diff --git a/.gitattributes b/.gitattributes
index a6344aac8c09253b3b630fb776ae94478aa0275b..3cc5355ac0bbf00f362d3c0a6c29974b8480e8da 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -33,3 +33,11 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-150/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-317/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-50/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
diff --git a/README.md b/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..ad44b51773bb0ffe727f4fd832322cf1218fb120
--- /dev/null
+++ b/README.md
@@ -0,0 +1,62 @@
+---
+base_model: zai-org/GLM-4-32B-0414
+library_name: peft
+model_name: uigen-fx-1
+tags:
+- base_model:adapter:zai-org/GLM-4-32B-0414
+- lora
+- sft
+- transformers
+- trl
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for uigen-fx-1
+
+This model is a fine-tuned version of [zai-org/GLM-4-32B-0414](https://huggingface.co/zai-org/GLM-4-32B-0414).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- PEFT 0.17.1
+- TRL: 0.23.1
+- Transformers: 4.57.0
+- Pytorch: 2.6.0+git684f6f2
+- Datasets: 4.1.1
+- Tokenizers: 0.22.1
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```
\ No newline at end of file
diff --git a/adapter_config.json b/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f0ebe86d1363a1171c6cd0dcf67ad18fa37c9f85
--- /dev/null
+++ b/adapter_config.json
@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "zai-org/GLM-4-32B-0414",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/adapter_model.safetensors b/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b59a542639a167049f8305880161855fb8df2bc6
--- /dev/null
+++ b/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0449cadcb46edd1c553d548c9e5994006bddec56295db09c6773bfb8407c8b75
+size 4157688432
diff --git a/chat_template.jinja b/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..fdd583731de8bdf1830d38a3e34f7cd8f80605dd
--- /dev/null
+++ b/chat_template.jinja
@@ -0,0 +1,41 @@
+[gMASK]<sop>
+{%- if tools -%}
+<|system|>
+# 可用工具
+{% for tool in tools %}
+    {%- set function = tool.function if tool.get("function") else tool %}
+
+## {{ function.name }}
+
+{{ function | tojson(indent=4, ensure_ascii=False) }}
+在调用上述函数时，请使用 Json 格式表示调用的参数。
+{%- endfor %}
+{%- endif -%}
+
+{%- for msg in messages %}
+    {%- if msg.role == 'system' %}
+<|system|>
+{{ msg.content }}
+    {%- endif %}
+{%- endfor %}
+
+{%- for message in messages if message.role != 'system' %}
+    {%- set role = message['role'] %}
+    {%- set content = message['content'] %}
+    {%- set meta = message.get("metadata", "") %}
+
+    {%- if role == 'user' %}
+<|user|>
+{{ content }}
+    {%- elif role == 'assistant' and not meta %}
+<|assistant|>
+{{ content }}
+    {%- elif role == 'assistant' and meta %}
+<|assistant|>{{ meta }}
+{{ content }}
+    {%- elif role == 'observation' %}
+<|observation|>
+{{ content }}
+    {%- endif %}
+{%- endfor %}
+{% if add_generation_prompt %}<|assistant|>{% endif %}
\ No newline at end of file
diff --git a/checkpoint-100/README.md b/checkpoint-100/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..235c2e6ff7d5d996be0c01802fa2d7707c43b969
--- /dev/null
+++ b/checkpoint-100/README.md
@@ -0,0 +1,209 @@
+---
+base_model: zai-org/GLM-4-32B-0414
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:zai-org/GLM-4-32B-0414
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.17.1
\ No newline at end of file
diff --git a/checkpoint-100/adapter_config.json b/checkpoint-100/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f0ebe86d1363a1171c6cd0dcf67ad18fa37c9f85
--- /dev/null
+++ b/checkpoint-100/adapter_config.json
@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "zai-org/GLM-4-32B-0414",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-100/adapter_model.safetensors b/checkpoint-100/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0ad60ad1ec28e5c9d5bae205e31ca043b4de5d23
--- /dev/null
+++ b/checkpoint-100/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8119c8e33cdd29aa4a638963b343ac471403042545b9d9ad2bbb969e77e28a90
+size 4157688432
diff --git a/checkpoint-100/chat_template.jinja b/checkpoint-100/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..fdd583731de8bdf1830d38a3e34f7cd8f80605dd
--- /dev/null
+++ b/checkpoint-100/chat_template.jinja
@@ -0,0 +1,41 @@
+[gMASK]<sop>
+{%- if tools -%}
+<|system|>
+# 可用工具
+{% for tool in tools %}
+    {%- set function = tool.function if tool.get("function") else tool %}
+
+## {{ function.name }}
+
+{{ function | tojson(indent=4, ensure_ascii=False) }}
+在调用上述函数时，请使用 Json 格式表示调用的参数。
+{%- endfor %}
+{%- endif -%}
+
+{%- for msg in messages %}
+    {%- if msg.role == 'system' %}
+<|system|>
+{{ msg.content }}
+    {%- endif %}
+{%- endfor %}
+
+{%- for message in messages if message.role != 'system' %}
+    {%- set role = message['role'] %}
+    {%- set content = message['content'] %}
+    {%- set meta = message.get("metadata", "") %}
+
+    {%- if role == 'user' %}
+<|user|>
+{{ content }}
+    {%- elif role == 'assistant' and not meta %}
+<|assistant|>
+{{ content }}
+    {%- elif role == 'assistant' and meta %}
+<|assistant|>{{ meta }}
+{{ content }}
+    {%- elif role == 'observation' %}
+<|observation|>
+{{ content }}
+    {%- endif %}
+{%- endfor %}
+{% if add_generation_prompt %}<|assistant|>{% endif %}
\ No newline at end of file
diff --git a/checkpoint-100/optimizer.pt b/checkpoint-100/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..43bf07ff9a96b6da78ffb812df4862ddf058efd9
--- /dev/null
+++ b/checkpoint-100/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:134b73c523d89acf042593d3baab87c3320580a8bd3b9f5c1b0f0912801d09cb
+size 8315744524
diff --git a/checkpoint-100/rng_state.pth b/checkpoint-100/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..93a52228ea16468eaab41b66555ced3eaaea002c
--- /dev/null
+++ b/checkpoint-100/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244
diff --git a/checkpoint-100/scheduler.pt b/checkpoint-100/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ce0e0033cf389c0d4a98dd27d6aa761bb2aa4c67
--- /dev/null
+++ b/checkpoint-100/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:053acfc89a09092c32ba9278f8c0b9013c2e1e739602a1c250edfada03704f42
+size 1064
diff --git a/checkpoint-100/special_tokens_map.json b/checkpoint-100/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..3cf953c2c8a3c89778c92e54c685942bb1130616
--- /dev/null
+++ b/checkpoint-100/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": "<|user|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-100/tokenizer.json b/checkpoint-100/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..4d1dde37a2715c11628fc84bf571976f9f80eb69
--- /dev/null
+++ b/checkpoint-100/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76ebeac0d8bd7879ead7b43c16b44981f277e47225de2bd7de9ae1a6cc664a8c
+size 19966496
diff --git a/checkpoint-100/tokenizer_config.json b/checkpoint-100/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d690b31eb34e3d9741aff67b37e0ecda2604739b
--- /dev/null
+++ b/checkpoint-100/tokenizer_config.json
@@ -0,0 +1,145 @@
+{
+  "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|>"
+  ],
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "<|user|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 128000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "remove_space": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}
diff --git a/checkpoint-100/trainer_state.json b/checkpoint-100/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..a603f958b5c492376112eb63359ae327ffde8a68
--- /dev/null
+++ b/checkpoint-100/trainer_state.json
@@ -0,0 +1,134 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.31620553359683795,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.5656170375645161,
+      "epoch": 0.03162055335968379,
+      "grad_norm": 487949.625,
+      "learning_rate": 0.000971608832807571,
+      "loss": 0.598,
+      "mean_token_accuracy": 0.8383935391902924,
+      "num_tokens": 611773.0,
+      "step": 10
+    },
+    {
+      "entropy": 0.5844515649601817,
+      "epoch": 0.06324110671936758,
+      "grad_norm": 3576.093505859375,
+      "learning_rate": 0.0009400630914826499,
+      "loss": 0.6717,
+      "mean_token_accuracy": 0.8245183542370796,
+      "num_tokens": 1210060.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.4919601235538721,
+      "epoch": 0.09486166007905138,
+      "grad_norm": 462362592.0,
+      "learning_rate": 0.0009085173501577287,
+      "loss": 0.6075,
+      "mean_token_accuracy": 0.8355057552456856,
+      "num_tokens": 1815732.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.45399096198379996,
+      "epoch": 0.12648221343873517,
+      "grad_norm": 48967.296875,
+      "learning_rate": 0.0008769716088328076,
+      "loss": 0.6877,
+      "mean_token_accuracy": 0.8247161574661732,
+      "num_tokens": 2372291.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.5189430050551891,
+      "epoch": 0.15810276679841898,
+      "grad_norm": 20488920.0,
+      "learning_rate": 0.0008454258675078864,
+      "loss": 0.6631,
+      "mean_token_accuracy": 0.8253108873963356,
+      "num_tokens": 2970656.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.5161575745791197,
+      "epoch": 0.18972332015810275,
+      "grad_norm": 11390319.0,
+      "learning_rate": 0.0008138801261829653,
+      "loss": 0.5682,
+      "mean_token_accuracy": 0.8430261947214603,
+      "num_tokens": 3561312.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.5097578268498182,
+      "epoch": 0.22134387351778656,
+      "grad_norm": 5408220.5,
+      "learning_rate": 0.0007823343848580442,
+      "loss": 0.598,
+      "mean_token_accuracy": 0.8383074931800365,
+      "num_tokens": 4164666.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.561078536324203,
+      "epoch": 0.25296442687747034,
+      "grad_norm": 3655628.0,
+      "learning_rate": 0.000750788643533123,
+      "loss": 0.5818,
+      "mean_token_accuracy": 0.8375455126166343,
