Hugging Face's logo

Shuu12121
/
CodeSearch-ModernBERT-Owl

Sentence Similarity
sentence-transformers
Safetensors
English
modernbert
feature-extraction
Eval Results
Model card Files Community
Shuu12121 commited on
Commit
6a998f1
·
verified ·
1 Parent(s): 07c0995

Upload ModernBERT model

Browse files
Files changed (13) hide show
  1. 1_Pooling/config.json +10 -0
  2. README.md +864 -0
  3. added_tokens.json +6 -0
  4. config.json +49 -0
  5. config_sentence_transformers.json +10 -0
  6. merges.txt +0 -0
  7. model.safetensors +3 -0
  8. modules.json +14 -0
  9. sentence_bert_config.json +4 -0
  10. special_tokens_map.json +51 -0
  11. tokenizer.json +0 -0
  12. tokenizer_config.json +97 -0
  13. vocab.json +0 -0
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": true,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": false,
9
+ "include_prompt": true
10
+ }
README.md ADDED
@@ -0,0 +1,864 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - sentence-transformers
4
+ - sentence-similarity
5
+ - feature-extraction
6
+ - generated_from_trainer
7
+ - dataset_size:1431743
8
+ - loss:MultipleNegativesRankingLoss
9
+ base_model: Shuu12121/CodeModernBERT-Owl
10
+ widget:
11
+ - source_sentence: return predicted ADEV of noise-type at given tau
12
+ sentences:
13
+ - "def get_instances(self):\n \n services = []\n for resource\
14
+ \ in self._get_instances():\n services.append(resource['entity']['name'])\n\
15
+ \n return services"
16
+ - "def handle_exception(self, *args):\n \n\n if not self.__enabled:\n\
17
+ \ return\n\n cls, instance, trcback = foundations.exceptions.extract_exception(*args)\n\
18
+ \n LOGGER.info(\"{0} | Handling '{1}' exception!\".format(\n \
19
+ \ self.__class__.__name__, foundations.strings.to_string(cls)))\n\n self.__initialize_context_ui()\n\
20
+ \n self.__update_html(self.format_html_exception(cls, instance, trcback))\n\
21
+ \n self.show()\n self.__report and self.report_exception_to_crittercism(cls,\
22
+ \ instance, trcback)\n foundations.exceptions.base_exception_handler(cls,\
23
+ \ instance, trcback)\n self.exec_()"
24
+ - "def adev(self, tau0, tau):\n \n prefactor = self.adev_from_qd(tau0=tau0,\
25
+ \ tau=tau)\n c = self.c_avar()\n avar = pow(prefactor, 2)*pow(tau,\
26
+ \ c)\n return np.sqrt(avar)"
27
+ - source_sentence: "Edit a IP4\n\n :param ip4: An IP4 available to save in\
28
+ \ format x.x.x.x.\n :param id_ip: IP identifier. Integer value and greater\
29
+ \ than zero.\n :param descricao: IP description.\n\n :return: None"
30
+ sentences:
31
+ - "def _vec_alpha(self, donor_catchments):\n \n return np.dot(linalg.inv(self._matrix_omega(donor_catchments)),\
32
+ \ self._vec_b(donor_catchments))"
33
+ - "def sync_balancer_files(self):\n \n\n def sync():\n \
34
+ \ for balancer in self.configurables[Balancer].values():\n balancer.sync_file(self.configurables[Cluster].values())\n\
35
+ \n self.work_pool.submit(sync)"
36
+ - "def edit_ipv4(self, ip4, descricao, id_ip):\n \n\n if not is_valid_int_param(id_ip):\n\
37
+ \ raise InvalidParameterError(\n u'Ip identifier is\
38
+ \ invalid or was not informed.')\n\n if ip4 is None or ip4 == \"\":\n \
39
+ \ raise InvalidParameterError(\n u'The IP4 is invalid\
40
+ \ or was not informed.')\n\n ip_map = dict()\n ip_map['descricao']\
41
+ \ = descricao\n ip_map['ip4'] = ip4\n ip_map['id_ip'] = id_ip\n\n\
42
+ \ url = \"ip4/edit/\"\n\n code, xml = self.submit({'ip_map': ip_map},\
43
+ \ 'POST', url)\n\n return self.response(code, xml)"
44
+ - source_sentence: "Check if health check is disabled.\n\n It logs a message\
45
+ \ if health check is disabled and it also adds an item\n to the action\
46
+ \ queue based on 'on_disabled' setting.\n\n Returns:\n True\
47
+ \ if check is disabled otherwise False."
48
+ sentences:
49
+ - "def find_guest(name, quiet=False, path=None):\n '''\n Returns the host\
50
+ \ for a container.\n\n path\n path to the container parent\n \
51
+ \ default: /var/lib/lxc (system default)\n\n .. versionadded:: 2015.8.0\n\
52
+ \n\n .. code-block:: bash\n\n salt-run lxc.find_guest name\n '''\n\
53
+ \ if quiet:\n log.warning(\"'quiet' argument is being deprecated.\"\n\
54
+ \ ' Please migrate to --quiet')\n for data in _list_iter(path=path):\n\
55
+ \ host, l = next(six.iteritems(data))\n for x in 'running', 'frozen',\
56
+ \ 'stopped':\n if name in l[x]:\n if not quiet:\n \
57
+ \ __jid_event__.fire_event(\n {'data':\
58
+ \ host,\n 'outputter': 'lxc_find_host'},\n \
59
+ \ 'progress')\n return host\n return None"
60
+ - "def iter_wave_values(self):\n \n typecode = self.get_typecode(self.samplewidth)\n\
61
+ \n if log.level >= 5:\n if self.cfg.AVG_COUNT > 1:\n \
62
+ \ # merge samples -> log output in iter_avg_wave_values\n \
63
+ \ tlm = None\n else:\n tlm = TextLevelMeter(self.max_value,\
64
+ \ 79)\n\n # Use only a read size which is a quare divider of the samplewidth\n\
65
+ \ # Otherwise array.array will raise: ValueError: string length not a multiple\
66
+ \ of item size\n divider = int(round(float(WAVE_READ_SIZE) / self.samplewidth))\n\
67
+ \ read_size = self.samplewidth * divider\n if read_size != WAVE_READ_SIZE:\n\
68
+ \ log.info(\"Real use wave read size: %i Bytes\" % read_size)\n\n \
69
+ \ get_wave_block_func = functools.partial(self.wavefile.readframes, read_size)\n\
70
+ \ skip_count = 0\n\n manually_audioop_bias = self.samplewidth ==\
71
+ \ 1 and audioop is None\n\n for frames in iter(get_wave_block_func, \"\"\
72
+ ):\n\n if self.samplewidth == 1:\n if audioop is None:\n\
73
+ \ log.warning(\"use audioop.bias() work-a-round for missing\
74
+ \ audioop.\")\n else:\n # 8 bit samples are\
75
+ \ unsigned, see:\n # http://docs.python.org/2/library/audioop.html#audioop.lin2lin\n\
76
+ \ frames = audioop.bias(frames, 1, 128)\n\n try:\n\
77
+ \ values = array.array(typecode, frames)\n except ValueError,\
78
+ \ err:\n # e.g.:\n # ValueError: string length\
79
+ \ not a multiple of item size\n # Work-a-round: Skip the last frames\
80
+ \ of this block\n frame_count = len(frames)\n divider\
81
+ \ = int(math.floor(float(frame_count) / self.samplewidth))\n new_count\
82
+ \ = self.samplewidth * divider\n frames = frames[:new_count] #\
83
+ \ skip frames\n log.error(\n \"Can't make array\
84
+ \ from %s frames: Value error: %s (Skip %i and use %i frames)\" % (\n \
85
+ \ frame_count, err, frame_count - new_count, len(frames)\n \
