removed 4bit checkpoints to save space

llama-factory/saves/internlm2_5_7b/lora/sft/README.md

@@ -1,69 +0,0 @@
----
-license: other
-library_name: peft
-tags:
-- llama-factory
-- lora
-- generated_from_trainer
-base_model: internlm/internlm2_5-7b-chat-1m
-model-index:
-- name: sft
-  results: []
----
-
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
-
-# sft
-
-This model is a fine-tuned version of [internlm/internlm2_5-7b-chat-1m](https://huggingface.co/internlm/internlm2_5-7b-chat-1m) on the alpaca_mgtv_p1 dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.7247
-
-## Model description
-
-More information needed
-
-## Intended uses & limitations
-
-More information needed
-
-## Training and evaluation data
-
-More information needed
-
-## Training procedure
-
-### Training hyperparameters
-
-The following hyperparameters were used during training:
-- learning_rate: 0.0001
-- train_batch_size: 1
-- eval_batch_size: 1
-- seed: 42
-- gradient_accumulation_steps: 8
-- total_train_batch_size: 8
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: cosine
-- lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 6.0
-
-### Training results
-
-| Training Loss | Epoch  | Step | Validation Loss |
-|:-------------:|:------:|:----:|:---------------:|
-| 0.3497        | 0.9991 | 562  | 0.6007          |
-| 0.2678        | 1.9982 | 1124 | 0.3570          |
-| 0.1949        | 2.9973 | 1686 | 0.4269          |
-| 0.1184        | 3.9964 | 2248 | 0.4489          |
-| 0.0684        | 4.9956 | 2810 | 0.6156          |
-| 0.029         | 5.9947 | 3372 | 0.7247          |
-
-
-### Framework versions
-
-- PEFT 0.11.1
-- Transformers 4.42.3
-- Pytorch 2.3.0+cu121
-- Datasets 2.20.0
-- Tokenizers 0.19.1

llama-factory/saves/internlm2_5_7b/lora/sft/adapter_config.json

@@ -1,32 +0,0 @@
-{
-  "alpha_pattern": {},
-  "auto_mapping": null,
-  "base_model_name_or_path": "internlm/internlm2_5-7b-chat-1m",
-  "bias": "none",
-  "fan_in_fan_out": false,
-  "inference_mode": true,
-  "init_lora_weights": true,
-  "layer_replication": null,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "loftq_config": {},
-  "lora_alpha": 16,
-  "lora_dropout": 0.0,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "r": 8,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "w3",
-    "wo",
-    "w1",
-    "wqkv",
-    "w2"
-  ],
-  "task_type": "CAUSAL_LM",
-  "use_dora": false,
-  "use_rslora": false
-}

llama-factory/saves/internlm2_5_7b/lora/sft/adapter_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7a925360dad2890e02463ad52f4b4968bcde5145f5fea2e900ddca1f84f78740
-size 75539712

llama-factory/saves/internlm2_5_7b/lora/sft/added_tokens.json

@@ -1,8 +0,0 @@
-{
-  "[UNUSED_TOKEN_141]": 92544,
-  "[UNUSED_TOKEN_142]": 92545,
-  "[UNUSED_TOKEN_143]": 92546,
-  "[UNUSED_TOKEN_144]": 92547,
-  "[UNUSED_TOKEN_145]": 92548,
-  "[UNUSED_TOKEN_146]": 92549
-}

llama-factory/saves/internlm2_5_7b/lora/sft/all_results.json

@@ -1,12 +0,0 @@
-{
-    "epoch": 5.994666666666666,
-    "eval_loss": 0.7247006893157959,
-    "eval_runtime": 366.243,
-    "eval_samples_per_second": 1.365,
-    "eval_steps_per_second": 1.365,
-    "total_flos": 4.067158614080225e+17,
-    "train_loss": 0.1883302003604803,
-    "train_runtime": 53299.0481,
-    "train_samples_per_second": 0.507,
-    "train_steps_per_second": 0.063
-}

llama-factory/saves/internlm2_5_7b/lora/sft/checkpoint-1124/README.md

@@ -1,202 +0,0 @@
----
-library_name: peft
-base_model: internlm/internlm2_5-7b-chat-1m
----
-
-# Model Card for Model ID
-
-<!-- Provide a quick summary of what the model is/does. -->
-
-
-
-## Model Details
-
-### Model Description
-
-<!-- Provide a longer summary of what this model is. -->
-
-
-
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-
-### Model Sources [optional]
-
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-
-## Uses
-
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
-### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
-
-### Downstream Use [optional]
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
-
-### Out-of-Scope Use
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
-
-## Bias, Risks, and Limitations
-
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
-
-### Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-
-## How to Get Started with the Model
-
-Use the code below to get started with the model.
-
-[More Information Needed]
-
-## Training Details
-
-### Training Data
-
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
-### Training Procedure
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
-[More Information Needed]
-### Framework versions
-
-- PEFT 0.11.1

llama-factory/saves/internlm2_5_7b/lora/sft/checkpoint-1124/adapter_config.json

@@ -1,32 +0,0 @@
-{
-  "alpha_pattern": {},
-  "auto_mapping": null,
-  "base_model_name_or_path": "internlm/internlm2_5-7b-chat-1m",
-  "bias": "none",
-  "fan_in_fan_out": false,
-  "inference_mode": true,
-  "init_lora_weights": true,
-  "layer_replication": null,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "loftq_config": {},
-  "lora_alpha": 16,
-  "lora_dropout": 0.0,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "r": 8,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "w3",
-    "wo",
-    "w1",
-    "wqkv",
-    "w2"
-  ],
-  "task_type": "CAUSAL_LM",
-  "use_dora": false,
-  "use_rslora": false
-}

llama-factory/saves/internlm2_5_7b/lora/sft/checkpoint-1124/adapter_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ce0a70697cdc890c7e6ab41e71c8202cca18f704c23c6ea2072aac2dc64665ec
-size 75539712

llama-factory/saves/internlm2_5_7b/lora/sft/checkpoint-1124/added_tokens.json

@@ -1,8 +0,0 @@
-{
-  "[UNUSED_TOKEN_141]": 92544,
-  "[UNUSED_TOKEN_142]": 92545,
-  "[UNUSED_TOKEN_143]": 92546,
-  "[UNUSED_TOKEN_144]": 92547,
-  "[UNUSED_TOKEN_145]": 92548,
-  "[UNUSED_TOKEN_146]": 92549
-}

llama-factory/saves/internlm2_5_7b/lora/sft/checkpoint-1124/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1efa824175500db8095dd0244fc72c11d5102f40096ba8dde0fbc0b7217734c4
-size 151264058

llama-factory/saves/internlm2_5_7b/lora/sft/checkpoint-1124/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8d138cfe3a4adf21f048848ee35837c9a757a0a3616ff7adbb45b69aac247435
-size 14244

llama-factory/saves/internlm2_5_7b/lora/sft/checkpoint-1124/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:87aaed7cb6dcc2e48d745ccf810d4294a0ed894de1a71242beeebd4a9c4d8393
-size 1064

llama-factory/saves/internlm2_5_7b/lora/sft/checkpoint-1124/special_tokens_map.json

@@ -1,38 +0,0 @@
-{
-  "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>",
-    "<|action_start|>",
-    "<|action_end|>",
-    "<|interpreter|>",
-    "<|plugin|>"
-  ],
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "<|im_end|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
-}

llama-factory/saves/internlm2_5_7b/lora/sft/checkpoint-1124/tokenization_internlm2.py

@@ -1,236 +0,0 @@
-# coding=utf-8
-# Copyright (c) The InternLM team and The HuggingFace Inc. team. All rights reserved.
-#
-# This code is based on transformers/src/transformers/models/llama/tokenization_llama.py
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-"""Tokenization classes for InternLM."""
-import os
-from shutil import copyfile
-from typing import Any, Dict, List, Optional, Tuple
-
-import sentencepiece as spm
-from transformers.tokenization_utils import PreTrainedTokenizer
-from transformers.utils import logging
-
-logger = logging.get_logger(__name__)
-
-VOCAB_FILES_NAMES = {"vocab_file": "./tokenizer.model"}
-
-PRETRAINED_VOCAB_FILES_MAP = {}
-
-
-# Modified from transformers.model.llama.tokenization_llama.LlamaTokenizer
-class InternLM2Tokenizer(PreTrainedTokenizer):
-    """
-    Construct a InternLM2 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
-    model_input_names = ["input_ids", "attention_mask"]
-    _auto_class = "AutoTokenizer"
-
-    def __init__(
-        self,
-        vocab_file,
-        unk_token="<unk>",
-        bos_token="<s>",
-        eos_token="</s>",
-        pad_token="</s>",
-        sp_model_kwargs: Optional[Dict[str, Any]] = None,
-        add_bos_token=True,
-        add_eos_token=False,
-        decode_with_prefix_space=False,
-        clean_up_tokenization_spaces=False,
-        **kwargs,
-    ):
-        self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
-        self.vocab_file = vocab_file
-        self.add_bos_token = add_bos_token
-        self.add_eos_token = add_eos_token
-        self.decode_with_prefix_space = decode_with_prefix_space
-        self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
-        self.sp_model.Load(vocab_file)
-        self._no_prefix_space_tokens = None
-        super().__init__(
-            bos_token=bos_token,
-            eos_token=eos_token,
-            unk_token=unk_token,
-            pad_token=pad_token,
-            clean_up_tokenization_spaces=clean_up_tokenization_spaces,
-            **kwargs,
-        )
-
-    @property
-    def no_prefix_space_tokens(self):
-        if self._no_prefix_space_tokens is None:
-            vocab = self.convert_ids_to_tokens(list(range(self.vocab_size)))
-            self._no_prefix_space_tokens = {i for i, tok in enumerate(vocab) if not tok.startswith("▁")}
-        return self._no_prefix_space_tokens
-
-    @property
-    def vocab_size(self):
-        """Returns vocab size"""
-        return self.sp_model.get_piece_size()
-
-    @property
-    def bos_token_id(self) -> Optional[int]:
-        return self.sp_model.bos_id()
-
-    @property
-    def eos_token_id(self) -> Optional[int]:
-        return self.sp_model.eos_id()
-
-    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 _maybe_add_prefix_space(self, tokens, decoded):
-        if tokens and tokens[0] not in self.no_prefix_space_tokens:
-            return " " + decoded
-        else:
-            return decoded
-
-    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 token in tokens:
-            # make sure that special tokens are not decoded using sentencepiece model
-            if token in self.all_special_tokens:
-                if not prev_is_special:
-                    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)
-        out_string = self.clean_up_tokenization(out_string)
-        out_string = self._maybe_add_prefix_space(tokens=tokens, decoded=out_string)
-        return out_string[1:]
-
-    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):
-        if self.add_bos_token:
-            bos_token_ids = [self.bos_token_id]
-        else:
-            bos_token_ids = []
-
-        output = bos_token_ids + token_ids_0
-
-        if token_ids_1 is not None:
-            output = output + token_ids_1
-
-        if self.add_eos_token:
-            output = output + [self.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
-            )
-
-        if token_ids_1 is None:
-            return [1] + ([0] * len(token_ids_0)) + [1]
-        return [1] + ([0] * len(token_ids_0)) + [1, 1] + ([0] * len(token_ids_1)) + [1]
-
-    def create_token_type_ids_from_sequences(
-        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
-    ) -> List[int]:
-        """
-        Create a mask from the two sequences passed to be used in a sequence-pair classification task. T5 does not make
-        use of token type ids, therefore a list of zeros is returned.
-
-        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 zeros.
-        """
-        eos = [self.eos_token_id]
-
-        if token_ids_1 is None:
-            return len(token_ids_0 + eos) * [0]
-        return len(token_ids_0 + eos + token_ids_1 + eos) * [0]

llama-factory/saves/internlm2_5_7b/lora/sft/checkpoint-1124/tokenization_internlm2_fast.py

