Upload 13 files

README.md

@@ -1,3 +1,207 @@
 ---
-license: apache-2.0
+library_name: peft
+base_model: /DATA4T/text-generation-webui/models/Yi-34B
 ---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Data Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+## Training procedure
+
+
+### Framework versions
+
+
+- PEFT 0.7.0.dev0

adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/DATA4T/text-generation-webui/models/Yi-34B",
+  "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,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "q_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02f40a159b1882104fcba402e99ee114ef7b44964b5b86e2b9ebd5205f42c70e
+size 123170349

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "train_loss": 1.0705227502962438,
+    "train_runtime": 220133.6189,
+    "train_samples_per_second": 1.019,
+    "train_steps_per_second": 0.011
+}

special_tokens_map.json

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

tokenization_yi.py

@@ -0,0 +1,255 @@
+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 YiTokenizer(PreTrainedTokenizer):
+    """
+    Construct a Yi 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="<|startoftext|>",
+        eos_token="<|endoftext|>",
+        pad_token="<unk>",
+        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
+        )
+        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)
+        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,
+        )
+
+    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

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
+size 1033105

tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_yi.YiTokenizer",
+      null
+    ]
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 4096,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "YiTokenizer",
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "train_loss": 1.0705227502962438,
+    "train_runtime": 220133.6189,
+    "train_samples_per_second": 1.019,
+    "train_steps_per_second": 0.011
+}

trainer_log.jsonl

@@ -0,0 +1,234 @@
+{"current_steps": 10, "total_steps": 2337, "loss": 1.9904, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9999096463326385e-06, "epoch": 0.01, "percentage": 0.43, "elapsed_time": "0:16:01", "remaining_time": "2 days, 14:10:39"}
+{"current_steps": 20, "total_steps": 2337, "loss": 1.9027, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9996386016581256e-06, "epoch": 0.03, "percentage": 0.86, "elapsed_time": "0:31:44", "remaining_time": "2 days, 13:17:40"}
+{"current_steps": 30, "total_steps": 2337, "loss": 1.8885, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9991869149562214e-06, "epoch": 0.04, "percentage": 1.28, "elapsed_time": "0:47:26", "remaining_time": "2 days, 12:47:53"}
+{"current_steps": 40, "total_steps": 2337, "loss": 1.9943, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9985546678500257e-06, "epoch": 0.05, "percentage": 1.71, "elapsed_time": "1:03:06", "remaining_time": "2 days, 12:24:28"}
+{"current_steps": 50, "total_steps": 2337, "loss": 1.9145, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.997741974591229e-06, "epoch": 0.06, "percentage": 2.14, "elapsed_time": "1:18:47", "remaining_time": "2 days, 12:03:39"}
+{"current_steps": 60, "total_steps": 2337, "loss": 1.9079, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9967489820394627e-06, "epoch": 0.08, "percentage": 2.57, "elapsed_time": "1:34:27", "remaining_time": "2 days, 11:44:49"}
+{"current_steps": 70, "total_steps": 2337, "loss": 1.8246, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.995575869635765e-06, "epoch": 0.09, "percentage": 3.0, "elapsed_time": "1:50:08", "remaining_time": "2 days, 11:26:51"}
+{"current_steps": 80, "total_steps": 2337, "loss": 1.759, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.994222849370152e-06, "epoch": 0.1, "percentage": 3.42, "elapsed_time": "2:05:48", "remaining_time": "2 days, 11:09:13"}
+{"current_steps": 90, "total_steps": 2337, "loss": 1.6747, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9926901657433085e-06, "epoch": 0.12, "percentage": 3.85, "elapsed_time": "2:21:28", "remaining_time": "2 days, 10:52:19"}
+{"current_steps": 100, "total_steps": 2337, "loss": 1.5992, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.990978095722409e-06, "epoch": 0.13, "percentage": 4.28, "elapsed_time": "2:37:10", "remaining_time": "2 days, 10:35:57"}
+{"current_steps": 110, "total_steps": 2337, "loss": 1.5288, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9890869486910627e-06, "epoch": 0.14, "percentage": 4.71, "elapsed_time": "2:52:52", "remaining_time": "2 days, 10:19:47"}
+{"current_steps": 120, "total_steps": 2337, "loss": 1.5143, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9870170663934104e-06, "epoch": 0.15, "percentage": 5.13, "elapsed_time": "3:08:35", "remaining_time": "2 days, 10:04:08"}
+{"current_steps": 130, "total_steps": 2337, "loss": 1.4542, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9847688228723645e-06, "epoch": 0.17, "percentage": 5.56, "elapsed_time": "3:24:15", "remaining_time": "2 days, 9:47:45"}
+{"current_steps": 140, "total_steps": 2337, "loss": 1.4081, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9823426244020197e-06, "epoch": 0.18, "percentage": 5.99, "elapsed_time": "3:39:59", "remaining_time": "2 days, 9:32:17"}
+{"current_steps": 150, "total_steps": 2337, "loss": 1.377, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.979738909414235e-06, "epoch": 0.19, "percentage": 6.42, "elapsed_time": "3:55:41", "remaining_time": "2 days, 9:16:21"}
+{"current_steps": 160, "total_steps": 2337, "loss": 1.3373, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9769581484194063e-06, "epoch": 0.21, "percentage": 6.85, "elapsed_time": "4:11:23", "remaining_time": "2 days, 9:00:28"}
+{"current_steps": 170, "total_steps": 2337, "loss": 1.3031, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9740008439214417e-06, "epoch": 0.22, "percentage": 7.27, "elapsed_time": "4:27:04", "remaining_time": "2 days, 8:44:25"}
+{"current_steps": 180, "total_steps": 2337, "loss": 1.3004, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9708675303269545e-06, "epoch": 0.23, "percentage": 7.7, "elapsed_time": "4:42:45", "remaining_time": "2 days, 8:28:21"}
+{"current_steps": 190, "total_steps": 2337, "loss": 1.2555, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9675587738486934e-06, "epoch": 0.24, "percentage": 8.13, "elapsed_time": "4:58:26", "remaining_time": "2 days, 8:12:26"}
+{"current_steps": 200, "total_steps": 2337, "loss": 1.277, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9640751724032234e-06, "epoch": 0.26, "percentage": 8.56, "elapsed_time": "5:14:08", "remaining_time": "2 days, 7:56:40"}
+{"current_steps": 210, "total_steps": 2337, "loss": 1.2142, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.960417355502876e-06, "epoch": 0.27, "percentage": 8.99, "elapsed_time": "5:29:52", "remaining_time": "2 days, 7:41:08"}
+{"current_steps": 220, "total_steps": 2337, "loss": 1.2023, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9565859841419945e-06, "epoch": 0.28, "percentage": 9.41, "elapsed_time": "5:45:32", "remaining_time": "2 days, 7:25:07"}
+{"current_steps": 230, "total_steps": 2337, "loss": 1.2301, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9525817506774864e-06, "epoch": 0.3, "percentage": 9.84, "elapsed_time": "6:01:16", "remaining_time": "2 days, 7:09:31"}
+{"current_steps": 240, "total_steps": 2337, "loss": 1.217, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.948405378703708e-06, "epoch": 0.31, "percentage": 10.27, "elapsed_time": "6:16:56", "remaining_time": "2 days, 6:53:32"}
+{"current_steps": 250, "total_steps": 2337, "loss": 1.1637, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9440576229217078e-06, "epoch": 0.32, "percentage": 10.7, "elapsed_time": "6:32:36", "remaining_time": "2 days, 6:37:32"}
+{"current_steps": 260, "total_steps": 2337, "loss": 1.214, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.939539269002845e-06, "epoch": 0.33, "percentage": 11.13, "elapsed_time": "6:48:16", "remaining_time": "2 days, 6:21:29"}
+{"current_steps": 270, "total_steps": 2337, "loss": 1.1571, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9348511334468137e-06, "epoch": 0.35, "percentage": 11.55, "elapsed_time": "7:03:56", "remaining_time": "2 days, 6:05:28"}
+{"current_steps": 280, "total_steps": 2337, "loss": 1.1329, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9299940634340954e-06, "epoch": 0.36, "percentage": 11.98, "elapsed_time": "7:19:37", "remaining_time": "2 days, 5:49:37"}
+{"current_steps": 290, "total_steps": 2337, "loss": 1.1524, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9249689366728658e-06, "epoch": 0.37, "percentage": 12.41, "elapsed_time": "7:35:17", "remaining_time": "2 days, 5:33:46"}
+{"current_steps": 300, "total_steps": 2337, "loss": 1.1853, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.91977666124039e-06, "epoch": 0.39, "percentage": 12.84, "elapsed_time": "7:50:57", "remaining_time": "2 days, 5:17:50"}
+{"current_steps": 310, "total_steps": 2337, "loss": 1.1614, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9144181754189207e-06, "epoch": 0.4, "percentage": 13.26, "elapsed_time": "8:06:38", "remaining_time": "2 days, 5:02:01"}
+{"current_steps": 320, "total_steps": 2337, "loss": 1.1166, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.90889444752615e-06, "epoch": 0.41, "percentage": 13.69, "elapsed_time": "8:22:20", "remaining_time": "2 days, 4:46:19"}
+{"current_steps": 330, "total_steps": 2337, "loss": 1.1298, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.903206475740223e-06, "epoch": 0.42, "percentage": 14.12, "elapsed_time": "8:38:00", "remaining_time": "2 days, 4:30:27"}
+{"current_steps": 340, "total_steps": 2337, "loss": 1.1577, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8973552879193612e-06, "epoch": 0.44, "percentage": 14.55, "elapsed_time": "8:53:41", "remaining_time": "2 days, 4:14:36"}
+{"current_steps": 350, "total_steps": 2337, "loss": 1.1421, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8913419414161202e-06, "epoch": 0.45, "percentage": 14.98, "elapsed_time": "9:09:23", "remaining_time": "2 days, 3:58:59"}
+{"current_steps": 360, "total_steps": 2337, "loss": 1.1569, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.88516752288632e-06, "epoch": 0.46, "percentage": 15.4, "elapsed_time": "9:25:04", "remaining_time": "2 days, 3:43:09"}
+{"current_steps": 370, "total_steps": 2337, "loss": 1.0961, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8788331480926763e-06, "epoch": 0.47, "percentage": 15.83, "elapsed_time": "9:40:44", "remaining_time": "2 days, 3:27:18"}
