 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

lora/sft/tokenization_chatglm.py

@@ -0,0 +1,323 @@
+import regex as re
+import base64
+import os
+import json
+import tiktoken
+from torch import TensorType
+from typing import List, Optional, Union, Dict, Any
+from transformers import PreTrainedTokenizer
+from transformers.utils import logging, PaddingStrategy
+from transformers.tokenization_utils_base import EncodedInput, BatchEncoding
+
+
+class ChatGLM4Tokenizer(PreTrainedTokenizer):
+    vocab_files_names = {"vocab_file": "tokenizer.model"}
+    model_input_names = ["input_ids", "attention_mask", "position_ids"]
+
+    def __init__(
+            self,
+            vocab_file,
+            padding_side="left",
+            clean_up_tokenization_spaces=False,
+            encode_special_tokens=False,
+            **kwargs
+    ):
+        self.name = "GLM4Tokenizer"
+        self.vocab_file = vocab_file
+        pat_str = "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}{1,3}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+"
+        self.pat_str = re.compile(pat_str)
+        self.encode_special_tokens = encode_special_tokens
+
+        mergeable_ranks = {}
+        with open(vocab_file) as f:
+            for line in f:
+                token, rank = line.strip().split()
+                rank = int(rank)
+                token = base64.b64decode(token)
+                mergeable_ranks[token] = rank
+
+        self.mergeable_ranks = mergeable_ranks
+
+        self.tokenizer = tiktoken.Encoding(
+            name="my_tokenizer",
+            pat_str=pat_str,
+            mergeable_ranks=mergeable_ranks,
+            special_tokens={}
+        )
+        self.decoder = {rank: token for token, rank in mergeable_ranks.items()}
+        self.n_words = len(self.decoder)
+
+        super().__init__(
+            padding_side=padding_side,
+            clean_up_tokenization_spaces=clean_up_tokenization_spaces,
+            **kwargs
+        )
+
+    @property
+    def vocab_size(self):
+        return self.n_words
+
+    def get_vocab(self):
+        """ Returns vocab as a dict """
+        vocab = {self._convert_id_to_token(i): i for i in range(self.vocab_size)}
+        vocab.update(self.added_tokens_encoder)
+        return vocab
+
+    def convert_tokens_to_string(self, tokens: List[Union[bytes, str, int]]) -> str:
+        """
+        Converts a sequence of tokens in a single string.
+        """
+        text = ""
+        temp = b""
+        for t in tokens:
+            if isinstance(t, int):
+                t = chr(t)
+            if isinstance(t, str):
+                if temp:
+                    text += temp.decode("utf-8", errors="replace")
+            elif isinstance(t, bytes):
+                temp += t
+            else:
+                raise TypeError("token should only be of type int, bytes or str")
+        if temp:
+            text += temp.decode("utf-8", errors="replace")
+        return text
+
+    def _tokenize(self, text, **kwargs):
+        tokens = []
+        ids = self.tokenizer.encode(text)
+        for t in ids:
+            tokens.append(self.decoder[t])
+        return tokens
+
+    def _convert_token_to_id(self, token):
+        """ Converts a token (str) in an id using the vocab. """
+        return self.mergeable_ranks[token]
+
+    def _convert_id_to_token(self, index):
+        """Converts an index (integer) in a token (str) using the vocab."""
+        return self.decoder.get(index, "")
+
+    def save_vocabulary(self, save_directory, filename_prefix=None):
+        """
+        Save the vocabulary and special tokens file to a directory.
+
+        Args:
+            save_directory (`str`):
+                The directory in which to save the vocabulary.
+            filename_prefix (`str`, *optional*):
+                An optional prefix to add to the named of the saved files.
+
+        Returns:
+            `Tuple(str)`: Paths to the files saved.
+        """
+        if os.path.isdir(save_directory):
+            vocab_file = os.path.join(
+                save_directory, self.vocab_files_names["vocab_file"]
+            )
+        else:
+            vocab_file = save_directory
+
+        with open(self.vocab_file, 'rb') as fin:
+            proto_str = fin.read()
+
+        with open(vocab_file, "wb") as writer:
+            writer.write(proto_str)
+
+        return (vocab_file,)
+
+    def get_prefix_tokens(self):
+        prefix_tokens = [self.convert_tokens_to_ids("[gMASK]"), self.convert_tokens_to_ids("<sop>")]
+        return prefix_tokens
+
+    def build_single_message(self, role, metadata, message, tokenize=True):
+        assert role in ["system", "user", "assistant", "observation"], role
+        if tokenize:
+            role_tokens = [self.convert_tokens_to_ids(f"<|{role}|>")] + self.tokenizer.encode(f"{metadata}\n",
+                                                                                              disallowed_special=())
