Training in progress, step 100

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/home/interstellarninja/ai_projects/axolotl/stablelm-1_6b-tool-calling-1/merged",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "embed_tokens",
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dac13d8ea70c951f34d886785caa5ad1c9454ed7379c6b592324dea15ecf3932
+size 852407184

config.json

@@ -1,31 +1,45 @@
 {
-  "_name_or_path": "/home/interstellarninja/ai_projects/axolotl/stablelm-func-calling-3/merged",
+  "_name_or_path": "/home/interstellarninja/ai_projects/axolotl/stablelm-1_6b-tool-calling-1/merged",
   "architectures": [
     "StableLMEpochForCausalLM"
   ],
+  "attention_dropout": 0.0,
   "auto_map": {
     "AutoConfig": "configuration_stablelm_epoch.StableLMEpochConfig",
     "AutoModelForCausalLM": "modeling_stablelm_epoch.StableLMEpochForCausalLM"
   },
-  "bos_token_id": 0,
-  "eos_token_id": 0,
+  "bos_token_id": 100257,
+  "eos_token_id": 100257,
   "hidden_act": "silu",
-  "hidden_size": 2560,
+  "hidden_size": 2048,
   "initializer_range": 0.02,
-  "intermediate_size": 6912,
+  "intermediate_size": 5632,
   "max_position_embeddings": 4096,
   "model_type": "stablelm_epoch",
   "norm_eps": 1e-05,
   "num_attention_heads": 32,
   "num_heads": 32,
-  "num_hidden_layers": 32,
+  "num_hidden_layers": 24,
   "num_key_value_heads": 32,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
   "rope_pct": 0.25,
   "rope_theta": 10000,
   "rotary_scaling_factor": 1.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.37.0.dev0",
   "use_cache": false,
-  "vocab_size": 50304
+  "use_qkv_bias": true,
+  "vocab_size": 100352
 }

configuration_stablelm_epoch.py

@@ -1,4 +1,3 @@
-# coding=utf-8
 # Copyright 2023 Stability and The HuggingFace Inc. team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
@@ -62,8 +61,12 @@ class StableLMEpochConfig(PretrainedConfig):
         use_cache (`bool`, *optional*, defaults to `True`):
             Whether or not the model should return the last key/values attentions
             (not used by all models). Only relevant if `config.is_decoder=True`.
+        use_qkv_bias (`bool`, *optional*, defaults to `True`):
+            Whether or not the model should use bias for qkv layers.
         tie_word_embeddings(`bool`, *optional*, defaults to `False`):
             Whether to tie weight embeddings
+        attention_dropout (`float`, *optional*, defaults to 0.0):
+            The dropout ratio for the attention probabilities.
     """
     model_type = "stablelm_epoch"
     keys_to_ignore_at_inference = ["past_key_values"]
@@ -83,9 +86,11 @@ class StableLMEpochConfig(PretrainedConfig):
         initializer_range=0.02,
         norm_eps=1.0e-5,
         use_cache=True,
+        use_qkv_bias=True,
         bos_token_id=0,
         eos_token_id=2,
         tie_word_embeddings=False,
+        attention_dropout: float = 0.0,
         **kwargs,
     ):
         self.vocab_size = vocab_size
@@ -101,7 +106,9 @@ class StableLMEpochConfig(PretrainedConfig):
         self.initializer_range = initializer_range
         self.norm_eps = norm_eps
         self.use_cache = use_cache
+        self.use_qkv_bias = use_qkv_bias
         self.tie_word_embeddings = tie_word_embeddings
+        self.attention_dropout = attention_dropout
         super().__init__(
             bos_token_id=bos_token_id,
             eos_token_id=eos_token_id,

runs/Jan24_03-21-57_WIN-2NFIRFU3FSK/events.out.tfevents.1706084518.WIN-2NFIRFU3FSK.39284.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:481fe540b63adb0ccdd50f5e247a7b41dbd07984cecc33cc491a113b0d29b5fb
+size 67513

special_tokens_map.json

@@ -1,30 +1,5 @@
 {
-  "bos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "[PAD]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>"
 }