86
+ \ ))\n values = array.array(typecode, frames)\n\n \
87
+ \ for value in values:\n self.wave_pos += 1 # Absolute\
88
+ \ position in the frame stream\n\n if manually_audioop_bias:\n\
89
+ \ # audioop.bias can't be used.\n # See:\
90
+ \ http://hg.python.org/cpython/file/482590320549/Modules/audioop.c#l957\n \
91
+ \ value = value % 0xff - 128\n\n# if abs(value)\
92
+ \ < self.min_volume:\n# # log.log(5, \"Ignore to lower amplitude\"\
93
+ )\n# skip_count += 1\n# continue\n\n \
94
+ \ yield (self.wave_pos, value)\n\n log.info(\"Skip %i samples\
95
+ \ that are lower than %i\" % (\n skip_count, self.min_volume\n \
96
+ \ ))\n log.info(\"Last readed Frame is: %s\" % self.pformat_pos())"
97
+ - "def _check_disabled(self):\n \n if self.config['check_disabled']:\n\
98
+ \ if self.config['on_disabled'] == 'withdraw':\n self.log.info(\"\
99
+ Check is disabled and ip_prefix will be \"\n \"withdrawn\"\
100
+ )\n self.log.info(\"adding %s in the queue\", self.ip_with_prefixlen)\n\
101
+ \ self.action.put(self.del_operation)\n self.log.info(\"\
102
+ Check is now permanently disabled\")\n elif self.config['on_disabled']\
103
+ \ == 'advertise':\n self.log.info(\"check is disabled, ip_prefix\
104
+ \ wont be withdrawn\")\n self.log.info(\"adding %s in the queue\"\
105
+ , self.ip_with_prefixlen)\n self.action.put(self.add_operation)\n\
106
+ \ self.log.info('check is now permanently disabled')\n\n \
107
+ \ return True\n\n return False"
108
+ - source_sentence: "When serializing an agent distribution, remove the thresholds,\
109
+ \ in order\n to avoid cluttering the YAML definition file."
110
+ sentences:
111
+ - "def serialize_distribution(network_agents, known_modules=[]):\n '''\n When\
112
+ \ serializing an agent distribution, remove the thresholds, in order\n to avoid\
113
+ \ cluttering the YAML definition file.\n '''\n d = deepcopy(list(network_agents))\n\
114
+ \ for v in d:\n if 'threshold' in v:\n del v['threshold']\n\
115
+ \ v['agent_type'] = serialize_type(v['agent_type'],\n \
116
+ \ known_modules=known_modules)\n return d"
117
+ - "def disconnect(self):\n \n if self.root.ref is not None:\n \
118
+ \ self.api.disconnect()\n self.root = None"
119
+ - "def make_tarball(src_dir):\n \n if type(src_dir) != str:\n raise\
120
+ \ TypeError('src_dir must be str')\n output_file = src_dir + \".tar.gz\"\n\
121
+ \ log.msg(\"Wrapping tarball '{out}' ...\".format(out=output_file))\n if\
122
+ \ not _dry_run:\n with tarfile.open(output_file, \"w:gz\") as tar:\n \
123
+ \ tar.add(src_dir, arcname=os.path.basename(src_dir))\n return output_file"
124
+ - source_sentence: Encrypts the zip file
125
+ sentences:
126
+ - "def nsUriMatch(self, value, wanted, strict=0, tt=type(())):\n \n \
127
+ \ if value == wanted or (type(wanted) is tt) and value in wanted:\n \
128
+ \ return 1\n if not strict and value is not None:\n wanted\
129
+ \ = type(wanted) is tt and wanted or (wanted,)\n value = value[-1:]\
130
+ \ != '/' and value or value[:-1]\n for item in wanted:\n \
131
+ \ if item == value or item[:-1] == value:\n return 1\n\
132
+ \ return 0"
133
+ - "def transform(self, sents):\n \n\n def convert(tokens):\n \
134
+ \ return torch.tensor([self.vocab.stoi[t] for t in tokens], dtype=torch.long)\n\
135
+ \n if self.vocab is None:\n raise Exception(\n \
136
+ \ \"Must run .fit() for .fit_transform() before \" \"calling .transform().\"\
137
+ \n )\n\n seqs = sorted([convert(s) for s in sents], key=lambda\
138
+ \ x: -len(x))\n X = torch.LongTensor(pad_sequence(seqs, batch_first=True))\n\
139
+ \ return X"
140
+ - "def freeze_encrypt(dest_dir, zip_filename, config, opt):\n \n pgp_keys\
141
+ \ = grok_keys(config)\n icefile_prefix = \"aomi-%s\" % \\\n \
142
+ \ os.path.basename(os.path.dirname(opt.secretfile))\n if opt.icefile_prefix:\n\
143
+ \ icefile_prefix = opt.icefile_prefix\n\n timestamp = time.strftime(\"\
144
+ %H%M%S-%m-%d-%Y\",\n datetime.datetime.now().timetuple())\n\
145
+ \ ice_file = \"%s/%s-%s.ice\" % (dest_dir, icefile_prefix, timestamp)\n \
146
+ \ if not encrypt(zip_filename, ice_file, pgp_keys):\n raise aomi.exceptions.GPG(\"\
147
+ Unable to encrypt zipfile\")\n\n return ice_file"
148
+ pipeline_tag: sentence-similarity
149
+ library_name: sentence-transformers
150
+ metrics:
151
+ - pearson_cosine
152
+ - spearman_cosine
153
+ model-index:
154
+ - name: SentenceTransformer based on Shuu12121/CodeModernBERT-Owl
155
+ results:
156
+ - task:
157
+ type: semantic-similarity
158
+ name: Semantic Similarity
159
+ dataset:
160
+ name: code docstring dev
161
+ type: code-docstring-dev
162
+ metrics:
163
+ - type: pearson_cosine
164
+ value: .nan
165
+ name: Pearson Cosine
166
+ - type: spearman_cosine
167
+ value: .nan
168
+ name: Spearman Cosine
169
+ ---
170
+
171
+ # SentenceTransformer based on Shuu12121/CodeModernBERT-Owl
172
+
173
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Shuu12121/CodeModernBERT-Owl](https://huggingface.co/Shuu12121/CodeModernBERT-Owl). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
174
+
175
+ ## Model Details
176
+
177
+ ### Model Description
178
+ - **Model Type:** Sentence Transformer
179
+ - **Base model:** [Shuu12121/CodeModernBERT-Owl](https://huggingface.co/Shuu12121/CodeModernBERT-Owl) <!-- at revision d403250d7979eb141409c611c0a39fd7110543a4 -->
180
+ - **Maximum Sequence Length:** 2048 tokens
181
+ - **Output Dimensionality:** 768 dimensions
182
+ - **Similarity Function:** Cosine Similarity
183
+ <!-- - **Training Dataset:** Unknown -->
184
+ <!-- - **Language:** Unknown -->
185
+ <!-- - **License:** Unknown -->
186
+
187
+ ### Model Sources
188
+
189
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
190
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
191
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
192
+
193
+ ### Full Model Architecture
194
+
195
+ ```
196
+ SentenceTransformer(
197
+ (0): Transformer({'max_seq_length': 2048, 'do_lower_case': False}) with Transformer model: ModernBertModel
198
+ (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
199
+ )
200
+ ```
201
+
202
+ ## Usage
203
+
204
+ ### Direct Usage (Sentence Transformers)
205
+
206
+ First install the Sentence Transformers library:
207
+
208
+ ```bash
209
+ pip install -U sentence-transformers
210
+ ```
211
+
212
+ Then you can load this model and run inference.
