Upload folder using huggingface_hub

README.md

@@ -14,334 +14,6 @@ model-index:
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# Install
-```bash
-pip install peft transformers bitsandbytes ipykernel rapidfuzz
-```
-# Run by transformers
-
-```python
-import json
-from dataclasses import dataclass
-from enum import Enum
-from typing import List, Dict, Tuple, Literal
-
-class Roles(Enum):
-    system = "system"
-    user = "user"
-    assistant = "assistant"
-    tool = "tool"
-
-class MessagesFormatterType(Enum):
-    """
-    Enum representing different types of predefined messages formatters.
-    """
-
-    MISTRAL = 1
-
-@dataclass
-class PromptMarkers:
-    start: str
-    end: str
-
-class MessagesFormatter:
-    def __init__(
-            self,
-            pre_prompt: str,
-            prompt_markers: Dict[Roles, PromptMarkers],
-            include_sys_prompt_in_first_user_message: bool,
-            default_stop_sequences: List[str],
-            use_user_role_for_function_call_result: bool = True,
-            strip_prompt: bool = True,
-            bos_token: str = "<s>",
-            eos_token: str = "</s>"
-    ):
-        self.pre_prompt = pre_prompt
-        self.prompt_markers = prompt_markers
-        self.include_sys_prompt_in_first_user_message = include_sys_prompt_in_first_user_message
-        self.default_stop_sequences = default_stop_sequences
-        self.use_user_role_for_function_call_result = use_user_role_for_function_call_result
-        self.strip_prompt = strip_prompt
-        self.bos_token = bos_token
-        self.eos_token = eos_token
-        self.added_system_prompt = False
-
-    def get_bos_token(self) -> str:
-        return self.bos_token
-
-    def format_conversation(
-            self,
-            messages: List[Dict[str, str]],
-            response_role: Literal[Roles.user, Roles.assistant] | None = None,
-    ) -> Tuple[str, Roles]:
-        formatted_messages = self.pre_prompt
-        last_role = Roles.assistant
-        self.added_system_prompt = False
-        for message in messages:
-            role = Roles(message["role"])
-            content = self._format_message_content(message["content"], role)
-
-            if role == Roles.system:
-                formatted_messages += self._format_system_message(content)
-                last_role = Roles.system
-            elif role == Roles.user:
-                formatted_messages += self._format_user_message(content)
-                last_role = Roles.user
-            elif role == Roles.assistant:
-                formatted_messages += self._format_assistant_message(content)
-                last_role = Roles.assistant
-            elif role == Roles.tool:
-                formatted_messages += self._format_tool_message(content)
-                last_role = Roles.tool
-
-        return self._format_response(formatted_messages, last_role, response_role)
-
-    def _format_message_content(self, content: str, role: Roles) -> str:
-        if self.strip_prompt:
-            return content.strip()
-        return content
-
-    def _format_system_message(self, content: str) -> str:
-        formatted_message = self.prompt_markers[Roles.system].start + content + self.prompt_markers[Roles.system].end
-        self.added_system_prompt = True
-        if self.include_sys_prompt_in_first_user_message:
-            formatted_message = self.prompt_markers[Roles.user].start + formatted_message
-        return formatted_message
-
-    def _format_user_message(self, content: str) -> str:
-        if self.include_sys_prompt_in_first_user_message and self.added_system_prompt:
-            self.added_system_prompt = False
-            return content + self.prompt_markers[Roles.user].end
-        return self.prompt_markers[Roles.user].start + content + self.prompt_markers[Roles.user].end
-
-    def _format_assistant_message(self, content: str) -> str:
-        return self.prompt_markers[Roles.assistant].start + content + self.prompt_markers[Roles.assistant].end
-
-    def _format_tool_message(self, content: str) -> str:
-        if isinstance(content, list):
-            content = "\n".join(json.dumps(m, indent=2) for m in content)
-        if self.use_user_role_for_function_call_result:
-            return self._format_user_message(content)
-        else:
-            return self.prompt_markers[Roles.tool].start + content + self.prompt_markers[Roles.tool].end
-
-    def _format_response(
-            self,
-            formatted_messages: str,
-            last_role: Roles,
-            response_role: Literal[Roles.user, Roles.assistant] | None = None,
-    ) -> Tuple[str, Roles]:
-        if response_role is None:
-            response_role = Roles.assistant if last_role != Roles.assistant else Roles.user
-
-        prompt_start = self.prompt_markers[response_role].start.strip() if self.strip_prompt else self.prompt_markers[
-            response_role].start
-        return formatted_messages + prompt_start, response_role
-
-mixtral_prompt_markers = {
-    Roles.system: PromptMarkers("", """\n\n"""),
-    Roles.user: PromptMarkers("""[INST] """, """ [/INST]"""),
-    Roles.assistant: PromptMarkers("""""", """</s>"""),
-    Roles.tool: PromptMarkers("", ""),
-}
-
-mixtral_formatter = MessagesFormatter(
-    "",
-    mixtral_prompt_markers,
-    True,
-    ["</s>"],
-)
-
-from transformers import TextStreamer, AutoTokenizer, AutoModelForCausalLM
-from peft import PeftModel
-tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.3",)
-mis_model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.3", load_in_4bit = True)
-mis_model = PeftModel.from_pretrained(mis_model, "svjack/Genshin_Impact_Mistral_v3_Plot_Chat_roleplay_chat_lora_small")
-mis_model = mis_model.eval()
-
-streamer = TextStreamer(tokenizer)
-
-def mistral_hf_predict(messages, mis_model = mis_model,
-    tokenizer = tokenizer, streamer = streamer,
-    do_sample = True,
-    top_p = 0.95,
-    top_k = 40,
-    max_new_tokens = 512,
-    max_input_length = 3500,
-    temperature = 0.9,
-    repetition_penalty = 1.0,
-    device = "cuda"):
-
-    #encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")
-    #model_inputs = encodeds.to(device)
-    prompt, _ = mixtral_formatter.format_conversation(messages)
-    model_inputs = tokenizer.encode(prompt, return_tensors="pt").to(device)
-
-    generated_ids = mis_model.generate(model_inputs, max_new_tokens=max_new_tokens,
-                                do_sample=do_sample,
-                                  streamer = streamer,
-                                  top_p = top_p,
-                                  top_k = top_k,
-                                  temperature = temperature,
-                                  repetition_penalty = repetition_penalty,
-                                  )
-    out = tokenizer.batch_decode(generated_ids)[0].split("[/INST]")[-1].replace("</s>", "").strip()
-    return out
-
-out = mistral_hf_predict([
-            {
-                "role": "system",
-                "content": '''
-                故事背景:图书管理员丽莎与助手派蒙在寻找偷书者的冒险中交流，揭示了真相并处理了书籍问题。
-                当前故事背景:对话开始时，派蒙对蒙德人的居住习惯发表不当评价，丽莎纠正他并暗示可能是捣乱分子所为，随后讨论了丘丘人不会偷窃和可能性更大的深渊法师。在解开封印后，他们进入遗迹，并决定继续深入调查。
-                参与者1:丽莎
-                参与者1角色经历:丽莎，作为蒙德城南风之狮庙宇的图书管理员，以其严肃认真的工作态度和对书籍的热爱，与旅行者派蒙共同解决图书丢失的问题。她运用元素感知力帮助找寻线索，与伙伴们互动，展现智慧和勇气，同时对偷书者的行为有着坚定的立场，通过惩罚计划来维护图书的尊严。在游戏中，她不仅提供历史背景，还作为知识库，帮助旅行者理解元素和蒙德的历史，她的存在对解决故事中的谜题和对抗敌人至关重要。在蒙德骑士团中，丽莎也协助凯亚和琴，展现她的团队精神和对守护者的责任感。
-                参与者1性格特征:丽莎性格严谨，热爱工作，尊重他人，对待偷书者的行为表现出坚定和公正。她聪明且勇敢，善于使用元素感知力解决问题，同时具有深厚的历史知识和对‘四风守护’的理解。她的智慧和责任感在剧情中起到了关键作用。
-                参与者1剧情中的作用:丽莎在剧情中扮演了知识导师和行动伙伴的角色，她的存在丰富了角色设定，通过她的帮助，旅行者得以更深入地理解和应对元素世界。她的出现推动了故事的发展，通过她的智慧和勇气，解决了许多难题，强化了角色间的互动和团队合作。同时，她的责任感和对蒙德的热爱也深化了游戏的主题，体现了对守护者的尊重和对家乡的忠诚。
-                参与者2:派蒙
-                参与者2角色经历:派蒙是宵宫的旅伴，他们共同面对船的问题，逃离稻妻，与森彦、阿创等人互动，参与烟花制作，解决孩子们的误解。派蒙对宵宫的强硬态度感到惊讶，但理解了沟通的力量。他与旅行者的关系亲密，共享冒险，是故事中的重要角色。他参与了对抗魔物、解决兽境猎犬事件，以及帮助影解决雷电将军的问题，表现出决心和行动力。在与凯亚的冒险中，他们共同解谜寻宝，面对误解，派蒙逐渐理解和接受‘黎明神剑’作为友谊的象征。在‘在此世的星空之外’，他与莫娜一起经历了寻找丢失戒指、解决朱老板问题和烹饪学习的挑战，加深了他们的信任和支持。
-                参与者2性格特征:派蒙勇敢、坚韧，对友情有着深刻的理解。他不畏困难，愿意面对挑战，同时也有着对宵宫处理问题方式的惊讶和理解。他���旅行者的关系亲密，显示出忠诚和共享冒险的精神。在与凯亚的互动中，他展现出对友谊的接纳和对占星术的好奇。
-                参与者2剧情中的作用:派蒙在剧情中起着多面作用，他不仅是宵宫的伙伴，也是旅行者和凯亚的友人。他的冒险经历丰富了故事的层次，通过他的角色，展示了沟通的力量、友情的重要性，以及面对问题时的决心。他的成长和理解深化了故事的主题，尤其是在处理误解和接受‘黎明神剑’象征友谊的过程中。同时，他与莫娜的合作也展示了角色之间的互动和信任，增加了故事的复杂性和深度。
-                要求进行"丽莎"与"派蒙"之间的对话。
-                我扮演"丽莎"，你扮演"派蒙"。
-                '''
-            },
-            {
-                "role": "user",
-                "content": "小派蒙，你如何评价蒙德人的习惯？"
-            },
-            {
-                "role": "assistant",
-                "content": "我觉得他们太懒散了，总是把东西放在家里，而且家里总是乱七八糟。"
-            },
-            {
-                "role": "user",
-                "content": "嘘，不要当着他们的面说。"
-            },
-            {
-                "role": "assistant",
-                "content": "那你认为是谁在偷书？"
-            },
-            {
-                "role": "user",
-                "content": "你认为可能是丘丘人吗？"
-            },
-            {
-                "role": "assistant",
-                "content": "丘丘人不会这样吧，他们不会偷东西。"
-            },
-            {
-                "role": "user",
-                "content": "喜欢暗中计划阴谋的深渊法师可能性比较大。"
-            },
-            {
-                "role": "assistant",
-                "content": "你们确定那些偷书的人不是从深渊来的吗？"
-            },
-            {
-                "role": "user",
-                "content": "说不定秘境里就有答案。"
-            },
-        ],
-        repetition_penalty = 1.0,
-        temperature = 0.5,
-        max_new_tokens=1024
-)
-print(out)
-```
-
-# Output 
-```
-那我们进去看看，你准备好了吗？
-```
-
-
-```python
-from rapidfuzz import fuzz 
-from IPython.display import clear_output
-def run_step_infer_times(x, times = 5, temperature = 0.01,
-                        repetition_penalty = 1.0,
-                        sim_val = 70
-                        ):
-    req = []
-    for _ in range(times):
-        clear_output(wait = True)
-        out = mistral_hf_predict([
-                {
-                    "role": "system",
-                    "content": ""
-                },
-                {
-                    "role": "user",
-                    "content": x
-                },
-            ],
-            repetition_penalty = repetition_penalty,
-            temperature = temperature,
-            max_new_tokens = 2070,
-            max_input_length = 6000,
-        )
-        if req:
-            val = max(map(lambda x: fuzz.ratio(x, out), req))
-            #print(val)
-            #print(req)
-            if val < sim_val:
-                req.append(out.strip())
-            x = x.strip() + "\n" + out.strip()
-        else:
-            req.append(out.strip())
-            x = x.strip() + "\n" + out.strip()
-    return req
-
-out_l = run_step_infer_times(
-'''
-故事标题:为了没有眼泪的明天
-故事背景:旅行者与琴、派蒙在蒙德城中经历了一系列事件，从元素流动回归、处理外交问题到对抗魔龙和寻找解决之道。他们偶遇吟游诗人温迪，后者提供了关于风神与巨龙的关键信息，并提出了借琴解救蒙德的计划。
-参与角色:派蒙、旅行者、琴、丽莎、温迪、歌特琳德
-''',
-    temperature=0.1,
-    repetition_penalty = 1.0,
-    times = 10
-)
-clear_output(wait = True)
-
-print("\n".join(out_l))
-```
-
-# Output 
-```
-{'参与者1': '派蒙', '参与者2': '旅行者', '当前故事背景': '两人在蒙德城中寻找琴，并在遇到温迪后得知琴可能在城内。'}
-{'参与者1': '琴', '参与者2': '丽莎', '当前故事背景': '琴与丽莎交谈，丽莎提出对琴的担忧和对琴的支持，以及对琴的信任和理解。'}
-{'参与者1': '温迪', '参与者2': '派蒙', '当前故事背景': '温迪提出借琴解救蒙德的计划，并提供了关于风神与巨龙的信息。'}
-{'参与者1': '琴', '参与者2': '温迪', '当前故事背景': '琴对温迪的提议表示理解，并准备接受任务。'}
-```
-
-```python
-out_l = run_step_infer_times(
-'''
-故事标题:归乡
-故事背景:在须弥城门口，派蒙与纳西妲偶遇并帮助一只昏迷的元素生命找寻家园。过程中揭示了这只生物并非普通的蕈兽，而是元素生物，并且它们曾受到过‘末日’的影响，家园被侵蚀。纳西妲回忆起晶体里的力量��能与一个预言有关，为了拯救它们的家园，她必须解决‘禁忌知识’问题，但这个过程对她自身也会产生干扰。
-参与角色:派蒙、纳西妲、浮游水蕈兽、旅行者
-''',
-    temperature=0.1,
-    repetition_penalty = 1.0,
-    times = 10
-)
-clear_output(wait = True)
-
-print("\n".join(out_l))
-```
-
-# Output 
-```
-{'参与者1': '派蒙', '参与者2': '纳西妲', '当前故事背景': '在须弥城门口，派蒙发现了一个昏迷的浮游水蕈兽，并询问它是否需要帮助。纳西妲注意到这只生物并提出要帮助它们找回家。'}
-{'参与者1': '派蒙', '参与者2': '纳西妲', '当前故事背景': '纳西妲解释了这只生物并非普通的蕈兽，而是元素生物，它们的家园被侵蚀，并且晶体里的力量可能与一个预言有关。'}
-{'参与者1': '派蒙', '参与者2': '纳西妲', '当前故事背景': '纳西妲提出解决‘禁忌知识’问题，这可能与拯救元素生物的家园有关，但这个过程对她自身也会产生影响。'}
-{'参与者1': '派蒙', '参与者2': '纳西妲', '当前故事背景': '派蒙询问‘禁忌知识’的具体内容，纳西妲提出这是为了解决元素生物的问题。'}
-{'参与者1': '纳西妲', '参与者2': '旅行者', '当前故事背景': '纳西妲提出解决‘禁忌知识’的问题，旅行者对此表示惊讶。'}
-```
-
-
 # train_2024-05-29-13-19-55
 
 This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on the plot_genshin_impact_roleplay_agent_vllm, the genshin_impact_plot_engine_step_inst_short_json and the plot_genshin_impact_roleplay_vllm datasets.

checkpoint-100/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+---
+
+# 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 0.11.1

checkpoint-100/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8810a3e71ecfb5477728078a76d43cd3e90119d3064f5b3bd630adf765600eb0
+size 13648432

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e950fe7d5935b2f67d3a37cc7f2f64ba68216769e31e7e2cd589a926787b3e8
+size 27370618

checkpoint-100/rng_state.pth

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

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d4048dab0aa064043ebda2bfc98cac77a60f76880c6e52509dd34cc13216ef1
+size 1064

checkpoint-100/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-100/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

checkpoint-100/trainer_state.json

@@ -0,0 +1,173 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0836382645060115,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004181913225300575,
+      "grad_norm": 3.3295910358428955,
+      "learning_rate": 4.9999760022374266e-05,
+      "loss": 1.8032,
+      "step": 5
+    },
+    {
+      "epoch": 0.00836382645060115,
+      "grad_norm": 2.002122163772583,
+      "learning_rate": 4.999904009410418e-05,
+      "loss": 1.5943,
+      "step": 10
+    },
+    {
+      "epoch": 0.012545739675901725,
+      "grad_norm": 1.9293591976165771,
+      "learning_rate": 4.9997840229011085e-05,
+      "loss": 1.5378,
+      "step": 15
+    },
+    {
+      "epoch": 0.0167276529012023,
+      "grad_norm": 1.936969518661499,
+      "learning_rate": 4.999616045013025e-05,
+      "loss": 1.5856,
+      "step": 20
+    },
+    {
+      "epoch": 0.020909566126502875,
+      "grad_norm": 1.8237314224243164,
+      "learning_rate": 4.9994000789710415e-05,
+      "loss": 1.5066,
+      "step": 25
+    },
+    {
+      "epoch": 0.02509147935180345,
+      "grad_norm": 1.8101543188095093,
+      "learning_rate": 4.9991361289213203e-05,
+      "loss": 1.4499,
+      "step": 30
+    },
+    {
+      "epoch": 0.029273392577104027,
+      "grad_norm": 1.647802710533142,
+      "learning_rate": 4.998824199931228e-05,
+      "loss": 1.4694,
+      "step": 35
+    },
+    {
+      "epoch": 0.0334553058024046,
+      "grad_norm": 1.7077428102493286,
+      "learning_rate": 4.998464297989245e-05,
+      "loss": 1.4945,
+      "step": 40
+    },
+    {
+      "epoch": 0.03763721902770518,
+      "grad_norm": 1.7119005918502808,
+      "learning_rate": 4.998056430004844e-05,
+      "loss": 1.4257,
+      "step": 45
+    },
+    {
+      "epoch": 0.04181913225300575,
+      "grad_norm": 2.0229578018188477,
+      "learning_rate": 4.997600603808359e-05,
+      "loss": 1.4713,
+      "step": 50
+    },
+    {
+      "epoch": 0.04600104547830632,
+      "grad_norm": 1.885362148284912,
+      "learning_rate": 4.997096828150838e-05,
+      "loss": 1.5145,
+      "step": 55
+    },
+    {
+      "epoch": 0.0501829587036069,
+      "grad_norm": 2.0357539653778076,
+      "learning_rate": 4.9965451127038714e-05,
+      "loss": 1.3811,
+      "step": 60
+    },
+    {
+      "epoch": 0.054364871928907474,
+      "grad_norm": 1.9780900478363037,
+      "learning_rate": 4.9959454680594086e-05,
+      "loss": 1.412,
+      "step": 65
+    },
+    {
+      "epoch": 0.05854678515420805,
+      "grad_norm": 1.6695700883865356,
+      "learning_rate": 4.995297905729554e-05,
+      "loss": 1.4093,
+      "step": 70
+    },
+    {
+      "epoch": 0.06272869837950862,
+      "grad_norm": 1.9424223899841309,
+      "learning_rate": 4.994602438146344e-05,
+      "loss": 1.4615,
+      "step": 75
+    },
+    {
+      "epoch": 0.0669106116048092,
+      "grad_norm": 1.9082552194595337,
+      "learning_rate": 4.9938590786615126e-05,
+      "loss": 1.4169,
+      "step": 80
+    },
+    {
+      "epoch": 0.07109252483010978,
+      "grad_norm": 1.8944685459136963,
+      "learning_rate": 4.993067841546231e-05,
+      "loss": 1.3064,
+      "step": 85
+    },
+    {
+      "epoch": 0.07527443805541036,
+      "grad_norm": 1.9688103199005127,
+      "learning_rate": 4.992228741990834e-05,
+      "loss": 1.3778,
+      "step": 90
+    },
+    {
+      "epoch": 0.07945635128071092,
+      "grad_norm": 2.0939650535583496,
+      "learning_rate": 4.991341796104534e-05,
+      "loss": 1.3905,
+      "step": 95
+    },
+    {
+      "epoch": 0.0836382645060115,
+      "grad_norm": 1.868986964225769,
+      "learning_rate": 4.9904070209151015e-05,
+      "loss": 1.3723,
+      "step": 100
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 3585,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2914497408794624e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ad489884f87ec96cc1e49b25622db5c6c3c1eafcad1be5306265a7460b6619a
+size 5304

checkpoint-1000/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+---
+
+# 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 0.11.1

checkpoint-1000/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55f95e09bf59843911eb652f7d3b822b548c83bf5275af6682e92fdb97d8a6b6
+size 13648432