+      "num_tokens": 4750115.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.6730448313057422,
+      "epoch": 0.2845849802371542,
+      "grad_norm": 65684.3125,
+      "learning_rate": 0.0007192429022082018,
+      "loss": 0.6005,
+      "mean_token_accuracy": 0.8356033861637115,
+      "num_tokens": 5290377.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.68943473957479,
+      "epoch": 0.31620553359683795,
+      "grad_norm": 18166769664.0,
+      "learning_rate": 0.0006876971608832808,
+      "loss": 0.6068,
+      "mean_token_accuracy": 0.8362394802272319,
+      "num_tokens": 5882068.0,
+      "step": 100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 317,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1531563857399153e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-100/training_args.bin b/checkpoint-100/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..120f85ab118be2c00862d7334c96dd25039dfeea
--- /dev/null
+++ b/checkpoint-100/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bad5302c07edbe0267e2b38e65245429ed8bff1dce0fb4fc7af4aef2083cf5b
+size 5880
diff --git a/checkpoint-150/README.md b/checkpoint-150/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..235c2e6ff7d5d996be0c01802fa2d7707c43b969
--- /dev/null
+++ b/checkpoint-150/README.md
@@ -0,0 +1,209 @@
+---
+base_model: zai-org/GLM-4-32B-0414
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:zai-org/GLM-4-32B-0414
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.17.1
\ No newline at end of file
diff --git a/checkpoint-150/adapter_config.json b/checkpoint-150/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f0ebe86d1363a1171c6cd0dcf67ad18fa37c9f85
--- /dev/null
+++ b/checkpoint-150/adapter_config.json
@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "zai-org/GLM-4-32B-0414",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-150/adapter_model.safetensors b/checkpoint-150/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0a6fb948ffb923bee7eeb7f63bc852df31df9d83
--- /dev/null
+++ b/checkpoint-150/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:288041dcdf35700a374cc8d817fc989940d6ab17ad5c8e42154ccada1b9692ad
+size 4157688432
diff --git a/checkpoint-150/chat_template.jinja b/checkpoint-150/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..fdd583731de8bdf1830d38a3e34f7cd8f80605dd
--- /dev/null
+++ b/checkpoint-150/chat_template.jinja
@@ -0,0 +1,41 @@
+[gMASK]<sop>
+{%- if tools -%}
+<|system|>
+# 可用工具
+{% for tool in tools %}
+    {%- set function = tool.function if tool.get("function") else tool %}
+
+## {{ function.name }}
+
+{{ function | tojson(indent=4, ensure_ascii=False) }}
+在调用上述函数时，请使用 Json 格式表示调用的参数。
+{%- endfor %}
+{%- endif -%}
+
+{%- for msg in messages %}
+    {%- if msg.role == 'system' %}
+<|system|>
+{{ msg.content }}
+    {%- endif %}
+{%- endfor %}
+
+{%- for message in messages if message.role != 'system' %}
+    {%- set role = message['role'] %}
+    {%- set content = message['content'] %}
+    {%- set meta = message.get("metadata", "") %}
+
+    {%- if role == 'user' %}
+<|user|>
+{{ content }}
+    {%- elif role == 'assistant' and not meta %}
+<|assistant|>
+{{ content }}
+    {%- elif role == 'assistant' and meta %}
+<|assistant|>{{ meta }}
+{{ content }}
+    {%- elif role == 'observation' %}
+<|observation|>
+{{ content }}
+    {%- endif %}
+{%- endfor %}
+{% if add_generation_prompt %}<|assistant|>{% endif %}
\ No newline at end of file
diff --git a/checkpoint-150/optimizer.pt b/checkpoint-150/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7d69721b88de123d5d9a730ef429cc85f74b26dc
--- /dev/null
+++ b/checkpoint-150/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a9cf9a826787bcddf53816dddb7b67a4d15143e694085f71a614974e535a844
+size 8315744524
diff --git a/checkpoint-150/rng_state.pth b/checkpoint-150/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..93a52228ea16468eaab41b66555ced3eaaea002c
--- /dev/null
+++ b/checkpoint-150/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244
diff --git a/checkpoint-150/scheduler.pt b/checkpoint-150/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1e2f308602c9b754a2484e6ea672a0766a55bf41
--- /dev/null
+++ b/checkpoint-150/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73df21ec5e54e407c7df638e8253ba4bfc6287c699d87bcb807486face86d5da
+size 1064
diff --git a/checkpoint-150/special_tokens_map.json b/checkpoint-150/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..3cf953c2c8a3c89778c92e54c685942bb1130616
--- /dev/null
+++ b/checkpoint-150/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": "<|user|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-150/tokenizer.json b/checkpoint-150/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..4d1dde37a2715c11628fc84bf571976f9f80eb69
--- /dev/null
+++ b/checkpoint-150/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76ebeac0d8bd7879ead7b43c16b44981f277e47225de2bd7de9ae1a6cc664a8c
+size 19966496
diff --git a/checkpoint-150/tokenizer_config.json b/checkpoint-150/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d690b31eb34e3d9741aff67b37e0ecda2604739b
--- /dev/null
+++ b/checkpoint-150/tokenizer_config.json
@@ -0,0 +1,145 @@
+{
+  "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|>"
+  ],
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "<|user|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 128000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "remove_space": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}
diff --git a/checkpoint-150/trainer_state.json b/checkpoint-150/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..a3c521b04d588daf39febe73ab2b6d96714a4a0f
--- /dev/null
+++ b/checkpoint-150/trainer_state.json
@@ -0,0 +1,184 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.4743083003952569,
+  "eval_steps": 500,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.5656170375645161,
+      "epoch": 0.03162055335968379,
+      "grad_norm": 487949.625,
+      "learning_rate": 0.000971608832807571,
+      "loss": 0.598,
+      "mean_token_accuracy": 0.8383935391902924,
+      "num_tokens": 611773.0,
+      "step": 10
+    },
+    {
+      "entropy": 0.5844515649601817,
+      "epoch": 0.06324110671936758,
+      "grad_norm": 3576.093505859375,
+      "learning_rate": 0.0009400630914826499,
+      "loss": 0.6717,
+      "mean_token_accuracy": 0.8245183542370796,
+      "num_tokens": 1210060.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.4919601235538721,
+      "epoch": 0.09486166007905138,
+      "grad_norm": 462362592.0,
+      "learning_rate": 0.0009085173501577287,
+      "loss": 0.6075,
+      "mean_token_accuracy": 0.8355057552456856,
+      "num_tokens": 1815732.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.45399096198379996,
+      "epoch": 0.12648221343873517,
+      "grad_norm": 48967.296875,
+      "learning_rate": 0.0008769716088328076,
+      "loss": 0.6877,
+      "mean_token_accuracy": 0.8247161574661732,
+      "num_tokens": 2372291.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.5189430050551891,
+      "epoch": 0.15810276679841898,
+      "grad_norm": 20488920.0,
+      "learning_rate": 0.0008454258675078864,
+      "loss": 0.6631,
+      "mean_token_accuracy": 0.8253108873963356,
+      "num_tokens": 2970656.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.5161575745791197,
+      "epoch": 0.18972332015810275,
+      "grad_norm": 11390319.0,
+      "learning_rate": 0.0008138801261829653,
+      "loss": 0.5682,
+      "mean_token_accuracy": 0.8430261947214603,
+      "num_tokens": 3561312.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.5097578268498182,
+      "epoch": 0.22134387351778656,
+      "grad_norm": 5408220.5,
+      "learning_rate": 0.0007823343848580442,
+      "loss": 0.598,
+      "mean_token_accuracy": 0.8383074931800365,
+      "num_tokens": 4164666.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.561078536324203,
+      "epoch": 0.25296442687747034,
+      "grad_norm": 3655628.0,
+      "learning_rate": 0.000750788643533123,
+      "loss": 0.5818,
+      "mean_token_accuracy": 0.8375455126166343,
+      "num_tokens": 4750115.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.6730448313057422,
+      "epoch": 0.2845849802371542,
+      "grad_norm": 65684.3125,
+      "learning_rate": 0.0007192429022082018,
+      "loss": 0.6005,
+      "mean_token_accuracy": 0.8356033861637115,
+      "num_tokens": 5290377.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.68943473957479,
+      "epoch": 0.31620553359683795,
+      "grad_norm": 18166769664.0,
+      "learning_rate": 0.0006876971608832808,
+      "loss": 0.6068,
+      "mean_token_accuracy": 0.8362394802272319,
+      "num_tokens": 5882068.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.7109859976917505,
+      "epoch": 0.34782608695652173,
+      "grad_norm": 4711626.5,
+      "learning_rate": 0.0006561514195583596,
+      "loss": 0.6385,
+      "mean_token_accuracy": 0.829913080483675,
+      "num_tokens": 6480962.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.6261379970237613,
+      "epoch": 0.3794466403162055,
+      "grad_norm": 1412058496.0,
+      "learning_rate": 0.0006246056782334385,
+      "loss": 0.5727,
+      "mean_token_accuracy": 0.8403497040271759,
+      "num_tokens": 7080708.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.6068891424685716,
+      "epoch": 0.41106719367588934,
+      "grad_norm": 3915769.0,
+      "learning_rate": 0.0005930599369085173,
+      "loss": 0.5622,
+      "mean_token_accuracy": 0.8430461063981056,
+      "num_tokens": 7692408.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.6536903701722622,
+      "epoch": 0.4426877470355731,
+      "grad_norm": 1457204.375,
+      "learning_rate": 0.0005615141955835961,
+      "loss": 0.6043,
+      "mean_token_accuracy": 0.833759855479002,
+      "num_tokens": 8329614.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.646093986183405,
+      "epoch": 0.4743083003952569,
+      "grad_norm": 96467.4765625,