213
+ ```python
214
+ from sentence_transformers import SentenceTransformer
215
+
216
+ # Download from the 🤗 Hub
217
+ model = SentenceTransformer("sentence_transformers_model_id")
218
+ # Run inference
219
+ sentences = [
220
+ 'Encrypts the zip file',
221
+ 'def freeze_encrypt(dest_dir, zip_filename, config, opt):\n \n pgp_keys = grok_keys(config)\n icefile_prefix = "aomi-%s" % \\\n os.path.basename(os.path.dirname(opt.secretfile))\n if opt.icefile_prefix:\n icefile_prefix = opt.icefile_prefix\n\n timestamp = time.strftime("%H%M%S-%m-%d-%Y",\n datetime.datetime.now().timetuple())\n ice_file = "%s/%s-%s.ice" % (dest_dir, icefile_prefix, timestamp)\n if not encrypt(zip_filename, ice_file, pgp_keys):\n raise aomi.exceptions.GPG("Unable to encrypt zipfile")\n\n return ice_file',
222
+ 'def transform(self, sents):\n \n\n def convert(tokens):\n return torch.tensor([self.vocab.stoi[t] for t in tokens], dtype=torch.long)\n\n if self.vocab is None:\n raise Exception(\n "Must run .fit() for .fit_transform() before " "calling .transform()."\n )\n\n seqs = sorted([convert(s) for s in sents], key=lambda x: -len(x))\n X = torch.LongTensor(pad_sequence(seqs, batch_first=True))\n return X',
223
+ ]
224
+ embeddings = model.encode(sentences)
225
+ print(embeddings.shape)
226
+ # [3, 768]
227
+
228
+ # Get the similarity scores for the embeddings
229
+ similarities = model.similarity(embeddings, embeddings)
230
+ print(similarities.shape)
231
+ # [3, 3]
232
+ ```
233
+
234
+ <!--
235
+ ### Direct Usage (Transformers)
236
+
237
+ <details><summary>Click to see the direct usage in Transformers</summary>
238
+
239
+ </details>
240
+ -->
241
+
242
+ <!--
243
+ ### Downstream Usage (Sentence Transformers)
244
+
245
+ You can finetune this model on your own dataset.
246
+
247
+ <details><summary>Click to expand</summary>
248
+
249
+ </details>
250
+ -->
251
+
252
+ <!--
253
+ ### Out-of-Scope Use
254
+
255
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
256
+ -->
257
+
258
+ ## Evaluation
259
+
260
+ ### Metrics
261
+
262
+ #### Semantic Similarity
263
+
264
+ * Dataset: `code-docstring-dev`
265
+ * Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
266
+
267
+ | Metric | Value |
268
+ |:--------------------|:--------|
269
+ | pearson_cosine | nan |
270
+ | **spearman_cosine** | **nan** |
271
+
272
+ <!--
273
+ ## Bias, Risks and Limitations
274
+
275
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
276
+ -->
277
+
278
+ <!--
279
+ ### Recommendations
280
+
281
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
282
+ -->
283
+
284
+ ## Training Details
285
+
286
+ ### Training Dataset
287
+
288
+ #### Unnamed Dataset
289
+
290
+ * Size: 1,431,743 training samples
291
+ * Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code>
292
+ * Approximate statistics based on the first 1000 samples:
293
+ | | sentence_0 | sentence_1 | label |
294
+ |:--------|:------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------|:--------------------------------------------------------------|
295
+ | type | string | string | float |
296
+ | details | <ul><li>min: 5 tokens</li><li>mean: 63.94 tokens</li><li>max: 1310 tokens</li></ul> | <ul><li>min: 29 tokens</li><li>mean: 173.04 tokens</li><li>max: 1801 tokens</li></ul> | <ul><li>min: 1.0</li><li>mean: 1.0</li><li>max: 1.0</li></ul> |
297
+ * Samples:
298
+ | sentence_0 | sentence_1 | label |
299
+ |:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------|
300
+ | <code>Serves a cross-domain policy which can allow other policies<br> to exist on the same domain.<br><br> Note that this view, if used, must be the master policy for the<br> domain, and so must be served from the URL ``/crossdomain.xml`` on<br> the domain: setting metapolicy information in other policy files<br> is forbidden by the cross-domain policy specification.<br><br> **Required arguments:**<br><br> ``permitted``<br> A string indicating the extent to which other policies are<br> permitted. A set of constants is available in<br> ``flashpolicies.policies``, defining acceptable values for<br> this argument.<br><br> **Optional arguments:**<br><br> ``domains``<br> A list of domains from which to allow access. Each value may<br> be either a domain name (e.g., ``example.com``) or a wildcard<br> (e.g., ``*.example.com``). Due to serious potential security<br> issues, it is strongly recommended that you not use wildcard<br> domain values.</code> | <code>def metapolicy(request, permitted, domains=None):<br> <br> if domains is None:<br> domains = []<br> policy = policies.Policy(*domains)<br> policy.metapolicy(permitted)<br> return serve(request, policy)</code> | <code>1.0</code> |
301
+ | <code>Puts a value from a VEX temporary register into a machine register.<br> This is how the results of operations done to registers get committed to the machine's state.<br><br> :param val: The VexValue to store (Want to store a constant? See Constant() first)<br> :param reg: The integer register number to store into, or register name<br> :return: None</code> | <code>def put(self, val, reg):<br> <br> offset = self.lookup_register(self.irsb_c.irsb.arch, reg)<br> self.irsb_c.put(val.rdt, offset)</code> | <code>1.0</code> |
