Upload 13 files

README.md

@@ -0,0 +1,61 @@
+---
+license: other
+library_name: peft
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+base_model: Qwen/Qwen-7B-Chat
+model-index:
+- name: brand_model
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# brand_model
+
+This model is a fine-tuned version of [Qwen/Qwen-7B-Chat](https://huggingface.co/Qwen/Qwen-7B-Chat) on the brand_train dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0127
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 1.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.7.1
+- Transformers 4.36.2
+- Pytorch 2.1.2+cu118
+- Datasets 2.15.0
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,25 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen-7B-Chat",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "c_attn"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4287c2802fef56fee6fd79795006f5a6d6caacb21b90d599369048fc43c8eb83
+size 16785504

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.012725877575576305,
+    "eval_runtime": 1718.6779,
+    "eval_samples_per_second": 22.862,
+    "eval_steps_per_second": 2.858,
+    "train_loss": 0.04709457870986094,
+    "train_runtime": 3992.6154,
+    "train_samples_per_second": 6.561,
+    "train_steps_per_second": 0.205
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.012725877575576305,
+    "eval_runtime": 1718.6779,
+    "eval_samples_per_second": 22.862,
+    "eval_steps_per_second": 2.858
+}

special_tokens_map.json

@@ -0,0 +1,13 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "eos_token": "<|endoftext|>",
+  "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 +1,19 @@
+{
+  "added_tokens_decoder": {},
+  "additional_special_tokens": [
+    "<|im_end|>"
+  ],
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_qwen.QWenTokenizer",
+      null
+    ]
+  },
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "QWenTokenizer"
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.04709457870986094,
+    "train_runtime": 3992.6154,
+    "train_samples_per_second": 6.561,
+    "train_steps_per_second": 0.205
+}

trainer_log.jsonl

@@ -0,0 +1,165 @@
+{"current_steps": 5, "total_steps": 818, "loss": 1.9867, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.999539075477821e-05, "epoch": 0.01, "percentage": 0.61, "elapsed_time": "0:00:20", "remaining_time": "0:55:25"}
+{"current_steps": 10, "total_steps": 818, "loss": 1.5198, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.998156471872415e-05, "epoch": 0.01, "percentage": 1.22, "elapsed_time": "0:00:42", "remaining_time": "0:57:15"}
+{"current_steps": 15, "total_steps": 818, "loss": 0.9883, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.995852699004508e-05, "epoch": 0.02, "percentage": 1.83, "elapsed_time": "0:01:05", "remaining_time": "0:58:11"}
+{"current_steps": 20, "total_steps": 818, "loss": 0.3031, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.992628606366426e-05, "epoch": 0.02, "percentage": 2.44, "elapsed_time": "0:01:27", "remaining_time": "0:57:51"}
+{"current_steps": 25, "total_steps": 818, "loss": 0.0533, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.988485382808856e-05, "epoch": 0.03, "percentage": 3.06, "elapsed_time": "0:01:49", "remaining_time": "0:58:03"}
+{"current_steps": 30, "total_steps": 818, "loss": 0.0318, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.983424556102469e-05, "epoch": 0.04, "percentage": 3.67, "elapsed_time": "0:02:12", "remaining_time": "0:57:53"}
+{"current_steps": 35, "total_steps": 818, "loss": 0.0605, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.97744799237457e-05, "epoch": 0.04, "percentage": 4.28, "elapsed_time": "0:02:34", "remaining_time": "0:57:42"}
+{"current_steps": 40, "total_steps": 818, "loss": 0.0126, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.970557895420984e-05, "epoch": 0.05, "percentage": 4.89, "elapsed_time": "0:02:56", "remaining_time": "0:57:12"}
+{"current_steps": 45, "total_steps": 818, "loss": 0.0017, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9627568058934274e-05, "epoch": 0.05, "percentage": 5.5, "elapsed_time": "0:03:16", "remaining_time": "0:56:23"}
+{"current_steps": 50, "total_steps": 818, "loss": 0.0005, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.95404760036267e-05, "epoch": 0.06, "percentage": 6.11, "elapsed_time": "0:03:39", "remaining_time": "0:56:06"}
+{"current_steps": 55, "total_steps": 818, "loss": 0.0784, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9444334902578315e-05, "epoch": 0.07, "percentage": 6.72, "elapsed_time": "0:04:00", "remaining_time": "0:55:34"}
+{"current_steps": 60, "total_steps": 818, "loss": 0.043, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9339180206821955e-05, "epoch": 0.07, "percentage": 7.33, "elapsed_time": "0:04:23", "remaining_time": "0:55:29"}
+{"current_steps": 65, "total_steps": 818, "loss": 0.0022, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.922505069105995e-05, "epoch": 0.08, "percentage": 7.95, "elapsed_time": "0:04:45", "remaining_time": "0:55:05"}
+{"current_steps": 70, "total_steps": 818, "loss": 0.0101, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9101988439366295e-05, "epoch": 0.09, "percentage": 8.56, "elapsed_time": "0:05:07", "remaining_time": "0:54:43"}
+{"current_steps": 75, "total_steps": 818, "loss": 0.0471, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.897003882966866e-05, "epoch": 0.09, "percentage": 9.17, "elapsed_time": "0:05:29", "remaining_time": "0:54:19"}
+{"current_steps": 80, "total_steps": 818, "loss": 0.002, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.8829250517015684e-05, "epoch": 0.1, "percentage": 9.78, "elapsed_time": "0:05:51", "remaining_time": "0:54:04"}
+{"current_steps": 85, "total_steps": 818, "loss": 0.0109, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.867967541563594e-05, "epoch": 0.1, "percentage": 10.39, "elapsed_time": "0:06:12", "remaining_time": "0:53:34"}
+{"current_steps": 90, "total_steps": 818, "loss": 0.0322, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.8521368679795154e-05, "epoch": 0.11, "percentage": 11.0, "elapsed_time": "0:06:33", "remaining_time": "0:53:05"}
+{"current_steps": 95, "total_steps": 818, "loss": 0.0156, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.835438868345858e-05, "epoch": 0.12, "percentage": 11.61, "elapsed_time": "0:06:54", "remaining_time": "0:52:31"}
+{"current_steps": 100, "total_steps": 818, "loss": 0.0912, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.817879699876623e-05, "epoch": 0.12, "percentage": 12.22, "elapsed_time": "0:07:16", "remaining_time": "0:52:12"}
+{"current_steps": 105, "total_steps": 818, "loss": 0.027, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.7994658373328804e-05, "epoch": 0.13, "percentage": 12.84, "elapsed_time": "0:07:37", "remaining_time": "0:51:47"}
+{"current_steps": 110, "total_steps": 818, "loss": 0.027, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.780204070635266e-05, "epoch": 0.13, "percentage": 13.45, "elapsed_time": "0:08:01", "remaining_time": "0:51:40"}
+{"current_steps": 115, "total_steps": 818, "loss": 0.0206, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.760101502360268e-05, "epoch": 0.14, "percentage": 14.06, "elapsed_time": "0:08:22", "remaining_time": "0:51:14"}
