Upload folder using huggingface_hub

README.md

@@ -0,0 +1,202 @@
+---
+base_model: sunjisen/qwen_Weather
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.13.2

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/home/qwen1_8/Qwen-1_8B-Chat-Int4",
+  "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": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "c_proj",
+    "w2",
+    "w1",
+    "c_attn"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b6dbe1ed71e3316bda59b515b949cec18be07512c444dc7197eb362d97031e4
+size 107378800

infer.py

@@ -0,0 +1,25 @@
+from peft import AutoPeftModelForCausalLM
+from transformers import AutoTokenizer
+
+prompt_template='''
+给定一句话：“%s”，请你按步骤要求工作。
+
+步骤1：识别这句话中的城市和日期共2个信息
+步骤2：根据城市和日期信息，生成JSON字符串，格式为{"city":城市,"date":日期}
+
+请问，这个JSON字符串是：
+'''
+tokenizer = AutoTokenizer.from_pretrained('/home/Qwen/output_qwen')
+model = AutoPeftModelForCausalLM.from_pretrained(
+    '/home/Qwen/output_qwen', # path to the output directory
+    device_map="auto",
+    trust_remote_code=True
+).eval()
+model.generation_config.top_p=0 # 只选择概率最高的token
+
+Q_list=['2020年4月16号三亚下雨么？','青岛3-15号天气预报','5月6号下雪么，城市是威海','青岛2023年12月30号有雾霾么?','我打算6月1号去北京旅游，请问天气怎么样？','你们打算1月3号坐哪一趟航班去上海？','小明和小红是8月8号在上海结婚么?',
+        '一起去东北看冰雕么，大概是1月15号左右，我们3个人一起']
+for Q in Q_list:
+    prompt=prompt_template%(Q,)
+    A,hist=model.chat(tokenizer,prompt,history=None)
+    print('Q:%s\nA:%s\n'%(Q,A))

inference.py

@@ -0,0 +1,13 @@
+from peft import AutoPeftModelForCausalLM
+from transformers import AutoTokenizer
+
+tokenizer = AutoTokenizer.from_pretrained('/home/Qwen/output_qwen')
+model = AutoPeftModelForCausalLM.from_pretrained(
+    '/home/Qwen/output_qwen', # path to the output directory
+    device_map="auto",
+    trust_remote_code=True
+).eval()
+model.generation_config.top_p=0
+prompt='青岛海边钓鱼需要特别注意什么？'
+resp,hist=model.chat(tokenizer,prompt,history=None)
+print(resp)