+{"current_steps": 380, "total_steps": 2337, "loss": 1.1173, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.872339961703175e-06, "epoch": 0.49, "percentage": 16.26, "elapsed_time": "9:56:24", "remaining_time": "2 days, 3:11:29"}
+{"current_steps": 390, "total_steps": 2337, "loss": 1.0712, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8656891370842223e-06, "epoch": 0.5, "percentage": 16.69, "elapsed_time": "10:12:07", "remaining_time": "2 days, 2:55:54"}
+{"current_steps": 400, "total_steps": 2337, "loss": 1.1055, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8588818760886094e-06, "epoch": 0.51, "percentage": 17.12, "elapsed_time": "10:27:47", "remaining_time": "2 days, 2:40:05"}
+{"current_steps": 410, "total_steps": 2337, "loss": 1.1006, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.851919408838327e-06, "epoch": 0.53, "percentage": 17.54, "elapsed_time": "10:43:30", "remaining_time": "2 days, 2:24:29"}
+{"current_steps": 420, "total_steps": 2337, "loss": 1.083, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8448029935022754e-06, "epoch": 0.54, "percentage": 17.97, "elapsed_time": "10:59:11", "remaining_time": "2 days, 2:08:43"}
+{"current_steps": 430, "total_steps": 2337, "loss": 1.0588, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8375339160689023e-06, "epoch": 0.55, "percentage": 18.4, "elapsed_time": "11:14:51", "remaining_time": "2 days, 1:52:53"}
+{"current_steps": 440, "total_steps": 2337, "loss": 1.0791, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.830113490113817e-06, "epoch": 0.56, "percentage": 18.83, "elapsed_time": "11:30:31", "remaining_time": "2 days, 1:37:08"}
+{"current_steps": 450, "total_steps": 2337, "loss": 1.0623, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.822543056562416e-06, "epoch": 0.58, "percentage": 19.26, "elapsed_time": "11:46:12", "remaining_time": "2 days, 1:21:20"}
+{"current_steps": 460, "total_steps": 2337, "loss": 1.1126, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8148239834475695e-06, "epoch": 0.59, "percentage": 19.68, "elapsed_time": "12:01:52", "remaining_time": "2 days, 1:05:34"}
+{"current_steps": 470, "total_steps": 2337, "loss": 1.0696, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.806957665662406e-06, "epoch": 0.6, "percentage": 20.11, "elapsed_time": "12:17:32", "remaining_time": "2 days, 0:49:44"}
+{"current_steps": 480, "total_steps": 2337, "loss": 1.0573, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7989455247082472e-06, "epoch": 0.62, "percentage": 20.54, "elapsed_time": "12:33:11", "remaining_time": "2 days, 0:33:54"}
+{"current_steps": 490, "total_steps": 2337, "loss": 1.0789, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7907890084377301e-06, "epoch": 0.63, "percentage": 20.97, "elapsed_time": "12:48:51", "remaining_time": "2 days, 0:18:07"}
+{"current_steps": 500, "total_steps": 2337, "loss": 1.0964, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7824895907931706e-06, "epoch": 0.64, "percentage": 21.39, "elapsed_time": "13:04:33", "remaining_time": "2 days, 0:02:26"}
+{"current_steps": 510, "total_steps": 2337, "loss": 1.0551, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7740487715402106e-06, "epoch": 0.65, "percentage": 21.82, "elapsed_time": "13:20:12", "remaining_time": "1 day, 23:46:39"}
+{"current_steps": 520, "total_steps": 2337, "loss": 1.0563, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7654680759968007e-06, "epoch": 0.67, "percentage": 22.25, "elapsed_time": "13:35:53", "remaining_time": "1 day, 23:30:55"}
+{"current_steps": 530, "total_steps": 2337, "loss": 1.0522, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.756749054757562e-06, "epoch": 0.68, "percentage": 22.68, "elapsed_time": "13:51:33", "remaining_time": "1 day, 23:15:08"}
+{"current_steps": 540, "total_steps": 2337, "loss": 1.0446, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.747893283413585e-06, "epoch": 0.69, "percentage": 23.11, "elapsed_time": "14:07:13", "remaining_time": "1 day, 22:59:23"}
+{"current_steps": 550, "total_steps": 2337, "loss": 1.0667, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.738902362267705e-06, "epoch": 0.71, "percentage": 23.53, "elapsed_time": "14:22:54", "remaining_time": "1 day, 22:43:39"}
+{"current_steps": 560, "total_steps": 2337, "loss": 1.0395, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.72977791604532e-06, "epoch": 0.72, "percentage": 23.96, "elapsed_time": "14:38:33", "remaining_time": "1 day, 22:27:51"}
+{"current_steps": 570, "total_steps": 2337, "loss": 1.039, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7205215936007869e-06, "epoch": 0.73, "percentage": 24.39, "elapsed_time": "14:54:12", "remaining_time": "1 day, 22:12:03"}
+{"current_steps": 580, "total_steps": 2337, "loss": 1.0987, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7111350676194647e-06, "epoch": 0.74, "percentage": 24.82, "elapsed_time": "15:09:53", "remaining_time": "1 day, 21:56:19"}
+{"current_steps": 590, "total_steps": 2337, "loss": 1.0748, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.701620034315445e-06, "epoch": 0.76, "percentage": 25.25, "elapsed_time": "15:25:34", "remaining_time": "1 day, 21:40:38"}
+{"current_steps": 600, "total_steps": 2337, "loss": 1.0446, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6919782131250366e-06, "epoch": 0.77, "percentage": 25.67, "elapsed_time": "15:41:16", "remaining_time": "1 day, 21:24:58"}
+{"current_steps": 610, "total_steps": 2337, "loss": 1.0279, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6822113463960483e-06, "epoch": 0.78, "percentage": 26.1, "elapsed_time": "15:56:58", "remaining_time": "1 day, 21:09:19"}
+{"current_steps": 620, "total_steps": 2337, "loss": 1.054, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6723211990729355e-06, "epoch": 0.8, "percentage": 26.53, "elapsed_time": "16:12:38", "remaining_time": "1 day, 20:53:36"}
+{"current_steps": 630, "total_steps": 2337, "loss": 1.0391, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6623095583778613e-06, "epoch": 0.81, "percentage": 26.96, "elapsed_time": "16:28:18", "remaining_time": "1 day, 20:37:51"}
+{"current_steps": 640, "total_steps": 2337, "loss": 1.0812, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.652178233487731e-06, "epoch": 0.82, "percentage": 27.39, "elapsed_time": "16:43:58", "remaining_time": "1 day, 20:22:07"}
+{"current_steps": 650, "total_steps": 2337, "loss": 1.0826, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6419290552072634e-06, "epoch": 0.83, "percentage": 27.81, "elapsed_time": "16:59:39", "remaining_time": "1 day, 20:06:23"}
+{"current_steps": 660, "total_steps": 2337, "loss": 1.0497, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6315638756381484e-06, "epoch": 0.85, "percentage": 28.24, "elapsed_time": "17:15:18", "remaining_time": "1 day, 19:50:37"}
+{"current_steps": 670, "total_steps": 2337, "loss": 1.0329, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6210845678443602e-06, "epoch": 0.86, "percentage": 28.67, "elapsed_time": "17:30:57", "remaining_time": "1 day, 19:34:51"}
+{"current_steps": 680, "total_steps": 2337, "loss": 1.0663, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6104930255136794e-06, "epoch": 0.87, "percentage": 29.1, "elapsed_time": "17:46:37", "remaining_time": "1 day, 19:19:07"}
+{"current_steps": 690, "total_steps": 2337, "loss": 1.059, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5997911626154914e-06, "epoch": 0.89, "percentage": 29.53, "elapsed_time": "18:02:18", "remaining_time": "1 day, 19:03:24"}
+{"current_steps": 700, "total_steps": 2337, "loss": 1.0123, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5889809130549174e-06, "epoch": 0.9, "percentage": 29.95, "elapsed_time": "18:17:57", "remaining_time": "1 day, 18:47:39"}
+{"current_steps": 710, "total_steps": 2337, "loss": 1.0264, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.578064230323343e-06, "epoch": 0.91, "percentage": 30.38, "elapsed_time": "18:33:38", "remaining_time": "1 day, 18:31:57"}
+{"current_steps": 720, "total_steps": 2337, "loss": 1.0411, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5670430871454081e-06, "epoch": 0.92, "percentage": 30.81, "elapsed_time": "18:49:18", "remaining_time": "1 day, 18:16:13"}
+{"current_steps": 730, "total_steps": 2337, "loss": 1.0428, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.555919475122523e-06, "epoch": 0.94, "percentage": 31.24, "elapsed_time": "19:04:58", "remaining_time": "1 day, 18:00:30"}
+{"current_steps": 740, "total_steps": 2337, "loss": 0.9994, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.544695404372968e-06, "epoch": 0.95, "percentage": 31.66, "elapsed_time": "19:20:38", "remaining_time": "1 day, 17:44:46"}
+{"current_steps": 750, "total_steps": 2337, "loss": 1.0452, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.533372903168653e-06, "epoch": 0.96, "percentage": 32.09, "elapsed_time": "19:36:18", "remaining_time": "1 day, 17:29:03"}
+{"current_steps": 760, "total_steps": 2337, "loss": 1.02, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5219540175685937e-06, "epoch": 0.98, "percentage": 32.52, "elapsed_time": "19:51:58", "remaining_time": "1 day, 17:13:20"}
+{"current_steps": 770, "total_steps": 2337, "loss": 1.0564, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5104408110491716e-06, "epoch": 0.99, "percentage": 32.95, "elapsed_time": "20:07:39", "remaining_time": "1 day, 16:57:39"}
+{"current_steps": 780, "total_steps": 2337, "loss": 0.9889, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4988353641312515e-06, "epoch": 1.0, "percentage": 33.38, "elapsed_time": "20:23:19", "remaining_time": "1 day, 16:41:56"}
+{"current_steps": 790, "total_steps": 2337, "loss": 1.0452, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.487139774004214e-06, "epoch": 1.01, "percentage": 33.8, "elapsed_time": "20:38:59", "remaining_time": "1 day, 16:26:13"}
+{"current_steps": 800, "total_steps": 2337, "loss": 1.0399, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4753561541469787e-06, "epoch": 1.03, "percentage": 34.23, "elapsed_time": "20:54:40", "remaining_time": "1 day, 16:10:31"}
+{"current_steps": 810, "total_steps": 2337, "loss": 1.0438, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.463486633946084e-06, "epoch": 1.04, "percentage": 34.66, "elapsed_time": "21:10:20", "remaining_time": "1 day, 15:54:50"}
+{"current_steps": 820, "total_steps": 2337, "loss": 1.0134, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4515333583108893e-06, "epoch": 1.05, "percentage": 35.09, "elapsed_time": "21:26:01", "remaining_time": "1 day, 15:39:08"}
