Training in progress, step 500

adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen-14B",
+  "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": [
+    "c_attn"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bbd1cc5f836a389e7914a7eea6fd789515c77d9e70304f0d46df1330d2a1d81
+size 26224792

runs/May11_02-40-27_d96183b7b29f/events.out.tfevents.1715395303.d96183b7b29f.1272.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33c1e6aa4e2f99cfd06ffcf4a29df62040cb9c79af218f7f3da23acda473416f
+size 16584

special_tokens_map.json

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

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 +1,17 @@
+{
+  "added_tokens_decoder": {},
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_qwen.QWenTokenizer",
+      null
+    ]
+  },
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 8192,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "QWenTokenizer"
+}

trainer_log.jsonl

@@ -0,0 +1,51 @@
+{"current_steps": 10, "total_steps": 1944, "loss": 2.7232, "learning_rate": 5e-06, "epoch": 0.01542317331791016, "percentage": 0.51, "elapsed_time": "0:01:09", "remaining_time": "3:45:00"}
+{"current_steps": 20, "total_steps": 1944, "loss": 2.8025, "learning_rate": 1e-05, "epoch": 0.03084634663582032, "percentage": 1.03, "elapsed_time": "0:02:19", "remaining_time": "3:43:44"}
+{"current_steps": 30, "total_steps": 1944, "loss": 2.7466, "learning_rate": 1.5e-05, "epoch": 0.04626951995373048, "percentage": 1.54, "elapsed_time": "0:03:29", "remaining_time": "3:42:37"}
+{"current_steps": 40, "total_steps": 1944, "loss": 2.7862, "learning_rate": 2e-05, "epoch": 0.06169269327164064, "percentage": 2.06, "elapsed_time": "0:04:39", "remaining_time": "3:41:27"}
+{"current_steps": 50, "total_steps": 1944, "loss": 2.7836, "learning_rate": 2.5e-05, "epoch": 0.0771158665895508, "percentage": 2.57, "elapsed_time": "0:05:48", "remaining_time": "3:40:16"}
+{"current_steps": 60, "total_steps": 1944, "loss": 2.7271, "learning_rate": 3e-05, "epoch": 0.09253903990746096, "percentage": 3.09, "elapsed_time": "0:06:58", "remaining_time": "3:39:06"}
+{"current_steps": 70, "total_steps": 1944, "loss": 2.7783, "learning_rate": 3.5e-05, "epoch": 0.10796221322537113, "percentage": 3.6, "elapsed_time": "0:08:08", "remaining_time": "3:37:57"}
+{"current_steps": 80, "total_steps": 1944, "loss": 2.7324, "learning_rate": 4e-05, "epoch": 0.12338538654328128, "percentage": 4.12, "elapsed_time": "0:09:18", "remaining_time": "3:36:46"}
+{"current_steps": 90, "total_steps": 1944, "loss": 2.7053, "learning_rate": 4.5e-05, "epoch": 0.13880855986119145, "percentage": 4.63, "elapsed_time": "0:10:27", "remaining_time": "3:35:35"}
+{"current_steps": 100, "total_steps": 1944, "loss": 2.5806, "learning_rate": 5e-05, "epoch": 0.1542317331791016, "percentage": 5.14, "elapsed_time": "0:11:37", "remaining_time": "3:34:25"}
+{"current_steps": 110, "total_steps": 1944, "loss": 2.7242, "learning_rate": 5.500000000000001e-05, "epoch": 0.16965490649701176, "percentage": 5.66, "elapsed_time": "0:12:47", "remaining_time": "3:33:14"}
+{"current_steps": 120, "total_steps": 1944, "loss": 2.6331, "learning_rate": 6e-05, "epoch": 0.18507807981492191, "percentage": 6.17, "elapsed_time": "0:13:57", "remaining_time": "3:32:03"}
+{"current_steps": 130, "total_steps": 1944, "loss": 2.508, "learning_rate": 6.500000000000001e-05, "epoch": 0.20050125313283207, "percentage": 6.69, "elapsed_time": "0:15:06", "remaining_time": "3:30:54"}
+{"current_steps": 140, "total_steps": 1944, "loss": 2.4189, "learning_rate": 7e-05, "epoch": 0.21592442645074225, "percentage": 7.2, "elapsed_time": "0:16:16", "remaining_time": "3:29:44"}
+{"current_steps": 150, "total_steps": 1944, "loss": 2.351, "learning_rate": 7.500000000000001e-05, "epoch": 0.2313475997686524, "percentage": 7.72, "elapsed_time": "0:17:26", "remaining_time": "3:28:35"}
