metadata
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- dense
- generated_from_trainer
- dataset_size:400
- loss:MultipleNegativesRankingLoss
base_model: Qwen/Qwen3-Embedding-0.6B
widget:
- source_sentence: |-
Wrapper for calling the clean method of services attribute
:return: None
sentences:
- |-
def import_from_nhmmer_table(hmmout_path):
res=HMMSearchResult()
res.fields = [
SequenceSearchResult.QUERY_ID_FIELD,
SequenceSearchResult.HMM_NAME_FIELD,
SequenceSearchResult.ALIGNMENT_LENGTH_FIELD,
SequenceSearchResult.QUERY_FROM_FIELD,
SequenceSearchResult.QUERY_TO_FIELD,
SequenceSearchResult.HIT_FROM_FIELD,
SequenceSearchResult.HIT_TO_FIELD,
SequenceSearchResult.ALIGNMENT_BIT_SCORE,
SequenceSearchResult.ALIGNMENT_DIRECTION,
]
for row in [x.rstrip().split() for x in open(hmmout_path) if not x.startswith()]:
alifrom = int(row[6])
alito = int(row[7])
aln_length = (alito-alifrom if alito-alifrom>0 else alifrom-alito)
res.results.append([row[0],
row[2],
aln_length,
int(row[4]),
int(row[5]),
alifrom,
alito,
row[13],
alito > alifrom
])
return res
- |-
def clean(self):
logger.debug("Cleaning configuration objects before configuration sending:")
types_creations = self.__class__.types_creations
for o_type in types_creations:
(_, _, inner_property, _, _) = types_creations[o_type]
logger.debug(" . for %s", inner_property, )
inner_object = getattr(self, inner_property)
inner_object.clean()
- |-
def index_modules(idx=None, path=None):
suppress_output()
modules = defaultdict(list)
pkglist = pkgutil.walk_packages(onerror=lambda x: True)
print(pkglist)
if path:
pkglist = pkgutil.walk_packages(path, onerror=lambda x: True)
for modl, name, ispkg in pkglist:
try:
path = os.path.join(modl.path, name.split()[-1])
except AttributeError:
continue
if os.path.isdir(path):
path = os.path.join(path, )
path +=
objs = []
if os.path.exists(path):
try:
objs = read_objs_from_path(path)
except:
continue
elif not re.search(MODULE_BLACKLIST, name):
try:
mod = __import__(name)
objs = [k for k in dir(mod) if not k.startswith()]
except:
continue
else:
continue
for obj in objs:
if name not in modules[obj]:
modules[obj].append(name)
suppress_output(True)
return merge_dicts(idx, dict(modules))
- source_sentence: Try to import the aeneas package and return ``True`` if that fails.
sentences:
- |-
def check_import():
try:
import aeneas
print_success(u"aeneas OK")
return False
except ImportError:
print_error(u"aeneas ERROR")
print_info(u" Unable to load the aeneas Python package")
print_info(u" This error is probably caused by:")
print_info(u" A. you did not download/git-clone the aeneas package properly; or")
print_info(u" B. you did not install the required Python packages:")
print_info(u" 1. BeautifulSoup4")
print_info(u" 2. lxml")
print_info(u" 3. numpy")
except Exception as e:
print_error(e)
return True
- |-
def simplify(source, kink=20):
source_coord = map(lambda o: {"lng": o.coordinates[0], "lat": o.coordinates[1]}, source)
F = (math.pi / 180.0) * 0.5
index = []
sig_start = []
sig_end = []
count = len(source_coord)
if count < 3:
return source_coord
band_sqr = kink * 360.0 / (2.0 * math.pi * 6378137.0)
band_sqr *= band_sqr
n_dest = 0
sig_start[0] = 0
sig_end[0] = count - 1
n_stack = 1
while n_stack > 0:
start = sig_start[n_stack - 1]
