Upload 15 files

README.md

@@ -0,0 +1,62 @@
+---
+license: other
+library_name: peft
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+base_model: qwen/Qwen-72B-Chat
+model-index:
+- name: path_to_sft_checkpoint_eevalplusceval
+  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. -->
+
+# path_to_sft_checkpoint_eevalplusceval
+
+This model is a fine-tuned version of [qwen/Qwen-72B-Chat](qwen/Qwen-72B-Chat) on the e_eval dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 32
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 3.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.8.2
+- Transformers 4.37.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.15.0
+- Tokenizers 0.15.1

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "qwen/Qwen-72B-Chat",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "c_attn"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a810d0575fcf03c415b79b0cc868c28d4e48b0108f57a1d82ab8fa3cba8ec8c
+size 41963856

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.5275618712107341,
+    "train_runtime": 2086.9604,
+    "train_samples_per_second": 2.069,
+    "train_steps_per_second": 0.065
+}

configuration.json

@@ -0,0 +1 @@
+{"framework":"Pytorch","task":"text-generation"}

special_tokens_map.json

@@ -0,0 +1,10 @@
+{
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|im_end|>"
+}

tokenization_qwen.py

@@ -0,0 +1,276 @@
+# Copyright (c) Alibaba Cloud.
+#
+# This source code is licensed under the license found in the
+# LICENSE file in the root directory of this source tree.
+
+"""Tokenization classes for QWen."""
+
+import base64
+import logging
+import os
+import unicodedata
+from typing import Collection, Dict, List, Set, Tuple, Union
+
+import tiktoken
+from transformers import PreTrainedTokenizer, AddedToken
+
+logger = logging.getLogger(__name__)
+
+
+VOCAB_FILES_NAMES = {"vocab_file": "qwen.tiktoken"}
+
+PAT_STR = r"""(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\r\n\p{L}\p{N}]?\p{L}+|\p{N}| ?[^\s\p{L}\p{N}]+[\r\n]*|\s*[\r\n]+|\s+(?!\S)|\s+"""
+ENDOFTEXT = "<|endoftext|>"
+IMSTART = "<|im_start|>"
+IMEND = "<|im_end|>"
+# as the default behavior is changed to allow special tokens in
+# regular texts, the surface forms of special tokens need to be
+# as different as possible to minimize the impact
+EXTRAS = tuple((f"<|extra_{i}|>" for i in range(205)))
+# changed to use actual index to avoid misconfiguration with vocabulary expansion
+SPECIAL_START_ID = 151643
+SPECIAL_TOKENS = tuple(
+    enumerate(
+        (
+            (
+                ENDOFTEXT,
+                IMSTART,
+                IMEND,
+            )
+            + EXTRAS
+        ),
+        start=SPECIAL_START_ID,
+    )
+)
+SPECIAL_TOKENS_SET = set(t for i, t in SPECIAL_TOKENS)
+
+
+def _load_tiktoken_bpe(tiktoken_bpe_file: str) -> Dict[bytes, int]:
+    with open(tiktoken_bpe_file, "rb") as f:
+        contents = f.read()
+    return {
+        base64.b64decode(token): int(rank)
+        for token, rank in (line.split() for line in contents.splitlines() if line)
+    }
+
+
+class QWenTokenizer(PreTrainedTokenizer):
+    """QWen tokenizer."""
+
+    vocab_files_names = VOCAB_FILES_NAMES
+
+    def __init__(
+        self,
+        vocab_file,
+        errors="replace",
+        extra_vocab_file=None,
+        **kwargs,
+    ):
+        super().__init__(**kwargs)
+
+        # how to handle errors in decoding UTF-8 byte sequences
+        # use ignore if you are in streaming inference
+        self.errors = errors  
+
+        self.mergeable_ranks = _load_tiktoken_bpe(vocab_file)  # type: Dict[bytes, int]
+        self.special_tokens = {
+            token: index
+            for index, token in SPECIAL_TOKENS
+        }
+
+        # try load extra vocab from file