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1568d2408b6a88982c138d5c10ebf316f5e8fd671f5619115a935449cc7ea9b
+size 27370618

checkpoint-1000/rng_state.pth

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

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21ad6c58bb3ecc1231a76b4dac6708c1d3dd5b06712d29800b533c8723f9de03
+size 1064

checkpoint-1000/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1000/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

checkpoint-1000/trainer_state.json

@@ -0,0 +1,1433 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.836382645060115,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004181913225300575,
+      "grad_norm": 3.3295910358428955,
+      "learning_rate": 4.9999760022374266e-05,
+      "loss": 1.8032,
+      "step": 5
+    },
+    {
+      "epoch": 0.00836382645060115,
+      "grad_norm": 2.002122163772583,
+      "learning_rate": 4.999904009410418e-05,
+      "loss": 1.5943,
+      "step": 10
+    },
+    {
+      "epoch": 0.012545739675901725,
+      "grad_norm": 1.9293591976165771,
+      "learning_rate": 4.9997840229011085e-05,
+      "loss": 1.5378,
+      "step": 15
+    },
+    {
+      "epoch": 0.0167276529012023,
+      "grad_norm": 1.936969518661499,
+      "learning_rate": 4.999616045013025e-05,
+      "loss": 1.5856,
+      "step": 20
+    },
+    {
+      "epoch": 0.020909566126502875,
+      "grad_norm": 1.8237314224243164,
+      "learning_rate": 4.9994000789710415e-05,
+      "loss": 1.5066,
+      "step": 25
+    },
+    {
+      "epoch": 0.02509147935180345,
+      "grad_norm": 1.8101543188095093,
+      "learning_rate": 4.9991361289213203e-05,
+      "loss": 1.4499,
+      "step": 30
+    },
+    {
+      "epoch": 0.029273392577104027,
+      "grad_norm": 1.647802710533142,
+      "learning_rate": 4.998824199931228e-05,
+      "loss": 1.4694,
+      "step": 35
+    },
+    {
+      "epoch": 0.0334553058024046,
+      "grad_norm": 1.7077428102493286,
+      "learning_rate": 4.998464297989245e-05,
+      "loss": 1.4945,
+      "step": 40
+    },
+    {
+      "epoch": 0.03763721902770518,
+      "grad_norm": 1.7119005918502808,
+      "learning_rate": 4.998056430004844e-05,
+      "loss": 1.4257,
+      "step": 45
+    },
+    {
+      "epoch": 0.04181913225300575,
+      "grad_norm": 2.0229578018188477,
+      "learning_rate": 4.997600603808359e-05,
+      "loss": 1.4713,
+      "step": 50
+    },
+    {
+      "epoch": 0.04600104547830632,
+      "grad_norm": 1.885362148284912,
+      "learning_rate": 4.997096828150838e-05,
+      "loss": 1.5145,
+      "step": 55
+    },
+    {
+      "epoch": 0.0501829587036069,
+      "grad_norm": 2.0357539653778076,
+      "learning_rate": 4.9965451127038714e-05,
+      "loss": 1.3811,
+      "step": 60
+    },
+    {
+      "epoch": 0.054364871928907474,
+      "grad_norm": 1.9780900478363037,
+      "learning_rate": 4.9959454680594086e-05,
+      "loss": 1.412,
+      "step": 65
+    },
+    {
+      "epoch": 0.05854678515420805,
+      "grad_norm": 1.6695700883865356,
+      "learning_rate": 4.995297905729554e-05,
+      "loss": 1.4093,
+      "step": 70
+    },
+    {
+      "epoch": 0.06272869837950862,
+      "grad_norm": 1.9424223899841309,
+      "learning_rate": 4.994602438146344e-05,
+      "loss": 1.4615,
+      "step": 75
+    },
+    {
+      "epoch": 0.0669106116048092,
+      "grad_norm": 1.9082552194595337,
+      "learning_rate": 4.9938590786615126e-05,
+      "loss": 1.4169,
+      "step": 80
+    },
+    {
+      "epoch": 0.07109252483010978,
+      "grad_norm": 1.8944685459136963,
+      "learning_rate": 4.993067841546231e-05,
+      "loss": 1.3064,
+      "step": 85
+    },
+    {
+      "epoch": 0.07527443805541036,
+      "grad_norm": 1.9688103199005127,
+      "learning_rate": 4.992228741990834e-05,
+      "loss": 1.3778,
+      "step": 90
+    },
+    {
+      "epoch": 0.07945635128071092,
+      "grad_norm": 2.0939650535583496,
+      "learning_rate": 4.991341796104534e-05,
+      "loss": 1.3905,
+      "step": 95
+    },
+    {
+      "epoch": 0.0836382645060115,
+      "grad_norm": 1.868986964225769,
+      "learning_rate": 4.9904070209151015e-05,
+      "loss": 1.3723,
+      "step": 100
+    },
+    {
+      "epoch": 0.08782017773131208,
+      "grad_norm": 2.069476842880249,
+      "learning_rate": 4.989424434368549e-05,
+      "loss": 1.4046,
+      "step": 105
+    },
+    {
+      "epoch": 0.09200209095661264,
+      "grad_norm": 2.1500356197357178,
+      "learning_rate": 4.988394055328779e-05,
+      "loss": 1.4319,
+      "step": 110
+    },
+    {
+      "epoch": 0.09618400418191322,
+      "grad_norm": 1.9786696434020996,
+      "learning_rate": 4.987315903577223e-05,
+      "loss": 1.4203,
+      "step": 115
+    },
+    {
+      "epoch": 0.1003659174072138,
+      "grad_norm": 2.035172939300537,
+      "learning_rate": 4.986189999812468e-05,
+      "loss": 1.4046,
+      "step": 120
+    },
+    {
+      "epoch": 0.10454783063251437,
+      "grad_norm": 1.9887930154800415,
+      "learning_rate": 4.985016365649848e-05,
+      "loss": 1.3836,
+      "step": 125
+    },
+    {
+      "epoch": 0.10872974385781495,
+      "grad_norm": 1.8339554071426392,
+      "learning_rate": 4.983795023621041e-05,
+      "loss": 1.3468,
+      "step": 130
+    },
+    {
+      "epoch": 0.11291165708311553,
+      "grad_norm": 2.06648588180542,
+      "learning_rate": 4.982525997173625e-05,
+      "loss": 1.3481,
+      "step": 135
+    },
+    {
+      "epoch": 0.1170935703084161,
+      "grad_norm": 2.1179702281951904,
+      "learning_rate": 4.9812093106706376e-05,
+      "loss": 1.4475,
+      "step": 140
+    },
+    {
+      "epoch": 0.12127548353371667,
+      "grad_norm": 2.1708436012268066,
+      "learning_rate": 4.979844989390104e-05,
+      "loss": 1.3662,
+      "step": 145
+    },
+    {
+      "epoch": 0.12545739675901724,
+      "grad_norm": 2.0533807277679443,
+      "learning_rate": 4.978433059524548e-05,
+      "loss": 1.3856,
+      "step": 150
+    },
+    {
+      "epoch": 0.12963930998431783,
+      "grad_norm": 1.9418696165084839,
+      "learning_rate": 4.976973548180498e-05,
+      "loss": 1.357,
+      "step": 155
+    },
+    {
+      "epoch": 0.1338212232096184,
+      "grad_norm": 2.1071596145629883,
+      "learning_rate": 4.975466483377959e-05,
+      "loss": 1.3613,
+      "step": 160
+    },
+    {
+      "epoch": 0.138003136434919,
+      "grad_norm": 2.3704464435577393,
+      "learning_rate": 4.9739118940498766e-05,
+      "loss": 1.3985,
+      "step": 165
+    },
+    {
+      "epoch": 0.14218504966021955,
+      "grad_norm": 2.1726176738739014,
+      "learning_rate": 4.9723098100415844e-05,
+      "loss": 1.4361,
+      "step": 170
+    },
+    {
+      "epoch": 0.14636696288552012,
+      "grad_norm": 2.608517646789551,
+      "learning_rate": 4.970660262110227e-05,
+      "loss": 1.3565,
+      "step": 175
+    },
+    {
+      "epoch": 0.1505488761108207,
+      "grad_norm": 2.185563564300537,
+      "learning_rate": 4.968963281924173e-05,
+      "loss": 1.2957,
+      "step": 180
+    },
+    {
+      "epoch": 0.15473078933612128,
+      "grad_norm": 1.9632441997528076,
+      "learning_rate": 4.967218902062403e-05,
+      "loss": 1.2833,
+      "step": 185
+    },
+    {
+      "epoch": 0.15891270256142184,
+      "grad_norm": 2.303462028503418,
+      "learning_rate": 4.96542715601389e-05,
+      "loss": 1.3238,
+      "step": 190
+    },
+    {
+      "epoch": 0.16309461578672244,
+      "grad_norm": 2.3211796283721924,
+      "learning_rate": 4.9635880781769495e-05,
+      "loss": 1.3848,
+      "step": 195
+    },
+    {
+      "epoch": 0.167276529012023,
+      "grad_norm": 2.0993776321411133,
+      "learning_rate": 4.961701703858584e-05,
+      "loss": 1.3997,
+      "step": 200
+    },
+    {
+      "epoch": 0.17145844223732357,
+      "grad_norm": 2.210942506790161,
+      "learning_rate": 4.9597680692738056e-05,
+      "loss": 1.334,
+      "step": 205
+    },
+    {
+      "epoch": 0.17564035546262416,
+      "grad_norm": 2.1277225017547607,
+      "learning_rate": 4.957787211544935e-05,
+      "loss": 1.3338,
+      "step": 210
+    },
+    {
+      "epoch": 0.17982226868792472,
+      "grad_norm": 2.287722587585449,
+      "learning_rate": 4.9557591687008966e-05,
+      "loss": 1.3621,
+      "step": 215
+    },
+    {
+      "epoch": 0.1840041819132253,
+      "grad_norm": 2.113842010498047,
+      "learning_rate": 4.9536839796764825e-05,
+      "loss": 1.3808,
+      "step": 220
+    },
+    {
+      "epoch": 0.18818609513852588,
+      "grad_norm": 2.0642735958099365,
+      "learning_rate": 4.951561684311608e-05,
+      "loss": 1.3429,
+      "step": 225
+    },
+    {
+      "epoch": 0.19236800836382645,
+      "grad_norm": 2.2026379108428955,
+      "learning_rate": 4.9493923233505435e-05,
+      "loss": 1.2855,
+      "step": 230
+    },
+    {
+      "epoch": 0.196549921589127,
+      "grad_norm": 2.2843308448791504,
+      "learning_rate": 4.947175938441138e-05,
+      "loss": 1.3432,
+      "step": 235
+    },
+    {
+      "epoch": 0.2007318348144276,
+      "grad_norm": 2.126749038696289,
+      "learning_rate": 4.9449125721340145e-05,
+      "loss": 1.3753,
+      "step": 240
+    },
+    {
+      "epoch": 0.20491374803972817,
+      "grad_norm": 2.514599561691284,
+      "learning_rate": 4.942602267881755e-05,
+      "loss": 1.3101,
+      "step": 245
+    },
+    {
+      "epoch": 0.20909566126502874,
+      "grad_norm": 2.2043542861938477,
+      "learning_rate": 4.940245070038064e-05,
+      "loss": 1.3395,
+      "step": 250
+    },
+    {
+      "epoch": 0.21327757449032933,
+      "grad_norm": 2.152742862701416,
+      "learning_rate": 4.937841023856923e-05,
+      "loss": 1.3188,
+      "step": 255
+    },
+    {
+      "epoch": 0.2174594877156299,
+      "grad_norm": 2.221057415008545,
+      "learning_rate": 4.935390175491716e-05,
+      "loss": 1.4205,
+      "step": 260
+    },
+    {
+      "epoch": 0.2216414009409305,
+      "grad_norm": 2.600109100341797,
+      "learning_rate": 4.932892571994342e-05,
+      "loss": 1.3499,
+      "step": 265
+    },
+    {
+      "epoch": 0.22582331416623105,
+      "grad_norm": 2.2291276454925537,
+      "learning_rate": 4.9303482613143194e-05,
+      "loss": 1.3984,
+      "step": 270
+    },
+    {
+      "epoch": 0.23000522739153162,
+      "grad_norm": 2.338000774383545,
+      "learning_rate": 4.9277572922978586e-05,
+      "loss": 1.344,
+      "step": 275
+    },
+    {
+      "epoch": 0.2341871406168322,
+      "grad_norm": 2.3423988819122314,
+      "learning_rate": 4.925119714686928e-05,
+      "loss": 1.2696,
+      "step": 280
+    },
+    {
+      "epoch": 0.23836905384213278,
+      "grad_norm": 2.433870553970337,
+      "learning_rate": 4.9224355791182955e-05,
+      "loss": 1.3903,
+      "step": 285
+    },
+    {
+      "epoch": 0.24255096706743334,
+      "grad_norm": 2.281836986541748,
+      "learning_rate": 4.919704937122559e-05,
+      "loss": 1.3694,
+      "step": 290
+    },
+    {
+      "epoch": 0.24673288029273394,
+      "grad_norm": 2.2429168224334717,
+      "learning_rate": 4.916927841123159e-05,
+      "loss": 1.3541,
+      "step": 295
+    },
+    {
+      "epoch": 0.2509147935180345,
+      "grad_norm": 2.4559881687164307,
+      "learning_rate": 4.9141043444353674e-05,
+      "loss": 1.3795,
+      "step": 300
+    },
+    {
+      "epoch": 0.25509670674333507,
+      "grad_norm": 2.7529919147491455,
+      "learning_rate": 4.911234501265266e-05,
+      "loss": 1.386,
+      "step": 305
+    },
+    {
+      "epoch": 0.25927861996863566,
+      "grad_norm": 2.229973554611206,
+      "learning_rate": 4.9083183667087064e-05,
+      "loss": 1.3653,
+      "step": 310
+    },
+    {
+      "epoch": 0.26346053319393625,
+      "grad_norm": 2.38677716255188,
+      "learning_rate": 4.9053559967502535e-05,
+      "loss": 1.3254,
+      "step": 315
+    },
+    {
+      "epoch": 0.2676424464192368,
+      "grad_norm": 2.292898416519165,
+      "learning_rate": 4.9023474482621075e-05,
+      "loss": 1.3756,
+      "step": 320
+    },
+    {
+      "epoch": 0.2718243596445374,
+      "grad_norm": 2.08819317817688,
+      "learning_rate": 4.899292779003014e-05,
+      "loss": 1.3286,
+      "step": 325
+    },
+    {
+      "epoch": 0.276006272869838,
+      "grad_norm": 2.1810929775238037,
+      "learning_rate": 4.896192047617156e-05,
+      "loss": 1.3884,
+      "step": 330
+    },
+    {
+      "epoch": 0.2801881860951385,
+      "grad_norm": 2.2136948108673096,
+      "learning_rate": 4.893045313633025e-05,
+      "loss": 1.2723,
+      "step": 335
+    },
+    {
+      "epoch": 0.2843700993204391,
+      "grad_norm": 2.3611645698547363,
+      "learning_rate": 4.8898526374622815e-05,
+      "loss": 1.3758,
+      "step": 340
+    },
+    {
+      "epoch": 0.2885520125457397,
+      "grad_norm": 2.2939200401306152,
+      "learning_rate": 4.886614080398594e-05,
+      "loss": 1.3727,
+      "step": 345
+    },
+    {
+      "epoch": 0.29273392577104024,
+      "grad_norm": 2.2382090091705322,
+      "learning_rate": 4.8833297046164594e-05,
+      "loss": 1.3412,
+      "step": 350
+    },
+    {
+      "epoch": 0.29691583899634083,
+      "grad_norm": 2.0420024394989014,
+      "learning_rate": 4.8799995731700155e-05,
+      "loss": 1.3378,
+      "step": 355
+    },
+    {
+      "epoch": 0.3010977522216414,
+      "grad_norm": 2.180814266204834,
+      "learning_rate": 4.8766237499918244e-05,
+      "loss": 1.3305,
+      "step": 360
+    },
+    {
+      "epoch": 0.30527966544694196,
+      "grad_norm": 2.641951560974121,
+      "learning_rate": 4.873202299891649e-05,
+      "loss": 1.3084,
+      "step": 365
+    },
+    {
+      "epoch": 0.30946157867224255,
+      "grad_norm": 2.421492099761963,
+      "learning_rate": 4.8697352885552077e-05,
+      "loss": 1.3321,
+      "step": 370
+    },
+    {
+      "epoch": 0.31364349189754315,
+      "grad_norm": 2.1777994632720947,
+      "learning_rate": 4.866222782542912e-05,
+      "loss": 1.3605,
+      "step": 375
+    },
+    {
+      "epoch": 0.3178254051228437,
+      "grad_norm": 2.097909450531006,
+      "learning_rate": 4.862664849288589e-05,
+      "loss": 1.3786,
+      "step": 380
+    },
+    {
+      "epoch": 0.3220073183481443,
+      "grad_norm": 2.3216776847839355,
+      "learning_rate": 4.8590615570981904e-05,
+      "loss": 1.3467,
+      "step": 385
+    },
+    {
+      "epoch": 0.32618923157344487,
+      "grad_norm": 2.199545383453369,
+      "learning_rate": 4.855412975148475e-05,
+      "loss": 1.3534,
+      "step": 390
+    },
+    {
+      "epoch": 0.3303711447987454,
+      "grad_norm": 2.4035983085632324,
+      "learning_rate": 4.851719173485686e-05,
+      "loss": 1.3545,
+      "step": 395
+    },
+    {
+      "epoch": 0.334553058024046,
+      "grad_norm": 2.130056142807007,
+      "learning_rate": 4.847980223024205e-05,
+      "loss": 1.3574,
+      "step": 400
+    },
+    {
+      "epoch": 0.3387349712493466,
+      "grad_norm": 2.2835471630096436,
+      "learning_rate": 4.8441961955451865e-05,
+      "loss": 1.2835,
+      "step": 405
+    },
+    {
+      "epoch": 0.34291688447464713,
+      "grad_norm": 2.129136085510254,
+      "learning_rate": 4.840367163695186e-05,
+      "loss": 1.3066,
+      "step": 410
+    },
+    {
+      "epoch": 0.3470987976999477,
+      "grad_norm": 2.199307680130005,
+      "learning_rate": 4.8364932009847614e-05,
+      "loss": 1.3891,
+      "step": 415
+    },
+    {
+      "epoch": 0.3512807109252483,
+      "grad_norm": 2.240877866744995,
+      "learning_rate": 4.8325743817870614e-05,
+      "loss": 1.3131,
+      "step": 420
+    },
+    {
+      "epoch": 0.35546262415054886,
+      "grad_norm": 2.4342916011810303,
+      "learning_rate": 4.8286107813364015e-05,
+      "loss": 1.2903,
+      "step": 425
+    },
+    {
+      "epoch": 0.35964453737584945,
+      "grad_norm": 2.323018789291382,
+      "learning_rate": 4.824602475726815e-05,
+      "loss": 1.3016,
+      "step": 430
+    },
+    {
+      "epoch": 0.36382645060115004,
+      "grad_norm": 2.2159998416900635,
+      "learning_rate": 4.820549541910595e-05,
+      "loss": 1.3312,
+      "step": 435
+    },
+    {
+      "epoch": 0.3680083638264506,
+      "grad_norm": 2.654232978820801,
+      "learning_rate": 4.8164520576968165e-05,
+      "loss": 1.3793,
+      "step": 440
+    },
+    {
+      "epoch": 0.3721902770517512,
+      "grad_norm": 2.3524513244628906,
+      "learning_rate": 4.8123101017498416e-05,
+      "loss": 1.3406,
+      "step": 445
+    },
+    {
+      "epoch": 0.37637219027705177,
+      "grad_norm": 2.3215346336364746,
+      "learning_rate": 4.8081237535878116e-05,
+      "loss": 1.3997,
+      "step": 450
+    },
+    {
+      "epoch": 0.3805541035023523,
+      "grad_norm": 2.0394012928009033,
+      "learning_rate": 4.803893093581117e-05,
+      "loss": 1.3084,
+      "step": 455
+    },
+    {
+      "epoch": 0.3847360167276529,
+      "grad_norm": 2.251598596572876,
+      "learning_rate": 4.799618202950857e-05,
+      "loss": 1.3396,
+      "step": 460
+    },
+    {
+      "epoch": 0.3889179299529535,
+      "grad_norm": 2.4240410327911377,
+      "learning_rate": 4.795299163767282e-05,
+      "loss": 1.359,
+      "step": 465
+    },
+    {
+      "epoch": 0.393099843178254,
+      "grad_norm": 2.2180769443511963,
+      "learning_rate": 4.790936058948211e-05,
+      "loss": 1.3575,
+      "step": 470
+    },
+    {
+      "epoch": 0.3972817564035546,
+      "grad_norm": 2.2782742977142334,
+      "learning_rate": 4.786528972257449e-05,
+      "loss": 1.2915,
+      "step": 475
+    },
+    {
+      "epoch": 0.4014636696288552,
+      "grad_norm": 2.2193851470947266,
+      "learning_rate": 4.7820779883031696e-05,
+      "loss": 1.3185,
+      "step": 480
+    },
+    {
+      "epoch": 0.40564558285415575,
+      "grad_norm": 2.2422704696655273,
+      "learning_rate": 4.7775831925363e-05,
+      "loss": 1.2638,
+      "step": 485
+    },
+    {
+      "epoch": 0.40982749607945634,
+      "grad_norm": 2.430154323577881,
+      "learning_rate": 4.773044671248872e-05,
+      "loss": 1.3616,
+      "step": 490
+    },
+    {
+      "epoch": 0.41400940930475694,
+      "grad_norm": 2.2115910053253174,
+      "learning_rate": 4.768462511572371e-05,