end = sig_end[n_stack - 1]
n_stack -= 1
if (end - start) > 1:
x12 = source[end]["lng"] - source[start]["lng"]
y12 = source[end]["lat"] - source[start]["lat"]
if math.fabs(x12) > 180.0:
x12 = 360.0 - math.fabs(x12)
x12 *= math.cos(F * (source[end]["lat"] + source[start]["lat"]))
d12 = (x12 * x12) + (y12 * y12)
i = start + 1
sig = start
max_dev_sqr = -1.0
while i < end:
x13 = source[i]["lng"] - source[start]["lng"]
y13 = source[i]["lat"] - source[start]["lat"]
if math.fabs(x13) > 180.0:
x13 = 360.0 - math.fabs(x13)
x13 *= math.cos(F * (source[i]["lat"] + source[start]["lat"]))
d13 = (x13 * x13) + (y13 * y13)
x23 = source[i]["lng"] - source[end]["lng"]
y23 = source[i]["lat"] - source[end]["lat"]
if math.fabs(x23) > 180.0:
x23 = 360.0 - math.fabs(x23)
x23 *= math.cos(F * (source[i]["lat"] + source[end]["lat"]))
d23 = (x23 * x23) + (y23 * y23)
if d13 >= (d12 + d23):
dev_sqr = d23
elif d23 >= (d12 + d13):
dev_sqr = d13
else:
dev_sqr = (x13 * y12 - y13 * x12) * (x13 * y12 - y13 * x12) / d12
if dev_sqr > max_dev_sqr:
sig = i
max_dev_sqr = dev_sqr
i += 1
if max_dev_sqr < band_sqr:
index[n_dest] = start
n_dest += 1
else:
n_stack += 1
sig_start[n_stack - 1] = sig
sig_end[n_stack - 1] = end
n_stack += 1
sig_start[n_stack - 1] = start
sig_end[n_stack - 1] = sig
else:
index[n_dest] = start
n_dest += 1
index[n_dest] = count - 1
n_dest += 1
r = []
for i in range(0, n_dest):
r.append(source_coord[index[i]])
return map(lambda o: {"type": "Point","coordinates": [o.lng, o.lat]}, r)
- "def smooth(data, fw):\r\n \r\n if fw == 0:\r\n fdata = data\r\n else:\r\n fdata = lfilter(np.ones(fw)/fw, 1, data)\r\n return fdata"
- source_sentence: Start response processing.
sentences:
- |-
async def start(self, connection: ) -> :
self._closed = False
self._protocol = connection.protocol
self._connection = connection
with self._timer:
while True:
try:
message, payload = await self._protocol.read()
except http.HttpProcessingError as exc:
raise ClientResponseError(
self.request_info, self.history,
status=exc.code,
message=exc.message, headers=exc.headers) from exc
if (message.code < 100 or
message.code > 199 or message.code == 101):
break
if self._continue is not None:
set_result(self._continue, True)
self._continue = None
payload.on_eof(self._response_eof)
self.version = message.version
self.status = message.code
self.reason = message.reason
self._headers = message.headers
self._raw_headers = message.raw_headers
self.content = payload
for hdr in self.headers.getall(hdrs.SET_COOKIE, ()):
try:
self.cookies.load(hdr)
except CookieError as exc:
client_logger.warning(
, exc)
return self
- |-
def solve(self, verbose=False, allow_brute_force=True):
while not self.is_solved:
self._update()
singles_found = False or self._fill_naked_singles() or self._fill_hidden_singles()
if not singles_found:
if allow_brute_force:
solution = None
try:
dlxs = DancingLinksSolver(copy.deepcopy(self._matrix))
solutions = dlxs.solve()
solution = next(solutions)
more_solutions = next(solutions)
except StopIteration as e:
if solution is not None:
self._matrix = solution
else:
raise SudokuHasNoSolutionError("Dancing Links solver could not find any solution.")
except Exception as e:
raise SudokuHasNoSolutionError("Brute Force method failed.")