+        if extra_vocab_file is not None:
+            used_ids = set(self.mergeable_ranks.values()) | set(self.special_tokens.values())
+            extra_mergeable_ranks = _load_tiktoken_bpe(extra_vocab_file)
+            for token, index in extra_mergeable_ranks.items():
+                if token in self.mergeable_ranks:
+                    logger.info(f"extra token {token} exists, skipping")
+                    continue
+                if index in used_ids:
+                    logger.info(f'the index {index} for extra token {token} exists, skipping')
+                    continue
+                self.mergeable_ranks[token] = index
+            # the index may be sparse after this, but don't worry tiktoken.Encoding will handle this
+
+        enc = tiktoken.Encoding(
+            "Qwen",
+            pat_str=PAT_STR,
+            mergeable_ranks=self.mergeable_ranks,
+            special_tokens=self.special_tokens,
+        )
+        assert (
+            len(self.mergeable_ranks) + len(self.special_tokens) == enc.n_vocab
+        ), f"{len(self.mergeable_ranks) + len(self.special_tokens)} != {enc.n_vocab} in encoding"
+
+        self.decoder = {
+            v: k for k, v in self.mergeable_ranks.items()
+        }  # type: dict[int, bytes|str]
+        self.decoder.update({v: k for k, v in self.special_tokens.items()})
+
+        self.tokenizer = enc  # type: tiktoken.Encoding
+
+        self.eod_id = self.tokenizer.eot_token
+        self.im_start_id = self.special_tokens[IMSTART]
+        self.im_end_id = self.special_tokens[IMEND]
+
+    def __getstate__(self):
+        # for pickle lovers
+        state = self.__dict__.copy()
+        del state["tokenizer"]
+        return state
+
+    def __setstate__(self, state):
+        # tokenizer is not python native; don't pass it; rebuild it
+        self.__dict__.update(state)
+        enc = tiktoken.Encoding(
+            "Qwen",
+            pat_str=PAT_STR,
+            mergeable_ranks=self.mergeable_ranks,
+            special_tokens=self.special_tokens,
+        )
+        self.tokenizer = enc
+
+    def __len__(self) -> int:
+        return self.tokenizer.n_vocab
+
+    def get_vocab(self) -> Dict[bytes, int]:
+        return self.mergeable_ranks
+
+    def convert_tokens_to_ids(
+        self, tokens: Union[bytes, str, List[Union[bytes, str]]]
+    ) -> List[int]:
+        ids = []
+        if isinstance(tokens, (str, bytes)):
+            if tokens in self.special_tokens:
+                return self.special_tokens[tokens]
+            else:
+                return self.mergeable_ranks.get(tokens)
+        for token in tokens:
+            if token in self.special_tokens:
+                ids.append(self.special_tokens[token])
+            else:
+                ids.append(self.mergeable_ranks.get(token))
+        return ids
+
+    def _add_tokens(
+        self,
+        new_tokens: Union[List[str], List[AddedToken]],
+        special_tokens: bool = False,
+    ) -> int:
+        if not special_tokens and new_tokens:
+            raise ValueError("Adding regular tokens is not supported")
+        for token in new_tokens:
+            surface_form = token.content if isinstance(token, AddedToken) else token
+            if surface_form not in SPECIAL_TOKENS_SET:
+                raise ValueError("Adding unknown special tokens is not supported")
+        return 0
+
+    def save_vocabulary(self, save_directory: str, **kwargs) -> Tuple[str]:
+        """
+        Save only the vocabulary of the tokenizer (vocabulary).
+
+        Returns:
+            `Tuple(str)`: Paths to the files saved.
+        """
+        file_path = os.path.join(save_directory, "qwen.tiktoken")
+        with open(file_path, "w", encoding="utf8") as w:
+            for k, v in self.mergeable_ranks.items():
+                line = base64.b64encode(k).decode("utf8") + " " + str(v) + "\n"
+                w.write(line)
+        return (file_path,)
+
+    def tokenize(
+        self,
+        text: str,
+        allowed_special: Union[Set, str] = "all",
+        disallowed_special: Union[Collection, str] = (),
+        **kwargs,
+    ) -> List[Union[bytes, str]]:
+        """
+        Converts a string in a sequence of tokens.
+
+        Args:
+            text (`str`):
+                The sequence to be encoded.
+            allowed_special (`Literal["all"]` or `set`):
+                The surface forms of the tokens to be encoded as special tokens in regular texts.
+                Default to "all".
+            disallowed_special (`Literal["all"]` or `Collection`):
+                The surface forms of the tokens that should not be in regular texts and trigger errors.
+                Default to an empty tuple.
+
+            kwargs (additional keyword arguments, *optional*):
+                Will be passed to the underlying model specific encode method.
+
+        Returns:
+            `List[bytes|str]`: The list of tokens.
+        """
+        tokens = []
+        text = unicodedata.normalize("NFC", text)
+
+        # this implementation takes a detour: text -> token id -> token surface forms
+        for t in self.tokenizer.encode(
+            text, allowed_special=allowed_special, disallowed_special=disallowed_special
+        ):
+            tokens.append(self.decoder[t])
+        return tokens
+
+    def convert_tokens_to_string(self, tokens: List[Union[bytes, str]]) -> str:
+        """
+        Converts a sequence of tokens in a single string.
+        """
+        text = ""
+        temp = b""
+        for t in tokens:
+            if isinstance(t, str):
+                if temp:
+                    text += temp.decode("utf-8", errors=self.errors)
+                    temp = b""
+                text += t
+            elif isinstance(t, bytes):
+                temp += t
+            else:
+                raise TypeError("token should only be of type types or str")
+        if temp:
+            text += temp.decode("utf-8", errors=self.errors)
+        return text
+
+    @property
+    def vocab_size(self):
+        return self.tokenizer.n_vocab
+
+    def _convert_id_to_token(self, index: int) -> Union[bytes, str]:
+        """Converts an id to a token, special tokens included"""
+        if index in self.decoder:
+            return self.decoder[index]
+        raise ValueError("unknown ids")
+
+    def _convert_token_to_id(self, token: Union[bytes, str]) -> int:
+        """Converts a token to an id using the vocab, special tokens included"""
+        if token in self.special_tokens:
+            return self.special_tokens[token]
+        if token in self.mergeable_ranks:
+            return self.mergeable_ranks[token]
+        raise ValueError("unknown token")
+
+    def _tokenize(self, text: str, **kwargs):
+        """
+        Converts a string in a sequence of tokens (string), using the tokenizer. Split in words for word-based
+        vocabulary or sub-words for sub-word-based vocabularies (BPE/SentencePieces/WordPieces).
+
+        Do NOT take care of added tokens.
+        """
+        raise NotImplementedError
+
+    def _decode(
+        self,
+        token_ids: Union[int, List[int]],
+        skip_special_tokens: bool = False,
+        errors: str = None,
+        **kwargs,
+    ) -> str:
+        if isinstance(token_ids, int):
+            token_ids = [token_ids]
+        if skip_special_tokens:
+            token_ids = [i for i in token_ids if i < self.eod_id]
+        return self.tokenizer.decode(token_ids, errors=errors or self.errors)