+{"current_steps": 120, "total_steps": 818, "loss": 0.012, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.739165545121228e-05, "epoch": 0.15, "percentage": 14.67, "elapsed_time": "0:08:44", "remaining_time": "0:50:50"}
+{"current_steps": 125, "total_steps": 818, "loss": 0.002, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.717403918835017e-05, "epoch": 0.15, "percentage": 15.28, "elapsed_time": "0:09:07", "remaining_time": "0:50:37"}
+{"current_steps": 130, "total_steps": 818, "loss": 0.0052, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.694824647875391e-05, "epoch": 0.16, "percentage": 15.89, "elapsed_time": "0:09:35", "remaining_time": "0:50:46"}
+{"current_steps": 135, "total_steps": 818, "loss": 0.0036, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.6714360581140935e-05, "epoch": 0.16, "percentage": 16.5, "elapsed_time": "0:10:20", "remaining_time": "0:52:21"}
+{"current_steps": 140, "total_steps": 818, "loss": 0.0386, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.647246773850773e-05, "epoch": 0.17, "percentage": 17.11, "elapsed_time": "0:11:08", "remaining_time": "0:53:56"}
+{"current_steps": 145, "total_steps": 818, "loss": 0.0546, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.6222657146328624e-05, "epoch": 0.18, "percentage": 17.73, "elapsed_time": "0:11:58", "remaining_time": "0:55:34"}
+{"current_steps": 150, "total_steps": 818, "loss": 0.0472, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.596502091966588e-05, "epoch": 0.18, "percentage": 18.34, "elapsed_time": "0:12:45", "remaining_time": "0:56:47"}
+{"current_steps": 155, "total_steps": 818, "loss": 0.0779, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.5699654059203225e-05, "epoch": 0.19, "percentage": 18.95, "elapsed_time": "0:20:59", "remaining_time": "1:29:47"}
+{"current_steps": 160, "total_steps": 818, "loss": 0.0169, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.542665441621537e-05, "epoch": 0.2, "percentage": 19.56, "elapsed_time": "0:22:48", "remaining_time": "1:33:49"}
+{"current_steps": 165, "total_steps": 818, "loss": 0.0249, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.51461226564863e-05, "epoch": 0.2, "percentage": 20.17, "elapsed_time": "0:23:10", "remaining_time": "1:31:43"}
+{"current_steps": 170, "total_steps": 818, "loss": 0.0132, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.485816222318986e-05, "epoch": 0.21, "percentage": 20.78, "elapsed_time": "0:23:32", "remaining_time": "1:29:43"}
+{"current_steps": 175, "total_steps": 818, "loss": 0.0163, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.4562879298746165e-05, "epoch": 0.21, "percentage": 21.39, "elapsed_time": "0:23:51", "remaining_time": "1:27:37"}
+{"current_steps": 180, "total_steps": 818, "loss": 0.0181, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.4260382765667875e-05, "epoch": 0.22, "percentage": 22.0, "elapsed_time": "0:24:10", "remaining_time": "1:25:41"}
+{"current_steps": 185, "total_steps": 818, "loss": 0.0421, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.395078416641099e-05, "epoch": 0.23, "percentage": 22.62, "elapsed_time": "0:24:29", "remaining_time": "1:23:49"}
+{"current_steps": 190, "total_steps": 818, "loss": 0.0011, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.363419766224464e-05, "epoch": 0.23, "percentage": 23.23, "elapsed_time": "0:24:49", "remaining_time": "1:22:03"}
+{"current_steps": 195, "total_steps": 818, "loss": 0.0062, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.3310739991155365e-05, "epoch": 0.24, "percentage": 23.84, "elapsed_time": "0:25:09", "remaining_time": "1:20:22"}
+{"current_steps": 200, "total_steps": 818, "loss": 0.0013, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.2980530424801146e-05, "epoch": 0.24, "percentage": 24.45, "elapsed_time": "0:25:30", "remaining_time": "1:18:50"}
+{"current_steps": 205, "total_steps": 818, "loss": 0.0515, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.264369072453126e-05, "epoch": 0.25, "percentage": 25.06, "elapsed_time": "0:25:51", "remaining_time": "1:17:19"}
+{"current_steps": 210, "total_steps": 818, "loss": 0.009, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.230034509648803e-05, "epoch": 0.26, "percentage": 25.67, "elapsed_time": "0:26:12", "remaining_time": "1:15:51"}
+{"current_steps": 215, "total_steps": 818, "loss": 0.0132, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.19506201458071e-05, "epoch": 0.26, "percentage": 26.28, "elapsed_time": "0:26:32", "remaining_time": "1:14:26"}
+{"current_steps": 220, "total_steps": 818, "loss": 0.0092, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.159464482993308e-05, "epoch": 0.27, "percentage": 26.89, "elapsed_time": "0:26:51", "remaining_time": "1:13:01"}
+{"current_steps": 225, "total_steps": 818, "loss": 0.0429, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.123255041106788e-05, "epoch": 0.27, "percentage": 27.51, "elapsed_time": "0:27:12", "remaining_time": "1:11:41"}
+{"current_steps": 230, "total_steps": 818, "loss": 0.0381, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.0864470407769114e-05, "epoch": 0.28, "percentage": 28.12, "elapsed_time": "0:27:31", "remaining_time": "1:10:21"}
+{"current_steps": 235, "total_steps": 818, "loss": 0.062, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.049054054571648e-05, "epoch": 0.29, "percentage": 28.73, "elapsed_time": "0:27:52", "remaining_time": "1:09:08"}
+{"current_steps": 240, "total_steps": 818, "loss": 0.0134, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.011089870766437e-05, "epoch": 0.29, "percentage": 29.34, "elapsed_time": "0:28:11", "remaining_time": "1:07:53"}
+{"current_steps": 245, "total_steps": 818, "loss": 0.0167, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.972568488259905e-05, "epoch": 0.3, "percentage": 29.95, "elapsed_time": "0:28:31", "remaining_time": "1:06:41"}
+{"current_steps": 250, "total_steps": 818, "loss": 0.0143, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.93350411141191e-05, "epoch": 0.31, "percentage": 30.56, "elapsed_time": "0:28:51", "remaining_time": "1:05:32"}
+{"current_steps": 255, "total_steps": 818, "loss": 0.0276, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.8939111448058404e-05, "epoch": 0.31, "percentage": 31.17, "elapsed_time": "0:29:09", "remaining_time": "1:04:23"}
+{"current_steps": 260, "total_steps": 818, "loss": 0.0636, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.853804187937066e-05, "epoch": 0.32, "percentage": 31.78, "elapsed_time": "0:29:30", "remaining_time": "1:03:20"}
+{"current_steps": 265, "total_steps": 818, "loss": 0.0279, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.813198029829532e-05, "epoch": 0.32, "percentage": 32.4, "elapsed_time": "0:29:49", "remaining_time": "1:02:13"}
+{"current_steps": 270, "total_steps": 818, "loss": 0.0518, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.772107643582458e-05, "epoch": 0.33, "percentage": 33.01, "elapsed_time": "0:30:10", "remaining_time": "1:01:13"}
+{"current_steps": 275, "total_steps": 818, "loss": 0.0189, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.730548180849161e-05, "epoch": 0.34, "percentage": 33.62, "elapsed_time": "0:30:31", "remaining_time": "1:00:15"}
+{"current_steps": 280, "total_steps": 818, "loss": 0.0099, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.688534966250042e-05, "epoch": 0.34, "percentage": 34.23, "elapsed_time": "0:30:51", "remaining_time": "0:59:17"}