+{"current_steps": 830, "total_steps": 2337, "loss": 0.9949, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.439498487285976e-06, "epoch": 1.07, "percentage": 35.52, "elapsed_time": "21:41:41", "remaining_time": "1 day, 15:23:26"}
+{"current_steps": 840, "total_steps": 2337, "loss": 1.0184, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.427384195660811e-06, "epoch": 1.08, "percentage": 35.94, "elapsed_time": "21:57:22", "remaining_time": "1 day, 15:07:44"}
+{"current_steps": 850, "total_steps": 2337, "loss": 1.0246, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4151926725767455e-06, "epoch": 1.09, "percentage": 36.37, "elapsed_time": "22:13:05", "remaining_time": "1 day, 14:52:06"}
+{"current_steps": 860, "total_steps": 2337, "loss": 1.0428, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4029261211314222e-06, "epoch": 1.1, "percentage": 36.8, "elapsed_time": "22:28:44", "remaining_time": "1 day, 14:36:22"}
+{"current_steps": 870, "total_steps": 2337, "loss": 1.0078, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3905867579806596e-06, "epoch": 1.12, "percentage": 37.23, "elapsed_time": "22:44:24", "remaining_time": "1 day, 14:20:40"}
+{"current_steps": 880, "total_steps": 2337, "loss": 1.0223, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3781768129378844e-06, "epoch": 1.13, "percentage": 37.66, "elapsed_time": "23:00:04", "remaining_time": "1 day, 14:04:58"}
+{"current_steps": 890, "total_steps": 2337, "loss": 0.9788, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3656985285711895e-06, "epoch": 1.14, "percentage": 38.08, "elapsed_time": "23:15:44", "remaining_time": "1 day, 13:49:16"}
+{"current_steps": 900, "total_steps": 2337, "loss": 1.0417, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3531541597980845e-06, "epoch": 1.16, "percentage": 38.51, "elapsed_time": "23:31:25", "remaining_time": "1 day, 13:33:33"}
+{"current_steps": 910, "total_steps": 2337, "loss": 1.0315, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.340545973478016e-06, "epoch": 1.17, "percentage": 38.94, "elapsed_time": "23:47:05", "remaining_time": "1 day, 13:17:52"}
+{"current_steps": 920, "total_steps": 2337, "loss": 0.9775, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.32787624800273e-06, "epoch": 1.18, "percentage": 39.37, "elapsed_time": "1 day, 0:02:46", "remaining_time": "1 day, 13:02:10"}
+{"current_steps": 930, "total_steps": 2337, "loss": 0.9992, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3151472728845492e-06, "epoch": 1.19, "percentage": 39.79, "elapsed_time": "1 day, 0:18:27", "remaining_time": "1 day, 12:46:30"}
+{"current_steps": 940, "total_steps": 2337, "loss": 0.957, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3023613483426399e-06, "epoch": 1.21, "percentage": 40.22, "elapsed_time": "1 day, 0:34:07", "remaining_time": "1 day, 12:30:48"}
+{"current_steps": 950, "total_steps": 2337, "loss": 1.0227, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2895207848873487e-06, "epoch": 1.22, "percentage": 40.65, "elapsed_time": "1 day, 0:49:48", "remaining_time": "1 day, 12:15:07"}
+{"current_steps": 960, "total_steps": 2337, "loss": 1.0311, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2766279029026735e-06, "epoch": 1.23, "percentage": 41.08, "elapsed_time": "1 day, 1:05:29", "remaining_time": "1 day, 11:59:26"}
+{"current_steps": 970, "total_steps": 2337, "loss": 1.0237, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2636850322269553e-06, "epoch": 1.25, "percentage": 41.51, "elapsed_time": "1 day, 1:21:10", "remaining_time": "1 day, 11:43:44"}
+{"current_steps": 980, "total_steps": 2337, "loss": 1.0338, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.250694511731857e-06, "epoch": 1.26, "percentage": 41.93, "elapsed_time": "1 day, 1:36:50", "remaining_time": "1 day, 11:28:03"}
+{"current_steps": 990, "total_steps": 2337, "loss": 1.0259, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2376586888997145e-06, "epoch": 1.27, "percentage": 42.36, "elapsed_time": "1 day, 1:52:31", "remaining_time": "1 day, 11:12:22"}
+{"current_steps": 1000, "total_steps": 2337, "loss": 1.0058, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.224579919399327e-06, "epoch": 1.28, "percentage": 42.79, "elapsed_time": "1 day, 2:08:12", "remaining_time": "1 day, 10:56:41"}
+{"current_steps": 1010, "total_steps": 2337, "loss": 0.9968, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2114605666602728e-06, "epoch": 1.3, "percentage": 43.22, "elapsed_time": "1 day, 2:25:11", "remaining_time": "1 day, 10:42:43"}
+{"current_steps": 1020, "total_steps": 2337, "loss": 0.9984, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1983030014458184e-06, "epoch": 1.31, "percentage": 43.65, "elapsed_time": "1 day, 2:40:52", "remaining_time": "1 day, 10:27:00"}
+{"current_steps": 1030, "total_steps": 2337, "loss": 1.0126, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1851096014245055e-06, "epoch": 1.32, "percentage": 44.07, "elapsed_time": "1 day, 2:56:31", "remaining_time": "1 day, 10:11:16"}
+{"current_steps": 1040, "total_steps": 2337, "loss": 1.0064, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1718827507404873e-06, "epoch": 1.34, "percentage": 44.5, "elapsed_time": "1 day, 3:12:11", "remaining_time": "1 day, 9:55:32"}
+{"current_steps": 1050, "total_steps": 2337, "loss": 0.9816, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1586248395826983e-06, "epoch": 1.35, "percentage": 44.93, "elapsed_time": "1 day, 3:27:51", "remaining_time": "1 day, 9:39:48"}
+{"current_steps": 1060, "total_steps": 2337, "loss": 1.0116, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1453382637529276e-06, "epoch": 1.36, "percentage": 45.36, "elapsed_time": "1 day, 3:43:31", "remaining_time": "1 day, 9:24:04"}
+{"current_steps": 1070, "total_steps": 2337, "loss": 0.9933, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1320254242328805e-06, "epoch": 1.37, "percentage": 45.79, "elapsed_time": "1 day, 3:59:13", "remaining_time": "1 day, 9:08:23"}
+{"current_steps": 1080, "total_steps": 2337, "loss": 1.0558, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1186887267503053e-06, "epoch": 1.39, "percentage": 46.21, "elapsed_time": "1 day, 4:14:53", "remaining_time": "1 day, 8:52:40"}
+{"current_steps": 1090, "total_steps": 2337, "loss": 0.9552, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1053305813442574e-06, "epoch": 1.4, "percentage": 46.64, "elapsed_time": "1 day, 4:30:33", "remaining_time": "1 day, 8:36:56"}
+{"current_steps": 1100, "total_steps": 2337, "loss": 0.9877, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0919534019295898e-06, "epoch": 1.41, "percentage": 47.07, "elapsed_time": "1 day, 4:46:12", "remaining_time": "1 day, 8:21:11"}
+{"current_steps": 1110, "total_steps": 2337, "loss": 1.0232, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.078559605860741e-06, "epoch": 1.42, "percentage": 47.5, "elapsed_time": "1 day, 5:01:51", "remaining_time": "1 day, 8:05:27"}
+{"current_steps": 1120, "total_steps": 2337, "loss": 1.0201, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0651516134949003e-06, "epoch": 1.44, "percentage": 47.92, "elapsed_time": "1 day, 5:17:31", "remaining_time": "1 day, 7:49:44"}
+{"current_steps": 1130, "total_steps": 2337, "loss": 1.0047, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0517318477546319e-06, "epoch": 1.45, "percentage": 48.35, "elapsed_time": "1 day, 5:33:11", "remaining_time": "1 day, 7:34:01"}
+{"current_steps": 1140, "total_steps": 2337, "loss": 0.9861, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0383027336900353e-06, "epoch": 1.46, "percentage": 48.78, "elapsed_time": "1 day, 5:48:50", "remaining_time": "1 day, 7:18:17"}
+{"current_steps": 1150, "total_steps": 2337, "loss": 1.0059, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0248666980405212e-06, "epoch": 1.48, "percentage": 49.21, "elapsed_time": "1 day, 6:04:30", "remaining_time": "1 day, 7:02:34"}
+{"current_steps": 1160, "total_steps": 2337, "loss": 0.9714, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.011426168796281e-06, "epoch": 1.49, "percentage": 49.64, "elapsed_time": "1 day, 6:20:12", "remaining_time": "1 day, 6:46:53"}
+{"current_steps": 1170, "total_steps": 2337, "loss": 1.0207, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.979835747595316e-07, "epoch": 1.5, "percentage": 50.06, "elapsed_time": "1 day, 6:35:51", "remaining_time": "1 day, 6:31:09"}
+{"current_steps": 1180, "total_steps": 2337, "loss": 1.0167, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.845413451056125e-07, "epoch": 1.51, "percentage": 50.49, "elapsed_time": "1 day, 6:51:31", "remaining_time": "1 day, 6:15:26"}
+{"current_steps": 1190, "total_steps": 2337, "loss": 0.9979, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.71101908944018e-07, "epoch": 1.53, "percentage": 50.92, "elapsed_time": "1 day, 7:07:13", "remaining_time": "1 day, 5:59:45"}
+{"current_steps": 1200, "total_steps": 2337, "loss": 1.0047, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.576676948794375e-07, "epoch": 1.54, "percentage": 51.35, "elapsed_time": "1 day, 7:22:55", "remaining_time": "1 day, 5:44:03"}
+{"current_steps": 1210, "total_steps": 2337, "loss": 1.0121, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.442411305728873e-07, "epoch": 1.55, "percentage": 51.78, "elapsed_time": "1 day, 7:38:35", "remaining_time": "1 day, 5:28:21"}
+{"current_steps": 1220, "total_steps": 2337, "loss": 1.0015, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.308246423030185e-07, "epoch": 1.57, "percentage": 52.2, "elapsed_time": "1 day, 7:54:19", "remaining_time": "1 day, 5:12:42"}
+{"current_steps": 1230, "total_steps": 2337, "loss": 1.0325, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.174206545276677e-07, "epoch": 1.58, "percentage": 52.63, "elapsed_time": "1 day, 8:10:00", "remaining_time": "1 day, 4:57:00"}
+{"current_steps": 1240, "total_steps": 2337, "loss": 1.019, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.040315894457404e-07, "epoch": 1.59, "percentage": 53.06, "elapsed_time": "1 day, 8:25:41", "remaining_time": "1 day, 4:41:18"}
+{"current_steps": 1250, "total_steps": 2337, "loss": 0.993, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.906598665595016e-07, "epoch": 1.6, "percentage": 53.49, "elapsed_time": "1 day, 8:41:22", "remaining_time": "1 day, 4:25:36"}
+{"current_steps": 1260, "total_steps": 2337, "loss": 0.9917, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.773079022373553e-07, "epoch": 1.62, "percentage": 53.92, "elapsed_time": "1 day, 8:57:03", "remaining_time": "1 day, 4:09:54"}
+{"current_steps": 1270, "total_steps": 2337, "loss": 0.9697, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.63978109277187e-07, "epoch": 1.63, "percentage": 54.34, "elapsed_time": "1 day, 9:12:44", "remaining_time": "1 day, 3:54:12"}