special_tokens_map.json

@@ -0,0 +1,3 @@
+{
+  "pad_token": "<|endoftext|>"
+}

tokenization_qwen.py

@@ -0,0 +1,276 @@
+# Copyright (c) Alibaba Cloud.
+#
+# This source code is licensed under the license found in the
+# LICENSE file in the root directory of this source tree.
+
+"""Tokenization classes for QWen."""
+
+import base64
+import logging
+import os
+import unicodedata
+from typing import Collection, Dict, List, Set, Tuple, Union
+
+import tiktoken
+from transformers import PreTrainedTokenizer, AddedToken
+
+logger = logging.getLogger(__name__)
+
+
+VOCAB_FILES_NAMES = {"vocab_file": "qwen.tiktoken"}
+
+PAT_STR = r"""(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\r\n\p{L}\p{N}]?\p{L}+|\p{N}| ?[^\s\p{L}\p{N}]+[\r\n]*|\s*[\r\n]+|\s+(?!\S)|\s+"""
+ENDOFTEXT = "<|endoftext|>"
+IMSTART = "<|im_start|>"
+IMEND = "<|im_end|>"
+# as the default behavior is changed to allow special tokens in
+# regular texts, the surface forms of special tokens need to be
+# as different as possible to minimize the impact
+EXTRAS = tuple((f"<|extra_{i}|>" for i in range(205)))
+# changed to use actual index to avoid misconfiguration with vocabulary expansion
+SPECIAL_START_ID = 151643
+SPECIAL_TOKENS = tuple(
+    enumerate(
+        (
+            (
+                ENDOFTEXT,
+                IMSTART,
+                IMEND,
+            )
+            + EXTRAS
+        ),
+        start=SPECIAL_START_ID,
+    )
+)
+SPECIAL_TOKENS_SET = set(t for i, t in SPECIAL_TOKENS)
+
+
+def _load_tiktoken_bpe(tiktoken_bpe_file: str) -> Dict[bytes, int]:
+    with open(tiktoken_bpe_file, "rb") as f:
+        contents = f.read()
+    return {
+        base64.b64decode(token): int(rank)
+        for token, rank in (line.split() for line in contents.splitlines() if line)
+    }
+
+
+class QWenTokenizer(PreTrainedTokenizer):
+    """QWen tokenizer."""
+
+    vocab_files_names = VOCAB_FILES_NAMES
+
+    def __init__(
+        self,
+        vocab_file,
+        errors="replace",
+        extra_vocab_file=None,
+        **kwargs,
+    ):
+        super().__init__(**kwargs)
+
+        # how to handle errors in decoding UTF-8 byte sequences
+        # use ignore if you are in streaming inference
+        self.errors = errors  
+
+        self.mergeable_ranks = _load_tiktoken_bpe(vocab_file)  # type: Dict[bytes, int]
+        self.special_tokens = {
+            token: index
+            for index, token in SPECIAL_TOKENS
+        }
+
+        # try load extra vocab from file
+        if extra_vocab_file is not None:
+            used_ids = set(self.mergeable_ranks.values()) | set(self.special_tokens.values())
+            extra_mergeable_ranks = _load_tiktoken_bpe(extra_vocab_file)
+            for token, index in extra_mergeable_ranks.items():
+                if token in self.mergeable_ranks:
+                    logger.info(f"extra token {token} exists, skipping")
+                    continue
+                if index in used_ids:
+                    logger.info(f'the index {index} for extra token {token} exists, skipping')
+                    continue
+                self.mergeable_ranks[token] = index
+            # the index may be sparse after this, but don't worry tiktoken.Encoding will handle this
+
+        enc = tiktoken.Encoding(
+            "Qwen",
+            pat_str=PAT_STR,
+            mergeable_ranks=self.mergeable_ranks,
+            special_tokens=self.special_tokens,
+        )
+        assert (
+            len(self.mergeable_ranks) + len(self.special_tokens) == enc.n_vocab
+        ), f"{len(self.mergeable_ranks) + len(self.special_tokens)} != {enc.n_vocab} in encoding"
+
+        self.decoder = {
+            v: k for k, v in self.mergeable_ranks.items()
+        }  # type: dict[int, bytes|str]
+        self.decoder.update({v: k for k, v in self.special_tokens.items()})
+
+        self.tokenizer = enc  # type: tiktoken.Encoding
+
+        self.eod_id = self.tokenizer.eot_token
+        self.im_start_id = self.special_tokens[IMSTART]
+        self.im_end_id = self.special_tokens[IMEND]
+
+    def __getstate__(self):
+        # for pickle lovers
+        state = self.__dict__.copy()
+        del state["tokenizer"]
+        return state
+
+    def __setstate__(self, state):
+        # tokenizer is not python native; don't pass it; rebuild it
+        self.__dict__.update(state)
+        enc = tiktoken.Encoding(
+            "Qwen",
+            pat_str=PAT_STR,
+            mergeable_ranks=self.mergeable_ranks,
+            special_tokens=self.special_tokens,
+        )
+        self.tokenizer = enc
+
+    def __len__(self) -> int:
+        return self.tokenizer.n_vocab
+
+    def get_vocab(self) -> Dict[bytes, int]:
+        return self.mergeable_ranks
+
+    def convert_tokens_to_ids(
+        self, tokens: Union[bytes, str, List[Union[bytes, str]]]
+    ) -> List[int]:
+        ids = []
+        if isinstance(tokens, (str, bytes)):
+            if tokens in self.special_tokens:
+                return self.special_tokens[tokens]