+{"current_steps": 285, "total_steps": 818, "loss": 0.0045, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.646083491721794e-05, "epoch": 0.35, "percentage": 34.84, "elapsed_time": "0:31:10", "remaining_time": "0:58:17"}
+{"current_steps": 290, "total_steps": 818, "loss": 0.003, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.603209410804906e-05, "epoch": 0.35, "percentage": 35.45, "elapsed_time": "0:31:29", "remaining_time": "0:57:19"}
+{"current_steps": 295, "total_steps": 818, "loss": 0.0229, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.559928532871587e-05, "epoch": 0.36, "percentage": 36.06, "elapsed_time": "0:31:48", "remaining_time": "0:56:24"}
+{"current_steps": 300, "total_steps": 818, "loss": 0.0148, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.516256817296222e-05, "epoch": 0.37, "percentage": 36.67, "elapsed_time": "0:32:08", "remaining_time": "0:55:29"}
+{"current_steps": 305, "total_steps": 818, "loss": 0.0131, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.472210367570518e-05, "epoch": 0.37, "percentage": 37.29, "elapsed_time": "0:32:28", "remaining_time": "0:54:37"}
+{"current_steps": 310, "total_steps": 818, "loss": 0.0104, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.427805425365509e-05, "epoch": 0.38, "percentage": 37.9, "elapsed_time": "0:32:49", "remaining_time": "0:53:46"}
+{"current_steps": 315, "total_steps": 818, "loss": 0.027, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.383058364542611e-05, "epoch": 0.38, "percentage": 38.51, "elapsed_time": "0:33:08", "remaining_time": "0:52:54"}
+{"current_steps": 320, "total_steps": 818, "loss": 0.0023, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.3379856851159267e-05, "epoch": 0.39, "percentage": 39.12, "elapsed_time": "0:33:28", "remaining_time": "0:52:05"}
+{"current_steps": 325, "total_steps": 818, "loss": 0.0019, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.292604007168037e-05, "epoch": 0.4, "percentage": 39.73, "elapsed_time": "0:33:47", "remaining_time": "0:51:14"}
+{"current_steps": 330, "total_steps": 818, "loss": 0.0023, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.246930064721524e-05, "epoch": 0.4, "percentage": 40.34, "elapsed_time": "0:34:07", "remaining_time": "0:50:28"}
+{"current_steps": 335, "total_steps": 818, "loss": 0.0248, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.200980699568463e-05, "epoch": 0.41, "percentage": 40.95, "elapsed_time": "0:34:27", "remaining_time": "0:49:40"}
+{"current_steps": 340, "total_steps": 818, "loss": 0.0134, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.154772855060198e-05, "epoch": 0.42, "percentage": 41.56, "elapsed_time": "0:34:46", "remaining_time": "0:48:53"}
+{"current_steps": 345, "total_steps": 818, "loss": 0.0011, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.1083235698596505e-05, "epoch": 0.42, "percentage": 42.18, "elapsed_time": "0:35:04", "remaining_time": "0:48:05"}
+{"current_steps": 350, "total_steps": 818, "loss": 0.0202, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.061649971658488e-05, "epoch": 0.43, "percentage": 42.79, "elapsed_time": "0:35:24", "remaining_time": "0:47:20"}
+{"current_steps": 355, "total_steps": 818, "loss": 0.001, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.01476927086147e-05, "epoch": 0.43, "percentage": 43.4, "elapsed_time": "0:35:43", "remaining_time": "0:46:35"}
+{"current_steps": 360, "total_steps": 818, "loss": 0.056, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.967698754240289e-05, "epoch": 0.44, "percentage": 44.01, "elapsed_time": "0:36:03", "remaining_time": "0:45:52"}
+{"current_steps": 365, "total_steps": 818, "loss": 0.0097, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.92045577855925e-05, "epoch": 0.45, "percentage": 44.62, "elapsed_time": "0:36:23", "remaining_time": "0:45:09"}
+{"current_steps": 370, "total_steps": 818, "loss": 0.062, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.8730577641751476e-05, "epoch": 0.45, "percentage": 45.23, "elapsed_time": "0:36:42", "remaining_time": "0:44:26"}
+{"current_steps": 375, "total_steps": 818, "loss": 0.0022, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.825522188613686e-05, "epoch": 0.46, "percentage": 45.84, "elapsed_time": "0:37:01", "remaining_time": "0:43:44"}
+{"current_steps": 380, "total_steps": 818, "loss": 0.0012, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.7778665801248292e-05, "epoch": 0.46, "percentage": 46.45, "elapsed_time": "0:37:20", "remaining_time": "0:43:02"}
+{"current_steps": 385, "total_steps": 818, "loss": 0.0058, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.730108511219433e-05, "epoch": 0.47, "percentage": 47.07, "elapsed_time": "0:37:41", "remaining_time": "0:42:23"}
+{"current_steps": 390, "total_steps": 818, "loss": 0.0053, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.6822655921895695e-05, "epoch": 0.48, "percentage": 47.68, "elapsed_time": "0:38:01", "remaining_time": "0:41:43"}
+{"current_steps": 395, "total_steps": 818, "loss": 0.0012, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.6343554646149154e-05, "epoch": 0.48, "percentage": 48.29, "elapsed_time": "0:38:21", "remaining_time": "0:41:04"}
+{"current_steps": 400, "total_steps": 818, "loss": 0.0206, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.586395794857597e-05, "epoch": 0.49, "percentage": 48.9, "elapsed_time": "0:38:40", "remaining_time": "0:40:24"}
+{"current_steps": 405, "total_steps": 818, "loss": 0.0009, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.538404267547908e-05, "epoch": 0.49, "percentage": 49.51, "elapsed_time": "0:39:00", "remaining_time": "0:39:46"}
+{"current_steps": 410, "total_steps": 818, "loss": 0.018, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.4903985790632835e-05, "epoch": 0.5, "percentage": 50.12, "elapsed_time": "0:39:19", "remaining_time": "0:39:07"}
+{"current_steps": 415, "total_steps": 818, "loss": 0.0238, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.4423964310029458e-05, "epoch": 0.51, "percentage": 50.73, "elapsed_time": "0:39:39", "remaining_time": "0:38:30"}
+{"current_steps": 420, "total_steps": 818, "loss": 0.0064, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3944155236606196e-05, "epoch": 0.51, "percentage": 51.34, "elapsed_time": "0:39:59", "remaining_time": "0:37:53"}
+{"current_steps": 425, "total_steps": 818, "loss": 0.0273, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3464735494977392e-05, "epoch": 0.52, "percentage": 51.96, "elapsed_time": "0:40:19", "remaining_time": "0:37:17"}
+{"current_steps": 430, "total_steps": 818, "loss": 0.0045, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2985881866195307e-05, "epoch": 0.53, "percentage": 52.57, "elapsed_time": "0:40:39", "remaining_time": "0:36:40"}
+{"current_steps": 435, "total_steps": 818, "loss": 0.0233, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2507770922563966e-05, "epoch": 0.53, "percentage": 53.18, "elapsed_time": "0:40:58", "remaining_time": "0:36:04"}
+{"current_steps": 440, "total_steps": 818, "loss": 0.0019, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2030578962529964e-05, "epoch": 0.54, "percentage": 53.79, "elapsed_time": "0:41:16", "remaining_time": "0:35:27"}
+{"current_steps": 445, "total_steps": 818, "loss": 0.0027, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.155448194567425e-05, "epoch": 0.54, "percentage": 54.4, "elapsed_time": "0:41:36", "remaining_time": "0:34:52"}