+            message_tokens = self.tokenizer.encode(message, disallowed_special=())
+            tokens = role_tokens + message_tokens
+            return tokens
+        else:
+            return str(f"<|{role}|>{metadata}\n{message}")
+
+    # Use Jinja Template in tokenizer_config.json
+    # def apply_chat_template(
+    #         self,
+    #         conversation: Union[List[Dict[str, str]], List[List[Dict[str, str]]], "Conversation"],
+    #         add_generation_prompt: bool = False,
+    #         tokenize: bool = True,
+    #         padding: bool = False,
+    #         truncation: bool = False,
+    #         max_length: Optional[int] = None,
+    #         return_tensors: Optional[Union[str, TensorType]] = None,
+    #         return_dict: bool = False,
+    #         tokenizer_kwargs: Optional[Dict[str, Any]] = None,
+    #         add_special_tokens: bool = True,
+    #         **kwargs,
+    # ) -> Union[str, List[int], List[str], List[List[int]], BatchEncoding]:
+    #
+    #     if return_dict and not tokenize:
+    #         raise ValueError(
+    #             "`return_dict=True` is incompatible with `tokenize=False`, because there is no dict "
+    #             "of tokenizer outputs to return."
+    #         )
+    #
+    #     def handle_single_conversation(conversation):
+    #         input_ids = self.get_prefix_tokens() if add_special_tokens else []
+    #         input_message = "[gMASK]<sop>" if add_special_tokens else ""
+    #         for item in conversation:
+    #             if item.get("tools"):
+    #                 tools = item["tools"]
+    #                 content = "你是一个名为 GhatGLM 的人工智能助手。你是基于智谱AI训练的语言模型 GLM-4 模型开发的，你的任务是针对用户的问题和要求提供适当的答复和支持。"
+    #                 content += "\n\n# 可用工具"
+    #                 for tool in tools:
+    #                     if tool["type"] == "function":
+    #                         function = tool["function"]
+    #                         content += f"\n\n## {function['name']}\n\n{json.dumps(function, ensure_ascii=False, indent=4)}"
+    #                         content += "\n在调用上述函数时，请使用 Json 格式表示调用的参数。"
+    #                     elif tool["type"] == "python":
+    #                         content += "\n\n## python\n\n当你向 `python` 发送包含 Python 代码的消息时，该代码将会在一个有状态的 Jupyter notebook 环境中执行。\n`python` 返回代码执行的输出，或在执行 60 秒后返回超时。\n`/mnt/data` 将会持久化存储你的文件。在此会话中，`python` 无法访问互联网。不要使用 `python` 进行任何网络请求或者在线 API 调用，这些在线内容的访问将不会成功。"
+    #                     elif tool["type"] == "simple_browser":
+    #                         content += "\n\n## simple_browser\n\n你可以使用 `simple_browser` 工具。该工具支持以下函数：\n`search(query: str, recency_days: int)`：使用搜索引擎进行查询并显示结果，可以使用 `recency_days` 参数控制搜索内容的时效性。\n`mclick(ids: list[int])`：获取一系列指定 id 的页面内容。每次调用时，须选择3-10个页面。选择多个角度的页面，同时尽可能选择可信任的信息来源。考虑到部分页面是无法加载的，你也可以多打开一些可能有用的页面而不用担心内容过多。\n`open_url(url: str)`：打开指定的 URL。\n\n使用 `【{引用 id}†{引用文本}】` 来引用内容。\n\n操作步骤：1. 使用 `search` 来获得信息列表; 2. 使用 `mclick` 来获取指定 ID 页面的内容; 3. 根据获得的内容进行回复。在回复中应当引用信息来源。\n 如果用户提供了 URL，也可以用 `open_url` 直接打开页面。\n如果初次搜索结果没有找到合适的信息，也可以再次使用 `search` 进行搜索。"
+    #                     elif tool["type"] == "cogview":
+    #                         content += "\n\n## cogview\n\n如果用户的请求中包含了对图像的描述，你可以使用 `cogview` 来生成图像并展示给用户。你需要向 `cogview` 发送图像描述，规则：\n- 发送给 `cogview` 的消息必须使用英语。用户的中文描述必须完全翻译为英语。\n- 应当尽可能详细地描述图像生成的需求，需求描述约 100 英文单词。\n- 保持用户原始描述的意图。不要虚构内容或者没见过的人物。\n- 如无特殊说明，所在地为中国，持有中国立场并遵循中国社会主义价值观。"
+    #                     else:
+    #                         raise NotImplementedError(f"Unknown tool type {tool['type']}")
+    #                 input = self.build_single_message("system", "", content, tokenize=tokenize)
+    #                 if tokenize:
+    #                     input_ids.extend(input)
+    #                 else:
+    #                     input_message += input
+    #             if item["content"]:
+    #                 input = self.build_single_message(
+    #                     item["role"],
+    #                     item.get("metadata", ""),
+    #                     item["content"],
+    #                     tokenize=tokenize
+    #                 )
+    #                 if tokenize:
+    #                     input_ids.extend(input)
+    #                 else:
+    #                     input_message += input
+    #         if add_generation_prompt:
+    #             if tokenize:
+    #                 input_ids.extend([self.convert_tokens_to_ids("<|assistant|>")])
+    #             else:
+    #                 input_message += "<|assistant|>"
+    #         return input_ids if tokenize else input_message
+    #
+    #     # Main logic to handle different conversation formats
+    #     if isinstance(conversation, list) and all(isinstance(i, dict) for i in conversation):
+    #         result = handle_single_conversation(conversation)
+    #     elif isinstance(conversation, list) and all(isinstance(i, list) for i in conversation):
+    #         result = [handle_single_conversation(c) for c in conversation]
+    #     elif hasattr(conversation, "messages"):