else:
raise SudokuHasMultipleSolutionsError("This Sudoku has multiple solutions!")
self.solution_steps.append("BRUTE FORCE - Dancing Links")
break
else:
print(self)
raise SudokuTooDifficultError("This Sudoku requires more advanced methods!")
if verbose:
print("Sudoku solved in {0} iterations!\n{1}".format(len(self.solution_steps), self))
for step in self.solution_steps:
print(step)
- |-
def get_peer_ips(self):
presponse = [ord(i) for i in self.tracker_response[]]
while presponse:
peer_ip = ((.join(str(x) for x in presponse[0:4]),
256 * presponse[4] + presponse[5]))
if peer_ip not in self.peer_ips:
self.peer_ips.append(peer_ip)
presponse = presponse[6:]
- source_sentence: >-
Setter method for ipv6_phy_intf_cmds, mapped from YANG variable
/interface/fortygigabitethernet/ipv6/ipv6_phy_intf_cmds (container)
If this variable is read-only (config: false) in the
source YANG file, then _set_ipv6_phy_intf_cmds is considered as a private
method. Backends looking to populate this variable should
do so via calling thisObj._set_ipv6_phy_intf_cmds() directly.
sentences:
- |-
def _trim_xpath(self, xpath, prop):
xroot = self._get_xroot_for(prop)
if xroot is None and isinstance(xpath, string_types):
xtags = xpath.split(XPATH_DELIM)
if xtags[-1] in _iso_tag_primitives:
xroot = XPATH_DELIM.join(xtags[:-1])
return xroot
- |-
def _set_ipv6_phy_intf_cmds(self, v, load=False):
if hasattr(v, "_utype"):
v = v._utype(v)
try:
t = YANGDynClass(v,base=ipv6_phy_intf_cmds.ipv6_phy_intf_cmds, is_container=, presence=False, yang_name="ipv6-phy-intf-cmds", rest_name="", parent=self, path_helper=self._path_helper, extmethods=self._extmethods, register_paths=True, extensions={u: {u: u, u: None, u: u}}, namespace=, defining_module=, yang_type=, is_config=True)
except (TypeError, ValueError):
raise ValueError({
: ,
: "container",
: ,
})
self.__ipv6_phy_intf_cmds = t
if hasattr(self, ):
self._set()
- |-
def create_snapshot(self, xml_bytes):
root = XML(xml_bytes)
snapshot_id = root.findtext("snapshotId")
volume_id = root.findtext("volumeId")
status = root.findtext("status")
start_time = root.findtext("startTime")
start_time = datetime.strptime(
start_time[:19], "%Y-%m-%dT%H:%M:%S")
progress = root.findtext("progress")[:-1]
progress = float(progress or "0") / 100.
return model.Snapshot(
snapshot_id, volume_id, status, start_time, progress)
- source_sentence: |-
Generates samples of text from the provided vocabulary.
Args:
plain_vocab: vocabulary.
distribution: distribution.
train_samples: samples for training.
length: length.
Returns:
train_indices (np.array of Integers): random integers for training.
shape = [num_samples, length]
test_indices (np.array of Integers): random integers for testing.
shape = [num_samples, length]
plain_vocab (list of Integers): unique vocabularies.