+      "learning_rate": 0.0005299684542586751,
+      "loss": 0.6169,
+      "mean_token_accuracy": 0.8327336788177491,
+      "num_tokens": 8933829.0,
+      "step": 150
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 317,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.7514421731368018e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-150/training_args.bin b/checkpoint-150/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..120f85ab118be2c00862d7334c96dd25039dfeea
--- /dev/null
+++ b/checkpoint-150/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bad5302c07edbe0267e2b38e65245429ed8bff1dce0fb4fc7af4aef2083cf5b
+size 5880
diff --git a/checkpoint-200/README.md b/checkpoint-200/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..235c2e6ff7d5d996be0c01802fa2d7707c43b969
--- /dev/null
+++ b/checkpoint-200/README.md
@@ -0,0 +1,209 @@
+---
+base_model: zai-org/GLM-4-32B-0414
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:zai-org/GLM-4-32B-0414
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.17.1
\ No newline at end of file
diff --git a/checkpoint-200/adapter_config.json b/checkpoint-200/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f0ebe86d1363a1171c6cd0dcf67ad18fa37c9f85
--- /dev/null
+++ b/checkpoint-200/adapter_config.json
@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "zai-org/GLM-4-32B-0414",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-200/adapter_model.safetensors b/checkpoint-200/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..398d81633f78d8b313d461671e4049d672151f35
--- /dev/null
+++ b/checkpoint-200/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12bd816899c9a54d32bc94b934220703dfe70f37d60e5937ff2dd627a04c3f5b
+size 4157688432
diff --git a/checkpoint-200/chat_template.jinja b/checkpoint-200/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..fdd583731de8bdf1830d38a3e34f7cd8f80605dd
--- /dev/null
+++ b/checkpoint-200/chat_template.jinja
@@ -0,0 +1,41 @@
+[gMASK]<sop>
+{%- if tools -%}
+<|system|>
+# 可用工具
+{% for tool in tools %}
+    {%- set function = tool.function if tool.get("function") else tool %}
+
+## {{ function.name }}
+
+{{ function | tojson(indent=4, ensure_ascii=False) }}
+在调用上述函数时，请使用 Json 格式表示调用的参数。
+{%- endfor %}
+{%- endif -%}
+
+{%- for msg in messages %}
+    {%- if msg.role == 'system' %}
+<|system|>
+{{ msg.content }}
+    {%- endif %}
+{%- endfor %}
+
+{%- for message in messages if message.role != 'system' %}
+    {%- set role = message['role'] %}
+    {%- set content = message['content'] %}
+    {%- set meta = message.get("metadata", "") %}
+
+    {%- if role == 'user' %}
+<|user|>
+{{ content }}
+    {%- elif role == 'assistant' and not meta %}
+<|assistant|>
+{{ content }}
+    {%- elif role == 'assistant' and meta %}
+<|assistant|>{{ meta }}
+{{ content }}
+    {%- elif role == 'observation' %}
+<|observation|>
+{{ content }}
+    {%- endif %}
+{%- endfor %}
+{% if add_generation_prompt %}<|assistant|>{% endif %}
\ No newline at end of file
diff --git a/checkpoint-200/optimizer.pt b/checkpoint-200/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..79acee2e692bbd46501ac9522191ea175f07f2b8
--- /dev/null
+++ b/checkpoint-200/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea5aed5ec8915fcc34c36a4818ab3dbe7aa8958d6d46449313b9bd88ebcc754e
+size 8315744524
diff --git a/checkpoint-200/rng_state.pth b/checkpoint-200/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..93a52228ea16468eaab41b66555ced3eaaea002c
--- /dev/null
+++ b/checkpoint-200/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244
diff --git a/checkpoint-200/scheduler.pt b/checkpoint-200/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f51aa5fb688d3dbec7ffc6e5705c20b15e8f31c2
--- /dev/null
+++ b/checkpoint-200/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a39f3c1e44d50edabecccb1ec93a5215344aa9e14e6304ed79e9fc0fd54b5cb2
+size 1064
diff --git a/checkpoint-200/special_tokens_map.json b/checkpoint-200/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..3cf953c2c8a3c89778c92e54c685942bb1130616
--- /dev/null
+++ b/checkpoint-200/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": "<|user|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-200/tokenizer.json b/checkpoint-200/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..4d1dde37a2715c11628fc84bf571976f9f80eb69
--- /dev/null
+++ b/checkpoint-200/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76ebeac0d8bd7879ead7b43c16b44981f277e47225de2bd7de9ae1a6cc664a8c
+size 19966496
diff --git a/checkpoint-200/tokenizer_config.json b/checkpoint-200/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d690b31eb34e3d9741aff67b37e0ecda2604739b
--- /dev/null
+++ b/checkpoint-200/tokenizer_config.json
@@ -0,0 +1,145 @@
+{
+  "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|>"
+  ],
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "<|user|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 128000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "remove_space": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}
diff --git a/checkpoint-200/trainer_state.json b/checkpoint-200/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..60acf4f7b8e6bf5315fcc7d78f0e3fbbabeffdf2
--- /dev/null
+++ b/checkpoint-200/trainer_state.json
@@ -0,0 +1,234 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6324110671936759,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.5656170375645161,
+      "epoch": 0.03162055335968379,
+      "grad_norm": 487949.625,
+      "learning_rate": 0.000971608832807571,
+      "loss": 0.598,
+      "mean_token_accuracy": 0.8383935391902924,
+      "num_tokens": 611773.0,
+      "step": 10
+    },
+    {
+      "entropy": 0.5844515649601817,
+      "epoch": 0.06324110671936758,
+      "grad_norm": 3576.093505859375,
+      "learning_rate": 0.0009400630914826499,
+      "loss": 0.6717,
+      "mean_token_accuracy": 0.8245183542370796,
+      "num_tokens": 1210060.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.4919601235538721,
+      "epoch": 0.09486166007905138,
+      "grad_norm": 462362592.0,
+      "learning_rate": 0.0009085173501577287,
+      "loss": 0.6075,
+      "mean_token_accuracy": 0.8355057552456856,
+      "num_tokens": 1815732.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.45399096198379996,
+      "epoch": 0.12648221343873517,
+      "grad_norm": 48967.296875,
+      "learning_rate": 0.0008769716088328076,
+      "loss": 0.6877,
+      "mean_token_accuracy": 0.8247161574661732,
+      "num_tokens": 2372291.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.5189430050551891,
+      "epoch": 0.15810276679841898,
+      "grad_norm": 20488920.0,
+      "learning_rate": 0.0008454258675078864,
+      "loss": 0.6631,
+      "mean_token_accuracy": 0.8253108873963356,
+      "num_tokens": 2970656.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.5161575745791197,
+      "epoch": 0.18972332015810275,
+      "grad_norm": 11390319.0,
+      "learning_rate": 0.0008138801261829653,
+      "loss": 0.5682,
+      "mean_token_accuracy": 0.8430261947214603,
+      "num_tokens": 3561312.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.5097578268498182,
+      "epoch": 0.22134387351778656,
+      "grad_norm": 5408220.5,
+      "learning_rate": 0.0007823343848580442,
+      "loss": 0.598,
+      "mean_token_accuracy": 0.8383074931800365,
+      "num_tokens": 4164666.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.561078536324203,
+      "epoch": 0.25296442687747034,
+      "grad_norm": 3655628.0,
+      "learning_rate": 0.000750788643533123,
+      "loss": 0.5818,
+      "mean_token_accuracy": 0.8375455126166343,
+      "num_tokens": 4750115.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.6730448313057422,
+      "epoch": 0.2845849802371542,
+      "grad_norm": 65684.3125,
+      "learning_rate": 0.0007192429022082018,
+      "loss": 0.6005,
+      "mean_token_accuracy": 0.8356033861637115,
+      "num_tokens": 5290377.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.68943473957479,
+      "epoch": 0.31620553359683795,
+      "grad_norm": 18166769664.0,
+      "learning_rate": 0.0006876971608832808,
+      "loss": 0.6068,
+      "mean_token_accuracy": 0.8362394802272319,
+      "num_tokens": 5882068.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.7109859976917505,
+      "epoch": 0.34782608695652173,
+      "grad_norm": 4711626.5,
+      "learning_rate": 0.0006561514195583596,
+      "loss": 0.6385,
+      "mean_token_accuracy": 0.829913080483675,
+      "num_tokens": 6480962.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.6261379970237613,
+      "epoch": 0.3794466403162055,
+      "grad_norm": 1412058496.0,
+      "learning_rate": 0.0006246056782334385,
+      "loss": 0.5727,
+      "mean_token_accuracy": 0.8403497040271759,
+      "num_tokens": 7080708.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.6068891424685716,
+      "epoch": 0.41106719367588934,
+      "grad_norm": 3915769.0,
+      "learning_rate": 0.0005930599369085173,
+      "loss": 0.5622,
+      "mean_token_accuracy": 0.8430461063981056,
+      "num_tokens": 7692408.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.6536903701722622,
+      "epoch": 0.4426877470355731,
+      "grad_norm": 1457204.375,
+      "learning_rate": 0.0005615141955835961,
+      "loss": 0.6043,
+      "mean_token_accuracy": 0.833759855479002,
+      "num_tokens": 8329614.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.646093986183405,
+      "epoch": 0.4743083003952569,
+      "grad_norm": 96467.4765625,
+      "learning_rate": 0.0005299684542586751,
+      "loss": 0.6169,
+      "mean_token_accuracy": 0.8327336788177491,
+      "num_tokens": 8933829.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.5853382866829634,
+      "epoch": 0.5059288537549407,
+      "grad_norm": 3098197.5,
+      "learning_rate": 0.000498422712933754,
+      "loss": 0.5469,
+      "mean_token_accuracy": 0.8443389609456062,
+      "num_tokens": 9522595.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.5903366718441247,
