p1 bf16 epoch 4 results

.gitignore

@@ -149,3 +149,4 @@ dmypy.json
 /llama.cpp
 /huggingface_tokenizers_cache
 /llama-factory/huggingface_tokenizers_cache
+**/Icon?

llama-factory/config/internlm2_5_7b_lora_sft_bf16_p2.yaml

@@ -0,0 +1,47 @@
+### model
+model_name_or_path: internlm/internlm2_5-7b-chat-1m
+
+### method
+stage: sft
+do_train: true
+finetuning_type: lora
+lora_target: all
+# quantization_bit: 4                     # use 4-bit QLoRA
+loraplus_lr_ratio: 16.0                 # use LoRA+ with lambda=16.0
+# use_unsloth: true                       # use UnslothAI's LoRA optimization for 2x faster training
+upcast_layernorm: true
+
+### dataset
+dataset: alpaca_mgtv_p2
+template: chatml
+cutoff_len: 1024
+max_samples: 5000
+overwrite_cache: true
+preprocessing_num_workers: 16
+
+### output
+output_dir: saves/internlm2_5_7b/lora/sft_bf16_p2
+logging_steps: 100
+save_steps: 562
+plot_loss: true
+overwrite_output_dir: true
+# resume_from_checkpoint: true
+
+### train
+per_device_train_batch_size: 1
+gradient_accumulation_steps: 8
+learning_rate: 1.0e-4
+num_train_epochs: 4.0
+lr_scheduler_type: cosine
+warmup_ratio: 0.1
+bf16: true
+ddp_timeout: 180000000
+
+### eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+eval_strategy: steps
+eval_steps: 562
+
+report_to: wandb
+run_name: internlm2_5_7b # optional

llama-factory/saves/internlm2_5_7b/lora/sft_bf16/checkpoint-2248/README.md

@@ -0,0 +1,202 @@
+---
+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_bf16/checkpoint-2248/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "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": [
+    "wo",
+    "w2",
+    "wqkv",
+    "w1",
+    "w3"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

llama-factory/saves/internlm2_5_7b/lora/sft_bf16/checkpoint-2248/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a708742af96cd7e2d49c0a8f3ba39e4b26d64a03ef22a0580ebfaf07fb327bd
+size 75539712

llama-factory/saves/internlm2_5_7b/lora/sft_bf16/checkpoint-2248/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efbadd2733d64366e621db9d58cc32bf25c202817e76e6c9968a41f011b846bd
+size 151264058

llama-factory/saves/internlm2_5_7b/lora/sft_bf16/checkpoint-2248/rng_state.pth

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

llama-factory/saves/internlm2_5_7b/lora/sft_bf16/checkpoint-2248/scheduler.pt

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

llama-factory/saves/internlm2_5_7b/lora/sft_bf16/checkpoint-2248/special_tokens_map.json

@@ -0,0 +1,38 @@
+{
+  "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_bf16/checkpoint-2248/tokenization_internlm2.py

@@ -0,0 +1,236 @@
+# 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_bf16/checkpoint-2248/tokenization_internlm2_fast.py

@@ -0,0 +1,214 @@
+# 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_bf16/checkpoint-2248/tokenizer.model

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

llama-factory/saves/internlm2_5_7b/lora/sft_bf16/checkpoint-2248/tokenizer_config.json

@@ -0,0 +1,104 @@
+{
+  "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
+    },
+    "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
+    }
+  },
+  "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_bf16/checkpoint-2248/trainer_state.json