+{"current_steps": 160, "total_steps": 1944, "loss": 2.2376, "learning_rate": 8e-05, "epoch": 0.24677077308656256, "percentage": 8.23, "elapsed_time": "0:18:36", "remaining_time": "3:27:24"}
+{"current_steps": 170, "total_steps": 1944, "loss": 2.2678, "learning_rate": 8.5e-05, "epoch": 0.26219394640447274, "percentage": 8.74, "elapsed_time": "0:19:45", "remaining_time": "3:26:13"}
+{"current_steps": 180, "total_steps": 1944, "loss": 2.2033, "learning_rate": 9e-05, "epoch": 0.2776171197223829, "percentage": 9.26, "elapsed_time": "0:20:55", "remaining_time": "3:25:02"}
+{"current_steps": 190, "total_steps": 1944, "loss": 2.126, "learning_rate": 9.5e-05, "epoch": 0.29304029304029305, "percentage": 9.77, "elapsed_time": "0:22:04", "remaining_time": "3:23:51"}
+{"current_steps": 200, "total_steps": 1944, "loss": 2.4127, "learning_rate": 0.0001, "epoch": 0.3084634663582032, "percentage": 10.29, "elapsed_time": "0:23:14", "remaining_time": "3:22:41"}
+{"current_steps": 210, "total_steps": 1944, "loss": 2.0718, "learning_rate": 9.999188786725007e-05, "epoch": 0.32388663967611336, "percentage": 10.8, "elapsed_time": "0:24:24", "remaining_time": "3:21:30"}
+{"current_steps": 220, "total_steps": 1944, "loss": 2.2014, "learning_rate": 9.996755410126815e-05, "epoch": 0.3393098129940235, "percentage": 11.32, "elapsed_time": "0:25:33", "remaining_time": "3:20:19"}
+{"current_steps": 230, "total_steps": 1944, "loss": 2.0259, "learning_rate": 9.992700659800388e-05, "epoch": 0.3547329863119337, "percentage": 11.83, "elapsed_time": "0:26:43", "remaining_time": "3:19:09"}
+{"current_steps": 240, "total_steps": 1944, "loss": 2.3585, "learning_rate": 9.987025851452639e-05, "epoch": 0.37015615962984383, "percentage": 12.35, "elapsed_time": "0:27:53", "remaining_time": "3:17:58"}
+{"current_steps": 250, "total_steps": 1944, "loss": 2.2215, "learning_rate": 9.979732826475515e-05, "epoch": 0.385579332947754, "percentage": 12.86, "elapsed_time": "0:29:02", "remaining_time": "3:16:48"}
+{"current_steps": 260, "total_steps": 1944, "loss": 2.3239, "learning_rate": 9.970823951348487e-05, "epoch": 0.40100250626566414, "percentage": 13.37, "elapsed_time": "0:30:12", "remaining_time": "3:15:38"}
+{"current_steps": 270, "total_steps": 1944, "loss": 2.2053, "learning_rate": 9.960302116870661e-05, "epoch": 0.4164256795835743, "percentage": 13.89, "elapsed_time": "0:31:21", "remaining_time": "3:14:28"}
+{"current_steps": 280, "total_steps": 1944, "loss": 2.2688, "learning_rate": 9.948170737222762e-05, "epoch": 0.4318488529014845, "percentage": 14.4, "elapsed_time": "0:32:31", "remaining_time": "3:13:17"}
+{"current_steps": 290, "total_steps": 1944, "loss": 2.2533, "learning_rate": 9.934433748859274e-05, "epoch": 0.44727202621939466, "percentage": 14.92, "elapsed_time": "0:33:41", "remaining_time": "3:12:10"}
+{"current_steps": 300, "total_steps": 1944, "loss": 2.1101, "learning_rate": 9.919095609231126e-05, "epoch": 0.4626951995373048, "percentage": 15.43, "elapsed_time": "0:34:51", "remaining_time": "3:11:00"}
+{"current_steps": 310, "total_steps": 1944, "loss": 2.1293, "learning_rate": 9.902161295339307e-05, "epoch": 0.47811837285521497, "percentage": 15.95, "elapsed_time": "0:36:01", "remaining_time": "3:09:50"}
+{"current_steps": 320, "total_steps": 1944, "loss": 2.0417, "learning_rate": 9.883636302119912e-05, "epoch": 0.4935415461731251, "percentage": 16.46, "elapsed_time": "0:37:10", "remaining_time": "3:08:40"}
+{"current_steps": 330, "total_steps": 1944, "loss": 2.1096, "learning_rate": 9.863526640661107e-05, "epoch": 0.5089647194910353, "percentage": 16.98, "elapsed_time": "0:38:20", "remaining_time": "3:07:30"}