+{"current_steps": 450, "total_steps": 818, "loss": 0.0246, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.1079655427828807e-05, "epoch": 0.55, "percentage": 55.01, "elapsed_time": "0:41:55", "remaining_time": "0:34:16"}
+{"current_steps": 455, "total_steps": 818, "loss": 0.0128, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.060627449634234e-05, "epoch": 0.56, "percentage": 55.62, "elapsed_time": "0:42:14", "remaining_time": "0:33:41"}
+{"current_steps": 460, "total_steps": 818, "loss": 0.0205, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0134513705518547e-05, "epoch": 0.56, "percentage": 56.23, "elapsed_time": "0:42:32", "remaining_time": "0:33:06"}
+{"current_steps": 465, "total_steps": 818, "loss": 0.0135, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9664547012251122e-05, "epoch": 0.57, "percentage": 56.85, "elapsed_time": "0:42:52", "remaining_time": "0:32:32"}
+{"current_steps": 470, "total_steps": 818, "loss": 0.009, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9196547711878883e-05, "epoch": 0.57, "percentage": 57.46, "elapsed_time": "0:43:11", "remaining_time": "0:31:58"}
+{"current_steps": 475, "total_steps": 818, "loss": 0.0289, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.873068837428497e-05, "epoch": 0.58, "percentage": 58.07, "elapsed_time": "0:43:30", "remaining_time": "0:31:25"}
+{"current_steps": 480, "total_steps": 818, "loss": 0.0587, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8267140780263427e-05, "epoch": 0.59, "percentage": 58.68, "elapsed_time": "0:43:49", "remaining_time": "0:30:51"}
+{"current_steps": 485, "total_steps": 818, "loss": 0.0152, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7806075858176903e-05, "epoch": 0.59, "percentage": 59.29, "elapsed_time": "0:44:09", "remaining_time": "0:30:19"}
+{"current_steps": 490, "total_steps": 818, "loss": 0.0148, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7347663620928495e-05, "epoch": 0.6, "percentage": 59.9, "elapsed_time": "0:44:28", "remaining_time": "0:29:46"}
+{"current_steps": 495, "total_steps": 818, "loss": 0.0339, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6892073103271355e-05, "epoch": 0.6, "percentage": 60.51, "elapsed_time": "0:44:48", "remaining_time": "0:29:14"}
+{"current_steps": 500, "total_steps": 818, "loss": 0.0227, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6439472299478803e-05, "epoch": 0.61, "percentage": 61.12, "elapsed_time": "0:45:12", "remaining_time": "0:28:44"}
+{"current_steps": 505, "total_steps": 818, "loss": 0.0308, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5990028101398234e-05, "epoch": 0.62, "percentage": 61.74, "elapsed_time": "0:45:31", "remaining_time": "0:28:13"}
+{"current_steps": 510, "total_steps": 818, "loss": 0.0014, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5543906236911424e-05, "epoch": 0.62, "percentage": 62.35, "elapsed_time": "0:45:51", "remaining_time": "0:27:41"}
+{"current_steps": 515, "total_steps": 818, "loss": 0.0023, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5101271208824168e-05, "epoch": 0.63, "percentage": 62.96, "elapsed_time": "0:46:09", "remaining_time": "0:27:09"}
+{"current_steps": 520, "total_steps": 818, "loss": 0.0098, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4662286234207512e-05, "epoch": 0.64, "percentage": 63.57, "elapsed_time": "0:46:28", "remaining_time": "0:26:38"}
+{"current_steps": 525, "total_steps": 818, "loss": 0.0209, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4227113184213198e-05, "epoch": 0.64, "percentage": 64.18, "elapsed_time": "0:46:48", "remaining_time": "0:26:07"}
+{"current_steps": 530, "total_steps": 818, "loss": 0.0026, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3795912524385323e-05, "epoch": 0.65, "percentage": 64.79, "elapsed_time": "0:47:07", "remaining_time": "0:25:36"}
+{"current_steps": 535, "total_steps": 818, "loss": 0.0309, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3368843255490383e-05, "epoch": 0.65, "percentage": 65.4, "elapsed_time": "0:47:25", "remaining_time": "0:25:05"}
+{"current_steps": 540, "total_steps": 818, "loss": 0.0016, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2946062854887313e-05, "epoch": 0.66, "percentage": 66.01, "elapsed_time": "0:47:44", "remaining_time": "0:24:34"}
+{"current_steps": 545, "total_steps": 818, "loss": 0.0083, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.252772721845945e-05, "epoch": 0.67, "percentage": 66.63, "elapsed_time": "0:48:03", "remaining_time": "0:24:04"}
+{"current_steps": 550, "total_steps": 818, "loss": 0.0041, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2113990603129433e-05, "epoch": 0.67, "percentage": 67.24, "elapsed_time": "0:48:22", "remaining_time": "0:23:34"}
+{"current_steps": 555, "total_steps": 818, "loss": 0.0195, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1705005569978664e-05, "epoch": 0.68, "percentage": 67.85, "elapsed_time": "0:48:40", "remaining_time": "0:23:04"}
+{"current_steps": 560, "total_steps": 818, "loss": 0.0216, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1300922927991913e-05, "epoch": 0.68, "percentage": 68.46, "elapsed_time": "0:48:59", "remaining_time": "0:22:34"}
+{"current_steps": 565, "total_steps": 818, "loss": 0.0304, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0901891678448144e-05, "epoch": 0.69, "percentage": 69.07, "elapsed_time": "0:49:19", "remaining_time": "0:22:05"}
+{"current_steps": 570, "total_steps": 818, "loss": 0.0028, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0508058959977757e-05, "epoch": 0.7, "percentage": 69.68, "elapsed_time": "0:49:38", "remaining_time": "0:21:35"}
+{"current_steps": 575, "total_steps": 818, "loss": 0.0037, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0119569994306841e-05, "epoch": 0.7, "percentage": 70.29, "elapsed_time": "0:49:59", "remaining_time": "0:21:07"}
+{"current_steps": 580, "total_steps": 818, "loss": 0.0062, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.736568032708069e-06, "epoch": 0.71, "percentage": 70.9, "elapsed_time": "0:50:19", "remaining_time": "0:20:39"}
+{"current_steps": 585, "total_steps": 818, "loss": 0.0018, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.359194303178371e-06, "epoch": 0.71, "percentage": 71.52, "elapsed_time": "0:50:38", "remaining_time": "0:20:10"}
+{"current_steps": 590, "total_steps": 818, "loss": 0.0052, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.987587958362517e-06, "epoch": 0.72, "percentage": 72.13, "elapsed_time": "0:50:57", "remaining_time": "0:19:41"}
+{"current_steps": 595, "total_steps": 818, "loss": 0.0419, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.621886024242057e-06, "epoch": 0.73, "percentage": 72.74, "elapsed_time": "0:51:17", "remaining_time": "0:19:13"}
+{"current_steps": 600, "total_steps": 818, "loss": 0.0037, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.262223349608366e-06, "epoch": 0.73, "percentage": 73.35, "elapsed_time": "0:51:36", "remaining_time": "0:18:45"}
+{"current_steps": 605, "total_steps": 818, "loss": 0.0027, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.908732556338628e-06, "epoch": 0.74, "percentage": 73.96, "elapsed_time": "0:51:56", "remaining_time": "0:18:17"}
+{"current_steps": 610, "total_steps": 818, "loss": 0.0571, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.561543990492803e-06, "epoch": 0.75, "percentage": 74.57, "elapsed_time": "0:52:15", "remaining_time": "0:17:49"}