@@ -0,0 +1,223 @@
+{
+  "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": 2.4078445434570312,
+      "learning_rate": 2.958579881656805e-05,
+      "loss": 0.4734,
+      "step": 100
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 4.478668689727783,
+      "learning_rate": 5.91715976331361e-05,
+      "loss": 0.3667,
+      "step": 200
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 4.706894397735596,
+      "learning_rate": 8.875739644970414e-05,
+      "loss": 0.3744,
+      "step": 300
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 2.9772543907165527,
+      "learning_rate": 9.989699867437137e-05,
+      "loss": 0.3797,
+      "step": 400
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 6.316380023956299,
+      "learning_rate": 9.92981892269398e-05,
+      "loss": 0.3443,
+      "step": 500
+    },
+    {
+      "epoch": 0.9991111111111111,
+      "eval_accuracy": 0.7856666666666667,
+      "eval_loss": 0.7739760279655457,
+      "eval_runtime": 87.6689,
+      "eval_samples_per_second": 5.703,
+      "eval_steps_per_second": 5.703,
+      "step": 562
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 3.866260051727295,
+      "learning_rate": 9.817128546774103e-05,
+      "loss": 0.3644,
+      "step": 600
+    },
+    {
+      "epoch": 1.2444444444444445,
+      "grad_norm": 2.369489908218384,
+      "learning_rate": 9.652835906663704e-05,
+      "loss": 0.3146,
+      "step": 700
+    },
+    {
+      "epoch": 1.4222222222222223,
+      "grad_norm": 4.548018932342529,
+      "learning_rate": 9.438700945477697e-05,
+      "loss": 0.3365,
+      "step": 800
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 12.139796257019043,
+      "learning_rate": 9.177017529516772e-05,
+      "loss": 0.2878,
+      "step": 900
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 0.8868021965026855,
+      "learning_rate": 8.870588875808164e-05,
+      "loss": 0.3291,
+      "step": 1000
+    },
+    {
+      "epoch": 1.9555555555555557,
+      "grad_norm": 0.3065238893032074,
+      "learning_rate": 8.522697523356319e-05,
+      "loss": 0.2604,
+      "step": 1100
+    },
+    {
+      "epoch": 1.9982222222222221,
+      "eval_accuracy": 0.8555,
+      "eval_loss": 0.38267847895622253,
+      "eval_runtime": 86.9945,
+      "eval_samples_per_second": 5.747,
+      "eval_steps_per_second": 5.747,
+      "step": 1124
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 1.911468744277954,
+      "learning_rate": 8.137070169778812e-05,
+      "loss": 0.2122,
+      "step": 1200
+    },
+    {
+      "epoch": 2.311111111111111,
+      "grad_norm": 3.41011381149292,
+      "learning_rate": 7.717837750006106e-05,
+      "loss": 0.2322,
+      "step": 1300
+    },
+    {
+      "epoch": 2.488888888888889,
+      "grad_norm": 4.826447486877441,
+      "learning_rate": 7.269491184691924e-05,
+      "loss": 0.2091,
+      "step": 1400
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 5.958643913269043,
+      "learning_rate": 6.79683327236813e-05,
+      "loss": 0.229,
+      "step": 1500
+    },
+    {
+      "epoch": 2.8444444444444446,
+      "grad_norm": 0.9083921909332275,
+      "learning_rate": 6.304927240687181e-05,
+      "loss": 0.2278,
+      "step": 1600
+    },
+    {
+      "epoch": 2.997333333333333,
+      "eval_accuracy": 0.867,
+      "eval_loss": 0.4158739745616913,
+      "eval_runtime": 87.1063,
+      "eval_samples_per_second": 5.74,
+      "eval_steps_per_second": 5.74,
+      "step": 1686
+    },
+    {
+      "epoch": 3.022222222222222,
+      "grad_norm": 3.2975399494171143,
+      "learning_rate": 5.799042507883874e-05,
+      "loss": 0.1859,
+      "step": 1700
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 0.3952264189720154,
+      "learning_rate": 5.284598235472912e-05,
+      "loss": 0.1403,
+      "step": 1800
+    },
+    {
+      "epoch": 3.3777777777777778,
+      "grad_norm": 0.7494814991950989,
+      "learning_rate": 4.7671052768596945e-05,
+      "loss": 0.156,
+      "step": 1900
+    },
+    {
+      "epoch": 3.5555555555555554,
+      "grad_norm": 0.022936208173632622,
+      "learning_rate": 4.2521071437250546e-05,
+      "loss": 0.1221,
+      "step": 2000
+    },
+    {
+      "epoch": 3.7333333333333334,
+      "grad_norm": 7.184863090515137,
+      "learning_rate": 3.7451206225665035e-05,
+      "loss": 0.1278,
+      "step": 2100
+    },
+    {
+      "epoch": 3.911111111111111,
+      "grad_norm": 1.4601508378982544,
+      "learning_rate": 3.251576677526236e-05,
+      "loss": 0.1115,
+      "step": 2200
+    },
+    {
+      "epoch": 3.9964444444444442,
+      "eval_accuracy": 0.8763333333333333,
+      "eval_loss": 0.48036429286003113,
+      "eval_runtime": 87.1857,
+      "eval_samples_per_second": 5.735,
+      "eval_steps_per_second": 5.735,
+      "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
+}