+            else:
+                return self.mergeable_ranks.get(tokens)
+        for token in tokens:
+            if token in self.special_tokens:
+                ids.append(self.special_tokens[token])
+            else:
+                ids.append(self.mergeable_ranks.get(token))
+        return ids
+
+    def _add_tokens(
+        self,
+        new_tokens: Union[List[str], List[AddedToken]],
+        special_tokens: bool = False,
+    ) -> int:
+        if not special_tokens and new_tokens:
+            raise ValueError("Adding regular tokens is not supported")
+        for token in new_tokens:
+            surface_form = token.content if isinstance(token, AddedToken) else token
+            if surface_form not in SPECIAL_TOKENS_SET:
+                raise ValueError("Adding unknown special tokens is not supported")
+        return 0
+
+    def save_vocabulary(self, save_directory: str, **kwargs) -> Tuple[str]:
+        """
+        Save only the vocabulary of the tokenizer (vocabulary).
+
+        Returns:
+            `Tuple(str)`: Paths to the files saved.
+        """
+        file_path = os.path.join(save_directory, "qwen.tiktoken")
+        with open(file_path, "w", encoding="utf8") as w:
+            for k, v in self.mergeable_ranks.items():
+                line = base64.b64encode(k).decode("utf8") + " " + str(v) + "\n"
+                w.write(line)
+        return (file_path,)
+
+    def tokenize(
+        self,
+        text: str,
+        allowed_special: Union[Set, str] = "all",
+        disallowed_special: Union[Collection, str] = (),
+        **kwargs,
+    ) -> List[Union[bytes, str]]:
+        """
+        Converts a string in a sequence of tokens.
+
+        Args:
+            text (`str`):
+                The sequence to be encoded.
+            allowed_special (`Literal["all"]` or `set`):
+                The surface forms of the tokens to be encoded as special tokens in regular texts.
+                Default to "all".
+            disallowed_special (`Literal["all"]` or `Collection`):
+                The surface forms of the tokens that should not be in regular texts and trigger errors.
+                Default to an empty tuple.
+
+            kwargs (additional keyword arguments, *optional*):
+                Will be passed to the underlying model specific encode method.
+
+        Returns:
+            `List[bytes|str]`: The list of tokens.
+        """
+        tokens = []
+        text = unicodedata.normalize("NFC", text)
+
+        # this implementation takes a detour: text -> token id -> token surface forms
+        for t in self.tokenizer.encode(
+            text, allowed_special=allowed_special, disallowed_special=disallowed_special
+        ):
+            tokens.append(self.decoder[t])
+        return tokens
+
+    def convert_tokens_to_string(self, tokens: List[Union[bytes, str]]) -> str:
+        """
+        Converts a sequence of tokens in a single string.
+        """
+        text = ""
+        temp = b""
+        for t in tokens:
+            if isinstance(t, str):
+                if temp:
+                    text += temp.decode("utf-8", errors=self.errors)
+                    temp = b""
+                text += t
+            elif isinstance(t, bytes):
+                temp += t
+            else:
+                raise TypeError("token should only be of type types or str")
+        if temp:
+            text += temp.decode("utf-8", errors=self.errors)
+        return text
+
+    @property
+    def vocab_size(self):
+        return self.tokenizer.n_vocab
+
+    def _convert_id_to_token(self, index: int) -> Union[bytes, str]:
+        """Converts an id to a token, special tokens included"""
+        if index in self.decoder:
+            return self.decoder[index]
+        raise ValueError("unknown ids")
+
+    def _convert_token_to_id(self, token: Union[bytes, str]) -> int:
+        """Converts a token to an id using the vocab, special tokens included"""
+        if token in self.special_tokens:
+            return self.special_tokens[token]
+        if token in self.mergeable_ranks:
+            return self.mergeable_ranks[token]
+        raise ValueError("unknown token")
+
+    def _tokenize(self, text: str, **kwargs):
+        """
+        Converts a string in a sequence of tokens (string), using the tokenizer. Split in words for word-based
+        vocabulary or sub-words for sub-word-based vocabularies (BPE/SentencePieces/WordPieces).
+
+        Do NOT take care of added tokens.
+        """
+        raise NotImplementedError
+
+    def _decode(
+        self,
+        token_ids: Union[int, List[int]],
+        skip_special_tokens: bool = False,
+        errors: str = None,
+        **kwargs,
+    ) -> str:
+        if isinstance(token_ids, int):
+            token_ids = [token_ids]
+        if skip_special_tokens:
+            token_ids = [i for i in token_ids if i < self.eod_id]
+        return self.tokenizer.decode(token_ids, errors=errors or self.errors)