@@ -1,214 +0,0 @@
-# coding=utf-8
-# Copyright (c) The InternLM team and The HuggingFace Inc. team. All rights reserved.
-#
-# This code is based on transformers/src/transformers/models/llama/tokenization_llama_fast.py
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-"""Tokenization Fast class for InternLM."""
-import os
-from shutil import copyfile
-from typing import Any, Dict, Optional, Tuple
-
-from tokenizers import processors, decoders, Tokenizer, normalizers
-from tokenizers.models import BPE
-
-from transformers.tokenization_utils_fast import PreTrainedTokenizerFast
-from transformers.utils import logging
-
-from transformers.convert_slow_tokenizer import (
-    SLOW_TO_FAST_CONVERTERS,
-    SpmConverter,
-    SentencePieceExtractor,
-)
-
-from .tokenization_internlm2 import InternLM2Tokenizer
-
-logger = logging.get_logger(__name__)
-
-VOCAB_FILES_NAMES = {"vocab_file": "./tokenizer.model"}
-
-# Modified from transformers.convert_slow_tokenizer.LlamaConverter
-class InternLM2Converter(SpmConverter):
-    handle_byte_fallback = True
-
-    def vocab(self, proto):
-        vocab = [
-            ("<unk>", 0.0),
-            ("<s>", 0.0),
-            ("</s>", 0.0),
-        ]
-        vocab += [(piece.piece, piece.score) for piece in proto.pieces[3:]]
-        return vocab
-
-    def unk_id(self, proto):
-        unk_id = 0
-        return unk_id
-
-    def decoder(self, replacement, add_prefix_space):
-        decoders_sequence = [
-            decoders.Replace("▁", " "),
-            decoders.ByteFallback(),
-            decoders.Fuse(),
-        ]
-        if self.proto.normalizer_spec.add_dummy_prefix:
-            decoders_sequence.append(decoders.Strip(content=" ", left=1))
-        return decoders.Sequence(decoders_sequence)
-
-    def tokenizer(self, proto):
-        model_type = proto.trainer_spec.model_type
-        vocab_scores = self.vocab(proto)
-        # special tokens
-        added_tokens = self.original_tokenizer.added_tokens_decoder
-        for i in range(len(vocab_scores)):
-            piece, score = vocab_scores[i]
-            if i in added_tokens:
-                vocab_scores[i] = (added_tokens[i].content, score)
-        if model_type == 1:
-            raise RuntimeError("InternLM2 is supposed to be a BPE model!")
-
-        elif model_type == 2:
-            _, merges = SentencePieceExtractor(self.original_tokenizer.vocab_file).extract(vocab_scores)
-            bpe_vocab = {word: i for i, (word, _score) in enumerate(vocab_scores)}
-            tokenizer = Tokenizer(
-                BPE(bpe_vocab, merges, unk_token=proto.trainer_spec.unk_piece, fuse_unk=True, byte_fallback=True)
-            )
-            tokenizer.add_special_tokens(
-                [ added_token for index, added_token in added_tokens.items()]
-            )
-        else:
-            raise Exception(
-                "You're trying to run a `Unigram` model but you're file was trained with a different algorithm"
-            )
-
-        return tokenizer
-
-    def normalizer(self, proto):
-        normalizers_list = []
-        if proto.normalizer_spec.add_dummy_prefix:
-            normalizers_list.append(normalizers.Prepend(prepend="▁"))
-        normalizers_list.append(normalizers.Replace(pattern=" ", content="▁"))
-        return normalizers.Sequence(normalizers_list)
-
-    def pre_tokenizer(self, replacement, add_prefix_space):
-        return None
-
-SLOW_TO_FAST_CONVERTERS["InternLM2Tokenizer"] = InternLM2Converter
-
-
-# Modified from transformers.model.llama.tokenization_llama_fast.LlamaTokenizerFast -> InternLM2TokenizerFast
-class InternLM2TokenizerFast(PreTrainedTokenizerFast):
-    vocab_files_names = VOCAB_FILES_NAMES
-    slow_tokenizer_class = InternLM2Tokenizer
-    padding_side = "left"
-    model_input_names = ["input_ids", "attention_mask"]
-    _auto_class = "AutoTokenizer"
-
-    def __init__(
-        self,
-        vocab_file,
-        unk_token="<unk>",
-        bos_token="<s>",
-        eos_token="</s>",
-        pad_token="</s>",
-        sp_model_kwargs: Optional[Dict[str, Any]] = None,
-        add_bos_token=True,
-        add_eos_token=False,
-        decode_with_prefix_space=False,
-        clean_up_tokenization_spaces=False,
-        **kwargs,
-    ):
-        super().__init__(
-            vocab_file=vocab_file,
-            unk_token=unk_token,
-            bos_token=bos_token,
-            eos_token=eos_token,
-            pad_token=pad_token,
-            sp_model_kwargs=sp_model_kwargs,
-            add_bos_token=add_bos_token,
-            add_eos_token=add_eos_token,
-            decode_with_prefix_space=decode_with_prefix_space,
-            clean_up_tokenization_spaces=clean_up_tokenization_spaces,
-            **kwargs,
-        )
-        self._add_bos_token = add_bos_token
-        self._add_eos_token = add_eos_token
-        self.update_post_processor()
-        self.vocab_file = vocab_file
-
-    @property
-    def can_save_slow_tokenizer(self) -> bool:
-        return os.path.isfile(self.vocab_file) if self.vocab_file else False
-
-    def update_post_processor(self):
-        """
-        Updates the underlying post processor with the current `bos_token` and `eos_token`.
-        """
-        bos = self.bos_token
-        bos_token_id = self.bos_token_id
-        if bos is None and self.add_bos_token:
-            raise ValueError("add_bos_token = True but bos_token = None")
-
-        eos = self.eos_token
-        eos_token_id = self.eos_token_id
-        if eos is None and self.add_eos_token:
-            raise ValueError("add_eos_token = True but eos_token = None")
-
-        single = f"{(bos+':0 ') if self.add_bos_token else ''}$A:0{(' '+eos+':0') if self.add_eos_token else ''}"
-        pair = f"{single}{(' '+bos+':1') if self.add_bos_token else ''} $B:1{(' '+eos+':1') if self.add_eos_token else ''}"
-
-        special_tokens = []
-        if self.add_bos_token:
-            special_tokens.append((bos, bos_token_id))
-        if self.add_eos_token:
-            special_tokens.append((eos, eos_token_id))
-        self._tokenizer.post_processor = processors.TemplateProcessing(
-            single=single, pair=pair, special_tokens=special_tokens
-        )
-
-    @property
-    def add_eos_token(self):
-        return self._add_eos_token
-
-    @property
-    def add_bos_token(self):
-        return self._add_bos_token
-
-    @add_eos_token.setter
-    def add_eos_token(self, value):
-        self._add_eos_token = value
-        self.update_post_processor()
-
-    @add_bos_token.setter
-    def add_bos_token(self, value):
-        self._add_bos_token = value
-        self.update_post_processor()
-
-    def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None) -> Tuple[str]:
-        if not self.can_save_slow_tokenizer:
-            raise ValueError(
-                "Your fast tokenizer does not have the necessary information to save the vocabulary for a slow "
-                "tokenizer."
-            )
-
-        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):
-            copyfile(self.vocab_file, out_vocab_file)
-
-        return (out_vocab_file,)

llama-factory/saves/internlm2_5_7b/lora/sft/checkpoint-1124/tokenizer.model

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f868398fc4e05ee1e8aeba95ddf18ddcc45b8bce55d5093bead5bbf80429b48b
-size 1477754

llama-factory/saves/internlm2_5_7b/lora/sft/checkpoint-1124/tokenizer_config.json

@@ -1,1640 +0,0 @@
-{
-  "add_bos_token": true,
-  "add_eos_token": false,
-  "added_tokens_decoder": {
-    "0": {
-      "content": "<unk>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "92352": {
-      "content": "Ｅ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92353": {
-      "content": "Ｆ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92354": {
-      "content": "Ｇ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92355": {
-      "content": "Ｈ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92356": {
-      "content": "Ｉ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92357": {
-      "content": "Ｊ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92358": {
-      "content": "Ｋ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92359": {
-      "content": "Ｌ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92360": {
-      "content": "Ｍ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92361": {
-      "content": "Ｎ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92362": {
-      "content": "Ｒ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92363": {
-      "content": "Ｕ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92364": {
-      "content": "Ｖ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92365": {
-      "content": "Ｗ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92366": {
-      "content": "Ｘ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92367": {
-      "content": "Ｙ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92368": {
-      "content": "Ｚ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92369": {
-      "content": "ａ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92370": {
-      "content": "ｂ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92371": {
-      "content": "ｃ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92372": {
-      "content": "ｄ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92373": {
-      "content": "ｅ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92374": {
-      "content": "ｆ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92375": {
-      "content": "ｇ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92376": {
-      "content": "ｈ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92377": {
-      "content": "ｉ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92378": {
-      "content": "ｊ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92379": {
-      "content": "ｋ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92380": {
-      "content": "ｌ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92381": {
-      "content": "ｍ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92382": {
-      "content": "ｎ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92383": {
-      "content": "ｏ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92384": {
-      "content": "ｐ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92385": {
-      "content": "ｑ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92386": {
-      "content": "ｒ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92387": {
-      "content": "ｓ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92388": {
-      "content": "ｔ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92389": {
-      "content": "ｕ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92390": {
-      "content": "ｖ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92391": {
-      "content": "ｗ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92392": {
-      "content": "ｘ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92393": {
-      "content": "ｙ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92394": {
-      "content": "ｚ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92395": {
-      "content": "——",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92396": {
-      "content": "……",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92397": {
-      "content": "[UNUSED_TOKEN_0]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92398": {
-      "content": "[UNUSED_TOKEN_1]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92399": {
-      "content": "[UNUSED_TOKEN_2]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92400": {
-      "content": "[UNUSED_TOKEN_3]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92401": {
-      "content": "[UNUSED_TOKEN_4]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92402": {
-      "content": "[UNUSED_TOKEN_5]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92403": {
-      "content": "[UNUSED_TOKEN_6]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92404": {
-      "content": "[UNUSED_TOKEN_7]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92405": {
-      "content": "[UNUSED_TOKEN_8]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92406": {
-      "content": "[UNUSED_TOKEN_9]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92407": {
-      "content": "[UNUSED_TOKEN_10]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92408": {
-      "content": "[UNUSED_TOKEN_11]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92409": {
-      "content": "[UNUSED_TOKEN_12]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92410": {
-      "content": "[UNUSED_TOKEN_13]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92411": {
-      "content": "[UNUSED_TOKEN_14]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92412": {
-      "content": "[UNUSED_TOKEN_15]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92413": {
-      "content": "[UNUSED_TOKEN_16]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92414": {
-      "content": "[UNUSED_TOKEN_17]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92415": {
-      "content": "[UNUSED_TOKEN_18]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92416": {
-      "content": "[UNUSED_TOKEN_19]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92417": {
-      "content": "[UNUSED_TOKEN_20]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92418": {
-      "content": "[UNUSED_TOKEN_21]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92419": {
-      "content": "[UNUSED_TOKEN_22]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92420": {
-      "content": "[UNUSED_TOKEN_23]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92421": {
-      "content": "[UNUSED_TOKEN_24]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92422": {
-      "content": "[UNUSED_TOKEN_25]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92423": {
-      "content": "[UNUSED_TOKEN_26]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92424": {
-      "content": "[UNUSED_TOKEN_27]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92425": {
-      "content": "[UNUSED_TOKEN_28]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92426": {
-      "content": "[UNUSED_TOKEN_29]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92427": {
-      "content": "[UNUSED_TOKEN_30]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92428": {
-      "content": "[UNUSED_TOKEN_31]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92429": {
-      "content": "[UNUSED_TOKEN_32]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92430": {
-      "content": "[UNUSED_TOKEN_33]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92431": {
-      "content": "[UNUSED_TOKEN_34]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92432": {
-      "content": "[UNUSED_TOKEN_35]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92433": {
-      "content": "[UNUSED_TOKEN_36]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92434": {
-      "content": "[UNUSED_TOKEN_37]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92435": {
-      "content": "[UNUSED_TOKEN_38]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92436": {
-      "content": "[UNUSED_TOKEN_39]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92437": {
-      "content": "[UNUSED_TOKEN_40]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92438": {
-      "content": "[UNUSED_TOKEN_41]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92439": {
-      "content": "[UNUSED_TOKEN_42]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92440": {
-      "content": "[UNUSED_TOKEN_43]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92441": {
-      "content": "[UNUSED_TOKEN_44]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92442": {
-      "content": "[UNUSED_TOKEN_45]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92443": {
-      "content": "[UNUSED_TOKEN_46]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92444": {
-      "content": "[UNUSED_TOKEN_47]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92445": {
-      "content": "[UNUSED_TOKEN_48]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92446": {
-      "content": "[UNUSED_TOKEN_49]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92447": {
-      "content": "[UNUSED_TOKEN_50]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92448": {
-      "content": "[UNUSED_TOKEN_51]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92449": {
-      "content": "[UNUSED_TOKEN_52]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92450": {
-      "content": "[UNUSED_TOKEN_53]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92451": {
-      "content": "[UNUSED_TOKEN_54]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92452": {
-      "content": "[UNUSED_TOKEN_55]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92453": {
-      "content": "[UNUSED_TOKEN_56]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92454": {
-      "content": "[UNUSED_TOKEN_57]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92455": {
-      "content": "[UNUSED_TOKEN_58]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92456": {
-      "content": "[UNUSED_TOKEN_59]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92457": {
-      "content": "[UNUSED_TOKEN_60]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92458": {
-      "content": "[UNUSED_TOKEN_61]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92459": {
-      "content": "[UNUSED_TOKEN_62]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92460": {
-      "content": "[UNUSED_TOKEN_63]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92461": {
-      "content": "[UNUSED_TOKEN_64]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92462": {
-      "content": "[UNUSED_TOKEN_65]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92463": {
-      "content": "[UNUSED_TOKEN_66]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92464": {
-      "content": "[UNUSED_TOKEN_67]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92465": {
-      "content": "[UNUSED_TOKEN_68]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92466": {
-      "content": "[UNUSED_TOKEN_69]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92467": {
-      "content": "[UNUSED_TOKEN_70]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92468": {
-      "content": "[UNUSED_TOKEN_71]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92469": {
-      "content": "[UNUSED_TOKEN_72]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92470": {
-      "content": "[UNUSED_TOKEN_73]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92471": {
-      "content": "[UNUSED_TOKEN_74]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92472": {
-      "content": "[UNUSED_TOKEN_75]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92473": {
-      "content": "[UNUSED_TOKEN_76]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92474": {
-      "content": "[UNUSED_TOKEN_77]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92475": {
-      "content": "[UNUSED_TOKEN_78]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92476": {
-      "content": "[UNUSED_TOKEN_79]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92477": {
-      "content": "[UNUSED_TOKEN_80]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92478": {
-      "content": "[UNUSED_TOKEN_81]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92479": {
-      "content": "[UNUSED_TOKEN_82]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92480": {
-      "content": "[UNUSED_TOKEN_83]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92481": {
-      "content": "[UNUSED_TOKEN_84]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92482": {
-      "content": "[UNUSED_TOKEN_85]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92483": {
-      "content": "[UNUSED_TOKEN_86]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92484": {
-      "content": "[UNUSED_TOKEN_87]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92485": {
-      "content": "[UNUSED_TOKEN_88]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92486": {
-      "content": "[UNUSED_TOKEN_89]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92487": {
-      "content": "[UNUSED_TOKEN_90]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92488": {
-      "content": "[UNUSED_TOKEN_91]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92489": {
-      "content": "[UNUSED_TOKEN_92]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92490": {
-      "content": "[UNUSED_TOKEN_93]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92491": {
-      "content": "[UNUSED_TOKEN_94]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92492": {
-      "content": "[UNUSED_TOKEN_95]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92493": {
-      "content": "[UNUSED_TOKEN_96]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92494": {
-      "content": "[UNUSED_TOKEN_97]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92495": {
-      "content": "[UNUSED_TOKEN_98]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92496": {
-      "content": "[UNUSED_TOKEN_99]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92497": {
-      "content": "[UNUSED_TOKEN_100]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92498": {
-      "content": "[UNUSED_TOKEN_101]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92499": {
-      "content": "[UNUSED_TOKEN_102]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92500": {
-      "content": "[UNUSED_TOKEN_103]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92501": {
-      "content": "[UNUSED_TOKEN_104]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92502": {
-      "content": "[UNUSED_TOKEN_105]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92503": {
-      "content": "[UNUSED_TOKEN_106]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92504": {
-      "content": "[UNUSED_TOKEN_107]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92505": {
-      "content": "[UNUSED_TOKEN_108]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92506": {
-      "content": "[UNUSED_TOKEN_109]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92507": {
-      "content": "[UNUSED_TOKEN_110]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92508": {
-      "content": "[UNUSED_TOKEN_111]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92509": {
-      "content": "[UNUSED_TOKEN_112]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92510": {
-      "content": "[UNUSED_TOKEN_113]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92511": {
-      "content": "[UNUSED_TOKEN_114]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92512": {
-      "content": "[UNUSED_TOKEN_115]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92513": {
-      "content": "[UNUSED_TOKEN_116]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92514": {
-      "content": "[UNUSED_TOKEN_117]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92515": {
-      "content": "[UNUSED_TOKEN_118]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92516": {
-      "content": "[UNUSED_TOKEN_119]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92517": {
-      "content": "[UNUSED_TOKEN_120]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92518": {
-      "content": "[UNUSED_TOKEN_121]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92519": {
-      "content": "[UNUSED_TOKEN_122]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92520": {
-      "content": "[UNUSED_TOKEN_123]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92521": {
-      "content": "[UNUSED_TOKEN_124]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92522": {
-      "content": "[UNUSED_TOKEN_125]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92523": {
-      "content": "[UNUSED_TOKEN_126]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92524": {
-      "content": "[UNUSED_TOKEN_127]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92525": {
-      "content": "[UNUSED_TOKEN_128]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92526": {
-      "content": "[UNUSED_TOKEN_129]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92527": {
-      "content": "[UNUSED_TOKEN_130]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92528": {
-      "content": "[UNUSED_TOKEN_131]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92529": {
-      "content": "[UNUSED_TOKEN_132]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92530": {
-      "content": "[UNUSED_TOKEN_133]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92531": {
-      "content": "[UNUSED_TOKEN_134]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92532": {
-      "content": "[UNUSED_TOKEN_135]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92533": {
-      "content": "[UNUSED_TOKEN_136]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92534": {
-      "content": "[UNUSED_TOKEN_137]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92535": {
-      "content": "[UNUSED_TOKEN_138]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92536": {
-      "content": "[UNUSED_TOKEN_139]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92537": {
-      "content": "[UNUSED_TOKEN_140]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92538": {
-      "content": "<|plugin|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "92539": {
-      "content": "<|interpreter|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "92540": {
-      "content": "<|action_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "92541": {
-      "content": "<|action_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "92542": {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "92543": {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "92544": {
-      "content": "[UNUSED_TOKEN_141]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92545": {
-      "content": "[UNUSED_TOKEN_142]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92546": {
-      "content": "[UNUSED_TOKEN_143]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92547": {
-      "content": "[UNUSED_TOKEN_144]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92548": {
-      "content": "[UNUSED_TOKEN_145]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92549": {
-      "content": "[UNUSED_TOKEN_146]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    }
-  },
-  "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>",
-    "<|action_start|>",
-    "<|action_end|>",
-    "<|interpreter|>",
-    "<|plugin|>"
-  ],
-  "auto_map": {
-    "AutoTokenizer": [
-      "tokenization_internlm2.InternLM2Tokenizer",
-      "tokenization_internlm2_fast.InternLM2TokenizerFast"
-    ]
-  },
-  "bos_token": "<s>",
-  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
-  "clean_up_tokenization_spaces": false,
-  "decode_with_prefix_space": false,
-  "eos_token": "<|im_end|>",
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "</s>",
-  "padding_side": "right",
-  "sp_model_kwargs": null,
-  "split_special_tokens": false,
-  "tokenizer_class": "InternLM2Tokenizer",
-  "unk_token": "<unk>"
-}