+      "epoch": 0.5375494071146245,
+      "grad_norm": 42660388.0,
+      "learning_rate": 0.0004668769716088328,
+      "loss": 0.604,
+      "mean_token_accuracy": 0.8362459398806095,
+      "num_tokens": 10143758.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.6122400458902121,
+      "epoch": 0.5691699604743083,
+      "grad_norm": 757395008.0,
+      "learning_rate": 0.0004353312302839117,
+      "loss": 0.6429,
+      "mean_token_accuracy": 0.8282213471829891,
+      "num_tokens": 10692662.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.7004607111215592,
+      "epoch": 0.6007905138339921,
+      "grad_norm": 316442400.0,
+      "learning_rate": 0.0004037854889589905,
+      "loss": 0.6737,
+      "mean_token_accuracy": 0.8188323535025119,
+      "num_tokens": 11286778.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.6795283857733011,
+      "epoch": 0.6324110671936759,
+      "grad_norm": 19859658752.0,
+      "learning_rate": 0.0003722397476340694,
+      "loss": 0.6629,
+      "mean_token_accuracy": 0.8223141871392727,
+      "num_tokens": 11910969.0,
+      "step": 200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 317,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.3350988058451845e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-200/training_args.bin b/checkpoint-200/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..120f85ab118be2c00862d7334c96dd25039dfeea
--- /dev/null
+++ b/checkpoint-200/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bad5302c07edbe0267e2b38e65245429ed8bff1dce0fb4fc7af4aef2083cf5b
+size 5880
diff --git a/checkpoint-250/README.md b/checkpoint-250/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..235c2e6ff7d5d996be0c01802fa2d7707c43b969
--- /dev/null
+++ b/checkpoint-250/README.md
@@ -0,0 +1,209 @@
+---
+base_model: zai-org/GLM-4-32B-0414
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:zai-org/GLM-4-32B-0414
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.17.1
\ No newline at end of file
diff --git a/checkpoint-250/adapter_config.json b/checkpoint-250/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f0ebe86d1363a1171c6cd0dcf67ad18fa37c9f85
--- /dev/null
+++ b/checkpoint-250/adapter_config.json
@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "zai-org/GLM-4-32B-0414",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-250/adapter_model.safetensors b/checkpoint-250/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..21830f9cbae1d6ad6793017a5e41dceeb9a0d3f1
--- /dev/null
+++ b/checkpoint-250/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a08d60566d33dbc37e640ce49300f3bf1d9b9b22cb005d697b873b3f8e7bee3c
+size 4157688432
diff --git a/checkpoint-250/chat_template.jinja b/checkpoint-250/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..fdd583731de8bdf1830d38a3e34f7cd8f80605dd
--- /dev/null
+++ b/checkpoint-250/chat_template.jinja
@@ -0,0 +1,41 @@
+[gMASK]<sop>
+{%- if tools -%}
+<|system|>
+# 可用工具
+{% for tool in tools %}
+    {%- set function = tool.function if tool.get("function") else tool %}
+
+## {{ function.name }}
+
+{{ function | tojson(indent=4, ensure_ascii=False) }}
+在调用上述函数时，请使用 Json 格式表示调用的参数。
+{%- endfor %}
+{%- endif -%}
+
+{%- for msg in messages %}
+    {%- if msg.role == 'system' %}
+<|system|>
+{{ msg.content }}
+    {%- endif %}
+{%- endfor %}
+
+{%- for message in messages if message.role != 'system' %}
+    {%- set role = message['role'] %}
+    {%- set content = message['content'] %}
+    {%- set meta = message.get("metadata", "") %}
+
+    {%- if role == 'user' %}
+<|user|>
+{{ content }}
+    {%- elif role == 'assistant' and not meta %}
+<|assistant|>
+{{ content }}
+    {%- elif role == 'assistant' and meta %}
+<|assistant|>{{ meta }}
+{{ content }}
+    {%- elif role == 'observation' %}
+<|observation|>
+{{ content }}
+    {%- endif %}
+{%- endfor %}
+{% if add_generation_prompt %}<|assistant|>{% endif %}
\ No newline at end of file
diff --git a/checkpoint-250/optimizer.pt b/checkpoint-250/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..647ac8792d024fad024fa9d150aceffc4fac3d8f
--- /dev/null
+++ b/checkpoint-250/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00d691beb57ed010bd1715b1f65fb9839c6a7ad1bc55782f5be99f049989cd14
+size 8315744524
diff --git a/checkpoint-250/rng_state.pth b/checkpoint-250/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..93a52228ea16468eaab41b66555ced3eaaea002c
--- /dev/null
+++ b/checkpoint-250/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244
diff --git a/checkpoint-250/scheduler.pt b/checkpoint-250/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4692a0a0ab88ee21ae7fd5d776ad21cf7bbeed7e
--- /dev/null
+++ b/checkpoint-250/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0312fddf7060481c73cb2a1291fdb26851aa4d528ad7c394a28b2a0b83a65101
+size 1064
diff --git a/checkpoint-250/special_tokens_map.json b/checkpoint-250/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..3cf953c2c8a3c89778c92e54c685942bb1130616
--- /dev/null
+++ b/checkpoint-250/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": "<|user|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-250/tokenizer.json b/checkpoint-250/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..4d1dde37a2715c11628fc84bf571976f9f80eb69
--- /dev/null
+++ b/checkpoint-250/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76ebeac0d8bd7879ead7b43c16b44981f277e47225de2bd7de9ae1a6cc664a8c
+size 19966496
diff --git a/checkpoint-250/tokenizer_config.json b/checkpoint-250/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d690b31eb34e3d9741aff67b37e0ecda2604739b
--- /dev/null
+++ b/checkpoint-250/tokenizer_config.json
@@ -0,0 +1,145 @@
+{
+  "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|>"
+  ],
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "<|user|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 128000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "remove_space": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}
diff --git a/checkpoint-250/trainer_state.json b/checkpoint-250/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..dcd62f926e7d4e3bdf85eb83a1b51809748d992c
--- /dev/null
+++ b/checkpoint-250/trainer_state.json
@@ -0,0 +1,284 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.7905138339920948,
+  "eval_steps": 500,
+  "global_step": 250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.5656170375645161,
+      "epoch": 0.03162055335968379,
+      "grad_norm": 487949.625,
+      "learning_rate": 0.000971608832807571,
+      "loss": 0.598,
+      "mean_token_accuracy": 0.8383935391902924,
+      "num_tokens": 611773.0,
+      "step": 10
+    },
+    {
+      "entropy": 0.5844515649601817,
+      "epoch": 0.06324110671936758,
+      "grad_norm": 3576.093505859375,
+      "learning_rate": 0.0009400630914826499,
+      "loss": 0.6717,
+      "mean_token_accuracy": 0.8245183542370796,
+      "num_tokens": 1210060.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.4919601235538721,
+      "epoch": 0.09486166007905138,
+      "grad_norm": 462362592.0,
+      "learning_rate": 0.0009085173501577287,
+      "loss": 0.6075,
+      "mean_token_accuracy": 0.8355057552456856,
+      "num_tokens": 1815732.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.45399096198379996,
+      "epoch": 0.12648221343873517,
+      "grad_norm": 48967.296875,
+      "learning_rate": 0.0008769716088328076,
+      "loss": 0.6877,
+      "mean_token_accuracy": 0.8247161574661732,
+      "num_tokens": 2372291.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.5189430050551891,
+      "epoch": 0.15810276679841898,
+      "grad_norm": 20488920.0,
+      "learning_rate": 0.0008454258675078864,
+      "loss": 0.6631,
+      "mean_token_accuracy": 0.8253108873963356,
+      "num_tokens": 2970656.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.5161575745791197,
+      "epoch": 0.18972332015810275,
+      "grad_norm": 11390319.0,
+      "learning_rate": 0.0008138801261829653,
+      "loss": 0.5682,
+      "mean_token_accuracy": 0.8430261947214603,
+      "num_tokens": 3561312.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.5097578268498182,
+      "epoch": 0.22134387351778656,
+      "grad_norm": 5408220.5,
+      "learning_rate": 0.0007823343848580442,
+      "loss": 0.598,
+      "mean_token_accuracy": 0.8383074931800365,
+      "num_tokens": 4164666.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.561078536324203,
+      "epoch": 0.25296442687747034,
+      "grad_norm": 3655628.0,
+      "learning_rate": 0.000750788643533123,
+      "loss": 0.5818,
+      "mean_token_accuracy": 0.8375455126166343,
+      "num_tokens": 4750115.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.6730448313057422,
+      "epoch": 0.2845849802371542,
+      "grad_norm": 65684.3125,
+      "learning_rate": 0.0007192429022082018,
+      "loss": 0.6005,
+      "mean_token_accuracy": 0.8356033861637115,
+      "num_tokens": 5290377.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.68943473957479,
+      "epoch": 0.31620553359683795,
+      "grad_norm": 18166769664.0,
+      "learning_rate": 0.0006876971608832808,
+      "loss": 0.6068,
+      "mean_token_accuracy": 0.8362394802272319,
+      "num_tokens": 5882068.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.7109859976917505,
+      "epoch": 0.34782608695652173,
+      "grad_norm": 4711626.5,
+      "learning_rate": 0.0006561514195583596,
+      "loss": 0.6385,
+      "mean_token_accuracy": 0.829913080483675,
+      "num_tokens": 6480962.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.6261379970237613,
+      "epoch": 0.3794466403162055,
+      "grad_norm": 1412058496.0,
+      "learning_rate": 0.0006246056782334385,
+      "loss": 0.5727,
+      "mean_token_accuracy": 0.8403497040271759,
+      "num_tokens": 7080708.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.6068891424685716,
+      "epoch": 0.41106719367588934,
+      "grad_norm": 3915769.0,