+    #         result = handle_single_conversation(conversation.messages)
+    #     else:
+    #         raise ValueError("Invalid conversation format")
+    #
+    #     if tokenize:
+    #         output = self.batch_encode_plus(
+    #             [result] if isinstance(result[0], int) else result,
+    #             padding=padding,
+    #             truncation=truncation,
+    #             max_length=max_length,
+    #             return_tensors=return_tensors,
+    #             is_split_into_words=True,
+    #             add_special_tokens=False
+    #         )
+    #         if return_dict:
+    #             return output
+    #         else:
+    #             return output["input_ids"]
+    #     else:
+    #         return result
+
+    def build_inputs_with_special_tokens(
+            self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
+    ) -> List[int]:
+        """
+        Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and
+        adding special tokens. A BERT sequence has the following format:
+
+        - single sequence: `[CLS] X [SEP]`
+        - pair of sequences: `[CLS] A [SEP] B [SEP]`
+
+        Args:
+            token_ids_0 (`List[int]`):
+                List of IDs to which the special tokens will be added.
+            token_ids_1 (`List[int]`, *optional*):
+                Optional second list of IDs for sequence pairs.
+
+        Returns:
+            `List[int]`: List of [input IDs](../glossary#input-ids) with the appropriate special tokens.
+        """
+        prefix_tokens = self.get_prefix_tokens()
+        token_ids_0 = prefix_tokens + token_ids_0
+        if token_ids_1 is not None:
+            token_ids_0 = token_ids_0 + token_ids_1 + [self.convert_tokens_to_ids("<eos>")]
+        return token_ids_0
+
+    def _pad(
+            self,
+            encoded_inputs: Union[Dict[str, EncodedInput], BatchEncoding],
+            max_length: Optional[int] = None,
+            padding_strategy: PaddingStrategy = PaddingStrategy.DO_NOT_PAD,
+            pad_to_multiple_of: Optional[int] = None,
+            return_attention_mask: Optional[bool] = None,
+    ) -> dict:
+        """
+        Pad encoded inputs (on left/right and up to predefined length or max length in the batch)
+
+        Args:
+            encoded_inputs:
+                Dictionary of tokenized inputs (`List[int]`) or batch of tokenized inputs (`List[List[int]]`).
+            max_length: maximum length of the returned list and optionally padding length (see below).
+                Will truncate by taking into account the special tokens.
+            padding_strategy: PaddingStrategy to use for padding.
+
+                - PaddingStrategy.LONGEST Pad to the longest sequence in the batch
+                - PaddingStrategy.MAX_LENGTH: Pad to the max length (default)
+                - PaddingStrategy.DO_NOT_PAD: Do not pad
+                The tokenizer padding sides are defined in self.padding_side:
+
+                    - 'left': pads on the left of the sequences
+                    - 'right': pads on the right of the sequences
+            pad_to_multiple_of: (optional) Integer if set will pad the sequence to a multiple of the provided value.
+                This is especially useful to enable the use of Tensor Core on NVIDIA hardware with compute capability
+                `>= 7.5` (Volta).
+            return_attention_mask:
+                (optional) Set to False to avoid returning attention mask (default: set to model specifics)
+        """
+        # Load from model defaults
+        assert self.padding_side == "left"
+
+        required_input = encoded_inputs[self.model_input_names[0]]
+        seq_length = len(required_input)
+
+        if padding_strategy == PaddingStrategy.LONGEST:
+            max_length = len(required_input)
+
+        if max_length is not None and pad_to_multiple_of is not None and (max_length % pad_to_multiple_of != 0):
+            max_length = ((max_length // pad_to_multiple_of) + 1) * pad_to_multiple_of
+
+        needs_to_be_padded = padding_strategy != PaddingStrategy.DO_NOT_PAD and len(required_input) != max_length
+
+        # Initialize attention mask if not present.
+        if "attention_mask" not in encoded_inputs:
+            encoded_inputs["attention_mask"] = [1] * seq_length
+
+        if "position_ids" not in encoded_inputs:
+            encoded_inputs["position_ids"] = list(range(seq_length))
+
+        if needs_to_be_padded:
+            difference = max_length - len(required_input)
+
+            if "attention_mask" in encoded_inputs:
+                encoded_inputs["attention_mask"] = [0] * difference + encoded_inputs["attention_mask"]
+            if "position_ids" in encoded_inputs:
+                encoded_inputs["position_ids"] = [0] * difference + encoded_inputs["position_ids"]
+            encoded_inputs[self.model_input_names[0]] = [self.pad_token_id] * difference + required_input
+
+        return encoded_inputs