sentences:
- |-
def late_filling(target, pressure=,
Pc_star=,
Swp_star=0.2, eta=3):
r
element = pressure.split()[0]
network = target.project.network
phase = target.project.find_phase(target)
pc_star = phase[Pc_star]
Pc = phase[pressure]
Ts = network.map_throats(throats=target.Ts, origin=target)
values = values[Ts]
else:
Ps = network.map_pores(pores=target.Ps, origin=target)
values = values[Ps]
return values
- |-
def switch(self, name):
try:
switch = self.storage[self.__namespaced(name)]
except KeyError:
if not self.autocreate:
raise ValueError("No switch named registered in " % (name, self.namespace))
switch = self.__create_and_register_disabled_switch(name)
switch.manager = self
return switch
- |-
def generate_plaintext_random(plain_vocab, distribution, train_samples,
length):
if distribution is not None:
assert len(distribution) == len(plain_vocab)
train_indices = np.random.choice(
range(len(plain_vocab)), (train_samples, length), p=distribution)
return train_indices
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
- cosine_accuracy@1
- cosine_accuracy@5
- cosine_accuracy@10
- cosine_precision@1
- cosine_precision@3
- cosine_precision@5
- cosine_precision@10
- cosine_recall@1
- cosine_recall@3
- cosine_recall@5
- cosine_recall@10
- cosine_ndcg@1
- cosine_ndcg@5
- cosine_ndcg@10
- cosine_mrr@1
- cosine_mrr@5
- cosine_mrr@10
- cosine_map@100
model-index:
- name: SentenceTransformer based on Qwen/Qwen3-Embedding-0.6B
results:
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: Unknown
type: unknown
metrics:
- type: cosine_accuracy@1
value: 0.99
name: Cosine Accuracy@1
- type: cosine_accuracy@5
value: 1
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 1
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.99
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.3333333333333334
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.19999999999999996
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.09999999999999998
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.99
name: Cosine Recall@1
- type: cosine_recall@3
value: 1
name: Cosine Recall@3
- type: cosine_recall@5
value: 1
name: Cosine Recall@5
- type: cosine_recall@10
value: 1
name: Cosine Recall@10
- type: cosine_ndcg@1
value: 0.99
name: Cosine Ndcg@1
- type: cosine_ndcg@5
value: 0.9963092975357145
name: Cosine Ndcg@5
- type: cosine_ndcg@10
value: 0.9963092975357145
name: Cosine Ndcg@10
- type: cosine_mrr@1
value: 0.99
name: Cosine Mrr@1
- type: cosine_mrr@5
value: 0.995
name: Cosine Mrr@5
- type: cosine_mrr@10
value: 0.995
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.995
name: Cosine Map@100
SentenceTransformer based on Qwen/Qwen3-Embedding-0.6B
This is a sentence-transformers model finetuned from Qwen/Qwen3-Embedding-0.6B. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
Model Details
Model Description
- Model Type: Sentence Transformer
- Base model: Qwen/Qwen3-Embedding-0.6B
- Maximum Sequence Length: 32768 tokens
- Output Dimensionality: 1024 dimensions
- Similarity Function: Cosine Similarity
Model Sources
- Documentation: Sentence Transformers Documentation
- Repository: Sentence Transformers on GitHub
- Hugging Face: Sentence Transformers on Hugging Face
Full Model Architecture
SentenceTransformer(
(0): Transformer({'max_seq_length': 32768, 'do_lower_case': False, 'architecture': 'Qwen3Model'})
(1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': True, 'include_prompt': True})
(2): Normalize()
)
Usage
Direct Usage (Sentence Transformers)
First install the Sentence Transformers library:
pip install -U sentence-transformers
Then you can load this model and run inference.