+      "loss": 1.35,
+      "step": 495
+    },
+    {
+      "epoch": 0.4181913225300575,
+      "grad_norm": 2.063385486602783,
+      "learning_rate": 4.763836801476061e-05,
+      "loss": 1.2797,
+      "step": 500
+    },
+    {
+      "epoch": 0.42237323575535807,
+      "grad_norm": 2.3508410453796387,
+      "learning_rate": 4.759167629765297e-05,
+      "loss": 1.3173,
+      "step": 505
+    },
+    {
+      "epoch": 0.42655514898065866,
+      "grad_norm": 2.3848047256469727,
+      "learning_rate": 4.7544550860798177e-05,
+      "loss": 1.2502,
+      "step": 510
+    },
+    {
+      "epoch": 0.43073706220595925,
+      "grad_norm": 2.227524757385254,
+      "learning_rate": 4.749699260892026e-05,
+      "loss": 1.3174,
+      "step": 515
+    },
+    {
+      "epoch": 0.4349189754312598,
+      "grad_norm": 2.2080676555633545,
+      "learning_rate": 4.744900245505253e-05,
+      "loss": 1.2567,
+      "step": 520
+    },
+    {
+      "epoch": 0.4391008886565604,
+      "grad_norm": 2.2167842388153076,
+      "learning_rate": 4.7400581320520055e-05,
+      "loss": 1.2906,
+      "step": 525
+    },
+    {
+      "epoch": 0.443282801881861,
+      "grad_norm": 2.4347431659698486,
+      "learning_rate": 4.735173013492193e-05,
+      "loss": 1.3109,
+      "step": 530
+    },
+    {
+      "epoch": 0.4474647151071615,
+      "grad_norm": 2.024902105331421,
+      "learning_rate": 4.73024498361135e-05,
+      "loss": 1.3265,
+      "step": 535
+    },
+    {
+      "epoch": 0.4516466283324621,
+      "grad_norm": 2.1333351135253906,
+      "learning_rate": 4.725274137018826e-05,
+      "loss": 1.3426,
+      "step": 540
+    },
+    {
+      "epoch": 0.4558285415577627,
+      "grad_norm": 2.400423049926758,
+      "learning_rate": 4.720260569145981e-05,
+      "loss": 1.2751,
+      "step": 545
+    },
+    {
+      "epoch": 0.46001045478306324,
+      "grad_norm": 2.5796918869018555,
+      "learning_rate": 4.715204376244343e-05,
+      "loss": 1.3453,
+      "step": 550
+    },
+    {
+      "epoch": 0.46419236800836383,
+      "grad_norm": 2.339895486831665,
+      "learning_rate": 4.7101056553837665e-05,
+      "loss": 1.2667,
+      "step": 555
+    },
+    {
+      "epoch": 0.4683742812336644,
+      "grad_norm": 2.273618221282959,
+      "learning_rate": 4.704964504450563e-05,
+      "loss": 1.3264,
+      "step": 560
+    },
+    {
+      "epoch": 0.47255619445896496,
+      "grad_norm": 1.9942044019699097,
+      "learning_rate": 4.69978102214563e-05,
+      "loss": 1.2907,
+      "step": 565
+    },
+    {
+      "epoch": 0.47673810768426556,
+      "grad_norm": 2.1848580837249756,
+      "learning_rate": 4.694555307982551e-05,
+      "loss": 1.2921,
+      "step": 570
+    },
+    {
+      "epoch": 0.48092002090956615,
+      "grad_norm": 2.2914299964904785,
+      "learning_rate": 4.689287462285681e-05,
+      "loss": 1.3612,
+      "step": 575
+    },
+    {
+      "epoch": 0.4851019341348667,
+      "grad_norm": 2.1165218353271484,
+      "learning_rate": 4.6839775861882306e-05,
+      "loss": 1.3419,
+      "step": 580
+    },
+    {
+      "epoch": 0.4892838473601673,
+      "grad_norm": 2.003962516784668,
+      "learning_rate": 4.678625781630315e-05,
+      "loss": 1.388,
+      "step": 585
+    },
+    {
+      "epoch": 0.49346576058546787,
+      "grad_norm": 2.366339683532715,
+      "learning_rate": 4.673232151357004e-05,
+      "loss": 1.2895,
+      "step": 590
+    },
+    {
+      "epoch": 0.4976476738107684,
+      "grad_norm": 2.4352052211761475,
+      "learning_rate": 4.667796798916343e-05,
+      "loss": 1.3457,
+      "step": 595
+    },
+    {
+      "epoch": 0.501829587036069,
+      "grad_norm": 2.4221272468566895,
+      "learning_rate": 4.662319828657371e-05,
+      "loss": 1.3298,
+      "step": 600
+    },
+    {
+      "epoch": 0.5060115002613695,
+      "grad_norm": 2.2551608085632324,
+      "learning_rate": 4.6568013457281126e-05,
+      "loss": 1.2192,
+      "step": 605
+    },
+    {
+      "epoch": 0.5101934134866701,
+      "grad_norm": 2.4560656547546387,
+      "learning_rate": 4.651241456073563e-05,
+      "loss": 1.3086,
+      "step": 610
+    },
+    {
+      "epoch": 0.5143753267119707,
+      "grad_norm": 2.266500473022461,
+      "learning_rate": 4.645640266433651e-05,
+      "loss": 1.2608,
+      "step": 615
+    },
+    {
+      "epoch": 0.5185572399372713,
+      "grad_norm": 2.175009250640869,
+      "learning_rate": 4.639997884341192e-05,
+      "loss": 1.3459,
+      "step": 620
+    },
+    {
+      "epoch": 0.5227391531625719,
+      "grad_norm": 2.329770803451538,
+      "learning_rate": 4.634314418119823e-05,
+      "loss": 1.2894,
+      "step": 625
+    },
+    {
+      "epoch": 0.5269210663878725,
+      "grad_norm": 2.545764446258545,
+      "learning_rate": 4.628589976881923e-05,
+      "loss": 1.3213,
+      "step": 630
+    },
+    {
+      "epoch": 0.531102979613173,
+      "grad_norm": 2.2759323120117188,
+      "learning_rate": 4.622824670526516e-05,
+      "loss": 1.3362,
+      "step": 635
+    },
+    {
+      "epoch": 0.5352848928384736,
+      "grad_norm": 2.341280221939087,
+      "learning_rate": 4.617018609737166e-05,
+      "loss": 1.24,
+      "step": 640
+    },
+    {
+      "epoch": 0.5394668060637742,
+      "grad_norm": 2.353301763534546,
+      "learning_rate": 4.6111719059798466e-05,
+      "loss": 1.3643,
+      "step": 645
+    },
+    {
+      "epoch": 0.5436487192890748,
+      "grad_norm": 2.223389148712158,
+      "learning_rate": 4.605284671500805e-05,
+      "loss": 1.3569,
+      "step": 650
+    },
+    {
+      "epoch": 0.5478306325143754,
+      "grad_norm": 2.2959463596343994,
+      "learning_rate": 4.599357019324405e-05,
+      "loss": 1.3581,
+      "step": 655
+    },
+    {
+      "epoch": 0.552012545739676,
+      "grad_norm": 2.1995513439178467,
+      "learning_rate": 4.593389063250958e-05,
+      "loss": 1.2962,
+      "step": 660
+    },
+    {
+      "epoch": 0.5561944589649764,
+      "grad_norm": 1.9802824258804321,
+      "learning_rate": 4.5873809178545396e-05,
+      "loss": 1.3121,
+      "step": 665
+    },
+    {
+      "epoch": 0.560376372190277,
+      "grad_norm": 2.2561113834381104,
+      "learning_rate": 4.581332698480786e-05,
+      "loss": 1.2395,
+      "step": 670
+    },
+    {
+      "epoch": 0.5645582854155776,
+      "grad_norm": 2.1277997493743896,
+      "learning_rate": 4.5752445212446836e-05,
+      "loss": 1.2782,
+      "step": 675
+    },
+    {
+      "epoch": 0.5687401986408782,
+      "grad_norm": 2.1406946182250977,
+      "learning_rate": 4.569116503028339e-05,
+      "loss": 1.3248,
+      "step": 680
+    },
+    {
+      "epoch": 0.5729221118661788,
+      "grad_norm": 2.190600872039795,
+      "learning_rate": 4.5629487614787306e-05,
+      "loss": 1.2975,
+      "step": 685
+    },
+    {
+      "epoch": 0.5771040250914794,
+      "grad_norm": 2.1068780422210693,
+      "learning_rate": 4.556741415005459e-05,
+      "loss": 1.3191,
+      "step": 690
+    },
+    {
+      "epoch": 0.5812859383167799,
+      "grad_norm": 2.3496341705322266,
+      "learning_rate": 4.5504945827784634e-05,
+      "loss": 1.2827,
+      "step": 695
+    },
+    {
+      "epoch": 0.5854678515420805,
+      "grad_norm": 2.33406400680542,
+      "learning_rate": 4.544208384725742e-05,
+      "loss": 1.2649,
+      "step": 700
+    },
+    {
+      "epoch": 0.5896497647673811,
+      "grad_norm": 2.365461587905884,
+      "learning_rate": 4.5378829415310465e-05,
+      "loss": 1.3121,
+      "step": 705
+    },
+    {
+      "epoch": 0.5938316779926817,
+      "grad_norm": 2.186875343322754,
+      "learning_rate": 4.531518374631564e-05,
+      "loss": 1.3113,
+      "step": 710
+    },
+    {
+      "epoch": 0.5980135912179823,
+      "grad_norm": 2.1798176765441895,
+      "learning_rate": 4.525114806215584e-05,
+      "loss": 1.3446,
+      "step": 715
+    },
+    {
+      "epoch": 0.6021955044432828,
+      "grad_norm": 1.9714925289154053,
+      "learning_rate": 4.518672359220161e-05,
+      "loss": 1.2979,
+      "step": 720
+    },
+    {
+      "epoch": 0.6063774176685833,
+      "grad_norm": 2.1850643157958984,
+      "learning_rate": 4.5121911573287446e-05,
+      "loss": 1.2412,
+      "step": 725
+    },
+    {
+      "epoch": 0.6105593308938839,
+      "grad_norm": 2.0708961486816406,
+      "learning_rate": 4.505671324968811e-05,
+      "loss": 1.2559,
+      "step": 730
+    },
+    {
+      "epoch": 0.6147412441191845,
+      "grad_norm": 2.461225986480713,
+      "learning_rate": 4.49911298730947e-05,
+      "loss": 1.3696,
+      "step": 735
+    },
+    {
+      "epoch": 0.6189231573444851,
+      "grad_norm": 2.2155981063842773,
+      "learning_rate": 4.492516270259066e-05,
+      "loss": 1.3459,
+      "step": 740
+    },
+    {
+      "epoch": 0.6231050705697857,
+      "grad_norm": 2.0899972915649414,
+      "learning_rate": 4.48588130046276e-05,
+      "loss": 1.2885,
+      "step": 745
+    },
+    {
+      "epoch": 0.6272869837950863,
+      "grad_norm": 2.2798969745635986,
+      "learning_rate": 4.479208205300094e-05,
+      "loss": 1.299,
+      "step": 750
+    },
+    {
+      "epoch": 0.6314688970203868,
+      "grad_norm": 2.4617793560028076,
+      "learning_rate": 4.472497112882552e-05,
+      "loss": 1.2973,
+      "step": 755
+    },
+    {
+      "epoch": 0.6356508102456874,
+      "grad_norm": 2.20271635055542,
+      "learning_rate": 4.465748152051096e-05,
+      "loss": 1.231,
+      "step": 760
+    },
+    {
+      "epoch": 0.639832723470988,
+      "grad_norm": 1.990775227546692,
+      "learning_rate": 4.458961452373692e-05,
+      "loss": 1.2594,
+      "step": 765
+    },
+    {
+      "epoch": 0.6440146366962886,
+      "grad_norm": 2.2898495197296143,
+      "learning_rate": 4.4521371441428284e-05,
+      "loss": 1.2721,
+      "step": 770
+    },
+    {
+      "epoch": 0.6481965499215891,
+      "grad_norm": 2.282844066619873,
+      "learning_rate": 4.445275358373006e-05,
+      "loss": 1.2742,
+      "step": 775
+    },
+    {
+      "epoch": 0.6523784631468897,
+      "grad_norm": 2.3958911895751953,
+      "learning_rate": 4.438376226798231e-05,
+      "loss": 1.2897,
+      "step": 780
+    },
+    {
+      "epoch": 0.6565603763721902,
+      "grad_norm": 2.2609405517578125,
+      "learning_rate": 4.43143988186948e-05,
+      "loss": 1.2891,
+      "step": 785
+    },
+    {
+      "epoch": 0.6607422895974908,
+      "grad_norm": 2.416956663131714,
+      "learning_rate": 4.42446645675216e-05,
+      "loss": 1.3711,
+      "step": 790
+    },
+    {
+      "epoch": 0.6649242028227914,
+      "grad_norm": 2.280547857284546,
+      "learning_rate": 4.4174560853235505e-05,
+      "loss": 1.3413,
+      "step": 795
+    },
+    {
+      "epoch": 0.669106116048092,
+      "grad_norm": 2.055990695953369,
+      "learning_rate": 4.410408902170235e-05,
+      "loss": 1.2829,
+      "step": 800
+    },
+    {
+      "epoch": 0.6732880292733926,
+      "grad_norm": 2.1436378955841064,
+      "learning_rate": 4.403325042585518e-05,
+      "loss": 1.2223,
+      "step": 805
+    },
+    {
+      "epoch": 0.6774699424986932,
+      "grad_norm": 2.1957428455352783,
+      "learning_rate": 4.396204642566821e-05,
+      "loss": 1.2923,
+      "step": 810
+    },
+    {
+      "epoch": 0.6816518557239938,
+      "grad_norm": 2.1543030738830566,
+      "learning_rate": 4.389047838813082e-05,
+      "loss": 1.2296,
+      "step": 815
+    },
+    {
+      "epoch": 0.6858337689492943,
+      "grad_norm": 2.1455068588256836,
+      "learning_rate": 4.3818547687221204e-05,
+      "loss": 1.2913,
+      "step": 820
+    },
+    {
+      "epoch": 0.6900156821745949,
+      "grad_norm": 2.2354376316070557,
+      "learning_rate": 4.374625570388008e-05,
+      "loss": 1.2647,
+      "step": 825
+    },
+    {
+      "epoch": 0.6941975953998955,
+      "grad_norm": 2.2896392345428467,
+      "learning_rate": 4.367360382598413e-05,
+      "loss": 1.329,
+      "step": 830
+    },
+    {
+      "epoch": 0.698379508625196,
+      "grad_norm": 2.0567495822906494,
+      "learning_rate": 4.360059344831936e-05,
+      "loss": 1.2306,
+      "step": 835
+    },
+    {
+      "epoch": 0.7025614218504966,
+      "grad_norm": 2.0631346702575684,
+      "learning_rate": 4.352722597255434e-05,
+      "loss": 1.2788,
+      "step": 840
+    },
+    {
+      "epoch": 0.7067433350757972,
+      "grad_norm": 2.3736605644226074,
+      "learning_rate": 4.345350280721328e-05,
+      "loss": 1.3236,
+      "step": 845
+    },
+    {
+      "epoch": 0.7109252483010977,
+      "grad_norm": 2.308960437774658,
+      "learning_rate": 4.337942536764901e-05,
+      "loss": 1.2993,
+      "step": 850
+    },
+    {
+      "epoch": 0.7151071615263983,
+      "grad_norm": 2.230039358139038,
+      "learning_rate": 4.330499507601575e-05,
+      "loss": 1.2544,
+      "step": 855
+    },
+    {
+      "epoch": 0.7192890747516989,
+      "grad_norm": 2.1853036880493164,
+      "learning_rate": 4.3230213361241894e-05,
+      "loss": 1.2829,
+      "step": 860
+    },
+    {
+      "epoch": 0.7234709879769995,
+      "grad_norm": 2.2859535217285156,
+      "learning_rate": 4.3155081659002506e-05,
+      "loss": 1.3128,
+      "step": 865
+    },
+    {
+      "epoch": 0.7276529012023001,
+      "grad_norm": 1.9847872257232666,
+      "learning_rate": 4.3079601411691775e-05,
+      "loss": 1.3126,
+      "step": 870
+    },
+    {
+      "epoch": 0.7318348144276007,
+      "grad_norm": 2.3204383850097656,
+      "learning_rate": 4.3003774068395355e-05,
+      "loss": 1.3275,
+      "step": 875
+    },
+    {
+      "epoch": 0.7360167276529012,
+      "grad_norm": 2.1831467151641846,
+      "learning_rate": 4.292760108486251e-05,
+      "loss": 1.3232,
+      "step": 880
+    },
+    {
+      "epoch": 0.7401986408782018,
+      "grad_norm": 2.241342544555664,
+      "learning_rate": 4.2851083923478186e-05,
+      "loss": 1.2484,
+      "step": 885
+    },
+    {
+      "epoch": 0.7443805541035023,
+      "grad_norm": 2.335024118423462,
+      "learning_rate": 4.27742240532349e-05,
+      "loss": 1.2466,
+      "step": 890
+    },
+    {
+      "epoch": 0.7485624673288029,
+      "grad_norm": 2.592941999435425,
+      "learning_rate": 4.269702294970461e-05,
+      "loss": 1.3111,
+      "step": 895
+    },
+    {
+      "epoch": 0.7527443805541035,
+      "grad_norm": 2.1964266300201416,
+      "learning_rate": 4.26194820950103e-05,
+      "loss": 1.3172,
+      "step": 900
+    },
+    {
+      "epoch": 0.7569262937794041,
+      "grad_norm": 2.253929853439331,
+      "learning_rate": 4.25416029777976e-05,
+      "loss": 1.2977,
+      "step": 905
+    },
+    {
+      "epoch": 0.7611082070047046,
+      "grad_norm": 2.3653616905212402,
+      "learning_rate": 4.246338709320615e-05,
+      "loss": 1.3397,
+      "step": 910
+    },
+    {
+      "epoch": 0.7652901202300052,
+      "grad_norm": 1.9790107011795044,
+      "learning_rate": 4.238483594284094e-05,
+      "loss": 1.299,
+      "step": 915
+    },
+    {
+      "epoch": 0.7694720334553058,
+      "grad_norm": 2.177802324295044,
+      "learning_rate": 4.230595103474345e-05,
+      "loss": 1.2083,
+      "step": 920
+    },
+    {
+      "epoch": 0.7736539466806064,
+      "grad_norm": 2.267620325088501,
+      "learning_rate": 4.222673388336272e-05,
+      "loss": 1.2712,
+      "step": 925
+    },
+    {
+      "epoch": 0.777835859905907,
+      "grad_norm": 2.323590040206909,
+      "learning_rate": 4.214718600952627e-05,
+      "loss": 1.2944,
+      "step": 930
+    },
+    {
+      "epoch": 0.7820177731312076,
+      "grad_norm": 2.2184839248657227,
+      "learning_rate": 4.2067308940410874e-05,
+      "loss": 1.3033,
+      "step": 935
+    },
+    {
+      "epoch": 0.786199686356508,
+      "grad_norm": 2.056938648223877,
+      "learning_rate": 4.1987104209513295e-05,
+      "loss": 1.2563,
+      "step": 940
+    },
+    {
+      "epoch": 0.7903815995818086,
+      "grad_norm": 2.0813541412353516,
+      "learning_rate": 4.1906573356620795e-05,
+      "loss": 1.3169,
+      "step": 945
+    },
+    {
+      "epoch": 0.7945635128071092,
+      "grad_norm": 2.2418994903564453,
+      "learning_rate": 4.182571792778163e-05,
+      "loss": 1.3366,
+      "step": 950
+    },
+    {
+      "epoch": 0.7987454260324098,
+      "grad_norm": 2.1746504306793213,
+      "learning_rate": 4.1744539475275276e-05,
+      "loss": 1.2695,
+      "step": 955
+    },
+    {
+      "epoch": 0.8029273392577104,
+      "grad_norm": 2.385899066925049,
+      "learning_rate": 4.1663039557582725e-05,
+      "loss": 1.275,
+      "step": 960
+    },
+    {
+      "epoch": 0.807109252483011,
+      "grad_norm": 2.4620730876922607,
+      "learning_rate": 4.158121973935653e-05,
+      "loss": 1.3441,
+      "step": 965
+    },
+    {
+      "epoch": 0.8112911657083115,
+      "grad_norm": 2.090711832046509,
+      "learning_rate": 4.149908159139073e-05,
+      "loss": 1.2754,
+      "step": 970
+    },
+    {
+      "epoch": 0.8154730789336121,
+      "grad_norm": 2.367952346801758,
+      "learning_rate": 4.141662669059076e-05,
+      "loss": 1.2821,
+      "step": 975
+    },
+    {
+      "epoch": 0.8196549921589127,
+      "grad_norm": 2.406475782394409,
+      "learning_rate": 4.133385661994312e-05,
+      "loss": 1.2917,
+      "step": 980
+    },
+    {
+      "epoch": 0.8238369053842133,
+      "grad_norm": 2.0637738704681396,
+      "learning_rate": 4.125077296848501e-05,
+      "loss": 1.2582,
+      "step": 985
+    },
+    {
+      "epoch": 0.8280188186095139,
+      "grad_norm": 2.3852176666259766,
+      "learning_rate": 4.1167377331273825e-05,
+      "loss": 1.2278,
+      "step": 990
+    },
+    {
+      "epoch": 0.8322007318348145,
+      "grad_norm": 2.0237960815429688,
+      "learning_rate": 4.1083671309356526e-05,
+      "loss": 1.3461,
+      "step": 995
+    },
+    {
+      "epoch": 0.836382645060115,
+      "grad_norm": 2.458031177520752,
+      "learning_rate": 4.0999656509738904e-05,
+      "loss": 1.2484,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 3585,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2932056998425395e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ad489884f87ec96cc1e49b25622db5c6c3c1eafcad1be5306265a7460b6619a
+size 5304