lora/sft/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a493598071550244b2ee7f26118f3edec2150b9dfa967929a99052ac83fe716
+size 2623634

lora/sft/tokenizer_config.json

@@ -0,0 +1,148 @@
+{
+  "added_tokens_decoder": {
+    "151329": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151330": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151331": {
+      "content": "[gMASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151332": {
+      "content": "[sMASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151333": {
+      "content": "<sop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151334": {
+      "content": "<eop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151335": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151336": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151337": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151338": {
+      "content": "<|observation|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151339": {
+      "content": "<|begin_of_image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151340": {
+      "content": "<|end_of_image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151341": {
+      "content": "<|begin_of_video|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151342": {
+      "content": "<|end_of_video|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>"
+  ],
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_chatglm.ChatGLM4Tokenizer",
+      null
+    ]
+  },
+  "chat_template": "{{ '[gMASK]<sop>' }}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|system|>\n' + system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|user|>\n' + content + '<|assistant|>' }}{% elif message['role'] == 'assistant' %}{{ '\n' + content }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 128000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "remove_space": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "ChatGLM4Tokenizer"
+}

lora/sft/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9955555555555555,
+    "total_flos": 1.2980476361834496e+16,
+    "train_loss": 1.7745797293526786,
+    "train_runtime": 341.4533,
+    "train_samples_per_second": 2.636,
+    "train_steps_per_second": 0.328
+}