302
+ | <code>Like `get_token`, but using an OAuth 2 authorization code.<br><br> Use this method if you run a webserver that serves as an endpoint for<br> the redirect URI. The webserver can retrieve the authorization code<br> from the URL that is requested by ORCID.<br><br> Parameters<br> ----------<br> :param redirect_uri: string<br> The redirect uri of the institution.<br> :param authorization_code: string<br> The authorization code.<br><br> Returns<br> -------<br> :returns: dict<br> All data of the access token. The access token itself is in the<br> ``"access_token"`` key.</code> | <code>def get_token_from_authorization_code(self,<br> authorization_code, redirect_uri):<br> <br> token_dict = {<br> "client_id": self._key,<br> "client_secret": self._secret,<br> "grant_type": "authorization_code",<br> "code": authorization_code,<br> "redirect_uri": redirect_uri,<br> }<br> response = requests.post(self._token_url, data=token_dict,<br> headers={'Accept': 'application/json'},<br> timeout=self._timeout)<br> response.raise_for_status()<br> if self.do_store_raw_response:<br> self.raw_response = response<br> return json.loads(response.text)</code> | <code>1.0</code> |
303
+ * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
304
+ ```json
305
+ {
306
+ "scale": 20.0,
307
+ "similarity_fct": "cos_sim"
308
+ }
309
+ ```
310
+
311
+ ### Training Hyperparameters
312
+ #### Non-Default Hyperparameters
313
+
314
+ - `eval_strategy`: steps
315
+ - `per_device_train_batch_size`: 24
316
+ - `per_device_eval_batch_size`: 24
317
+ - `fp16`: True
318
+ - `multi_dataset_batch_sampler`: round_robin
319
+
320
+ #### All Hyperparameters
321
+ <details><summary>Click to expand</summary>
322
+
323
+ - `overwrite_output_dir`: False
324
+ - `do_predict`: False
325
+ - `eval_strategy`: steps
326
+ - `prediction_loss_only`: True
327
+ - `per_device_train_batch_size`: 24
328
+ - `per_device_eval_batch_size`: 24
329
+ - `per_gpu_train_batch_size`: None
330
+ - `per_gpu_eval_batch_size`: None
331
+ - `gradient_accumulation_steps`: 1
332
+ - `eval_accumulation_steps`: None
333
+ - `torch_empty_cache_steps`: None
334
+ - `learning_rate`: 5e-05
335
+ - `weight_decay`: 0.0
336
+ - `adam_beta1`: 0.9
337
+ - `adam_beta2`: 0.999
338
+ - `adam_epsilon`: 1e-08
339
+ - `max_grad_norm`: 1
340
+ - `num_train_epochs`: 3
341
+ - `max_steps`: -1
342
+ - `lr_scheduler_type`: linear
343
+ - `lr_scheduler_kwargs`: {}
344
+ - `warmup_ratio`: 0.0
345
+ - `warmup_steps`: 0
346
+ - `log_level`: passive
347
+ - `log_level_replica`: warning
348
+ - `log_on_each_node`: True
349
+ - `logging_nan_inf_filter`: True
350
+ - `save_safetensors`: True
351
+ - `save_on_each_node`: False
352
+ - `save_only_model`: False
353
+ - `restore_callback_states_from_checkpoint`: False
354
+ - `no_cuda`: False
355
+ - `use_cpu`: False
356
+ - `use_mps_device`: False
357
+ - `seed`: 42
358
+ - `data_seed`: None
359
+ - `jit_mode_eval`: False
360
+ - `use_ipex`: False
361
+ - `bf16`: False
362
+ - `fp16`: True
363
+ - `fp16_opt_level`: O1
364
+ - `half_precision_backend`: auto
365
+ - `bf16_full_eval`: False
366
+ - `fp16_full_eval`: False
367
+ - `tf32`: None
368
+ - `local_rank`: 0
369
+ - `ddp_backend`: None
370
+ - `tpu_num_cores`: None
371
+ - `tpu_metrics_debug`: False
372
+ - `debug`: []
373
+ - `dataloader_drop_last`: False
374
+ - `dataloader_num_workers`: 0
375
+ - `dataloader_prefetch_factor`: None
376
+ - `past_index`: -1
377
+ - `disable_tqdm`: False
378
+ - `remove_unused_columns`: True
379
+ - `label_names`: None
380
+ - `load_best_model_at_end`: False
381
+ - `ignore_data_skip`: False
382
+ - `fsdp`: []
383
+ - `fsdp_min_num_params`: 0
384
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
385
+ - `tp_size`: 0
386
+ - `fsdp_transformer_layer_cls_to_wrap`: None
387
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
388
+ - `deepspeed`: None
389
+ - `label_smoothing_factor`: 0.0
390
+ - `optim`: adamw_torch
391
+ - `optim_args`: None
392
+ - `adafactor`: False
393
+ - `group_by_length`: False
394
+ - `length_column_name`: length
395
+ - `ddp_find_unused_parameters`: None
396
+ - `ddp_bucket_cap_mb`: None
397
+ - `ddp_broadcast_buffers`: False
398
+ - `dataloader_pin_memory`: True
399
+ - `dataloader_persistent_workers`: False
400
+ - `skip_memory_metrics`: True
401
+ - `use_legacy_prediction_loop`: False
402
+ - `push_to_hub`: False
403
+ - `resume_from_checkpoint`: None
404
+ - `hub_model_id`: None
405
+ - `hub_strategy`: every_save
406
+ - `hub_private_repo`: None
407
+ - `hub_always_push`: False
408
+ - `gradient_checkpointing`: False
409
+ - `gradient_checkpointing_kwargs`: None
410
+ - `include_inputs_for_metrics`: False
411
+ - `include_for_metrics`: []
412
+ - `eval_do_concat_batches`: True
413
+ - `fp16_backend`: auto
414
