commit from root

Baichuan-13B-Chat-lora-Task/README.md

@@ -0,0 +1,9 @@
+---
+library_name: peft
+---
+## Training procedure
+
+### Framework versions
+
+
+- PEFT 0.5.0

Baichuan-13B-Chat-lora-Task/adapter_config.json

@@ -0,0 +1,20 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "baichuan-inc/Baichuan-13B-Chat",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32.0,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "revision": null,
+  "target_modules": [
+    "W_pack"
+  ],
+  "task_type": "CAUSAL_LM"
+}

Baichuan-13B-Chat-lora-Task/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84594037c53e9a300bbdebbc3534f704f22f429b6b912fe36e32aeec5a928e3a
+size 26243422

Baichuan-13B-Chat-lora-Task/all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 2.0,
+    "eval_loss": 0.41885045170783997,
+    "eval_runtime": 69.6555,
+    "eval_samples_per_second": 15.821,
+    "eval_steps_per_second": 1.594,
+    "train_loss": 0.46561298847898175,
+    "train_runtime": 35477.4141,
+    "train_samples_per_second": 6.149,
+    "train_steps_per_second": 0.077
+}

Baichuan-13B-Chat-lora-Task/eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.0,
+    "eval_loss": 0.41885045170783997,
+    "eval_runtime": 69.6555,
+    "eval_samples_per_second": 15.821,
+    "eval_steps_per_second": 1.594
+}

Baichuan-13B-Chat-lora-Task/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": true
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": true
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": true
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": true
+  }
+}

Baichuan-13B-Chat-lora-Task/tokenization_baichuan.py

@@ -0,0 +1,232 @@
+# Copyright (c) 2023, Baichuan Intelligent Technology. All rights reserved.
+
+import os
+from shutil import copyfile
+from typing import Any, Dict, List, Optional, Tuple
+
+import sentencepiece as spm
+from transformers.tokenization_utils import AddedToken, PreTrainedTokenizer
+from transformers.utils import logging
+
+
+logger = logging.get_logger(__name__)
+
+VOCAB_FILES_NAMES = {"vocab_file": "tokenizer.model"}
+
+PRETRAINED_VOCAB_FILES_MAP = {
+    "vocab_file": {},
+    "tokenizer_file": {},
+}
+PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {}
+
+
+class BaichuanTokenizer(PreTrainedTokenizer):
+    """
+    Construct a Baichuan tokenizer. Based on byte-level Byte-Pair-Encoding.
+
+    Args:
+        vocab_file (`str`):
+            Path to the vocabulary file.
+    """
+
+    vocab_files_names = VOCAB_FILES_NAMES
+    pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
+    max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES
+    model_input_names = ["input_ids", "attention_mask"]
+
+    def __init__(
+        self,
+        vocab_file,
+        unk_token="<unk>",
+        bos_token="<s>",
+        eos_token="</s>",
+        pad_token=None,
+        sp_model_kwargs: Optional[Dict[str, Any]] = None,
+        add_bos_token=True,
+        add_eos_token=False,
+        clean_up_tokenization_spaces=False,
+        **kwargs,
+    ):
+        self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
+        bos_token = AddedToken(bos_token, lstrip=False, rstrip=False) if isinstance(bos_token, str) else bos_token
+        eos_token = AddedToken(eos_token, lstrip=False, rstrip=False) if isinstance(eos_token, str) else eos_token
+        unk_token = AddedToken(unk_token, lstrip=False, rstrip=False) if isinstance(unk_token, str) else unk_token
+        pad_token = AddedToken(pad_token, lstrip=False, rstrip=False) if isinstance(pad_token, str) else pad_token
+        super().__init__(
+            bos_token=bos_token,
+            eos_token=eos_token,
+            unk_token=unk_token,
+            pad_token=pad_token,
+            add_bos_token=add_bos_token,
+            add_eos_token=add_eos_token,
+            sp_model_kwargs=self.sp_model_kwargs,
+            clean_up_tokenization_spaces=clean_up_tokenization_spaces,
+            **kwargs,
+        )
+        self.vocab_file = vocab_file
+        self.add_bos_token = add_bos_token
+        self.add_eos_token = add_eos_token
+        self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
+        self.sp_model.Load(vocab_file)
+
+    def __getstate__(self):
+        state = self.__dict__.copy()
+        state["sp_model"] = None
+        return state
+
+    def __setstate__(self, d):
+        self.__dict__ = d
+        self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
+        self.sp_model.Load(self.vocab_file)
+
+    @property
+    def vocab_size(self):
+        """Returns vocab size"""
+        return self.sp_model.get_piece_size()
+
+    def get_vocab(self):
+        """Returns vocab as a dict"""
+        vocab = {self.convert_ids_to_tokens(i): i for i in range(self.vocab_size)}
+        vocab.update(self.added_tokens_encoder)
+        return vocab
+
+    def _tokenize(self, text):
+        """Returns a tokenized string."""
+        return self.sp_model.encode(text, out_type=str)
+
+    def _convert_token_to_id(self, token):
+        """Converts a token (str) in an id using the vocab."""
+        return self.sp_model.piece_to_id(token)
+
+    def _convert_id_to_token(self, index):
+        """Converts an index (integer) in a token (str) using the vocab."""
+        token = self.sp_model.IdToPiece(index)
+        return token
+
+    def convert_tokens_to_string(self, tokens):
+        """Converts a sequence of tokens (string) in a single string."""
+        current_sub_tokens = []
+        out_string = ""
+        prev_is_special = False
+        for i, token in enumerate(tokens):
+            # make sure that special tokens are not decoded using sentencepiece model
+            if token in self.all_special_tokens:
+                if not prev_is_special and i != 0:
+                    out_string += " "
+                out_string += self.sp_model.decode(current_sub_tokens) + token
+                prev_is_special = True
+                current_sub_tokens = []
+            else:
+                current_sub_tokens.append(token)
+                prev_is_special = False
+        out_string += self.sp_model.decode(current_sub_tokens)
+        return out_string
+
+    def save_vocabulary(self, save_directory, filename_prefix: Optional[str] = None) -> Tuple[str]:
+        """
+        Save the vocabulary and special tokens file to a directory.
+
+        Args:
+            save_directory (`str`):
+                The directory in which to save the vocabulary.
+
+        Returns:
+            `Tuple(str)`: Paths to the files saved.
+        """
+        if not os.path.isdir(save_directory):
+            logger.error(f"Vocabulary path ({save_directory}) should be a directory")
+            return
+        out_vocab_file = os.path.join(
+            save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"]
+        )
+
+        if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file) and os.path.isfile(self.vocab_file):
+            copyfile(self.vocab_file, out_vocab_file)
+        elif not os.path.isfile(self.vocab_file):
+            with open(out_vocab_file, "wb") as fi:
+                content_spiece_model = self.sp_model.serialized_model_proto()
+                fi.write(content_spiece_model)
+
+        return (out_vocab_file,)
+
+    def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None):
+        bos_token_id = [self.bos_token_id] if self.add_bos_token else []
+        eos_token_id = [self.eos_token_id] if self.add_eos_token else []
+
+        output = bos_token_id + token_ids_0 + eos_token_id
+
+        if token_ids_1 is not None:
+            output = output + bos_token_id + token_ids_1 + eos_token_id
+
+        return output
+
+    def get_special_tokens_mask(
+        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False
+    ) -> List[int]:
+        """
+        Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
+        special tokens using the tokenizer `prepare_for_model` method.
+
+        Args:
+            token_ids_0 (`List[int]`):
+                List of IDs.
+            token_ids_1 (`List[int]`, *optional*):
+                Optional second list of IDs for sequence pairs.
+            already_has_special_tokens (`bool`, *optional*, defaults to `False`):
+                Whether or not the token list is already formatted with special tokens for the model.
+
+        Returns:
+            `List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
+        """
+        if already_has_special_tokens:
+            return super().get_special_tokens_mask(
+                token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True
+            )
+
+        bos_token_id = [1] if self.add_bos_token else []
+        eos_token_id = [1] if self.add_eos_token else []
+
+        if token_ids_1 is None:
+            return bos_token_id + ([0] * len(token_ids_0)) + eos_token_id
+        return (
+            bos_token_id
+            + ([0] * len(token_ids_0))
+            + eos_token_id
+            + bos_token_id
+            + ([0] * len(token_ids_1))
+            + eos_token_id
+        )
+
+    def create_token_type_ids_from_sequences(
+        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
+    ) -> List[int]:
+        """
+        Creates a mask from the two sequences passed to be used in a sequence-pair classification task. An ALBERT
+        sequence pair mask has the following format:
+
+        ```
+        0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1
+        | first sequence    | second sequence |
+        ```
+
+        if token_ids_1 is None, only returns the first portion of the mask (0s).
+
+        Args:
+            token_ids_0 (`List[int]`):
+                List of ids.
+            token_ids_1 (`List[int]`, *optional*):
+                Optional second list of IDs for sequence pairs.
+
+        Returns:
+            `List[int]`: List of [token type IDs](../glossary#token-type-ids) according to the given sequence(s).
+        """
+        bos_token_id = [self.bos_token_id] if self.add_bos_token else []
+        eos_token_id = [self.eos_token_id] if self.add_eos_token else []
+
+        output = [0] * len(bos_token_id + token_ids_0 + eos_token_id)
+
+        if token_ids_1 is not None:
+            output += [1] * len(bos_token_id + token_ids_1 + eos_token_id)
+
+        return output
+

Baichuan-13B-Chat-lora-Task/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7d1ab69d25c74644af5c5e4dcd1cc6e96d33783dbd257b6bdea55b643c72813
+size 1136765

Baichuan-13B-Chat-lora-Task/tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_baichuan.BaichuanTokenizer",
+      null
+    ]
+  },
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": true
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": true
+  },
+  "model_max_length": 4096,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": true
+  },
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "BaichuanTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": true
+  }
+}

Baichuan-13B-Chat-lora-Task/train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.0,
+    "train_loss": 0.46561298847898175,
+    "train_runtime": 35477.4141,
+    "train_samples_per_second": 6.149,
+    "train_steps_per_second": 0.077
+}