lora/sft/trainer_log.jsonl

@@ -0,0 +1,12 @@
+{"current_steps": 10, "total_steps": 112, "loss": 2.4521, "learning_rate": 8.333333333333334e-06, "epoch": 0.08888888888888889, "percentage": 8.93, "elapsed_time": "0:00:32", "remaining_time": "0:05:29", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 20, "total_steps": 112, "loss": 2.1638, "learning_rate": 9.842915805643156e-06, "epoch": 0.17777777777777778, "percentage": 17.86, "elapsed_time": "0:01:01", "remaining_time": "0:04:44", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 30, "total_steps": 112, "loss": 1.9103, "learning_rate": 9.221639627510076e-06, "epoch": 0.26666666666666666, "percentage": 26.79, "elapsed_time": "0:01:31", "remaining_time": "0:04:09", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 40, "total_steps": 112, "loss": 1.7952, "learning_rate": 8.18711994874345e-06, "epoch": 0.35555555555555557, "percentage": 35.71, "elapsed_time": "0:02:00", "remaining_time": "0:03:36", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 50, "total_steps": 112, "loss": 1.6722, "learning_rate": 6.840622763423391e-06, "epoch": 0.4444444444444444, "percentage": 44.64, "elapsed_time": "0:02:31", "remaining_time": "0:03:08", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 60, "total_steps": 112, "loss": 1.6154, "learning_rate": 5.3139525976465675e-06, "epoch": 0.5333333333333333, "percentage": 53.57, "elapsed_time": "0:03:01", "remaining_time": "0:02:37", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 70, "total_steps": 112, "loss": 1.6036, "learning_rate": 3.756550564175727e-06, "epoch": 0.6222222222222222, "percentage": 62.5, "elapsed_time": "0:03:31", "remaining_time": "0:02:07", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 80, "total_steps": 112, "loss": 1.5899, "learning_rate": 2.320866025105016e-06, "epoch": 0.7111111111111111, "percentage": 71.43, "elapsed_time": "0:04:01", "remaining_time": "0:01:36", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 90, "total_steps": 112, "loss": 1.6193, "learning_rate": 1.1474337861210543e-06, "epoch": 0.8, "percentage": 80.36, "elapsed_time": "0:04:32", "remaining_time": "0:01:06", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 100, "total_steps": 112, "loss": 1.569, "learning_rate": 3.511175705587433e-07, "epoch": 0.8888888888888888, "percentage": 89.29, "elapsed_time": "0:05:03", "remaining_time": "0:00:36", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 110, "total_steps": 112, "loss": 1.5909, "learning_rate": 9.866357858642206e-09, "epoch": 0.9777777777777777, "percentage": 98.21, "elapsed_time": "0:05:33", "remaining_time": "0:00:06", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 112, "total_steps": 112, "epoch": 0.9955555555555555, "percentage": 100.0, "elapsed_time": "0:05:41", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}

lora/sft/trainer_state.json

@@ -0,0 +1,119 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9955555555555555,
+  "eval_steps": 500,
+  "global_step": 112,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 7.216278553009033,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 2.4521,
+      "step": 10
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 5.572214603424072,
+      "learning_rate": 9.842915805643156e-06,
+      "loss": 2.1638,
+      "step": 20
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 2.498288631439209,
+      "learning_rate": 9.221639627510076e-06,
+      "loss": 1.9103,
+      "step": 30
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 3.3242993354797363,
+      "learning_rate": 8.18711994874345e-06,
+      "loss": 1.7952,
+      "step": 40
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 2.2792470455169678,
+      "learning_rate": 6.840622763423391e-06,
+      "loss": 1.6722,
+      "step": 50
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 2.598036289215088,
+      "learning_rate": 5.3139525976465675e-06,
+      "loss": 1.6154,
+      "step": 60
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 2.531435489654541,
+      "learning_rate": 3.756550564175727e-06,
+      "loss": 1.6036,
+      "step": 70
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 2.560697317123413,
+      "learning_rate": 2.320866025105016e-06,
+      "loss": 1.5899,
+      "step": 80
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.3769493103027344,
+      "learning_rate": 1.1474337861210543e-06,
+      "loss": 1.6193,
+      "step": 90
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 2.1420528888702393,
+      "learning_rate": 3.511175705587433e-07,
+      "loss": 1.569,
+      "step": 100
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 1.8092883825302124,
+      "learning_rate": 9.866357858642206e-09,
+      "loss": 1.5909,
+      "step": 110
+    },
+    {
+      "epoch": 0.9955555555555555,
+      "step": 112,
+      "total_flos": 1.2980476361834496e+16,
+      "train_loss": 1.7745797293526786,
+      "train_runtime": 341.4533,
+      "train_samples_per_second": 2.636,
+      "train_steps_per_second": 0.328
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 112,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2980476361834496e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

lora/sft/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a91a4ed932e171381acdd219106313852fe2612831e5273940b143e95ee3af6f
+size 5304