+{"current_steps": 1280, "total_steps": 2337, "loss": 0.973, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.506728964703549e-07, "epoch": 1.64, "percentage": 54.77, "elapsed_time": "1 day, 9:28:25", "remaining_time": "1 day, 3:38:31"}
+{"current_steps": 1290, "total_steps": 2337, "loss": 1.0183, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.37394668166404e-07, "epoch": 1.66, "percentage": 55.2, "elapsed_time": "1 day, 9:44:06", "remaining_time": "1 day, 3:22:49"}
+{"current_steps": 1300, "total_steps": 2337, "loss": 1.0098, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.241458238385798e-07, "epoch": 1.67, "percentage": 55.63, "elapsed_time": "1 day, 9:59:47", "remaining_time": "1 day, 3:07:07"}
+{"current_steps": 1310, "total_steps": 2337, "loss": 0.9765, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.109287576502299e-07, "epoch": 1.68, "percentage": 56.05, "elapsed_time": "1 day, 10:15:28", "remaining_time": "1 day, 2:51:25"}
+{"current_steps": 1320, "total_steps": 2337, "loss": 1.01, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.977458580221578e-07, "epoch": 1.69, "percentage": 56.48, "elapsed_time": "1 day, 10:31:09", "remaining_time": "1 day, 2:35:44"}
+{"current_steps": 1330, "total_steps": 2337, "loss": 1.0378, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.845995072010187e-07, "epoch": 1.71, "percentage": 56.91, "elapsed_time": "1 day, 10:46:50", "remaining_time": "1 day, 2:20:02"}
+{"current_steps": 1340, "total_steps": 2337, "loss": 0.9665, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.714920808288313e-07, "epoch": 1.72, "percentage": 57.34, "elapsed_time": "1 day, 11:02:31", "remaining_time": "1 day, 2:04:20"}
+{"current_steps": 1350, "total_steps": 2337, "loss": 0.9927, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.584259475136804e-07, "epoch": 1.73, "percentage": 57.77, "elapsed_time": "1 day, 11:18:12", "remaining_time": "1 day, 1:48:39"}
+{"current_steps": 1360, "total_steps": 2337, "loss": 0.9571, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.454034684016923e-07, "epoch": 1.75, "percentage": 58.19, "elapsed_time": "1 day, 11:33:54", "remaining_time": "1 day, 1:32:57"}
+{"current_steps": 1370, "total_steps": 2337, "loss": 0.9813, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.324269967503587e-07, "epoch": 1.76, "percentage": 58.62, "elapsed_time": "1 day, 11:49:35", "remaining_time": "1 day, 1:17:15"}
+{"current_steps": 1380, "total_steps": 2337, "loss": 0.9641, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.19498877503286e-07, "epoch": 1.77, "percentage": 59.05, "elapsed_time": "1 day, 12:05:15", "remaining_time": "1 day, 1:01:33"}
+{"current_steps": 1390, "total_steps": 2337, "loss": 0.9696, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.066214468664467e-07, "epoch": 1.78, "percentage": 59.48, "elapsed_time": "1 day, 12:20:57", "remaining_time": "1 day, 0:45:52"}
+{"current_steps": 1400, "total_steps": 2337, "loss": 0.9824, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.937970318860085e-07, "epoch": 1.8, "percentage": 59.91, "elapsed_time": "1 day, 12:36:38", "remaining_time": "1 day, 0:30:10"}
+{"current_steps": 1410, "total_steps": 2337, "loss": 0.9829, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.810279500278223e-07, "epoch": 1.81, "percentage": 60.33, "elapsed_time": "1 day, 12:52:19", "remaining_time": "1 day, 0:14:29"}
+{"current_steps": 1420, "total_steps": 2337, "loss": 1.0099, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.683165087586377e-07, "epoch": 1.82, "percentage": 60.76, "elapsed_time": "1 day, 13:08:00", "remaining_time": "23:58:47"}
+{"current_steps": 1430, "total_steps": 2337, "loss": 0.9737, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.556650051291264e-07, "epoch": 1.84, "percentage": 61.19, "elapsed_time": "1 day, 13:23:41", "remaining_time": "23:43:05"}
+{"current_steps": 1440, "total_steps": 2337, "loss": 0.9962, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.430757253587901e-07, "epoch": 1.85, "percentage": 61.62, "elapsed_time": "1 day, 13:39:22", "remaining_time": "23:27:24"}
+{"current_steps": 1450, "total_steps": 2337, "loss": 0.9736, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.305509444228219e-07, "epoch": 1.86, "percentage": 62.05, "elapsed_time": "1 day, 13:55:03", "remaining_time": "23:11:42"}
+{"current_steps": 1460, "total_steps": 2337, "loss": 0.9813, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.180929256410027e-07, "epoch": 1.87, "percentage": 62.47, "elapsed_time": "1 day, 14:10:44", "remaining_time": "22:56:01"}
+{"current_steps": 1470, "total_steps": 2337, "loss": 1.0075, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.057039202687022e-07, "epoch": 1.89, "percentage": 62.9, "elapsed_time": "1 day, 14:26:25", "remaining_time": "22:40:19"}
+{"current_steps": 1480, "total_steps": 2337, "loss": 0.9858, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.93386167090062e-07, "epoch": 1.9, "percentage": 63.33, "elapsed_time": "1 day, 14:42:08", "remaining_time": "22:24:38"}
+{"current_steps": 1490, "total_steps": 2337, "loss": 0.992, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.811418920134277e-07, "epoch": 1.91, "percentage": 63.76, "elapsed_time": "1 day, 14:57:49", "remaining_time": "22:08:56"}
+{"current_steps": 1500, "total_steps": 2337, "loss": 0.9919, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.689733076691148e-07, "epoch": 1.93, "percentage": 64.18, "elapsed_time": "1 day, 15:13:29", "remaining_time": "21:53:15"}
+{"current_steps": 1510, "total_steps": 2337, "loss": 0.9786, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.56882613009567e-07, "epoch": 1.94, "percentage": 64.61, "elapsed_time": "1 day, 15:29:10", "remaining_time": "21:37:33"}
+{"current_steps": 1520, "total_steps": 2337, "loss": 0.9814, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.448719929119915e-07, "epoch": 1.95, "percentage": 65.04, "elapsed_time": "1 day, 15:44:50", "remaining_time": "21:21:51"}
+{"current_steps": 1530, "total_steps": 2337, "loss": 0.9847, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.329436177835339e-07, "epoch": 1.96, "percentage": 65.47, "elapsed_time": "1 day, 16:00:31", "remaining_time": "21:06:09"}
+{"current_steps": 1540, "total_steps": 2337, "loss": 0.9752, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.210996431690722e-07, "epoch": 1.98, "percentage": 65.9, "elapsed_time": "1 day, 16:16:13", "remaining_time": "20:50:28"}
+{"current_steps": 1550, "total_steps": 2337, "loss": 1.0272, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.093422093616909e-07, "epoch": 1.99, "percentage": 66.32, "elapsed_time": "1 day, 16:31:54", "remaining_time": "20:34:46"}
+{"current_steps": 1560, "total_steps": 2337, "loss": 1.0187, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.976734410159165e-07, "epoch": 2.0, "percentage": 66.75, "elapsed_time": "1 day, 16:47:36", "remaining_time": "20:19:05"}
+{"current_steps": 1570, "total_steps": 2337, "loss": 0.9922, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.860954467637762e-07, "epoch": 2.02, "percentage": 67.18, "elapsed_time": "1 day, 17:03:17", "remaining_time": "20:03:24"}
+{"current_steps": 1580, "total_steps": 2337, "loss": 0.9881, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.7461031883375335e-07, "epoch": 2.03, "percentage": 67.61, "elapsed_time": "1 day, 17:18:58", "remaining_time": "19:47:42"}
+{"current_steps": 1590, "total_steps": 2337, "loss": 0.9972, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.632201326727041e-07, "epoch": 2.04, "percentage": 68.04, "elapsed_time": "1 day, 17:34:40", "remaining_time": "19:32:01"}
+{"current_steps": 1600, "total_steps": 2337, "loss": 0.9841, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.519269465708125e-07, "epoch": 2.05, "percentage": 68.46, "elapsed_time": "1 day, 17:50:21", "remaining_time": "19:16:19"}
+{"current_steps": 1610, "total_steps": 2337, "loss": 1.0147, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.407328012896393e-07, "epoch": 2.07, "percentage": 68.89, "elapsed_time": "1 day, 18:06:01", "remaining_time": "19:00:38"}
+{"current_steps": 1620, "total_steps": 2337, "loss": 0.9832, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.2963971969334254e-07, "epoch": 2.08, "percentage": 69.32, "elapsed_time": "1 day, 18:21:42", "remaining_time": "18:44:56"}
+{"current_steps": 1630, "total_steps": 2337, "loss": 1.0031, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.186497063831316e-07, "epoch": 2.09, "percentage": 69.75, "elapsed_time": "1 day, 18:37:22", "remaining_time": "18:29:14"}
+{"current_steps": 1640, "total_steps": 2337, "loss": 0.9694, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.0776474733502007e-07, "epoch": 2.11, "percentage": 70.18, "elapsed_time": "1 day, 18:53:03", "remaining_time": "18:13:33"}
+{"current_steps": 1650, "total_steps": 2337, "loss": 0.9836, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.9698680954094645e-07, "epoch": 2.12, "percentage": 70.6, "elapsed_time": "1 day, 19:08:45", "remaining_time": "17:57:51"}
+{"current_steps": 1660, "total_steps": 2337, "loss": 0.9895, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.8631784065332253e-07, "epoch": 2.13, "percentage": 71.03, "elapsed_time": "1 day, 19:24:25", "remaining_time": "17:42:10"}
+{"current_steps": 1670, "total_steps": 2337, "loss": 0.9894, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.7575976863308156e-07, "epoch": 2.14, "percentage": 71.46, "elapsed_time": "1 day, 19:40:06", "remaining_time": "17:26:28"}
+{"current_steps": 1680, "total_steps": 2337, "loss": 0.9978, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.653145014012766e-07, "epoch": 2.16, "percentage": 71.89, "elapsed_time": "1 day, 19:55:46", "remaining_time": "17:10:46"}
+{"current_steps": 1690, "total_steps": 2337, "loss": 0.9492, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.5498392649431087e-07, "epoch": 2.17, "percentage": 72.31, "elapsed_time": "1 day, 20:11:27", "remaining_time": "16:55:05"}
+{"current_steps": 1700, "total_steps": 2337, "loss": 0.9666, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.447699107228412e-07, "epoch": 2.18, "percentage": 72.74, "elapsed_time": "1 day, 20:27:08", "remaining_time": "16:39:23"}
+{"current_steps": 1710, "total_steps": 2337, "loss": 0.9963, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.3467429983443476e-07, "epoch": 2.2, "percentage": 73.17, "elapsed_time": "1 day, 20:42:49", "remaining_time": "16:23:42"}
+{"current_steps": 1720, "total_steps": 2337, "loss": 0.9629, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.2469891818002715e-07, "epoch": 2.21, "percentage": 73.6, "elapsed_time": "1 day, 20:58:31", "remaining_time": "16:08:00"}