+{"current_steps": 340, "total_steps": 1944, "loss": 2.2787, "learning_rate": 9.841838836252627e-05, "epoch": 0.5243878928089455, "percentage": 17.49, "elapsed_time": "0:39:29", "remaining_time": "3:06:20"}
+{"current_steps": 350, "total_steps": 1944, "loss": 2.3788, "learning_rate": 9.818579926268405e-05, "epoch": 0.5398110661268556, "percentage": 18.0, "elapsed_time": "0:40:39", "remaining_time": "3:05:10"}
+{"current_steps": 360, "total_steps": 1944, "loss": 2.1264, "learning_rate": 9.793757457883062e-05, "epoch": 0.5552342394447658, "percentage": 18.52, "elapsed_time": "0:41:49", "remaining_time": "3:04:01"}
+{"current_steps": 370, "total_steps": 1944, "loss": 2.2351, "learning_rate": 9.767379485622943e-05, "epoch": 0.5706574127626759, "percentage": 19.03, "elapsed_time": "0:42:59", "remaining_time": "3:02:51"}
+{"current_steps": 380, "total_steps": 1944, "loss": 2.1219, "learning_rate": 9.739454568752556e-05, "epoch": 0.5860805860805861, "percentage": 19.55, "elapsed_time": "0:44:08", "remaining_time": "3:01:42"}
+{"current_steps": 390, "total_steps": 1944, "loss": 2.0565, "learning_rate": 9.709991768497208e-05, "epoch": 0.6015037593984962, "percentage": 20.06, "elapsed_time": "0:45:18", "remaining_time": "3:00:32"}
+{"current_steps": 400, "total_steps": 1944, "loss": 2.2406, "learning_rate": 9.679000645102771e-05, "epoch": 0.6169269327164064, "percentage": 20.58, "elapsed_time": "0:46:28", "remaining_time": "2:59:23"}
+{"current_steps": 410, "total_steps": 1944, "loss": 2.154, "learning_rate": 9.646491254733532e-05, "epoch": 0.6323501060343165, "percentage": 21.09, "elapsed_time": "0:47:38", "remaining_time": "2:58:13"}
+{"current_steps": 420, "total_steps": 1944, "loss": 2.1421, "learning_rate": 9.612474146209096e-05, "epoch": 0.6477732793522267, "percentage": 21.6, "elapsed_time": "0:48:48", "remaining_time": "2:57:04"}
+{"current_steps": 430, "total_steps": 1944, "loss": 2.1537, "learning_rate": 9.576960357581475e-05, "epoch": 0.6631964526701368, "percentage": 22.12, "elapsed_time": "0:49:57", "remaining_time": "2:55:55"}
+{"current_steps": 440, "total_steps": 1944, "loss": 2.1743, "learning_rate": 9.539961412553375e-05, "epoch": 0.678619625988047, "percentage": 22.63, "elapsed_time": "0:51:07", "remaining_time": "2:54:45"}
+{"current_steps": 450, "total_steps": 1944, "loss": 2.0946, "learning_rate": 9.501489316738945e-05, "epoch": 0.6940427993059572, "percentage": 23.15, "elapsed_time": "0:52:17", "remaining_time": "2:53:36"}
+{"current_steps": 460, "total_steps": 1944, "loss": 2.1048, "learning_rate": 9.461556553768123e-05, "epoch": 0.7094659726238673, "percentage": 23.66, "elapsed_time": "0:53:27", "remaining_time": "2:52:26"}
+{"current_steps": 470, "total_steps": 1944, "loss": 2.1311, "learning_rate": 9.420176081235881e-05, "epoch": 0.7248891459417776, "percentage": 24.18, "elapsed_time": "0:54:36", "remaining_time": "2:51:16"}
+{"current_steps": 480, "total_steps": 1944, "loss": 2.3041, "learning_rate": 9.377361326497674e-05, "epoch": 0.7403123192596877, "percentage": 24.69, "elapsed_time": "0:55:46", "remaining_time": "2:50:06"}
+{"current_steps": 490, "total_steps": 1944, "loss": 2.0653, "learning_rate": 9.333126182312465e-05, "epoch": 0.7557354925775979, "percentage": 25.21, "elapsed_time": "0:56:55", "remaining_time": "2:48:55"}
+{"current_steps": 500, "total_steps": 1944, "loss": 1.9974, "learning_rate": 9.287485002334733e-05, "epoch": 0.771158665895508, "percentage": 25.72, "elapsed_time": "0:58:05", "remaining_time": "2:47:45"}
+{"current_steps": 500, "total_steps": 1944, "eval_loss": 2.0961015224456787, "epoch": 0.771158665895508, "percentage": 25.72, "elapsed_time": "1:00:39", "remaining_time": "2:55:12"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32bf23f5bcb38c28d4d6096effe4db08214b617b327540fc98708e16abd7887d
+size 5176