llama-factory/saves/internlm2_5_7b/lora/sft/checkpoint-1124/trainer_state.json

@@ -1,126 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 1.9982222222222221,
-  "eval_steps": 562,
-  "global_step": 1124,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.17777777777777778,
-      "grad_norm": 4.040336608886719,
-      "learning_rate": 2.958579881656805e-05,
-      "loss": 0.4641,
-      "step": 100
-    },
-    {
-      "epoch": 0.35555555555555557,
-      "grad_norm": 3.9950191974639893,
-      "learning_rate": 5.91715976331361e-05,
-      "loss": 0.3704,
-      "step": 200
-    },
-    {
-      "epoch": 0.5333333333333333,
-      "grad_norm": 3.9038829803466797,
-      "learning_rate": 8.875739644970414e-05,
-      "loss": 0.3751,
-      "step": 300
-    },
-    {
-      "epoch": 0.7111111111111111,
-      "grad_norm": 3.4998044967651367,
-      "learning_rate": 9.989699867437137e-05,
-      "loss": 0.3928,
-      "step": 400
-    },
-    {
-      "epoch": 0.8888888888888888,
-      "grad_norm": 9.73261833190918,
-      "learning_rate": 9.92981892269398e-05,
-      "loss": 0.3497,
-      "step": 500
-    },
-    {
-      "epoch": 0.9991111111111111,
-      "eval_loss": 0.6006748080253601,
-      "eval_runtime": 411.5999,
-      "eval_samples_per_second": 1.215,
-      "eval_steps_per_second": 1.215,
-      "step": 562
-    },
-    {
-      "epoch": 1.0666666666666667,
-      "grad_norm": 2.8831710815429688,
-      "learning_rate": 9.817128546774103e-05,
-      "loss": 0.3383,
-      "step": 600
-    },
-    {
-      "epoch": 1.2444444444444445,
-      "grad_norm": 6.632827281951904,
-      "learning_rate": 9.652835906663704e-05,
-      "loss": 0.3167,
-      "step": 700
-    },
-    {
-      "epoch": 1.4222222222222223,
-      "grad_norm": 6.977548122406006,
-      "learning_rate": 9.438700945477697e-05,
-      "loss": 0.3165,
-      "step": 800
-    },
-    {
-      "epoch": 1.6,
-      "grad_norm": 10.037060737609863,
-      "learning_rate": 9.177017529516772e-05,
-      "loss": 0.2927,
-      "step": 900
-    },
-    {
-      "epoch": 1.7777777777777777,
-      "grad_norm": 6.976019859313965,
-      "learning_rate": 8.870588875808164e-05,
-      "loss": 0.3062,
-      "step": 1000
-    },
-    {
-      "epoch": 1.9555555555555557,
-      "grad_norm": 2.106227159500122,
-      "learning_rate": 8.522697523356319e-05,
-      "loss": 0.2678,
-      "step": 1100
-    },
-    {
-      "epoch": 1.9982222222222221,
-      "eval_loss": 0.3569962680339813,
-      "eval_runtime": 367.3155,
-      "eval_samples_per_second": 1.361,
-      "eval_steps_per_second": 1.361,
-      "step": 1124
-    }
-  ],
-  "logging_steps": 100,
-  "max_steps": 3372,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 6,
-  "save_steps": 562,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": false
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 1.3557561305392742e+17,
-  "train_batch_size": 1,
-  "trial_name": null,
-  "trial_params": null
-}

llama-factory/saves/internlm2_5_7b/lora/sft/checkpoint-1124/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:aee0526e63b02d5d5f300a2e1dfcfcc13e168aae73493f8d596712a07178876b
-size 5304

llama-factory/saves/internlm2_5_7b/lora/sft/checkpoint-1686/README.md

@@ -1,202 +0,0 @@
----
-library_name: peft
-base_model: internlm/internlm2_5-7b-chat-1m
----
-
-# Model Card for Model ID
-
-<!-- Provide a quick summary of what the model is/does. -->
-
-
-
-## Model Details
-
-### Model Description
-
-<!-- Provide a longer summary of what this model is. -->
-
-
-
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-
-### Model Sources [optional]
-
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-
-## Uses
-
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
-### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
-
-### Downstream Use [optional]
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
-
-### Out-of-Scope Use
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
-
-## Bias, Risks, and Limitations
-
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
-
-### Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-
-## How to Get Started with the Model
-
-Use the code below to get started with the model.
-
-[More Information Needed]
-
-## Training Details
-
-### Training Data
-
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
-### Training Procedure
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
-[More Information Needed]
-### Framework versions
-
-- PEFT 0.11.1

llama-factory/saves/internlm2_5_7b/lora/sft/checkpoint-1686/adapter_config.json

@@ -1,32 +0,0 @@
-{
-  "alpha_pattern": {},
-  "auto_mapping": null,
-  "base_model_name_or_path": "internlm/internlm2_5-7b-chat-1m",
-  "bias": "none",
-  "fan_in_fan_out": false,
-  "inference_mode": true,
-  "init_lora_weights": true,
-  "layer_replication": null,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "loftq_config": {},
-  "lora_alpha": 16,
-  "lora_dropout": 0.0,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "r": 8,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "w3",
-    "wo",
-    "w1",
-    "wqkv",
-    "w2"
-  ],
-  "task_type": "CAUSAL_LM",
-  "use_dora": false,
-  "use_rslora": false
-}

llama-factory/saves/internlm2_5_7b/lora/sft/checkpoint-1686/adapter_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2db59fc1969809c41246edf4ce25225643730120516d17662a7d1bb14d7cfe39
-size 75539712

llama-factory/saves/internlm2_5_7b/lora/sft/checkpoint-1686/added_tokens.json

@@ -1,8 +0,0 @@
-{
-  "[UNUSED_TOKEN_141]": 92544,
-  "[UNUSED_TOKEN_142]": 92545,
-  "[UNUSED_TOKEN_143]": 92546,
-  "[UNUSED_TOKEN_144]": 92547,
-  "[UNUSED_TOKEN_145]": 92548,
-  "[UNUSED_TOKEN_146]": 92549
-}

llama-factory/saves/internlm2_5_7b/lora/sft/checkpoint-1686/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d1646f40df6fb41e1f3d0b5332c11e3ae9119600089df0a51ade6a7157c4b212
-size 151264058

llama-factory/saves/internlm2_5_7b/lora/sft/checkpoint-1686/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c062f7f375beded48b5337f5a3f3a5cb38807fa3e85dbf3e294c0ab6b627bfc2
-size 14244

llama-factory/saves/internlm2_5_7b/lora/sft/checkpoint-1686/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:905747c81bda26664cb2ffce8f8ce9044aa6bf92fd1cd473dd32e646b88e5e1a
-size 1064

llama-factory/saves/internlm2_5_7b/lora/sft/checkpoint-1686/special_tokens_map.json