+{"current_steps": 615, "total_steps": 818, "loss": 0.0077, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.2207856742499695e-06, "epoch": 0.75, "percentage": 75.18, "elapsed_time": "0:52:34", "remaining_time": "0:17:21"}
+{"current_steps": 620, "total_steps": 818, "loss": 0.0448, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.886583258701382e-06, "epoch": 0.76, "percentage": 75.79, "elapsed_time": "0:52:56", "remaining_time": "0:16:54"}
+{"current_steps": 625, "total_steps": 818, "loss": 0.0117, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.559059977518017e-06, "epoch": 0.76, "percentage": 76.41, "elapsed_time": "0:53:21", "remaining_time": "0:16:28"}
+{"current_steps": 630, "total_steps": 818, "loss": 0.0025, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.238336601509365e-06, "epoch": 0.77, "percentage": 77.02, "elapsed_time": "0:53:48", "remaining_time": "0:16:03"}
+{"current_steps": 635, "total_steps": 818, "loss": 0.0024, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.92453139409051e-06, "epoch": 0.78, "percentage": 77.63, "elapsed_time": "0:54:13", "remaining_time": "0:15:37"}
+{"current_steps": 640, "total_steps": 818, "loss": 0.0329, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.617760067673666e-06, "epoch": 0.78, "percentage": 78.24, "elapsed_time": "0:54:37", "remaining_time": "0:15:11"}
+{"current_steps": 645, "total_steps": 818, "loss": 0.0176, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.318135741000488e-06, "epoch": 0.79, "percentage": 78.85, "elapsed_time": "0:54:59", "remaining_time": "0:14:45"}
+{"current_steps": 650, "total_steps": 818, "loss": 0.0184, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.025768897430644e-06, "epoch": 0.79, "percentage": 79.46, "elapsed_time": "0:55:23", "remaining_time": "0:14:18"}
+{"current_steps": 655, "total_steps": 818, "loss": 0.0028, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.740767344202282e-06, "epoch": 0.8, "percentage": 80.07, "elapsed_time": "0:55:47", "remaining_time": "0:13:53"}
+{"current_steps": 660, "total_steps": 818, "loss": 0.0018, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.463236172679192e-06, "epoch": 0.81, "percentage": 80.68, "elapsed_time": "0:56:09", "remaining_time": "0:13:26"}
+{"current_steps": 665, "total_steps": 818, "loss": 0.0275, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.193277719599481e-06, "epoch": 0.81, "percentage": 81.3, "elapsed_time": "0:56:31", "remaining_time": "0:13:00"}
+{"current_steps": 670, "total_steps": 818, "loss": 0.007, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.9309915293399366e-06, "epoch": 0.82, "percentage": 81.91, "elapsed_time": "0:56:53", "remaining_time": "0:12:33"}
+{"current_steps": 675, "total_steps": 818, "loss": 0.0182, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.676474317210099e-06, "epoch": 0.82, "percentage": 82.52, "elapsed_time": "0:57:12", "remaining_time": "0:12:07"}
+{"current_steps": 680, "total_steps": 818, "loss": 0.0015, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.4298199337894685e-06, "epoch": 0.83, "percentage": 83.13, "elapsed_time": "0:57:31", "remaining_time": "0:11:40"}
+{"current_steps": 685, "total_steps": 818, "loss": 0.0018, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.1911193303211185e-06, "epoch": 0.84, "percentage": 83.74, "elapsed_time": "0:57:49", "remaining_time": "0:11:13"}
+{"current_steps": 690, "total_steps": 818, "loss": 0.0024, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.9604605251743136e-06, "epoch": 0.84, "percentage": 84.35, "elapsed_time": "0:58:08", "remaining_time": "0:10:47"}
+{"current_steps": 695, "total_steps": 818, "loss": 0.0023, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.7379285713886954e-06, "epoch": 0.85, "percentage": 84.96, "elapsed_time": "0:58:29", "remaining_time": "0:10:21"}
+{"current_steps": 700, "total_steps": 818, "loss": 0.0048, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5236055253118423e-06, "epoch": 0.85, "percentage": 85.57, "elapsed_time": "0:58:50", "remaining_time": "0:09:55"}
+{"current_steps": 705, "total_steps": 818, "loss": 0.0022, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3175704163418353e-06, "epoch": 0.86, "percentage": 86.19, "elapsed_time": "0:59:10", "remaining_time": "0:09:29"}
+{"current_steps": 710, "total_steps": 818, "loss": 0.0246, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.119899217785995e-06, "epoch": 0.87, "percentage": 86.8, "elapsed_time": "0:59:30", "remaining_time": "0:09:03"}
+{"current_steps": 715, "total_steps": 818, "loss": 0.0014, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9306648188465252e-06, "epoch": 0.87, "percentage": 87.41, "elapsed_time": "0:59:49", "remaining_time": "0:08:37"}
+{"current_steps": 720, "total_steps": 818, "loss": 0.0012, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7499369977433456e-06, "epoch": 0.88, "percentage": 88.02, "elapsed_time": "1:00:09", "remaining_time": "0:08:11"}
+{"current_steps": 725, "total_steps": 818, "loss": 0.0812, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.577782395984126e-06, "epoch": 0.89, "percentage": 88.63, "elapsed_time": "1:00:29", "remaining_time": "0:07:45"}
+{"current_steps": 730, "total_steps": 818, "loss": 0.0427, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4142644937909206e-06, "epoch": 0.89, "percentage": 89.24, "elapsed_time": "1:00:49", "remaining_time": "0:07:19"}
+{"current_steps": 735, "total_steps": 818, "loss": 0.0075, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2594435866924686e-06, "epoch": 0.9, "percentage": 89.85, "elapsed_time": "1:01:08", "remaining_time": "0:06:54"}
+{"current_steps": 740, "total_steps": 818, "loss": 0.0267, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.113376763290877e-06, "epoch": 0.9, "percentage": 90.46, "elapsed_time": "1:01:28", "remaining_time": "0:06:28"}
+{"current_steps": 745, "total_steps": 818, "loss": 0.0237, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.761178842107699e-07, "epoch": 0.91, "percentage": 91.08, "elapsed_time": "1:01:47", "remaining_time": "0:06:03"}
+{"current_steps": 750, "total_steps": 818, "loss": 0.0269, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.477175622387562e-07, "epoch": 0.92, "percentage": 91.69, "elapsed_time": "1:02:06", "remaining_time": "0:05:37"}
+{"current_steps": 755, "total_steps": 818, "loss": 0.0014, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.282231436604698e-07, "epoch": 0.92, "percentage": 92.3, "elapsed_time": "1:02:24", "remaining_time": "0:05:12"}
+{"current_steps": 760, "total_steps": 818, "loss": 0.0012, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.176786908021453e-07, "epoch": 0.93, "percentage": 92.91, "elapsed_time": "1:02:43", "remaining_time": "0:04:47"}
+{"current_steps": 765, "total_steps": 818, "loss": 0.0019, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.161249657830686e-07, "epoch": 0.93, "percentage": 93.52, "elapsed_time": "1:03:04", "remaining_time": "0:04:22"}
+{"current_steps": 770, "total_steps": 818, "loss": 0.0036, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.2359941548499037e-07, "epoch": 0.94, "percentage": 94.13, "elapsed_time": "1:03:24", "remaining_time": "0:03:57"}