+ - `push_to_hub_model_id`: None
415
+ - `push_to_hub_organization`: None
416
+ - `mp_parameters`:
417
+ - `auto_find_batch_size`: False
418
+ - `full_determinism`: False
419
+ - `torchdynamo`: None
420
+ - `ray_scope`: last
421
+ - `ddp_timeout`: 1800
422
+ - `torch_compile`: False
423
+ - `torch_compile_backend`: None
424
+ - `torch_compile_mode`: None
425
+ - `dispatch_batches`: None
426
+ - `split_batches`: None
427
+ - `include_tokens_per_second`: False
428
+ - `include_num_input_tokens_seen`: False
429
+ - `neftune_noise_alpha`: None
430
+ - `optim_target_modules`: None
431
+ - `batch_eval_metrics`: False
432
+ - `eval_on_start`: False
433
+ - `use_liger_kernel`: False
434
+ - `eval_use_gather_object`: False
435
+ - `average_tokens_across_devices`: False
436
+ - `prompts`: None
437
+ - `batch_sampler`: batch_sampler
438
+ - `multi_dataset_batch_sampler`: round_robin
439
+
440
+ </details>
441
+
442
+ ### Training Logs
443
+ <details><summary>Click to expand</summary>
444
+
445
+ | Epoch | Step | Training Loss | code-docstring-dev_spearman_cosine |
446
+ |:------:|:------:|:-------------:|:----------------------------------:|
447
+ | 0.0084 | 500 | 0.9451 | - |
448
+ | 0.0168 | 1000 | 0.1154 | - |
449
+ | 0.0251 | 1500 | 0.0817 | - |
450
+ | 0.0335 | 2000 | 0.0733 | - |
451
+ | 0.0419 | 2500 | 0.0751 | - |
452
+ | 0.0503 | 3000 | 0.0629 | - |
453
+ | 0.0587 | 3500 | 0.0551 | - |
454
+ | 0.0671 | 4000 | 0.0604 | - |
455
+ | 0.0754 | 4500 | 0.0628 | - |
456
+ | 0.0838 | 5000 | 0.0548 | nan |
457
+ | 0.0922 | 5500 | 0.054 | - |
458
+ | 0.1006 | 6000 | 0.0538 | - |
459
+ | 0.1090 | 6500 | 0.0518 | - |
460
+ | 0.1173 | 7000 | 0.0543 | - |
461
+ | 0.1257 | 7500 | 0.0491 | - |
462
+ | 0.1341 | 8000 | 0.0446 | - |
463
+ | 0.1425 | 8500 | 0.049 | - |
464
+ | 0.1509 | 9000 | 0.0477 | - |
465
+ | 0.1592 | 9500 | 0.0458 | - |
466
+ | 0.1676 | 10000 | 0.0425 | nan |
467
+ | 0.1760 | 10500 | 0.0445 | - |
468
+ | 0.1844 | 11000 | 0.0397 | - |
469
+ | 0.1928 | 11500 | 0.044 | - |
470
+ | 0.2012 | 12000 | 0.0432 | - |
471
+ | 0.2095 | 12500 | 0.0402 | - |
472
+ | 0.2179 | 13000 | 0.0483 | - |
473
+ | 0.2263 | 13500 | 0.0434 | - |
474
+ | 0.2347 | 14000 | 0.0425 | - |
475
+ | 0.2431 | 14500 | 0.0464 | - |
476
+ | 0.2514 | 15000 | 0.038 | nan |
477
+ | 0.2598 | 15500 | 0.0391 | - |
478
+ | 0.2682 | 16000 | 0.0385 | - |
479
+ | 0.2766 | 16500 | 0.0383 | - |
480
+ | 0.2850 | 17000 | 0.0396 | - |
481
+ | 0.2933 | 17500 | 0.0394 | - |
482
+ | 0.3017 | 18000 | 0.0407 | - |
483
+ | 0.3101 | 18500 | 0.0437 | - |
484
+ | 0.3185 | 19000 | 0.0362 | - |
485
+ | 0.3269 | 19500 | 0.0398 | - |
486
+ | 0.3353 | 20000 | 0.0379 | nan |
487
+ | 0.3436 | 20500 | 0.0418 | - |
488
+ | 0.3520 | 21000 | 0.0348 | - |
489
+ | 0.3604 | 21500 | 0.0382 | - |
490
+ | 0.3688 | 22000 | 0.0374 | - |
491
+ | 0.3772 | 22500 | 0.038 | - |
492
+ | 0.3855 | 23000 | 0.0365 | - |
493
+ | 0.3939 | 23500 | 0.0348 | - |
494
+ | 0.4023 | 24000 | 0.0405 | - |
495
+ | 0.4107 | 24500 | 0.04 | - |
496
+ | 0.4191 | 25000 | 0.0362 | nan |
497
+ | 0.4275 | 25500 | 0.0327 | - |
498
+ | 0.4358 | 26000 | 0.0331 | - |
499
+ | 0.4442 | 26500 | 0.0309 | - |
500
+ | 0.4526 | 27000 | 0.0348 | - |
501
+ | 0.4610 | 27500 | 0.0295 | - |
502
+ | 0.4694 | 28000 | 0.0378 | - |
503
+ | 0.4777 | 28500 | 0.0318 | - |
504
+ | 0.4861 | 29000 | 0.0323 | - |
505
+ | 0.4945 | 29500 | 0.0315 | - |
506
+ | 0.5029 | 30000 | 0.0336 | nan |
507
+ | 0.5113 | 30500 | 0.0334 | - |
508
+ | 0.5196 | 31000 | 0.0342 | - |
509
+ | 0.5280 | 31500 | 0.0289 | - |
510
+ | 0.5364 | 32000 | 0.0332 | - |
511
+ | 0.5448 | 32500 | 0.0305 | - |
512
+ | 0.5532 | 33000 | 0.0349 | - |
513
+ | 0.5616 | 33500 | 0.0309 | - |
514
+ | 0.5699 | 34000 | 0.0352 | - |
515
+ | 0.5783 | 34500 | 0.035 | - |
516
+ | 0.5867 | 35000 | 0.0316 | nan |
517
+ | 0.5951 | 35500 | 0.0342 | - |
518
+ | 0.6035 | 36000 | 0.0274 | - |
519
+ | 0.6118 | 36500 | 0.0333 | - |
520
+ | 0.6202 | 37000 | 0.0294 | - |
521
+ | 0.6286 | 37500 | 0.029 | - |
522
+ | 0.6370 | 38000 | 0.0302 | - |
523
+ | 0.6454 | 38500 | 0.0292 | - |
524
+ | 0.6537 | 39000 | 0.032 | - |
525
+ | 0.6621 | 39500 | 0.03 | - |
526
+ | 0.6705 | 40000 | 0.0246 | nan |
527
+ | 0.6789 | 40500 | 0.0277 | - |
528
+ | 0.6873 | 41000 | 0.0262 | - |
529
+ | 0.6957 | 41500 | 0.0293 | - |
530
+ | 0.7040 | 42000 | 0.0284 | - |
531
+ | 0.7124 | 42500 | 0.028 | - |
532
+ | 0.7208 | 43000 | 0.0321 | - |
533
+ | 0.7292 | 43500 | 0.0283 | - |
534
+ | 0.7376 | 44000 | 0.0295 | - |
535
+ | 0.7459 | 44500 | 0.0279 | - |
536
+ | 0.7543 | 45000 | 0.0249 | nan |
537
+ | 0.7627 | 45500 | 0.0299 | - |
538
+ | 0.7711 | 46000 | 0.0258 | - |
539
+ | 0.7795 | 46500 | 0.0257 | - |
540
+ | 0.7879 | 47000 | 0.0256 | - |
541
+ | 0.7962 | 47500 | 0.0281 | - |
542
+ | 0.8046 | 48000 | 0.0279 | - |
543
+ | 0.8130 | 48500 | 0.0299 | - |
544
+ | 0.8214 | 49000 | 0.027 | - |
545
+ | 0.8298 | 49500 | 0.0271 | - |
546
+ | 0.8381 | 50000 | 0.0281 | nan |
547
+ | 0.8465 | 50500 | 0.0274 | - |
548