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "added_tokens_decoder": {},
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_qwen.QWenTokenizer",
+      null
+    ]
+  },
+  "clean_up_tokenization_spaces": true,
+  "model_max_length": 512,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "tokenizer_class": "QWenTokenizer"
+}

trainer_state.json

@@ -0,0 +1,1890 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.96,
+  "eval_steps": 500,
+  "global_step": 310,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0,
+      "loss": 0.7372,
+      "step": 1
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00015,
+      "loss": 0.8221,
+      "step": 2
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0002377443751081734,
+      "loss": 0.7888,
+      "step": 3
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 0.5,
+      "step": 4
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 0.2017,
+      "step": 5
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 0.0627,
+      "step": 6
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 0.0665,
+      "step": 7
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.0402,
+      "step": 8
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.0236,
+      "step": 9
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.0195,
+      "step": 10
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.0181,
+      "step": 11
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.015,
+      "step": 12
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.0082,
+      "step": 13
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.0096,
+      "step": 14
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.004,
+      "step": 15
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.0025,
+      "step": 16
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.001,
+      "step": 17
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.0106,
+      "step": 18
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.0011,
+      "step": 19
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.0022,
+      "step": 20
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.0011,
+      "step": 21
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.0011,
+      "step": 22
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.0033,
+      "step": 23
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.0016,
+      "step": 24
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.0003,
+      "step": 25
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.0001,
+      "step": 26
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.0011,
+      "step": 27
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.0013,
+      "step": 28
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.0001,
+      "step": 29
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.0001,
+      "step": 30
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.0001,
+      "step": 31
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.0227,
+      "step": 32
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.0001,
+      "step": 33
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.0001,
+      "step": 34
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.0001,
+      "step": 35
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.0477,
+      "step": 36
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.0001,
+      "step": 37
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.0002,
+      "step": 38
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.0022,
+      "step": 39
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.0001,
+      "step": 40
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.0005,
+      "step": 41
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.0001,
+      "step": 43
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.0001,
+      "step": 44
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.0001,
+      "step": 45
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.0001,
+      "step": 46
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.0001,
+      "step": 47
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.0001,
+      "step": 48
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.0015,
+      "step": 49
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.0001,
+      "step": 50
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.0001,
+      "step": 51
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.0001,
+      "step": 52
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.0001,
+      "step": 53
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.0001,
+      "step": 54
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003,
+      "loss": 0.0001,
+      "step": 55
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003,
+      "loss": 0.0001,
+      "step": 56
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.0002,
+      "step": 57
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003,
+      "loss": 0.0002,
+      "step": 58
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003,
+      "loss": 0.0001,
+      "step": 59
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003,
+      "loss": 0.0001,
+      "step": 60
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003,
+      "loss": 0.0001,
+      "step": 61
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 62
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0003,
+      "loss": 0.0001,
+      "step": 63
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0003,
+      "loss": 0.0001,
+      "step": 64
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 65
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 66
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 67
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.0003,
+      "loss": 0.0001,
+      "step": 68
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0003,
+      "loss": 0.0001,
+      "step": 69
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.0003,
+      "loss": 0.0001,
+      "step": 70
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 71
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 72
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 73
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.0003,
+      "loss": 0.0007,
+      "step": 74
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 75
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 76
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 77
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 78
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 79
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.0003,
+      "loss": 0.0001,
+      "step": 80
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 81
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 82
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 83
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 84
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 85
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 86
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 87
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 88
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 89
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 90
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.0003,
+      "loss": 0.0001,
+      "step": 91
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 92
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 93
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 94
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 95
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 96
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 97
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 98
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 99
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.0003,
+      "loss": 0.0002,
+      "step": 100
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 101
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.0003,
+      "loss": 0.0001,
+      "step": 102
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 103
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 104
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 105