+{"current_steps": 775, "total_steps": 818, "loss": 0.0073, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.4013615774395323e-07, "epoch": 0.95, "percentage": 94.74, "elapsed_time": "1:03:44", "remaining_time": "0:03:32"}
+{"current_steps": 780, "total_steps": 818, "loss": 0.0022, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.657659687697156e-07, "epoch": 0.95, "percentage": 95.35, "elapsed_time": "1:04:03", "remaining_time": "0:03:07"}
+{"current_steps": 785, "total_steps": 818, "loss": 0.0021, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0051627179733247e-07, "epoch": 0.96, "percentage": 95.97, "elapsed_time": "1:04:22", "remaining_time": "0:02:42"}
+{"current_steps": 790, "total_steps": 818, "loss": 0.0007, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.444111269751164e-07, "epoch": 0.96, "percentage": 96.58, "elapsed_time": "1:04:42", "remaining_time": "0:02:17"}
+{"current_steps": 795, "total_steps": 818, "loss": 0.0016, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.747122249273156e-08, "epoch": 0.97, "percentage": 97.19, "elapsed_time": "1:05:01", "remaining_time": "0:01:52"}
+{"current_steps": 800, "total_steps": 818, "loss": 0.0051, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.971386695260706e-08, "epoch": 0.98, "percentage": 97.8, "elapsed_time": "1:05:20", "remaining_time": "0:01:28"}
+{"current_steps": 805, "total_steps": 818, "loss": 0.0021, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.1152982987595056e-08, "epoch": 0.98, "percentage": 98.41, "elapsed_time": "1:05:41", "remaining_time": "0:01:03"}
+{"current_steps": 810, "total_steps": 818, "loss": 0.0054, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1799102127130202e-08, "epoch": 0.99, "percentage": 99.02, "elapsed_time": "1:06:02", "remaining_time": "0:00:39"}
+{"current_steps": 815, "total_steps": 818, "loss": 0.0027, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6593609138415567e-09, "epoch": 1.0, "percentage": 99.63, "elapsed_time": "1:06:20", "remaining_time": "0:00:14"}
+{"current_steps": 818, "total_steps": 818, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "1:06:32", "remaining_time": "0:00:00"}
+{"current_steps": 4912, "total_steps": 4912, "loss": null, "eval_loss": 0.012725877575576305, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "1:35:11", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1008 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9990839694656488,
+  "eval_steps": 1000,
+  "global_step": 818,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.999539075477821e-05,
+      "loss": 1.9867,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.998156471872415e-05,
+      "loss": 1.5198,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.995852699004508e-05,
+      "loss": 0.9883,
+      "step": 15
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.992628606366426e-05,
+      "loss": 0.3031,
+      "step": 20
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.988485382808856e-05,
+      "loss": 0.0533,
+      "step": 25
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.983424556102469e-05,
+      "loss": 0.0318,
+      "step": 30
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.97744799237457e-05,
+      "loss": 0.0605,
+      "step": 35
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.970557895420984e-05,
+      "loss": 0.0126,
+      "step": 40
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.9627568058934274e-05,
+      "loss": 0.0017,
+      "step": 45
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.95404760036267e-05,
+      "loss": 0.0005,
+      "step": 50
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.9444334902578315e-05,
+      "loss": 0.0784,
+      "step": 55
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.9339180206821955e-05,
+      "loss": 0.043,
+      "step": 60
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.922505069105995e-05,
+      "loss": 0.0022,
+      "step": 65
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.9101988439366295e-05,
+      "loss": 0.0101,
+      "step": 70
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.897003882966866e-05,
+      "loss": 0.0471,
+      "step": 75
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.8829250517015684e-05,
+      "loss": 0.002,
+      "step": 80
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.867967541563594e-05,
+      "loss": 0.0109,
+      "step": 85
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.8521368679795154e-05,
+      "loss": 0.0322,
+      "step": 90
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.835438868345858e-05,
+      "loss": 0.0156,
+      "step": 95
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.817879699876623e-05,
+      "loss": 0.0912,
+      "step": 100
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.7994658373328804e-05,
+      "loss": 0.027,
+      "step": 105
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.780204070635266e-05,
+      "loss": 0.027,
+      "step": 110
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.760101502360268e-05,
+      "loss": 0.0206,
+      "step": 115
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.739165545121228e-05,
+      "loss": 0.012,
+      "step": 120
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.717403918835017e-05,
+      "loss": 0.002,
+      "step": 125
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.694824647875391e-05,
+      "loss": 0.0052,
+      "step": 130
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.6714360581140935e-05,
+      "loss": 0.0036,
+      "step": 135
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.647246773850773e-05,
+      "loss": 0.0386,
+      "step": 140
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.6222657146328624e-05,
+      "loss": 0.0546,
+      "step": 145
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.596502091966588e-05,
+      "loss": 0.0472,
+      "step": 150
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.5699654059203225e-05,
+      "loss": 0.0779,
+      "step": 155
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.542665441621537e-05,
+      "loss": 0.0169,
+      "step": 160
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.51461226564863e-05,
+      "loss": 0.0249,
+      "step": 165
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.485816222318986e-05,
+      "loss": 0.0132,
+      "step": 170
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.4562879298746165e-05,
+      "loss": 0.0163,
+      "step": 175
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.4260382765667875e-05,
+      "loss": 0.0181,
+      "step": 180
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.395078416641099e-05,
+      "loss": 0.0421,
+      "step": 185
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.363419766224464e-05,
+      "loss": 0.0011,
+      "step": 190
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.3310739991155365e-05,
+      "loss": 0.0062,
+      "step": 195
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.2980530424801146e-05,
+      "loss": 0.0013,
+      "step": 200
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.264369072453126e-05,
+      "loss": 0.0515,
+      "step": 205
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.230034509648803e-05,
+      "loss": 0.009,
+      "step": 210
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.19506201458071e-05,