+ | 0.8549 | 51000 | 0.0262 | - |
549
+ | 0.8633 | 51500 | 0.0306 | - |
550
+ | 0.8717 | 52000 | 0.0262 | - |
551
+ | 0.8800 | 52500 | 0.0241 | - |
552
+ | 0.8884 | 53000 | 0.0235 | - |
553
+ | 0.8968 | 53500 | 0.0268 | - |
554
+ | 0.9052 | 54000 | 0.0251 | - |
555
+ | 0.9136 | 54500 | 0.0328 | - |
556
+ | 0.9220 | 55000 | 0.0235 | nan |
557
+ | 0.9303 | 55500 | 0.0261 | - |
558
+ | 0.9387 | 56000 | 0.0249 | - |
559
+ | 0.9471 | 56500 | 0.0262 | - |
560
+ | 0.9555 | 57000 | 0.0231 | - |
561
+ | 0.9639 | 57500 | 0.0249 | - |
562
+ | 0.9722 | 58000 | 0.0246 | - |
563
+ | 0.9806 | 58500 | 0.0299 | - |
564
+ | 0.9890 | 59000 | 0.0238 | - |
565
+ | 0.9974 | 59500 | 0.0215 | - |
566
+ | 1.0 | 59656 | - | nan |
567
+ | 1.0058 | 60000 | 0.0157 | nan |
568
+ | 1.0141 | 60500 | 0.0095 | - |
569
+ | 1.0225 | 61000 | 0.012 | - |
570
+ | 1.0309 | 61500 | 0.0105 | - |
571
+ | 1.0393 | 62000 | 0.01 | - |
572
+ | 1.0477 | 62500 | 0.0101 | - |
573
+ | 1.0561 | 63000 | 0.0107 | - |
574
+ | 1.0644 | 63500 | 0.0102 | - |
575
+ | 1.0728 | 64000 | 0.011 | - |
576
+ | 1.0812 | 64500 | 0.0088 | - |
577
+ | 1.0896 | 65000 | 0.0106 | nan |
578
+ | 1.0980 | 65500 | 0.0108 | - |
579
+ | 1.1063 | 66000 | 0.0108 | - |
580
+ | 1.1147 | 66500 | 0.011 | - |
581
+ | 1.1231 | 67000 | 0.0082 | - |
582
+ | 1.1315 | 67500 | 0.0092 | - |
583
+ | 1.1399 | 68000 | 0.0106 | - |
584
+ | 1.1482 | 68500 | 0.0117 | - |
585
+ | 1.1566 | 69000 | 0.0096 | - |
586
+ | 1.1650 | 69500 | 0.0094 | - |
587
+ | 1.1734 | 70000 | 0.0098 | nan |
588
+ | 1.1818 | 70500 | 0.0084 | - |
589
+ | 1.1902 | 71000 | 0.0103 | - |
590
+ | 1.1985 | 71500 | 0.0112 | - |
591
+ | 1.2069 | 72000 | 0.0108 | - |
592
+ | 1.2153 | 72500 | 0.0121 | - |
593
+ | 1.2237 | 73000 | 0.0103 | - |
594
+ | 1.2321 | 73500 | 0.012 | - |
595
+ | 1.2404 | 74000 | 0.0134 | - |
596
+ | 1.2488 | 74500 | 0.0097 | - |
597
+ | 1.2572 | 75000 | 0.0121 | nan |
598
+ | 1.2656 | 75500 | 0.0117 | - |
599
+ | 1.2740 | 76000 | 0.0108 | - |
600
+ | 1.2824 | 76500 | 0.0106 | - |
601
+ | 1.2907 | 77000 | 0.0085 | - |
602
+ | 1.2991 | 77500 | 0.0119 | - |
603
+ | 1.3075 | 78000 | 0.0099 | - |
604
+ | 1.3159 | 78500 | 0.0102 | - |
605
+ | 1.3243 | 79000 | 0.011 | - |
606
+ | 1.3326 | 79500 | 0.0108 | - |
607
+ | 1.3410 | 80000 | 0.0097 | nan |
608
+ | 1.3494 | 80500 | 0.0101 | - |
609
+ | 1.3578 | 81000 | 0.0082 | - |
610
+ | 1.3662 | 81500 | 0.0107 | - |
611
+ | 1.3745 | 82000 | 0.013 | - |
612
+ | 1.3829 | 82500 | 0.0068 | - |
613
+ | 1.3913 | 83000 | 0.0102 | - |
614
+ | 1.3997 | 83500 | 0.0079 | - |
615
+ | 1.4081 | 84000 | 0.0116 | - |
616
+ | 1.4165 | 84500 | 0.0095 | - |
617
+ | 1.4248 | 85000 | 0.0105 | nan |
618
+ | 1.4332 | 85500 | 0.011 | - |
619
+ | 1.4416 | 86000 | 0.0131 | - |
620
+ | 1.4500 | 86500 | 0.012 | - |
621
+ | 1.4584 | 87000 | 0.0105 | - |
622
+ | 1.4667 | 87500 | 0.0117 | - |
623
+ | 1.4751 | 88000 | 0.0101 | - |
624
+ | 1.4835 | 88500 | 0.0108 | - |
625
+ | 1.4919 | 89000 | 0.0091 | - |
626
+ | 1.5003 | 89500 | 0.0086 | - |
627
+ | 1.5086 | 90000 | 0.0093 | nan |
628
+ | 1.5170 | 90500 | 0.0102 | - |
629
+ | 1.5254 | 91000 | 0.0078 | - |
630
+ | 1.5338 | 91500 | 0.0096 | - |
631
+ | 1.5422 | 92000 | 0.0103 | - |
632
+ | 1.5506 | 92500 | 0.0099 | - |
633
+ | 1.5589 | 93000 | 0.011 | - |
634
+ | 1.5673 | 93500 | 0.0079 | - |
635
+ | 1.5757 | 94000 | 0.0108 | - |
636
+ | 1.5841 | 94500 | 0.0089 | - |
637
+ | 1.5925 | 95000 | 0.0115 | nan |
638
+ | 1.6008 | 95500 | 0.0092 | - |
639
+ | 1.6092 | 96000 | 0.0093 | - |
640
+ | 1.6176 | 96500 | 0.0083 | - |
641
+ | 1.6260 | 97000 | 0.0103 | - |
642
+ | 1.6344 | 97500 | 0.01 | - |
643
+ | 1.6428 | 98000 | 0.0091 | - |
644
+ | 1.6511 | 98500 | 0.0106 | - |
645
+ | 1.6595 | 99000 | 0.0105 | - |
646
+ | 1.6679 | 99500 | 0.0096 | - |
647
+ | 1.6763 | 100000 | 0.0116 | nan |
648
+ | 1.6847 | 100500 | 0.0093 | - |
649
+ | 1.6930 | 101000 | 0.01 | - |
650
+ | 1.7014 | 101500 | 0.0076 | - |
651
+ | 1.7098 | 102000 | 0.0078 | - |
652
+ | 1.7182 | 102500 | 0.0089 | - |
653
+ | 1.7266 | 103000 | 0.0082 | - |
654
+ | 1.7349 | 103500 | 0.0081 | - |
655
+ | 1.7433 | 104000 | 0.009 | - |
656
+ | 1.7517 | 104500 | 0.0082 | - |
657
+ | 1.7601 | 105000 | 0.008 | nan |
658
+ | 1.7685 | 105500 | 0.0082 | - |
659
+ | 1.7769 | 106000 | 0.0077 | - |
660
+ | 1.7852 | 106500 | 0.0103 | - |
661
+ | 1.7936 | 107000 | 0.0103 | - |
662
+ | 1.8020 | 107500 | 0.0103 | - |
663
+ | 1.8104 | 108000 | 0.0079 | - |
664
+ | 1.8188 | 108500 | 0.0082 | - |
665
+ | 1.8271 | 109000 | 0.0088 | - |
666
+ | 1.8355 | 109500 | 0.0096 | - |
667
+ | 1.8439 | 110000 | 0.0097 | nan |
668
+ | 1.8523 | 110500 | 0.0085 | - |
669
+ | 1.8607 | 111000 | 0.01 | - |
670
+ | 1.8690 | 111500 | 0.0114 | - |
671
+ | 1.8774 | 112000 | 0.0075 | - |
672
+ | 1.8858 | 112500 | 0.0083 | - |
673
+ | 1.8942 | 113000 | 0.0113 | - |
674
+ | 1.9026 | 113500 | 0.0077 | - |
675
+ | 1.9110 | 114000 | 0.0077 | - |
676
+ | 1.9193 | 114500 | 0.0107 | - |
677
+ | 1.9277 | 115000 | 0.0077 | nan |
678