Baichuan-13B-Chat-lora-Task/trainer_log.jsonl

@@ -0,0 +1,287 @@
+{"current_steps": 10, "total_steps": 2726, "loss": 1.5452, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.999865525734509e-05, "epoch": 0.01, "percentage": 0.37, "elapsed_time": "0:02:32", "remaining_time": "11:29:51"}
+{"current_steps": 20, "total_steps": 2726, "loss": 1.3291, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9994621174046976e-05, "epoch": 0.01, "percentage": 0.73, "elapsed_time": "0:04:36", "remaining_time": "10:23:36"}
+{"current_steps": 30, "total_steps": 2726, "loss": 1.1048, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9986985231938546e-05, "epoch": 0.02, "percentage": 1.1, "elapsed_time": "0:06:36", "remaining_time": "9:54:30"}
+{"current_steps": 40, "total_steps": 2726, "loss": 0.9155, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.99760306731191e-05, "epoch": 0.03, "percentage": 1.47, "elapsed_time": "0:08:47", "remaining_time": "9:50:47"}
+{"current_steps": 50, "total_steps": 2726, "loss": 0.8856, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9961758952505326e-05, "epoch": 0.04, "percentage": 1.83, "elapsed_time": "0:10:46", "remaining_time": "9:36:34"}
+{"current_steps": 60, "total_steps": 2726, "loss": 0.8052, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9944171965578836e-05, "epoch": 0.04, "percentage": 2.2, "elapsed_time": "0:13:03", "remaining_time": "9:40:26"}
+{"current_steps": 70, "total_steps": 2726, "loss": 0.7332, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.992327204813435e-05, "epoch": 0.05, "percentage": 2.57, "elapsed_time": "0:15:01", "remaining_time": "9:30:01"}
+{"current_steps": 80, "total_steps": 2726, "loss": 0.6982, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.989906197596955e-05, "epoch": 0.06, "percentage": 2.93, "elapsed_time": "0:17:01", "remaining_time": "9:22:57"}
+{"current_steps": 90, "total_steps": 2726, "loss": 0.6811, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.987154496451635e-05, "epoch": 0.07, "percentage": 3.3, "elapsed_time": "0:18:51", "remaining_time": "9:12:22"}
+{"current_steps": 100, "total_steps": 2726, "loss": 0.6323, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.984072466841389e-05, "epoch": 0.07, "percentage": 3.67, "elapsed_time": "0:21:04", "remaining_time": "9:13:18"}
+{"current_steps": 110, "total_steps": 2726, "loss": 0.6234, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.981016546765289e-05, "epoch": 0.08, "percentage": 4.04, "elapsed_time": "0:23:02", "remaining_time": "9:07:57"}
+{"current_steps": 120, "total_steps": 2726, "loss": 0.6125, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.977308057009269e-05, "epoch": 0.09, "percentage": 4.4, "elapsed_time": "0:25:11", "remaining_time": "9:07:04"}
+{"current_steps": 130, "total_steps": 2726, "loss": 0.5977, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.97327054653146e-05, "epoch": 0.1, "percentage": 4.77, "elapsed_time": "0:27:29", "remaining_time": "9:08:54"}
+{"current_steps": 140, "total_steps": 2726, "loss": 0.6179, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.968904551569013e-05, "epoch": 0.1, "percentage": 5.14, "elapsed_time": "0:29:47", "remaining_time": "9:10:22"}
+{"current_steps": 150, "total_steps": 2726, "loss": 0.5879, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9642106519863544e-05, "epoch": 0.11, "percentage": 5.5, "elapsed_time": "0:31:46", "remaining_time": "9:05:40"}
+{"current_steps": 160, "total_steps": 2726, "loss": 0.5472, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.959189471198171e-05, "epoch": 0.12, "percentage": 5.87, "elapsed_time": "0:33:38", "remaining_time": "8:59:28"}
+{"current_steps": 170, "total_steps": 2726, "loss": 0.602, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.953841676086613e-05, "epoch": 0.12, "percentage": 6.24, "elapsed_time": "0:35:33", "remaining_time": "8:54:43"}
+{"current_steps": 180, "total_steps": 2726, "loss": 0.5773, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9481679769127275e-05, "epoch": 0.13, "percentage": 6.6, "elapsed_time": "0:37:48", "remaining_time": "8:54:48"}
+{"current_steps": 190, "total_steps": 2726, "loss": 0.5615, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9421691272221167e-05, "epoch": 0.14, "percentage": 6.97, "elapsed_time": "0:39:45", "remaining_time": "8:50:36"}
+{"current_steps": 200, "total_steps": 2726, "loss": 0.5704, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.935845923744865e-05, "epoch": 0.15, "percentage": 7.34, "elapsed_time": "0:41:50", "remaining_time": "8:48:29"}
+{"current_steps": 200, "total_steps": 2726, "loss": null, "eval_loss": 0.5564362406730652, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.15, "percentage": 7.34, "elapsed_time": "0:41:50", "remaining_time": "8:48:29"}
+{"current_steps": 210, "total_steps": 2726, "loss": 0.5803, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9291992062897183e-05, "epoch": 0.15, "percentage": 7.7, "elapsed_time": "0:44:59", "remaining_time": "8:59:06"}
+{"current_steps": 220, "total_steps": 2726, "loss": 0.5655, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.922229857632545e-05, "epoch": 0.16, "percentage": 8.07, "elapsed_time": "0:46:42", "remaining_time": "8:52:03"}
+{"current_steps": 230, "total_steps": 2726, "loss": 0.5769, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9149388033990966e-05, "epoch": 0.17, "percentage": 8.44, "elapsed_time": "0:49:02", "remaining_time": "8:52:13"}
+{"current_steps": 240, "total_steps": 2726, "loss": 0.5862, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9073270119420635e-05, "epoch": 0.18, "percentage": 8.8, "elapsed_time": "0:51:04", "remaining_time": "8:49:08"}
+{"current_steps": 250, "total_steps": 2726, "loss": 0.5506, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.899395494212471e-05, "epoch": 0.18, "percentage": 9.17, "elapsed_time": "0:53:13", "remaining_time": "8:47:07"}
+{"current_steps": 260, "total_steps": 2726, "loss": 0.5183, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.891145303625408e-05, "epoch": 0.19, "percentage": 9.54, "elapsed_time": "0:55:40", "remaining_time": "8:48:05"}
+{"current_steps": 270, "total_steps": 2726, "loss": 0.575, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.882577535920121e-05, "epoch": 0.2, "percentage": 9.9, "elapsed_time": "0:58:06", "remaining_time": "8:48:33"}
+{"current_steps": 280, "total_steps": 2726, "loss": 0.5359, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.8736933290144815e-05, "epoch": 0.21, "percentage": 10.27, "elapsed_time": "1:00:24", "remaining_time": "8:47:41"}
+{"current_steps": 290, "total_steps": 2726, "loss": 0.5302, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.8644938628538606e-05, "epoch": 0.21, "percentage": 10.64, "elapsed_time": "1:02:22", "remaining_time": "8:43:57"}
+{"current_steps": 300, "total_steps": 2726, "loss": 0.5399, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.8549803592544076e-05, "epoch": 0.22, "percentage": 11.01, "elapsed_time": "1:04:13", "remaining_time": "8:39:25"}
+{"current_steps": 310, "total_steps": 2726, "loss": 0.5379, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.845154081740783e-05, "epoch": 0.23, "percentage": 11.37, "elapsed_time": "1:06:13", "remaining_time": "8:36:11"}
+{"current_steps": 320, "total_steps": 2726, "loss": 0.5299, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.835016335378343e-05, "epoch": 0.23, "percentage": 11.74, "elapsed_time": "1:08:08", "remaining_time": "8:32:17"}
+{"current_steps": 330, "total_steps": 2726, "loss": 0.535, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.8245684665998073e-05, "epoch": 0.24, "percentage": 12.11, "elapsed_time": "1:10:23", "remaining_time": "8:31:06"}
+{"current_steps": 340, "total_steps": 2726, "loss": 0.5145, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.813811863026436e-05, "epoch": 0.25, "percentage": 12.47, "elapsed_time": "1:12:33", "remaining_time": "8:29:13"}
+{"current_steps": 350, "total_steps": 2726, "loss": 0.5126, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.802747953283732e-05, "epoch": 0.26, "percentage": 12.84, "elapsed_time": "1:14:40", "remaining_time": "8:26:55"}
+{"current_steps": 360, "total_steps": 2726, "loss": 0.5012, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.791378206811704e-05, "epoch": 0.26, "percentage": 13.21, "elapsed_time": "1:16:47", "remaining_time": "8:24:39"}
+{"current_steps": 370, "total_steps": 2726, "loss": 0.5373, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.7797041336696995e-05, "epoch": 0.27, "percentage": 13.57, "elapsed_time": "1:19:07", "remaining_time": "8:23:47"}
+{"current_steps": 380, "total_steps": 2726, "loss": 0.4778, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.767727284335852e-05, "epoch": 0.28, "percentage": 13.94, "elapsed_time": "1:21:18", "remaining_time": "8:21:59"}
+{"current_steps": 390, "total_steps": 2726, "loss": 0.4894, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.755449249501155e-05, "epoch": 0.29, "percentage": 14.31, "elapsed_time": "1:23:03", "remaining_time": "8:17:32"}
+{"current_steps": 400, "total_steps": 2726, "loss": 0.4986, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.7428716598581934e-05, "epoch": 0.29, "percentage": 14.67, "elapsed_time": "1:25:10", "remaining_time": "8:15:20"}
+{"current_steps": 400, "total_steps": 2726, "loss": null, "eval_loss": 0.4967592656612396, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.29, "percentage": 14.67, "elapsed_time": "1:25:10", "remaining_time": "8:15:20"}
+{"current_steps": 410, "total_steps": 2726, "loss": 0.4928, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.729996185884571e-05, "epoch": 0.3, "percentage": 15.04, "elapsed_time": "1:28:14", "remaining_time": "8:18:25"}
+{"current_steps": 420, "total_steps": 2726, "loss": 0.4807, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.716824537621042e-05, "epoch": 0.31, "percentage": 15.41, "elapsed_time": "1:30:05", "remaining_time": "8:14:40"}
+{"current_steps": 430, "total_steps": 2726, "loss": 0.4734, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.703358464444397e-05, "epoch": 0.32, "percentage": 15.77, "elapsed_time": "1:32:27", "remaining_time": "8:13:42"}
+{"current_steps": 440, "total_steps": 2726, "loss": 0.4603, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.689599754835122e-05, "epoch": 0.32, "percentage": 16.14, "elapsed_time": "1:34:29", "remaining_time": "8:10:56"}
+{"current_steps": 450, "total_steps": 2726, "loss": 0.4661, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.6755502361398616e-05, "epoch": 0.33, "percentage": 16.51, "elapsed_time": "1:36:31", "remaining_time": "8:08:14"}
+{"current_steps": 460, "total_steps": 2726, "loss": 0.5072, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.6612117743287234e-05, "epoch": 0.34, "percentage": 16.87, "elapsed_time": "1:38:36", "remaining_time": "8:05:42"}
+{"current_steps": 470, "total_steps": 2726, "loss": 0.5056, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.646586273747452e-05, "epoch": 0.34, "percentage": 17.24, "elapsed_time": "1:40:39", "remaining_time": "8:03:07"}
+{"current_steps": 480, "total_steps": 2726, "loss": 0.4391, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.631675676864503e-05, "epoch": 0.35, "percentage": 17.61, "elapsed_time": "1:43:01", "remaining_time": "8:02:03"}
+{"current_steps": 490, "total_steps": 2726, "loss": 0.483, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.6164819640130595e-05, "epoch": 0.36, "percentage": 17.98, "elapsed_time": "1:45:28", "remaining_time": "8:01:17"}
+{"current_steps": 500, "total_steps": 2726, "loss": 0.4774, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.601007153128014e-05, "epoch": 0.37, "percentage": 18.34, "elapsed_time": "1:47:35", "remaining_time": "7:59:00"}
+{"current_steps": 510, "total_steps": 2726, "loss": 0.4848, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.5852532994779606e-05, "epoch": 0.37, "percentage": 18.71, "elapsed_time": "1:49:45", "remaining_time": "7:56:55"}
+{"current_steps": 520, "total_steps": 2726, "loss": 0.5099, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.5692224953922266e-05, "epoch": 0.38, "percentage": 19.08, "elapsed_time": "1:51:38", "remaining_time": "7:53:35"}
+{"current_steps": 530, "total_steps": 2726, "loss": 0.4851, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.5529168699829805e-05, "epoch": 0.39, "percentage": 19.44, "elapsed_time": "1:53:42", "remaining_time": "7:51:09"}
+{"current_steps": 540, "total_steps": 2726, "loss": 0.498, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.536338588862459e-05, "epoch": 0.4, "percentage": 19.81, "elapsed_time": "1:55:51", "remaining_time": "7:48:59"}
+{"current_steps": 550, "total_steps": 2726, "loss": 0.5398, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.519489853855341e-05, "epoch": 0.4, "percentage": 20.18, "elapsed_time": "1:58:05", "remaining_time": "7:47:11"}