@@ -1,38 +0,0 @@
-{
-  "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>",
-    "<|action_start|>",
-    "<|action_end|>",
-    "<|interpreter|>",
-    "<|plugin|>"
-  ],
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "<|im_end|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
-}

llama-factory/saves/internlm2_5_7b/lora/sft/checkpoint-1686/tokenization_internlm2.py

@@ -1,236 +0,0 @@
-# coding=utf-8
-# Copyright (c) The InternLM team and The HuggingFace Inc. team. All rights reserved.
-#
-# This code is based on transformers/src/transformers/models/llama/tokenization_llama.py
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-"""Tokenization classes for InternLM."""
-import os
-from shutil import copyfile
-from typing import Any, Dict, List, Optional, Tuple
-
-import sentencepiece as spm
-from transformers.tokenization_utils import PreTrainedTokenizer
-from transformers.utils import logging
-
-logger = logging.get_logger(__name__)
-
-VOCAB_FILES_NAMES = {"vocab_file": "./tokenizer.model"}
-
-PRETRAINED_VOCAB_FILES_MAP = {}
-
-
-# Modified from transformers.model.llama.tokenization_llama.LlamaTokenizer
-class InternLM2Tokenizer(PreTrainedTokenizer):
-    """
-    Construct a InternLM2 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
-    model_input_names = ["input_ids", "attention_mask"]
-    _auto_class = "AutoTokenizer"
-
-    def __init__(
-        self,
-        vocab_file,
-        unk_token="<unk>",
-        bos_token="<s>",
-        eos_token="</s>",
-        pad_token="</s>",
-        sp_model_kwargs: Optional[Dict[str, Any]] = None,
-        add_bos_token=True,
-        add_eos_token=False,
-        decode_with_prefix_space=False,
-        clean_up_tokenization_spaces=False,
-        **kwargs,
-    ):
-        self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
-        self.vocab_file = vocab_file
-        self.add_bos_token = add_bos_token
-        self.add_eos_token = add_eos_token
-        self.decode_with_prefix_space = decode_with_prefix_space
-        self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
-        self.sp_model.Load(vocab_file)
-        self._no_prefix_space_tokens = None
-        super().__init__(
-            bos_token=bos_token,
-            eos_token=eos_token,
-            unk_token=unk_token,
-            pad_token=pad_token,
-            clean_up_tokenization_spaces=clean_up_tokenization_spaces,
-            **kwargs,
-        )
-
-    @property
-    def no_prefix_space_tokens(self):
-        if self._no_prefix_space_tokens is None:
-            vocab = self.convert_ids_to_tokens(list(range(self.vocab_size)))
-            self._no_prefix_space_tokens = {i for i, tok in enumerate(vocab) if not tok.startswith("▁")}
-        return self._no_prefix_space_tokens
-
-    @property
-    def vocab_size(self):
-        """Returns vocab size"""
-        return self.sp_model.get_piece_size()
-
-    @property
-    def bos_token_id(self) -> Optional[int]:
-        return self.sp_model.bos_id()
-
-    @property
-    def eos_token_id(self) -> Optional[int]:
-        return self.sp_model.eos_id()
-
-    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 _maybe_add_prefix_space(self, tokens, decoded):
-        if tokens and tokens[0] not in self.no_prefix_space_tokens:
-            return " " + decoded
-        else:
-            return decoded
-
-    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 token in tokens:
-            # make sure that special tokens are not decoded using sentencepiece model
-            if token in self.all_special_tokens:
-                if not prev_is_special:
-                    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)
-        out_string = self.clean_up_tokenization(out_string)
-        out_string = self._maybe_add_prefix_space(tokens=tokens, decoded=out_string)
-        return out_string[1:]
-
-    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):
-        if self.add_bos_token:
-            bos_token_ids = [self.bos_token_id]
-        else:
-            bos_token_ids = []
-
-        output = bos_token_ids + token_ids_0
-
-        if token_ids_1 is not None:
-            output = output + token_ids_1
-
-        if self.add_eos_token:
-            output = output + [self.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
-            )
-
-        if token_ids_1 is None:
-            return [1] + ([0] * len(token_ids_0)) + [1]
-        return [1] + ([0] * len(token_ids_0)) + [1, 1] + ([0] * len(token_ids_1)) + [1]
-
-    def create_token_type_ids_from_sequences(
-        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
-    ) -> List[int]:
-        """
-        Create a mask from the two sequences passed to be used in a sequence-pair classification task. T5 does not make
-        use of token type ids, therefore a list of zeros is returned.
-
-        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 zeros.
-        """
-        eos = [self.eos_token_id]
-
-        if token_ids_1 is None:
-            return len(token_ids_0 + eos) * [0]
-        return len(token_ids_0 + eos + token_ids_1 + eos) * [0]

llama-factory/saves/internlm2_5_7b/lora/sft/checkpoint-1686/tokenization_internlm2_fast.py

@@ -1,214 +0,0 @@
-# coding=utf-8
-# Copyright (c) The InternLM team and The HuggingFace Inc. team. All rights reserved.
-#
-# This code is based on transformers/src/transformers/models/llama/tokenization_llama_fast.py
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-"""Tokenization Fast class for InternLM."""
-import os
-from shutil import copyfile
-from typing import Any, Dict, Optional, Tuple
-
-from tokenizers import processors, decoders, Tokenizer, normalizers
-from tokenizers.models import BPE
-
-from transformers.tokenization_utils_fast import PreTrainedTokenizerFast
-from transformers.utils import logging
-
-from transformers.convert_slow_tokenizer import (
-    SLOW_TO_FAST_CONVERTERS,
-    SpmConverter,
-    SentencePieceExtractor,
-)
-
-from .tokenization_internlm2 import InternLM2Tokenizer
-
-logger = logging.get_logger(__name__)
-
-VOCAB_FILES_NAMES = {"vocab_file": "./tokenizer.model"}
-
-# Modified from transformers.convert_slow_tokenizer.LlamaConverter
-class InternLM2Converter(SpmConverter):
-    handle_byte_fallback = True
-
-    def vocab(self, proto):
-        vocab = [
-            ("<unk>", 0.0),
-            ("<s>", 0.0),
-            ("</s>", 0.0),
-        ]
-        vocab += [(piece.piece, piece.score) for piece in proto.pieces[3:]]
-        return vocab
-
-    def unk_id(self, proto):
-        unk_id = 0
-        return unk_id
-
-    def decoder(self, replacement, add_prefix_space):
-        decoders_sequence = [
-            decoders.Replace("▁", " "),
-            decoders.ByteFallback(),
-            decoders.Fuse(),
-        ]
-        if self.proto.normalizer_spec.add_dummy_prefix:
-            decoders_sequence.append(decoders.Strip(content=" ", left=1))
-        return decoders.Sequence(decoders_sequence)
-
-    def tokenizer(self, proto):
-        model_type = proto.trainer_spec.model_type
-        vocab_scores = self.vocab(proto)
-        # special tokens
-        added_tokens = self.original_tokenizer.added_tokens_decoder
-        for i in range(len(vocab_scores)):
-            piece, score = vocab_scores[i]
-            if i in added_tokens:
-                vocab_scores[i] = (added_tokens[i].content, score)
-        if model_type == 1:
-            raise RuntimeError("InternLM2 is supposed to be a BPE model!")
-
-        elif model_type == 2:
-            _, merges = SentencePieceExtractor(self.original_tokenizer.vocab_file).extract(vocab_scores)
-            bpe_vocab = {word: i for i, (word, _score) in enumerate(vocab_scores)}
-            tokenizer = Tokenizer(
-                BPE(bpe_vocab, merges, unk_token=proto.trainer_spec.unk_piece, fuse_unk=True, byte_fallback=True)
-            )
-            tokenizer.add_special_tokens(
-                [ added_token for index, added_token in added_tokens.items()]
-            )
-        else:
-            raise Exception(
-                "You're trying to run a `Unigram` model but you're file was trained with a different algorithm"
-            )
-
-        return tokenizer
-
-    def normalizer(self, proto):
-        normalizers_list = []
-        if proto.normalizer_spec.add_dummy_prefix:
-            normalizers_list.append(normalizers.Prepend(prepend="▁"))
-        normalizers_list.append(normalizers.Replace(pattern=" ", content="▁"))
-        return normalizers.Sequence(normalizers_list)
-
-    def pre_tokenizer(self, replacement, add_prefix_space):
-        return None
-
-SLOW_TO_FAST_CONVERTERS["InternLM2Tokenizer"] = InternLM2Converter
-
-
-# Modified from transformers.model.llama.tokenization_llama_fast.LlamaTokenizerFast -> InternLM2TokenizerFast
-class InternLM2TokenizerFast(PreTrainedTokenizerFast):
-    vocab_files_names = VOCAB_FILES_NAMES
-    slow_tokenizer_class = InternLM2Tokenizer
-    padding_side = "left"
-    model_input_names = ["input_ids", "attention_mask"]
-    _auto_class = "AutoTokenizer"
-
-    def __init__(
-        self,
-        vocab_file,
-        unk_token="<unk>",
-        bos_token="<s>",
-        eos_token="</s>",
-        pad_token="</s>",
-        sp_model_kwargs: Optional[Dict[str, Any]] = None,
-        add_bos_token=True,
-        add_eos_token=False,
-        decode_with_prefix_space=False,
-        clean_up_tokenization_spaces=False,
-        **kwargs,
-    ):
-        super().__init__(
-            vocab_file=vocab_file,
-            unk_token=unk_token,
-            bos_token=bos_token,
-            eos_token=eos_token,
-            pad_token=pad_token,
-            sp_model_kwargs=sp_model_kwargs,
-            add_bos_token=add_bos_token,
-            add_eos_token=add_eos_token,
-            decode_with_prefix_space=decode_with_prefix_space,
-            clean_up_tokenization_spaces=clean_up_tokenization_spaces,
-            **kwargs,
-        )
-        self._add_bos_token = add_bos_token
-        self._add_eos_token = add_eos_token
-        self.update_post_processor()
-        self.vocab_file = vocab_file
-
-    @property
-    def can_save_slow_tokenizer(self) -> bool:
-        return os.path.isfile(self.vocab_file) if self.vocab_file else False
-
-    def update_post_processor(self):
-        """
-        Updates the underlying post processor with the current `bos_token` and `eos_token`.
-        """
-        bos = self.bos_token
-        bos_token_id = self.bos_token_id
-        if bos is None and self.add_bos_token:
-            raise ValueError("add_bos_token = True but bos_token = None")
-
-        eos = self.eos_token
-        eos_token_id = self.eos_token_id
-        if eos is None and self.add_eos_token:
-            raise ValueError("add_eos_token = True but eos_token = None")
-
-        single = f"{(bos+':0 ') if self.add_bos_token else ''}$A:0{(' '+eos+':0') if self.add_eos_token else ''}"
-        pair = f"{single}{(' '+bos+':1') if self.add_bos_token else ''} $B:1{(' '+eos+':1') if self.add_eos_token else ''}"
-
-        special_tokens = []
-        if self.add_bos_token:
-            special_tokens.append((bos, bos_token_id))
-        if self.add_eos_token:
-            special_tokens.append((eos, eos_token_id))
-        self._tokenizer.post_processor = processors.TemplateProcessing(
-            single=single, pair=pair, special_tokens=special_tokens
-        )
-
-    @property
-    def add_eos_token(self):
-        return self._add_eos_token
-
-    @property
-    def add_bos_token(self):
-        return self._add_bos_token
-
-    @add_eos_token.setter
-    def add_eos_token(self, value):
-        self._add_eos_token = value
-        self.update_post_processor()
-
-    @add_bos_token.setter
-    def add_bos_token(self, value):
-        self._add_bos_token = value
-        self.update_post_processor()
-
-    def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None) -> Tuple[str]:
-        if not self.can_save_slow_tokenizer:
-            raise ValueError(
-                "Your fast tokenizer does not have the necessary information to save the vocabulary for a slow "
-                "tokenizer."
-            )
-
-        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):
-            copyfile(self.vocab_file, out_vocab_file)
-
-        return (out_vocab_file,)

llama-factory/saves/internlm2_5_7b/lora/sft/checkpoint-1686/tokenizer.model

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f868398fc4e05ee1e8aeba95ddf18ddcc45b8bce55d5093bead5bbf80429b48b
-size 1477754

llama-factory/saves/internlm2_5_7b/lora/sft/checkpoint-1686/tokenizer_config.json