+      "learning_rate": 0.0005930599369085173,
+      "loss": 0.5622,
+      "mean_token_accuracy": 0.8430461063981056,
+      "num_tokens": 7692408.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.6536903701722622,
+      "epoch": 0.4426877470355731,
+      "grad_norm": 1457204.375,
+      "learning_rate": 0.0005615141955835961,
+      "loss": 0.6043,
+      "mean_token_accuracy": 0.833759855479002,
+      "num_tokens": 8329614.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.646093986183405,
+      "epoch": 0.4743083003952569,
+      "grad_norm": 96467.4765625,
+      "learning_rate": 0.0005299684542586751,
+      "loss": 0.6169,
+      "mean_token_accuracy": 0.8327336788177491,
+      "num_tokens": 8933829.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.5853382866829634,
+      "epoch": 0.5059288537549407,
+      "grad_norm": 3098197.5,
+      "learning_rate": 0.000498422712933754,
+      "loss": 0.5469,
+      "mean_token_accuracy": 0.8443389609456062,
+      "num_tokens": 9522595.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.5903366718441247,
+      "epoch": 0.5375494071146245,
+      "grad_norm": 42660388.0,
+      "learning_rate": 0.0004668769716088328,
+      "loss": 0.604,
+      "mean_token_accuracy": 0.8362459398806095,
+      "num_tokens": 10143758.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.6122400458902121,
+      "epoch": 0.5691699604743083,
+      "grad_norm": 757395008.0,
+      "learning_rate": 0.0004353312302839117,
+      "loss": 0.6429,
+      "mean_token_accuracy": 0.8282213471829891,
+      "num_tokens": 10692662.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.7004607111215592,
+      "epoch": 0.6007905138339921,
+      "grad_norm": 316442400.0,
+      "learning_rate": 0.0004037854889589905,
+      "loss": 0.6737,
+      "mean_token_accuracy": 0.8188323535025119,
+      "num_tokens": 11286778.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.6795283857733011,
+      "epoch": 0.6324110671936759,
+      "grad_norm": 19859658752.0,
+      "learning_rate": 0.0003722397476340694,
+      "loss": 0.6629,
+      "mean_token_accuracy": 0.8223141871392727,
+      "num_tokens": 11910969.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.6172661986202002,
+      "epoch": 0.6640316205533597,
+      "grad_norm": 596563.25,
+      "learning_rate": 0.00034069400630914825,
+      "loss": 0.6219,
+      "mean_token_accuracy": 0.8312948845326901,
+      "num_tokens": 12506898.0,
+      "step": 210
+    },
+    {
+      "entropy": 0.5889476146548986,
+      "epoch": 0.6956521739130435,
+      "grad_norm": 38292772.0,
+      "learning_rate": 0.00030914826498422714,
+      "loss": 0.6256,
+      "mean_token_accuracy": 0.833721686899662,
+      "num_tokens": 13097833.0,
+      "step": 220
+    },
+    {
+      "entropy": 0.5375086467713117,
+      "epoch": 0.7272727272727273,
+      "grad_norm": 7002747.5,
+      "learning_rate": 0.00027760252365930597,
+      "loss": 0.5423,
+      "mean_token_accuracy": 0.8461122632026672,
+      "num_tokens": 13690464.0,
+      "step": 230
+    },
+    {
+      "entropy": 0.5905131205916405,
+      "epoch": 0.758893280632411,
+      "grad_norm": 4201593.0,
+      "learning_rate": 0.00024605678233438486,
+      "loss": 0.5946,
+      "mean_token_accuracy": 0.8356382519006729,
+      "num_tokens": 14269150.0,
+      "step": 240
+    },
+    {
+      "entropy": 0.553895766660571,
+      "epoch": 0.7905138339920948,
+      "grad_norm": 7530.97509765625,
+      "learning_rate": 0.00021451104100946372,
+      "loss": 0.5512,
+      "mean_token_accuracy": 0.8458476938307286,
+      "num_tokens": 14877904.0,
+      "step": 250
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 317,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.9167547882862674e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-250/training_args.bin b/checkpoint-250/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..120f85ab118be2c00862d7334c96dd25039dfeea
--- /dev/null
+++ b/checkpoint-250/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bad5302c07edbe0267e2b38e65245429ed8bff1dce0fb4fc7af4aef2083cf5b
+size 5880
diff --git a/checkpoint-300/README.md b/checkpoint-300/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..235c2e6ff7d5d996be0c01802fa2d7707c43b969
--- /dev/null
+++ b/checkpoint-300/README.md
@@ -0,0 +1,209 @@
+---
+base_model: zai-org/GLM-4-32B-0414
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:zai-org/GLM-4-32B-0414
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.17.1
\ No newline at end of file
diff --git a/checkpoint-300/adapter_config.json b/checkpoint-300/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f0ebe86d1363a1171c6cd0dcf67ad18fa37c9f85
--- /dev/null
+++ b/checkpoint-300/adapter_config.json
@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "zai-org/GLM-4-32B-0414",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-300/adapter_model.safetensors b/checkpoint-300/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..42a96ecea97520b64919c6d3ad787c32c07fcdb2
--- /dev/null
+++ b/checkpoint-300/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dacad7e648d2e356cf5f7410762ca618857405654e5a0afa2781e629eb1f9efb
+size 4157688432
diff --git a/checkpoint-300/chat_template.jinja b/checkpoint-300/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..fdd583731de8bdf1830d38a3e34f7cd8f80605dd
--- /dev/null
+++ b/checkpoint-300/chat_template.jinja
@@ -0,0 +1,41 @@
+[gMASK]<sop>
+{%- if tools -%}
+<|system|>
+# 可用工具
+{% for tool in tools %}
+    {%- set function = tool.function if tool.get("function") else tool %}
+
+## {{ function.name }}
+
+{{ function | tojson(indent=4, ensure_ascii=False) }}
+在调用上述函数时，请使用 Json 格式表示调用的参数。
+{%- endfor %}
+{%- endif -%}
+
+{%- for msg in messages %}
+    {%- if msg.role == 'system' %}
+<|system|>
+{{ msg.content }}
+    {%- endif %}
+{%- endfor %}
+
+{%- for message in messages if message.role != 'system' %}
+    {%- set role = message['role'] %}
+    {%- set content = message['content'] %}
+    {%- set meta = message.get("metadata", "") %}
+
+    {%- if role == 'user' %}
+<|user|>
+{{ content }}
+    {%- elif role == 'assistant' and not meta %}
+<|assistant|>
+{{ content }}
+    {%- elif role == 'assistant' and meta %}
+<|assistant|>{{ meta }}
+{{ content }}
+    {%- elif role == 'observation' %}
+<|observation|>
+{{ content }}
+    {%- endif %}
+{%- endfor %}
+{% if add_generation_prompt %}<|assistant|>{% endif %}
\ No newline at end of file
diff --git a/checkpoint-300/optimizer.pt b/checkpoint-300/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2501924a662dbbfb0359359731a23aa517ea92e7
--- /dev/null
+++ b/checkpoint-300/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3333bf5f531f60a6fc3d740ab135365c6df439918937a954bfe5193cdc0f2410
+size 8315744524
diff --git a/checkpoint-300/rng_state.pth b/checkpoint-300/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..93a52228ea16468eaab41b66555ced3eaaea002c
--- /dev/null
+++ b/checkpoint-300/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244
diff --git a/checkpoint-300/scheduler.pt b/checkpoint-300/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5b3e9b9e5fad1c054f0626489f3f4fbeed34dd83
--- /dev/null
+++ b/checkpoint-300/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8b6009fc7186316152f008e93444f14b13a9bc780422a9a3551f8a4615e2a8f
+size 1064
diff --git a/checkpoint-300/special_tokens_map.json b/checkpoint-300/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..3cf953c2c8a3c89778c92e54c685942bb1130616
--- /dev/null
+++ b/checkpoint-300/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": "<|user|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-300/tokenizer.json b/checkpoint-300/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..4d1dde37a2715c11628fc84bf571976f9f80eb69
--- /dev/null
+++ b/checkpoint-300/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76ebeac0d8bd7879ead7b43c16b44981f277e47225de2bd7de9ae1a6cc664a8c
+size 19966496
diff --git a/checkpoint-300/tokenizer_config.json b/checkpoint-300/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d690b31eb34e3d9741aff67b37e0ecda2604739b
--- /dev/null
+++ b/checkpoint-300/tokenizer_config.json
@@ -0,0 +1,145 @@
+{
+  "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|>"
+  ],
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "<|user|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 128000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "remove_space": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}
diff --git a/checkpoint-300/trainer_state.json b/checkpoint-300/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..3902a72dcdb56f1c572d12e39feef2d24121a58d
--- /dev/null
+++ b/checkpoint-300/trainer_state.json
@@ -0,0 +1,334 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9486166007905138,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.5656170375645161,
+      "epoch": 0.03162055335968379,
+      "grad_norm": 487949.625,
+      "learning_rate": 0.000971608832807571,
+      "loss": 0.598,
+      "mean_token_accuracy": 0.8383935391902924,
+      "num_tokens": 611773.0,
+      "step": 10
+    },
+    {
+      "entropy": 0.5844515649601817,
+      "epoch": 0.06324110671936758,
+      "grad_norm": 3576.093505859375,
+      "learning_rate": 0.0009400630914826499,
+      "loss": 0.6717,
+      "mean_token_accuracy": 0.8245183542370796,
+      "num_tokens": 1210060.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.4919601235538721,
+      "epoch": 0.09486166007905138,
+      "grad_norm": 462362592.0,
+      "learning_rate": 0.0009085173501577287,
+      "loss": 0.6075,
+      "mean_token_accuracy": 0.8355057552456856,
+      "num_tokens": 1815732.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.45399096198379996,
+      "epoch": 0.12648221343873517,
+      "grad_norm": 48967.296875,
+      "learning_rate": 0.0008769716088328076,
+      "loss": 0.6877,
+      "mean_token_accuracy": 0.8247161574661732,
+      "num_tokens": 2372291.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.5189430050551891,