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "added_tokens_decoder": {},
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_qwen.QWenTokenizer",
+      null
+    ]
+  },
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|im_end|>",
+  "model_max_length": 8192,
+  "pad_token": "<|im_end|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "QWenTokenizer"
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.5275618712107341,
+    "train_runtime": 2086.9604,
+    "train_samples_per_second": 2.069,
+    "train_steps_per_second": 0.065
+}

trainer_log.jsonl

@@ -0,0 +1,14 @@
+{"current_steps": 10, "total_steps": 135, "loss": 4.7333, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5e-05, "epoch": 0.22, "percentage": 7.41, "elapsed_time": "0:02:42", "remaining_time": "0:33:46"}
+{"current_steps": 20, "total_steps": 135, "loss": 1.0511, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5e-05, "epoch": 0.44, "percentage": 14.81, "elapsed_time": "0:05:16", "remaining_time": "0:30:20"}
+{"current_steps": 30, "total_steps": 135, "loss": 0.2765, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5e-05, "epoch": 0.67, "percentage": 22.22, "elapsed_time": "0:07:50", "remaining_time": "0:27:26"}
+{"current_steps": 40, "total_steps": 135, "loss": 0.1875, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5e-05, "epoch": 0.89, "percentage": 29.63, "elapsed_time": "0:10:24", "remaining_time": "0:24:42"}
+{"current_steps": 50, "total_steps": 135, "loss": 0.2089, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5e-05, "epoch": 1.11, "percentage": 37.04, "elapsed_time": "0:12:57", "remaining_time": "0:22:02"}
+{"current_steps": 60, "total_steps": 135, "loss": 0.1893, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5e-05, "epoch": 1.33, "percentage": 44.44, "elapsed_time": "0:15:32", "remaining_time": "0:19:25"}
+{"current_steps": 70, "total_steps": 135, "loss": 0.1092, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5e-05, "epoch": 1.56, "percentage": 51.85, "elapsed_time": "0:18:06", "remaining_time": "0:16:48"}
+{"current_steps": 80, "total_steps": 135, "loss": 0.1111, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5e-05, "epoch": 1.78, "percentage": 59.26, "elapsed_time": "0:20:40", "remaining_time": "0:14:12"}
+{"current_steps": 90, "total_steps": 135, "loss": 0.0726, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5e-05, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:23:14", "remaining_time": "0:11:37"}
+{"current_steps": 100, "total_steps": 135, "loss": 0.048, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5e-05, "epoch": 2.22, "percentage": 74.07, "elapsed_time": "0:25:48", "remaining_time": "0:09:01"}
+{"current_steps": 110, "total_steps": 135, "loss": 0.029, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5e-05, "epoch": 2.44, "percentage": 81.48, "elapsed_time": "0:28:21", "remaining_time": "0:06:26"}
+{"current_steps": 120, "total_steps": 135, "loss": 0.037, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5e-05, "epoch": 2.67, "percentage": 88.89, "elapsed_time": "0:30:55", "remaining_time": "0:03:51"}
+{"current_steps": 130, "total_steps": 135, "loss": 0.0554, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5e-05, "epoch": 2.89, "percentage": 96.3, "elapsed_time": "0:33:30", "remaining_time": "0:01:17"}
+{"current_steps": 135, "total_steps": 135, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:34:46", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,108 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 135,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.22,
+      "learning_rate": 5e-05,
+      "loss": 4.7333,
+      "step": 10
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 5e-05,
+      "loss": 1.0511,
+      "step": 20
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5e-05,
+      "loss": 0.2765,
+      "step": 30
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 5e-05,
+      "loss": 0.1875,
+      "step": 40
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 5e-05,
+      "loss": 0.2089,
+      "step": 50
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 5e-05,
+      "loss": 0.1893,
+      "step": 60
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 5e-05,
+      "loss": 0.1092,
+      "step": 70
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 5e-05,
+      "loss": 0.1111,
+      "step": 80
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 5e-05,
+      "loss": 0.0726,
+      "step": 90
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 5e-05,
+      "loss": 0.048,
+      "step": 100
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 5e-05,
+      "loss": 0.029,
+      "step": 110
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 5e-05,
+      "loss": 0.037,
+      "step": 120
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 5e-05,
+      "loss": 0.0554,
+      "step": 130
+    },
+    {
+      "epoch": 3.0,
+      "step": 135,
+      "total_flos": 26945073709056.0,
+      "train_loss": 0.5275618712107341,
+      "train_runtime": 2086.9604,
+      "train_samples_per_second": 2.069,
+      "train_steps_per_second": 0.065
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 135,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "total_flos": 26945073709056.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f101cba683a42d4cf967d5baa893c0b73fc95dec41338e58bde1698e156605e6
+size 7288