@@ -1,1640 +0,0 @@
-{
-  "add_bos_token": true,
-  "add_eos_token": false,
-  "added_tokens_decoder": {
-    "0": {
-      "content": "<unk>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "92352": {
-      "content": "Ｅ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92353": {
-      "content": "Ｆ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92354": {
-      "content": "Ｇ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92355": {
-      "content": "Ｈ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92356": {
-      "content": "Ｉ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92357": {
-      "content": "Ｊ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92358": {
-      "content": "Ｋ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92359": {
-      "content": "Ｌ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92360": {
-      "content": "Ｍ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92361": {
-      "content": "Ｎ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92362": {
-      "content": "Ｒ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92363": {
-      "content": "Ｕ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92364": {
-      "content": "Ｖ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92365": {
-      "content": "Ｗ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92366": {
-      "content": "Ｘ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92367": {
-      "content": "Ｙ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92368": {
-      "content": "Ｚ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92369": {
-      "content": "ａ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92370": {
-      "content": "ｂ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92371": {
-      "content": "ｃ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92372": {
-      "content": "ｄ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92373": {
-      "content": "ｅ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92374": {
-      "content": "ｆ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92375": {
-      "content": "ｇ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92376": {
-      "content": "ｈ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92377": {
-      "content": "ｉ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92378": {
-      "content": "ｊ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92379": {
-      "content": "ｋ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92380": {
-      "content": "ｌ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92381": {
-      "content": "ｍ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92382": {
-      "content": "ｎ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92383": {
-      "content": "ｏ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92384": {
-      "content": "ｐ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92385": {
-      "content": "ｑ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92386": {
-      "content": "ｒ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92387": {
-      "content": "ｓ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92388": {
-      "content": "ｔ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92389": {
-      "content": "ｕ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92390": {
-      "content": "ｖ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92391": {
-      "content": "ｗ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92392": {
-      "content": "ｘ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92393": {
-      "content": "ｙ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92394": {
-      "content": "ｚ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92395": {
-      "content": "——",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92396": {
-      "content": "……",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92397": {
-      "content": "[UNUSED_TOKEN_0]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92398": {
-      "content": "[UNUSED_TOKEN_1]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92399": {
-      "content": "[UNUSED_TOKEN_2]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92400": {
-      "content": "[UNUSED_TOKEN_3]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92401": {
-      "content": "[UNUSED_TOKEN_4]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92402": {
-      "content": "[UNUSED_TOKEN_5]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92403": {
-      "content": "[UNUSED_TOKEN_6]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92404": {
-      "content": "[UNUSED_TOKEN_7]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92405": {
-      "content": "[UNUSED_TOKEN_8]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92406": {
-      "content": "[UNUSED_TOKEN_9]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92407": {
-      "content": "[UNUSED_TOKEN_10]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92408": {
-      "content": "[UNUSED_TOKEN_11]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92409": {
-      "content": "[UNUSED_TOKEN_12]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92410": {
-      "content": "[UNUSED_TOKEN_13]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92411": {
-      "content": "[UNUSED_TOKEN_14]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92412": {
-      "content": "[UNUSED_TOKEN_15]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92413": {
-      "content": "[UNUSED_TOKEN_16]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92414": {
-      "content": "[UNUSED_TOKEN_17]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92415": {
-      "content": "[UNUSED_TOKEN_18]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92416": {
-      "content": "[UNUSED_TOKEN_19]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92417": {
-      "content": "[UNUSED_TOKEN_20]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92418": {
-      "content": "[UNUSED_TOKEN_21]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92419": {
-      "content": "[UNUSED_TOKEN_22]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92420": {
-      "content": "[UNUSED_TOKEN_23]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92421": {
-      "content": "[UNUSED_TOKEN_24]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92422": {
-      "content": "[UNUSED_TOKEN_25]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92423": {
-      "content": "[UNUSED_TOKEN_26]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92424": {
-      "content": "[UNUSED_TOKEN_27]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92425": {
-      "content": "[UNUSED_TOKEN_28]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92426": {
-      "content": "[UNUSED_TOKEN_29]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92427": {
-      "content": "[UNUSED_TOKEN_30]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92428": {
-      "content": "[UNUSED_TOKEN_31]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92429": {
-      "content": "[UNUSED_TOKEN_32]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92430": {
-      "content": "[UNUSED_TOKEN_33]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92431": {
-      "content": "[UNUSED_TOKEN_34]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92432": {
-      "content": "[UNUSED_TOKEN_35]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92433": {
-      "content": "[UNUSED_TOKEN_36]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92434": {
-      "content": "[UNUSED_TOKEN_37]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92435": {
-      "content": "[UNUSED_TOKEN_38]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92436": {
-      "content": "[UNUSED_TOKEN_39]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92437": {
-      "content": "[UNUSED_TOKEN_40]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92438": {
-      "content": "[UNUSED_TOKEN_41]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92439": {
-      "content": "[UNUSED_TOKEN_42]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92440": {
-      "content": "[UNUSED_TOKEN_43]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92441": {
-      "content": "[UNUSED_TOKEN_44]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92442": {
-      "content": "[UNUSED_TOKEN_45]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92443": {
-      "content": "[UNUSED_TOKEN_46]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92444": {
-      "content": "[UNUSED_TOKEN_47]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92445": {
-      "content": "[UNUSED_TOKEN_48]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92446": {
-      "content": "[UNUSED_TOKEN_49]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92447": {
-      "content": "[UNUSED_TOKEN_50]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92448": {
-      "content": "[UNUSED_TOKEN_51]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92449": {
-      "content": "[UNUSED_TOKEN_52]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92450": {
-      "content": "[UNUSED_TOKEN_53]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92451": {
-      "content": "[UNUSED_TOKEN_54]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92452": {
-      "content": "[UNUSED_TOKEN_55]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92453": {
-      "content": "[UNUSED_TOKEN_56]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92454": {
-      "content": "[UNUSED_TOKEN_57]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92455": {
-      "content": "[UNUSED_TOKEN_58]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92456": {
-      "content": "[UNUSED_TOKEN_59]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92457": {
-      "content": "[UNUSED_TOKEN_60]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92458": {
-      "content": "[UNUSED_TOKEN_61]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92459": {
-      "content": "[UNUSED_TOKEN_62]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92460": {
-      "content": "[UNUSED_TOKEN_63]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92461": {
-      "content": "[UNUSED_TOKEN_64]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92462": {
-      "content": "[UNUSED_TOKEN_65]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92463": {
-      "content": "[UNUSED_TOKEN_66]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92464": {
-      "content": "[UNUSED_TOKEN_67]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92465": {
-      "content": "[UNUSED_TOKEN_68]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92466": {
-      "content": "[UNUSED_TOKEN_69]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92467": {
-      "content": "[UNUSED_TOKEN_70]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92468": {
-      "content": "[UNUSED_TOKEN_71]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92469": {
-      "content": "[UNUSED_TOKEN_72]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92470": {
-      "content": "[UNUSED_TOKEN_73]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92471": {
-      "content": "[UNUSED_TOKEN_74]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92472": {
-      "content": "[UNUSED_TOKEN_75]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92473": {
-      "content": "[UNUSED_TOKEN_76]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92474": {
-      "content": "[UNUSED_TOKEN_77]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92475": {
-      "content": "[UNUSED_TOKEN_78]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92476": {
-      "content": "[UNUSED_TOKEN_79]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92477": {
-      "content": "[UNUSED_TOKEN_80]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92478": {
-      "content": "[UNUSED_TOKEN_81]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92479": {
-      "content": "[UNUSED_TOKEN_82]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92480": {
-      "content": "[UNUSED_TOKEN_83]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92481": {
-      "content": "[UNUSED_TOKEN_84]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92482": {
-      "content": "[UNUSED_TOKEN_85]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92483": {
-      "content": "[UNUSED_TOKEN_86]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92484": {
-      "content": "[UNUSED_TOKEN_87]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92485": {
-      "content": "[UNUSED_TOKEN_88]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92486": {
-      "content": "[UNUSED_TOKEN_89]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92487": {
-      "content": "[UNUSED_TOKEN_90]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92488": {
-      "content": "[UNUSED_TOKEN_91]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92489": {
-      "content": "[UNUSED_TOKEN_92]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92490": {
-      "content": "[UNUSED_TOKEN_93]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92491": {
-      "content": "[UNUSED_TOKEN_94]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92492": {
-      "content": "[UNUSED_TOKEN_95]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92493": {
-      "content": "[UNUSED_TOKEN_96]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92494": {
-      "content": "[UNUSED_TOKEN_97]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92495": {
-      "content": "[UNUSED_TOKEN_98]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92496": {
-      "content": "[UNUSED_TOKEN_99]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92497": {
-      "content": "[UNUSED_TOKEN_100]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92498": {
-      "content": "[UNUSED_TOKEN_101]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92499": {
-      "content": "[UNUSED_TOKEN_102]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92500": {
-      "content": "[UNUSED_TOKEN_103]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92501": {
-      "content": "[UNUSED_TOKEN_104]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92502": {
-      "content": "[UNUSED_TOKEN_105]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92503": {
-      "content": "[UNUSED_TOKEN_106]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92504": {
-      "content": "[UNUSED_TOKEN_107]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92505": {
-      "content": "[UNUSED_TOKEN_108]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92506": {
-      "content": "[UNUSED_TOKEN_109]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92507": {
-      "content": "[UNUSED_TOKEN_110]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92508": {
-      "content": "[UNUSED_TOKEN_111]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92509": {
-      "content": "[UNUSED_TOKEN_112]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92510": {
-      "content": "[UNUSED_TOKEN_113]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92511": {
-      "content": "[UNUSED_TOKEN_114]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92512": {
-      "content": "[UNUSED_TOKEN_115]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92513": {
-      "content": "[UNUSED_TOKEN_116]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92514": {
-      "content": "[UNUSED_TOKEN_117]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92515": {
-      "content": "[UNUSED_TOKEN_118]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92516": {
-      "content": "[UNUSED_TOKEN_119]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92517": {
-      "content": "[UNUSED_TOKEN_120]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92518": {
-      "content": "[UNUSED_TOKEN_121]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92519": {
-      "content": "[UNUSED_TOKEN_122]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92520": {
-      "content": "[UNUSED_TOKEN_123]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92521": {
-      "content": "[UNUSED_TOKEN_124]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92522": {
-      "content": "[UNUSED_TOKEN_125]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92523": {
-      "content": "[UNUSED_TOKEN_126]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92524": {
-      "content": "[UNUSED_TOKEN_127]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92525": {
-      "content": "[UNUSED_TOKEN_128]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92526": {
-      "content": "[UNUSED_TOKEN_129]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92527": {
-      "content": "[UNUSED_TOKEN_130]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92528": {
-      "content": "[UNUSED_TOKEN_131]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92529": {
-      "content": "[UNUSED_TOKEN_132]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92530": {
-      "content": "[UNUSED_TOKEN_133]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92531": {
-      "content": "[UNUSED_TOKEN_134]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92532": {
-      "content": "[UNUSED_TOKEN_135]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92533": {
-      "content": "[UNUSED_TOKEN_136]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92534": {
-      "content": "[UNUSED_TOKEN_137]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92535": {
-      "content": "[UNUSED_TOKEN_138]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92536": {
-      "content": "[UNUSED_TOKEN_139]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92537": {
-      "content": "[UNUSED_TOKEN_140]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92538": {
-      "content": "<|plugin|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "92539": {
-      "content": "<|interpreter|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "92540": {
-      "content": "<|action_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "92541": {
-      "content": "<|action_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "92542": {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "92543": {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "92544": {
-      "content": "[UNUSED_TOKEN_141]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92545": {
-      "content": "[UNUSED_TOKEN_142]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92546": {
-      "content": "[UNUSED_TOKEN_143]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92547": {
-      "content": "[UNUSED_TOKEN_144]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92548": {
-      "content": "[UNUSED_TOKEN_145]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92549": {
-      "content": "[UNUSED_TOKEN_146]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    }
-  },
-  "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>",
-    "<|action_start|>",
-    "<|action_end|>",
-    "<|interpreter|>",
-    "<|plugin|>"
-  ],
-  "auto_map": {
-    "AutoTokenizer": [
-      "tokenization_internlm2.InternLM2Tokenizer",
-      "tokenization_internlm2_fast.InternLM2TokenizerFast"
-    ]
-  },
-  "bos_token": "<s>",
-  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
-  "clean_up_tokenization_spaces": false,
-  "decode_with_prefix_space": false,
-  "eos_token": "<|im_end|>",
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "</s>",
-  "padding_side": "right",
-  "sp_model_kwargs": null,
-  "split_special_tokens": false,
-  "tokenizer_class": "InternLM2Tokenizer",
-  "unk_token": "<unk>"
-}