+{"current_steps": 560, "total_steps": 2726, "loss": 0.4566, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.50237290270632e-05, "epoch": 0.41, "percentage": 20.54, "elapsed_time": "1:59:55", "remaining_time": "7:43:50"}
+{"current_steps": 570, "total_steps": 2726, "loss": 0.4942, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.484990008782893e-05, "epoch": 0.42, "percentage": 20.91, "elapsed_time": "2:01:51", "remaining_time": "7:40:56"}
+{"current_steps": 580, "total_steps": 2726, "loss": 0.4625, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.467343480773433e-05, "epoch": 0.43, "percentage": 21.28, "elapsed_time": "2:04:02", "remaining_time": "7:38:55"}
+{"current_steps": 590, "total_steps": 2726, "loss": 0.4703, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.44943566238056e-05, "epoch": 0.43, "percentage": 21.64, "elapsed_time": "2:06:02", "remaining_time": "7:36:17"}
+{"current_steps": 600, "total_steps": 2726, "loss": 0.464, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.431268932009865e-05, "epoch": 0.44, "percentage": 22.01, "elapsed_time": "2:08:29", "remaining_time": "7:35:16"}
+{"current_steps": 600, "total_steps": 2726, "loss": null, "eval_loss": 0.46821752190589905, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.44, "percentage": 22.01, "elapsed_time": "2:08:29", "remaining_time": "7:35:16"}
+{"current_steps": 610, "total_steps": 2726, "loss": 0.4739, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.412845702454024e-05, "epoch": 0.45, "percentage": 22.38, "elapsed_time": "2:11:46", "remaining_time": "7:37:07"}
+{"current_steps": 620, "total_steps": 2726, "loss": 0.4529, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.394168420572349e-05, "epoch": 0.45, "percentage": 22.74, "elapsed_time": "2:14:01", "remaining_time": "7:35:15"}
+{"current_steps": 630, "total_steps": 2726, "loss": 0.4433, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.3752395669658086e-05, "epoch": 0.46, "percentage": 23.11, "elapsed_time": "2:16:41", "remaining_time": "7:34:47"}
+{"current_steps": 640, "total_steps": 2726, "loss": 0.459, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.356061655647571e-05, "epoch": 0.47, "percentage": 23.48, "elapsed_time": "2:18:53", "remaining_time": "7:32:41"}
+{"current_steps": 650, "total_steps": 2726, "loss": 0.4877, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.336637233709107e-05, "epoch": 0.48, "percentage": 23.84, "elapsed_time": "2:20:42", "remaining_time": "7:29:22"}
+{"current_steps": 660, "total_steps": 2726, "loss": 0.4676, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.316968880981903e-05, "epoch": 0.48, "percentage": 24.21, "elapsed_time": "2:22:37", "remaining_time": "7:26:26"}
+{"current_steps": 670, "total_steps": 2726, "loss": 0.4782, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.2970592096948236e-05, "epoch": 0.49, "percentage": 24.58, "elapsed_time": "2:24:37", "remaining_time": "7:23:48"}
+{"current_steps": 680, "total_steps": 2726, "loss": 0.4778, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.276910864127168e-05, "epoch": 0.5, "percentage": 24.94, "elapsed_time": "2:26:47", "remaining_time": "7:21:39"}
+{"current_steps": 690, "total_steps": 2726, "loss": 0.454, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.25652652025748e-05, "epoch": 0.51, "percentage": 25.31, "elapsed_time": "2:28:42", "remaining_time": "7:18:47"}
+{"current_steps": 700, "total_steps": 2726, "loss": 0.4399, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.235908885408133e-05, "epoch": 0.51, "percentage": 25.68, "elapsed_time": "2:30:54", "remaining_time": "7:16:47"}
+{"current_steps": 710, "total_steps": 2726, "loss": 0.5106, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.215060697885767e-05, "epoch": 0.52, "percentage": 26.05, "elapsed_time": "2:32:57", "remaining_time": "7:14:19"}
+{"current_steps": 720, "total_steps": 2726, "loss": 0.4683, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.1939847266176e-05, "epoch": 0.53, "percentage": 26.41, "elapsed_time": "2:35:12", "remaining_time": "7:12:26"}
+{"current_steps": 730, "total_steps": 2726, "loss": 0.4896, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.172683770783677e-05, "epoch": 0.54, "percentage": 26.78, "elapsed_time": "2:37:07", "remaining_time": "7:09:37"}
+{"current_steps": 740, "total_steps": 2726, "loss": 0.4633, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.1511606594451016e-05, "epoch": 0.54, "percentage": 27.15, "elapsed_time": "2:39:14", "remaining_time": "7:07:20"}
+{"current_steps": 750, "total_steps": 2726, "loss": 0.4486, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.1294182511682946e-05, "epoch": 0.55, "percentage": 27.51, "elapsed_time": "2:41:16", "remaining_time": "7:04:53"}
+{"current_steps": 760, "total_steps": 2726, "loss": 0.4706, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.1074594336453384e-05, "epoch": 0.56, "percentage": 27.88, "elapsed_time": "2:43:11", "remaining_time": "7:02:09"}
+{"current_steps": 770, "total_steps": 2726, "loss": 0.4797, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.085287123310455e-05, "epoch": 0.56, "percentage": 28.25, "elapsed_time": "2:44:59", "remaining_time": "6:59:07"}
+{"current_steps": 780, "total_steps": 2726, "loss": 0.4251, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.062904264952657e-05, "epoch": 0.57, "percentage": 28.61, "elapsed_time": "2:47:04", "remaining_time": "6:56:49"}
+{"current_steps": 790, "total_steps": 2726, "loss": 0.4687, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.0403138313246435e-05, "epoch": 0.58, "percentage": 28.98, "elapsed_time": "2:49:15", "remaining_time": "6:54:47"}
+{"current_steps": 800, "total_steps": 2726, "loss": 0.48, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.017518822747976e-05, "epoch": 0.59, "percentage": 29.35, "elapsed_time": "2:51:34", "remaining_time": "6:53:03"}
+{"current_steps": 800, "total_steps": 2726, "loss": null, "eval_loss": 0.4554018974304199, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.59, "percentage": 29.35, "elapsed_time": "2:51:34", "remaining_time": "6:53:03"}
+{"current_steps": 810, "total_steps": 2726, "loss": 0.4662, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.994522266714594e-05, "epoch": 0.59, "percentage": 29.71, "elapsed_time": "2:54:51", "remaining_time": "6:53:36"}
+{"current_steps": 820, "total_steps": 2726, "loss": 0.4837, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.9713272174847246e-05, "epoch": 0.6, "percentage": 30.08, "elapsed_time": "2:57:25", "remaining_time": "6:52:24"}
+{"current_steps": 830, "total_steps": 2726, "loss": 0.5014, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.947936755681229e-05, "epoch": 0.61, "percentage": 30.45, "elapsed_time": "2:59:33", "remaining_time": "6:50:10"}
+{"current_steps": 840, "total_steps": 2726, "loss": 0.4764, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.92435398788046e-05, "epoch": 0.62, "percentage": 30.81, "elapsed_time": "3:01:44", "remaining_time": "6:48:02"}
+{"current_steps": 850, "total_steps": 2726, "loss": 0.4587, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.9005820461996604e-05, "epoch": 0.62, "percentage": 31.18, "elapsed_time": "3:03:52", "remaining_time": "6:45:49"}
+{"current_steps": 860, "total_steps": 2726, "loss": 0.484, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.876624087880979e-05, "epoch": 0.63, "percentage": 31.55, "elapsed_time": "3:06:00", "remaining_time": "6:43:35"}
+{"current_steps": 870, "total_steps": 2726, "loss": 0.4285, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.85248329487214e-05, "epoch": 0.64, "percentage": 31.91, "elapsed_time": "3:08:03", "remaining_time": "6:41:10"}
+{"current_steps": 880, "total_steps": 2726, "loss": 0.4742, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.828162873403843e-05, "epoch": 0.65, "percentage": 32.28, "elapsed_time": "3:10:09", "remaining_time": "6:38:53"}
+{"current_steps": 890, "total_steps": 2726, "loss": 0.4533, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.803666053563926e-05, "epoch": 0.65, "percentage": 32.65, "elapsed_time": "3:12:20", "remaining_time": "6:36:48"}
+{"current_steps": 900, "total_steps": 2726, "loss": 0.4395, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.778996088868365e-05, "epoch": 0.66, "percentage": 33.02, "elapsed_time": "3:14:34", "remaining_time": "6:34:47"}
+{"current_steps": 910, "total_steps": 2726, "loss": 0.4519, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.754156255829167e-05, "epoch": 0.67, "percentage": 33.38, "elapsed_time": "3:16:42", "remaining_time": "6:32:33"}
+{"current_steps": 920, "total_steps": 2726, "loss": 0.4684, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.7291498535191996e-05, "epoch": 0.67, "percentage": 33.75, "elapsed_time": "3:18:41", "remaining_time": "6:30:02"}
+{"current_steps": 930, "total_steps": 2726, "loss": 0.4259, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.703980203134029e-05, "epoch": 0.68, "percentage": 34.12, "elapsed_time": "3:20:24", "remaining_time": "6:27:00"}
+{"current_steps": 940, "total_steps": 2726, "loss": 0.4576, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.678650647550822e-05, "epoch": 0.69, "percentage": 34.48, "elapsed_time": "3:22:27", "remaining_time": "6:24:40"}
+{"current_steps": 950, "total_steps": 2726, "loss": 0.446, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.6531645508843636e-05, "epoch": 0.7, "percentage": 34.85, "elapsed_time": "3:24:21", "remaining_time": "6:22:01"}
+{"current_steps": 960, "total_steps": 2726, "loss": 0.4439, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.6275252980402544e-05, "epoch": 0.7, "percentage": 35.22, "elapsed_time": "3:26:18", "remaining_time": "6:19:31"}
+{"current_steps": 970, "total_steps": 2726, "loss": 0.476, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.601736294265354e-05, "epoch": 0.71, "percentage": 35.58, "elapsed_time": "3:28:32", "remaining_time": "6:17:31"}
+{"current_steps": 980, "total_steps": 2726, "loss": 0.4153, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.5758009646955115e-05, "epoch": 0.72, "percentage": 35.95, "elapsed_time": "3:30:27", "remaining_time": "6:14:57"}
+{"current_steps": 990, "total_steps": 2726, "loss": 0.4444, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.5497227539006614e-05, "epoch": 0.73, "percentage": 36.32, "elapsed_time": "3:32:34", "remaining_time": "6:12:46"}
+{"current_steps": 1000, "total_steps": 2726, "loss": 0.4395, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.523505125427341e-05, "epoch": 0.73, "percentage": 36.68, "elapsed_time": "3:34:52", "remaining_time": "6:10:52"}
+{"current_steps": 1000, "total_steps": 2726, "loss": null, "eval_loss": 0.44357746839523315, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.73, "percentage": 36.68, "elapsed_time": "3:34:52", "remaining_time": "6:10:52"}
+{"current_steps": 1010, "total_steps": 2726, "loss": 0.4387, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.497151561338678e-05, "epoch": 0.74, "percentage": 37.05, "elapsed_time": "3:38:14", "remaining_time": "6:10:46"}
+{"current_steps": 1020, "total_steps": 2726, "loss": 0.4559, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.470665561751928e-05, "epoch": 0.75, "percentage": 37.42, "elapsed_time": "3:40:04", "remaining_time": "6:08:04"}
+{"current_steps": 1030, "total_steps": 2726, "loss": 0.4349, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.444050644373611e-05, "epoch": 0.76, "percentage": 37.78, "elapsed_time": "3:42:11", "remaining_time": "6:05:50"}
+{"current_steps": 1040, "total_steps": 2726, "loss": 0.4661, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.417310344032309e-05, "epoch": 0.76, "percentage": 38.15, "elapsed_time": "3:44:11", "remaining_time": "6:03:26"}
+{"current_steps": 1050, "total_steps": 2726, "loss": 0.4945, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.390448212209191e-05, "epoch": 0.77, "percentage": 38.52, "elapsed_time": "3:46:22", "remaining_time": "6:01:20"}
+{"current_steps": 1060, "total_steps": 2726, "loss": 0.4399, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.3634678165663325e-05, "epoch": 0.78, "percentage": 38.88, "elapsed_time": "3:48:36", "remaining_time": "5:59:18"}
+{"current_steps": 1070, "total_steps": 2726, "loss": 0.4399, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.336372740472877e-05, "epoch": 0.78, "percentage": 39.25, "elapsed_time": "3:50:31", "remaining_time": "5:56:47"}
+{"current_steps": 1080, "total_steps": 2726, "loss": 0.4251, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.309166582529114e-05, "epoch": 0.79, "percentage": 39.62, "elapsed_time": "3:52:21", "remaining_time": "5:54:08"}
+{"current_steps": 1090, "total_steps": 2726, "loss": 0.4385, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.281852956088537e-05, "epoch": 0.8, "percentage": 39.99, "elapsed_time": "3:54:18", "remaining_time": "5:51:40"}
+{"current_steps": 1100, "total_steps": 2726, "loss": 0.4566, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.254435488777941e-05, "epoch": 0.81, "percentage": 40.35, "elapsed_time": "3:56:22", "remaining_time": "5:49:24"}
+{"current_steps": 1110, "total_steps": 2726, "loss": 0.4352, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.226917822015623e-05, "epoch": 0.81, "percentage": 40.72, "elapsed_time": "3:58:33", "remaining_time": "5:47:19"}
+{"current_steps": 1120, "total_steps": 2726, "loss": 0.4617, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.199303610527749e-05, "epoch": 0.82, "percentage": 41.09, "elapsed_time": "4:00:57", "remaining_time": "5:45:30"}
+{"current_steps": 1130, "total_steps": 2726, "loss": 0.476, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.1715965218629595e-05, "epoch": 0.83, "percentage": 41.45, "elapsed_time": "4:02:46", "remaining_time": "5:42:54"}
+{"current_steps": 1140, "total_steps": 2726, "loss": 0.4322, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.143800235905268e-05, "epoch": 0.84, "percentage": 41.82, "elapsed_time": "4:04:46", "remaining_time": "5:40:32"}
+{"current_steps": 1150, "total_steps": 2726, "loss": 0.4736, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.115918444385315e-05, "epoch": 0.84, "percentage": 42.19, "elapsed_time": "4:06:57", "remaining_time": "5:38:26"}
+{"current_steps": 1160, "total_steps": 2726, "loss": 0.4322, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.0879548503900665e-05, "epoch": 0.85, "percentage": 42.55, "elapsed_time": "4:09:21", "remaining_time": "5:36:37"}
+{"current_steps": 1170, "total_steps": 2726, "loss": 0.4152, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.0599131678709836e-05, "epoch": 0.86, "percentage": 42.92, "elapsed_time": "4:11:20", "remaining_time": "5:34:16"}
+{"current_steps": 1180, "total_steps": 2726, "loss": 0.4187, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.031797121150764e-05, "epoch": 0.87, "percentage": 43.29, "elapsed_time": "4:13:18", "remaining_time": "5:31:52"}
+{"current_steps": 1190, "total_steps": 2726, "loss": 0.4331, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.0036104444286954e-05, "epoch": 0.87, "percentage": 43.65, "elapsed_time": "4:15:22", "remaining_time": "5:29:37"}
+{"current_steps": 1200, "total_steps": 2726, "loss": 0.45, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.9753568812847065e-05, "epoch": 0.88, "percentage": 44.02, "elapsed_time": "4:17:56", "remaining_time": "5:28:00"}
+{"current_steps": 1200, "total_steps": 2726, "loss": null, "eval_loss": 0.43782830238342285, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.88, "percentage": 44.02, "elapsed_time": "4:17:56", "remaining_time": "5:28:00"}
+{"current_steps": 1210, "total_steps": 2726, "loss": 0.4457, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.9470401841821686e-05, "epoch": 0.89, "percentage": 44.39, "elapsed_time": "4:21:17", "remaining_time": "5:27:22"}
+{"current_steps": 1220, "total_steps": 2726, "loss": 0.4667, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.9186641139695108e-05, "epoch": 0.89, "percentage": 44.75, "elapsed_time": "4:23:21", "remaining_time": "5:25:05"}
+{"current_steps": 1230, "total_steps": 2726, "loss": 0.4516, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.8902324393807333e-05, "epoch": 0.9, "percentage": 45.12, "elapsed_time": "4:25:38", "remaining_time": "5:23:05"}
+{"current_steps": 1240, "total_steps": 2726, "loss": 0.4695, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.861748936534867e-05, "epoch": 0.91, "percentage": 45.49, "elapsed_time": "4:27:43", "remaining_time": "5:20:50"}
+{"current_steps": 1250, "total_steps": 2726, "loss": 0.45, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.8332173884344477e-05, "epoch": 0.92, "percentage": 45.85, "elapsed_time": "4:30:07", "remaining_time": "5:18:58"}
+{"current_steps": 1260, "total_steps": 2726, "loss": 0.4246, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.8046415844630857e-05, "epoch": 0.92, "percentage": 46.22, "elapsed_time": "4:32:04", "remaining_time": "5:16:33"}
+{"current_steps": 1270, "total_steps": 2726, "loss": 0.4449, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.7760253198821822e-05, "epoch": 0.93, "percentage": 46.59, "elapsed_time": "4:34:02", "remaining_time": "5:14:10"}
+{"current_steps": 1280, "total_steps": 2726, "loss": 0.4217, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.7473723953268687e-05, "epoch": 0.94, "percentage": 46.96, "elapsed_time": "4:36:21", "remaining_time": "5:12:11"}
+{"current_steps": 1290, "total_steps": 2726, "loss": 0.4495, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.7186866163012232e-05, "epoch": 0.95, "percentage": 47.32, "elapsed_time": "4:38:18", "remaining_time": "5:09:48"}
+{"current_steps": 1300, "total_steps": 2726, "loss": 0.4523, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.6899717926728535e-05, "epoch": 0.95, "percentage": 47.69, "elapsed_time": "4:40:31", "remaining_time": "5:07:43"}
+{"current_steps": 1310, "total_steps": 2726, "loss": 0.4523, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.6612317381668915e-05, "epoch": 0.96, "percentage": 48.06, "elapsed_time": "4:42:52", "remaining_time": "5:05:45"}
+{"current_steps": 1320, "total_steps": 2726, "loss": 0.45, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.632470269859478e-05, "epoch": 0.97, "percentage": 48.42, "elapsed_time": "4:44:43", "remaining_time": "5:03:16"}
+{"current_steps": 1330, "total_steps": 2726, "loss": 0.4371, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.603691207670803e-05, "epoch": 0.98, "percentage": 48.79, "elapsed_time": "4:46:50", "remaining_time": "5:01:04"}
+{"current_steps": 1340, "total_steps": 2726, "loss": 0.4221, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5748983738577653e-05, "epoch": 0.98, "percentage": 49.16, "elapsed_time": "4:49:12", "remaining_time": "4:59:08"}
+{"current_steps": 1350, "total_steps": 2726, "loss": 0.4565, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5460955925063268e-05, "epoch": 0.99, "percentage": 49.52, "elapsed_time": "4:51:37", "remaining_time": "4:57:14"}
+{"current_steps": 1360, "total_steps": 2726, "loss": 0.3892, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5172866890236203e-05, "epoch": 1.0, "percentage": 49.89, "elapsed_time": "4:53:48", "remaining_time": "4:55:05"}
+{"current_steps": 1370, "total_steps": 2726, "loss": 0.3973, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.48847548962988e-05, "epoch": 1.0, "percentage": 50.26, "elapsed_time": "4:56:07", "remaining_time": "4:53:06"}
+{"current_steps": 1380, "total_steps": 2726, "loss": 0.4151, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.4596658208502713e-05, "epoch": 1.01, "percentage": 50.62, "elapsed_time": "4:58:09", "remaining_time": "4:50:48"}
+{"current_steps": 1390, "total_steps": 2726, "loss": 0.3839, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.4308615090066735e-05, "epoch": 1.02, "percentage": 50.99, "elapsed_time": "5:00:25", "remaining_time": "4:48:44"}
+{"current_steps": 1400, "total_steps": 2726, "loss": 0.4062, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.4020663797094864e-05, "epoch": 1.03, "percentage": 51.36, "elapsed_time": "5:02:30", "remaining_time": "4:46:31"}
+{"current_steps": 1400, "total_steps": 2726, "loss": null, "eval_loss": 0.43284282088279724, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.03, "percentage": 51.36, "elapsed_time": "5:02:30", "remaining_time": "4:46:31"}
+{"current_steps": 1410, "total_steps": 2726, "loss": 0.4003, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.373284257349544e-05, "epoch": 1.03, "percentage": 51.72, "elapsed_time": "5:05:58", "remaining_time": "4:45:34"}
+{"current_steps": 1420, "total_steps": 2726, "loss": 0.4447, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3445189645901806e-05, "epoch": 1.04, "percentage": 52.09, "elapsed_time": "5:08:26", "remaining_time": "4:43:40"}
+{"current_steps": 1430, "total_steps": 2726, "loss": 0.4565, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3157743218595247e-05, "epoch": 1.05, "percentage": 52.46, "elapsed_time": "5:10:20", "remaining_time": "4:41:15"}
+{"current_steps": 1440, "total_steps": 2726, "loss": 0.4265, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.287054146843097e-05, "epoch": 1.06, "percentage": 52.82, "elapsed_time": "5:12:13", "remaining_time": "4:38:50"}
+{"current_steps": 1450, "total_steps": 2726, "loss": 0.4056, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2583622539767668e-05, "epoch": 1.06, "percentage": 53.19, "elapsed_time": "5:14:21", "remaining_time": "4:36:38"}
+{"current_steps": 1460, "total_steps": 2726, "loss": 0.4074, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2297024539401463e-05, "epoch": 1.07, "percentage": 53.56, "elapsed_time": "5:16:26", "remaining_time": "4:34:23"}
+{"current_steps": 1470, "total_steps": 2726, "loss": 0.4281, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2010785531504716e-05, "epoch": 1.08, "percentage": 53.93, "elapsed_time": "5:18:46", "remaining_time": "4:32:22"}
+{"current_steps": 1480, "total_steps": 2726, "loss": 0.4663, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.172494353257066e-05, "epoch": 1.09, "percentage": 54.29, "elapsed_time": "5:21:04", "remaining_time": "4:30:18"}
+{"current_steps": 1490, "total_steps": 2726, "loss": 0.4281, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.1439536506364274e-05, "epoch": 1.09, "percentage": 54.66, "elapsed_time": "5:23:36", "remaining_time": "4:28:26"}
+{"current_steps": 1500, "total_steps": 2726, "loss": 0.4111, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.1154602358880122e-05, "epoch": 1.1, "percentage": 55.03, "elapsed_time": "5:25:52", "remaining_time": "4:26:20"}
+{"current_steps": 1510, "total_steps": 2726, "loss": 0.4187, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0870178933307948e-05, "epoch": 1.11, "percentage": 55.39, "elapsed_time": "5:27:49", "remaining_time": "4:23:59"}
+{"current_steps": 1520, "total_steps": 2726, "loss": 0.3964, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0586304005006585e-05, "epoch": 1.11, "percentage": 55.76, "elapsed_time": "5:30:05", "remaining_time": "4:21:54"}
+{"current_steps": 1530, "total_steps": 2726, "loss": 0.4331, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.030301527648684e-05, "epoch": 1.12, "percentage": 56.13, "elapsed_time": "5:32:15", "remaining_time": "4:19:43"}
+{"current_steps": 1540, "total_steps": 2726, "loss": 0.4432, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0020350372404102e-05, "epoch": 1.13, "percentage": 56.49, "elapsed_time": "5:34:15", "remaining_time": "4:17:25"}
+{"current_steps": 1550, "total_steps": 2726, "loss": 0.4056, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9738346834561254e-05, "epoch": 1.14, "percentage": 56.86, "elapsed_time": "5:36:18", "remaining_time": "4:15:09"}
+{"current_steps": 1560, "total_steps": 2726, "loss": 0.4354, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.945704211692262e-05, "epoch": 1.14, "percentage": 57.23, "elapsed_time": "5:38:26", "remaining_time": "4:12:57"}
+{"current_steps": 1570, "total_steps": 2726, "loss": 0.4309, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9176473580639538e-05, "epoch": 1.15, "percentage": 57.59, "elapsed_time": "5:40:42", "remaining_time": "4:10:52"}
+{"current_steps": 1580, "total_steps": 2726, "loss": 0.4058, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8896678489088304e-05, "epoch": 1.16, "percentage": 57.96, "elapsed_time": "5:42:44", "remaining_time": "4:08:35"}
+{"current_steps": 1590, "total_steps": 2726, "loss": 0.4319, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8617694002921064e-05, "epoch": 1.17, "percentage": 58.33, "elapsed_time": "5:44:54", "remaining_time": "4:06:25"}
+{"current_steps": 1600, "total_steps": 2726, "loss": 0.4267, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8339557175130383e-05, "epoch": 1.17, "percentage": 58.69, "elapsed_time": "5:46:47", "remaining_time": "4:04:03"}
+{"current_steps": 1600, "total_steps": 2726, "loss": null, "eval_loss": 0.42894992232322693, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.17, "percentage": 58.69, "elapsed_time": "5:46:47", "remaining_time": "4:04:03"}
+{"current_steps": 1610, "total_steps": 2726, "loss": 0.3921, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8062304946128073e-05, "epoch": 1.18, "percentage": 59.06, "elapsed_time": "5:50:11", "remaining_time": "4:02:44"}
+{"current_steps": 1620, "total_steps": 2726, "loss": 0.4206, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7785974138839018e-05, "epoch": 1.19, "percentage": 59.43, "elapsed_time": "5:52:10", "remaining_time": "4:00:26"}
+{"current_steps": 1630, "total_steps": 2726, "loss": 0.4356, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7510601453810594e-05, "epoch": 1.2, "percentage": 59.79, "elapsed_time": "5:54:17", "remaining_time": "3:58:13"}
+{"current_steps": 1640, "total_steps": 2726, "loss": 0.4167, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.723622346433828e-05, "epoch": 1.2, "percentage": 60.16, "elapsed_time": "5:56:29", "remaining_time": "3:56:03"}
+{"current_steps": 1650, "total_steps": 2726, "loss": 0.4233, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6962876611608262e-05, "epoch": 1.21, "percentage": 60.53, "elapsed_time": "5:58:26", "remaining_time": "3:53:45"}
+{"current_steps": 1660, "total_steps": 2726, "loss": 0.4176, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6690597199857523e-05, "epoch": 1.22, "percentage": 60.9, "elapsed_time": "6:00:33", "remaining_time": "3:51:32"}
+{"current_steps": 1670, "total_steps": 2726, "loss": 0.4241, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6419421391552142e-05, "epoch": 1.22, "percentage": 61.26, "elapsed_time": "6:02:41", "remaining_time": "3:49:20"}
+{"current_steps": 1680, "total_steps": 2726, "loss": 0.4524, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6149385202584423e-05, "epoch": 1.23, "percentage": 61.63, "elapsed_time": "6:04:45", "remaining_time": "3:47:06"}
+{"current_steps": 1690, "total_steps": 2726, "loss": 0.4647, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5880524497489474e-05, "epoch": 1.24, "percentage": 62.0, "elapsed_time": "6:07:03", "remaining_time": "3:45:01"}
+{"current_steps": 1700, "total_steps": 2726, "loss": 0.4036, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5612874984681923e-05, "epoch": 1.25, "percentage": 62.36, "elapsed_time": "6:09:03", "remaining_time": "3:42:44"}
+{"current_steps": 1710, "total_steps": 2726, "loss": 0.4148, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.534647221171334e-05, "epoch": 1.25, "percentage": 62.73, "elapsed_time": "6:11:22", "remaining_time": "3:40:38"}
+{"current_steps": 1720, "total_steps": 2726, "loss": 0.408, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5081351560551021e-05, "epoch": 1.26, "percentage": 63.1, "elapsed_time": "6:13:19", "remaining_time": "3:38:21"}
+{"current_steps": 1730, "total_steps": 2726, "loss": 0.457, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4817548242878759e-05, "epoch": 1.27, "percentage": 63.46, "elapsed_time": "6:15:23", "remaining_time": "3:36:07"}
+{"current_steps": 1740, "total_steps": 2726, "loss": 0.4193, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.45550972954203e-05, "epoch": 1.28, "percentage": 63.83, "elapsed_time": "6:17:21", "remaining_time": "3:33:50"}
+{"current_steps": 1750, "total_steps": 2726, "loss": 0.4149, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4294033575285914e-05, "epoch": 1.28, "percentage": 64.2, "elapsed_time": "6:19:35", "remaining_time": "3:31:42"}
+{"current_steps": 1760, "total_steps": 2726, "loss": 0.4032, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4034391755342972e-05, "epoch": 1.29, "percentage": 64.56, "elapsed_time": "6:21:52", "remaining_time": "3:29:35"}
+{"current_steps": 1770, "total_steps": 2726, "loss": 0.4078, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3776206319610823e-05, "epoch": 1.3, "percentage": 64.93, "elapsed_time": "6:23:56", "remaining_time": "3:27:22"}
+{"current_steps": 1780, "total_steps": 2726, "loss": 0.4123, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3519511558680892e-05, "epoch": 1.31, "percentage": 65.3, "elapsed_time": "6:26:23", "remaining_time": "3:25:21"}
+{"current_steps": 1790, "total_steps": 2726, "loss": 0.4089, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3264341565162422e-05, "epoch": 1.31, "percentage": 65.66, "elapsed_time": "6:28:17", "remaining_time": "3:23:02"}
+{"current_steps": 1800, "total_steps": 2726, "loss": 0.383, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3010730229154445e-05, "epoch": 1.32, "percentage": 66.03, "elapsed_time": "6:30:17", "remaining_time": "3:20:47"}
+{"current_steps": 1800, "total_steps": 2726, "loss": null, "eval_loss": 0.4250344932079315, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.32, "percentage": 66.03, "elapsed_time": "6:30:17", "remaining_time": "3:20:47"}
+{"current_steps": 1810, "total_steps": 2726, "loss": 0.3936, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2758711233744783e-05, "epoch": 1.33, "percentage": 66.4, "elapsed_time": "6:33:42", "remaining_time": "3:19:14"}
+{"current_steps": 1820, "total_steps": 2726, "loss": 0.4127, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2508318050536421e-05, "epoch": 1.33, "percentage": 66.76, "elapsed_time": "6:35:33", "remaining_time": "3:16:54"}
+{"current_steps": 1830, "total_steps": 2726, "loss": 0.4015, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2259583935202062e-05, "epoch": 1.34, "percentage": 67.13, "elapsed_time": "6:37:28", "remaining_time": "3:14:36"}
+{"current_steps": 1840, "total_steps": 2726, "loss": 0.4203, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2012541923067244e-05, "epoch": 1.35, "percentage": 67.5, "elapsed_time": "6:39:29", "remaining_time": "3:12:21"}
+{"current_steps": 1850, "total_steps": 2726, "loss": 0.4367, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.176722482472286e-05, "epoch": 1.36, "percentage": 67.87, "elapsed_time": "6:41:25", "remaining_time": "3:10:04"}
+{"current_steps": 1860, "total_steps": 2726, "loss": 0.4233, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1523665221667398e-05, "epoch": 1.36, "percentage": 68.23, "elapsed_time": "6:43:12", "remaining_time": "3:07:44"}
+{"current_steps": 1870, "total_steps": 2726, "loss": 0.4405, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1281895461979732e-05, "epoch": 1.37, "percentage": 68.6, "elapsed_time": "6:45:16", "remaining_time": "3:05:31"}
+{"current_steps": 1880, "total_steps": 2726, "loss": 0.4379, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.104194765602281e-05, "epoch": 1.38, "percentage": 68.97, "elapsed_time": "6:47:24", "remaining_time": "3:03:20"}
+{"current_steps": 1890, "total_steps": 2726, "loss": 0.4146, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0803853672178946e-05, "epoch": 1.39, "percentage": 69.33, "elapsed_time": "6:49:44", "remaining_time": "3:01:14"}
+{"current_steps": 1900, "total_steps": 2726, "loss": 0.4438, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0567645132617316e-05, "epoch": 1.39, "percentage": 69.7, "elapsed_time": "6:51:53", "remaining_time": "2:59:03"}
+{"current_steps": 1910, "total_steps": 2726, "loss": 0.3915, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0333353409094015e-05, "epoch": 1.4, "percentage": 70.07, "elapsed_time": "6:54:02", "remaining_time": "2:56:53"}
+{"current_steps": 1920, "total_steps": 2726, "loss": 0.4063, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0101009618785528e-05, "epoch": 1.41, "percentage": 70.43, "elapsed_time": "6:56:21", "remaining_time": "2:54:47"}
+{"current_steps": 1930, "total_steps": 2726, "loss": 0.3974, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.870644620155877e-06, "epoch": 1.42, "percentage": 70.8, "elapsed_time": "6:58:32", "remaining_time": "2:52:37"}
+{"current_steps": 1940, "total_steps": 2726, "loss": 0.4015, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.642289008858244e-06, "epoch": 1.42, "percentage": 71.17, "elapsed_time": "7:00:49", "remaining_time": "2:50:30"}
+{"current_steps": 1950, "total_steps": 2726, "loss": 0.4264, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.41597311367142e-06, "epoch": 1.43, "percentage": 71.53, "elapsed_time": "7:02:59", "remaining_time": "2:48:19"}
+{"current_steps": 1960, "total_steps": 2726, "loss": 0.4334, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.191726992471725e-06, "epoch": 1.44, "percentage": 71.9, "elapsed_time": "7:05:22", "remaining_time": "2:46:14"}
+{"current_steps": 1970, "total_steps": 2726, "loss": 0.4197, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.969580428240903e-06, "epoch": 1.44, "percentage": 72.27, "elapsed_time": "7:07:11", "remaining_time": "2:43:56"}
+{"current_steps": 1980, "total_steps": 2726, "loss": 0.422, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.74956292511056e-06, "epoch": 1.45, "percentage": 72.63, "elapsed_time": "7:09:23", "remaining_time": "2:41:46"}
+{"current_steps": 1990, "total_steps": 2726, "loss": 0.4077, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.531703704443575e-06, "epoch": 1.46, "percentage": 73.0, "elapsed_time": "7:11:33", "remaining_time": "2:39:36"}
+{"current_steps": 2000, "total_steps": 2726, "loss": 0.4334, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.316031700953086e-06, "epoch": 1.47, "percentage": 73.37, "elapsed_time": "7:13:58", "remaining_time": "2:37:31"}
+{"current_steps": 2000, "total_steps": 2726, "loss": null, "eval_loss": 0.4206145107746124, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.47, "percentage": 73.37, "elapsed_time": "7:13:58", "remaining_time": "2:37:31"}
+{"current_steps": 2010, "total_steps": 2726, "loss": 0.4171, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.102575558859612e-06, "epoch": 1.47, "percentage": 73.73, "elapsed_time": "7:17:28", "remaining_time": "2:35:50"}
+{"current_steps": 2020, "total_steps": 2726, "loss": 0.3957, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.891363628086671e-06, "epoch": 1.48, "percentage": 74.1, "elapsed_time": "7:19:27", "remaining_time": "2:33:35"}
+{"current_steps": 2030, "total_steps": 2726, "loss": 0.4174, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.682423960495517e-06, "epoch": 1.49, "percentage": 74.47, "elapsed_time": "7:21:25", "remaining_time": "2:31:20"}
+{"current_steps": 2040, "total_steps": 2726, "loss": 0.4187, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.475784306159478e-06, "epoch": 1.5, "percentage": 74.83, "elapsed_time": "7:23:33", "remaining_time": "2:29:09"}
+{"current_steps": 2050, "total_steps": 2726, "loss": 0.3775, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.271472109678379e-06, "epoch": 1.5, "percentage": 75.2, "elapsed_time": "7:25:41", "remaining_time": "2:26:58"}
+{"current_steps": 2060, "total_steps": 2726, "loss": 0.4019, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.0695145065334585e-06, "epoch": 1.51, "percentage": 75.57, "elapsed_time": "7:27:36", "remaining_time": "2:24:42"}
+{"current_steps": 2070, "total_steps": 2726, "loss": 0.4143, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.869938319483471e-06, "epoch": 1.52, "percentage": 75.94, "elapsed_time": "7:29:45", "remaining_time": "2:22:31"}
+{"current_steps": 2080, "total_steps": 2726, "loss": 0.3853, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.67277005500222e-06, "epoch": 1.53, "percentage": 76.3, "elapsed_time": "7:31:46", "remaining_time": "2:20:18"}
+{"current_steps": 2090, "total_steps": 2726, "loss": 0.4403, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.478035899758139e-06, "epoch": 1.53, "percentage": 76.67, "elapsed_time": "7:33:54", "remaining_time": "2:18:07"}
+{"current_steps": 2100, "total_steps": 2726, "loss": 0.3888, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.285761717136335e-06, "epoch": 1.54, "percentage": 77.04, "elapsed_time": "7:36:12", "remaining_time": "2:15:59"}
+{"current_steps": 2110, "total_steps": 2726, "loss": 0.4123, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.095973043803577e-06, "epoch": 1.55, "percentage": 77.4, "elapsed_time": "7:38:32", "remaining_time": "2:13:52"}
+{"current_steps": 2120, "total_steps": 2726, "loss": 0.4035, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.908695086316701e-06, "epoch": 1.55, "percentage": 77.77, "elapsed_time": "7:40:48", "remaining_time": "2:11:43"}
+{"current_steps": 2130, "total_steps": 2726, "loss": 0.4219, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.723952717774763e-06, "epoch": 1.56, "percentage": 78.14, "elapsed_time": "7:42:48", "remaining_time": "2:09:30"}
+{"current_steps": 2140, "total_steps": 2726, "loss": 0.4209, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.54177047451562e-06, "epoch": 1.57, "percentage": 78.5, "elapsed_time": "7:44:53", "remaining_time": "2:07:18"}
+{"current_steps": 2150, "total_steps": 2726, "loss": 0.4286, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.362172552857128e-06, "epoch": 1.58, "percentage": 78.87, "elapsed_time": "7:47:02", "remaining_time": "2:05:07"}
+{"current_steps": 2160, "total_steps": 2726, "loss": 0.4134, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.18518280588354e-06, "epoch": 1.58, "percentage": 79.24, "elapsed_time": "7:49:04", "remaining_time": "2:02:54"}
+{"current_steps": 2170, "total_steps": 2726, "loss": 0.4005, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.010824740277501e-06, "epoch": 1.59, "percentage": 79.6, "elapsed_time": "7:51:12", "remaining_time": "2:00:44"}
+{"current_steps": 2180, "total_steps": 2726, "loss": 0.3973, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.83912151319802e-06, "epoch": 1.6, "percentage": 79.97, "elapsed_time": "7:53:12", "remaining_time": "1:58:31"}
+{"current_steps": 2190, "total_steps": 2726, "loss": 0.3959, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.6700959292048875e-06, "epoch": 1.61, "percentage": 80.34, "elapsed_time": "7:55:29", "remaining_time": "1:56:22"}
+{"current_steps": 2200, "total_steps": 2726, "loss": 0.4017, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.503770437229918e-06, "epoch": 1.61, "percentage": 80.7, "elapsed_time": "7:57:38", "remaining_time": "1:54:12"}
+{"current_steps": 2200, "total_steps": 2726, "loss": null, "eval_loss": 0.41970890760421753, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.61, "percentage": 80.7, "elapsed_time": "7:57:38", "remaining_time": "1:54:12"}
+{"current_steps": 2210, "total_steps": 2726, "loss": 0.4013, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.340167127595407e-06, "epoch": 1.62, "percentage": 81.07, "elapsed_time": "8:00:51", "remaining_time": "1:52:16"}
+{"current_steps": 2220, "total_steps": 2726, "loss": 0.4069, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.179307729080256e-06, "epoch": 1.63, "percentage": 81.44, "elapsed_time": "8:03:00", "remaining_time": "1:50:05"}
+{"current_steps": 2230, "total_steps": 2726, "loss": 0.3857, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.021213606034064e-06, "epoch": 1.64, "percentage": 81.8, "elapsed_time": "8:05:05", "remaining_time": "1:47:53"}
+{"current_steps": 2240, "total_steps": 2726, "loss": 0.4262, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.8659057555396645e-06, "epoch": 1.64, "percentage": 82.17, "elapsed_time": "8:07:03", "remaining_time": "1:45:40"}
+{"current_steps": 2250, "total_steps": 2726, "loss": 0.3953, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.713404804624418e-06, "epoch": 1.65, "percentage": 82.54, "elapsed_time": "8:09:07", "remaining_time": "1:43:28"}
+{"current_steps": 2260, "total_steps": 2726, "loss": 0.4231, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.5637310075206544e-06, "epoch": 1.66, "percentage": 82.91, "elapsed_time": "8:11:23", "remaining_time": "1:41:19"}
+{"current_steps": 2270, "total_steps": 2726, "loss": 0.407, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.416904242975635e-06, "epoch": 1.66, "percentage": 83.27, "elapsed_time": "8:13:23", "remaining_time": "1:39:06"}
+{"current_steps": 2280, "total_steps": 2726, "loss": 0.4254, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.2729440116113843e-06, "epoch": 1.67, "percentage": 83.64, "elapsed_time": "8:15:40", "remaining_time": "1:36:57"}
+{"current_steps": 2290, "total_steps": 2726, "loss": 0.4054, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.131869433334725e-06, "epoch": 1.68, "percentage": 84.01, "elapsed_time": "8:17:43", "remaining_time": "1:34:45"}
+{"current_steps": 2300, "total_steps": 2726, "loss": 0.3801, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.9936992447979068e-06, "epoch": 1.69, "percentage": 84.37, "elapsed_time": "8:20:05", "remaining_time": "1:32:37"}
+{"current_steps": 2310, "total_steps": 2726, "loss": 0.4335, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.8584517969101054e-06, "epoch": 1.69, "percentage": 84.74, "elapsed_time": "8:21:46", "remaining_time": "1:30:21"}
+{"current_steps": 2320, "total_steps": 2726, "loss": 0.412, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.7261450524001807e-06, "epoch": 1.7, "percentage": 85.11, "elapsed_time": "8:23:37", "remaining_time": "1:28:08"}
+{"current_steps": 2330, "total_steps": 2726, "loss": 0.4456, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.596796583430969e-06, "epoch": 1.71, "percentage": 85.47, "elapsed_time": "8:25:39", "remaining_time": "1:25:56"}
+{"current_steps": 2340, "total_steps": 2726, "loss": 0.3972, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.470423569265462e-06, "epoch": 1.72, "percentage": 85.84, "elapsed_time": "8:27:30", "remaining_time": "1:23:43"}
+{"current_steps": 2350, "total_steps": 2726, "loss": 0.3935, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.34704279398516e-06, "epoch": 1.72, "percentage": 86.21, "elapsed_time": "8:29:12", "remaining_time": "1:21:28"}
+{"current_steps": 2360, "total_steps": 2726, "loss": 0.3974, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2266706442609226e-06, "epoch": 1.73, "percentage": 86.57, "elapsed_time": "8:31:13", "remaining_time": "1:19:17"}
+{"current_steps": 2370, "total_steps": 2726, "loss": 0.4157, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.109323107176578e-06, "epoch": 1.74, "percentage": 86.94, "elapsed_time": "8:33:31", "remaining_time": "1:17:08"}
+{"current_steps": 2380, "total_steps": 2726, "loss": 0.4379, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9950157681056318e-06, "epoch": 1.75, "percentage": 87.31, "elapsed_time": "8:35:40", "remaining_time": "1:14:58"}
+{"current_steps": 2390, "total_steps": 2726, "loss": 0.4035, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8837638086413063e-06, "epoch": 1.75, "percentage": 87.67, "elapsed_time": "8:37:35", "remaining_time": "1:12:46"}
+{"current_steps": 2400, "total_steps": 2726, "loss": 0.4455, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7755820045802145e-06, "epoch": 1.76, "percentage": 88.04, "elapsed_time": "8:39:45", "remaining_time": "1:10:35"}
+{"current_steps": 2400, "total_steps": 2726, "loss": null, "eval_loss": 0.41885045170783997, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.76, "percentage": 88.04, "elapsed_time": "8:39:45", "remaining_time": "1:10:35"}
+{"current_steps": 2410, "total_steps": 2726, "loss": 0.4532, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6704847239599364e-06, "epoch": 1.77, "percentage": 88.41, "elapsed_time": "8:43:09", "remaining_time": "1:08:35"}
+{"current_steps": 2420, "total_steps": 2726, "loss": 0.4213, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5684859251507394e-06, "epoch": 1.77, "percentage": 88.77, "elapsed_time": "8:45:22", "remaining_time": "1:06:25"}
+{"current_steps": 2430, "total_steps": 2726, "loss": 0.3873, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4695991550017164e-06, "epoch": 1.78, "percentage": 89.14, "elapsed_time": "8:47:29", "remaining_time": "1:04:15"}
+{"current_steps": 2440, "total_steps": 2726, "loss": 0.4163, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.373837547041576e-06, "epoch": 1.79, "percentage": 89.51, "elapsed_time": "8:49:41", "remaining_time": "1:02:05"}
+{"current_steps": 2450, "total_steps": 2726, "loss": 0.3946, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2812138197343392e-06, "epoch": 1.8, "percentage": 89.88, "elapsed_time": "8:51:48", "remaining_time": "0:59:54"}
+{"current_steps": 2460, "total_steps": 2726, "loss": 0.41, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1917402747901152e-06, "epoch": 1.8, "percentage": 90.24, "elapsed_time": "8:53:44", "remaining_time": "0:57:42"}
+{"current_steps": 2470, "total_steps": 2726, "loss": 0.4126, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.105428795531327e-06, "epoch": 1.81, "percentage": 90.61, "elapsed_time": "8:55:59", "remaining_time": "0:55:33"}
+{"current_steps": 2480, "total_steps": 2726, "loss": 0.4505, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0222908453143804e-06, "epoch": 1.82, "percentage": 90.98, "elapsed_time": "8:58:09", "remaining_time": "0:53:22"}
+{"current_steps": 2490, "total_steps": 2726, "loss": 0.4303, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.423374660072065e-07, "epoch": 1.83, "percentage": 91.34, "elapsed_time": "9:00:00", "remaining_time": "0:51:10"}
+{"current_steps": 2500, "total_steps": 2726, "loss": 0.4179, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.655792765227405e-07, "epoch": 1.83, "percentage": 91.71, "elapsed_time": "9:01:58", "remaining_time": "0:48:59"}
+{"current_steps": 2510, "total_steps": 2726, "loss": 0.4376, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.920264714085828e-07, "epoch": 1.84, "percentage": 92.08, "elapsed_time": "9:04:05", "remaining_time": "0:46:49"}
+{"current_steps": 2520, "total_steps": 2726, "loss": 0.4069, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.216888194930272e-07, "epoch": 1.85, "percentage": 92.44, "elapsed_time": "9:06:08", "remaining_time": "0:44:38"}
+{"current_steps": 2530, "total_steps": 2726, "loss": 0.3887, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.545756625876031e-07, "epoch": 1.86, "percentage": 92.81, "elapsed_time": "9:08:12", "remaining_time": "0:42:28"}
+{"current_steps": 2540, "total_steps": 2726, "loss": 0.3972, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.906959142463947e-07, "epoch": 1.86, "percentage": 93.18, "elapsed_time": "9:10:08", "remaining_time": "0:40:17"}
+{"current_steps": 2550, "total_steps": 2726, "loss": 0.4078, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.300580585821696e-07, "epoch": 1.87, "percentage": 93.54, "elapsed_time": "9:12:17", "remaining_time": "0:38:07"}
+{"current_steps": 2560, "total_steps": 2726, "loss": 0.4467, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.7267014913956463e-07, "epoch": 1.88, "percentage": 93.91, "elapsed_time": "9:14:11", "remaining_time": "0:35:56"}
+{"current_steps": 2570, "total_steps": 2726, "loss": 0.4567, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.1853980782549097e-07, "epoch": 1.88, "percentage": 94.28, "elapsed_time": "9:16:09", "remaining_time": "0:33:45"}
+{"current_steps": 2580, "total_steps": 2726, "loss": 0.4494, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.6767422389682173e-07, "epoch": 1.89, "percentage": 94.64, "elapsed_time": "9:18:36", "remaining_time": "0:31:36"}
+{"current_steps": 2590, "total_steps": 2726, "loss": 0.4344, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.2008015300555306e-07, "epoch": 1.9, "percentage": 95.01, "elapsed_time": "9:20:48", "remaining_time": "0:29:26"}
+{"current_steps": 2600, "total_steps": 2726, "loss": 0.4101, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.757639163015774e-07, "epoch": 1.91, "percentage": 95.38, "elapsed_time": "9:22:52", "remaining_time": "0:27:16"}
+{"current_steps": 2600, "total_steps": 2726, "loss": null, "eval_loss": 0.41886425018310547, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.91, "percentage": 95.38, "elapsed_time": "9:22:52", "remaining_time": "0:27:16"}
+{"current_steps": 2610, "total_steps": 2726, "loss": 0.4058, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.347313995931466e-07, "epoch": 1.91, "percentage": 95.74, "elapsed_time": "9:26:02", "remaining_time": "0:25:09"}
+{"current_steps": 2620, "total_steps": 2726, "loss": 0.414, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9698805256513908e-07, "epoch": 1.92, "percentage": 96.11, "elapsed_time": "9:28:14", "remaining_time": "0:22:59"}
+{"current_steps": 2630, "total_steps": 2726, "loss": 0.4254, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6253888805527474e-07, "epoch": 1.93, "percentage": 96.48, "elapsed_time": "9:30:26", "remaining_time": "0:20:49"}
+{"current_steps": 2640, "total_steps": 2726, "loss": 0.4017, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3138848138835313e-07, "epoch": 1.94, "percentage": 96.85, "elapsed_time": "9:32:34", "remaining_time": "0:18:39"}
+{"current_steps": 2650, "total_steps": 2726, "loss": 0.4258, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0354096976856186e-07, "epoch": 1.94, "percentage": 97.21, "elapsed_time": "9:34:48", "remaining_time": "0:16:29"}
+{"current_steps": 2660, "total_steps": 2726, "loss": 0.4098, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.900005173002712e-08, "epoch": 1.95, "percentage": 97.58, "elapsed_time": "9:37:06", "remaining_time": "0:14:19"}
+{"current_steps": 2670, "total_steps": 2726, "loss": 0.42, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.776898664557051e-08, "epoch": 1.96, "percentage": 97.95, "elapsed_time": "9:39:14", "remaining_time": "0:12:08"}
+{"current_steps": 2680, "total_steps": 2726, "loss": 0.3886, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.985059429383875e-08, "epoch": 1.97, "percentage": 98.31, "elapsed_time": "9:41:31", "remaining_time": "0:09:58"}
+{"current_steps": 2690, "total_steps": 2726, "loss": 0.4276, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5247254484794813e-08, "epoch": 1.97, "percentage": 98.68, "elapsed_time": "9:43:48", "remaining_time": "0:07:48"}
+{"current_steps": 2700, "total_steps": 2726, "loss": 0.4006, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3960906743634706e-08, "epoch": 1.98, "percentage": 99.05, "elapsed_time": "9:45:40", "remaining_time": "0:05:38"}
+{"current_steps": 2710, "total_steps": 2726, "loss": 0.4243, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.993050053204607e-09, "epoch": 1.99, "percentage": 99.41, "elapsed_time": "9:47:47", "remaining_time": "0:03:28"}
+{"current_steps": 2720, "total_steps": 2726, "loss": 0.4439, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3447426549129117e-09, "epoch": 1.99, "percentage": 99.78, "elapsed_time": "9:50:02", "remaining_time": "0:01:18"}
+{"current_steps": 2726, "total_steps": 2726, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "9:51:16", "remaining_time": "0:00:00"}
+{"current_steps": 111, "total_steps": 111, "loss": null, "eval_loss": 0.41885045170783997, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "9:52:25", "remaining_time": "0:00:00"}

Baichuan-13B-Chat-lora-Task/trainer_state.json

@@ -0,0 +1,1761 @@
+{
+  "best_metric": 0.41885045170783997,
+  "best_model_checkpoint": "output/Baichuan-13B-Chat_lora_wqs_nlp/checkpoint-2400",
+  "epoch": 1.9992665933259994,
+  "global_step": 2726,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.999865525734509e-05,
+      "loss": 1.5452,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.9994621174046976e-05,
+      "loss": 1.3291,
+      "step": 20
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.9986985231938546e-05,
+      "loss": 1.1048,
+      "step": 30
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.99760306731191e-05,
+      "loss": 0.9155,
+      "step": 40
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.9961758952505326e-05,
+      "loss": 0.8856,
+      "step": 50
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.9944171965578836e-05,
+      "loss": 0.8052,
+      "step": 60
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.992327204813435e-05,
+      "loss": 0.7332,
+      "step": 70
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.989906197596955e-05,
+      "loss": 0.6982,
+      "step": 80
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.987154496451635e-05,
+      "loss": 0.6811,
+      "step": 90
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.984072466841389e-05,
+      "loss": 0.6323,
+      "step": 100
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.981016546765289e-05,
+      "loss": 0.6234,
+      "step": 110
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.977308057009269e-05,
+      "loss": 0.6125,
+      "step": 120
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.97327054653146e-05,
+      "loss": 0.5977,
+      "step": 130
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.968904551569013e-05,
+      "loss": 0.6179,
+      "step": 140
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.9642106519863544e-05,
+      "loss": 0.5879,
+      "step": 150
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.959189471198171e-05,
+      "loss": 0.5472,
+      "step": 160
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.953841676086613e-05,
+      "loss": 0.602,
+      "step": 170
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.9481679769127275e-05,
+      "loss": 0.5773,
+      "step": 180
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.9421691272221167e-05,
+      "loss": 0.5615,
+      "step": 190
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.935845923744865e-05,
+      "loss": 0.5704,
+      "step": 200
+    },
+    {
+      "epoch": 0.15,
+      "eval_loss": 0.5564362406730652,
+      "eval_runtime": 72.9469,
+      "eval_samples_per_second": 15.107,
+      "eval_steps_per_second": 1.522,
+      "step": 200
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.9291992062897183e-05,
+      "loss": 0.5803,
+      "step": 210
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.922229857632545e-05,
+      "loss": 0.5655,
+      "step": 220
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.9149388033990966e-05,
+      "loss": 0.5769,
+      "step": 230
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.9073270119420635e-05,
+      "loss": 0.5862,
+      "step": 240
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.899395494212471e-05,
+      "loss": 0.5506,
+      "step": 250
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.891145303625408e-05,
+      "loss": 0.5183,
+      "step": 260
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.882577535920121e-05,
+      "loss": 0.575,
+      "step": 270
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.8736933290144815e-05,
+      "loss": 0.5359,
+      "step": 280
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.8644938628538606e-05,
+      "loss": 0.5302,
+      "step": 290
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.8549803592544076e-05,
+      "loss": 0.5399,
+      "step": 300
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.845154081740783e-05,
+      "loss": 0.5379,
+      "step": 310
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.835016335378343e-05,
+      "loss": 0.5299,
+      "step": 320
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.8245684665998073e-05,
+      "loss": 0.535,
+      "step": 330
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.813811863026436e-05,
+      "loss": 0.5145,
+      "step": 340
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.802747953283732e-05,
+      "loss": 0.5126,
+      "step": 350
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.791378206811704e-05,
+      "loss": 0.5012,
+      "step": 360
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.7797041336696995e-05,
+      "loss": 0.5373,
+      "step": 370
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.767727284335852e-05,
+      "loss": 0.4778,
+      "step": 380
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.755449249501155e-05,
+      "loss": 0.4894,
+      "step": 390
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.7428716598581934e-05,
+      "loss": 0.4986,
+      "step": 400
+    },
+    {
+      "epoch": 0.29,
+      "eval_loss": 0.4967592656612396,
+      "eval_runtime": 70.0948,
+      "eval_samples_per_second": 15.722,
+      "eval_steps_per_second": 1.584,
+      "step": 400
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.729996185884571e-05,
+      "loss": 0.4928,
+      "step": 410
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.716824537621042e-05,
+      "loss": 0.4807,
+      "step": 420
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.703358464444397e-05,
+      "loss": 0.4734,
+      "step": 430
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.689599754835122e-05,
+      "loss": 0.4603,
+      "step": 440
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 4.6755502361398616e-05,
+      "loss": 0.4661,
+      "step": 450
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 4.6612117743287234e-05,
+      "loss": 0.5072,
+      "step": 460
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 4.646586273747452e-05,
+      "loss": 0.5056,
+      "step": 470
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 4.631675676864503e-05,
+      "loss": 0.4391,
+      "step": 480
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.6164819640130595e-05,
+      "loss": 0.483,
+      "step": 490
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 4.601007153128014e-05,
+      "loss": 0.4774,
+      "step": 500
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 4.5852532994779606e-05,
+      "loss": 0.4848,
+      "step": 510
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 4.5692224953922266e-05,
+      "loss": 0.5099,
+      "step": 520
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 4.5529168699829805e-05,
+      "loss": 0.4851,
+      "step": 530
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.536338588862459e-05,
+      "loss": 0.498,
+      "step": 540
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.519489853855341e-05,
+      "loss": 0.5398,
+      "step": 550
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 4.50237290270632e-05,
+      "loss": 0.4566,
+      "step": 560
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 4.484990008782893e-05,
+      "loss": 0.4942,
+      "step": 570
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 4.467343480773433e-05,
+      "loss": 0.4625,
+      "step": 580
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 4.44943566238056e-05,
+      "loss": 0.4703,
+      "step": 590
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 4.431268932009865e-05,
+      "loss": 0.464,
+      "step": 600
+    },
+    {
+      "epoch": 0.44,
+      "eval_loss": 0.46821752190589905,
+      "eval_runtime": 69.9505,
+      "eval_samples_per_second": 15.754,
+      "eval_steps_per_second": 1.587,
+      "step": 600
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 4.412845702454024e-05,
+      "loss": 0.4739,
+      "step": 610
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 4.394168420572349e-05,
+      "loss": 0.4529,
+      "step": 620
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 4.3752395669658086e-05,
+      "loss": 0.4433,
+      "step": 630
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.356061655647571e-05,
+      "loss": 0.459,
+      "step": 640
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 4.336637233709107e-05,
+      "loss": 0.4877,
+      "step": 650
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 4.316968880981903e-05,
+      "loss": 0.4676,
+      "step": 660
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 4.2970592096948236e-05,
+      "loss": 0.4782,
+      "step": 670
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.276910864127168e-05,
+      "loss": 0.4778,
+      "step": 680
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 4.25652652025748e-05,
+      "loss": 0.454,
+      "step": 690
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 4.235908885408133e-05,
+      "loss": 0.4399,
+      "step": 700
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 4.215060697885767e-05,
+      "loss": 0.5106,
+      "step": 710
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.1939847266176e-05,
+      "loss": 0.4683,
+      "step": 720
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.172683770783677e-05,
+      "loss": 0.4896,
+      "step": 730
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.1511606594451016e-05,
+      "loss": 0.4633,
+      "step": 740
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.1294182511682946e-05,
+      "loss": 0.4486,
+      "step": 750
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.1074594336453384e-05,
+      "loss": 0.4706,
+      "step": 760
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.085287123310455e-05,
+      "loss": 0.4797,
+      "step": 770
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.062904264952657e-05,
+      "loss": 0.4251,
+      "step": 780
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 4.0403138313246435e-05,
+      "loss": 0.4687,
+      "step": 790
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.017518822747976e-05,
+      "loss": 0.48,
+      "step": 800
+    },
+    {
+      "epoch": 0.59,
+      "eval_loss": 0.4554018974304199,
+      "eval_runtime": 70.2392,
+      "eval_samples_per_second": 15.689,
+      "eval_steps_per_second": 1.58,
+      "step": 800
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 3.994522266714594e-05,
+      "loss": 0.4662,
+      "step": 810
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 3.9713272174847246e-05,
+      "loss": 0.4837,
+      "step": 820
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 3.947936755681229e-05,
+      "loss": 0.5014,
+      "step": 830
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 3.92435398788046e-05,
+      "loss": 0.4764,
+      "step": 840
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 3.9005820461996604e-05,
+      "loss": 0.4587,
+      "step": 850
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 3.876624087880979e-05,
+      "loss": 0.484,
+      "step": 860
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.85248329487214e-05,
+      "loss": 0.4285,
+      "step": 870
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.828162873403843e-05,
+      "loss": 0.4742,
+      "step": 880
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.803666053563926e-05,
+      "loss": 0.4533,
+      "step": 890
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 3.778996088868365e-05,
+      "loss": 0.4395,
+      "step": 900
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 3.754156255829167e-05,
+      "loss": 0.4519,
+      "step": 910
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 3.7291498535191996e-05,
+      "loss": 0.4684,
+      "step": 920
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 3.703980203134029e-05,
+      "loss": 0.4259,
+      "step": 930
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 3.678650647550822e-05,
+      "loss": 0.4576,
+      "step": 940
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 3.6531645508843636e-05,
+      "loss": 0.446,
+      "step": 950
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 3.6275252980402544e-05,
+      "loss": 0.4439,
+      "step": 960
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 3.601736294265354e-05,
+      "loss": 0.476,
+      "step": 970
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.5758009646955115e-05,
+      "loss": 0.4153,
+      "step": 980
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.5497227539006614e-05,
+      "loss": 0.4444,
+      "step": 990
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.523505125427341e-05,
+      "loss": 0.4395,
+      "step": 1000
+    },
+    {
+      "epoch": 0.73,
+      "eval_loss": 0.44357746839523315,
+      "eval_runtime": 70.1513,
+      "eval_samples_per_second": 15.709,
+      "eval_steps_per_second": 1.582,
+      "step": 1000
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.497151561338678e-05,
+      "loss": 0.4387,
+      "step": 1010
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.470665561751928e-05,
+      "loss": 0.4559,
+      "step": 1020
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 3.444050644373611e-05,
+      "loss": 0.4349,
+      "step": 1030
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 3.417310344032309e-05,
+      "loss": 0.4661,
+      "step": 1040
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.390448212209191e-05,
+      "loss": 0.4945,
+      "step": 1050
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.3634678165663325e-05,
+      "loss": 0.4399,
+      "step": 1060
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.336372740472877e-05,
+      "loss": 0.4399,
+      "step": 1070
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 3.309166582529114e-05,
+      "loss": 0.4251,
+      "step": 1080
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 3.281852956088537e-05,
+      "loss": 0.4385,
+      "step": 1090
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 3.254435488777941e-05,
+      "loss": 0.4566,
+      "step": 1100
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 3.226917822015623e-05,
+      "loss": 0.4352,
+      "step": 1110
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.199303610527749e-05,
+      "loss": 0.4617,
+      "step": 1120
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.1715965218629595e-05,
+      "loss": 0.476,
+      "step": 1130
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.143800235905268e-05,
+      "loss": 0.4322,
+      "step": 1140
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.115918444385315e-05,
+      "loss": 0.4736,
+      "step": 1150
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.0879548503900665e-05,
+      "loss": 0.4322,
+      "step": 1160
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 3.0599131678709836e-05,
+      "loss": 0.4152,
+      "step": 1170
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 3.031797121150764e-05,
+      "loss": 0.4187,
+      "step": 1180
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 3.0036104444286954e-05,
+      "loss": 0.4331,
+      "step": 1190
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 2.9753568812847065e-05,
+      "loss": 0.45,
+      "step": 1200
+    },
+    {
+      "epoch": 0.88,
+      "eval_loss": 0.43782830238342285,
+      "eval_runtime": 70.0939,
+      "eval_samples_per_second": 15.722,
+      "eval_steps_per_second": 1.584,
+      "step": 1200
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 2.9470401841821686e-05,
+      "loss": 0.4457,
+      "step": 1210
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 2.9186641139695108e-05,
+      "loss": 0.4667,
+      "step": 1220
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 2.8902324393807333e-05,
+      "loss": 0.4516,
+      "step": 1230
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 2.861748936534867e-05,
+      "loss": 0.4695,
+      "step": 1240
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.8332173884344477e-05,
+      "loss": 0.45,
+      "step": 1250
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.8046415844630857e-05,
+      "loss": 0.4246,
+      "step": 1260
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.7760253198821822e-05,
+      "loss": 0.4449,
+      "step": 1270
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.7473723953268687e-05,
+      "loss": 0.4217,
+      "step": 1280
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.7186866163012232e-05,
+      "loss": 0.4495,
+      "step": 1290
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.6899717926728535e-05,
+      "loss": 0.4523,
+      "step": 1300
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.6612317381668915e-05,
+      "loss": 0.4523,
+      "step": 1310
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.632470269859478e-05,
+      "loss": 0.45,
+      "step": 1320
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.603691207670803e-05,
+      "loss": 0.4371,
+      "step": 1330
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.5748983738577653e-05,
+      "loss": 0.4221,
+      "step": 1340
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.5460955925063268e-05,
+      "loss": 0.4565,
+      "step": 1350
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.5172866890236203e-05,
+      "loss": 0.3892,
+      "step": 1360
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.48847548962988e-05,
+      "loss": 0.3973,
+      "step": 1370
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 2.4596658208502713e-05,
+      "loss": 0.4151,
+      "step": 1380
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 2.4308615090066735e-05,
+      "loss": 0.3839,
+      "step": 1390
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 2.4020663797094864e-05,
+      "loss": 0.4062,
+      "step": 1400
+    },
+    {
+      "epoch": 1.03,
+      "eval_loss": 0.43284282088279724,
+      "eval_runtime": 70.1658,
+      "eval_samples_per_second": 15.706,
+      "eval_steps_per_second": 1.582,
+      "step": 1400
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 2.373284257349544e-05,
+      "loss": 0.4003,
+      "step": 1410
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 2.3445189645901806e-05,
+      "loss": 0.4447,
+      "step": 1420
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 2.3157743218595247e-05,
+      "loss": 0.4565,
+      "step": 1430
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 2.287054146843097e-05,
+      "loss": 0.4265,
+      "step": 1440
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 2.2583622539767668e-05,
+      "loss": 0.4056,
+      "step": 1450
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 2.2297024539401463e-05,
+      "loss": 0.4074,
+      "step": 1460
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 2.2010785531504716e-05,
+      "loss": 0.4281,
+      "step": 1470
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 2.172494353257066e-05,
+      "loss": 0.4663,
+      "step": 1480
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 2.1439536506364274e-05,
+      "loss": 0.4281,
+      "step": 1490
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 2.1154602358880122e-05,
+      "loss": 0.4111,
+      "step": 1500
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 2.0870178933307948e-05,
+      "loss": 0.4187,
+      "step": 1510
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 2.0586304005006585e-05,
+      "loss": 0.3964,
+      "step": 1520
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 2.030301527648684e-05,
+      "loss": 0.4331,
+      "step": 1530
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 2.0020350372404102e-05,
+      "loss": 0.4432,
+      "step": 1540
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.9738346834561254e-05,
+      "loss": 0.4056,
+      "step": 1550
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.945704211692262e-05,
+      "loss": 0.4354,
+      "step": 1560
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.9176473580639538e-05,
+      "loss": 0.4309,
+      "step": 1570
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.8896678489088304e-05,
+      "loss": 0.4058,
+      "step": 1580
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.8617694002921064e-05,
+      "loss": 0.4319,
+      "step": 1590
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.8339557175130383e-05,
+      "loss": 0.4267,
+      "step": 1600
+    },
+    {
+      "epoch": 1.17,
+      "eval_loss": 0.42894992232322693,
+      "eval_runtime": 70.251,
+      "eval_samples_per_second": 15.687,
+      "eval_steps_per_second": 1.58,
+      "step": 1600
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.8062304946128073e-05,
+      "loss": 0.3921,
+      "step": 1610
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.7785974138839018e-05,
+      "loss": 0.4206,
+      "step": 1620
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.7510601453810594e-05,
+      "loss": 0.4356,
+      "step": 1630
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.723622346433828e-05,
+      "loss": 0.4167,
+      "step": 1640
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.6962876611608262e-05,
+      "loss": 0.4233,
+      "step": 1650
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.6690597199857523e-05,
+      "loss": 0.4176,
+      "step": 1660
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.6419421391552142e-05,
+      "loss": 0.4241,
+      "step": 1670
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.6149385202584423e-05,
+      "loss": 0.4524,
+      "step": 1680
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.5880524497489474e-05,
+      "loss": 0.4647,
+      "step": 1690
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.5612874984681923e-05,
+      "loss": 0.4036,
+      "step": 1700
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.534647221171334e-05,
+      "loss": 0.4148,
+      "step": 1710
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.5081351560551021e-05,
+      "loss": 0.408,
+      "step": 1720
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.4817548242878759e-05,
+      "loss": 0.457,
+      "step": 1730
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.45550972954203e-05,
+      "loss": 0.4193,
+      "step": 1740
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.4294033575285914e-05,
+      "loss": 0.4149,
+      "step": 1750
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.4034391755342972e-05,
+      "loss": 0.4032,
+      "step": 1760
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.3776206319610823e-05,
+      "loss": 0.4078,
+      "step": 1770
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.3519511558680892e-05,
+      "loss": 0.4123,
+      "step": 1780
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.3264341565162422e-05,
+      "loss": 0.4089,
+      "step": 1790
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.3010730229154445e-05,
+      "loss": 0.383,
+      "step": 1800
+    },
+    {
+      "epoch": 1.32,
+      "eval_loss": 0.4250344932079315,
+      "eval_runtime": 70.4814,
+      "eval_samples_per_second": 15.635,
+      "eval_steps_per_second": 1.575,
+      "step": 1800
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.2758711233744783e-05,
+      "loss": 0.3936,
+      "step": 1810
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.2508318050536421e-05,
+      "loss": 0.4127,
+      "step": 1820
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.2259583935202062e-05,
+      "loss": 0.4015,
+      "step": 1830
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.2012541923067244e-05,
+      "loss": 0.4203,
+      "step": 1840
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.176722482472286e-05,
+      "loss": 0.4367,
+      "step": 1850
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.1523665221667398e-05,
+      "loss": 0.4233,
+      "step": 1860
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.1281895461979732e-05,
+      "loss": 0.4405,
+      "step": 1870
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.104194765602281e-05,
+      "loss": 0.4379,
+      "step": 1880
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.0803853672178946e-05,
+      "loss": 0.4146,
+      "step": 1890
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.0567645132617316e-05,
+      "loss": 0.4438,
+      "step": 1900
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.0333353409094015e-05,
+      "loss": 0.3915,
+      "step": 1910
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.0101009618785528e-05,
+      "loss": 0.4063,
+      "step": 1920
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 9.870644620155877e-06,
+      "loss": 0.3974,
+      "step": 1930
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 9.642289008858244e-06,
+      "loss": 0.4015,
+      "step": 1940
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 9.41597311367142e-06,
+      "loss": 0.4264,
+      "step": 1950
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 9.191726992471725e-06,
+      "loss": 0.4334,
+      "step": 1960
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 8.969580428240903e-06,
+      "loss": 0.4197,
+      "step": 1970
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 8.74956292511056e-06,
+      "loss": 0.422,
+      "step": 1980
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 8.531703704443575e-06,
+      "loss": 0.4077,
+      "step": 1990
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 8.316031700953086e-06,
+      "loss": 0.4334,
+      "step": 2000
+    },
+    {
+      "epoch": 1.47,
+      "eval_loss": 0.4206145107746124,
+      "eval_runtime": 70.0533,
+      "eval_samples_per_second": 15.731,
+      "eval_steps_per_second": 1.585,
+      "step": 2000
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 8.102575558859612e-06,
+      "loss": 0.4171,
+      "step": 2010
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 7.891363628086671e-06,
+      "loss": 0.3957,
+      "step": 2020
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 7.682423960495517e-06,
+      "loss": 0.4174,
+      "step": 2030
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 7.475784306159478e-06,
+      "loss": 0.4187,
+      "step": 2040
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 7.271472109678379e-06,
+      "loss": 0.3775,
+      "step": 2050
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 7.0695145065334585e-06,
+      "loss": 0.4019,
+      "step": 2060
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 6.869938319483471e-06,
+      "loss": 0.4143,
+      "step": 2070
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 6.67277005500222e-06,
+      "loss": 0.3853,
+      "step": 2080
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 6.478035899758139e-06,
+      "loss": 0.4403,
+      "step": 2090
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 6.285761717136335e-06,
+      "loss": 0.3888,
+      "step": 2100
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 6.095973043803577e-06,
+      "loss": 0.4123,
+      "step": 2110
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 5.908695086316701e-06,
+      "loss": 0.4035,
+      "step": 2120
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 5.723952717774763e-06,
+      "loss": 0.4219,
+      "step": 2130
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 5.54177047451562e-06,
+      "loss": 0.4209,
+      "step": 2140
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 5.362172552857128e-06,
+      "loss": 0.4286,
+      "step": 2150
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 5.18518280588354e-06,
+      "loss": 0.4134,
+      "step": 2160
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 5.010824740277501e-06,
+      "loss": 0.4005,
+      "step": 2170
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 4.83912151319802e-06,
+      "loss": 0.3973,
+      "step": 2180
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 4.6700959292048875e-06,
+      "loss": 0.3959,
+      "step": 2190
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 4.503770437229918e-06,
+      "loss": 0.4017,
+      "step": 2200
+    },
+    {
+      "epoch": 1.61,
+      "eval_loss": 0.41970890760421753,
+      "eval_runtime": 69.9019,
+      "eval_samples_per_second": 15.765,
+      "eval_steps_per_second": 1.588,
+      "step": 2200
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 4.340167127595407e-06,
+      "loss": 0.4013,
+      "step": 2210
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 4.179307729080256e-06,
+      "loss": 0.4069,
+      "step": 2220
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 4.021213606034064e-06,
+      "loss": 0.3857,
+      "step": 2230
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 3.8659057555396645e-06,
+      "loss": 0.4262,
+      "step": 2240
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 3.713404804624418e-06,
+      "loss": 0.3953,
+      "step": 2250
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 3.5637310075206544e-06,
+      "loss": 0.4231,
+      "step": 2260
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 3.416904242975635e-06,
+      "loss": 0.407,
+      "step": 2270
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 3.2729440116113843e-06,
+      "loss": 0.4254,
+      "step": 2280
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 3.131869433334725e-06,
+      "loss": 0.4054,
+      "step": 2290
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 2.9936992447979068e-06,
+      "loss": 0.3801,
+      "step": 2300
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 2.8584517969101054e-06,
+      "loss": 0.4335,
+      "step": 2310
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 2.7261450524001807e-06,
+      "loss": 0.412,
+      "step": 2320
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 2.596796583430969e-06,
+      "loss": 0.4456,
+      "step": 2330
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 2.470423569265462e-06,
+      "loss": 0.3972,
+      "step": 2340
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 2.34704279398516e-06,
+      "loss": 0.3935,
+      "step": 2350
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 2.2266706442609226e-06,
+      "loss": 0.3974,
+      "step": 2360
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 2.109323107176578e-06,
+      "loss": 0.4157,
+      "step": 2370
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 1.9950157681056318e-06,
+      "loss": 0.4379,
+      "step": 2380
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 1.8837638086413063e-06,
+      "loss": 0.4035,
+      "step": 2390
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 1.7755820045802145e-06,
+      "loss": 0.4455,
+      "step": 2400
+    },
+    {
+      "epoch": 1.76,
+      "eval_loss": 0.41885045170783997,
+      "eval_runtime": 70.0957,
+      "eval_samples_per_second": 15.721,
+      "eval_steps_per_second": 1.584,
+      "step": 2400
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 1.6704847239599364e-06,
+      "loss": 0.4532,
+      "step": 2410
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 1.5684859251507394e-06,
+      "loss": 0.4213,
+      "step": 2420
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 1.4695991550017164e-06,
+      "loss": 0.3873,
+      "step": 2430
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 1.373837547041576e-06,
+      "loss": 0.4163,
+      "step": 2440
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 1.2812138197343392e-06,
+      "loss": 0.3946,
+      "step": 2450
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 1.1917402747901152e-06,
+      "loss": 0.41,
+      "step": 2460
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 1.105428795531327e-06,
+      "loss": 0.4126,
+      "step": 2470
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 1.0222908453143804e-06,
+      "loss": 0.4505,
+      "step": 2480
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 9.423374660072065e-07,
+      "loss": 0.4303,
+      "step": 2490
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 8.655792765227405e-07,
+      "loss": 0.4179,
+      "step": 2500
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 7.920264714085828e-07,
+      "loss": 0.4376,
+      "step": 2510
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 7.216888194930272e-07,
+      "loss": 0.4069,
+      "step": 2520
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 6.545756625876031e-07,
+      "loss": 0.3887,
+      "step": 2530
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 5.906959142463947e-07,
+      "loss": 0.3972,
+      "step": 2540
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 5.300580585821696e-07,
+      "loss": 0.4078,
+      "step": 2550
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 4.7267014913956463e-07,
+      "loss": 0.4467,
+      "step": 2560
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 4.1853980782549097e-07,
+      "loss": 0.4567,
+      "step": 2570
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 3.6767422389682173e-07,
+      "loss": 0.4494,
+      "step": 2580
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 3.2008015300555306e-07,
+      "loss": 0.4344,
+      "step": 2590
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 2.757639163015774e-07,
+      "loss": 0.4101,
+      "step": 2600
+    },
+    {
+      "epoch": 1.91,
+      "eval_loss": 0.41886425018310547,
+      "eval_runtime": 70.2179,
+      "eval_samples_per_second": 15.694,
+      "eval_steps_per_second": 1.581,
+      "step": 2600
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 2.347313995931466e-07,
+      "loss": 0.4058,
+      "step": 2610
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.9698805256513908e-07,
+      "loss": 0.414,
+      "step": 2620
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 1.6253888805527474e-07,
+      "loss": 0.4254,
+      "step": 2630
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.3138848138835313e-07,
+      "loss": 0.4017,
+      "step": 2640
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.0354096976856186e-07,
+      "loss": 0.4258,
+      "step": 2650
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 7.900005173002712e-08,
+      "loss": 0.4098,
+      "step": 2660
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 5.776898664557051e-08,
+      "loss": 0.42,
+      "step": 2670
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 3.985059429383875e-08,
+      "loss": 0.3886,
+      "step": 2680
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 2.5247254484794813e-08,
+      "loss": 0.4276,
+      "step": 2690
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 1.3960906743634706e-08,
+      "loss": 0.4006,
+      "step": 2700
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 5.993050053204607e-09,
+      "loss": 0.4243,
+      "step": 2710
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.3447426549129117e-09,
+      "loss": 0.4439,
+      "step": 2720
+    },
+    {
+      "epoch": 2.0,
+      "step": 2726,
+      "total_flos": 1.1289170586615415e+19,
+      "train_loss": 0.46561298847898175,
+      "train_runtime": 35477.4141,
+      "train_samples_per_second": 6.149,
+      "train_steps_per_second": 0.077
+    }
+  ],
+  "max_steps": 2726,
+  "num_train_epochs": 2,
+  "total_flos": 1.1289170586615415e+19,
+  "trial_name": null,
+  "trial_params": null
+}

Baichuan-13B-Chat-lora-Task/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0037c3e69fa21891dd65687a3f79ad20a8abc0a75790c554b437378b35c59fe9
+size 4600