from sentence_transformers import SentenceTransformer
# Download from the 🤗 Hub
model = SentenceTransformer("JacobLinCool/Qwen3-Embedding-0.6B-GIR-1")
# Run inference
queries = [
"Generates samples of text from the provided vocabulary.\n\n Args:\n plain_vocab: vocabulary.\n distribution: distribution.\n train_samples: samples for training.\n length: length.\n\n Returns:\n train_indices (np.array of Integers): random integers for training.\n shape = [num_samples, length]\n test_indices (np.array of Integers): random integers for testing.\n shape = [num_samples, length]\n plain_vocab (list of Integers): unique vocabularies.",
]
documents = [
'def generate_plaintext_random(plain_vocab, distribution, train_samples,\n length):\n \n if distribution is not None:\n assert len(distribution) == len(plain_vocab)\n\n train_indices = np.random.choice(\n range(len(plain_vocab)), (train_samples, length), p=distribution)\n\n return train_indices',
'def switch(self, name):\n \n try:\n switch = self.storage[self.__namespaced(name)]\n except KeyError:\n if not self.autocreate:\n raise ValueError("No switch named registered in " % (name, self.namespace))\n\n switch = self.__create_and_register_disabled_switch(name)\n\n switch.manager = self\n return switch',
'def late_filling(target, pressure=,\n Pc_star=,\n Swp_star=0.2, eta=3):\n r\n element = pressure.split()[0]\n network = target.project.network\n phase = target.project.find_phase(target)\n pc_star = phase[Pc_star]\n Pc = phase[pressure]\n \n Ts = network.map_throats(throats=target.Ts, origin=target)\n values = values[Ts]\n else:\n Ps = network.map_pores(pores=target.Ps, origin=target)\n values = values[Ps]\n return values',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 1024] [3, 1024]
# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[ 0.8344, -0.0822, 0.0233]])
Evaluation
Metrics
Information Retrieval
- Evaluated with
InformationRetrievalEvaluator
| Metric | Value |
|---|---|
| cosine_accuracy@1 | 0.99 |
| cosine_accuracy@5 | 1.0 |
| cosine_accuracy@10 | 1.0 |
| cosine_precision@1 | 0.99 |
| cosine_precision@3 | 0.3333 |
| cosine_precision@5 | 0.2 |
| cosine_precision@10 | 0.1 |
| cosine_recall@1 | 0.99 |
| cosine_recall@3 | 1.0 |
| cosine_recall@5 | 1.0 |
| cosine_recall@10 | 1.0 |
| cosine_ndcg@1 | 0.99 |
| cosine_ndcg@5 | 0.9963 |
| cosine_ndcg@10 | 0.9963 |
| cosine_mrr@1 | 0.99 |
| cosine_mrr@5 | 0.995 |
| cosine_mrr@10 | 0.995 |
| cosine_map@100 | 0.995 |
Training Details
Training Dataset
Unnamed Dataset
- Size: 400 training samples
- Columns:
queryandcode - Approximate statistics based on the first 400 samples:
query code type string string details - min: 2 tokens
- mean: 67.12 tokens
- max: 3156 tokens
- min: 24 tokens
- mean: 126.98 tokens
- max: 1236 tokens
- Samples:
query code For memory actions, get a list of addresses it operates on.
:param SimAction action: The action object to work with.
:return: A list of addresses that are accessed with that action.
:rtype: listdef _get_actual_addrs(action, state):
if action.actual_addrs is None:
addr_list = {0x60000000}
else:
addr_list = set(action.actual_addrs)
return addr_listConstruct the input file of the calculation.def make_input(self, with_header=False):
s = str(self.input)
if with_header: s = str(self) + "\n" + s
return sCheck worker status routedef check_worker_status():
if not in request.args:
resp = {"status": "bad request"}
return jsonify(**resp)
else:
worker_id = request.args[]
assignment_id = request.args[]
allow_repeats = CONFIG.getboolean(, )
if allow_repeats:
try:
part = Participant.query.<br> filter(Participant.workerid == worker_id).<br> filter(Participant.assignmentid == assignment_id).one()
status = part.status
except exc.SQLAlchemyError:
status = NOT_ACCEPTED
else:
try:
matches = Participant.query.<br> filter(Participant.workerid == worker_id).all()
numrecs = len(matches)
if numrecs==0:
status = NOT_ACCEPTED
else:
status = max([record.status for record in matches])
except exc.SQLAlchemyError:
... - Loss:
MultipleNegativesRankingLosswith these parameters:{ "scale": 20.0, "similarity_fct": "cos_sim", "gather_across_devices": false }
Evaluation Dataset
Unnamed Dataset
- Size: 100 evaluation samples
- Columns:
queryandcode - Approximate statistics based on the first 100 samples:
query code type string string details - min: 5 tokens
- mean: 66.56 tokens
- max: 548 tokens
- min: 24 tokens
- mean: 142.11 tokens
- max: 901 tokens
- Samples:
query code Return the value of the android prefixed attribute in a specific tag.