llama-factory/saves/internlm2_5_7b/lora/sft/checkpoint-1686/trainer_state.json

@@ -1,169 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 2.997333333333333,
-  "eval_steps": 562,
-  "global_step": 1686,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.17777777777777778,
-      "grad_norm": 4.040336608886719,
-      "learning_rate": 2.958579881656805e-05,
-      "loss": 0.4641,
-      "step": 100
-    },
-    {
-      "epoch": 0.35555555555555557,
-      "grad_norm": 3.9950191974639893,
-      "learning_rate": 5.91715976331361e-05,
-      "loss": 0.3704,
-      "step": 200
-    },
-    {
-      "epoch": 0.5333333333333333,
-      "grad_norm": 3.9038829803466797,
-      "learning_rate": 8.875739644970414e-05,
-      "loss": 0.3751,
-      "step": 300
-    },
-    {
-      "epoch": 0.7111111111111111,
-      "grad_norm": 3.4998044967651367,
-      "learning_rate": 9.989699867437137e-05,
-      "loss": 0.3928,
-      "step": 400
-    },
-    {
-      "epoch": 0.8888888888888888,
-      "grad_norm": 9.73261833190918,
-      "learning_rate": 9.92981892269398e-05,
-      "loss": 0.3497,
-      "step": 500
-    },
-    {
-      "epoch": 0.9991111111111111,
-      "eval_loss": 0.6006748080253601,
-      "eval_runtime": 411.5999,
-      "eval_samples_per_second": 1.215,
-      "eval_steps_per_second": 1.215,
-      "step": 562
-    },
-    {
-      "epoch": 1.0666666666666667,
-      "grad_norm": 2.8831710815429688,
-      "learning_rate": 9.817128546774103e-05,
-      "loss": 0.3383,
-      "step": 600
-    },
-    {
-      "epoch": 1.2444444444444445,
-      "grad_norm": 6.632827281951904,
-      "learning_rate": 9.652835906663704e-05,
-      "loss": 0.3167,
-      "step": 700
-    },
-    {
-      "epoch": 1.4222222222222223,
-      "grad_norm": 6.977548122406006,
-      "learning_rate": 9.438700945477697e-05,
-      "loss": 0.3165,
-      "step": 800
-    },
-    {
-      "epoch": 1.6,
-      "grad_norm": 10.037060737609863,
-      "learning_rate": 9.177017529516772e-05,
-      "loss": 0.2927,
-      "step": 900
-    },
-    {
-      "epoch": 1.7777777777777777,
-      "grad_norm": 6.976019859313965,
-      "learning_rate": 8.870588875808164e-05,
-      "loss": 0.3062,
-      "step": 1000
-    },
-    {
-      "epoch": 1.9555555555555557,
-      "grad_norm": 2.106227159500122,
-      "learning_rate": 8.522697523356319e-05,
-      "loss": 0.2678,
-      "step": 1100
-    },
-    {
-      "epoch": 1.9982222222222221,
-      "eval_loss": 0.3569962680339813,
-      "eval_runtime": 367.3155,
-      "eval_samples_per_second": 1.361,
-      "eval_steps_per_second": 1.361,
-      "step": 1124
-    },
-    {
-      "epoch": 2.1333333333333333,
-      "grad_norm": 2.639159679412842,
-      "learning_rate": 8.137070169778812e-05,
-      "loss": 0.2198,
-      "step": 1200
-    },
-    {
-      "epoch": 2.311111111111111,
-      "grad_norm": 3.6480841636657715,
-      "learning_rate": 7.717837750006106e-05,
-      "loss": 0.2412,
-      "step": 1300
-    },
-    {
-      "epoch": 2.488888888888889,
-      "grad_norm": 2.240994930267334,
-      "learning_rate": 7.269491184691924e-05,
-      "loss": 0.1952,
-      "step": 1400
-    },
-    {
-      "epoch": 2.6666666666666665,
-      "grad_norm": 13.413070678710938,
-      "learning_rate": 6.79683327236813e-05,
-      "loss": 0.2262,
-      "step": 1500
-    },
-    {
-      "epoch": 2.8444444444444446,
-      "grad_norm": 0.8566445112228394,
-      "learning_rate": 6.304927240687181e-05,
-      "loss": 0.1949,
-      "step": 1600
-    },
-    {
-      "epoch": 2.997333333333333,
-      "eval_loss": 0.42686474323272705,
-      "eval_runtime": 365.7769,
-      "eval_samples_per_second": 1.367,
-      "eval_steps_per_second": 1.367,
-      "step": 1686
-    }
-  ],
-  "logging_steps": 100,
-  "max_steps": 3372,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 6,
-  "save_steps": 562,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": false
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 2.033572224618332e+17,
-  "train_batch_size": 1,
-  "trial_name": null,
-  "trial_params": null
-}

llama-factory/saves/internlm2_5_7b/lora/sft/checkpoint-1686/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:aee0526e63b02d5d5f300a2e1dfcfcc13e168aae73493f8d596712a07178876b
-size 5304

llama-factory/saves/internlm2_5_7b/lora/sft/checkpoint-2248/README.md

@@ -1,202 +0,0 @@
----
-library_name: peft
-base_model: internlm/internlm2_5-7b-chat-1m
----
-
-# Model Card for Model ID
-
-<!-- Provide a quick summary of what the model is/does. -->
-
-
-
-## Model Details
-
-### Model Description
-
-<!-- Provide a longer summary of what this model is. -->
-
-
-
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-
-### Model Sources [optional]
-
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-
-## Uses
-
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
-### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
-
-### Downstream Use [optional]
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
-
-### Out-of-Scope Use
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
-
-## Bias, Risks, and Limitations
-
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
-
-### Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-
-## How to Get Started with the Model
-
-Use the code below to get started with the model.
-
-[More Information Needed]
-
-## Training Details
-
-### Training Data
-
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
-### Training Procedure
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
-[More Information Needed]
-### Framework versions
-
-- PEFT 0.11.1

llama-factory/saves/internlm2_5_7b/lora/sft/checkpoint-2248/adapter_config.json

@@ -1,32 +0,0 @@
-{
-  "alpha_pattern": {},
-  "auto_mapping": null,
-  "base_model_name_or_path": "internlm/internlm2_5-7b-chat-1m",
-  "bias": "none",
-  "fan_in_fan_out": false,
-  "inference_mode": true,
-  "init_lora_weights": true,
-  "layer_replication": null,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "loftq_config": {},
-  "lora_alpha": 16,
-  "lora_dropout": 0.0,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "r": 8,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "w3",
-    "wo",
-    "w1",
-    "wqkv",
-    "w2"
-  ],
-  "task_type": "CAUSAL_LM",
-  "use_dora": false,
-  "use_rslora": false
-}

llama-factory/saves/internlm2_5_7b/lora/sft/checkpoint-2248/adapter_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7c9c1e3de94ce17bac71870c9fdb4f38ee793dedf63408a300be4f77a3e99d52
-size 75539712

llama-factory/saves/internlm2_5_7b/lora/sft/checkpoint-2248/added_tokens.json

@@ -1,8 +0,0 @@
-{
-  "[UNUSED_TOKEN_141]": 92544,
-  "[UNUSED_TOKEN_142]": 92545,
-  "[UNUSED_TOKEN_143]": 92546,
-  "[UNUSED_TOKEN_144]": 92547,
-  "[UNUSED_TOKEN_145]": 92548,
-  "[UNUSED_TOKEN_146]": 92549
-}

llama-factory/saves/internlm2_5_7b/lora/sft/checkpoint-2248/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4637115ef19bf33a9b74063e48b805549dfd0582b7a622f402223671dbfc201c
-size 151264058

llama-factory/saves/internlm2_5_7b/lora/sft/checkpoint-2248/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9899ccda7f0d8d9511991180b93aab508ce6e8489de708c88ad1188e7e1d90d6
-size 14244

llama-factory/saves/internlm2_5_7b/lora/sft/checkpoint-2248/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:999d23797fcc8ea5f6c9314d2f36a0519a6c95f473b2a0839184c31f854432ee
-size 1064

llama-factory/saves/internlm2_5_7b/lora/sft/checkpoint-2248/special_tokens_map.json

@@ -1,38 +0,0 @@
-{
-  "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>",
-    "<|action_start|>",
-    "<|action_end|>",
-    "<|interpreter|>",
-    "<|plugin|>"
-  ],
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "<|im_end|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
-}

llama-factory/saves/internlm2_5_7b/lora/sft/checkpoint-2248/tokenization_internlm2.py

@@ -1,236 +0,0 @@
-# coding=utf-8
-# Copyright (c) The InternLM team and The HuggingFace Inc. team. All rights reserved.
-#
-# This code is based on transformers/src/transformers/models/llama/tokenization_llama.py
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-"""Tokenization classes for InternLM."""
-import os
-from shutil import copyfile
-from typing import Any, Dict, List, Optional, Tuple
-
-import sentencepiece as spm
-from transformers.tokenization_utils import PreTrainedTokenizer
-from transformers.utils import logging
-
-logger = logging.get_logger(__name__)
-
-VOCAB_FILES_NAMES = {"vocab_file": "./tokenizer.model"}
-
-PRETRAINED_VOCAB_FILES_MAP = {}
-
-
-# Modified from transformers.model.llama.tokenization_llama.LlamaTokenizer
-class InternLM2Tokenizer(PreTrainedTokenizer):
-    """
-    Construct a InternLM2 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
-    model_input_names = ["input_ids", "attention_mask"]
-    _auto_class = "AutoTokenizer"
-
-    def __init__(
-        self,
-        vocab_file,
-        unk_token="<unk>",
-        bos_token="<s>",
-        eos_token="</s>",
-        pad_token="</s>",
-        sp_model_kwargs: Optional[Dict[str, Any]] = None,
-        add_bos_token=True,
-        add_eos_token=False,
-        decode_with_prefix_space=False,
-        clean_up_tokenization_spaces=False,
-        **kwargs,
-    ):
-        self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
-        self.vocab_file = vocab_file
-        self.add_bos_token = add_bos_token
-        self.add_eos_token = add_eos_token
-        self.decode_with_prefix_space = decode_with_prefix_space
-        self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
-        self.sp_model.Load(vocab_file)
-        self._no_prefix_space_tokens = None
-        super().__init__(
-            bos_token=bos_token,
-            eos_token=eos_token,
-            unk_token=unk_token,
-            pad_token=pad_token,
-            clean_up_tokenization_spaces=clean_up_tokenization_spaces,
-            **kwargs,
-        )
-
-    @property
-    def no_prefix_space_tokens(self):
-        if self._no_prefix_space_tokens is None:
-            vocab = self.convert_ids_to_tokens(list(range(self.vocab_size)))
-            self._no_prefix_space_tokens = {i for i, tok in enumerate(vocab) if not tok.startswith("▁")}
-        return self._no_prefix_space_tokens
-
-    @property
-    def vocab_size(self):
-        """Returns vocab size"""
-        return self.sp_model.get_piece_size()
-
-    @property
-    def bos_token_id(self) -> Optional[int]:
-        return self.sp_model.bos_id()
-
-    @property
-    def eos_token_id(self) -> Optional[int]:
-        return self.sp_model.eos_id()
-
-    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 _maybe_add_prefix_space(self, tokens, decoded):
-        if tokens and tokens[0] not in self.no_prefix_space_tokens:
-            return " " + decoded
-        else:
-            return decoded
-
-    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 token in tokens:
-            # make sure that special tokens are not decoded using sentencepiece model
-            if token in self.all_special_tokens:
-                if not prev_is_special:
-                    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)
-        out_string = self.clean_up_tokenization(out_string)
-        out_string = self._maybe_add_prefix_space(tokens=tokens, decoded=out_string)
-        return out_string[1:]
-
-    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):
-        if self.add_bos_token:
-            bos_token_ids = [self.bos_token_id]
-        else:
-            bos_token_ids = []
-
-        output = bos_token_ids + token_ids_0
-
-        if token_ids_1 is not None:
-            output = output + token_ids_1
-
-        if self.add_eos_token:
-            output = output + [self.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
-            )
-
-        if token_ids_1 is None:
-            return [1] + ([0] * len(token_ids_0)) + [1]
-        return [1] + ([0] * len(token_ids_0)) + [1, 1] + ([0] * len(token_ids_1)) + [1]
-
-    def create_token_type_ids_from_sequences(
-        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
-    ) -> List[int]:
-        """
-        Create a mask from the two sequences passed to be used in a sequence-pair classification task. T5 does not make
-        use of token type ids, therefore a list of zeros is returned.
-
-        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 zeros.
-        """
-        eos = [self.eos_token_id]
-
-        if token_ids_1 is None:
-            return len(token_ids_0 + eos) * [0]
-        return len(token_ids_0 + eos + token_ids_1 + eos) * [0]

llama-factory/saves/internlm2_5_7b/lora/sft/checkpoint-2248/tokenization_internlm2_fast.py