checkpoint-1100/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+---
+
+# 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 0.11.1

checkpoint-1100/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68ae2337969e49f4d260bc6f2c040def77384c87ba80728caae17d7611cf1d6b
+size 13648432

checkpoint-1100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1b11dcfa1e30bf17cb557d11e79c056b3a788d0a65364c69856dbdcb564c1a0
+size 27370618

checkpoint-1100/rng_state.pth

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

checkpoint-1100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bafd80ca1b4b768a36222bdb98758dc12047628d69993444a379c4cc3ee39ab9
+size 1064

checkpoint-1100/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1100/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

checkpoint-1100/trainer_state.json

@@ -0,0 +1,1573 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9200209095661265,
+  "eval_steps": 500,
+  "global_step": 1100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004181913225300575,
+      "grad_norm": 3.3295910358428955,
+      "learning_rate": 4.9999760022374266e-05,
+      "loss": 1.8032,
+      "step": 5
+    },
+    {
+      "epoch": 0.00836382645060115,
+      "grad_norm": 2.002122163772583,
+      "learning_rate": 4.999904009410418e-05,
+      "loss": 1.5943,
+      "step": 10
+    },
+    {
+      "epoch": 0.012545739675901725,
+      "grad_norm": 1.9293591976165771,
+      "learning_rate": 4.9997840229011085e-05,
+      "loss": 1.5378,
+      "step": 15
+    },
+    {
+      "epoch": 0.0167276529012023,
+      "grad_norm": 1.936969518661499,
+      "learning_rate": 4.999616045013025e-05,
+      "loss": 1.5856,
+      "step": 20
+    },
+    {
+      "epoch": 0.020909566126502875,
+      "grad_norm": 1.8237314224243164,
+      "learning_rate": 4.9994000789710415e-05,
+      "loss": 1.5066,
+      "step": 25
+    },
+    {
+      "epoch": 0.02509147935180345,
+      "grad_norm": 1.8101543188095093,
+      "learning_rate": 4.9991361289213203e-05,
+      "loss": 1.4499,
+      "step": 30
+    },
+    {
+      "epoch": 0.029273392577104027,
+      "grad_norm": 1.647802710533142,
+      "learning_rate": 4.998824199931228e-05,
+      "loss": 1.4694,
+      "step": 35
+    },
+    {
+      "epoch": 0.0334553058024046,
+      "grad_norm": 1.7077428102493286,
+      "learning_rate": 4.998464297989245e-05,
+      "loss": 1.4945,
+      "step": 40
+    },
+    {
+      "epoch": 0.03763721902770518,
+      "grad_norm": 1.7119005918502808,
+      "learning_rate": 4.998056430004844e-05,
+      "loss": 1.4257,
+      "step": 45
+    },
+    {
+      "epoch": 0.04181913225300575,
+      "grad_norm": 2.0229578018188477,
+      "learning_rate": 4.997600603808359e-05,
+      "loss": 1.4713,
+      "step": 50
+    },
+    {
+      "epoch": 0.04600104547830632,
+      "grad_norm": 1.885362148284912,
+      "learning_rate": 4.997096828150838e-05,
+      "loss": 1.5145,
+      "step": 55
+    },
+    {
+      "epoch": 0.0501829587036069,
+      "grad_norm": 2.0357539653778076,
+      "learning_rate": 4.9965451127038714e-05,
+      "loss": 1.3811,
+      "step": 60
+    },
+    {
+      "epoch": 0.054364871928907474,
+      "grad_norm": 1.9780900478363037,
+      "learning_rate": 4.9959454680594086e-05,
+      "loss": 1.412,
+      "step": 65
+    },
+    {
+      "epoch": 0.05854678515420805,
+      "grad_norm": 1.6695700883865356,
+      "learning_rate": 4.995297905729554e-05,
+      "loss": 1.4093,
+      "step": 70
+    },
+    {
+      "epoch": 0.06272869837950862,
+      "grad_norm": 1.9424223899841309,
+      "learning_rate": 4.994602438146344e-05,
+      "loss": 1.4615,
+      "step": 75
+    },
+    {
+      "epoch": 0.0669106116048092,
+      "grad_norm": 1.9082552194595337,
+      "learning_rate": 4.9938590786615126e-05,
+      "loss": 1.4169,
+      "step": 80
+    },
+    {
+      "epoch": 0.07109252483010978,
+      "grad_norm": 1.8944685459136963,
+      "learning_rate": 4.993067841546231e-05,
+      "loss": 1.3064,
+      "step": 85
+    },
+    {
+      "epoch": 0.07527443805541036,
+      "grad_norm": 1.9688103199005127,
+      "learning_rate": 4.992228741990834e-05,
+      "loss": 1.3778,
+      "step": 90
+    },
+    {
+      "epoch": 0.07945635128071092,
+      "grad_norm": 2.0939650535583496,
+      "learning_rate": 4.991341796104534e-05,
+      "loss": 1.3905,
+      "step": 95
+    },
+    {
+      "epoch": 0.0836382645060115,
+      "grad_norm": 1.868986964225769,
+      "learning_rate": 4.9904070209151015e-05,
+      "loss": 1.3723,
+      "step": 100
+    },
+    {
+      "epoch": 0.08782017773131208,
+      "grad_norm": 2.069476842880249,
+      "learning_rate": 4.989424434368549e-05,
+      "loss": 1.4046,
+      "step": 105
+    },
+    {
+      "epoch": 0.09200209095661264,
+      "grad_norm": 2.1500356197357178,
+      "learning_rate": 4.988394055328779e-05,
+      "loss": 1.4319,
+      "step": 110
+    },
+    {
+      "epoch": 0.09618400418191322,
+      "grad_norm": 1.9786696434020996,
+      "learning_rate": 4.987315903577223e-05,
+      "loss": 1.4203,
+      "step": 115
+    },
+    {
+      "epoch": 0.1003659174072138,
+      "grad_norm": 2.035172939300537,
+      "learning_rate": 4.986189999812468e-05,
+      "loss": 1.4046,
+      "step": 120
+    },
+    {
+      "epoch": 0.10454783063251437,
+      "grad_norm": 1.9887930154800415,
+      "learning_rate": 4.985016365649848e-05,
+      "loss": 1.3836,
+      "step": 125
+    },
+    {
+      "epoch": 0.10872974385781495,
+      "grad_norm": 1.8339554071426392,
+      "learning_rate": 4.983795023621041e-05,
+      "loss": 1.3468,
+      "step": 130
+    },
+    {
+      "epoch": 0.11291165708311553,
+      "grad_norm": 2.06648588180542,
+      "learning_rate": 4.982525997173625e-05,
+      "loss": 1.3481,
+      "step": 135
+    },
+    {
+      "epoch": 0.1170935703084161,
+      "grad_norm": 2.1179702281951904,
+      "learning_rate": 4.9812093106706376e-05,
+      "loss": 1.4475,
+      "step": 140
+    },
+    {
+      "epoch": 0.12127548353371667,
+      "grad_norm": 2.1708436012268066,
+      "learning_rate": 4.979844989390104e-05,
+      "loss": 1.3662,
+      "step": 145
+    },
+    {
+      "epoch": 0.12545739675901724,
+      "grad_norm": 2.0533807277679443,
+      "learning_rate": 4.978433059524548e-05,
+      "loss": 1.3856,
+      "step": 150
+    },
+    {
+      "epoch": 0.12963930998431783,
+      "grad_norm": 1.9418696165084839,
+      "learning_rate": 4.976973548180498e-05,
+      "loss": 1.357,
+      "step": 155
+    },
+    {
+      "epoch": 0.1338212232096184,
+      "grad_norm": 2.1071596145629883,
+      "learning_rate": 4.975466483377959e-05,
+      "loss": 1.3613,
+      "step": 160
+    },
+    {
+      "epoch": 0.138003136434919,
+      "grad_norm": 2.3704464435577393,
+      "learning_rate": 4.9739118940498766e-05,
+      "loss": 1.3985,
+      "step": 165
+    },
+    {
+      "epoch": 0.14218504966021955,
+      "grad_norm": 2.1726176738739014,
+      "learning_rate": 4.9723098100415844e-05,
+      "loss": 1.4361,
+      "step": 170
+    },
+    {
+      "epoch": 0.14636696288552012,
+      "grad_norm": 2.608517646789551,
+      "learning_rate": 4.970660262110227e-05,
+      "loss": 1.3565,
+      "step": 175
+    },
+    {
+      "epoch": 0.1505488761108207,
+      "grad_norm": 2.185563564300537,
+      "learning_rate": 4.968963281924173e-05,
+      "loss": 1.2957,
+      "step": 180
+    },
+    {
+      "epoch": 0.15473078933612128,
+      "grad_norm": 1.9632441997528076,
+      "learning_rate": 4.967218902062403e-05,
+      "loss": 1.2833,
+      "step": 185
+    },
+    {
+      "epoch": 0.15891270256142184,
+      "grad_norm": 2.303462028503418,
+      "learning_rate": 4.96542715601389e-05,
+      "loss": 1.3238,
+      "step": 190
+    },
+    {
+      "epoch": 0.16309461578672244,
+      "grad_norm": 2.3211796283721924,
+      "learning_rate": 4.9635880781769495e-05,
+      "loss": 1.3848,
+      "step": 195
+    },
+    {
+      "epoch": 0.167276529012023,
+      "grad_norm": 2.0993776321411133,
+      "learning_rate": 4.961701703858584e-05,
+      "loss": 1.3997,
+      "step": 200
+    },
+    {
+      "epoch": 0.17145844223732357,
+      "grad_norm": 2.210942506790161,
+      "learning_rate": 4.9597680692738056e-05,
+      "loss": 1.334,
+      "step": 205
+    },
+    {
+      "epoch": 0.17564035546262416,
+      "grad_norm": 2.1277225017547607,
+      "learning_rate": 4.957787211544935e-05,
+      "loss": 1.3338,
+      "step": 210
+    },
+    {
+      "epoch": 0.17982226868792472,
+      "grad_norm": 2.287722587585449,
+      "learning_rate": 4.9557591687008966e-05,
+      "loss": 1.3621,
+      "step": 215
+    },
+    {
+      "epoch": 0.1840041819132253,
+      "grad_norm": 2.113842010498047,
+      "learning_rate": 4.9536839796764825e-05,
+      "loss": 1.3808,
+      "step": 220
+    },
+    {
+      "epoch": 0.18818609513852588,
+      "grad_norm": 2.0642735958099365,
+      "learning_rate": 4.951561684311608e-05,
+      "loss": 1.3429,
+      "step": 225
+    },
+    {
+      "epoch": 0.19236800836382645,
+      "grad_norm": 2.2026379108428955,
+      "learning_rate": 4.9493923233505435e-05,
+      "loss": 1.2855,
+      "step": 230
+    },
+    {
+      "epoch": 0.196549921589127,
+      "grad_norm": 2.2843308448791504,
+      "learning_rate": 4.947175938441138e-05,
+      "loss": 1.3432,
+      "step": 235
+    },
+    {
+      "epoch": 0.2007318348144276,
+      "grad_norm": 2.126749038696289,
+      "learning_rate": 4.9449125721340145e-05,
+      "loss": 1.3753,
+      "step": 240
+    },
+    {
+      "epoch": 0.20491374803972817,
+      "grad_norm": 2.514599561691284,
+      "learning_rate": 4.942602267881755e-05,
+      "loss": 1.3101,
+      "step": 245
+    },
+    {
+      "epoch": 0.20909566126502874,
+      "grad_norm": 2.2043542861938477,
+      "learning_rate": 4.940245070038064e-05,
+      "loss": 1.3395,
+      "step": 250
+    },
+    {
+      "epoch": 0.21327757449032933,
+      "grad_norm": 2.152742862701416,
+      "learning_rate": 4.937841023856923e-05,
+      "loss": 1.3188,
+      "step": 255
+    },
+    {
+      "epoch": 0.2174594877156299,
+      "grad_norm": 2.221057415008545,
+      "learning_rate": 4.935390175491716e-05,
+      "loss": 1.4205,
+      "step": 260
+    },
+    {
+      "epoch": 0.2216414009409305,
+      "grad_norm": 2.600109100341797,
+      "learning_rate": 4.932892571994342e-05,
+      "loss": 1.3499,
+      "step": 265
+    },
+    {
+      "epoch": 0.22582331416623105,
+      "grad_norm": 2.2291276454925537,
+      "learning_rate": 4.9303482613143194e-05,
+      "loss": 1.3984,
+      "step": 270
+    },
+    {
+      "epoch": 0.23000522739153162,
+      "grad_norm": 2.338000774383545,
+      "learning_rate": 4.9277572922978586e-05,
+      "loss": 1.344,
+      "step": 275
+    },
+    {
+      "epoch": 0.2341871406168322,
+      "grad_norm": 2.3423988819122314,
+      "learning_rate": 4.925119714686928e-05,
+      "loss": 1.2696,
+      "step": 280
+    },
+    {
+      "epoch": 0.23836905384213278,
+      "grad_norm": 2.433870553970337,
+      "learning_rate": 4.9224355791182955e-05,
+      "loss": 1.3903,
+      "step": 285
+    },
+    {
+      "epoch": 0.24255096706743334,
+      "grad_norm": 2.281836986541748,
+      "learning_rate": 4.919704937122559e-05,
+      "loss": 1.3694,
+      "step": 290
+    },
+    {
+      "epoch": 0.24673288029273394,
+      "grad_norm": 2.2429168224334717,
+      "learning_rate": 4.916927841123159e-05,
+      "loss": 1.3541,
+      "step": 295
+    },
+    {
+      "epoch": 0.2509147935180345,
+      "grad_norm": 2.4559881687164307,
+      "learning_rate": 4.9141043444353674e-05,
+      "loss": 1.3795,
+      "step": 300
+    },
+    {
+      "epoch": 0.25509670674333507,
+      "grad_norm": 2.7529919147491455,
+      "learning_rate": 4.911234501265266e-05,
+      "loss": 1.386,
+      "step": 305
+    },
+    {
+      "epoch": 0.25927861996863566,
+      "grad_norm": 2.229973554611206,
+      "learning_rate": 4.9083183667087064e-05,
+      "loss": 1.3653,
+      "step": 310
+    },
+    {
+      "epoch": 0.26346053319393625,
+      "grad_norm": 2.38677716255188,
+      "learning_rate": 4.9053559967502535e-05,
+      "loss": 1.3254,
+      "step": 315
+    },
+    {
+      "epoch": 0.2676424464192368,
+      "grad_norm": 2.292898416519165,
+      "learning_rate": 4.9023474482621075e-05,
+      "loss": 1.3756,
+      "step": 320
+    },
+    {
+      "epoch": 0.2718243596445374,
+      "grad_norm": 2.08819317817688,
+      "learning_rate": 4.899292779003014e-05,
+      "loss": 1.3286,
+      "step": 325
+    },
+    {
+      "epoch": 0.276006272869838,
+      "grad_norm": 2.1810929775238037,
+      "learning_rate": 4.896192047617156e-05,
+      "loss": 1.3884,
+      "step": 330
+    },
+    {
+      "epoch": 0.2801881860951385,
+      "grad_norm": 2.2136948108673096,
+      "learning_rate": 4.893045313633025e-05,
+      "loss": 1.2723,
+      "step": 335
+    },
+    {
+      "epoch": 0.2843700993204391,
+      "grad_norm": 2.3611645698547363,
+      "learning_rate": 4.8898526374622815e-05,
+      "loss": 1.3758,
+      "step": 340
+    },
+    {
+      "epoch": 0.2885520125457397,
+      "grad_norm": 2.2939200401306152,
+      "learning_rate": 4.886614080398594e-05,
+      "loss": 1.3727,
+      "step": 345
+    },
+    {
+      "epoch": 0.29273392577104024,
+      "grad_norm": 2.2382090091705322,
+      "learning_rate": 4.8833297046164594e-05,
+      "loss": 1.3412,
+      "step": 350
+    },
+    {
+      "epoch": 0.29691583899634083,
+      "grad_norm": 2.0420024394989014,
+      "learning_rate": 4.8799995731700155e-05,
+      "loss": 1.3378,
+      "step": 355
+    },
+    {
+      "epoch": 0.3010977522216414,
+      "grad_norm": 2.180814266204834,
+      "learning_rate": 4.8766237499918244e-05,
+      "loss": 1.3305,
+      "step": 360
+    },
+    {
+      "epoch": 0.30527966544694196,
+      "grad_norm": 2.641951560974121,
+      "learning_rate": 4.873202299891649e-05,
+      "loss": 1.3084,
+      "step": 365
+    },
+    {
+      "epoch": 0.30946157867224255,
+      "grad_norm": 2.421492099761963,
+      "learning_rate": 4.8697352885552077e-05,
+      "loss": 1.3321,
+      "step": 370
+    },
+    {
+      "epoch": 0.31364349189754315,
+      "grad_norm": 2.1777994632720947,
+      "learning_rate": 4.866222782542912e-05,
+      "loss": 1.3605,
+      "step": 375
+    },
+    {
+      "epoch": 0.3178254051228437,
+      "grad_norm": 2.097909450531006,
+      "learning_rate": 4.862664849288589e-05,
+      "loss": 1.3786,
+      "step": 380
+    },
+    {
+      "epoch": 0.3220073183481443,
+      "grad_norm": 2.3216776847839355,
+      "learning_rate": 4.8590615570981904e-05,
+      "loss": 1.3467,
+      "step": 385
+    },
+    {
+      "epoch": 0.32618923157344487,
+      "grad_norm": 2.199545383453369,
+      "learning_rate": 4.855412975148475e-05,
+      "loss": 1.3534,
+      "step": 390
+    },
+    {
+      "epoch": 0.3303711447987454,
+      "grad_norm": 2.4035983085632324,
+      "learning_rate": 4.851719173485686e-05,
+      "loss": 1.3545,
+      "step": 395
+    },
+    {
+      "epoch": 0.334553058024046,
+      "grad_norm": 2.130056142807007,
+      "learning_rate": 4.847980223024205e-05,
+      "loss": 1.3574,
+      "step": 400
+    },
+    {
+      "epoch": 0.3387349712493466,
+      "grad_norm": 2.2835471630096436,
+      "learning_rate": 4.8441961955451865e-05,
+      "loss": 1.2835,
+      "step": 405
+    },
+    {
+      "epoch": 0.34291688447464713,
+      "grad_norm": 2.129136085510254,
+      "learning_rate": 4.840367163695186e-05,
+      "loss": 1.3066,
+      "step": 410
+    },
+    {
+      "epoch": 0.3470987976999477,
+      "grad_norm": 2.199307680130005,
+      "learning_rate": 4.8364932009847614e-05,
+      "loss": 1.3891,
+      "step": 415
+    },
+    {
+      "epoch": 0.3512807109252483,
+      "grad_norm": 2.240877866744995,
+      "learning_rate": 4.8325743817870614e-05,
+      "loss": 1.3131,
+      "step": 420
+    },
+    {
+      "epoch": 0.35546262415054886,
+      "grad_norm": 2.4342916011810303,
+      "learning_rate": 4.8286107813364015e-05,
+      "loss": 1.2903,
+      "step": 425
+    },
+    {
+      "epoch": 0.35964453737584945,
+      "grad_norm": 2.323018789291382,
+      "learning_rate": 4.824602475726815e-05,
+      "loss": 1.3016,
+      "step": 430
+    },
+    {
+      "epoch": 0.36382645060115004,
+      "grad_norm": 2.2159998416900635,
+      "learning_rate": 4.820549541910595e-05,
+      "loss": 1.3312,
+      "step": 435
+    },
+    {
+      "epoch": 0.3680083638264506,
+      "grad_norm": 2.654232978820801,
+      "learning_rate": 4.8164520576968165e-05,
+      "loss": 1.3793,
+      "step": 440
+    },
+    {
+      "epoch": 0.3721902770517512,
+      "grad_norm": 2.3524513244628906,
+      "learning_rate": 4.8123101017498416e-05,
+      "loss": 1.3406,
+      "step": 445
+    },
+    {
+      "epoch": 0.37637219027705177,
+      "grad_norm": 2.3215346336364746,
+      "learning_rate": 4.8081237535878116e-05,
+      "loss": 1.3997,
+      "step": 450
+    },
+    {
+      "epoch": 0.3805541035023523,
+      "grad_norm": 2.0394012928009033,
+      "learning_rate": 4.803893093581117e-05,
+      "loss": 1.3084,
+      "step": 455
+    },
+    {
+      "epoch": 0.3847360167276529,
+      "grad_norm": 2.251598596572876,
+      "learning_rate": 4.799618202950857e-05,
+      "loss": 1.3396,
+      "step": 460
+    },
+    {
+      "epoch": 0.3889179299529535,
+      "grad_norm": 2.4240410327911377,
+      "learning_rate": 4.795299163767282e-05,
+      "loss": 1.359,
+      "step": 465
+    },
+    {
+      "epoch": 0.393099843178254,
+      "grad_norm": 2.2180769443511963,
+      "learning_rate": 4.790936058948211e-05,
+      "loss": 1.3575,
+      "step": 470
+    },
+    {
+      "epoch": 0.3972817564035546,
+      "grad_norm": 2.2782742977142334,
+      "learning_rate": 4.786528972257449e-05,
+      "loss": 1.2915,
+      "step": 475
+    },
+    {
+      "epoch": 0.4014636696288552,
+      "grad_norm": 2.2193851470947266,
+      "learning_rate": 4.7820779883031696e-05,
+      "loss": 1.3185,
+      "step": 480
+    },
+    {
+      "epoch": 0.40564558285415575,
+      "grad_norm": 2.2422704696655273,
+      "learning_rate": 4.7775831925363e-05,
+      "loss": 1.2638,
+      "step": 485
+    },
+    {
+      "epoch": 0.40982749607945634,
+      "grad_norm": 2.430154323577881,
+      "learning_rate": 4.773044671248872e-05,
+      "loss": 1.3616,
+      "step": 490
+    },
+    {
+      "epoch": 0.41400940930475694,
+      "grad_norm": 2.2115910053253174,
+      "learning_rate": 4.768462511572371e-05,
+      "loss": 1.35,
+      "step": 495
+    },
+    {
+      "epoch": 0.4181913225300575,
+      "grad_norm": 2.063385486602783,
+      "learning_rate": 4.763836801476061e-05,
+      "loss": 1.2797,
+      "step": 500
+    },
+    {
+      "epoch": 0.42237323575535807,
+      "grad_norm": 2.3508410453796387,
+      "learning_rate": 4.759167629765297e-05,
+      "loss": 1.3173,
+      "step": 505
+    },
+    {
+      "epoch": 0.42655514898065866,
+      "grad_norm": 2.3848047256469727,
+      "learning_rate": 4.7544550860798177e-05,
+      "loss": 1.2502,
+      "step": 510
+    },
+    {
+      "epoch": 0.43073706220595925,
+      "grad_norm": 2.227524757385254,
+      "learning_rate": 4.749699260892026e-05,
+      "loss": 1.3174,
+      "step": 515
+    },
+    {
+      "epoch": 0.4349189754312598,
+      "grad_norm": 2.2080676555633545,
+      "learning_rate": 4.744900245505253e-05,
+      "loss": 1.2567,
+      "step": 520
+    },
+    {
+      "epoch": 0.4391008886565604,
+      "grad_norm": 2.2167842388153076,
+      "learning_rate": 4.7400581320520055e-05,
+      "loss": 1.2906,
+      "step": 525
+    },
+    {
+      "epoch": 0.443282801881861,
+      "grad_norm": 2.4347431659698486,
+      "learning_rate": 4.735173013492193e-05,
+      "loss": 1.3109,
+      "step": 530
+    },
+    {
+      "epoch": 0.4474647151071615,
+      "grad_norm": 2.024902105331421,
+      "learning_rate": 4.73024498361135e-05,
+      "loss": 1.3265,
+      "step": 535
+    },
+    {
+      "epoch": 0.4516466283324621,
+      "grad_norm": 2.1333351135253906,
+      "learning_rate": 4.725274137018826e-05,
+      "loss": 1.3426,