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 106
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 107
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 108
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 109
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 110
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 111
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 112
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 0.0003,
+      "loss": 0.0007,
+      "step": 113
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 114
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 115
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 116
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 117
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 118
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 119
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 120
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 121
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 122
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 123
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 124
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 125
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 126
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 127
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 128
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 129
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 130
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 131
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 132
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 133
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 134
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 135
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 136
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 137
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 138
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 139
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 140
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 141
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 142
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 143
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 144
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 145
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 146
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 147
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 148
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 149
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 150
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 151
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 152
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 153
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 154
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 155
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 156
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 157
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 158
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 159
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 160
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 161
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 162
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 163
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 164
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 165
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 166
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 167
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 168
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 169
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 170
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 171
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 172
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 173
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 174
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 175
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 176
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 177
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 178
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 179
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 180
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 181
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 182
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 183
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 184
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 185
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 186
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 187
+    },
+    {
+      "epoch": 3.01,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 188
+    },
+    {
+      "epoch": 3.02,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 189
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 190
+    },
+    {
+      "epoch": 3.06,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 191
+    },
+    {
+      "epoch": 3.07,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 192
+    },
+    {
+      "epoch": 3.09,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 193
+    },
+    {
+      "epoch": 3.1,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 194
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 195
+    },
+    {
+      "epoch": 3.14,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 196
+    },
+    {
+      "epoch": 3.15,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 197
+    },
+    {
+      "epoch": 3.17,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 198
+    },
+    {
+      "epoch": 3.18,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 199
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 200
+    },
+    {
+      "epoch": 3.22,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 201
+    },
+    {
+      "epoch": 3.23,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 202
+    },
+    {
+      "epoch": 3.25,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 203
+    },
+    {
+      "epoch": 3.26,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 204
+    },
+    {
+      "epoch": 3.28,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 205
+    },
+    {
+      "epoch": 3.3,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 206
+    },
+    {
+      "epoch": 3.31,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 207
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 208
+    },
+    {
+      "epoch": 3.34,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 209
+    },
+    {
+      "epoch": 3.36,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 210
+    },
+    {
+      "epoch": 3.38,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 211
+    },
+    {
+      "epoch": 3.39,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 212
+    },
+    {
+      "epoch": 3.41,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 213
+    },
+    {
+      "epoch": 3.42,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 214
+    },
+    {
+      "epoch": 3.44,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 215
+    },
+    {
+      "epoch": 3.46,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 216
+    },
+    {
+      "epoch": 3.47,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 217
+    },
+    {
+      "epoch": 3.49,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 218
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 219
+    },
+    {
+      "epoch": 3.52,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 220
+    },
+    {
+      "epoch": 3.54,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 221
+    },
+    {
+      "epoch": 3.55,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 222
+    },
+    {
+      "epoch": 3.57,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 223
+    },
+    {
+      "epoch": 3.58,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 224
+    },
+    {
+      "epoch": 3.6,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 225
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 226
+    },