+      "loss": 0.0132,
+      "step": 215
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.159464482993308e-05,
+      "loss": 0.0092,
+      "step": 220
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.123255041106788e-05,
+      "loss": 0.0429,
+      "step": 225
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.0864470407769114e-05,
+      "loss": 0.0381,
+      "step": 230
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.049054054571648e-05,
+      "loss": 0.062,
+      "step": 235
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.011089870766437e-05,
+      "loss": 0.0134,
+      "step": 240
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 3.972568488259905e-05,
+      "loss": 0.0167,
+      "step": 245
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 3.93350411141191e-05,
+      "loss": 0.0143,
+      "step": 250
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 3.8939111448058404e-05,
+      "loss": 0.0276,
+      "step": 255
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 3.853804187937066e-05,
+      "loss": 0.0636,
+      "step": 260
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 3.813198029829532e-05,
+      "loss": 0.0279,
+      "step": 265
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 3.772107643582458e-05,
+      "loss": 0.0518,
+      "step": 270
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 3.730548180849161e-05,
+      "loss": 0.0189,
+      "step": 275
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 3.688534966250042e-05,
+      "loss": 0.0099,
+      "step": 280
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 3.646083491721794e-05,
+      "loss": 0.0045,
+      "step": 285
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 3.603209410804906e-05,
+      "loss": 0.003,
+      "step": 290
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 3.559928532871587e-05,
+      "loss": 0.0229,
+      "step": 295
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 3.516256817296222e-05,
+      "loss": 0.0148,
+      "step": 300
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 3.472210367570518e-05,
+      "loss": 0.0131,
+      "step": 305
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.427805425365509e-05,
+      "loss": 0.0104,
+      "step": 310
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.383058364542611e-05,
+      "loss": 0.027,
+      "step": 315
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 3.3379856851159267e-05,
+      "loss": 0.0023,
+      "step": 320
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 3.292604007168037e-05,
+      "loss": 0.0019,
+      "step": 325
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 3.246930064721524e-05,
+      "loss": 0.0023,
+      "step": 330
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 3.200980699568463e-05,
+      "loss": 0.0248,
+      "step": 335
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 3.154772855060198e-05,
+      "loss": 0.0134,
+      "step": 340
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 3.1083235698596505e-05,
+      "loss": 0.0011,
+      "step": 345
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 3.061649971658488e-05,
+      "loss": 0.0202,
+      "step": 350
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 3.01476927086147e-05,
+      "loss": 0.001,
+      "step": 355
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 2.967698754240289e-05,
+      "loss": 0.056,
+      "step": 360
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 2.92045577855925e-05,
+      "loss": 0.0097,
+      "step": 365
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 2.8730577641751476e-05,
+      "loss": 0.062,
+      "step": 370
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 2.825522188613686e-05,
+      "loss": 0.0022,
+      "step": 375
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 2.7778665801248292e-05,
+      "loss": 0.0012,
+      "step": 380
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.730108511219433e-05,
+      "loss": 0.0058,
+      "step": 385
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.6822655921895695e-05,
+      "loss": 0.0053,
+      "step": 390
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.6343554646149154e-05,
+      "loss": 0.0012,
+      "step": 395
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2.586395794857597e-05,
+      "loss": 0.0206,
+      "step": 400
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2.538404267547908e-05,
+      "loss": 0.0009,
+      "step": 405
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.4903985790632835e-05,
+      "loss": 0.018,
+      "step": 410
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 2.4423964310029458e-05,
+      "loss": 0.0238,
+      "step": 415
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 2.3944155236606196e-05,
+      "loss": 0.0064,
+      "step": 420
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 2.3464735494977392e-05,
+      "loss": 0.0273,
+      "step": 425
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.2985881866195307e-05,
+      "loss": 0.0045,
+      "step": 430
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.2507770922563966e-05,
+      "loss": 0.0233,
+      "step": 435
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.2030578962529964e-05,
+      "loss": 0.0019,
+      "step": 440
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.155448194567425e-05,
+      "loss": 0.0027,
+      "step": 445
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.1079655427828807e-05,
+      "loss": 0.0246,
+      "step": 450
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 2.060627449634234e-05,
+      "loss": 0.0128,
+      "step": 455
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 2.0134513705518547e-05,
+      "loss": 0.0205,
+      "step": 460
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.9664547012251122e-05,
+      "loss": 0.0135,
+      "step": 465
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.9196547711878883e-05,
+      "loss": 0.009,
+      "step": 470
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.873068837428497e-05,
+      "loss": 0.0289,
+      "step": 475
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.8267140780263427e-05,
+      "loss": 0.0587,
+      "step": 480
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.7806075858176903e-05,
+      "loss": 0.0152,
+      "step": 485
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.7347663620928495e-05,
+      "loss": 0.0148,
+      "step": 490
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.6892073103271355e-05,
+      "loss": 0.0339,
+      "step": 495
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.6439472299478803e-05,
+      "loss": 0.0227,
+      "step": 500
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.5990028101398234e-05,
+      "loss": 0.0308,
+      "step": 505
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.5543906236911424e-05,
+      "loss": 0.0014,
+      "step": 510
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.5101271208824168e-05,
+      "loss": 0.0023,
+      "step": 515
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.4662286234207512e-05,
+      "loss": 0.0098,
+      "step": 520
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.4227113184213198e-05,
+      "loss": 0.0209,
+      "step": 525