@@ -1,214 +0,0 @@
-# coding=utf-8
-# Copyright (c) The InternLM team and The HuggingFace Inc. team. All rights reserved.
-#
-# This code is based on transformers/src/transformers/models/llama/tokenization_llama_fast.py
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-"""Tokenization Fast class for InternLM."""
-import os
-from shutil import copyfile
-from typing import Any, Dict, Optional, Tuple
-
-from tokenizers import processors, decoders, Tokenizer, normalizers
-from tokenizers.models import BPE
-
-from transformers.tokenization_utils_fast import PreTrainedTokenizerFast
-from transformers.utils import logging
-
-from transformers.convert_slow_tokenizer import (
-    SLOW_TO_FAST_CONVERTERS,
-    SpmConverter,
-    SentencePieceExtractor,
-)
-
-from .tokenization_internlm2 import InternLM2Tokenizer
-
-logger = logging.get_logger(__name__)
-
-VOCAB_FILES_NAMES = {"vocab_file": "./tokenizer.model"}
-
-# Modified from transformers.convert_slow_tokenizer.LlamaConverter
-class InternLM2Converter(SpmConverter):
-    handle_byte_fallback = True
-
-    def vocab(self, proto):
-        vocab = [
-            ("<unk>", 0.0),
-            ("<s>", 0.0),
-            ("</s>", 0.0),
-        ]
-        vocab += [(piece.piece, piece.score) for piece in proto.pieces[3:]]
-        return vocab
-
-    def unk_id(self, proto):
-        unk_id = 0
-        return unk_id
-
-    def decoder(self, replacement, add_prefix_space):
-        decoders_sequence = [
-            decoders.Replace("▁", " "),
-            decoders.ByteFallback(),
-            decoders.Fuse(),
-        ]
-        if self.proto.normalizer_spec.add_dummy_prefix:
-            decoders_sequence.append(decoders.Strip(content=" ", left=1))
-        return decoders.Sequence(decoders_sequence)
-
-    def tokenizer(self, proto):
-        model_type = proto.trainer_spec.model_type
-        vocab_scores = self.vocab(proto)
-        # special tokens
-        added_tokens = self.original_tokenizer.added_tokens_decoder
-        for i in range(len(vocab_scores)):
-            piece, score = vocab_scores[i]
-            if i in added_tokens:
-                vocab_scores[i] = (added_tokens[i].content, score)
-        if model_type == 1:
-            raise RuntimeError("InternLM2 is supposed to be a BPE model!")
-
-        elif model_type == 2:
-            _, merges = SentencePieceExtractor(self.original_tokenizer.vocab_file).extract(vocab_scores)
-            bpe_vocab = {word: i for i, (word, _score) in enumerate(vocab_scores)}
-            tokenizer = Tokenizer(
-                BPE(bpe_vocab, merges, unk_token=proto.trainer_spec.unk_piece, fuse_unk=True, byte_fallback=True)
-            )
-            tokenizer.add_special_tokens(
-                [ added_token for index, added_token in added_tokens.items()]
-            )
-        else:
-            raise Exception(
-                "You're trying to run a `Unigram` model but you're file was trained with a different algorithm"
-            )
-
-        return tokenizer
-
-    def normalizer(self, proto):
-        normalizers_list = []
-        if proto.normalizer_spec.add_dummy_prefix:
-            normalizers_list.append(normalizers.Prepend(prepend="▁"))
-        normalizers_list.append(normalizers.Replace(pattern=" ", content="▁"))
-        return normalizers.Sequence(normalizers_list)
-
-    def pre_tokenizer(self, replacement, add_prefix_space):
-        return None
-
-SLOW_TO_FAST_CONVERTERS["InternLM2Tokenizer"] = InternLM2Converter
-
-
-# Modified from transformers.model.llama.tokenization_llama_fast.LlamaTokenizerFast -> InternLM2TokenizerFast
-class InternLM2TokenizerFast(PreTrainedTokenizerFast):
-    vocab_files_names = VOCAB_FILES_NAMES
-    slow_tokenizer_class = InternLM2Tokenizer
-    padding_side = "left"
-    model_input_names = ["input_ids", "attention_mask"]
-    _auto_class = "AutoTokenizer"
-
-    def __init__(
-        self,
-        vocab_file,
-        unk_token="<unk>",
-        bos_token="<s>",
-        eos_token="</s>",
-        pad_token="</s>",
-        sp_model_kwargs: Optional[Dict[str, Any]] = None,
-        add_bos_token=True,
-        add_eos_token=False,
-        decode_with_prefix_space=False,
-        clean_up_tokenization_spaces=False,
-        **kwargs,
-    ):
-        super().__init__(
-            vocab_file=vocab_file,
-            unk_token=unk_token,
-            bos_token=bos_token,
-            eos_token=eos_token,
-            pad_token=pad_token,
-            sp_model_kwargs=sp_model_kwargs,
-            add_bos_token=add_bos_token,
-            add_eos_token=add_eos_token,
-            decode_with_prefix_space=decode_with_prefix_space,
-            clean_up_tokenization_spaces=clean_up_tokenization_spaces,
-            **kwargs,
-        )
-        self._add_bos_token = add_bos_token
-        self._add_eos_token = add_eos_token
-        self.update_post_processor()
-        self.vocab_file = vocab_file
-
-    @property
-    def can_save_slow_tokenizer(self) -> bool:
-        return os.path.isfile(self.vocab_file) if self.vocab_file else False
-
-    def update_post_processor(self):
-        """
-        Updates the underlying post processor with the current `bos_token` and `eos_token`.
-        """
-        bos = self.bos_token
-        bos_token_id = self.bos_token_id
-        if bos is None and self.add_bos_token:
-            raise ValueError("add_bos_token = True but bos_token = None")
-
-        eos = self.eos_token
-        eos_token_id = self.eos_token_id
-        if eos is None and self.add_eos_token:
-            raise ValueError("add_eos_token = True but eos_token = None")
-
-        single = f"{(bos+':0 ') if self.add_bos_token else ''}$A:0{(' '+eos+':0') if self.add_eos_token else ''}"
-        pair = f"{single}{(' '+bos+':1') if self.add_bos_token else ''} $B:1{(' '+eos+':1') if self.add_eos_token else ''}"
-
-        special_tokens = []
-        if self.add_bos_token:
-            special_tokens.append((bos, bos_token_id))
-        if self.add_eos_token:
-            special_tokens.append((eos, eos_token_id))
-        self._tokenizer.post_processor = processors.TemplateProcessing(
-            single=single, pair=pair, special_tokens=special_tokens
-        )
-
-    @property
-    def add_eos_token(self):
-        return self._add_eos_token
-
-    @property
-    def add_bos_token(self):
-        return self._add_bos_token
-
-    @add_eos_token.setter
-    def add_eos_token(self, value):
-        self._add_eos_token = value
-        self.update_post_processor()
-
-    @add_bos_token.setter
-    def add_bos_token(self, value):
-        self._add_bos_token = value
-        self.update_post_processor()
-
-    def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None) -> Tuple[str]:
-        if not self.can_save_slow_tokenizer:
-            raise ValueError(
-                "Your fast tokenizer does not have the necessary information to save the vocabulary for a slow "
-                "tokenizer."
-            )
-
-        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):
-            copyfile(self.vocab_file, out_vocab_file)
-
-        return (out_vocab_file,)

llama-factory/saves/internlm2_5_7b/lora/sft/checkpoint-2248/tokenizer.model

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f868398fc4e05ee1e8aeba95ddf18ddcc45b8bce55d5093bead5bbf80429b48b
-size 1477754

llama-factory/saves/internlm2_5_7b/lora/sft/checkpoint-2248/tokenizer_config.json