+      "step": 540
+    },
+    {
+      "epoch": 0.4558285415577627,
+      "grad_norm": 2.400423049926758,
+      "learning_rate": 4.720260569145981e-05,
+      "loss": 1.2751,
+      "step": 545
+    },
+    {
+      "epoch": 0.46001045478306324,
+      "grad_norm": 2.5796918869018555,
+      "learning_rate": 4.715204376244343e-05,
+      "loss": 1.3453,
+      "step": 550
+    },
+    {
+      "epoch": 0.46419236800836383,
+      "grad_norm": 2.339895486831665,
+      "learning_rate": 4.7101056553837665e-05,
+      "loss": 1.2667,
+      "step": 555
+    },
+    {
+      "epoch": 0.4683742812336644,
+      "grad_norm": 2.273618221282959,
+      "learning_rate": 4.704964504450563e-05,
+      "loss": 1.3264,
+      "step": 560
+    },
+    {
+      "epoch": 0.47255619445896496,
+      "grad_norm": 1.9942044019699097,
+      "learning_rate": 4.69978102214563e-05,
+      "loss": 1.2907,
+      "step": 565
+    },
+    {
+      "epoch": 0.47673810768426556,
+      "grad_norm": 2.1848580837249756,
+      "learning_rate": 4.694555307982551e-05,
+      "loss": 1.2921,
+      "step": 570
+    },
+    {
+      "epoch": 0.48092002090956615,
+      "grad_norm": 2.2914299964904785,
+      "learning_rate": 4.689287462285681e-05,
+      "loss": 1.3612,
+      "step": 575
+    },
+    {
+      "epoch": 0.4851019341348667,
+      "grad_norm": 2.1165218353271484,
+      "learning_rate": 4.6839775861882306e-05,
+      "loss": 1.3419,
+      "step": 580
+    },
+    {
+      "epoch": 0.4892838473601673,
+      "grad_norm": 2.003962516784668,
+      "learning_rate": 4.678625781630315e-05,
+      "loss": 1.388,
+      "step": 585
+    },
+    {
+      "epoch": 0.49346576058546787,
+      "grad_norm": 2.366339683532715,
+      "learning_rate": 4.673232151357004e-05,
+      "loss": 1.2895,
+      "step": 590
+    },
+    {
+      "epoch": 0.4976476738107684,
+      "grad_norm": 2.4352052211761475,
+      "learning_rate": 4.667796798916343e-05,
+      "loss": 1.3457,
+      "step": 595
+    },
+    {
+      "epoch": 0.501829587036069,
+      "grad_norm": 2.4221272468566895,
+      "learning_rate": 4.662319828657371e-05,
+      "loss": 1.3298,
+      "step": 600
+    },
+    {
+      "epoch": 0.5060115002613695,
+      "grad_norm": 2.2551608085632324,
+      "learning_rate": 4.6568013457281126e-05,
+      "loss": 1.2192,
+      "step": 605
+    },
+    {
+      "epoch": 0.5101934134866701,
+      "grad_norm": 2.4560656547546387,
+      "learning_rate": 4.651241456073563e-05,
+      "loss": 1.3086,
+      "step": 610
+    },
+    {
+      "epoch": 0.5143753267119707,
+      "grad_norm": 2.266500473022461,
+      "learning_rate": 4.645640266433651e-05,
+      "loss": 1.2608,
+      "step": 615
+    },
+    {
+      "epoch": 0.5185572399372713,
+      "grad_norm": 2.175009250640869,
+      "learning_rate": 4.639997884341192e-05,
+      "loss": 1.3459,
+      "step": 620
+    },
+    {
+      "epoch": 0.5227391531625719,
+      "grad_norm": 2.329770803451538,
+      "learning_rate": 4.634314418119823e-05,
+      "loss": 1.2894,
+      "step": 625
+    },
+    {
+      "epoch": 0.5269210663878725,
+      "grad_norm": 2.545764446258545,
+      "learning_rate": 4.628589976881923e-05,
+      "loss": 1.3213,
+      "step": 630
+    },
+    {
+      "epoch": 0.531102979613173,
+      "grad_norm": 2.2759323120117188,
+      "learning_rate": 4.622824670526516e-05,
+      "loss": 1.3362,
+      "step": 635
+    },
+    {
+      "epoch": 0.5352848928384736,
+      "grad_norm": 2.341280221939087,
+      "learning_rate": 4.617018609737166e-05,
+      "loss": 1.24,
+      "step": 640
+    },
+    {
+      "epoch": 0.5394668060637742,
+      "grad_norm": 2.353301763534546,
+      "learning_rate": 4.6111719059798466e-05,
+      "loss": 1.3643,
+      "step": 645
+    },
+    {
+      "epoch": 0.5436487192890748,
+      "grad_norm": 2.223389148712158,
+      "learning_rate": 4.605284671500805e-05,
+      "loss": 1.3569,
+      "step": 650
+    },
+    {
+      "epoch": 0.5478306325143754,
+      "grad_norm": 2.2959463596343994,
+      "learning_rate": 4.599357019324405e-05,
+      "loss": 1.3581,
+      "step": 655
+    },
+    {
+      "epoch": 0.552012545739676,
+      "grad_norm": 2.1995513439178467,
+      "learning_rate": 4.593389063250958e-05,
+      "loss": 1.2962,
+      "step": 660
+    },
+    {
+      "epoch": 0.5561944589649764,
+      "grad_norm": 1.9802824258804321,
+      "learning_rate": 4.5873809178545396e-05,
+      "loss": 1.3121,
+      "step": 665
+    },
+    {
+      "epoch": 0.560376372190277,
+      "grad_norm": 2.2561113834381104,
+      "learning_rate": 4.581332698480786e-05,
+      "loss": 1.2395,
+      "step": 670
+    },
+    {
+      "epoch": 0.5645582854155776,
+      "grad_norm": 2.1277997493743896,
+      "learning_rate": 4.5752445212446836e-05,
+      "loss": 1.2782,
+      "step": 675
+    },
+    {
+      "epoch": 0.5687401986408782,
+      "grad_norm": 2.1406946182250977,
+      "learning_rate": 4.569116503028339e-05,
+      "loss": 1.3248,
+      "step": 680
+    },
+    {
+      "epoch": 0.5729221118661788,
+      "grad_norm": 2.190600872039795,
+      "learning_rate": 4.5629487614787306e-05,
+      "loss": 1.2975,
+      "step": 685
+    },
+    {
+      "epoch": 0.5771040250914794,
+      "grad_norm": 2.1068780422210693,
+      "learning_rate": 4.556741415005459e-05,
+      "loss": 1.3191,
+      "step": 690
+    },
+    {
+      "epoch": 0.5812859383167799,
+      "grad_norm": 2.3496341705322266,
+      "learning_rate": 4.5504945827784634e-05,
+      "loss": 1.2827,
+      "step": 695
+    },
+    {
+      "epoch": 0.5854678515420805,
+      "grad_norm": 2.33406400680542,
+      "learning_rate": 4.544208384725742e-05,
+      "loss": 1.2649,
+      "step": 700
+    },
+    {
+      "epoch": 0.5896497647673811,
+      "grad_norm": 2.365461587905884,
+      "learning_rate": 4.5378829415310465e-05,
+      "loss": 1.3121,
+      "step": 705
+    },
+    {
+      "epoch": 0.5938316779926817,
+      "grad_norm": 2.186875343322754,
+      "learning_rate": 4.531518374631564e-05,
+      "loss": 1.3113,
+      "step": 710
+    },
+    {
+      "epoch": 0.5980135912179823,
+      "grad_norm": 2.1798176765441895,
+      "learning_rate": 4.525114806215584e-05,
+      "loss": 1.3446,
+      "step": 715
+    },
+    {
+      "epoch": 0.6021955044432828,
+      "grad_norm": 1.9714925289154053,
+      "learning_rate": 4.518672359220161e-05,
+      "loss": 1.2979,
+      "step": 720
+    },
+    {
+      "epoch": 0.6063774176685833,
+      "grad_norm": 2.1850643157958984,
+      "learning_rate": 4.5121911573287446e-05,
+      "loss": 1.2412,
+      "step": 725
+    },
+    {
+      "epoch": 0.6105593308938839,
+      "grad_norm": 2.0708961486816406,
+      "learning_rate": 4.505671324968811e-05,
+      "loss": 1.2559,
+      "step": 730
+    },
+    {
+      "epoch": 0.6147412441191845,
+      "grad_norm": 2.461225986480713,
+      "learning_rate": 4.49911298730947e-05,
+      "loss": 1.3696,
+      "step": 735
+    },
+    {
+      "epoch": 0.6189231573444851,
+      "grad_norm": 2.2155981063842773,
+      "learning_rate": 4.492516270259066e-05,
+      "loss": 1.3459,
+      "step": 740
+    },
+    {
+      "epoch": 0.6231050705697857,
+      "grad_norm": 2.0899972915649414,
+      "learning_rate": 4.48588130046276e-05,
+      "loss": 1.2885,
+      "step": 745
+    },
+    {
+      "epoch": 0.6272869837950863,
+      "grad_norm": 2.2798969745635986,
+      "learning_rate": 4.479208205300094e-05,
+      "loss": 1.299,
+      "step": 750
+    },
+    {
+      "epoch": 0.6314688970203868,
+      "grad_norm": 2.4617793560028076,
+      "learning_rate": 4.472497112882552e-05,
+      "loss": 1.2973,
+      "step": 755
+    },
+    {
+      "epoch": 0.6356508102456874,
+      "grad_norm": 2.20271635055542,
+      "learning_rate": 4.465748152051096e-05,
+      "loss": 1.231,
+      "step": 760
+    },
+    {
+      "epoch": 0.639832723470988,
+      "grad_norm": 1.990775227546692,
+      "learning_rate": 4.458961452373692e-05,
+      "loss": 1.2594,
+      "step": 765
+    },
+    {
+      "epoch": 0.6440146366962886,
+      "grad_norm": 2.2898495197296143,
+      "learning_rate": 4.4521371441428284e-05,
+      "loss": 1.2721,
+      "step": 770
+    },
+    {
+      "epoch": 0.6481965499215891,
+      "grad_norm": 2.282844066619873,
+      "learning_rate": 4.445275358373006e-05,
+      "loss": 1.2742,
+      "step": 775
+    },
+    {
+      "epoch": 0.6523784631468897,
+      "grad_norm": 2.3958911895751953,
+      "learning_rate": 4.438376226798231e-05,
+      "loss": 1.2897,
+      "step": 780
+    },
+    {
+      "epoch": 0.6565603763721902,
+      "grad_norm": 2.2609405517578125,
+      "learning_rate": 4.43143988186948e-05,
+      "loss": 1.2891,
+      "step": 785
+    },
+    {
+      "epoch": 0.6607422895974908,
+      "grad_norm": 2.416956663131714,
+      "learning_rate": 4.42446645675216e-05,
+      "loss": 1.3711,
+      "step": 790
+    },
+    {
+      "epoch": 0.6649242028227914,
+      "grad_norm": 2.280547857284546,
+      "learning_rate": 4.4174560853235505e-05,
+      "loss": 1.3413,
+      "step": 795
+    },
+    {
+      "epoch": 0.669106116048092,
+      "grad_norm": 2.055990695953369,
+      "learning_rate": 4.410408902170235e-05,
+      "loss": 1.2829,
+      "step": 800
+    },
+    {
+      "epoch": 0.6732880292733926,
+      "grad_norm": 2.1436378955841064,
+      "learning_rate": 4.403325042585518e-05,
+      "loss": 1.2223,
+      "step": 805
+    },
+    {
+      "epoch": 0.6774699424986932,
+      "grad_norm": 2.1957428455352783,
+      "learning_rate": 4.396204642566821e-05,
+      "loss": 1.2923,
+      "step": 810
+    },
+    {
+      "epoch": 0.6816518557239938,
+      "grad_norm": 2.1543030738830566,
+      "learning_rate": 4.389047838813082e-05,
+      "loss": 1.2296,
+      "step": 815
+    },
+    {
+      "epoch": 0.6858337689492943,
+      "grad_norm": 2.1455068588256836,
+      "learning_rate": 4.3818547687221204e-05,
+      "loss": 1.2913,
+      "step": 820
+    },
+    {
+      "epoch": 0.6900156821745949,
+      "grad_norm": 2.2354376316070557,
+      "learning_rate": 4.374625570388008e-05,
+      "loss": 1.2647,
+      "step": 825
+    },
+    {
+      "epoch": 0.6941975953998955,
+      "grad_norm": 2.2896392345428467,
+      "learning_rate": 4.367360382598413e-05,
+      "loss": 1.329,
+      "step": 830
+    },
+    {
+      "epoch": 0.698379508625196,
+      "grad_norm": 2.0567495822906494,
+      "learning_rate": 4.360059344831936e-05,
+      "loss": 1.2306,
+      "step": 835
+    },
+    {
+      "epoch": 0.7025614218504966,
+      "grad_norm": 2.0631346702575684,
+      "learning_rate": 4.352722597255434e-05,
+      "loss": 1.2788,
+      "step": 840
+    },
+    {
+      "epoch": 0.7067433350757972,
+      "grad_norm": 2.3736605644226074,
+      "learning_rate": 4.345350280721328e-05,
+      "loss": 1.3236,
+      "step": 845
+    },
+    {
+      "epoch": 0.7109252483010977,
+      "grad_norm": 2.308960437774658,
+      "learning_rate": 4.337942536764901e-05,
+      "loss": 1.2993,
+      "step": 850
+    },
+    {
+      "epoch": 0.7151071615263983,
+      "grad_norm": 2.230039358139038,
+      "learning_rate": 4.330499507601575e-05,
+      "loss": 1.2544,
+      "step": 855
+    },
+    {
+      "epoch": 0.7192890747516989,
+      "grad_norm": 2.1853036880493164,
+      "learning_rate": 4.3230213361241894e-05,
+      "loss": 1.2829,
+      "step": 860
+    },
+    {
+      "epoch": 0.7234709879769995,
+      "grad_norm": 2.2859535217285156,
+      "learning_rate": 4.3155081659002506e-05,
+      "loss": 1.3128,
+      "step": 865
+    },
+    {
+      "epoch": 0.7276529012023001,
+      "grad_norm": 1.9847872257232666,
+      "learning_rate": 4.3079601411691775e-05,
+      "loss": 1.3126,
+      "step": 870
+    },
+    {
+      "epoch": 0.7318348144276007,
+      "grad_norm": 2.3204383850097656,
+      "learning_rate": 4.3003774068395355e-05,
+      "loss": 1.3275,
+      "step": 875
+    },
+    {
+      "epoch": 0.7360167276529012,
+      "grad_norm": 2.1831467151641846,
+      "learning_rate": 4.292760108486251e-05,
+      "loss": 1.3232,
+      "step": 880
+    },
+    {
+      "epoch": 0.7401986408782018,
+      "grad_norm": 2.241342544555664,
+      "learning_rate": 4.2851083923478186e-05,
+      "loss": 1.2484,
+      "step": 885
+    },
+    {
+      "epoch": 0.7443805541035023,
+      "grad_norm": 2.335024118423462,
+      "learning_rate": 4.27742240532349e-05,
+      "loss": 1.2466,
+      "step": 890
+    },
+    {
+      "epoch": 0.7485624673288029,
+      "grad_norm": 2.592941999435425,
+      "learning_rate": 4.269702294970461e-05,
+      "loss": 1.3111,
+      "step": 895
+    },
+    {
+      "epoch": 0.7527443805541035,
+      "grad_norm": 2.1964266300201416,
+      "learning_rate": 4.26194820950103e-05,
+      "loss": 1.3172,
+      "step": 900
+    },
+    {
+      "epoch": 0.7569262937794041,
+      "grad_norm": 2.253929853439331,
+      "learning_rate": 4.25416029777976e-05,
+      "loss": 1.2977,
+      "step": 905
+    },
+    {
+      "epoch": 0.7611082070047046,
+      "grad_norm": 2.3653616905212402,
+      "learning_rate": 4.246338709320615e-05,
+      "loss": 1.3397,
+      "step": 910
+    },
+    {
+      "epoch": 0.7652901202300052,
+      "grad_norm": 1.9790107011795044,
+      "learning_rate": 4.238483594284094e-05,
+      "loss": 1.299,
+      "step": 915
+    },
+    {
+      "epoch": 0.7694720334553058,
+      "grad_norm": 2.177802324295044,
+      "learning_rate": 4.230595103474345e-05,
+      "loss": 1.2083,
+      "step": 920
+    },
+    {
+      "epoch": 0.7736539466806064,
+      "grad_norm": 2.267620325088501,
+      "learning_rate": 4.222673388336272e-05,
+      "loss": 1.2712,
+      "step": 925
+    },
+    {
+      "epoch": 0.777835859905907,
+      "grad_norm": 2.323590040206909,
+      "learning_rate": 4.214718600952627e-05,
+      "loss": 1.2944,
+      "step": 930
+    },
+    {
+      "epoch": 0.7820177731312076,
+      "grad_norm": 2.2184839248657227,
+      "learning_rate": 4.2067308940410874e-05,
+      "loss": 1.3033,
+      "step": 935
+    },
+    {
+      "epoch": 0.786199686356508,
+      "grad_norm": 2.056938648223877,
+      "learning_rate": 4.1987104209513295e-05,
+      "loss": 1.2563,
+      "step": 940
+    },
+    {
+      "epoch": 0.7903815995818086,
+      "grad_norm": 2.0813541412353516,
+      "learning_rate": 4.1906573356620795e-05,
+      "loss": 1.3169,
+      "step": 945
+    },
+    {
+      "epoch": 0.7945635128071092,
+      "grad_norm": 2.2418994903564453,
+      "learning_rate": 4.182571792778163e-05,
+      "loss": 1.3366,
+      "step": 950
+    },
+    {
+      "epoch": 0.7987454260324098,
+      "grad_norm": 2.1746504306793213,
+      "learning_rate": 4.1744539475275276e-05,
+      "loss": 1.2695,
+      "step": 955
+    },
+    {
+      "epoch": 0.8029273392577104,
+      "grad_norm": 2.385899066925049,
+      "learning_rate": 4.1663039557582725e-05,
+      "loss": 1.275,
+      "step": 960
+    },
+    {
+      "epoch": 0.807109252483011,
+      "grad_norm": 2.4620730876922607,
+      "learning_rate": 4.158121973935653e-05,
+      "loss": 1.3441,
+      "step": 965
+    },
+    {
+      "epoch": 0.8112911657083115,
+      "grad_norm": 2.090711832046509,
+      "learning_rate": 4.149908159139073e-05,
+      "loss": 1.2754,
+      "step": 970
+    },
+    {
+      "epoch": 0.8154730789336121,
+      "grad_norm": 2.367952346801758,
+      "learning_rate": 4.141662669059076e-05,
+      "loss": 1.2821,
+      "step": 975
+    },
+    {
+      "epoch": 0.8196549921589127,
+      "grad_norm": 2.406475782394409,
+      "learning_rate": 4.133385661994312e-05,
+      "loss": 1.2917,
+      "step": 980
+    },
+    {
+      "epoch": 0.8238369053842133,
+      "grad_norm": 2.0637738704681396,
+      "learning_rate": 4.125077296848501e-05,
+      "loss": 1.2582,
+      "step": 985
+    },
+    {
+      "epoch": 0.8280188186095139,
+      "grad_norm": 2.3852176666259766,
+      "learning_rate": 4.1167377331273825e-05,
+      "loss": 1.2278,
+      "step": 990
+    },
+    {
+      "epoch": 0.8322007318348145,
+      "grad_norm": 2.0237960815429688,
+      "learning_rate": 4.1083671309356526e-05,
+      "loss": 1.3461,
+      "step": 995
+    },
+    {
+      "epoch": 0.836382645060115,
+      "grad_norm": 2.458031177520752,
+      "learning_rate": 4.0999656509738904e-05,
+      "loss": 1.2484,
+      "step": 1000
+    },
+    {
+      "epoch": 0.8405645582854155,
+      "grad_norm": 2.3338541984558105,
+      "learning_rate": 4.0915334545354734e-05,
+      "loss": 1.2526,
+      "step": 1005
+    },
+    {
+      "epoch": 0.8447464715107161,
+      "grad_norm": 2.289320230484009,
+      "learning_rate": 4.0830707035034795e-05,
+      "loss": 1.2643,
+      "step": 1010
+    },
+    {
+      "epoch": 0.8489283847360167,
+      "grad_norm": 2.461848735809326,
+      "learning_rate": 4.074577560347581e-05,
+      "loss": 1.29,
+      "step": 1015
+    },
+    {
+      "epoch": 0.8531102979613173,
+      "grad_norm": 2.458249568939209,
+      "learning_rate": 4.066054188120924e-05,
+      "loss": 1.2673,
+      "step": 1020
+    },
+    {
+      "epoch": 0.8572922111866179,
+      "grad_norm": 2.21874737739563,
+      "learning_rate": 4.0575007504569994e-05,
+      "loss": 1.3085,
+      "step": 1025
+    },
+    {
+      "epoch": 0.8614741244119185,
+      "grad_norm": 2.275045871734619,
+      "learning_rate": 4.0489174115665006e-05,
+      "loss": 1.2335,
+      "step": 1030
+    },
+    {
+      "epoch": 0.865656037637219,
+      "grad_norm": 2.1374430656433105,
+      "learning_rate": 4.04030433623417e-05,
+      "loss": 1.2699,
+      "step": 1035
+    },
+    {
+      "epoch": 0.8698379508625196,
+      "grad_norm": 2.3316330909729004,
+      "learning_rate": 4.031661689815637e-05,
+      "loss": 1.2847,
+      "step": 1040
+    },
+    {
+      "epoch": 0.8740198640878202,
+      "grad_norm": 2.3386001586914062,
+      "learning_rate": 4.022989638234243e-05,
+      "loss": 1.3394,
+      "step": 1045
+    },
+    {
+      "epoch": 0.8782017773131208,
+      "grad_norm": 2.4343066215515137,
+      "learning_rate": 4.0142883479778555e-05,
+      "loss": 1.2541,
+      "step": 1050
+    },
+    {
+      "epoch": 0.8823836905384214,
+      "grad_norm": 2.1589419841766357,
+      "learning_rate": 4.005557986095673e-05,
+      "loss": 1.3327,
+      "step": 1055
+    },
+    {
+      "epoch": 0.886565603763722,
+      "grad_norm": 2.2223572731018066,
+      "learning_rate": 3.996798720195018e-05,
+      "loss": 1.3057,
+      "step": 1060
+    },
+    {
+      "epoch": 0.8907475169890224,
+      "grad_norm": 2.5740420818328857,
+      "learning_rate": 3.988010718438115e-05,
+      "loss": 1.2945,
+      "step": 1065
+    },
+    {
+      "epoch": 0.894929430214323,
+      "grad_norm": 2.214611053466797,
+      "learning_rate": 3.9791941495388696e-05,
+      "loss": 1.2855,
+      "step": 1070
+    },
+    {
+      "epoch": 0.8991113434396236,
+      "grad_norm": 2.21602463722229,
+      "learning_rate": 3.970349182759623e-05,
+      "loss": 1.3271,
+      "step": 1075
+    },
+    {
+      "epoch": 0.9032932566649242,
+      "grad_norm": 2.2032415866851807,
+      "learning_rate": 3.9614759879079057e-05,
+      "loss": 1.2027,
+      "step": 1080
+    },
+    {
+      "epoch": 0.9074751698902248,
+      "grad_norm": 2.518728017807007,
+      "learning_rate": 3.9525747353331746e-05,
+      "loss": 1.2886,
+      "step": 1085
+    },
+    {
+      "epoch": 0.9116570831155254,
+      "grad_norm": 2.438845157623291,
+      "learning_rate": 3.943645595923548e-05,
+      "loss": 1.2054,
+      "step": 1090
+    },
+    {
+      "epoch": 0.9158389963408259,
+      "grad_norm": 2.460658073425293,
+      "learning_rate": 3.934688741102521e-05,
+      "loss": 1.2868,
+      "step": 1095
+    },
+    {
+      "epoch": 0.9200209095661265,
+      "grad_norm": 2.09260892868042,
+      "learning_rate": 3.925704342825671e-05,
+      "loss": 1.3027,
+      "step": 1100
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 3585,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.4234917056302285e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ad489884f87ec96cc1e49b25622db5c6c3c1eafcad1be5306265a7460b6619a
+size 5304