+ | 1.9361 | 115500 | 0.0094 | - |
679
+ | 1.9445 | 116000 | 0.0082 | - |
680
+ | 1.9529 | 116500 | 0.0089 | - |
681
+ | 1.9612 | 117000 | 0.0066 | - |
682
+ | 1.9696 | 117500 | 0.0102 | - |
683
+ | 1.9780 | 118000 | 0.0097 | - |
684
+ | 1.9864 | 118500 | 0.0081 | - |
685
+ | 1.9948 | 119000 | 0.0086 | - |
686
+ | 2.0 | 119312 | - | nan |
687
+ | 2.0032 | 119500 | 0.0063 | - |
688
+ | 2.0115 | 120000 | 0.0051 | nan |
689
+ | 2.0199 | 120500 | 0.0037 | - |
690
+ | 2.0283 | 121000 | 0.0062 | - |
691
+ | 2.0367 | 121500 | 0.0045 | - |
692
+ | 2.0451 | 122000 | 0.0046 | - |
693
+ | 2.0534 | 122500 | 0.0038 | - |
694
+ | 2.0618 | 123000 | 0.0044 | - |
695
+ | 2.0702 | 123500 | 0.0042 | - |
696
+ | 2.0786 | 124000 | 0.0029 | - |
697
+ | 2.0870 | 124500 | 0.0029 | - |
698
+ | 2.0953 | 125000 | 0.0067 | nan |
699
+ | 2.1037 | 125500 | 0.0067 | - |
700
+ | 2.1121 | 126000 | 0.005 | - |
701
+ | 2.1205 | 126500 | 0.005 | - |
702
+ | 2.1289 | 127000 | 0.0037 | - |
703
+ | 2.1373 | 127500 | 0.0043 | - |
704
+ | 2.1456 | 128000 | 0.0036 | - |
705
+ | 2.1540 | 128500 | 0.0042 | - |
706
+ | 2.1624 | 129000 | 0.0039 | - |
707
+ | 2.1708 | 129500 | 0.0032 | - |
708
+ | 2.1792 | 130000 | 0.0046 | nan |
709
+ | 2.1875 | 130500 | 0.0037 | - |
710
+ | 2.1959 | 131000 | 0.0036 | - |
711
+ | 2.2043 | 131500 | 0.0042 | - |
712
+ | 2.2127 | 132000 | 0.0044 | - |
713
+ | 2.2211 | 132500 | 0.0028 | - |
714
+ | 2.2294 | 133000 | 0.0043 | - |
715
+ | 2.2378 | 133500 | 0.0052 | - |
716
+ | 2.2462 | 134000 | 0.0031 | - |
717
+ | 2.2546 | 134500 | 0.0048 | - |
718
+ | 2.2630 | 135000 | 0.0031 | nan |
719
+ | 2.2714 | 135500 | 0.0054 | - |
720
+ | 2.2797 | 136000 | 0.0033 | - |
721
+ | 2.2881 | 136500 | 0.0036 | - |
722
+ | 2.2965 | 137000 | 0.0033 | - |
723
+ | 2.3049 | 137500 | 0.0039 | - |
724
+ | 2.3133 | 138000 | 0.0044 | - |
725
+ | 2.3216 | 138500 | 0.0034 | - |
726
+ | 2.3300 | 139000 | 0.0058 | - |
727
+ | 2.3384 | 139500 | 0.0036 | - |
728
+ | 2.3468 | 140000 | 0.0033 | nan |
729
+ | 2.3552 | 140500 | 0.0034 | - |
730
+ | 2.3636 | 141000 | 0.0032 | - |
731
+ | 2.3719 | 141500 | 0.0036 | - |
732
+ | 2.3803 | 142000 | 0.0038 | - |
733
+ | 2.3887 | 142500 | 0.0036 | - |
734
+ | 2.3971 | 143000 | 0.0045 | - |
735
+ | 2.4055 | 143500 | 0.0035 | - |
736
+ | 2.4138 | 144000 | 0.0042 | - |
737
+ | 2.4222 | 144500 | 0.0029 | - |
738
+ | 2.4306 | 145000 | 0.005 | nan |
739
+ | 2.4390 | 145500 | 0.0045 | - |
740
+ | 2.4474 | 146000 | 0.0035 | - |
741
+ | 2.4557 | 146500 | 0.004 | - |
742
+ | 2.4641 | 147000 | 0.0044 | - |
743
+ | 2.4725 | 147500 | 0.0036 | - |
744
+ | 2.4809 | 148000 | 0.0047 | - |
745
+ | 2.4893 | 148500 | 0.0035 | - |
746
+ | 2.4977 | 149000 | 0.0048 | - |
747
+ | 2.5060 | 149500 | 0.0041 | - |
748
+ | 2.5144 | 150000 | 0.0029 | nan |
749
+ | 2.5228 | 150500 | 0.0038 | - |
750
+ | 2.5312 | 151000 | 0.0032 | - |
751
+ | 2.5396 | 151500 | 0.0043 | - |
752
+ | 2.5479 | 152000 | 0.0038 | - |
753
+ | 2.5563 | 152500 | 0.0037 | - |
754
+ | 2.5647 | 153000 | 0.0023 | - |
755
+ | 2.5731 | 153500 | 0.0041 | - |
756
+ | 2.5815 | 154000 | 0.0049 | - |
757
+ | 2.5898 | 154500 | 0.0048 | - |
758
+ | 2.5982 | 155000 | 0.0034 | nan |
759
+ | 2.6066 | 155500 | 0.0031 | - |
760
+ | 2.6150 | 156000 | 0.0036 | - |
761
+ | 2.6234 | 156500 | 0.0034 | - |
762
+ | 2.6318 | 157000 | 0.0037 | - |
763
+ | 2.6401 | 157500 | 0.0035 | - |
764
+ | 2.6485 | 158000 | 0.0037 | - |
765
+ | 2.6569 | 158500 | 0.0043 | - |
766
+ | 2.6653 | 159000 | 0.0042 | - |
767
+ | 2.6737 | 159500 | 0.0049 | - |
768
+ | 2.6820 | 160000 | 0.0035 | nan |
769
+ | 2.6904 | 160500 | 0.0026 | - |
770
+ | 2.6988 | 161000 | 0.0049 | - |
771
+ | 2.7072 | 161500 | 0.0034 | - |
772
+ | 2.7156 | 162000 | 0.0039 | - |
773
+ | 2.7240 | 162500 | 0.0042 | - |
774
+ | 2.7323 | 163000 | 0.0052 | - |
775
+ | 2.7407 | 163500 | 0.0045 | - |
776
+ | 2.7491 | 164000 | 0.0043 | - |
777
+ | 2.7575 | 164500 | 0.0034 | - |
778
+ | 2.7659 | 165000 | 0.0038 | nan |
779
+ | 2.7742 | 165500 | 0.0029 | - |
780
+ | 2.7826 | 166000 | 0.0041 | - |
781
+ | 2.7910 | 166500 | 0.0041 | - |
782
+ | 2.7994 | 167000 | 0.0048 | - |
783
+ | 2.8078 | 167500 | 0.0044 | - |
784
+ | 2.8161 | 168000 | 0.0041 | - |
785
+ | 2.8245 | 168500 | 0.0035 | - |
786
+ | 2.8329 | 169000 | 0.0026 | - |
787
+ | 2.8413 | 169500 | 0.0033 | - |
788
+ | 2.8497 | 170000 | 0.0048 | nan |
789
+ | 2.8581 | 170500 | 0.0046 | - |
790
+ | 2.8664 | 171000 | 0.0027 | - |
791
+ | 2.8748 | 171500 | 0.0037 | - |
792
+ | 2.8832 | 172000 | 0.0028 | - |
793
+ | 2.8916 | 172500 | 0.0032 | - |
794
+ | 2.9000 | 173000 | 0.0029 | - |
795
+ | 2.9083 | 173500 | 0.0043 | - |
796
+ | 2.9167 | 174000 | 0.0048 | - |
797
+ | 2.9251 | 174500 | 0.0037 | - |
798
+ | 2.9335 | 175000 | 0.003 | nan |
799
+ | 2.9419 | 175500 | 0.0034 | - |
800
+ | 2.9502 | 176000 | 0.0035 | - |
801
+ | 2.9586 | 176500 | 0.0042 | - |
802
+ | 2.9670 | 177000 | 0.005 | - |
803
+ | 2.9754 | 177500 | 0.0038 | - |
804
+ | 2.9838 | 178000 | 0.0032 | - |
805
+ | 2.9922 | 178500 | 0.0028 | - |