+      "epoch": 0.15810276679841898,
+      "grad_norm": 20488920.0,
+      "learning_rate": 0.0008454258675078864,
+      "loss": 0.6631,
+      "mean_token_accuracy": 0.8253108873963356,
+      "num_tokens": 2970656.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.5161575745791197,
+      "epoch": 0.18972332015810275,
+      "grad_norm": 11390319.0,
+      "learning_rate": 0.0008138801261829653,
+      "loss": 0.5682,
+      "mean_token_accuracy": 0.8430261947214603,
+      "num_tokens": 3561312.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.5097578268498182,
+      "epoch": 0.22134387351778656,
+      "grad_norm": 5408220.5,
+      "learning_rate": 0.0007823343848580442,
+      "loss": 0.598,
+      "mean_token_accuracy": 0.8383074931800365,
+      "num_tokens": 4164666.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.561078536324203,
+      "epoch": 0.25296442687747034,
+      "grad_norm": 3655628.0,
+      "learning_rate": 0.000750788643533123,
+      "loss": 0.5818,
+      "mean_token_accuracy": 0.8375455126166343,
+      "num_tokens": 4750115.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.6730448313057422,
+      "epoch": 0.2845849802371542,
+      "grad_norm": 65684.3125,
+      "learning_rate": 0.0007192429022082018,
+      "loss": 0.6005,
+      "mean_token_accuracy": 0.8356033861637115,
+      "num_tokens": 5290377.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.68943473957479,
+      "epoch": 0.31620553359683795,
+      "grad_norm": 18166769664.0,
+      "learning_rate": 0.0006876971608832808,
+      "loss": 0.6068,
+      "mean_token_accuracy": 0.8362394802272319,
+      "num_tokens": 5882068.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.7109859976917505,
+      "epoch": 0.34782608695652173,
+      "grad_norm": 4711626.5,
+      "learning_rate": 0.0006561514195583596,
+      "loss": 0.6385,
+      "mean_token_accuracy": 0.829913080483675,
+      "num_tokens": 6480962.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.6261379970237613,
+      "epoch": 0.3794466403162055,
+      "grad_norm": 1412058496.0,
+      "learning_rate": 0.0006246056782334385,
+      "loss": 0.5727,
+      "mean_token_accuracy": 0.8403497040271759,
+      "num_tokens": 7080708.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.6068891424685716,
+      "epoch": 0.41106719367588934,
+      "grad_norm": 3915769.0,
+      "learning_rate": 0.0005930599369085173,
+      "loss": 0.5622,
+      "mean_token_accuracy": 0.8430461063981056,
+      "num_tokens": 7692408.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.6536903701722622,
+      "epoch": 0.4426877470355731,
+      "grad_norm": 1457204.375,
+      "learning_rate": 0.0005615141955835961,
+      "loss": 0.6043,
+      "mean_token_accuracy": 0.833759855479002,
+      "num_tokens": 8329614.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.646093986183405,
+      "epoch": 0.4743083003952569,
+      "grad_norm": 96467.4765625,
+      "learning_rate": 0.0005299684542586751,
+      "loss": 0.6169,
+      "mean_token_accuracy": 0.8327336788177491,
+      "num_tokens": 8933829.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.5853382866829634,
+      "epoch": 0.5059288537549407,
+      "grad_norm": 3098197.5,
+      "learning_rate": 0.000498422712933754,
+      "loss": 0.5469,
+      "mean_token_accuracy": 0.8443389609456062,
+      "num_tokens": 9522595.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.5903366718441247,
+      "epoch": 0.5375494071146245,
+      "grad_norm": 42660388.0,
+      "learning_rate": 0.0004668769716088328,
+      "loss": 0.604,
+      "mean_token_accuracy": 0.8362459398806095,
+      "num_tokens": 10143758.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.6122400458902121,
+      "epoch": 0.5691699604743083,
+      "grad_norm": 757395008.0,
+      "learning_rate": 0.0004353312302839117,
+      "loss": 0.6429,
+      "mean_token_accuracy": 0.8282213471829891,
+      "num_tokens": 10692662.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.7004607111215592,
+      "epoch": 0.6007905138339921,
+      "grad_norm": 316442400.0,
+      "learning_rate": 0.0004037854889589905,
+      "loss": 0.6737,
+      "mean_token_accuracy": 0.8188323535025119,
+      "num_tokens": 11286778.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.6795283857733011,
+      "epoch": 0.6324110671936759,
+      "grad_norm": 19859658752.0,
+      "learning_rate": 0.0003722397476340694,
+      "loss": 0.6629,
+      "mean_token_accuracy": 0.8223141871392727,
+      "num_tokens": 11910969.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.6172661986202002,
+      "epoch": 0.6640316205533597,
+      "grad_norm": 596563.25,
+      "learning_rate": 0.00034069400630914825,
+      "loss": 0.6219,
+      "mean_token_accuracy": 0.8312948845326901,
+      "num_tokens": 12506898.0,
+      "step": 210
+    },
+    {
+      "entropy": 0.5889476146548986,
+      "epoch": 0.6956521739130435,
+      "grad_norm": 38292772.0,
+      "learning_rate": 0.00030914826498422714,
+      "loss": 0.6256,
+      "mean_token_accuracy": 0.833721686899662,
+      "num_tokens": 13097833.0,
+      "step": 220
+    },
+    {
+      "entropy": 0.5375086467713117,
+      "epoch": 0.7272727272727273,
+      "grad_norm": 7002747.5,
+      "learning_rate": 0.00027760252365930597,
+      "loss": 0.5423,
+      "mean_token_accuracy": 0.8461122632026672,
+      "num_tokens": 13690464.0,
+      "step": 230
+    },
+    {
+      "entropy": 0.5905131205916405,
+      "epoch": 0.758893280632411,
+      "grad_norm": 4201593.0,
+      "learning_rate": 0.00024605678233438486,
+      "loss": 0.5946,
+      "mean_token_accuracy": 0.8356382519006729,
+      "num_tokens": 14269150.0,
+      "step": 240
+    },
+    {
+      "entropy": 0.553895766660571,
+      "epoch": 0.7905138339920948,
+      "grad_norm": 7530.97509765625,
+      "learning_rate": 0.00021451104100946372,
+      "loss": 0.5512,
+      "mean_token_accuracy": 0.8458476938307286,
+      "num_tokens": 14877904.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.6424776270985604,
+      "epoch": 0.8221343873517787,
+      "grad_norm": 30025678.0,
+      "learning_rate": 0.00018296529968454258,
+      "loss": 0.6752,
+      "mean_token_accuracy": 0.8269011005759239,
+      "num_tokens": 15470400.0,
+      "step": 260
+    },
+    {
+      "entropy": 0.6024509601294994,
+      "epoch": 0.8537549407114624,
+      "grad_norm": 179891.234375,
+      "learning_rate": 0.00015141955835962145,
+      "loss": 0.6077,
+      "mean_token_accuracy": 0.8359923847019672,
+      "num_tokens": 16078040.0,
+      "step": 270
+    },
+    {
+      "entropy": 0.6116770006716251,
+      "epoch": 0.8853754940711462,
+      "grad_norm": 43860216.0,
+      "learning_rate": 0.00011987381703470032,
+      "loss": 0.6142,
+      "mean_token_accuracy": 0.8328806236386299,
+      "num_tokens": 16666971.0,
+      "step": 280
+    },
+    {
+      "entropy": 0.593284934386611,
+      "epoch": 0.9169960474308301,
+      "grad_norm": 2078294.875,
+      "learning_rate": 8.832807570977918e-05,
+      "loss": 0.6079,
+      "mean_token_accuracy": 0.8367695853114128,
+      "num_tokens": 17271306.0,
+      "step": 290
+    },
+    {
+      "entropy": 0.5837210457772016,
+      "epoch": 0.9486166007905138,
+      "grad_norm": 2131766.0,
+      "learning_rate": 5.6782334384858046e-05,
+      "loss": 0.5676,
+      "mean_token_accuracy": 0.8406473062932491,
+      "num_tokens": 17878825.0,
+      "step": 300
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 317,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.5050735928718336e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-300/training_args.bin b/checkpoint-300/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..120f85ab118be2c00862d7334c96dd25039dfeea
--- /dev/null
+++ b/checkpoint-300/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bad5302c07edbe0267e2b38e65245429ed8bff1dce0fb4fc7af4aef2083cf5b
+size 5880
diff --git a/checkpoint-317/README.md b/checkpoint-317/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..235c2e6ff7d5d996be0c01802fa2d7707c43b969
--- /dev/null
+++ b/checkpoint-317/README.md
@@ -0,0 +1,209 @@
+---
+base_model: zai-org/GLM-4-32B-0414
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:zai-org/GLM-4-32B-0414
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.17.1
\ No newline at end of file
diff --git a/checkpoint-317/adapter_config.json b/checkpoint-317/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f0ebe86d1363a1171c6cd0dcf67ad18fa37c9f85
--- /dev/null
+++ b/checkpoint-317/adapter_config.json
@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "zai-org/GLM-4-32B-0414",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-317/adapter_model.safetensors b/checkpoint-317/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b59a542639a167049f8305880161855fb8df2bc6
--- /dev/null
+++ b/checkpoint-317/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0449cadcb46edd1c553d548c9e5994006bddec56295db09c6773bfb8407c8b75
+size 4157688432
diff --git a/checkpoint-317/chat_template.jinja b/checkpoint-317/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..fdd583731de8bdf1830d38a3e34f7cd8f80605dd
--- /dev/null
+++ b/checkpoint-317/chat_template.jinja
@@ -0,0 +1,41 @@
+[gMASK]<sop>
+{%- if tools -%}
+<|system|>
+# 可用工具
+{% for tool in tools %}
+    {%- set function = tool.function if tool.get("function") else tool %}
+
+## {{ function.name }}
+
+{{ function | tojson(indent=4, ensure_ascii=False) }}
+在调用上述函数时，请使用 Json 格式表示调用的参数。
+{%- endfor %}
+{%- endif -%}
+
+{%- for msg in messages %}
+    {%- if msg.role == 'system' %}
+<|system|>
+{{ msg.content }}
+    {%- endif %}
+{%- endfor %}
+
+{%- for message in messages if message.role != 'system' %}
+    {%- set role = message['role'] %}
+    {%- set content = message['content'] %}
+    {%- set meta = message.get("metadata", "") %}
+
+    {%- if role == 'user' %}
+<|user|>