@@ -1,1640 +0,0 @@
-{
-  "add_bos_token": true,
-  "add_eos_token": false,
-  "added_tokens_decoder": {
-    "0": {
-      "content": "<unk>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "92352": {
-      "content": "Ｅ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92353": {
-      "content": "Ｆ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92354": {
-      "content": "Ｇ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92355": {
-      "content": "Ｈ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92356": {
-      "content": "Ｉ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92357": {
-      "content": "Ｊ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92358": {
-      "content": "Ｋ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92359": {
-      "content": "Ｌ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92360": {
-      "content": "Ｍ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92361": {
-      "content": "Ｎ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92362": {
-      "content": "Ｒ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92363": {
-      "content": "Ｕ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92364": {
-      "content": "Ｖ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92365": {
-      "content": "Ｗ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92366": {
-      "content": "Ｘ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92367": {
-      "content": "Ｙ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92368": {
-      "content": "Ｚ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92369": {
-      "content": "ａ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92370": {
-      "content": "ｂ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92371": {
-      "content": "ｃ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92372": {
-      "content": "ｄ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92373": {
-      "content": "ｅ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92374": {
-      "content": "ｆ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92375": {
-      "content": "ｇ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92376": {
-      "content": "ｈ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92377": {
-      "content": "ｉ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92378": {
-      "content": "ｊ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92379": {
-      "content": "ｋ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92380": {
-      "content": "ｌ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92381": {
-      "content": "ｍ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92382": {
-      "content": "ｎ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92383": {
-      "content": "ｏ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92384": {
-      "content": "ｐ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92385": {
-      "content": "ｑ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92386": {
-      "content": "ｒ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92387": {
-      "content": "ｓ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92388": {
-      "content": "ｔ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92389": {
-      "content": "ｕ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92390": {
-      "content": "ｖ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92391": {
-      "content": "ｗ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92392": {
-      "content": "ｘ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92393": {
-      "content": "ｙ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92394": {
-      "content": "ｚ",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92395": {
-      "content": "——",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92396": {
-      "content": "……",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92397": {
-      "content": "[UNUSED_TOKEN_0]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92398": {
-      "content": "[UNUSED_TOKEN_1]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92399": {
-      "content": "[UNUSED_TOKEN_2]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92400": {
-      "content": "[UNUSED_TOKEN_3]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92401": {
-      "content": "[UNUSED_TOKEN_4]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92402": {
-      "content": "[UNUSED_TOKEN_5]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92403": {
-      "content": "[UNUSED_TOKEN_6]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92404": {
-      "content": "[UNUSED_TOKEN_7]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92405": {
-      "content": "[UNUSED_TOKEN_8]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92406": {
-      "content": "[UNUSED_TOKEN_9]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92407": {
-      "content": "[UNUSED_TOKEN_10]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92408": {
-      "content": "[UNUSED_TOKEN_11]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92409": {
-      "content": "[UNUSED_TOKEN_12]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92410": {
-      "content": "[UNUSED_TOKEN_13]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92411": {
-      "content": "[UNUSED_TOKEN_14]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92412": {
-      "content": "[UNUSED_TOKEN_15]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92413": {
-      "content": "[UNUSED_TOKEN_16]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92414": {
-      "content": "[UNUSED_TOKEN_17]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92415": {
-      "content": "[UNUSED_TOKEN_18]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92416": {
-      "content": "[UNUSED_TOKEN_19]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92417": {
-      "content": "[UNUSED_TOKEN_20]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92418": {
-      "content": "[UNUSED_TOKEN_21]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92419": {
-      "content": "[UNUSED_TOKEN_22]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92420": {
-      "content": "[UNUSED_TOKEN_23]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92421": {
-      "content": "[UNUSED_TOKEN_24]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92422": {
-      "content": "[UNUSED_TOKEN_25]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92423": {
-      "content": "[UNUSED_TOKEN_26]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92424": {
-      "content": "[UNUSED_TOKEN_27]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92425": {
-      "content": "[UNUSED_TOKEN_28]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92426": {
-      "content": "[UNUSED_TOKEN_29]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92427": {
-      "content": "[UNUSED_TOKEN_30]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92428": {
-      "content": "[UNUSED_TOKEN_31]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92429": {
-      "content": "[UNUSED_TOKEN_32]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92430": {
-      "content": "[UNUSED_TOKEN_33]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92431": {
-      "content": "[UNUSED_TOKEN_34]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92432": {
-      "content": "[UNUSED_TOKEN_35]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92433": {
-      "content": "[UNUSED_TOKEN_36]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92434": {
-      "content": "[UNUSED_TOKEN_37]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92435": {
-      "content": "[UNUSED_TOKEN_38]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92436": {
-      "content": "[UNUSED_TOKEN_39]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92437": {
-      "content": "[UNUSED_TOKEN_40]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92438": {
-      "content": "[UNUSED_TOKEN_41]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92439": {
-      "content": "[UNUSED_TOKEN_42]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92440": {
-      "content": "[UNUSED_TOKEN_43]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92441": {
-      "content": "[UNUSED_TOKEN_44]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92442": {
-      "content": "[UNUSED_TOKEN_45]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92443": {
-      "content": "[UNUSED_TOKEN_46]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92444": {
-      "content": "[UNUSED_TOKEN_47]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92445": {
-      "content": "[UNUSED_TOKEN_48]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92446": {
-      "content": "[UNUSED_TOKEN_49]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92447": {
-      "content": "[UNUSED_TOKEN_50]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92448": {
-      "content": "[UNUSED_TOKEN_51]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92449": {
-      "content": "[UNUSED_TOKEN_52]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92450": {
-      "content": "[UNUSED_TOKEN_53]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92451": {
-      "content": "[UNUSED_TOKEN_54]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92452": {
-      "content": "[UNUSED_TOKEN_55]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92453": {
-      "content": "[UNUSED_TOKEN_56]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92454": {
-      "content": "[UNUSED_TOKEN_57]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92455": {
-      "content": "[UNUSED_TOKEN_58]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92456": {
-      "content": "[UNUSED_TOKEN_59]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92457": {
-      "content": "[UNUSED_TOKEN_60]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92458": {
-      "content": "[UNUSED_TOKEN_61]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92459": {
-      "content": "[UNUSED_TOKEN_62]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92460": {
-      "content": "[UNUSED_TOKEN_63]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92461": {
-      "content": "[UNUSED_TOKEN_64]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92462": {
-      "content": "[UNUSED_TOKEN_65]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92463": {
-      "content": "[UNUSED_TOKEN_66]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92464": {
-      "content": "[UNUSED_TOKEN_67]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92465": {
-      "content": "[UNUSED_TOKEN_68]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92466": {
-      "content": "[UNUSED_TOKEN_69]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92467": {
-      "content": "[UNUSED_TOKEN_70]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92468": {
-      "content": "[UNUSED_TOKEN_71]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92469": {
-      "content": "[UNUSED_TOKEN_72]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92470": {
-      "content": "[UNUSED_TOKEN_73]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92471": {
-      "content": "[UNUSED_TOKEN_74]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92472": {
-      "content": "[UNUSED_TOKEN_75]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92473": {
-      "content": "[UNUSED_TOKEN_76]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92474": {
-      "content": "[UNUSED_TOKEN_77]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92475": {
-      "content": "[UNUSED_TOKEN_78]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92476": {
-      "content": "[UNUSED_TOKEN_79]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92477": {
-      "content": "[UNUSED_TOKEN_80]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92478": {
-      "content": "[UNUSED_TOKEN_81]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92479": {
-      "content": "[UNUSED_TOKEN_82]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92480": {
-      "content": "[UNUSED_TOKEN_83]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92481": {
-      "content": "[UNUSED_TOKEN_84]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92482": {
-      "content": "[UNUSED_TOKEN_85]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92483": {
-      "content": "[UNUSED_TOKEN_86]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92484": {
-      "content": "[UNUSED_TOKEN_87]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92485": {
-      "content": "[UNUSED_TOKEN_88]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92486": {
-      "content": "[UNUSED_TOKEN_89]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92487": {
-      "content": "[UNUSED_TOKEN_90]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92488": {
-      "content": "[UNUSED_TOKEN_91]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92489": {
-      "content": "[UNUSED_TOKEN_92]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92490": {
-      "content": "[UNUSED_TOKEN_93]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92491": {
-      "content": "[UNUSED_TOKEN_94]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92492": {
-      "content": "[UNUSED_TOKEN_95]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92493": {
-      "content": "[UNUSED_TOKEN_96]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92494": {
-      "content": "[UNUSED_TOKEN_97]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92495": {
-      "content": "[UNUSED_TOKEN_98]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92496": {
-      "content": "[UNUSED_TOKEN_99]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92497": {
-      "content": "[UNUSED_TOKEN_100]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92498": {
-      "content": "[UNUSED_TOKEN_101]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92499": {
-      "content": "[UNUSED_TOKEN_102]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92500": {
-      "content": "[UNUSED_TOKEN_103]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92501": {
-      "content": "[UNUSED_TOKEN_104]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92502": {
-      "content": "[UNUSED_TOKEN_105]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92503": {
-      "content": "[UNUSED_TOKEN_106]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92504": {
-      "content": "[UNUSED_TOKEN_107]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92505": {
-      "content": "[UNUSED_TOKEN_108]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92506": {
-      "content": "[UNUSED_TOKEN_109]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92507": {
-      "content": "[UNUSED_TOKEN_110]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92508": {
-      "content": "[UNUSED_TOKEN_111]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92509": {
-      "content": "[UNUSED_TOKEN_112]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92510": {
-      "content": "[UNUSED_TOKEN_113]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92511": {
-      "content": "[UNUSED_TOKEN_114]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92512": {
-      "content": "[UNUSED_TOKEN_115]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92513": {
-      "content": "[UNUSED_TOKEN_116]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92514": {
-      "content": "[UNUSED_TOKEN_117]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92515": {
-      "content": "[UNUSED_TOKEN_118]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92516": {
-      "content": "[UNUSED_TOKEN_119]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92517": {
-      "content": "[UNUSED_TOKEN_120]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92518": {
-      "content": "[UNUSED_TOKEN_121]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92519": {
-      "content": "[UNUSED_TOKEN_122]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92520": {
-      "content": "[UNUSED_TOKEN_123]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92521": {
-      "content": "[UNUSED_TOKEN_124]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92522": {
-      "content": "[UNUSED_TOKEN_125]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92523": {
-      "content": "[UNUSED_TOKEN_126]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92524": {
-      "content": "[UNUSED_TOKEN_127]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92525": {
-      "content": "[UNUSED_TOKEN_128]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92526": {
-      "content": "[UNUSED_TOKEN_129]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92527": {
-      "content": "[UNUSED_TOKEN_130]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92528": {
-      "content": "[UNUSED_TOKEN_131]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92529": {
-      "content": "[UNUSED_TOKEN_132]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92530": {
-      "content": "[UNUSED_TOKEN_133]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92531": {
-      "content": "[UNUSED_TOKEN_134]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92532": {
-      "content": "[UNUSED_TOKEN_135]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92533": {
-      "content": "[UNUSED_TOKEN_136]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92534": {
-      "content": "[UNUSED_TOKEN_137]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92535": {
-      "content": "[UNUSED_TOKEN_138]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92536": {
-      "content": "[UNUSED_TOKEN_139]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92537": {
-      "content": "[UNUSED_TOKEN_140]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92538": {
-      "content": "<|plugin|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "92539": {
-      "content": "<|interpreter|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "92540": {
-      "content": "<|action_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "92541": {
-      "content": "<|action_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "92542": {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "92543": {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "92544": {
-      "content": "[UNUSED_TOKEN_141]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92545": {
-      "content": "[UNUSED_TOKEN_142]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92546": {
-      "content": "[UNUSED_TOKEN_143]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92547": {
-      "content": "[UNUSED_TOKEN_144]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92548": {
-      "content": "[UNUSED_TOKEN_145]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "92549": {
-      "content": "[UNUSED_TOKEN_146]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    }
-  },
-  "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>",
-    "<|action_start|>",
-    "<|action_end|>",
-    "<|interpreter|>",
-    "<|plugin|>"
-  ],
-  "auto_map": {
-    "AutoTokenizer": [
-      "tokenization_internlm2.InternLM2Tokenizer",
-      "tokenization_internlm2_fast.InternLM2TokenizerFast"
-    ]
-  },
-  "bos_token": "<s>",
-  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
-  "clean_up_tokenization_spaces": false,
-  "decode_with_prefix_space": false,
-  "eos_token": "<|im_end|>",
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "</s>",
-  "padding_side": "right",
-  "sp_model_kwargs": null,
-  "split_special_tokens": false,
-  "tokenizer_class": "InternLM2Tokenizer",
-  "unk_token": "<unk>"
-}

llama-factory/saves/internlm2_5_7b/lora/sft/checkpoint-2248/trainer_state.json

@@ -1,219 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 3.9964444444444442,
-  "eval_steps": 562,
-  "global_step": 2248,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.17777777777777778,
-      "grad_norm": 4.040336608886719,
-      "learning_rate": 2.958579881656805e-05,
-      "loss": 0.4641,
-      "step": 100
-    },
-    {
-      "epoch": 0.35555555555555557,
-      "grad_norm": 3.9950191974639893,
-      "learning_rate": 5.91715976331361e-05,
-      "loss": 0.3704,
-      "step": 200
-    },
-    {
-      "epoch": 0.5333333333333333,
-      "grad_norm": 3.9038829803466797,
-      "learning_rate": 8.875739644970414e-05,
-      "loss": 0.3751,
-      "step": 300
-    },
-    {
-      "epoch": 0.7111111111111111,
-      "grad_norm": 3.4998044967651367,
-      "learning_rate": 9.989699867437137e-05,
-      "loss": 0.3928,
-      "step": 400
-    },
-    {
-      "epoch": 0.8888888888888888,
-      "grad_norm": 9.73261833190918,
-      "learning_rate": 9.92981892269398e-05,
-      "loss": 0.3497,
-      "step": 500
-    },
-    {
-      "epoch": 0.9991111111111111,
-      "eval_loss": 0.6006748080253601,
-      "eval_runtime": 411.5999,
-      "eval_samples_per_second": 1.215,
-      "eval_steps_per_second": 1.215,
-      "step": 562
-    },
-    {
-      "epoch": 1.0666666666666667,
-      "grad_norm": 2.8831710815429688,
-      "learning_rate": 9.817128546774103e-05,
-      "loss": 0.3383,
-      "step": 600
-    },
-    {
-      "epoch": 1.2444444444444445,
-      "grad_norm": 6.632827281951904,
-      "learning_rate": 9.652835906663704e-05,
-      "loss": 0.3167,
-      "step": 700
-    },
-    {
-      "epoch": 1.4222222222222223,
-      "grad_norm": 6.977548122406006,
-      "learning_rate": 9.438700945477697e-05,
-      "loss": 0.3165,
-      "step": 800
-    },
-    {
-      "epoch": 1.6,
-      "grad_norm": 10.037060737609863,
-      "learning_rate": 9.177017529516772e-05,
-      "loss": 0.2927,
-      "step": 900
-    },
-    {
-      "epoch": 1.7777777777777777,
-      "grad_norm": 6.976019859313965,
-      "learning_rate": 8.870588875808164e-05,
-      "loss": 0.3062,
-      "step": 1000
-    },
-    {
-      "epoch": 1.9555555555555557,
-      "grad_norm": 2.106227159500122,
-      "learning_rate": 8.522697523356319e-05,
-      "loss": 0.2678,
-      "step": 1100
-    },
-    {
-      "epoch": 1.9982222222222221,
-      "eval_loss": 0.3569962680339813,
-      "eval_runtime": 367.3155,
-      "eval_samples_per_second": 1.361,
-      "eval_steps_per_second": 1.361,
-      "step": 1124
-    },
-    {
-      "epoch": 2.1333333333333333,
-      "grad_norm": 2.639159679412842,
-      "learning_rate": 8.137070169778812e-05,
-      "loss": 0.2198,
-      "step": 1200
-    },
-    {
-      "epoch": 2.311111111111111,
-      "grad_norm": 3.6480841636657715,
-      "learning_rate": 7.717837750006106e-05,
-      "loss": 0.2412,
-      "step": 1300
-    },
-    {
-      "epoch": 2.488888888888889,
-      "grad_norm": 2.240994930267334,
-      "learning_rate": 7.269491184691924e-05,
-      "loss": 0.1952,
-      "step": 1400
-    },
-    {
-      "epoch": 2.6666666666666665,
-      "grad_norm": 13.413070678710938,
-      "learning_rate": 6.79683327236813e-05,
-      "loss": 0.2262,
-      "step": 1500
-    },
-    {
-      "epoch": 2.8444444444444446,
-      "grad_norm": 0.8566445112228394,
-      "learning_rate": 6.304927240687181e-05,
-      "loss": 0.1949,
-      "step": 1600
-    },
-    {
-      "epoch": 2.997333333333333,
-      "eval_loss": 0.42686474323272705,
-      "eval_runtime": 365.7769,
-      "eval_samples_per_second": 1.367,
-      "eval_steps_per_second": 1.367,
-      "step": 1686
-    },
-    {
-      "epoch": 3.022222222222222,
-      "grad_norm": 0.11057106405496597,
-      "learning_rate": 5.799042507883874e-05,
-      "loss": 0.2061,
-      "step": 1700
-    },
-    {
-      "epoch": 3.2,
-      "grad_norm": 4.739655017852783,
-      "learning_rate": 5.284598235472912e-05,
-      "loss": 0.1207,
-      "step": 1800
-    },
-    {
-      "epoch": 3.3777777777777778,
-      "grad_norm": 0.25179940462112427,
-      "learning_rate": 4.7671052768596945e-05,
-      "loss": 0.1683,
-      "step": 1900
-    },
-    {
-      "epoch": 3.5555555555555554,
-      "grad_norm": 0.13251110911369324,
-      "learning_rate": 4.2521071437250546e-05,
-      "loss": 0.1325,
-      "step": 2000
-    },
-    {
-      "epoch": 3.7333333333333334,
-      "grad_norm": 2.5385780334472656,
-      "learning_rate": 3.7451206225665035e-05,
-      "loss": 0.1328,
-      "step": 2100
-    },
-    {
-      "epoch": 3.911111111111111,
-      "grad_norm": 0.5059184432029724,
-      "learning_rate": 3.251576677526236e-05,
-      "loss": 0.1184,
-      "step": 2200
-    },
-    {
-      "epoch": 3.9964444444444442,
-      "eval_loss": 0.448859840631485,
-      "eval_runtime": 364.0973,
-      "eval_samples_per_second": 1.373,
-      "eval_steps_per_second": 1.373,
-      "step": 2248
-    }
-  ],
-  "logging_steps": 100,
-  "max_steps": 3372,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 6,
-  "save_steps": 562,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": false
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 2.7113989423300608e+17,
-  "train_batch_size": 1,
-  "trial_name": null,
-  "trial_params": null
-}