tokenization_arcade100k.py

@@ -0,0 +1,290 @@
+# coding=utf-8
+# Copyright (c) 2023 Alibaba Cloud & Stability AI.
+#
+# Tongyi Qianwen LICENSE AGREEMENT:
+# https://github.com/QwenLM/Qwen/blob/5aa84bdfd3237b37f01bc88cd49b3279b9a71d0b/Tongyi%20Qianwen%20LICENSE%20AGREEMENT
+"""Tokenization classes for Arcade100k."""
+
+import base64
+import os
+import unicodedata
+from typing import Collection, Dict, List, Set, Tuple, Union
+
+import tiktoken
+from transformers.utils import logging
+from transformers import PreTrainedTokenizer, AddedToken
+
+logger = logging.get_logger(__name__)
+
+VOCAB_FILES_NAMES = {"vocab_file": "arcade100k.tiktoken"}
+NAME = "arcade100k"
+
+
+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)
+    }
+
+
+ENDOFTEXT = "<|endoftext|>"
+FIM = [
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>",
+    "<|fim_pad|>",
+]
+# `StarCoder` Tokens
+CODE = [
+    "<gh_stars>",
+    "<filename>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>",
+]
+CHAT = [
+    "<|im_start|>",  # Chat: Input message start
+    "<|im_end|>",  # Chat: Input message end
+]
+PAUSE = "<|pause|>"  # Think before you speak (https://arxiv.org/abs/2310.02226)
+REGISTERS = [
+    f"<|reg{i}|>" for i in range(0, 8)
+]  # Register 0 sink token (https://arxiv.org/abs/2309.17453)
+ENDOFPROMPT = "<|endofprompt|>"
+SPECIAL_TOKENS_NAMES = (
+    [ENDOFTEXT]
+    + FIM
+    + CODE
+    + [ENDOFPROMPT]
+    + CHAT
+    + [PAUSE]
+    + REGISTERS
+    + ["<|extra0|>"]
+)
+START_ID = 100257
+SPECIAL_TOKENS = {t: START_ID + i for i, t in enumerate(SPECIAL_TOKENS_NAMES)}
+
+
+def _arcade100k(vocab_file: str):
+    mergeable_ranks = _load_tiktoken_bpe(vocab_file)
+
+    return {
+        "name": NAME,
+        "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+""",
+        "mergeable_ranks": mergeable_ranks,
+        "special_tokens": SPECIAL_TOKENS,
+    }
+
+
+class Arcade100kTokenizer(PreTrainedTokenizer):
+    """
+    Construct a Arcade100k tokenizer backed by `tiktoken`.
+
+    Args:
+        vocab_file (`str`):
+            Path to the vocabulary file.
+        errors (`str`, *optional*, defaults to `"replace"`):
+            How to handle errors in decoding UTF-8 byte sequences.
+            WARNING: the default behaviour of this function is lossy, since decoded bytes are not
+            guaranteed to be valid UTF-8. You can control this behaviour using the `errors` parameter,
+            for instance, setting `errors=strict`.
+    """
+
+    vocab_files_names = VOCAB_FILES_NAMES
+    model_input_names = ["input_ids", "attention_mask"]
+
+    def __init__(
+        self,
+        vocab_file: str,
+        errors: str = "replace",
+        **kwargs,
+    ):
+        super().__init__(errors=errors, **kwargs)
+        self._tiktoken_config = _arcade100k(vocab_file)
+        self.tokenizer = tiktoken.Encoding(**self._tiktoken_config)
+
+        # TODO: Remove this assertion
+        assert (
+            len(self.tokenizer._mergeable_ranks)
+            + len(self.tokenizer._special_tokens)
+            + 1
+            == self.tokenizer.n_vocab
+        ), f"{len(self.tokenizer._mergeable_ranks) + len(self.tokenizer._special_tokens)} != {self.tokenizer.n_vocab} in encoding"
+
+        self.decoder = {i: n for n, i in self.tokenizer._mergeable_ranks.items()}
+        self.decoder.update({i: n for n, i in self.tokenizer._special_tokens.items()})
+        # Provide default `eos_token` and `pad_token`
+        if self.eos_token is None:
+            self.eos_token = self.decoder[self.tokenizer.eot_token]
+        if self.pad_token is None:
+            self.pad_token = self.decoder[self.tokenizer.pad_token]
+
+        # Expose for convenience
+        self.mergeable_ranks = self.tokenizer._mergeable_ranks
+        self.special_tokens = self.tokenizer._special_tokens
+
+    def __len__(self):
+        return self.tokenizer.n_vocab
+
+    def __getstate__(self):
+        # Required for `pickle` support
+        state = self.__dict__.copy()
+        del state["tokenizer"]
+        return state
+
+    def __setstate__(self, state):
+        self.__dict__.update(state)
+        self.tokenizer = tiktoken.Encoding(**self._tiktoken_config)
+
+    @property
+    def vocab_size(self):
+        return self.tokenizer.n_vocab
+
+    def get_vocab(self) -> Dict[bytes, int]:
+        return self.tokenizer._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.tokenizer._special_tokens:
+                return self.tokenizer._special_tokens[tokens]
+            else:
+                return self.tokenizer._mergeable_ranks.get(tokens)
+        for token in tokens:
+            if token in self.tokenizer._special_tokens:
+                ids.append(self.tokenizer._special_tokens[token])
+            else:
+                ids.append(self.tokenizer._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:
+                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, "arcade100k.tiktoken")
+        with open(file_path, "w", encoding="utf8") as w:
+            for k, v in self.tokenizer._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
+
+    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.tokenizer._special_tokens:
+            return self.tokenizer._special_tokens[token]
+        if token in self.tokenizer._mergeable_ranks:
+            return self.tokenizer._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.tokenizer.eot_token]
+        return self.tokenizer.decode(token_ids)

tokenizer_config.json

@@ -1,221 +1,17 @@
 {
-  "add_prefix_space": false,
-  "added_tokens_decoder": {
-    "0": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": "<|padding|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "50254": {
-      "content": "                        ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50255": {
-      "content": "                       ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50256": {
-      "content": "                      ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50257": {
-      "content": "                     ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50258": {
-      "content": "                    ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50259": {
-      "content": "                   ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50260": {
-      "content": "                  ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50261": {
-      "content": "                 ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50262": {
-      "content": "                ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50263": {
-      "content": "               ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50264": {
-      "content": "              ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50265": {
-      "content": "             ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50266": {
-      "content": "            ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50267": {
-      "content": "           ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50268": {
-      "content": "          ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50269": {
-      "content": "         ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50270": {
-      "content": "        ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50271": {
-      "content": "       ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50272": {
-      "content": "      ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50273": {
-      "content": "     ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50274": {
-      "content": "    ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50275": {
-      "content": "   ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50276": {
-      "content": "  ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50277": {
-      "content": "[PAD]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
+  "added_tokens_decoder": {},
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_arcade100k.Arcade100kTokenizer",
+      null
+    ]
   },
   "bos_token": "<|endoftext|>",
   "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
+  "errors": "replace",
   "model_max_length": 2048,
-  "pad_token": "[PAD]",
-  "tokenizer_class": "GPTNeoXTokenizer",
-  "unk_token": "<|endoftext|>"
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "Arcade100kTokenizer"
 }

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:661b08b166c876c9c6d5f90b918f55da075201b27d1bd2861ed89c5500df2bf7
+size 4411