checkpoint-1200/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+---
+
+# 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 0.11.1

checkpoint-1200/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11d19254861b1a6d2b796dc92ac6c0652e2f8a2da9421ace8c72f7f2f28114a2
+size 13648432

checkpoint-1200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44b6d02692d1e8eedb51d4521e1e229bf559f1f5c78e18827baa34ef6b6244d7
+size 27370618

checkpoint-1200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
+size 14244

checkpoint-1200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83c748c565b326f1420d0de27e5cc267bde896ddc4ed07b6f53c713ba343ded2
+size 1064

checkpoint-1200/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1200/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

checkpoint-1200/trainer_state.json

@@ -0,0 +1,1713 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.003659174072138,
+  "eval_steps": 500,
+  "global_step": 1200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004181913225300575,
+      "grad_norm": 3.3295910358428955,
+      "learning_rate": 4.9999760022374266e-05,
+      "loss": 1.8032,
+      "step": 5
+    },
+    {
+      "epoch": 0.00836382645060115,
+      "grad_norm": 2.002122163772583,
+      "learning_rate": 4.999904009410418e-05,
+      "loss": 1.5943,
+      "step": 10
+    },
+    {
+      "epoch": 0.012545739675901725,
+      "grad_norm": 1.9293591976165771,
+      "learning_rate": 4.9997840229011085e-05,
+      "loss": 1.5378,
+      "step": 15
+    },
+    {
+      "epoch": 0.0167276529012023,
+      "grad_norm": 1.936969518661499,
+      "learning_rate": 4.999616045013025e-05,
+      "loss": 1.5856,
+      "step": 20
+    },
+    {
+      "epoch": 0.020909566126502875,
+      "grad_norm": 1.8237314224243164,
+      "learning_rate": 4.9994000789710415e-05,
+      "loss": 1.5066,
+      "step": 25
+    },
+    {
+      "epoch": 0.02509147935180345,
+      "grad_norm": 1.8101543188095093,
+      "learning_rate": 4.9991361289213203e-05,
+      "loss": 1.4499,
+      "step": 30
+    },
+    {
+      "epoch": 0.029273392577104027,
+      "grad_norm": 1.647802710533142,
+      "learning_rate": 4.998824199931228e-05,
+      "loss": 1.4694,
+      "step": 35
+    },
+    {
+      "epoch": 0.0334553058024046,
+      "grad_norm": 1.7077428102493286,
+      "learning_rate": 4.998464297989245e-05,
+      "loss": 1.4945,
+      "step": 40
+    },
+    {
+      "epoch": 0.03763721902770518,
+      "grad_norm": 1.7119005918502808,
+      "learning_rate": 4.998056430004844e-05,
+      "loss": 1.4257,
+      "step": 45
+    },
+    {
+      "epoch": 0.04181913225300575,
+      "grad_norm": 2.0229578018188477,
+      "learning_rate": 4.997600603808359e-05,
+      "loss": 1.4713,
+      "step": 50
+    },
+    {
+      "epoch": 0.04600104547830632,
+      "grad_norm": 1.885362148284912,
+      "learning_rate": 4.997096828150838e-05,
+      "loss": 1.5145,
+      "step": 55
+    },
+    {
+      "epoch": 0.0501829587036069,
+      "grad_norm": 2.0357539653778076,
+      "learning_rate": 4.9965451127038714e-05,
+      "loss": 1.3811,
+      "step": 60
+    },
+    {
+      "epoch": 0.054364871928907474,
+      "grad_norm": 1.9780900478363037,
+      "learning_rate": 4.9959454680594086e-05,
+      "loss": 1.412,
+      "step": 65
+    },
+    {
+      "epoch": 0.05854678515420805,
+      "grad_norm": 1.6695700883865356,
+      "learning_rate": 4.995297905729554e-05,
+      "loss": 1.4093,
+      "step": 70
+    },
+    {
+      "epoch": 0.06272869837950862,
+      "grad_norm": 1.9424223899841309,
+      "learning_rate": 4.994602438146344e-05,
+      "loss": 1.4615,
+      "step": 75
+    },
+    {
+      "epoch": 0.0669106116048092,
+      "grad_norm": 1.9082552194595337,
+      "learning_rate": 4.9938590786615126e-05,
+      "loss": 1.4169,
+      "step": 80
+    },
+    {
+      "epoch": 0.07109252483010978,
+      "grad_norm": 1.8944685459136963,
+      "learning_rate": 4.993067841546231e-05,
+      "loss": 1.3064,
+      "step": 85
+    },
+    {
+      "epoch": 0.07527443805541036,
+      "grad_norm": 1.9688103199005127,
+      "learning_rate": 4.992228741990834e-05,
+      "loss": 1.3778,
+      "step": 90
+    },
+    {
+      "epoch": 0.07945635128071092,
+      "grad_norm": 2.0939650535583496,
+      "learning_rate": 4.991341796104534e-05,
+      "loss": 1.3905,
+      "step": 95
+    },
+    {
+      "epoch": 0.0836382645060115,
+      "grad_norm": 1.868986964225769,
+      "learning_rate": 4.9904070209151015e-05,
+      "loss": 1.3723,
+      "step": 100
+    },
+    {
+      "epoch": 0.08782017773131208,
+      "grad_norm": 2.069476842880249,
+      "learning_rate": 4.989424434368549e-05,
+      "loss": 1.4046,
+      "step": 105
+    },
+    {
+      "epoch": 0.09200209095661264,
+      "grad_norm": 2.1500356197357178,
+      "learning_rate": 4.988394055328779e-05,
+      "loss": 1.4319,
+      "step": 110
+    },
+    {
+      "epoch": 0.09618400418191322,
+      "grad_norm": 1.9786696434020996,
+      "learning_rate": 4.987315903577223e-05,
+      "loss": 1.4203,
+      "step": 115
+    },
+    {
+      "epoch": 0.1003659174072138,
+      "grad_norm": 2.035172939300537,
+      "learning_rate": 4.986189999812468e-05,
+      "loss": 1.4046,
+      "step": 120
+    },
+    {
+      "epoch": 0.10454783063251437,
+      "grad_norm": 1.9887930154800415,
+      "learning_rate": 4.985016365649848e-05,
+      "loss": 1.3836,
+      "step": 125
+    },
+    {
+      "epoch": 0.10872974385781495,
+      "grad_norm": 1.8339554071426392,
+      "learning_rate": 4.983795023621041e-05,
+      "loss": 1.3468,
+      "step": 130
+    },
+    {
+      "epoch": 0.11291165708311553,
+      "grad_norm": 2.06648588180542,
+      "learning_rate": 4.982525997173625e-05,
+      "loss": 1.3481,
+      "step": 135
+    },
+    {
+      "epoch": 0.1170935703084161,
+      "grad_norm": 2.1179702281951904,
+      "learning_rate": 4.9812093106706376e-05,
+      "loss": 1.4475,
+      "step": 140
+    },
+    {
+      "epoch": 0.12127548353371667,
+      "grad_norm": 2.1708436012268066,
+      "learning_rate": 4.979844989390104e-05,
+      "loss": 1.3662,
+      "step": 145
+    },
+    {
+      "epoch": 0.12545739675901724,
+      "grad_norm": 2.0533807277679443,
+      "learning_rate": 4.978433059524548e-05,
+      "loss": 1.3856,
+      "step": 150
+    },
+    {
+      "epoch": 0.12963930998431783,
+      "grad_norm": 1.9418696165084839,
+      "learning_rate": 4.976973548180498e-05,
+      "loss": 1.357,
+      "step": 155
+    },
+    {
+      "epoch": 0.1338212232096184,
+      "grad_norm": 2.1071596145629883,
+      "learning_rate": 4.975466483377959e-05,
+      "loss": 1.3613,
+      "step": 160
+    },
+    {
+      "epoch": 0.138003136434919,
+      "grad_norm": 2.3704464435577393,
+      "learning_rate": 4.9739118940498766e-05,
+      "loss": 1.3985,
+      "step": 165
+    },
+    {
+      "epoch": 0.14218504966021955,
+      "grad_norm": 2.1726176738739014,
+      "learning_rate": 4.9723098100415844e-05,
+      "loss": 1.4361,
+      "step": 170
+    },
+    {
+      "epoch": 0.14636696288552012,
+      "grad_norm": 2.608517646789551,
+      "learning_rate": 4.970660262110227e-05,
+      "loss": 1.3565,
+      "step": 175
+    },
+    {
+      "epoch": 0.1505488761108207,
+      "grad_norm": 2.185563564300537,
+      "learning_rate": 4.968963281924173e-05,
+      "loss": 1.2957,
+      "step": 180
+    },
+    {
+      "epoch": 0.15473078933612128,
+      "grad_norm": 1.9632441997528076,
+      "learning_rate": 4.967218902062403e-05,
+      "loss": 1.2833,
+      "step": 185
+    },
+    {
+      "epoch": 0.15891270256142184,
+      "grad_norm": 2.303462028503418,
+      "learning_rate": 4.96542715601389e-05,
+      "loss": 1.3238,
+      "step": 190
+    },
+    {
+      "epoch": 0.16309461578672244,
+      "grad_norm": 2.3211796283721924,
+      "learning_rate": 4.9635880781769495e-05,
+      "loss": 1.3848,
+      "step": 195
+    },
+    {
+      "epoch": 0.167276529012023,
+      "grad_norm": 2.0993776321411133,
+      "learning_rate": 4.961701703858584e-05,
+      "loss": 1.3997,
+      "step": 200
+    },
+    {
+      "epoch": 0.17145844223732357,
+      "grad_norm": 2.210942506790161,
+      "learning_rate": 4.9597680692738056e-05,
+      "loss": 1.334,
+      "step": 205
+    },
+    {
+      "epoch": 0.17564035546262416,
+      "grad_norm": 2.1277225017547607,
+      "learning_rate": 4.957787211544935e-05,
+      "loss": 1.3338,
+      "step": 210
+    },
+    {
+      "epoch": 0.17982226868792472,
+      "grad_norm": 2.287722587585449,
+      "learning_rate": 4.9557591687008966e-05,
+      "loss": 1.3621,
+      "step": 215
+    },
+    {
+      "epoch": 0.1840041819132253,
+      "grad_norm": 2.113842010498047,
+      "learning_rate": 4.9536839796764825e-05,
+      "loss": 1.3808,
+      "step": 220
+    },
+    {
+      "epoch": 0.18818609513852588,
+      "grad_norm": 2.0642735958099365,
+      "learning_rate": 4.951561684311608e-05,
+      "loss": 1.3429,
+      "step": 225
+    },
+    {
+      "epoch": 0.19236800836382645,
+      "grad_norm": 2.2026379108428955,
+      "learning_rate": 4.9493923233505435e-05,
+      "loss": 1.2855,
+      "step": 230
+    },
+    {
+      "epoch": 0.196549921589127,
+      "grad_norm": 2.2843308448791504,
+      "learning_rate": 4.947175938441138e-05,
+      "loss": 1.3432,
+      "step": 235
+    },
+    {
+      "epoch": 0.2007318348144276,
+      "grad_norm": 2.126749038696289,
+      "learning_rate": 4.9449125721340145e-05,
+      "loss": 1.3753,
+      "step": 240
+    },
+    {
+      "epoch": 0.20491374803972817,
+      "grad_norm": 2.514599561691284,
+      "learning_rate": 4.942602267881755e-05,
+      "loss": 1.3101,
+      "step": 245
+    },
+    {
+      "epoch": 0.20909566126502874,
+      "grad_norm": 2.2043542861938477,
+      "learning_rate": 4.940245070038064e-05,
+      "loss": 1.3395,
+      "step": 250
+    },
+    {
+      "epoch": 0.21327757449032933,
+      "grad_norm": 2.152742862701416,
+      "learning_rate": 4.937841023856923e-05,
+      "loss": 1.3188,
+      "step": 255
+    },
+    {
+      "epoch": 0.2174594877156299,
+      "grad_norm": 2.221057415008545,
+      "learning_rate": 4.935390175491716e-05,
+      "loss": 1.4205,
+      "step": 260
+    },
+    {
+      "epoch": 0.2216414009409305,
+      "grad_norm": 2.600109100341797,
+      "learning_rate": 4.932892571994342e-05,
+      "loss": 1.3499,
+      "step": 265
+    },
+    {
+      "epoch": 0.22582331416623105,
+      "grad_norm": 2.2291276454925537,
+      "learning_rate": 4.9303482613143194e-05,
+      "loss": 1.3984,
+      "step": 270
+    },
+    {
+      "epoch": 0.23000522739153162,
+      "grad_norm": 2.338000774383545,
+      "learning_rate": 4.9277572922978586e-05,
+      "loss": 1.344,
+      "step": 275
+    },
+    {
+      "epoch": 0.2341871406168322,
+      "grad_norm": 2.3423988819122314,
+      "learning_rate": 4.925119714686928e-05,
+      "loss": 1.2696,
+      "step": 280
+    },
+    {
+      "epoch": 0.23836905384213278,
+      "grad_norm": 2.433870553970337,
+      "learning_rate": 4.9224355791182955e-05,
+      "loss": 1.3903,
+      "step": 285
+    },
+    {
+      "epoch": 0.24255096706743334,
+      "grad_norm": 2.281836986541748,
+      "learning_rate": 4.919704937122559e-05,
+      "loss": 1.3694,
+      "step": 290
+    },
+    {
+      "epoch": 0.24673288029273394,
+      "grad_norm": 2.2429168224334717,
+      "learning_rate": 4.916927841123159e-05,
+      "loss": 1.3541,
+      "step": 295
+    },
+    {
+      "epoch": 0.2509147935180345,
+      "grad_norm": 2.4559881687164307,
+      "learning_rate": 4.9141043444353674e-05,
+      "loss": 1.3795,
+      "step": 300
+    },
+    {
+      "epoch": 0.25509670674333507,
+      "grad_norm": 2.7529919147491455,
+      "learning_rate": 4.911234501265266e-05,
+      "loss": 1.386,
+      "step": 305
+    },
+    {
+      "epoch": 0.25927861996863566,
+      "grad_norm": 2.229973554611206,
+      "learning_rate": 4.9083183667087064e-05,
+      "loss": 1.3653,
+      "step": 310
+    },
+    {
+      "epoch": 0.26346053319393625,
+      "grad_norm": 2.38677716255188,
+      "learning_rate": 4.9053559967502535e-05,
+      "loss": 1.3254,
+      "step": 315
+    },
+    {
+      "epoch": 0.2676424464192368,
+      "grad_norm": 2.292898416519165,
+      "learning_rate": 4.9023474482621075e-05,
+      "loss": 1.3756,
+      "step": 320
+    },
+    {
+      "epoch": 0.2718243596445374,
+      "grad_norm": 2.08819317817688,
+      "learning_rate": 4.899292779003014e-05,
+      "loss": 1.3286,
+      "step": 325
+    },
+    {
+      "epoch": 0.276006272869838,
+      "grad_norm": 2.1810929775238037,
+      "learning_rate": 4.896192047617156e-05,
+      "loss": 1.3884,
+      "step": 330
+    },
+    {
+      "epoch": 0.2801881860951385,
+      "grad_norm": 2.2136948108673096,
+      "learning_rate": 4.893045313633025e-05,
+      "loss": 1.2723,
+      "step": 335
+    },
+    {
+      "epoch": 0.2843700993204391,
+      "grad_norm": 2.3611645698547363,
+      "learning_rate": 4.8898526374622815e-05,
+      "loss": 1.3758,
+      "step": 340
+    },
+    {
+      "epoch": 0.2885520125457397,
+      "grad_norm": 2.2939200401306152,
+      "learning_rate": 4.886614080398594e-05,
+      "loss": 1.3727,
+      "step": 345
+    },
+    {
+      "epoch": 0.29273392577104024,
+      "grad_norm": 2.2382090091705322,
+      "learning_rate": 4.8833297046164594e-05,
+      "loss": 1.3412,
+      "step": 350
+    },
+    {
+      "epoch": 0.29691583899634083,
+      "grad_norm": 2.0420024394989014,
+      "learning_rate": 4.8799995731700155e-05,
+      "loss": 1.3378,
+      "step": 355
+    },
+    {
+      "epoch": 0.3010977522216414,
+      "grad_norm": 2.180814266204834,
+      "learning_rate": 4.8766237499918244e-05,
+      "loss": 1.3305,
+      "step": 360
+    },
+    {
+      "epoch": 0.30527966544694196,
+      "grad_norm": 2.641951560974121,
+      "learning_rate": 4.873202299891649e-05,
+      "loss": 1.3084,
+      "step": 365
+    },
+    {
+      "epoch": 0.30946157867224255,
+      "grad_norm": 2.421492099761963,
+      "learning_rate": 4.8697352885552077e-05,
+      "loss": 1.3321,
+      "step": 370
+    },
+    {
+      "epoch": 0.31364349189754315,
+      "grad_norm": 2.1777994632720947,
+      "learning_rate": 4.866222782542912e-05,
+      "loss": 1.3605,
+      "step": 375
+    },
+    {
+      "epoch": 0.3178254051228437,
+      "grad_norm": 2.097909450531006,
+      "learning_rate": 4.862664849288589e-05,
+      "loss": 1.3786,
+      "step": 380
+    },
+    {
+      "epoch": 0.3220073183481443,
+      "grad_norm": 2.3216776847839355,
+      "learning_rate": 4.8590615570981904e-05,
+      "loss": 1.3467,
+      "step": 385