806
+ | 3.0 | 178968 | - | nan |
807
+
808
+ </details>
809
+
810
+ ### Framework Versions
811
+ - Python: 3.11.11
812
+ - Sentence Transformers: 3.4.1
813
+ - Transformers: 4.50.0
814
+ - PyTorch: 2.6.0+cu124
815
+ - Accelerate: 1.5.2
816
+ - Datasets: 3.4.1
817
+ - Tokenizers: 0.21.1
818
+
819
+ ## Citation
820
+
821
+ ### BibTeX
822
+
823
+ #### Sentence Transformers
824
+ ```bibtex
825
+ @inproceedings{reimers-2019-sentence-bert,
826
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
827
+ author = "Reimers, Nils and Gurevych, Iryna",
828
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
829
+ month = "11",
830
+ year = "2019",
831
+ publisher = "Association for Computational Linguistics",
832
+ url = "https://arxiv.org/abs/1908.10084",
833
+ }
834
+ ```
835
+
836
+ #### MultipleNegativesRankingLoss
837
+ ```bibtex
838
+ @misc{henderson2017efficient,
839
+ title={Efficient Natural Language Response Suggestion for Smart Reply},
840
+ author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
841
+ year={2017},
842
+ eprint={1705.00652},
843
+ archivePrefix={arXiv},
844
+ primaryClass={cs.CL}
845
+ }
846
+ ```
847
+
848
+ <!--
849
+ ## Glossary
850
+
851
+ *Clearly define terms in order to be accessible across audiences.*
852
+ -->
853
+
854
+ <!--
855
+ ## Model Card Authors
856
+
857
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
858
+ -->
859
+
860
+ <!--
861
+ ## Model Card Contact
862
+
863
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
864
+ -->
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 50001,
3
+ "<mask>": 50003,
4
+ "<s>": 50000,
5
+ "<unk>": 50002
6
+ }
config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertModel"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "bos_token_id": 50000,
9
+ "classifier_activation": "gelu",
10
+ "classifier_bias": false,
11
+ "classifier_dropout": 0.0,
12
+ "classifier_pooling": "cls",
13
+ "cls_token_id": 50281,
14
+ "decoder_bias": true,
15
+ "deterministic_flash_attn": false,
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": 50001,
18
+ "global_attn_every_n_layers": 3,
19
+ "global_rope_theta": 160000.0,
20
+ "hidden_activation": "gelu",
21
+ "hidden_dropout_prob": 0.1,
22
+ "hidden_size": 768,
23
+ "initializer_cutoff_factor": 2.0,
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 3072,
26
+ "local_attention": 128,
27
+ "local_attention_rope_theta": 10000,
28
+ "local_attention_window": 128,
29
+ "local_rope_theta": 10000.0,
30
+ "max_position_embeddings": 2048,
31
+ "mlp_bias": false,
32
+ "mlp_dropout": 0.0,
33
+ "model_type": "modernbert",
34
+ "norm_bias": false,
35
+ "norm_eps": 1e-05,
36
+ "num_attention_heads": 12,
37
+ "num_hidden_layers": 12,
38
+ "pad_token_id": 0,
39
+ "reference_compile": true,
40
+ "repad_logits_with_grad": false,
41
+ "rope_theta": 160000,
42
+ "sep_token_id": 50282,
43
+ "sparse_pred_ignore_index": -100,
44
+ "sparse_prediction": false,
45
+ "torch_dtype": "float32",
46
+ "transformers_version": "4.50.0",
47
+ "type_vocab_size": 2,
48
+ "vocab_size": 50004
49
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.4.1",
4
+ "transformers": "4.50.0",
5
+ "pytorch": "2.6.0+cu124"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null,
9
+ "similarity_fn_name": "cosine"
10
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce36f107bd10656b4ecc916283ead69854b319716689adb30de197cde6dd8aed
3
+ size 606681112
modules.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ }
14
+ ]
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 2048,
3
+ "do_lower_case": false
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "[PAD]",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "[UNK]",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "[CLS]",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "[SEP]",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "[MASK]",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "50000": {
45
+ "content": "<s>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "50001": {
53
+ "content": "</s>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "50002": {
61
+ "content": "<unk>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "50003": {
69
+ "content": "<mask>",
70
+ "lstrip": true,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ }
76
+ },
77
+ "bos_token": "<s>",
78
+ "clean_up_tokenization_spaces": false,
79
+ "cls_token": "<s>",
80
+ "eos_token": "</s>",
81
+ "errors": "replace",
82
+ "extra_special_tokens": {},
83
+ "mask_token": "<mask>",
84
+ "max_length": null,
85
+ "model_max_length": 1000000000000000019884624838656,
86
+ "pad_to_multiple_of": null,
87
+ "pad_token": "[PAD]",
88
+ "pad_token_type_id": 0,
89
+ "padding_side": "right",
90
+ "sep_token": "</s>",
91
+ "stride": 0,
92
+ "tokenizer_class": "RobertaTokenizer",
93
+ "trim_offsets": true,
94
+ "truncation_side": "right",
95
+ "truncation_strategy": "longest_first",
96
+ "unk_token": "<unk>"
97
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff