metadata
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- dense
- generated_from_trainer
- dataset_size:799680
- loss:MultipleNegativesRankingLoss
base_model: Shuu12121/CodeModernBERT-Owl-v1
widget:
- source_sentence: |-
Disconnects the pool.
Does everything that +clear+ does, except if the pool is closed
this method does nothing but +clear+ would raise PoolClosedError.
@since 2.1.0
@api private
sentences:
- |-
def disconnect!(options = nil)
do_clear(options)
rescue Error::PoolClosedError
# The "disconnected" state is between closed and paused.
# When we are trying to disconnect the pool, permit the pool to be
# already closed.
end
- "func TestNamedTupleWithEscapedColumns(t *testing.T) {\n\tTestProtocols(t, func(t *testing.T, protocol clickhouse.Protocol) {\n\t\tconn, err := GetNativeConnection(t, protocol, nil, nil, nil)\n\t\tctx := context.Background()\n\t\trequire.NoError(t, err)\n\t\t// https://github.com/ClickHouse/ClickHouse/pull/36544\n\t\tif !CheckMinServerServerVersion(conn, 22, 5, 0) {\n\t\t\tt.Skip(fmt.Errorf(\"unsupported clickhouse version\"))\n\t\t\treturn\n\t\t}\n\t\tconst ddl = \"CREATE TABLE test_tuple (Col1 Tuple(`56` String, `a22\\\\`` Int64)) Engine MergeTree() ORDER BY tuple()\"\n\t\tdefer func() {\n\t\t\tconn.Exec(ctx, \"DROP TABLE IF EXISTS test_tuple\")\n\t\t}()\n\t\trequire.NoError(t, conn.Exec(ctx, ddl))\n\t\tbatch, err := conn.PrepareBatch(ctx, \"INSERT INTO test_tuple\")\n\t\trequire.NoError(t, err)\n\t\tvar (\n\t\t\tcol1Data = map[string]any{\"56\": \"A\", \"a22`\": int64(1)}\n\t\t)\n\t\trequire.NoError(t, batch.Append(col1Data))\n\t\trequire.Equal(t, 1, batch.Rows())\n\t\trequire.NoError(t, batch.Send())\n\t\tvar col1 map[string]any\n\t\trequire.NoError(t, conn.QueryRow(ctx, \"SELECT * FROM test_tuple\").Scan(&col1))\n\t\tassert.Equal(t, col1Data, col1)\n\t})\n}"
- |-
def parse_region(url)
parts = URI.parse(url).host.split('.')
parts.each_with_index do |part, index|
if part == 'sqs'
# assume region is the part right after the 'sqs' part
return parts[index + 1]
end
end
nil # no region found
end
- source_sentence: |-
Cancel a running workflow by sync job ID.
This will search for workflows with IDs matching the pattern sync-{sync_job_id}-*
and cancel them. The workflow will catch the CancelledError and update the
sync job status to CANCELLED.
Args:
sync_job_id: The sync job ID to cancel
Returns:
True if a workflow was found and cancelled, False otherwise
sentences:
- |-
async def cancel_sync_job_workflow(self, sync_job_id: str) -> bool:
"""
"""
try:
client = await temporal_client.get_client()
# List workflows to find the one matching our sync job
# Note: In production, you might want to store the workflow ID
# when starting it for direct lookup
workflows = []
async for workflow in client.list_workflows(
query=f'WorkflowId STARTS_WITH "sync-{sync_job_id}-"'
):
workflows.append(workflow)
if not workflows:
logger.warning(f"No running workflow found for sync job {sync_job_id}")
return False
# Cancel the workflow(s)
for workflow in workflows:
handle = client.get_workflow_handle(workflow.id)
await handle.cancel()
logger.info(
f"Successfully cancelled workflow {workflow.id} for sync job {sync_job_id}"
)
return True
except Exception as e:
logger.error(f"Failed to cancel workflow for sync job {sync_job_id}: {e}")
raise
- |-
def __init__(name, account):
"""
"""
- |-
renderRows = async (
table,
viewname,
{ columns, layout },
extra,
rows,
state
) => {
//console.log(columns);
//console.log(layout);
if (!columns || !layout) return "View not yet built";
const fields = table.getFields();
const role = extra.req.user ? extra.req.user.role_id : 100;
var views = {};
const getView = async (name, relation) => {
if (views[name]) return views[name];
const view_select = parse_view_select(name, relation);
const view = View.findOne({ name: view_select.viewname });
if (!view) return false;
if (view.table_id === table.id) view.table = table;
else view.table = Table.findOne({ id: view.table_id });
view.view_select = view_select;
views[name] = view;
return view;
};
await set_load_actions_join_fieldviews({
table,
layout,
fields,
req: extra.req,
res: extra.res,
});
const owner_field = await table.owner_fieldname();
const subviewExtra = { ...extra };
if (extra.req?.generate_email) {
// no mjml markup for for nested subviews, only for the top view
subviewExtra.req = { ...extra.req, isSubView: true };
}
return await asyncMap(rows, async (row) => {
await eachView(layout, async (segment) => {
// do all the parsing with data here? make a factory
const view = await getView(segment.view, segment.relation);
if (!view)
throw new InvalidConfiguration(
`View ${viewname} incorrectly configured: cannot find view ${segment.view}`
);
view.check_viewtemplate();
if (view.viewtemplateObj.renderRows && view.view_select.type === "Own") {
segment.contents = (
await view.viewtemplateObj.renderRows(
view.table,
view.name,
view.configuration,
subviewExtra,
[row],
state
)
)[0];
} else {
let state1 = {};
const pk_name = table.pk_name;
const get_row_val = (k) => {
//handle expanded joinfields
if (row[k] === null) return null;
if (row[k]?.id === null) return null;
return row[k]?.id || row[k];
};
const get_user_id = () => (extra.req.user ? extra.req.user.id : 0);
if (view.view_select.type === "RelationPath" && view.table_id) {
const targetTbl = Table.findOne({ id: view.table_id });
const relation = new Relation(
segment.relation,
targetTbl.name,
displayType(await view.get_state_fields())
);
state1 = pathToState(
relation,
relation.isFixedRelation() ? get_user_id : get_row_val
);
} else {
switch (view.view_select.type) {
case "Own":
state1 = { [pk_name]: get_row_val(pk_name) };
break;
case "Independent":
state1 = {};
break;
case "ChildList":
case "OneToOneShow":
state1 = {
[view.view_select.through
? `${view.view_select.throughTable}.${view.view_select.through}.${view.view_select.table_name}.${view.view_select.field_name}`
: view.view_select.field_name]: get_row_val(pk_name),
};
break;
case "ParentShow":
//todo set by pk name of parent tablr
state1 = {
id: get_row_val(view.view_select.field_name),
};
break;
}
}
const extra_state = segment.extra_state_fml
? eval_expression(
segment.extra_state_fml,
{
...dollarizeObject(state),
session_id: getSessionId(extra.req),
...row,
},
extra.req.user,
`Extra state formula for view ${view.name}`
)
: {};
const { id, ...outerState } = state;
//console.log(segment);
if (segment.state === "local") {
const state2 = { ...state1, ...extra_state };
const qs = stateToQueryString(state2, true);
if (
view.name === viewname &&
JSON.stringify(state) === JSON.stringify(state2)
)
throw new InvalidConfiguration(
`View ${view.name} embeds itself with same state; inifinite loop detected`
);
segment.contents = div(
{
class: "d-inline",
"data-sc-embed-viewname": view.name,
"data-sc-local-state": `/view/${view.name}${qs}`,
},
await view.run(state2, subviewExtra, view.isRemoteTable())
);
} else {
const state2 = { ...outerState, ...state1, ...extra_state };
const qs = stateToQueryString(state2, true);
if (
view.name === viewname &&
JSON.stringify(state) === JSON.stringify(state2)
)
throw new InvalidConfiguration(
`View ${view.name} embeds itself with same state; inifinite loop detected`
);
segment.contents = div(
{
class: "d-inline",
"data-sc-embed-viewname": view.name,
"data-sc-view-source": `/view/${view.name}${qs}`,
},
await view.run(state2, subviewExtra, view.isRemoteTable())
);
}
}
});
const user_id = extra.req.user ? extra.req.user.id : null;
const is_owner =
table.ownership_formula && user_id && role > table.min_role_read
? await table.is_owner(extra.req.user, row)
: owner_field && user_id && row[owner_field] === user_id;
return render(
row,
fields,
layout,
viewname,
table,
role,
extra.req,
is_owner,
state,
extra
);
});
}
- source_sentence: >-
AddFlags adds flags related to NodeLifecycleController for controller
manager to the specified FlagSet.
sentences:
- "func (o *NodeLifecycleControllerOptions) AddFlags(fs *pflag.FlagSet) {\n\tif o == nil {\n\t\treturn\n\t}\n\n\tfs.DurationVar(&o.NodeStartupGracePeriod.Duration, \"node-startup-grace-period\", o.NodeStartupGracePeriod.Duration,\n\t\t\"Amount of time which we allow starting Node to be unresponsive before marking it unhealthy.\")\n\tfs.DurationVar(&o.NodeMonitorGracePeriod.Duration, \"node-monitor-grace-period\", o.NodeMonitorGracePeriod.Duration,\n\t\t\"Amount of time which we allow running Node to be unresponsive before marking it unhealthy. \"+\n\t\t\t\"Must be N times more than kubelet's nodeStatusUpdateFrequency, \"+\n\t\t\t\"where N means number of retries allowed for kubelet to post node status. \"+\n\t\t\t\"This value should also be greater than the sum of HTTP2_PING_TIMEOUT_SECONDS and HTTP2_READ_IDLE_TIMEOUT_SECONDS\")\n\tfs.Float32Var(&o.NodeEvictionRate, \"node-eviction-rate\", 0.1, \"Number of nodes per second on which pods are deleted in case of node failure when a zone is healthy (see --unhealthy-zone-threshold for definition of healthy/unhealthy). Zone refers to entire cluster in non-multizone clusters.\")\n\tfs.Float32Var(&o.SecondaryNodeEvictionRate, \"secondary-node-eviction-rate\", 0.01, \"Number of nodes per second on which pods are deleted in case of node failure when a zone is unhealthy (see --unhealthy-zone-threshold for definition of healthy/unhealthy). Zone refers to entire cluster in non-multizone clusters. This value is implicitly overridden to 0 if the cluster size is smaller than --large-cluster-size-threshold.\")\n\tfs.Int32Var(&o.LargeClusterSizeThreshold, \"large-cluster-size-threshold\", 50, fmt.Sprintf(\"Number of nodes from which %s treats the cluster as large for the eviction logic purposes. --secondary-node-eviction-rate is implicitly overridden to 0 for clusters this size or smaller. Notice: If nodes reside in multiple zones, this threshold will be considered as zone node size threshold for each zone to determine node eviction rate independently.\", names.NodeLifecycleController))\n\tfs.Float32Var(&o.UnhealthyZoneThreshold, \"unhealthy-zone-threshold\", 0.55, \"Fraction of Nodes in a zone which needs to be not Ready (minimum 3) for zone to be treated as unhealthy. \")\n}"
- "func (v Value) IsNull() bool {\n\treturn v.Val == nil || v.Typ == querypb.Type_NULL_TYPE\n}"
- |-
public function response(array $errors)
{
if ($this->ajax() || $this->wantsJson()) {
return new JsonResponse($errors, 422);
}
return $this->redirector->to($this->getRedirectUrl())
->withInput($this->except($this->dontFlash))
->withErrors($errors, $this->errorBag);
}
- source_sentence: >-
Count of all the processing errors in this task and its subtasks.
Generated from protobuf field <code>int32 total_processing_error_count =
21;</code>
@return int
sentences:
- |-
fn add_helper(&self, msg: SignedMessage) -> Result<(), Error> {
let from = msg.from();
let cur_ts = self.cur_tipset.lock().clone();
add_helper(
self.api.as_ref(),
self.bls_sig_cache.as_ref(),
self.pending.as_ref(),
msg,
self.get_state_sequence(&from, &cur_ts)?,
)
}
- |-
public function getTotalProcessingErrorCount()
{
return $this->total_processing_error_count;
}
- "def datetime_utc_to_local(dt):\n\t\"\"\"\n\t\n\t\"\"\"\n\tdt = dt.replace(tzinfo=dateutil.tz.tzutc())\n\tdt = dt.astimezone(dateutil.tz.tzlocal())\n\treturn dt.replace(tzinfo=None)"
- source_sentence: >-
Computes the absolute value of each element retrieved from a strided input
array `x` via a callback function and assigns each result to an element in
a strided output array `y`.
@param {NonNegativeInteger} N - number of indexed elements
@param {Collection} x - input array/collection
@param {integer} strideX - `x` stride length
@param {NonNegativeInteger} offsetX - starting `x` index
@param {Collection} y - destination array/collection
@param {integer} strideY - `y` stride length
@param {NonNegativeInteger} offsetY - starting `y` index
@param {Callback} clbk - callback
@param {*} [thisArg] - callback execution context
@returns {Collection} `y`
@example
function accessor( v ) {
return v * 2.0;
}
var x = [ 1.0, -2.0, 3.0, -4.0, 5.0 ];
var y = [ 0.0, 0.0, 0.0, 0.0, 0.0 ];
absBy( x.length, x, 1, 0, y, 1, 0, accessor );
console.log( y );
// => [ 2.0, 4.0, 6.0, 8.0, 10.0 ]
sentences:
- |-
public ArrayList<Skyline> findSkyline(int start, int end) {
// Base case: only one building, return its skyline.
if (start == end) {
ArrayList<Skyline> list = new ArrayList<>();
list.add(new Skyline(building[start].left, building[start].height));
list.add(new Skyline(building[end].right, 0)); // Add the end of the building
return list;
}
int mid = (start + end) / 2;
ArrayList<Skyline> sky1 = this.findSkyline(start, mid); // Find the skyline of the left half
ArrayList<Skyline> sky2 = this.findSkyline(mid + 1, end); // Find the skyline of the right half
return this.mergeSkyline(sky1, sky2); // Merge the two skylines
}
- |-
def get_supported_systems_info
request(
:expects => 200,
:idempotent => true,
:method => 'GET',
:parser => Fog::ToHashDocument.new,
:path => 'supportedSystemsInfo'
)
end
- "function absBy( N, x, strideX, offsetX, y, strideY, offsetY, clbk, thisArg ) {\n\treturn mapBy( N, x, strideX, offsetX, y, strideY, offsetY, abs, clbk, thisArg ); // eslint-disable-line max-len\n}"
pipeline_tag: sentence-similarity
library_name: sentence-transformers
SentenceTransformer based on Shuu12121/CodeModernBERT-Owl-v1
This is a sentence-transformers model finetuned from Shuu12121/CodeModernBERT-Owl-v1. 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.
Model Details
Model Description
- Model Type: Sentence Transformer
- Base model: Shuu12121/CodeModernBERT-Owl-v1
- Maximum Sequence Length: 1024 tokens
- Output Dimensionality: 768 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': 1024, 'do_lower_case': False, 'architecture': 'ModernBertModel'})
(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})
)
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("sentence_transformers_model_id")
# Run inference
sentences = [
'Computes the absolute value of each element retrieved from a strided input array `x` via a callback function and assigns each result to an element in a strided output array `y`.\n\n@param {NonNegativeInteger} N - number of indexed elements\n@param {Collection} x - input array/collection\n@param {integer} strideX - `x` stride length\n@param {NonNegativeInteger} offsetX - starting `x` index\n@param {Collection} y - destination array/collection\n@param {integer} strideY - `y` stride length\n@param {NonNegativeInteger} offsetY - starting `y` index\n@param {Callback} clbk - callback\n@param {*} [thisArg] - callback execution context\n@returns {Collection} `y`\n\n@example\nfunction accessor( v ) {\n return v * 2.0;\n}\n\nvar x = [ 1.0, -2.0, 3.0, -4.0, 5.0 ];\nvar y = [ 0.0, 0.0, 0.0, 0.0, 0.0 ];\n\nabsBy( x.length, x, 1, 0, y, 1, 0, accessor );\n\nconsole.log( y );\n// => [ 2.0, 4.0, 6.0, 8.0, 10.0 ]',
'function absBy( N, x, strideX, offsetX, y, strideY, offsetY, clbk, thisArg ) {\n\treturn mapBy( N, x, strideX, offsetX, y, strideY, offsetY, abs, clbk, thisArg ); // eslint-disable-line max-len\n}',
'public ArrayList<Skyline> findSkyline(int start, int end) {\n // Base case: only one building, return its skyline.\n if (start == end) {\n ArrayList<Skyline> list = new ArrayList<>();\n list.add(new Skyline(building[start].left, building[start].height));\n list.add(new Skyline(building[end].right, 0)); // Add the end of the building\n return list;\n }\n\n int mid = (start + end) / 2;\n\n ArrayList<Skyline> sky1 = this.findSkyline(start, mid); // Find the skyline of the left half\n ArrayList<Skyline> sky2 = this.findSkyline(mid + 1, end); // Find the skyline of the right half\n return this.mergeSkyline(sky1, sky2); // Merge the two skylines\n }',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]
# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.8429, 0.0136],
# [0.8429, 1.0000, 0.1084],
# [0.0136, 0.1084, 1.0000]])
Training Details
Training Dataset
Unnamed Dataset
- Size: 799,680 training samples
- Columns:
sentence_0,sentence_1, andlabel - Approximate statistics based on the first 1000 samples:
sentence_0 sentence_1 label type string string float details - min: 8 tokens
- mean: 72.08 tokens
- max: 1024 tokens
- min: 13 tokens
- mean: 165.78 tokens
- max: 1024 tokens
- min: 1.0
- mean: 1.0
- max: 1.0
- Samples:
sentence_0 sentence_1 label Set the column title
@param column - column number (first column is: 0)
@param title - new column titlesetHeader = function(column, newValue) {
const obj = this;
if (obj.headers[column]) {
const oldValue = obj.headers[column].textContent;
const onchangeheaderOldValue = (obj.options.columns && obj.options.columns[column] && obj.options.columns[column].title)Elsewhere this is known as a "Weak Value Map". Whereas a std JS WeakMap
is weak on its keys, this map is weak on its values. It does not retain these
values strongly. If a given value disappears, then the entries for it
disappear from every weak-value-map that holds it as a value.
Just as a WeakMap only allows gc-able values as keys, a weak-value-map
only allows gc-able values as values.
Unlike a WeakMap, a weak-value-map unavoidably exposes the non-determinism of
gc to its clients. Thus, both the ability to create one, as well as each
created one, must be treated as dangerous capabilities that must be closely
held. A program with access to these can read side channels though gc that do
not* rely on the ability to measure duration. This is a separate, and bad,
timing-independent side channel.
This non-determinism also enables code to escape deterministic replay. In a
blockchain context, this could cause validators to differ from each other,
preventing consensus, and thus preventing ...makeFinalizingMap = (finalizer, opts) => {
const { weakValues = false } = optsCreates a function that memoizes the result offunc. Ifresolveris
provided, it determines the cache key for storing the result based on the
arguments provided to the memoized function. By default, the first argument
provided to the memoized function is used as the map cache key. Thefunc
is invoked with thethisbinding of the memoized function.
Note: The cache is exposed as thecacheproperty on the memoized
function. Its creation may be customized by replacing the_.memoize.Cache
constructor with one whose instances implement theMap
method interface ofdelete,get,has, andset.
@static
@memberOf _
@since 0.1.0
@category Function
@param {Function} func The function to have its output memoized.
@param {Function} [resolver] The function to resolve the cache key.
@returns {Function} Returns the new memoized function.
@example
var object = { 'a': 1, 'b': 2 };
var othe...function memoize(func, resolver) {
if (typeof func != 'function' - Loss:
MultipleNegativesRankingLosswith these parameters:{ "scale": 20.0, "similarity_fct": "cos_sim" }
Training Hyperparameters
Non-Default Hyperparameters
per_device_train_batch_size: 120per_device_eval_batch_size: 120fp16: Truemulti_dataset_batch_sampler: round_robin
All Hyperparameters
Click to expand
overwrite_output_dir: Falsedo_predict: Falseeval_strategy: noprediction_loss_only: Trueper_device_train_batch_size: 120per_device_eval_batch_size: 120per_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: 1num_train_epochs: 3max_steps: -1lr_scheduler_type: linearlr_scheduler_kwargs: {}warmup_ratio: 0.0warmup_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: 42data_seed: Nonejit_mode_eval: Falseuse_ipex: Falsebf16: Falsefp16: Truefp16_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: Falseignore_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}deepspeed: 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: Falseresume_from_checkpoint: Nonehub_model_id: Nonehub_strategy: every_savehub_private_repo: Nonehub_always_push: Falsehub_revision: Nonegradient_checkpointing: Falsegradient_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: Falseuse_liger_kernel: Falseliger_kernel_config: Noneeval_use_gather_object: Falseaverage_tokens_across_devices: Falseprompts: Nonebatch_sampler: batch_samplermulti_dataset_batch_sampler: round_robinrouter_mapping: {}learning_rate_mapping: {}
Training Logs
| Epoch | Step | Training Loss |
|---|---|---|
| 0.0750 | 500 | 0.2167 |
| 0.1501 | 1000 | 0.1158 |
| 0.2251 | 1500 | 0.1081 |
| 0.3001 | 2000 | 0.1079 |
| 0.3752 | 2500 | 0.0994 |
| 0.4502 | 3000 | 0.0941 |
| 0.5252 | 3500 | 0.0873 |
| 0.6002 | 4000 | 0.0967 |
| 0.6753 | 4500 | 0.0863 |
| 0.7503 | 5000 | 0.0829 |
| 0.8253 | 5500 | 0.0821 |
| 0.9004 | 6000 | 0.0821 |
| 0.9754 | 6500 | 0.0794 |
| 1.0504 | 7000 | 0.0418 |
| 1.1255 | 7500 | 0.0237 |
| 1.2005 | 8000 | 0.0233 |
| 1.2755 | 8500 | 0.0231 |
| 1.3505 | 9000 | 0.0248 |
| 1.4256 | 9500 | 0.0245 |
| 1.5006 | 10000 | 0.0237 |
| 1.5756 | 10500 | 0.025 |
| 1.6507 | 11000 | 0.0232 |
| 1.7257 | 11500 | 0.0231 |
| 1.8007 | 12000 | 0.0218 |
| 1.8758 | 12500 | 0.0233 |
| 1.9508 | 13000 | 0.0221 |
| 2.0258 | 13500 | 0.0177 |
| 2.1008 | 14000 | 0.0072 |
| 2.1759 | 14500 | 0.0066 |
| 2.2509 | 15000 | 0.0068 |
| 2.3259 | 15500 | 0.0069 |
| 2.4010 | 16000 | 0.0062 |
| 2.4760 | 16500 | 0.0068 |
| 2.5510 | 17000 | 0.0064 |
| 2.6261 | 17500 | 0.0061 |
| 2.7011 | 18000 | 0.0062 |
| 2.7761 | 18500 | 0.0058 |
| 2.8511 | 19000 | 0.0057 |
| 2.9262 | 19500 | 0.0058 |
Framework Versions
- Python: 3.10.12
- Sentence Transformers: 5.0.0
- Transformers: 4.53.1
- PyTorch: 2.7.0+cu128
- Accelerate: 1.7.0
- Datasets: 3.6.0
- Tokenizers: 0.21.2
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}
}