+    },
+    {
+      "epoch": 0.32618923157344487,
+      "grad_norm": 2.199545383453369,
+      "learning_rate": 4.855412975148475e-05,
+      "loss": 1.3534,
+      "step": 390
+    },
+    {
+      "epoch": 0.3303711447987454,
+      "grad_norm": 2.4035983085632324,
+      "learning_rate": 4.851719173485686e-05,
+      "loss": 1.3545,
+      "step": 395
+    },
+    {
+      "epoch": 0.334553058024046,
+      "grad_norm": 2.130056142807007,
+      "learning_rate": 4.847980223024205e-05,
+      "loss": 1.3574,
+      "step": 400
+    },
+    {
+      "epoch": 0.3387349712493466,
+      "grad_norm": 2.2835471630096436,
+      "learning_rate": 4.8441961955451865e-05,
+      "loss": 1.2835,
+      "step": 405
+    },
+    {
+      "epoch": 0.34291688447464713,
+      "grad_norm": 2.129136085510254,
+      "learning_rate": 4.840367163695186e-05,
+      "loss": 1.3066,
+      "step": 410
+    },
+    {
+      "epoch": 0.3470987976999477,
+      "grad_norm": 2.199307680130005,
+      "learning_rate": 4.8364932009847614e-05,
+      "loss": 1.3891,
+      "step": 415
+    },
+    {
+      "epoch": 0.3512807109252483,
+      "grad_norm": 2.240877866744995,
+      "learning_rate": 4.8325743817870614e-05,
+      "loss": 1.3131,
+      "step": 420
+    },
+    {
+      "epoch": 0.35546262415054886,
+      "grad_norm": 2.4342916011810303,
+      "learning_rate": 4.8286107813364015e-05,
+      "loss": 1.2903,
+      "step": 425
+    },
+    {
+      "epoch": 0.35964453737584945,
+      "grad_norm": 2.323018789291382,
+      "learning_rate": 4.824602475726815e-05,
+      "loss": 1.3016,
+      "step": 430
+    },
+    {
+      "epoch": 0.36382645060115004,
+      "grad_norm": 2.2159998416900635,
+      "learning_rate": 4.820549541910595e-05,
+      "loss": 1.3312,
+      "step": 435
+    },
+    {
+      "epoch": 0.3680083638264506,
+      "grad_norm": 2.654232978820801,
+      "learning_rate": 4.8164520576968165e-05,
+      "loss": 1.3793,
+      "step": 440
+    },
+    {
+      "epoch": 0.3721902770517512,
+      "grad_norm": 2.3524513244628906,
+      "learning_rate": 4.8123101017498416e-05,
+      "loss": 1.3406,
+      "step": 445
+    },
+    {
+      "epoch": 0.37637219027705177,
+      "grad_norm": 2.3215346336364746,
+      "learning_rate": 4.8081237535878116e-05,
+      "loss": 1.3997,
+      "step": 450
+    },
+    {
+      "epoch": 0.3805541035023523,
+      "grad_norm": 2.0394012928009033,
+      "learning_rate": 4.803893093581117e-05,
+      "loss": 1.3084,
+      "step": 455
+    },
+    {
+      "epoch": 0.3847360167276529,
+      "grad_norm": 2.251598596572876,
+      "learning_rate": 4.799618202950857e-05,
+      "loss": 1.3396,
+      "step": 460
+    },
+    {
+      "epoch": 0.3889179299529535,
+      "grad_norm": 2.4240410327911377,
+      "learning_rate": 4.795299163767282e-05,
+      "loss": 1.359,
+      "step": 465
+    },
+    {
+      "epoch": 0.393099843178254,
+      "grad_norm": 2.2180769443511963,
+      "learning_rate": 4.790936058948211e-05,
+      "loss": 1.3575,
+      "step": 470
+    },
+    {
+      "epoch": 0.3972817564035546,
+      "grad_norm": 2.2782742977142334,
+      "learning_rate": 4.786528972257449e-05,
+      "loss": 1.2915,
+      "step": 475
+    },
+    {
+      "epoch": 0.4014636696288552,
+      "grad_norm": 2.2193851470947266,
+      "learning_rate": 4.7820779883031696e-05,
+      "loss": 1.3185,
+      "step": 480
+    },
+    {
+      "epoch": 0.40564558285415575,
+      "grad_norm": 2.2422704696655273,
+      "learning_rate": 4.7775831925363e-05,
+      "loss": 1.2638,
+      "step": 485
+    },
+    {
+      "epoch": 0.40982749607945634,
+      "grad_norm": 2.430154323577881,
+      "learning_rate": 4.773044671248872e-05,
+      "loss": 1.3616,
+      "step": 490
+    },
+    {
+      "epoch": 0.41400940930475694,
+      "grad_norm": 2.2115910053253174,
+      "learning_rate": 4.768462511572371e-05,
+      "loss": 1.35,
+      "step": 495
+    },
+    {
+      "epoch": 0.4181913225300575,
+      "grad_norm": 2.063385486602783,
+      "learning_rate": 4.763836801476061e-05,
+      "loss": 1.2797,
+      "step": 500
+    },
+    {
+      "epoch": 0.42237323575535807,
+      "grad_norm": 2.3508410453796387,
+      "learning_rate": 4.759167629765297e-05,
+      "loss": 1.3173,
+      "step": 505
+    },
+    {
+      "epoch": 0.42655514898065866,
+      "grad_norm": 2.3848047256469727,
+      "learning_rate": 4.7544550860798177e-05,
+      "loss": 1.2502,
+      "step": 510
+    },
+    {
+      "epoch": 0.43073706220595925,
+      "grad_norm": 2.227524757385254,
+      "learning_rate": 4.749699260892026e-05,
+      "loss": 1.3174,
+      "step": 515
+    },
+    {
+      "epoch": 0.4349189754312598,
+      "grad_norm": 2.2080676555633545,
+      "learning_rate": 4.744900245505253e-05,
+      "loss": 1.2567,
+      "step": 520
+    },
+    {
+      "epoch": 0.4391008886565604,
+      "grad_norm": 2.2167842388153076,
+      "learning_rate": 4.7400581320520055e-05,
+      "loss": 1.2906,
+      "step": 525
+    },
+    {
+      "epoch": 0.443282801881861,
+      "grad_norm": 2.4347431659698486,
+      "learning_rate": 4.735173013492193e-05,
+      "loss": 1.3109,
+      "step": 530
+    },
+    {
+      "epoch": 0.4474647151071615,
+      "grad_norm": 2.024902105331421,
+      "learning_rate": 4.73024498361135e-05,
+      "loss": 1.3265,
+      "step": 535
+    },
+    {
+      "epoch": 0.4516466283324621,
+      "grad_norm": 2.1333351135253906,
+      "learning_rate": 4.725274137018826e-05,
+      "loss": 1.3426,
+      "step": 540
+    },
+    {
+      "epoch": 0.4558285415577627,
+      "grad_norm": 2.400423049926758,
+      "learning_rate": 4.720260569145981e-05,
+      "loss": 1.2751,
+      "step": 545
+    },
+    {
+      "epoch": 0.46001045478306324,
+      "grad_norm": 2.5796918869018555,
+      "learning_rate": 4.715204376244343e-05,
+      "loss": 1.3453,
+      "step": 550
+    },
+    {
+      "epoch": 0.46419236800836383,
+      "grad_norm": 2.339895486831665,
+      "learning_rate": 4.7101056553837665e-05,
+      "loss": 1.2667,
+      "step": 555
+    },
+    {
+      "epoch": 0.4683742812336644,
+      "grad_norm": 2.273618221282959,
+      "learning_rate": 4.704964504450563e-05,
+      "loss": 1.3264,
+      "step": 560
+    },
+    {
+      "epoch": 0.47255619445896496,
+      "grad_norm": 1.9942044019699097,
+      "learning_rate": 4.69978102214563e-05,
+      "loss": 1.2907,
+      "step": 565
+    },
+    {
+      "epoch": 0.47673810768426556,
+      "grad_norm": 2.1848580837249756,
+      "learning_rate": 4.694555307982551e-05,
+      "loss": 1.2921,
+      "step": 570
+    },
+    {
+      "epoch": 0.48092002090956615,
+      "grad_norm": 2.2914299964904785,
+      "learning_rate": 4.689287462285681e-05,
+      "loss": 1.3612,
+      "step": 575
+    },
+    {
+      "epoch": 0.4851019341348667,
+      "grad_norm": 2.1165218353271484,
+      "learning_rate": 4.6839775861882306e-05,
+      "loss": 1.3419,
+      "step": 580
+    },
+    {
+      "epoch": 0.4892838473601673,
+      "grad_norm": 2.003962516784668,
+      "learning_rate": 4.678625781630315e-05,
+      "loss": 1.388,
+      "step": 585
+    },
+    {
+      "epoch": 0.49346576058546787,
+      "grad_norm": 2.366339683532715,
+      "learning_rate": 4.673232151357004e-05,
+      "loss": 1.2895,
+      "step": 590
+    },
+    {
+      "epoch": 0.4976476738107684,
+      "grad_norm": 2.4352052211761475,
+      "learning_rate": 4.667796798916343e-05,
+      "loss": 1.3457,
+      "step": 595
+    },
+    {
+      "epoch": 0.501829587036069,
+      "grad_norm": 2.4221272468566895,
+      "learning_rate": 4.662319828657371e-05,
+      "loss": 1.3298,
+      "step": 600
+    },
+    {
+      "epoch": 0.5060115002613695,
+      "grad_norm": 2.2551608085632324,
+      "learning_rate": 4.6568013457281126e-05,
+      "loss": 1.2192,
+      "step": 605
+    },
+    {
+      "epoch": 0.5101934134866701,
+      "grad_norm": 2.4560656547546387,
+      "learning_rate": 4.651241456073563e-05,
+      "loss": 1.3086,
+      "step": 610
+    },
+    {
+      "epoch": 0.5143753267119707,
+      "grad_norm": 2.266500473022461,
+      "learning_rate": 4.645640266433651e-05,
+      "loss": 1.2608,
+      "step": 615
+    },
+    {
+      "epoch": 0.5185572399372713,
+      "grad_norm": 2.175009250640869,
+      "learning_rate": 4.639997884341192e-05,
+      "loss": 1.3459,
+      "step": 620
+    },
+    {
+      "epoch": 0.5227391531625719,
+      "grad_norm": 2.329770803451538,
+      "learning_rate": 4.634314418119823e-05,
+      "loss": 1.2894,
+      "step": 625
+    },
+    {
+      "epoch": 0.5269210663878725,
+      "grad_norm": 2.545764446258545,
+      "learning_rate": 4.628589976881923e-05,
+      "loss": 1.3213,
+      "step": 630
+    },
+    {
+      "epoch": 0.531102979613173,
+      "grad_norm": 2.2759323120117188,
+      "learning_rate": 4.622824670526516e-05,
+      "loss": 1.3362,
+      "step": 635
+    },
+    {
+      "epoch": 0.5352848928384736,
+      "grad_norm": 2.341280221939087,
+      "learning_rate": 4.617018609737166e-05,
+      "loss": 1.24,
+      "step": 640
+    },
+    {
+      "epoch": 0.5394668060637742,
+      "grad_norm": 2.353301763534546,
+      "learning_rate": 4.6111719059798466e-05,
+      "loss": 1.3643,
+      "step": 645
+    },
+    {
+      "epoch": 0.5436487192890748,
+      "grad_norm": 2.223389148712158,
+      "learning_rate": 4.605284671500805e-05,
+      "loss": 1.3569,
+      "step": 650
+    },
+    {
+      "epoch": 0.5478306325143754,
+      "grad_norm": 2.2959463596343994,
+      "learning_rate": 4.599357019324405e-05,
+      "loss": 1.3581,
+      "step": 655
+    },
+    {
+      "epoch": 0.552012545739676,
+      "grad_norm": 2.1995513439178467,
+      "learning_rate": 4.593389063250958e-05,
+      "loss": 1.2962,
+      "step": 660
+    },
+    {
+      "epoch": 0.5561944589649764,
+      "grad_norm": 1.9802824258804321,
+      "learning_rate": 4.5873809178545396e-05,
+      "loss": 1.3121,
+      "step": 665
+    },
+    {
+      "epoch": 0.560376372190277,
+      "grad_norm": 2.2561113834381104,
+      "learning_rate": 4.581332698480786e-05,
+      "loss": 1.2395,
+      "step": 670
+    },
+    {
+      "epoch": 0.5645582854155776,
+      "grad_norm": 2.1277997493743896,
+      "learning_rate": 4.5752445212446836e-05,
+      "loss": 1.2782,
+      "step": 675
+    },
+    {
+      "epoch": 0.5687401986408782,
+      "grad_norm": 2.1406946182250977,
+      "learning_rate": 4.569116503028339e-05,
+      "loss": 1.3248,
+      "step": 680
+    },
+    {
+      "epoch": 0.5729221118661788,
+      "grad_norm": 2.190600872039795,
+      "learning_rate": 4.5629487614787306e-05,
+      "loss": 1.2975,
+      "step": 685
+    },
+    {
+      "epoch": 0.5771040250914794,
+      "grad_norm": 2.1068780422210693,
+      "learning_rate": 4.556741415005459e-05,
+      "loss": 1.3191,
+      "step": 690
+    },
+    {
+      "epoch": 0.5812859383167799,
+      "grad_norm": 2.3496341705322266,
+      "learning_rate": 4.5504945827784634e-05,
+      "loss": 1.2827,
+      "step": 695
+    },
+    {
+      "epoch": 0.5854678515420805,
+      "grad_norm": 2.33406400680542,
+      "learning_rate": 4.544208384725742e-05,
+      "loss": 1.2649,
+      "step": 700
+    },
+    {
+      "epoch": 0.5896497647673811,
+      "grad_norm": 2.365461587905884,
+      "learning_rate": 4.5378829415310465e-05,
+      "loss": 1.3121,
+      "step": 705
+    },
+    {
+      "epoch": 0.5938316779926817,
+      "grad_norm": 2.186875343322754,
+      "learning_rate": 4.531518374631564e-05,
+      "loss": 1.3113,
+      "step": 710
+    },
+    {
+      "epoch": 0.5980135912179823,
+      "grad_norm": 2.1798176765441895,
+      "learning_rate": 4.525114806215584e-05,
+      "loss": 1.3446,
+      "step": 715
+    },
+    {
+      "epoch": 0.6021955044432828,
+      "grad_norm": 1.9714925289154053,
+      "learning_rate": 4.518672359220161e-05,
+      "loss": 1.2979,
+      "step": 720
+    },
+    {
+      "epoch": 0.6063774176685833,
+      "grad_norm": 2.1850643157958984,
+      "learning_rate": 4.5121911573287446e-05,
+      "loss": 1.2412,
+      "step": 725
+    },
+    {
+      "epoch": 0.6105593308938839,
+      "grad_norm": 2.0708961486816406,
+      "learning_rate": 4.505671324968811e-05,
+      "loss": 1.2559,
+      "step": 730
+    },
+    {
+      "epoch": 0.6147412441191845,
+      "grad_norm": 2.461225986480713,
+      "learning_rate": 4.49911298730947e-05,
+      "loss": 1.3696,
+      "step": 735
+    },
+    {
+      "epoch": 0.6189231573444851,
+      "grad_norm": 2.2155981063842773,
+      "learning_rate": 4.492516270259066e-05,
+      "loss": 1.3459,
+      "step": 740
+    },
+    {
+      "epoch": 0.6231050705697857,
+      "grad_norm": 2.0899972915649414,
+      "learning_rate": 4.48588130046276e-05,
+      "loss": 1.2885,
+      "step": 745
+    },
+    {
+      "epoch": 0.6272869837950863,
+      "grad_norm": 2.2798969745635986,
+      "learning_rate": 4.479208205300094e-05,
+      "loss": 1.299,
+      "step": 750
+    },
+    {
+      "epoch": 0.6314688970203868,
+      "grad_norm": 2.4617793560028076,
+      "learning_rate": 4.472497112882552e-05,
+      "loss": 1.2973,
+      "step": 755
+    },
+    {
+      "epoch": 0.6356508102456874,
+      "grad_norm": 2.20271635055542,
+      "learning_rate": 4.465748152051096e-05,
+      "loss": 1.231,
+      "step": 760
+    },
+    {
+      "epoch": 0.639832723470988,
+      "grad_norm": 1.990775227546692,
+      "learning_rate": 4.458961452373692e-05,
+      "loss": 1.2594,
+      "step": 765
+    },
+    {
+      "epoch": 0.6440146366962886,
+      "grad_norm": 2.2898495197296143,
+      "learning_rate": 4.4521371441428284e-05,
+      "loss": 1.2721,
+      "step": 770
+    },
+    {
+      "epoch": 0.6481965499215891,
+      "grad_norm": 2.282844066619873,
+      "learning_rate": 4.445275358373006e-05,
+      "loss": 1.2742,
+      "step": 775
+    },
+    {
+      "epoch": 0.6523784631468897,
+      "grad_norm": 2.3958911895751953,
+      "learning_rate": 4.438376226798231e-05,
+      "loss": 1.2897,
+      "step": 780
+    },
+    {
+      "epoch": 0.6565603763721902,
+      "grad_norm": 2.2609405517578125,
+      "learning_rate": 4.43143988186948e-05,
+      "loss": 1.2891,
+      "step": 785
+    },
+    {
+      "epoch": 0.6607422895974908,
+      "grad_norm": 2.416956663131714,
+      "learning_rate": 4.42446645675216e-05,
+      "loss": 1.3711,
+      "step": 790
+    },
+    {
+      "epoch": 0.6649242028227914,
+      "grad_norm": 2.280547857284546,
+      "learning_rate": 4.4174560853235505e-05,
+      "loss": 1.3413,
+      "step": 795
+    },
+    {
+      "epoch": 0.669106116048092,
+      "grad_norm": 2.055990695953369,