+{{ content }}
+    {%- elif role == 'assistant' and not meta %}
+<|assistant|>
+{{ content }}
+    {%- elif role == 'assistant' and meta %}
+<|assistant|>{{ meta }}
+{{ content }}
+    {%- elif role == 'observation' %}
+<|observation|>
+{{ content }}
+    {%- endif %}
+{%- endfor %}
+{% if add_generation_prompt %}<|assistant|>{% endif %}
\ No newline at end of file
diff --git a/checkpoint-317/optimizer.pt b/checkpoint-317/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6681cdcba292dc574d55258541a9f28730dc6a81
--- /dev/null
+++ b/checkpoint-317/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:babbff104872058ce9f0dbaef97484e24519b4b4156a974f734f6f05f9cd76fd
+size 8315744524
diff --git a/checkpoint-317/rng_state.pth b/checkpoint-317/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..93a52228ea16468eaab41b66555ced3eaaea002c
--- /dev/null
+++ b/checkpoint-317/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244
diff --git a/checkpoint-317/scheduler.pt b/checkpoint-317/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4317cc47a2228463b9db3c973c24f7d7decfe1c5
--- /dev/null
+++ b/checkpoint-317/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15d705da2903d14f5fb7a6e8985263984e21045c6722f90267e9774272447190
+size 1064
diff --git a/checkpoint-317/special_tokens_map.json b/checkpoint-317/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..3cf953c2c8a3c89778c92e54c685942bb1130616
--- /dev/null
+++ b/checkpoint-317/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": "<|user|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-317/tokenizer.json b/checkpoint-317/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..4d1dde37a2715c11628fc84bf571976f9f80eb69
--- /dev/null
+++ b/checkpoint-317/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76ebeac0d8bd7879ead7b43c16b44981f277e47225de2bd7de9ae1a6cc664a8c
+size 19966496
diff --git a/checkpoint-317/tokenizer_config.json b/checkpoint-317/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d690b31eb34e3d9741aff67b37e0ecda2604739b
--- /dev/null
+++ b/checkpoint-317/tokenizer_config.json
@@ -0,0 +1,145 @@
+{
+  "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|>"
+  ],
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "<|user|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 128000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "remove_space": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}
diff --git a/checkpoint-317/trainer_state.json b/checkpoint-317/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..6f236338799047bd16ab007ae583935c4cf4440c
--- /dev/null
+++ b/checkpoint-317/trainer_state.json
@@ -0,0 +1,344 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 317,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.5656170375645161,
+      "epoch": 0.03162055335968379,
+      "grad_norm": 487949.625,
+      "learning_rate": 0.000971608832807571,
+      "loss": 0.598,
+      "mean_token_accuracy": 0.8383935391902924,
+      "num_tokens": 611773.0,
+      "step": 10
+    },
+    {
+      "entropy": 0.5844515649601817,
+      "epoch": 0.06324110671936758,
+      "grad_norm": 3576.093505859375,
+      "learning_rate": 0.0009400630914826499,
+      "loss": 0.6717,
+      "mean_token_accuracy": 0.8245183542370796,
+      "num_tokens": 1210060.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.4919601235538721,
+      "epoch": 0.09486166007905138,
+      "grad_norm": 462362592.0,
+      "learning_rate": 0.0009085173501577287,
+      "loss": 0.6075,
+      "mean_token_accuracy": 0.8355057552456856,
+      "num_tokens": 1815732.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.45399096198379996,
+      "epoch": 0.12648221343873517,
+      "grad_norm": 48967.296875,
+      "learning_rate": 0.0008769716088328076,
+      "loss": 0.6877,
+      "mean_token_accuracy": 0.8247161574661732,
+      "num_tokens": 2372291.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.5189430050551891,
+      "epoch": 0.15810276679841898,
+      "grad_norm": 20488920.0,
+      "learning_rate": 0.0008454258675078864,
+      "loss": 0.6631,
+      "mean_token_accuracy": 0.8253108873963356,
+      "num_tokens": 2970656.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.5161575745791197,
+      "epoch": 0.18972332015810275,
+      "grad_norm": 11390319.0,
+      "learning_rate": 0.0008138801261829653,
+      "loss": 0.5682,
+      "mean_token_accuracy": 0.8430261947214603,
+      "num_tokens": 3561312.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.5097578268498182,
+      "epoch": 0.22134387351778656,
+      "grad_norm": 5408220.5,
+      "learning_rate": 0.0007823343848580442,
+      "loss": 0.598,
+      "mean_token_accuracy": 0.8383074931800365,
+      "num_tokens": 4164666.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.561078536324203,
+      "epoch": 0.25296442687747034,
+      "grad_norm": 3655628.0,
+      "learning_rate": 0.000750788643533123,
+      "loss": 0.5818,
+      "mean_token_accuracy": 0.8375455126166343,
+      "num_tokens": 4750115.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.6730448313057422,
+      "epoch": 0.2845849802371542,
+      "grad_norm": 65684.3125,
+      "learning_rate": 0.0007192429022082018,
+      "loss": 0.6005,
+      "mean_token_accuracy": 0.8356033861637115,
+      "num_tokens": 5290377.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.68943473957479,
+      "epoch": 0.31620553359683795,
+      "grad_norm": 18166769664.0,
+      "learning_rate": 0.0006876971608832808,
+      "loss": 0.6068,
+      "mean_token_accuracy": 0.8362394802272319,
+      "num_tokens": 5882068.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.7109859976917505,
+      "epoch": 0.34782608695652173,
+      "grad_norm": 4711626.5,
+      "learning_rate": 0.0006561514195583596,
+      "loss": 0.6385,
+      "mean_token_accuracy": 0.829913080483675,
+      "num_tokens": 6480962.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.6261379970237613,
+      "epoch": 0.3794466403162055,
+      "grad_norm": 1412058496.0,
+      "learning_rate": 0.0006246056782334385,
+      "loss": 0.5727,
+      "mean_token_accuracy": 0.8403497040271759,
+      "num_tokens": 7080708.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.6068891424685716,
+      "epoch": 0.41106719367588934,
+      "grad_norm": 3915769.0,
+      "learning_rate": 0.0005930599369085173,
+      "loss": 0.5622,
+      "mean_token_accuracy": 0.8430461063981056,
+      "num_tokens": 7692408.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.6536903701722622,
+      "epoch": 0.4426877470355731,
+      "grad_norm": 1457204.375,
+      "learning_rate": 0.0005615141955835961,
+      "loss": 0.6043,
+      "mean_token_accuracy": 0.833759855479002,
+      "num_tokens": 8329614.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.646093986183405,
+      "epoch": 0.4743083003952569,
+      "grad_norm": 96467.4765625,
+      "learning_rate": 0.0005299684542586751,
+      "loss": 0.6169,
+      "mean_token_accuracy": 0.8327336788177491,
+      "num_tokens": 8933829.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.5853382866829634,
+      "epoch": 0.5059288537549407,
+      "grad_norm": 3098197.5,
+      "learning_rate": 0.000498422712933754,
+      "loss": 0.5469,
+      "mean_token_accuracy": 0.8443389609456062,
+      "num_tokens": 9522595.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.5903366718441247,
+      "epoch": 0.5375494071146245,
+      "grad_norm": 42660388.0,
+      "learning_rate": 0.0004668769716088328,
+      "loss": 0.604,
+      "mean_token_accuracy": 0.8362459398806095,
+      "num_tokens": 10143758.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.6122400458902121,
+      "epoch": 0.5691699604743083,
+      "grad_norm": 757395008.0,
+      "learning_rate": 0.0004353312302839117,
+      "loss": 0.6429,
+      "mean_token_accuracy": 0.8282213471829891,
+      "num_tokens": 10692662.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.7004607111215592,
+      "epoch": 0.6007905138339921,
+      "grad_norm": 316442400.0,
+      "learning_rate": 0.0004037854889589905,
+      "loss": 0.6737,
+      "mean_token_accuracy": 0.8188323535025119,
+      "num_tokens": 11286778.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.6795283857733011,
+      "epoch": 0.6324110671936759,
+      "grad_norm": 19859658752.0,
+      "learning_rate": 0.0003722397476340694,
+      "loss": 0.6629,
+      "mean_token_accuracy": 0.8223141871392727,
+      "num_tokens": 11910969.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.6172661986202002,
+      "epoch": 0.6640316205533597,
+      "grad_norm": 596563.25,
+      "learning_rate": 0.00034069400630914825,
+      "loss": 0.6219,
+      "mean_token_accuracy": 0.8312948845326901,
+      "num_tokens": 12506898.0,
+      "step": 210
+    },
+    {
+      "entropy": 0.5889476146548986,
+      "epoch": 0.6956521739130435,
+      "grad_norm": 38292772.0,
+      "learning_rate": 0.00030914826498422714,
+      "loss": 0.6256,
+      "mean_token_accuracy": 0.833721686899662,
+      "num_tokens": 13097833.0,
+      "step": 220
+    },
+    {
+      "entropy": 0.5375086467713117,
+      "epoch": 0.7272727272727273,
+      "grad_norm": 7002747.5,
+      "learning_rate": 0.00027760252365930597,
+      "loss": 0.5423,
+      "mean_token_accuracy": 0.8461122632026672,
+      "num_tokens": 13690464.0,
+      "step": 230
+    },
+    {
+      "entropy": 0.5905131205916405,
+      "epoch": 0.758893280632411,
+      "grad_norm": 4201593.0,
+      "learning_rate": 0.00024605678233438486,
+      "loss": 0.5946,
+      "mean_token_accuracy": 0.8356382519006729,
+      "num_tokens": 14269150.0,
+      "step": 240
+    },
+    {
+      "entropy": 0.553895766660571,
+      "epoch": 0.7905138339920948,
+      "grad_norm": 7530.97509765625,
+      "learning_rate": 0.00021451104100946372,
+      "loss": 0.5512,
+      "mean_token_accuracy": 0.8458476938307286,
+      "num_tokens": 14877904.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.6424776270985604,