This function will always try to get the attribute with a android: prefix first,
and will try to return the attribute without the prefix, if the attribute could not be found.
This is useful for some broken AndroidManifest.xml, where no android namespace is set,
but could also indicate malicious activity (i.e. wrongly repackaged files).
A warning is printed if the attribute is found without a namespace prefix.
If you require to get the exact result you need to query the tag directly:
example::
>>> from lxml.etree import Element
>>> tag = Element('bar', nsmap={'android': 'http://schemas.android.com/apk/res/android'})
>>> tag.set('{http://schemas.android.com/apk/res/android}foobar', 'barfoo')
>>> tag.set('name', 'baz')
# Assume thatais some APK object
>>> a.get_value_from_tag(tag, 'name'...def get_value_from_tag(self, tag, attribute):
value = tag.get(self._ns(attribute))
if value is None:
value = tag.get(attribute)
if value:
log.warning("Failed to get the attribute on tag with namespace. "
"But found the same attribute without namespace!".format(attribute, tag.tag))
return valueGet information about this object as a dictionary. Used by WebSocket interface to pass some
relevant information to client applications.def get_as_datadict(self):
return dict(type=self.class.name, tags=list(self.tags))Makes forecast with the estimated model
Parameters
----------
h : int (default : 5)
How many steps ahead would you like to forecast?
past_values : int (default : 20)
How many past observations to show on the forecast graph?
intervals : Boolean
Would you like to show 95% prediction intervals for the forecast?
Returns
----------
- Plot of the forecastdef plot_predict(self,h=5,past_values=20,intervals=True,**kwargs):
import matplotlib.pyplot as plt
import seaborn as sns
figsize = kwargs.get(,(10,7))
if self.latent_variables.estimated is False:
raise Exception("No latent variables estimated!")
else:
scale, shape, skewness = self._get_scale_and_shape(self.latent_variables.get_z_values(transformed=True))
previous_value = self.data[-1]
forecasted_values = np.ones(h)*self.states[-1]
date_index = self.shift_dates(h)
simulations = 10000
sim_vector = np.zeros([simulations,h])
t_params = self.transform_z()
for n in range(0,simulations):
rnd_q = np.random.normal(0,np.sqrt(self.latent_variables.get_z_values(transformed=True)[0]),h)
exp = forecasted_values.copy()
for t in range(0,h):
if t == 0:... - Loss:
MultipleNegativesRankingLosswith these parameters:{ "scale": 20.0, "similarity_fct": "cos_sim", "gather_across_devices": false }
Training Hyperparameters
Non-Default Hyperparameters
eval_strategy: epochper_device_train_batch_size: 64per_device_eval_batch_size: 64num_train_epochs: 1warmup_ratio: 0.1seed: 2025bf16: Trueload_best_model_at_end: Trueoptim: adamw_torchpush_to_hub: Truehub_model_id: JacobLinCool/Qwen3-Embedding-0.6B-GIR-1hub_private_repo: Falsegradient_checkpointing: Trueeval_on_start: Truebatch_sampler: no_duplicates
All Hyperparameters
Click to expand