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.3795912524385323e-05,
+      "loss": 0.0026,
+      "step": 530
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.3368843255490383e-05,
+      "loss": 0.0309,
+      "step": 535
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.2946062854887313e-05,
+      "loss": 0.0016,
+      "step": 540
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.252772721845945e-05,
+      "loss": 0.0083,
+      "step": 545
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.2113990603129433e-05,
+      "loss": 0.0041,
+      "step": 550
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.1705005569978664e-05,
+      "loss": 0.0195,
+      "step": 555
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.1300922927991913e-05,
+      "loss": 0.0216,
+      "step": 560
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.0901891678448144e-05,
+      "loss": 0.0304,
+      "step": 565
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.0508058959977757e-05,
+      "loss": 0.0028,
+      "step": 570
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.0119569994306841e-05,
+      "loss": 0.0037,
+      "step": 575
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 9.736568032708069e-06,
+      "loss": 0.0062,
+      "step": 580
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 9.359194303178371e-06,
+      "loss": 0.0018,
+      "step": 585
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 8.987587958362517e-06,
+      "loss": 0.0052,
+      "step": 590
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 8.621886024242057e-06,
+      "loss": 0.0419,
+      "step": 595
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 8.262223349608366e-06,
+      "loss": 0.0037,
+      "step": 600
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 7.908732556338628e-06,
+      "loss": 0.0027,
+      "step": 605
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 7.561543990492803e-06,
+      "loss": 0.0571,
+      "step": 610
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 7.2207856742499695e-06,
+      "loss": 0.0077,
+      "step": 615
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 6.886583258701382e-06,
+      "loss": 0.0448,
+      "step": 620
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 6.559059977518017e-06,
+      "loss": 0.0117,
+      "step": 625
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 6.238336601509365e-06,
+      "loss": 0.0025,
+      "step": 630
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 5.92453139409051e-06,
+      "loss": 0.0024,
+      "step": 635
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 5.617760067673666e-06,
+      "loss": 0.0329,
+      "step": 640
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 5.318135741000488e-06,
+      "loss": 0.0176,
+      "step": 645
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 5.025768897430644e-06,
+      "loss": 0.0184,
+      "step": 650
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.740767344202282e-06,
+      "loss": 0.0028,
+      "step": 655
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.463236172679192e-06,
+      "loss": 0.0018,
+      "step": 660
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.193277719599481e-06,
+      "loss": 0.0275,
+      "step": 665
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.9309915293399366e-06,
+      "loss": 0.007,
+      "step": 670
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.676474317210099e-06,
+      "loss": 0.0182,
+      "step": 675
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.4298199337894685e-06,
+      "loss": 0.0015,
+      "step": 680
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.1911193303211185e-06,
+      "loss": 0.0018,
+      "step": 685
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 2.9604605251743136e-06,
+      "loss": 0.0024,
+      "step": 690
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 2.7379285713886954e-06,
+      "loss": 0.0023,
+      "step": 695
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 2.5236055253118423e-06,
+      "loss": 0.0048,
+      "step": 700
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.3175704163418353e-06,
+      "loss": 0.0022,
+      "step": 705
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.119899217785995e-06,
+      "loss": 0.0246,
+      "step": 710
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.9306648188465252e-06,
+      "loss": 0.0014,
+      "step": 715
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.7499369977433456e-06,
+      "loss": 0.0012,
+      "step": 720
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.577782395984126e-06,
+      "loss": 0.0812,
+      "step": 725
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.4142644937909206e-06,
+      "loss": 0.0427,
+      "step": 730
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.2594435866924686e-06,
+      "loss": 0.0075,
+      "step": 735
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.113376763290877e-06,
+      "loss": 0.0267,
+      "step": 740
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 9.761178842107699e-07,
+      "loss": 0.0237,
+      "step": 745
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 8.477175622387562e-07,
+      "loss": 0.0269,
+      "step": 750
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 7.282231436604698e-07,
+      "loss": 0.0014,
+      "step": 755
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 6.176786908021453e-07,
+      "loss": 0.0012,
+      "step": 760
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 5.161249657830686e-07,
+      "loss": 0.0019,
+      "step": 765
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.2359941548499037e-07,
+      "loss": 0.0036,
+      "step": 770
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 3.4013615774395323e-07,
+      "loss": 0.0073,
+      "step": 775
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.657659687697156e-07,
+      "loss": 0.0022,
+      "step": 780
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.0051627179733247e-07,
+      "loss": 0.0021,
+      "step": 785
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.444111269751164e-07,
+      "loss": 0.0007,
+      "step": 790
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 9.747122249273156e-08,
+      "loss": 0.0016,
+      "step": 795
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 5.971386695260706e-08,
+      "loss": 0.0051,
+      "step": 800
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 3.1152982987595056e-08,
+      "loss": 0.0021,
+      "step": 805
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.1799102127130202e-08,
+      "loss": 0.0054,
+      "step": 810
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.6593609138415567e-09,
+      "loss": 0.0027,
+      "step": 815
+    },
+    {
+      "epoch": 1.0,
+      "step": 818,
+      "total_flos": 1.474472015387689e+17,
+      "train_loss": 0.04709457870986094,
+      "train_runtime": 3992.6154,
+      "train_samples_per_second": 6.561,
+      "train_steps_per_second": 0.205
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 818,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1000,
+  "total_flos": 1.474472015387689e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84865721dbcc46921be500315b02abd9a9d24109c098df73457691b4d012b820
+size 4920