+      "epoch": 0.8221343873517787,
+      "grad_norm": 30025678.0,
+      "learning_rate": 0.00018296529968454258,
+      "loss": 0.6752,
+      "mean_token_accuracy": 0.8269011005759239,
+      "num_tokens": 15470400.0,
+      "step": 260
+    },
+    {
+      "entropy": 0.6024509601294994,
+      "epoch": 0.8537549407114624,
+      "grad_norm": 179891.234375,
+      "learning_rate": 0.00015141955835962145,
+      "loss": 0.6077,
+      "mean_token_accuracy": 0.8359923847019672,
+      "num_tokens": 16078040.0,
+      "step": 270
+    },
+    {
+      "entropy": 0.6116770006716251,
+      "epoch": 0.8853754940711462,
+      "grad_norm": 43860216.0,
+      "learning_rate": 0.00011987381703470032,
+      "loss": 0.6142,
+      "mean_token_accuracy": 0.8328806236386299,
+      "num_tokens": 16666971.0,
+      "step": 280
+    },
+    {
+      "entropy": 0.593284934386611,
+      "epoch": 0.9169960474308301,
+      "grad_norm": 2078294.875,
+      "learning_rate": 8.832807570977918e-05,
+      "loss": 0.6079,
+      "mean_token_accuracy": 0.8367695853114128,
+      "num_tokens": 17271306.0,
+      "step": 290
+    },
+    {
+      "entropy": 0.5837210457772016,
+      "epoch": 0.9486166007905138,
+      "grad_norm": 2131766.0,
+      "learning_rate": 5.6782334384858046e-05,
+      "loss": 0.5676,
+      "mean_token_accuracy": 0.8406473062932491,
+      "num_tokens": 17878825.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.5644817750900983,
+      "epoch": 0.9802371541501976,
+      "grad_norm": 11456195.0,
+      "learning_rate": 2.5236593059936908e-05,
+      "loss": 0.5706,
+      "mean_token_accuracy": 0.8438552170991898,
+      "num_tokens": 18498693.0,
+      "step": 310
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 317,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.6925009010147574e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-317/training_args.bin b/checkpoint-317/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..120f85ab118be2c00862d7334c96dd25039dfeea
--- /dev/null
+++ b/checkpoint-317/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bad5302c07edbe0267e2b38e65245429ed8bff1dce0fb4fc7af4aef2083cf5b
+size 5880
diff --git a/checkpoint-50/README.md b/checkpoint-50/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..235c2e6ff7d5d996be0c01802fa2d7707c43b969
--- /dev/null
+++ b/checkpoint-50/README.md
@@ -0,0 +1,209 @@
+---
+base_model: zai-org/GLM-4-32B-0414
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:zai-org/GLM-4-32B-0414
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.17.1
\ No newline at end of file
diff --git a/checkpoint-50/adapter_config.json b/checkpoint-50/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f0ebe86d1363a1171c6cd0dcf67ad18fa37c9f85
--- /dev/null
+++ b/checkpoint-50/adapter_config.json
@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "zai-org/GLM-4-32B-0414",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-50/adapter_model.safetensors b/checkpoint-50/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..07ec940a467dc825c98cfaf61ff416be5bbfef90
--- /dev/null
+++ b/checkpoint-50/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd393cf0b22d511d1526b8ede144ce8e555f7ddd6c6f6c1a1c6ef0e975b139b6
+size 4157688432
diff --git a/checkpoint-50/chat_template.jinja b/checkpoint-50/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..fdd583731de8bdf1830d38a3e34f7cd8f80605dd
--- /dev/null
+++ b/checkpoint-50/chat_template.jinja
@@ -0,0 +1,41 @@
+[gMASK]<sop>
+{%- if tools -%}
+<|system|>
+# 可用工具
+{% for tool in tools %}
+    {%- set function = tool.function if tool.get("function") else tool %}
+
+## {{ function.name }}
+
+{{ function | tojson(indent=4, ensure_ascii=False) }}
+在调用上述函数时，请使用 Json 格式表示调用的参数。
+{%- endfor %}
+{%- endif -%}
+
+{%- for msg in messages %}
+    {%- if msg.role == 'system' %}
+<|system|>
+{{ msg.content }}
+    {%- endif %}
+{%- endfor %}
+
+{%- for message in messages if message.role != 'system' %}
+    {%- set role = message['role'] %}
+    {%- set content = message['content'] %}
+    {%- set meta = message.get("metadata", "") %}
+
+    {%- if role == 'user' %}
+<|user|>
+{{ content }}
+    {%- elif role == 'assistant' and not meta %}
+<|assistant|>
+{{ content }}
+    {%- elif role == 'assistant' and meta %}
+<|assistant|>{{ meta }}
+{{ content }}
+    {%- elif role == 'observation' %}
+<|observation|>
+{{ content }}
+    {%- endif %}
+{%- endfor %}
+{% if add_generation_prompt %}<|assistant|>{% endif %}
\ No newline at end of file
diff --git a/checkpoint-50/optimizer.pt b/checkpoint-50/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4ccec7733159552c785fa8548716183b72677c58
--- /dev/null
+++ b/checkpoint-50/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c257e527ce5ba8c2e2327e7167a002505934ebf85035077b43ff79484c157e47
+size 8315744524
diff --git a/checkpoint-50/rng_state.pth b/checkpoint-50/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..93a52228ea16468eaab41b66555ced3eaaea002c
--- /dev/null
+++ b/checkpoint-50/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244
diff --git a/checkpoint-50/scheduler.pt b/checkpoint-50/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c2b5e59c32706c726e69c769dd3d08411fb1395d
--- /dev/null
+++ b/checkpoint-50/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0fac3922a836e4f00f87cfe1225d31aa2d017be320ad0d10597e2ab326b3425
+size 1064
diff --git a/checkpoint-50/special_tokens_map.json b/checkpoint-50/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..3cf953c2c8a3c89778c92e54c685942bb1130616
--- /dev/null
+++ b/checkpoint-50/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": "<|user|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-50/tokenizer.json b/checkpoint-50/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..4d1dde37a2715c11628fc84bf571976f9f80eb69
--- /dev/null
+++ b/checkpoint-50/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76ebeac0d8bd7879ead7b43c16b44981f277e47225de2bd7de9ae1a6cc664a8c
+size 19966496
diff --git a/checkpoint-50/tokenizer_config.json b/checkpoint-50/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d690b31eb34e3d9741aff67b37e0ecda2604739b
--- /dev/null
+++ b/checkpoint-50/tokenizer_config.json
@@ -0,0 +1,145 @@
+{
+  "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|>"
+  ],
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "<|user|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 128000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "remove_space": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}
diff --git a/checkpoint-50/trainer_state.json b/checkpoint-50/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..a77f26ba3eb4bd019dc6a9d742e44d94d5bb4d80
--- /dev/null
+++ b/checkpoint-50/trainer_state.json
@@ -0,0 +1,84 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.15810276679841898,
+  "eval_steps": 500,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.5656170375645161,
+      "epoch": 0.03162055335968379,
+      "grad_norm": 487949.625,
+      "learning_rate": 0.000971608832807571,
+      "loss": 0.598,
+      "mean_token_accuracy": 0.8383935391902924,
+      "num_tokens": 611773.0,
+      "step": 10
+    },
+    {
+      "entropy": 0.5844515649601817,
+      "epoch": 0.06324110671936758,
+      "grad_norm": 3576.093505859375,
+      "learning_rate": 0.0009400630914826499,
+      "loss": 0.6717,
+      "mean_token_accuracy": 0.8245183542370796,
+      "num_tokens": 1210060.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.4919601235538721,
+      "epoch": 0.09486166007905138,
+      "grad_norm": 462362592.0,
+      "learning_rate": 0.0009085173501577287,
+      "loss": 0.6075,
+      "mean_token_accuracy": 0.8355057552456856,
+      "num_tokens": 1815732.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.45399096198379996,
+      "epoch": 0.12648221343873517,
+      "grad_norm": 48967.296875,
+      "learning_rate": 0.0008769716088328076,
+      "loss": 0.6877,
+      "mean_token_accuracy": 0.8247161574661732,
+      "num_tokens": 2372291.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.5189430050551891,
+      "epoch": 0.15810276679841898,
+      "grad_norm": 20488920.0,
+      "learning_rate": 0.0008454258675078864,
+      "loss": 0.6631,
+      "mean_token_accuracy": 0.8253108873963356,
+      "num_tokens": 2970656.0,
+      "step": 50
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 317,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.823854699123835e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-50/training_args.bin b/checkpoint-50/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..120f85ab118be2c00862d7334c96dd25039dfeea
--- /dev/null
+++ b/checkpoint-50/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bad5302c07edbe0267e2b38e65245429ed8bff1dce0fb4fc7af4aef2083cf5b
+size 5880
diff --git a/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..3cf953c2c8a3c89778c92e54c685942bb1130616
--- /dev/null
+++ b/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": "<|user|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..4d1dde37a2715c11628fc84bf571976f9f80eb69
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76ebeac0d8bd7879ead7b43c16b44981f277e47225de2bd7de9ae1a6cc664a8c
+size 19966496
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d690b31eb34e3d9741aff67b37e0ecda2604739b
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,145 @@
+{
+  "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|>"
+  ],
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "<|user|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 128000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "remove_space": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}
diff --git a/training_args.bin b/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..120f85ab118be2c00862d7334c96dd25039dfeea
--- /dev/null
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bad5302c07edbe0267e2b38e65245429ed8bff1dce0fb4fc7af4aef2083cf5b
+size 5880