overwrite_output_dir: Falsedo_predict: Falseeval_strategy: epochprediction_loss_only: Trueper_device_train_batch_size: 64per_device_eval_batch_size: 64per_gpu_train_batch_size: Noneper_gpu_eval_batch_size: Nonegradient_accumulation_steps: 1eval_accumulation_steps: Nonetorch_empty_cache_steps: Nonelearning_rate: 5e-05weight_decay: 0.0adam_beta1: 0.9adam_beta2: 0.999adam_epsilon: 1e-08max_grad_norm: 1.0num_train_epochs: 1max_steps: -1lr_scheduler_type: linearlr_scheduler_kwargs: {}warmup_ratio: 0.1warmup_steps: 0log_level: passivelog_level_replica: warninglog_on_each_node: Truelogging_nan_inf_filter: Truesave_safetensors: Truesave_on_each_node: Falsesave_only_model: Falserestore_callback_states_from_checkpoint: Falseno_cuda: Falseuse_cpu: Falseuse_mps_device: Falseseed: 2025data_seed: Nonejit_mode_eval: Falseuse_ipex: Falsebf16: Truefp16: Falsefp16_opt_level: O1half_precision_backend: autobf16_full_eval: Falsefp16_full_eval: Falsetf32: Nonelocal_rank: 0ddp_backend: Nonetpu_num_cores: Nonetpu_metrics_debug: Falsedebug: []dataloader_drop_last: Falsedataloader_num_workers: 0dataloader_prefetch_factor: Nonepast_index: -1disable_tqdm: Falseremove_unused_columns: Truelabel_names: Noneload_best_model_at_end: Trueignore_data_skip: Falsefsdp: []fsdp_min_num_params: 0fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}fsdp_transformer_layer_cls_to_wrap: Noneaccelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}parallelism_config: Nonedeepspeed: Nonelabel_smoothing_factor: 0.0optim: adamw_torchoptim_args: Noneadafactor: Falsegroup_by_length: Falselength_column_name: lengthddp_find_unused_parameters: Noneddp_bucket_cap_mb: Noneddp_broadcast_buffers: Falsedataloader_pin_memory: Truedataloader_persistent_workers: Falseskip_memory_metrics: Trueuse_legacy_prediction_loop: Falsepush_to_hub: Trueresume_from_checkpoint: Nonehub_model_id: JacobLinCool/Qwen3-Embedding-0.6B-GIR-1hub_strategy: every_savehub_private_repo: Falsehub_always_push: Falsehub_revision: Nonegradient_checkpointing: Truegradient_checkpointing_kwargs: Noneinclude_inputs_for_metrics: Falseinclude_for_metrics: []eval_do_concat_batches: Truefp16_backend: autopush_to_hub_model_id: Nonepush_to_hub_organization: Nonemp_parameters:auto_find_batch_size: Falsefull_determinism: Falsetorchdynamo: Noneray_scope: lastddp_timeout: 1800torch_compile: Falsetorch_compile_backend: Nonetorch_compile_mode: Noneinclude_tokens_per_second: Falseinclude_num_input_tokens_seen: Falseneftune_noise_alpha: Noneoptim_target_modules: Nonebatch_eval_metrics: Falseeval_on_start: Trueuse_liger_kernel: Falseliger_kernel_config: Noneeval_use_gather_object: Falseaverage_tokens_across_devices: Falseprompts: Nonebatch_sampler: no_duplicatesmulti_dataset_batch_sampler: proportionalrouter_mapping: {}learning_rate_mapping: {}
Training Logs
| Epoch | Step | Validation Loss | cosine_ndcg@10 |
|---|---|---|---|
| 0 | 0 | 0.0616 | 0.9926 |
| 1.0 | 7 | 0.0358 | 0.9963 |
| -1 | -1 | - | 0.9963 |
- The bold row denotes the saved checkpoint.
Framework Versions
- Python: 3.11.11
- Sentence Transformers: 5.1.1
- Transformers: 4.56.2
- PyTorch: 2.8.0+cu128
- Accelerate: 1.10.1
- Datasets: 4.1.1
- Tokenizers: 0.22.1
Citation
BibTeX
Sentence Transformers
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "https://arxiv.org/abs/1908.10084",
}
MultipleNegativesRankingLoss
@misc{henderson2017efficient,
title={Efficient Natural Language Response Suggestion for Smart Reply},
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},
year={2017},
eprint={1705.00652},
archivePrefix={arXiv},
primaryClass={cs.CL}
}