+{"current_steps": 1730, "total_steps": 2337, "loss": 1.0002, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.148455683842507e-07, "epoch": 2.22, "percentage": 74.03, "elapsed_time": "1 day, 21:14:12", "remaining_time": "15:52:19"}
+{"current_steps": 1740, "total_steps": 2337, "loss": 1.0029, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.0511603101968475e-07, "epoch": 2.23, "percentage": 74.45, "elapsed_time": "1 day, 21:29:53", "remaining_time": "15:36:38"}
+{"current_steps": 1750, "total_steps": 2337, "loss": 0.9456, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.9551206428509446e-07, "epoch": 2.25, "percentage": 74.88, "elapsed_time": "1 day, 21:45:34", "remaining_time": "15:20:56"}
+{"current_steps": 1760, "total_steps": 2337, "loss": 0.9792, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.860354036877113e-07, "epoch": 2.26, "percentage": 75.31, "elapsed_time": "1 day, 22:01:16", "remaining_time": "15:05:15"}
+{"current_steps": 1770, "total_steps": 2337, "loss": 0.9614, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.7668776172961375e-07, "epoch": 2.27, "percentage": 75.74, "elapsed_time": "1 day, 22:16:58", "remaining_time": "14:49:34"}
+{"current_steps": 1780, "total_steps": 2337, "loss": 1.0142, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.6747082759826613e-07, "epoch": 2.28, "percentage": 76.17, "elapsed_time": "1 day, 22:32:42", "remaining_time": "14:33:54"}
+{"current_steps": 1790, "total_steps": 2337, "loss": 0.9993, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.583862668612693e-07, "epoch": 2.3, "percentage": 76.59, "elapsed_time": "1 day, 22:48:24", "remaining_time": "14:18:12"}
+{"current_steps": 1800, "total_steps": 2337, "loss": 1.0057, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.4943572116538205e-07, "epoch": 2.31, "percentage": 77.02, "elapsed_time": "1 day, 23:04:09", "remaining_time": "14:02:32"}
+{"current_steps": 1810, "total_steps": 2337, "loss": 0.9717, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.4062080793986004e-07, "epoch": 2.32, "percentage": 77.45, "elapsed_time": "1 day, 23:19:50", "remaining_time": "13:46:50"}
+{"current_steps": 1820, "total_steps": 2337, "loss": 1.0034, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3194312010417927e-07, "epoch": 2.34, "percentage": 77.88, "elapsed_time": "1 day, 23:35:34", "remaining_time": "13:31:10"}
+{"current_steps": 1830, "total_steps": 2337, "loss": 0.9612, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2340422578017958e-07, "epoch": 2.35, "percentage": 78.31, "elapsed_time": "1 day, 23:51:16", "remaining_time": "13:15:28"}
+{"current_steps": 1840, "total_steps": 2337, "loss": 0.9932, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.150056680086958e-07, "epoch": 2.36, "percentage": 78.73, "elapsed_time": "2 days, 0:06:58", "remaining_time": "12:59:47"}
+{"current_steps": 1850, "total_steps": 2337, "loss": 1.0122, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0674896447071833e-07, "epoch": 2.37, "percentage": 79.16, "elapsed_time": "2 days, 0:22:38", "remaining_time": "12:44:06"}
+{"current_steps": 1860, "total_steps": 2337, "loss": 1.0008, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9863560721313698e-07, "epoch": 2.39, "percentage": 79.59, "elapsed_time": "2 days, 0:38:22", "remaining_time": "12:28:25"}
+{"current_steps": 1870, "total_steps": 2337, "loss": 1.0085, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9066706237911756e-07, "epoch": 2.4, "percentage": 80.02, "elapsed_time": "2 days, 0:54:03", "remaining_time": "12:12:43"}
+{"current_steps": 1880, "total_steps": 2337, "loss": 0.9867, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8284476994315835e-07, "epoch": 2.41, "percentage": 80.45, "elapsed_time": "2 days, 1:09:45", "remaining_time": "11:57:02"}
+{"current_steps": 1890, "total_steps": 2337, "loss": 0.987, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7517014345087766e-07, "epoch": 2.43, "percentage": 80.87, "elapsed_time": "2 days, 1:25:27", "remaining_time": "11:41:21"}
+{"current_steps": 1900, "total_steps": 2337, "loss": 0.9703, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6764456976357277e-07, "epoch": 2.44, "percentage": 81.3, "elapsed_time": "2 days, 1:41:09", "remaining_time": "11:25:39"}
+{"current_steps": 1910, "total_steps": 2337, "loss": 0.9949, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6026940880760797e-07, "epoch": 2.45, "percentage": 81.73, "elapsed_time": "2 days, 1:56:50", "remaining_time": "11:09:58"}
+{"current_steps": 1920, "total_steps": 2337, "loss": 1.0132, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5304599332866197e-07, "epoch": 2.46, "percentage": 82.16, "elapsed_time": "2 days, 2:12:30", "remaining_time": "10:54:16"}
+{"current_steps": 1930, "total_steps": 2337, "loss": 1.0076, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.459756286508945e-07, "epoch": 2.48, "percentage": 82.58, "elapsed_time": "2 days, 2:28:10", "remaining_time": "10:38:35"}
+{"current_steps": 1940, "total_steps": 2337, "loss": 0.9801, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.390595924410609e-07, "epoch": 2.49, "percentage": 83.01, "elapsed_time": "2 days, 2:43:52", "remaining_time": "10:22:53"}
+{"current_steps": 1950, "total_steps": 2337, "loss": 0.9947, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.322991344776323e-07, "epoch": 2.5, "percentage": 83.44, "elapsed_time": "2 days, 2:59:36", "remaining_time": "10:07:12"}
+{"current_steps": 1960, "total_steps": 2337, "loss": 0.9898, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.256954764249486e-07, "epoch": 2.52, "percentage": 83.87, "elapsed_time": "2 days, 3:15:17", "remaining_time": "9:51:31"}
+{"current_steps": 1970, "total_steps": 2337, "loss": 1.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1924981161245574e-07, "epoch": 2.53, "percentage": 84.3, "elapsed_time": "2 days, 3:30:57", "remaining_time": "9:35:49"}
+{"current_steps": 1980, "total_steps": 2337, "loss": 0.9637, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1296330481906247e-07, "epoch": 2.54, "percentage": 84.72, "elapsed_time": "2 days, 3:46:38", "remaining_time": "9:20:08"}
+{"current_steps": 1990, "total_steps": 2337, "loss": 1.0058, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0683709206265635e-07, "epoch": 2.55, "percentage": 85.15, "elapsed_time": "2 days, 4:02:22", "remaining_time": "9:04:27"}
+{"current_steps": 2000, "total_steps": 2337, "loss": 1.0164, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0087228039481643e-07, "epoch": 2.57, "percentage": 85.58, "elapsed_time": "2 days, 4:18:03", "remaining_time": "8:48:45"}
+{"current_steps": 2010, "total_steps": 2337, "loss": 0.9956, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.506994770076115e-08, "epoch": 2.58, "percentage": 86.01, "elapsed_time": "2 days, 4:35:00", "remaining_time": "8:33:16"}
+{"current_steps": 2020, "total_steps": 2337, "loss": 0.9945, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.94311425045674e-08, "epoch": 2.59, "percentage": 86.44, "elapsed_time": "2 days, 4:50:42", "remaining_time": "8:17:34"}
+{"current_steps": 2030, "total_steps": 2337, "loss": 0.9916, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.395688377969235e-08, "epoch": 2.61, "percentage": 86.86, "elapsed_time": "2 days, 5:06:24", "remaining_time": "8:01:53"}
+{"current_steps": 2040, "total_steps": 2337, "loss": 0.998, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.864816076484049e-08, "epoch": 2.62, "percentage": 87.29, "elapsed_time": "2 days, 5:22:06", "remaining_time": "7:46:11"}
+{"current_steps": 2050, "total_steps": 2337, "loss": 0.9892, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.350593278519823e-08, "epoch": 2.63, "percentage": 87.72, "elapsed_time": "2 days, 5:37:47", "remaining_time": "7:30:29"}
+{"current_steps": 2060, "total_steps": 2337, "loss": 0.9772, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.853112907907854e-08, "epoch": 2.64, "percentage": 88.15, "elapsed_time": "2 days, 5:53:28", "remaining_time": "7:14:47"}
+{"current_steps": 2070, "total_steps": 2337, "loss": 0.9784, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.372464862999949e-08, "epoch": 2.66, "percentage": 88.58, "elapsed_time": "2 days, 6:09:15", "remaining_time": "6:59:06"}
+{"current_steps": 2080, "total_steps": 2337, "loss": 0.9986, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.908736000423309e-08, "epoch": 2.67, "percentage": 89.0, "elapsed_time": "2 days, 6:24:58", "remaining_time": "6:43:24"}
+{"current_steps": 2090, "total_steps": 2337, "loss": 0.978, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.462010119384664e-08, "epoch": 2.68, "percentage": 89.43, "elapsed_time": "2 days, 6:40:40", "remaining_time": "6:27:43"}
+{"current_steps": 2100, "total_steps": 2337, "loss": 0.9783, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0323679465273605e-08, "epoch": 2.7, "percentage": 89.86, "elapsed_time": "2 days, 6:56:22", "remaining_time": "6:12:01"}
+{"current_steps": 2110, "total_steps": 2337, "loss": 0.9555, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.619887121343324e-08, "epoch": 2.71, "percentage": 90.29, "elapsed_time": "2 days, 7:12:04", "remaining_time": "5:56:19"}
+{"current_steps": 2120, "total_steps": 2337, "loss": 0.9857, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.2246421821431123e-08, "epoch": 2.72, "percentage": 90.71, "elapsed_time": "2 days, 7:27:46", "remaining_time": "5:40:37"}
+{"current_steps": 2130, "total_steps": 2337, "loss": 0.961, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.846704552586244e-08, "epoch": 2.73, "percentage": 91.14, "elapsed_time": "2 days, 7:43:28", "remaining_time": "5:24:55"}
+{"current_steps": 2140, "total_steps": 2337, "loss": 0.9973, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.4861425287744276e-08, "epoch": 2.75, "percentage": 91.57, "elapsed_time": "2 days, 7:59:13", "remaining_time": "5:09:14"}
+{"current_steps": 2150, "total_steps": 2337, "loss": 0.9497, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.143021266910029e-08, "epoch": 2.76, "percentage": 92.0, "elapsed_time": "2 days, 8:14:54", "remaining_time": "4:53:32"}
+{"current_steps": 2160, "total_steps": 2337, "loss": 0.9707, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.8174027715217263e-08, "epoch": 2.77, "percentage": 92.43, "elapsed_time": "2 days, 8:30:37", "remaining_time": "4:37:50"}
+{"current_steps": 2170, "total_steps": 2337, "loss": 0.9564, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5093458842599946e-08, "epoch": 2.79, "percentage": 92.85, "elapsed_time": "2 days, 8:46:19", "remaining_time": "4:22:08"}
+{"current_steps": 2180, "total_steps": 2337, "loss": 0.9395, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.218906273263843e-08, "epoch": 2.8, "percentage": 93.28, "elapsed_time": "2 days, 9:02:01", "remaining_time": "4:06:26"}
+{"current_steps": 2190, "total_steps": 2337, "loss": 0.9569, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9461364231012856e-08, "epoch": 2.81, "percentage": 93.71, "elapsed_time": "2 days, 9:17:44", "remaining_time": "3:50:45"}
+{"current_steps": 2200, "total_steps": 2337, "loss": 1.0239, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6910856252849382e-08, "epoch": 2.82, "percentage": 94.14, "elapsed_time": "2 days, 9:33:26", "remaining_time": "3:35:03"}
+{"current_steps": 2210, "total_steps": 2337, "loss": 0.9657, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4537999693646885e-08, "epoch": 2.84, "percentage": 94.57, "elapsed_time": "2 days, 9:49:07", "remaining_time": "3:19:21"}
+{"current_steps": 2220, "total_steps": 2337, "loss": 0.9456, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2343223345989917e-08, "epoch": 2.85, "percentage": 94.99, "elapsed_time": "2 days, 10:04:49", "remaining_time": "3:03:39"}
+{"current_steps": 2230, "total_steps": 2337, "loss": 1.0241, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0326923822062461e-08, "epoch": 2.86, "percentage": 95.42, "elapsed_time": "2 days, 10:20:32", "remaining_time": "2:47:57"}
+{"current_steps": 2240, "total_steps": 2337, "loss": 1.0016, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.489465481977708e-09, "epoch": 2.88, "percentage": 95.85, "elapsed_time": "2 days, 10:36:17", "remaining_time": "2:32:16"}
+{"current_steps": 2250, "total_steps": 2337, "loss": 0.9713, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.83118036793473e-09, "epoch": 2.89, "percentage": 96.28, "elapsed_time": "2 days, 10:51:59", "remaining_time": "2:16:34"}
+{"current_steps": 2260, "total_steps": 2337, "loss": 0.9896, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.352368144216801e-09, "epoch": 2.9, "percentage": 96.71, "elapsed_time": "2 days, 11:07:43", "remaining_time": "2:00:52"}
+{"current_steps": 2270, "total_steps": 2337, "loss": 0.976, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.053296043039389e-09, "epoch": 2.91, "percentage": 97.13, "elapsed_time": "2 days, 11:23:25", "remaining_time": "1:45:10"}
+{"current_steps": 2280, "total_steps": 2337, "loss": 1.0155, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.934198816259559e-09, "epoch": 2.93, "percentage": 97.56, "elapsed_time": "2 days, 11:39:07", "remaining_time": "1:29:28"}
+{"current_steps": 2290, "total_steps": 2337, "loss": 0.9782, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9952786929543495e-09, "epoch": 2.94, "percentage": 97.99, "elapsed_time": "2 days, 11:54:53", "remaining_time": "1:13:46"}
+{"current_steps": 2300, "total_steps": 2337, "loss": 1.015, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.236705342876898e-09, "epoch": 2.95, "percentage": 98.42, "elapsed_time": "2 days, 12:10:36", "remaining_time": "0:58:05"}
+{"current_steps": 2310, "total_steps": 2337, "loss": 0.9742, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.586158457954072e-10, "epoch": 2.97, "percentage": 98.84, "elapsed_time": "2 days, 12:26:23", "remaining_time": "0:42:23"}
+{"current_steps": 2320, "total_steps": 2337, "loss": 1.0113, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.611146667221842e-10, "epoch": 2.98, "percentage": 99.27, "elapsed_time": "2 days, 12:42:04", "remaining_time": "0:26:41"}
+{"current_steps": 2330, "total_steps": 2337, "loss": 0.9955, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.4273637035852074e-11, "epoch": 2.99, "percentage": 99.7, "elapsed_time": "2 days, 12:57:47", "remaining_time": "0:10:59"}
+{"current_steps": 2337, "total_steps": 2337, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2 days, 13:08:47", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1426 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 2337,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9999096463326385e-06,
+      "loss": 1.9904,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.9996386016581256e-06,
+      "loss": 1.9027,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9991869149562214e-06,
+      "loss": 1.8885,
+      "step": 30
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9985546678500257e-06,
+      "loss": 1.9943,
+      "step": 40
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.997741974591229e-06,
+      "loss": 1.9145,
+      "step": 50
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9967489820394627e-06,
+      "loss": 1.9079,
+      "step": 60
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.995575869635765e-06,
+      "loss": 1.8246,
+      "step": 70
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.994222849370152e-06,
+      "loss": 1.759,
+      "step": 80
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9926901657433085e-06,
+      "loss": 1.6747,
+      "step": 90
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.990978095722409e-06,
+      "loss": 1.5992,
+      "step": 100
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9890869486910627e-06,
+      "loss": 1.5288,
+      "step": 110
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9870170663934104e-06,
+      "loss": 1.5143,
+      "step": 120
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9847688228723645e-06,
+      "loss": 1.4542,
+      "step": 130
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9823426244020197e-06,
+      "loss": 1.4081,
+      "step": 140
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.979738909414235e-06,
+      "loss": 1.377,
+      "step": 150
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9769581484194063e-06,
+      "loss": 1.3373,
+      "step": 160
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9740008439214417e-06,
+      "loss": 1.3031,
+      "step": 170
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9708675303269545e-06,
+      "loss": 1.3004,
+      "step": 180
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9675587738486934e-06,
+      "loss": 1.2555,
+      "step": 190
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9640751724032234e-06,
+      "loss": 1.277,
+      "step": 200
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.960417355502876e-06,
+      "loss": 1.2142,
+      "step": 210
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9565859841419945e-06,
+      "loss": 1.2023,
+      "step": 220
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9525817506774864e-06,
+      "loss": 1.2301,
+      "step": 230
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.948405378703708e-06,
+      "loss": 1.217,
+      "step": 240
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9440576229217078e-06,
+      "loss": 1.1637,
+      "step": 250
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.939539269002845e-06,
+      "loss": 1.214,
+      "step": 260
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.9348511334468137e-06,
+      "loss": 1.1571,
+      "step": 270
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.9299940634340954e-06,
+      "loss": 1.1329,
+      "step": 280
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.9249689366728658e-06,
+      "loss": 1.1524,
+      "step": 290
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.91977666124039e-06,
+      "loss": 1.1853,
+      "step": 300
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.9144181754189207e-06,
+      "loss": 1.1614,
+      "step": 310
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.90889444752615e-06,
+      "loss": 1.1166,
+      "step": 320
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.903206475740223e-06,
+      "loss": 1.1298,
+      "step": 330
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.8973552879193612e-06,
+      "loss": 1.1577,
+      "step": 340
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.8913419414161202e-06,
+      "loss": 1.1421,
+      "step": 350
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.88516752288632e-06,
+      "loss": 1.1569,
+      "step": 360
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.8788331480926763e-06,
+      "loss": 1.0961,
+      "step": 370
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.872339961703175e-06,
+      "loss": 1.1173,
+      "step": 380
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.8656891370842223e-06,
+      "loss": 1.0712,
+      "step": 390
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.8588818760886094e-06,
+      "loss": 1.1055,
+      "step": 400
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.851919408838327e-06,
+      "loss": 1.1006,
+      "step": 410
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.8448029935022754e-06,
+      "loss": 1.083,
+      "step": 420
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.8375339160689023e-06,
+      "loss": 1.0588,
+      "step": 430
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.830113490113817e-06,
+      "loss": 1.0791,
+      "step": 440
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.822543056562416e-06,
+      "loss": 1.0623,
+      "step": 450
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.8148239834475695e-06,
+      "loss": 1.1126,
+      "step": 460
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.806957665662406e-06,
+      "loss": 1.0696,
+      "step": 470
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.7989455247082472e-06,
+      "loss": 1.0573,
+      "step": 480
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.7907890084377301e-06,
+      "loss": 1.0789,
+      "step": 490
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.7824895907931706e-06,
+      "loss": 1.0964,
+      "step": 500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.7740487715402106e-06,
+      "loss": 1.0551,
+      "step": 510
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.7654680759968007e-06,
+      "loss": 1.0563,
+      "step": 520
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.756749054757562e-06,
+      "loss": 1.0522,
+      "step": 530
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.747893283413585e-06,
+      "loss": 1.0446,
+      "step": 540
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.738902362267705e-06,
+      "loss": 1.0667,
+      "step": 550
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.72977791604532e-06,
+      "loss": 1.0395,
+      "step": 560
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.7205215936007869e-06,
+      "loss": 1.039,
+      "step": 570
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.7111350676194647e-06,
+      "loss": 1.0987,
+      "step": 580