+    {
+      "epoch": 3.63,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 227
+    },
+    {
+      "epoch": 3.65,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 228
+    },
+    {
+      "epoch": 3.66,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 229
+    },
+    {
+      "epoch": 3.68,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 230
+    },
+    {
+      "epoch": 3.7,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 231
+    },
+    {
+      "epoch": 3.71,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 232
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 233
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 234
+    },
+    {
+      "epoch": 3.76,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 235
+    },
+    {
+      "epoch": 3.78,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 236
+    },
+    {
+      "epoch": 3.79,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 237
+    },
+    {
+      "epoch": 3.81,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 238
+    },
+    {
+      "epoch": 3.82,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 239
+    },
+    {
+      "epoch": 3.84,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 240
+    },
+    {
+      "epoch": 3.86,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 241
+    },
+    {
+      "epoch": 3.87,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 242
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 243
+    },
+    {
+      "epoch": 3.9,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 244
+    },
+    {
+      "epoch": 3.92,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 245
+    },
+    {
+      "epoch": 3.94,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 246
+    },
+    {
+      "epoch": 3.95,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 247
+    },
+    {
+      "epoch": 3.97,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 248
+    },
+    {
+      "epoch": 3.98,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 249
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 250
+    },
+    {
+      "epoch": 4.02,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 251
+    },
+    {
+      "epoch": 4.03,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 252
+    },
+    {
+      "epoch": 4.05,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 253
+    },
+    {
+      "epoch": 4.06,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 254
+    },
+    {
+      "epoch": 4.08,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 255
+    },
+    {
+      "epoch": 4.1,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 256
+    },
+    {
+      "epoch": 4.11,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 257
+    },
+    {
+      "epoch": 4.13,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 258
+    },
+    {
+      "epoch": 4.14,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 259
+    },
+    {
+      "epoch": 4.16,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 260
+    },
+    {
+      "epoch": 4.18,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 261
+    },
+    {
+      "epoch": 4.19,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 262
+    },
+    {
+      "epoch": 4.21,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 263
+    },
+    {
+      "epoch": 4.22,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 264
+    },
+    {
+      "epoch": 4.24,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 265
+    },
+    {
+      "epoch": 4.26,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 266
+    },
+    {
+      "epoch": 4.27,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 267
+    },
+    {
+      "epoch": 4.29,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 268
+    },
+    {
+      "epoch": 4.3,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 269
+    },
+    {
+      "epoch": 4.32,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 270
+    },
+    {
+      "epoch": 4.34,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 271
+    },
+    {
+      "epoch": 4.35,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 272
+    },
+    {
+      "epoch": 4.37,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 273
+    },
+    {
+      "epoch": 4.38,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 274
+    },
+    {
+      "epoch": 4.4,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 275
+    },
+    {
+      "epoch": 4.42,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 276
+    },
+    {
+      "epoch": 4.43,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 277
+    },
+    {
+      "epoch": 4.45,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 278
+    },
+    {
+      "epoch": 4.46,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 279
+    },
+    {
+      "epoch": 4.48,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 280
+    },
+    {
+      "epoch": 4.5,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 281
+    },
+    {
+      "epoch": 4.51,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 282
+    },
+    {
+      "epoch": 4.53,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 283
+    },
+    {
+      "epoch": 4.54,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 284
+    },
+    {
+      "epoch": 4.56,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 285
+    },
+    {
+      "epoch": 4.58,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 286
+    },
+    {
+      "epoch": 4.59,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 287
+    },
+    {
+      "epoch": 4.61,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 288
+    },
+    {
+      "epoch": 4.62,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 289
+    },
+    {
+      "epoch": 4.64,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 290
+    },
+    {
+      "epoch": 4.66,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 291
+    },
+    {
+      "epoch": 4.67,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 292
+    },
+    {
+      "epoch": 4.69,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 293
+    },
+    {
+      "epoch": 4.7,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 294
+    },
+    {
+      "epoch": 4.72,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 295
+    },
+    {
+      "epoch": 4.74,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 296
+    },
+    {
+      "epoch": 4.75,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 297
+    },
+    {
+      "epoch": 4.77,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 298
+    },
+    {
+      "epoch": 4.78,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 299
+    },
+    {
+      "epoch": 4.8,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 300
+    },
+    {
+      "epoch": 4.82,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 301
+    },
+    {
+      "epoch": 4.83,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 302
+    },
+    {
+      "epoch": 4.85,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 303
+    },
+    {
+      "epoch": 4.86,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 304
+    },
+    {
+      "epoch": 4.88,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 305
+    },
+    {
+      "epoch": 4.9,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 306
+    },
+    {
+      "epoch": 4.91,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 307
+    },
+    {
+      "epoch": 4.93,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 308
+    },
+    {
+      "epoch": 4.94,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 309
+    },
+    {
+      "epoch": 4.96,
+      "learning_rate": 0.0003,
+      "loss": 0.0,
+      "step": 310
+    },
+    {
+      "epoch": 4.96,
+      "step": 310,
+      "total_flos": 5560623358279680.0,
+      "train_loss": 0.011049593456329838,
+      "train_runtime": 1789.5384,
+      "train_samples_per_second": 2.794,
+      "train_steps_per_second": 0.173
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 310,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 1000,
+  "total_flos": 5560623358279680.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dc2c60bc953b5c1b5bf33cb3150c7336cddb6245c71e813c947a01cf5c9d25d
+size 6264