llama-factory/saves/internlm2_5_7b/lora/sft_bf16/checkpoint-2248/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba59bb13ccbc1536fe7be63d6753c0657b8ec8334daccb6ec740876a5104de43
+size 5304

llama-factory/saves/internlm2_5_7b/lora/sft_bf16/trainer_log.jsonl

@@ -21,3 +21,11 @@
 {"current_steps": 1800, "total_steps": 3372, "loss": 0.1403, "learning_rate": 5.284598235472912e-05, "epoch": 3.2, "percentage": 53.38, "elapsed_time": "2:16:13", "remaining_time": "1:58:58", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 1900, "total_steps": 3372, "loss": 0.156, "learning_rate": 4.7671052768596945e-05, "epoch": 3.3777777777777778, "percentage": 56.35, "elapsed_time": "2:23:31", "remaining_time": "1:51:11", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 2000, "total_steps": 3372, "loss": 0.1221, "learning_rate": 4.2521071437250546e-05, "epoch": 3.5555555555555554, "percentage": 59.31, "elapsed_time": "2:30:49", "remaining_time": "1:43:27", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2100, "total_steps": 3372, "loss": 0.1278, "learning_rate": 3.7451206225665035e-05, "epoch": 3.7333333333333334, "percentage": 62.28, "elapsed_time": "2:38:06", "remaining_time": "1:35:46", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2200, "total_steps": 3372, "loss": 0.1115, "learning_rate": 3.251576677526236e-05, "epoch": 3.911111111111111, "percentage": 65.24, "elapsed_time": "2:45:25", "remaining_time": "1:28:07", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2248, "total_steps": 3372, "eval_loss": 0.48036429286003113, "epoch": 3.9964444444444442, "percentage": 66.67, "elapsed_time": "2:50:23", "remaining_time": "1:25:11", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2300, "total_steps": 3372, "loss": 0.1009, "learning_rate": 2.776762272569255e-05, "epoch": 4.088888888888889, "percentage": 68.21, "elapsed_time": "2:54:12", "remaining_time": "1:21:11", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2400, "total_steps": 3372, "loss": 0.0724, "learning_rate": 2.325763736226793e-05, "epoch": 4.266666666666667, "percentage": 71.17, "elapsed_time": "3:01:30", "remaining_time": "1:13:30", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2500, "total_steps": 3372, "loss": 0.0598, "learning_rate": 1.9034122755957523e-05, "epoch": 4.444444444444445, "percentage": 74.14, "elapsed_time": "3:08:47", "remaining_time": "1:05:51", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2600, "total_steps": 3372, "loss": 0.0631, "learning_rate": 1.5142322232616412e-05, "epoch": 4.622222222222222, "percentage": 77.11, "elapsed_time": "3:16:05", "remaining_time": "0:58:13", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 2700, "total_steps": 3372, "loss": 0.063, "learning_rate": 1.1623925715366247e-05, "epoch": 4.8, "percentage": 80.07, "elapsed_time": "3:23:23", "remaining_time": "0:50:37", "throughput": "0.00", "total_tokens": 0}

llama-factory/saves/internlm2_5_7b/lora/sft_bf16_p2/trainer_log.jsonl

@@ -0,0 +1 @@
+{"current_steps": 100, "total_steps": 2248, "loss": 0.4683, "learning_rate": 4.4444444444444447e-05, "epoch": 0.17777777777777778, "percentage": 4.45, "elapsed_time": "0:09:48", "remaining_time": "3:30:39", "throughput": "0.00", "total_tokens": 0}