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.701620034315445e-06,
+      "loss": 1.0748,
+      "step": 590
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.6919782131250366e-06,
+      "loss": 1.0446,
+      "step": 600
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.6822113463960483e-06,
+      "loss": 1.0279,
+      "step": 610
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.6723211990729355e-06,
+      "loss": 1.054,
+      "step": 620
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.6623095583778613e-06,
+      "loss": 1.0391,
+      "step": 630
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.652178233487731e-06,
+      "loss": 1.0812,
+      "step": 640
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.6419290552072634e-06,
+      "loss": 1.0826,
+      "step": 650
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.6315638756381484e-06,
+      "loss": 1.0497,
+      "step": 660
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.6210845678443602e-06,
+      "loss": 1.0329,
+      "step": 670
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.6104930255136794e-06,
+      "loss": 1.0663,
+      "step": 680
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.5997911626154914e-06,
+      "loss": 1.059,
+      "step": 690
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.5889809130549174e-06,
+      "loss": 1.0123,
+      "step": 700
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.578064230323343e-06,
+      "loss": 1.0264,
+      "step": 710
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.5670430871454081e-06,
+      "loss": 1.0411,
+      "step": 720
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.555919475122523e-06,
+      "loss": 1.0428,
+      "step": 730
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.544695404372968e-06,
+      "loss": 0.9994,
+      "step": 740
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.533372903168653e-06,
+      "loss": 1.0452,
+      "step": 750
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.5219540175685937e-06,
+      "loss": 1.02,
+      "step": 760
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.5104408110491716e-06,
+      "loss": 1.0564,
+      "step": 770
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.4988353641312515e-06,
+      "loss": 0.9889,
+      "step": 780
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.487139774004214e-06,
+      "loss": 1.0452,
+      "step": 790
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.4753561541469787e-06,
+      "loss": 1.0399,
+      "step": 800
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.463486633946084e-06,
+      "loss": 1.0438,
+      "step": 810
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.4515333583108893e-06,
+      "loss": 1.0134,
+      "step": 820
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.439498487285976e-06,
+      "loss": 0.9949,
+      "step": 830
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.427384195660811e-06,
+      "loss": 1.0184,
+      "step": 840
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.4151926725767455e-06,
+      "loss": 1.0246,
+      "step": 850
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.4029261211314222e-06,
+      "loss": 1.0428,
+      "step": 860
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.3905867579806596e-06,
+      "loss": 1.0078,
+      "step": 870
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 1.3781768129378844e-06,
+      "loss": 1.0223,
+      "step": 880
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.3656985285711895e-06,
+      "loss": 0.9788,
+      "step": 890
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.3531541597980845e-06,
+      "loss": 1.0417,
+      "step": 900
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.340545973478016e-06,
+      "loss": 1.0315,
+      "step": 910
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.32787624800273e-06,
+      "loss": 0.9775,
+      "step": 920
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.3151472728845492e-06,
+      "loss": 0.9992,
+      "step": 930
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.3023613483426399e-06,
+      "loss": 0.957,
+      "step": 940
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.2895207848873487e-06,
+      "loss": 1.0227,
+      "step": 950
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.2766279029026735e-06,
+      "loss": 1.0311,
+      "step": 960
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.2636850322269553e-06,
+      "loss": 1.0237,
+      "step": 970
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.250694511731857e-06,
+      "loss": 1.0338,
+      "step": 980
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.2376586888997145e-06,
+      "loss": 1.0259,
+      "step": 990
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.224579919399327e-06,
+      "loss": 1.0058,
+      "step": 1000
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.2114605666602728e-06,
+      "loss": 0.9968,
+      "step": 1010
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.1983030014458184e-06,
+      "loss": 0.9984,
+      "step": 1020
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.1851096014245055e-06,
+      "loss": 1.0126,
+      "step": 1030
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.1718827507404873e-06,
+      "loss": 1.0064,
+      "step": 1040
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.1586248395826983e-06,
+      "loss": 0.9816,
+      "step": 1050
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.1453382637529276e-06,
+      "loss": 1.0116,
+      "step": 1060
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.1320254242328805e-06,
+      "loss": 0.9933,
+      "step": 1070
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.1186887267503053e-06,
+      "loss": 1.0558,
+      "step": 1080
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.1053305813442574e-06,
+      "loss": 0.9552,
+      "step": 1090
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.0919534019295898e-06,
+      "loss": 0.9877,
+      "step": 1100
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.078559605860741e-06,
+      "loss": 1.0232,
+      "step": 1110
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.0651516134949003e-06,
+      "loss": 1.0201,
+      "step": 1120
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.0517318477546319e-06,
+      "loss": 1.0047,
+      "step": 1130
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.0383027336900353e-06,
+      "loss": 0.9861,
+      "step": 1140
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.0248666980405212e-06,
+      "loss": 1.0059,
+      "step": 1150
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.011426168796281e-06,
+      "loss": 0.9714,
+      "step": 1160
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 9.979835747595316e-07,
+      "loss": 1.0207,
+      "step": 1170
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 9.845413451056125e-07,
+      "loss": 1.0167,
+      "step": 1180
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 9.71101908944018e-07,
+      "loss": 0.9979,
+      "step": 1190
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 9.576676948794375e-07,
+      "loss": 1.0047,
+      "step": 1200
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 9.442411305728873e-07,
+      "loss": 1.0121,
+      "step": 1210
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 9.308246423030185e-07,
+      "loss": 1.0015,
+      "step": 1220
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 9.174206545276677e-07,
+      "loss": 1.0325,
+      "step": 1230
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 9.040315894457404e-07,
+      "loss": 1.019,
+      "step": 1240
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 8.906598665595016e-07,
+      "loss": 0.993,
+      "step": 1250
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 8.773079022373553e-07,
+      "loss": 0.9917,
+      "step": 1260
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 8.63978109277187e-07,
+      "loss": 0.9697,
+      "step": 1270
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 8.506728964703549e-07,
+      "loss": 0.973,
+      "step": 1280
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 8.37394668166404e-07,
+      "loss": 1.0183,
+      "step": 1290
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 8.241458238385798e-07,
+      "loss": 1.0098,
+      "step": 1300
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 8.109287576502299e-07,
+      "loss": 0.9765,
+      "step": 1310
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 7.977458580221578e-07,
+      "loss": 1.01,
+      "step": 1320
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 7.845995072010187e-07,
+      "loss": 1.0378,
+      "step": 1330
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 7.714920808288313e-07,
+      "loss": 0.9665,
+      "step": 1340
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 7.584259475136804e-07,
+      "loss": 0.9927,
+      "step": 1350
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 7.454034684016923e-07,
+      "loss": 0.9571,
+      "step": 1360
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 7.324269967503587e-07,
+      "loss": 0.9813,
+      "step": 1370
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 7.19498877503286e-07,
+      "loss": 0.9641,
+      "step": 1380
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 7.066214468664467e-07,
+      "loss": 0.9696,
+      "step": 1390
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 6.937970318860085e-07,
+      "loss": 0.9824,
+      "step": 1400
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 6.810279500278223e-07,
+      "loss": 0.9829,
+      "step": 1410
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 6.683165087586377e-07,
+      "loss": 1.0099,
+      "step": 1420
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 6.556650051291264e-07,
+      "loss": 0.9737,
+      "step": 1430
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 6.430757253587901e-07,
+      "loss": 0.9962,
+      "step": 1440
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 6.305509444228219e-07,
+      "loss": 0.9736,
+      "step": 1450
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 6.180929256410027e-07,
+      "loss": 0.9813,
+      "step": 1460
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 6.057039202687022e-07,
+      "loss": 1.0075,
+      "step": 1470
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 5.93386167090062e-07,
+      "loss": 0.9858,
+      "step": 1480