+      "learning_rate": 4.410408902170235e-05,
+      "loss": 1.2829,
+      "step": 800
+    },
+    {
+      "epoch": 0.6732880292733926,
+      "grad_norm": 2.1436378955841064,
+      "learning_rate": 4.403325042585518e-05,
+      "loss": 1.2223,
+      "step": 805
+    },
+    {
+      "epoch": 0.6774699424986932,
+      "grad_norm": 2.1957428455352783,
+      "learning_rate": 4.396204642566821e-05,
+      "loss": 1.2923,
+      "step": 810
+    },
+    {
+      "epoch": 0.6816518557239938,
+      "grad_norm": 2.1543030738830566,
+      "learning_rate": 4.389047838813082e-05,
+      "loss": 1.2296,
+      "step": 815
+    },
+    {
+      "epoch": 0.6858337689492943,
+      "grad_norm": 2.1455068588256836,
+      "learning_rate": 4.3818547687221204e-05,
+      "loss": 1.2913,
+      "step": 820
+    },
+    {
+      "epoch": 0.6900156821745949,
+      "grad_norm": 2.2354376316070557,
+      "learning_rate": 4.374625570388008e-05,
+      "loss": 1.2647,
+      "step": 825
+    },
+    {
+      "epoch": 0.6941975953998955,
+      "grad_norm": 2.2896392345428467,
+      "learning_rate": 4.367360382598413e-05,
+      "loss": 1.329,
+      "step": 830
+    },
+    {
+      "epoch": 0.698379508625196,
+      "grad_norm": 2.0567495822906494,
+      "learning_rate": 4.360059344831936e-05,
+      "loss": 1.2306,
+      "step": 835
+    },
+    {
+      "epoch": 0.7025614218504966,
+      "grad_norm": 2.0631346702575684,
+      "learning_rate": 4.352722597255434e-05,
+      "loss": 1.2788,
+      "step": 840
+    },
+    {
+      "epoch": 0.7067433350757972,
+      "grad_norm": 2.3736605644226074,
+      "learning_rate": 4.345350280721328e-05,
+      "loss": 1.3236,
+      "step": 845
+    },
+    {
+      "epoch": 0.7109252483010977,
+      "grad_norm": 2.308960437774658,
+      "learning_rate": 4.337942536764901e-05,
+      "loss": 1.2993,
+      "step": 850
+    },
+    {
+      "epoch": 0.7151071615263983,
+      "grad_norm": 2.230039358139038,
+      "learning_rate": 4.330499507601575e-05,
+      "loss": 1.2544,
+      "step": 855
+    },
+    {
+      "epoch": 0.7192890747516989,
+      "grad_norm": 2.1853036880493164,
+      "learning_rate": 4.3230213361241894e-05,
+      "loss": 1.2829,
+      "step": 860
+    },
+    {
+      "epoch": 0.7234709879769995,
+      "grad_norm": 2.2859535217285156,
+      "learning_rate": 4.3155081659002506e-05,
+      "loss": 1.3128,
+      "step": 865
+    },
+    {
+      "epoch": 0.7276529012023001,
+      "grad_norm": 1.9847872257232666,
+      "learning_rate": 4.3079601411691775e-05,
+      "loss": 1.3126,
+      "step": 870
+    },
+    {
+      "epoch": 0.7318348144276007,
+      "grad_norm": 2.3204383850097656,
+      "learning_rate": 4.3003774068395355e-05,
+      "loss": 1.3275,
+      "step": 875
+    },
+    {
+      "epoch": 0.7360167276529012,
+      "grad_norm": 2.1831467151641846,
+      "learning_rate": 4.292760108486251e-05,
+      "loss": 1.3232,
+      "step": 880
+    },
+    {
+      "epoch": 0.7401986408782018,
+      "grad_norm": 2.241342544555664,
+      "learning_rate": 4.2851083923478186e-05,
+      "loss": 1.2484,
+      "step": 885
+    },
+    {
+      "epoch": 0.7443805541035023,
+      "grad_norm": 2.335024118423462,
+      "learning_rate": 4.27742240532349e-05,
+      "loss": 1.2466,
+      "step": 890
+    },
+    {
+      "epoch": 0.7485624673288029,
+      "grad_norm": 2.592941999435425,
+      "learning_rate": 4.269702294970461e-05,
+      "loss": 1.3111,
+      "step": 895
+    },
+    {
+      "epoch": 0.7527443805541035,
+      "grad_norm": 2.1964266300201416,
+      "learning_rate": 4.26194820950103e-05,
+      "loss": 1.3172,
+      "step": 900
+    },
+    {
+      "epoch": 0.7569262937794041,
+      "grad_norm": 2.253929853439331,
+      "learning_rate": 4.25416029777976e-05,
+      "loss": 1.2977,
+      "step": 905
+    },
+    {
+      "epoch": 0.7611082070047046,
+      "grad_norm": 2.3653616905212402,
+      "learning_rate": 4.246338709320615e-05,
+      "loss": 1.3397,
+      "step": 910
+    },
+    {
+      "epoch": 0.7652901202300052,
+      "grad_norm": 1.9790107011795044,
+      "learning_rate": 4.238483594284094e-05,
+      "loss": 1.299,
+      "step": 915
+    },
+    {
+      "epoch": 0.7694720334553058,
+      "grad_norm": 2.177802324295044,
+      "learning_rate": 4.230595103474345e-05,
+      "loss": 1.2083,
+      "step": 920
+    },
+    {
+      "epoch": 0.7736539466806064,
+      "grad_norm": 2.267620325088501,
+      "learning_rate": 4.222673388336272e-05,
+      "loss": 1.2712,
+      "step": 925
+    },
+    {
+      "epoch": 0.777835859905907,
+      "grad_norm": 2.323590040206909,
+      "learning_rate": 4.214718600952627e-05,
+      "loss": 1.2944,
+      "step": 930
+    },
+    {
+      "epoch": 0.7820177731312076,
+      "grad_norm": 2.2184839248657227,
+      "learning_rate": 4.2067308940410874e-05,
+      "loss": 1.3033,
+      "step": 935
+    },
+    {
+      "epoch": 0.786199686356508,
+      "grad_norm": 2.056938648223877,
+      "learning_rate": 4.1987104209513295e-05,
+      "loss": 1.2563,
+      "step": 940
+    },
+    {
+      "epoch": 0.7903815995818086,
+      "grad_norm": 2.0813541412353516,
+      "learning_rate": 4.1906573356620795e-05,
+      "loss": 1.3169,
+      "step": 945
+    },
+    {
+      "epoch": 0.7945635128071092,
+      "grad_norm": 2.2418994903564453,
+      "learning_rate": 4.182571792778163e-05,
+      "loss": 1.3366,
+      "step": 950
+    },
+    {
+      "epoch": 0.7987454260324098,
+      "grad_norm": 2.1746504306793213,
+      "learning_rate": 4.1744539475275276e-05,
+      "loss": 1.2695,
+      "step": 955
+    },
+    {
+      "epoch": 0.8029273392577104,
+      "grad_norm": 2.385899066925049,
+      "learning_rate": 4.1663039557582725e-05,
+      "loss": 1.275,
+      "step": 960
+    },
+    {
+      "epoch": 0.807109252483011,
+      "grad_norm": 2.4620730876922607,
+      "learning_rate": 4.158121973935653e-05,
+      "loss": 1.3441,
+      "step": 965
+    },
+    {
+      "epoch": 0.8112911657083115,
+      "grad_norm": 2.090711832046509,
+      "learning_rate": 4.149908159139073e-05,
+      "loss": 1.2754,
+      "step": 970
+    },
+    {
+      "epoch": 0.8154730789336121,
+      "grad_norm": 2.367952346801758,
+      "learning_rate": 4.141662669059076e-05,
+      "loss": 1.2821,
+      "step": 975
+    },
+    {
+      "epoch": 0.8196549921589127,
+      "grad_norm": 2.406475782394409,
+      "learning_rate": 4.133385661994312e-05,
+      "loss": 1.2917,
+      "step": 980
+    },
+    {
+      "epoch": 0.8238369053842133,
+      "grad_norm": 2.0637738704681396,
+      "learning_rate": 4.125077296848501e-05,
+      "loss": 1.2582,
+      "step": 985
+    },
+    {
+      "epoch": 0.8280188186095139,
+      "grad_norm": 2.3852176666259766,
+      "learning_rate": 4.1167377331273825e-05,
+      "loss": 1.2278,
+      "step": 990
+    },
+    {
+      "epoch": 0.8322007318348145,
+      "grad_norm": 2.0237960815429688,
+      "learning_rate": 4.1083671309356526e-05,
+      "loss": 1.3461,
+      "step": 995
+    },
+    {
+      "epoch": 0.836382645060115,
+      "grad_norm": 2.458031177520752,
+      "learning_rate": 4.0999656509738904e-05,
+      "loss": 1.2484,
+      "step": 1000
+    },
+    {
+      "epoch": 0.8405645582854155,
+      "grad_norm": 2.3338541984558105,
+      "learning_rate": 4.0915334545354734e-05,
+      "loss": 1.2526,
+      "step": 1005
+    },
+    {
+      "epoch": 0.8447464715107161,
+      "grad_norm": 2.289320230484009,
+      "learning_rate": 4.0830707035034795e-05,
+      "loss": 1.2643,
+      "step": 1010
+    },
+    {
+      "epoch": 0.8489283847360167,
+      "grad_norm": 2.461848735809326,
+      "learning_rate": 4.074577560347581e-05,
+      "loss": 1.29,
+      "step": 1015
+    },
+    {
+      "epoch": 0.8531102979613173,
+      "grad_norm": 2.458249568939209,
+      "learning_rate": 4.066054188120924e-05,
+      "loss": 1.2673,
+      "step": 1020
+    },
+    {
+      "epoch": 0.8572922111866179,
+      "grad_norm": 2.21874737739563,
+      "learning_rate": 4.0575007504569994e-05,
+      "loss": 1.3085,
+      "step": 1025
+    },
+    {
+      "epoch": 0.8614741244119185,
+      "grad_norm": 2.275045871734619,
+      "learning_rate": 4.0489174115665006e-05,
+      "loss": 1.2335,
+      "step": 1030
+    },
+    {
+      "epoch": 0.865656037637219,
+      "grad_norm": 2.1374430656433105,
+      "learning_rate": 4.04030433623417e-05,
+      "loss": 1.2699,
+      "step": 1035
+    },
+    {
+      "epoch": 0.8698379508625196,
+      "grad_norm": 2.3316330909729004,
+      "learning_rate": 4.031661689815637e-05,
+      "loss": 1.2847,
+      "step": 1040
+    },
+    {
+      "epoch": 0.8740198640878202,
+      "grad_norm": 2.3386001586914062,
+      "learning_rate": 4.022989638234243e-05,
+      "loss": 1.3394,
+      "step": 1045
+    },
+    {
+      "epoch": 0.8782017773131208,
+      "grad_norm": 2.4343066215515137,
+      "learning_rate": 4.0142883479778555e-05,
+      "loss": 1.2541,
+      "step": 1050
+    },
+    {
+      "epoch": 0.8823836905384214,
+      "grad_norm": 2.1589419841766357,
+      "learning_rate": 4.005557986095673e-05,
+      "loss": 1.3327,
+      "step": 1055
+    },
+    {
+      "epoch": 0.886565603763722,
+      "grad_norm": 2.2223572731018066,
+      "learning_rate": 3.996798720195018e-05,
+      "loss": 1.3057,
+      "step": 1060
+    },
+    {
+      "epoch": 0.8907475169890224,
+      "grad_norm": 2.5740420818328857,
+      "learning_rate": 3.988010718438115e-05,
+      "loss": 1.2945,
+      "step": 1065
+    },
+    {
+      "epoch": 0.894929430214323,
+      "grad_norm": 2.214611053466797,
+      "learning_rate": 3.9791941495388696e-05,
+      "loss": 1.2855,
+      "step": 1070
+    },
+    {
+      "epoch": 0.8991113434396236,
+      "grad_norm": 2.21602463722229,
+      "learning_rate": 3.970349182759623e-05,
+      "loss": 1.3271,
+      "step": 1075
+    },
+    {
+      "epoch": 0.9032932566649242,
+      "grad_norm": 2.2032415866851807,
+      "learning_rate": 3.9614759879079057e-05,
+      "loss": 1.2027,
+      "step": 1080
+    },
+    {
+      "epoch": 0.9074751698902248,
+      "grad_norm": 2.518728017807007,
+      "learning_rate": 3.9525747353331746e-05,
+      "loss": 1.2886,
+      "step": 1085
+    },
+    {
+      "epoch": 0.9116570831155254,
+      "grad_norm": 2.438845157623291,
+      "learning_rate": 3.943645595923548e-05,
+      "loss": 1.2054,
+      "step": 1090
+    },
+    {
+      "epoch": 0.9158389963408259,
+      "grad_norm": 2.460658073425293,
+      "learning_rate": 3.934688741102521e-05,
+      "loss": 1.2868,
+      "step": 1095
+    },
+    {
+      "epoch": 0.9200209095661265,
+      "grad_norm": 2.09260892868042,
+      "learning_rate": 3.925704342825671e-05,
+      "loss": 1.3027,
+      "step": 1100
+    },
+    {
+      "epoch": 0.9242028227914271,
+      "grad_norm": 2.4112346172332764,
+      "learning_rate": 3.916692573577366e-05,
+      "loss": 1.2995,
+      "step": 1105
+    },
+    {
+      "epoch": 0.9283847360167277,
+      "grad_norm": 2.157417058944702,
+      "learning_rate": 3.907653606367444e-05,
+      "loss": 1.2915,
+      "step": 1110
+    },
+    {
+      "epoch": 0.9325666492420283,
+      "grad_norm": 2.2395179271698,
+      "learning_rate": 3.898587614727896e-05,
+      "loss": 1.3126,
+      "step": 1115
+    },
+    {
+      "epoch": 0.9367485624673288,
+      "grad_norm": 2.457878589630127,
+      "learning_rate": 3.889494772709534e-05,
+      "loss": 1.2875,
+      "step": 1120
+    },
+    {
+      "epoch": 0.9409304756926293,
+      "grad_norm": 2.3669779300689697,
+      "learning_rate": 3.880375254878649e-05,
+      "loss": 1.2374,
+      "step": 1125
+    },
+    {
+      "epoch": 0.9451123889179299,
+      "grad_norm": 2.3185997009277344,
+      "learning_rate": 3.87122923631366e-05,
+      "loss": 1.1883,
+      "step": 1130
+    },
+    {
+      "epoch": 0.9492943021432305,
+      "grad_norm": 2.198770046234131,
+      "learning_rate": 3.862056892601753e-05,
+      "loss": 1.3516,
+      "step": 1135
+    },
+    {
+      "epoch": 0.9534762153685311,
+      "grad_norm": 2.344870090484619,
+      "learning_rate": 3.8528583998355094e-05,
+      "loss": 1.3012,
+      "step": 1140
+    },
+    {
+      "epoch": 0.9576581285938317,
+      "grad_norm": 2.1669209003448486,
+      "learning_rate": 3.843633934609526e-05,
+      "loss": 1.2588,
+      "step": 1145
+    },
+    {
+      "epoch": 0.9618400418191323,
+      "grad_norm": 2.242072820663452,
+      "learning_rate": 3.8343836740170216e-05,
+      "loss": 1.3303,
+      "step": 1150
+    },
+    {
+      "epoch": 0.9660219550444328,
+      "grad_norm": 2.9194626808166504,
+      "learning_rate": 3.825107795646444e-05,
+      "loss": 1.3177,
+      "step": 1155
+    },
+    {
+      "epoch": 0.9702038682697334,
+      "grad_norm": 2.298553943634033,
+      "learning_rate": 3.8158064775780554e-05,
+      "loss": 1.2528,
+      "step": 1160
+    },
+    {
+      "epoch": 0.974385781495034,
+      "grad_norm": 2.338935375213623,
+      "learning_rate": 3.806479898380512e-05,
+      "loss": 1.301,
+      "step": 1165
+    },
+    {
+      "epoch": 0.9785676947203346,
+      "grad_norm": 2.299428701400757,
+      "learning_rate": 3.797128237107441e-05,
+      "loss": 1.2752,
+      "step": 1170
+    },
+    {
+      "epoch": 0.9827496079456352,
+      "grad_norm": 2.338583469390869,
+      "learning_rate": 3.787751673294001e-05,
+      "loss": 1.2573,
+      "step": 1175
+    },
+    {
+      "epoch": 0.9869315211709357,
+      "grad_norm": 2.1797266006469727,
+      "learning_rate": 3.7783503869534327e-05,
+      "loss": 1.2752,
+      "step": 1180
+    },
+    {
+      "epoch": 0.9911134343962362,
+      "grad_norm": 2.1566450595855713,
+      "learning_rate": 3.768924558573606e-05,
+      "loss": 1.2867,
+      "step": 1185
+    },
+    {
+      "epoch": 0.9952953476215368,
+      "grad_norm": 2.3432397842407227,
+      "learning_rate": 3.759474369113555e-05,
+      "loss": 1.3053,
+      "step": 1190
+    },
+    {
+      "epoch": 0.9994772608468374,
+      "grad_norm": 2.2833595275878906,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 1.2817,
+      "step": 1195
+    },
+    {
+      "epoch": 1.003659174072138,
+      "grad_norm": 2.286717176437378,
+      "learning_rate": 3.740501633123872e-05,
+      "loss": 1.2423,
+      "step": 1200
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 3585,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.5544326089533686e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ad489884f87ec96cc1e49b25622db5c6c3c1eafcad1be5306265a7460b6619a
+size 5304

checkpoint-1300/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+---
+
+# 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 0.11.1