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 5.811418920134277e-07,
+      "loss": 0.992,
+      "step": 1490
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 5.689733076691148e-07,
+      "loss": 0.9919,
+      "step": 1500
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 5.56882613009567e-07,
+      "loss": 0.9786,
+      "step": 1510
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 5.448719929119915e-07,
+      "loss": 0.9814,
+      "step": 1520
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 5.329436177835339e-07,
+      "loss": 0.9847,
+      "step": 1530
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 5.210996431690722e-07,
+      "loss": 0.9752,
+      "step": 1540
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 5.093422093616909e-07,
+      "loss": 1.0272,
+      "step": 1550
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.976734410159165e-07,
+      "loss": 1.0187,
+      "step": 1560
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 4.860954467637762e-07,
+      "loss": 0.9922,
+      "step": 1570
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 4.7461031883375335e-07,
+      "loss": 0.9881,
+      "step": 1580
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 4.632201326727041e-07,
+      "loss": 0.9972,
+      "step": 1590
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 4.519269465708125e-07,
+      "loss": 0.9841,
+      "step": 1600
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 4.407328012896393e-07,
+      "loss": 1.0147,
+      "step": 1610
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 4.2963971969334254e-07,
+      "loss": 0.9832,
+      "step": 1620
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 4.186497063831316e-07,
+      "loss": 1.0031,
+      "step": 1630
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 4.0776474733502007e-07,
+      "loss": 0.9694,
+      "step": 1640
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 3.9698680954094645e-07,
+      "loss": 0.9836,
+      "step": 1650
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 3.8631784065332253e-07,
+      "loss": 0.9895,
+      "step": 1660
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 3.7575976863308156e-07,
+      "loss": 0.9894,
+      "step": 1670
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 3.653145014012766e-07,
+      "loss": 0.9978,
+      "step": 1680
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 3.5498392649431087e-07,
+      "loss": 0.9492,
+      "step": 1690
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 3.447699107228412e-07,
+      "loss": 0.9666,
+      "step": 1700
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 3.3467429983443476e-07,
+      "loss": 0.9963,
+      "step": 1710
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 3.2469891818002715e-07,
+      "loss": 0.9629,
+      "step": 1720
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 3.148455683842507e-07,
+      "loss": 1.0002,
+      "step": 1730
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 3.0511603101968475e-07,
+      "loss": 1.0029,
+      "step": 1740
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 2.9551206428509446e-07,
+      "loss": 0.9456,
+      "step": 1750
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 2.860354036877113e-07,
+      "loss": 0.9792,
+      "step": 1760
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 2.7668776172961375e-07,
+      "loss": 0.9614,
+      "step": 1770
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 2.6747082759826613e-07,
+      "loss": 1.0142,
+      "step": 1780
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 2.583862668612693e-07,
+      "loss": 0.9993,
+      "step": 1790
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 2.4943572116538205e-07,
+      "loss": 1.0057,
+      "step": 1800
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 2.4062080793986004e-07,
+      "loss": 0.9717,
+      "step": 1810
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 2.3194312010417927e-07,
+      "loss": 1.0034,
+      "step": 1820
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 2.2340422578017958e-07,
+      "loss": 0.9612,
+      "step": 1830
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 2.150056680086958e-07,
+      "loss": 0.9932,
+      "step": 1840
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 2.0674896447071833e-07,
+      "loss": 1.0122,
+      "step": 1850
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 1.9863560721313698e-07,
+      "loss": 1.0008,
+      "step": 1860
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 1.9066706237911756e-07,
+      "loss": 1.0085,
+      "step": 1870
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 1.8284476994315835e-07,
+      "loss": 0.9867,
+      "step": 1880
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 1.7517014345087766e-07,
+      "loss": 0.987,
+      "step": 1890
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 1.6764456976357277e-07,
+      "loss": 0.9703,
+      "step": 1900
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 1.6026940880760797e-07,
+      "loss": 0.9949,
+      "step": 1910
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 1.5304599332866197e-07,
+      "loss": 1.0132,
+      "step": 1920
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 1.459756286508945e-07,
+      "loss": 1.0076,
+      "step": 1930
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 1.390595924410609e-07,
+      "loss": 0.9801,
+      "step": 1940
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 1.322991344776323e-07,
+      "loss": 0.9947,
+      "step": 1950
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 1.256954764249486e-07,
+      "loss": 0.9898,
+      "step": 1960
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 1.1924981161245574e-07,
+      "loss": 1.0,
+      "step": 1970
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 1.1296330481906247e-07,
+      "loss": 0.9637,
+      "step": 1980
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 1.0683709206265635e-07,
+      "loss": 1.0058,
+      "step": 1990
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 1.0087228039481643e-07,
+      "loss": 1.0164,
+      "step": 2000
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 9.506994770076115e-08,
+      "loss": 0.9956,
+      "step": 2010
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 8.94311425045674e-08,
+      "loss": 0.9945,
+      "step": 2020
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 8.395688377969235e-08,
+      "loss": 0.9916,
+      "step": 2030
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 7.864816076484049e-08,
+      "loss": 0.998,
+      "step": 2040
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 7.350593278519823e-08,
+      "loss": 0.9892,
+      "step": 2050
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 6.853112907907854e-08,
+      "loss": 0.9772,
+      "step": 2060
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 6.372464862999949e-08,
+      "loss": 0.9784,
+      "step": 2070
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 5.908736000423309e-08,
+      "loss": 0.9986,
+      "step": 2080
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 5.462010119384664e-08,
+      "loss": 0.978,
+      "step": 2090
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 5.0323679465273605e-08,
+      "loss": 0.9783,
+      "step": 2100
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 4.619887121343324e-08,
+      "loss": 0.9555,
+      "step": 2110
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 4.2246421821431123e-08,
+      "loss": 0.9857,
+      "step": 2120
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 3.846704552586244e-08,
+      "loss": 0.961,
+      "step": 2130
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 3.4861425287744276e-08,
+      "loss": 0.9973,
+      "step": 2140
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 3.143021266910029e-08,
+      "loss": 0.9497,
+      "step": 2150
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 2.8174027715217263e-08,
+      "loss": 0.9707,
+      "step": 2160
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 2.5093458842599946e-08,
+      "loss": 0.9564,
+      "step": 2170
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 2.218906273263843e-08,
+      "loss": 0.9395,
+      "step": 2180
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.9461364231012856e-08,
+      "loss": 0.9569,
+      "step": 2190
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 1.6910856252849382e-08,
+      "loss": 1.0239,
+      "step": 2200
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 1.4537999693646885e-08,
+      "loss": 0.9657,
+      "step": 2210
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 1.2343223345989917e-08,
+      "loss": 0.9456,
+      "step": 2220
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 1.0326923822062461e-08,
+      "loss": 1.0241,
+      "step": 2230
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 8.489465481977708e-09,
+      "loss": 1.0016,
+      "step": 2240
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 6.83118036793473e-09,
+      "loss": 0.9713,
+      "step": 2250
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 5.352368144216801e-09,
+      "loss": 0.9896,
+      "step": 2260
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 4.053296043039389e-09,
+      "loss": 0.976,
+      "step": 2270
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 2.934198816259559e-09,
+      "loss": 1.0155,
+      "step": 2280
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 1.9952786929543495e-09,
+      "loss": 0.9782,
+      "step": 2290
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 1.236705342876898e-09,
+      "loss": 1.015,
+      "step": 2300
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 6.586158457954072e-10,
+      "loss": 0.9742,
+      "step": 2310
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 2.611146667221842e-10,
+      "loss": 1.0113,
+      "step": 2320
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 4.4273637035852074e-11,
+      "loss": 0.9955,
+      "step": 2330
+    },
+    {
+      "epoch": 3.0,
+      "step": 2337,
+      "total_flos": 9336786417352704.0,
+      "train_loss": 1.0705227502962438,
+      "train_runtime": 220133.6189,
+      "train_samples_per_second": 1.019,
+      "train_steps_per_second": 0.011
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2337,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "total_flos": 9336786417352704.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf991cf7a99979c2fa7da9c2df58697a3026b1a713dbb83381f91befb8d99814
+size 5435