End of training

cda1461 verified 5 months ago

30.2 kB

language:
  - en
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - dense
  - generated_from_trainer
  - dataset_size:19963
  - loss:CachedMultipleNegativesRankingLoss
base_model: benjamintli/modernbert-cosqa
widget:
  - source_sentence: python string to microseconds
    sentences:
      - |-
        def seconds_to_hms(seconds):
            """
            Converts seconds float to 'hh:mm:ss.ssssss' format.
            """
            hours = int(seconds / 3600.0)
            minutes = int((seconds / 60.0) % 60.0)
            secs = float(seconds % 60.0)
            return "{0:02d}:{1:02d}:{2:02.6f}".format(hours, minutes, secs)
      - |-
        def align_file_position(f, size):
            """ Align the position in the file to the next block of specified size """
            align = (size - 1) - (f.tell() % size)
            f.seek(align, 1)
      - |-
        def timestamp_to_microseconds(timestamp):
            """Convert a timestamp string into a microseconds value
            :param timestamp
            :return time in microseconds
            """
            timestamp_str = datetime.datetime.strptime(timestamp, ISO_DATETIME_REGEX)
            epoch_time_secs = calendar.timegm(timestamp_str.timetuple())
            epoch_time_mus = epoch_time_secs * 1e6 + timestamp_str.microsecond
            return epoch_time_mus
  - source_sentence: python remove parenthesis around stringf
    sentences:
      - |-
        def format_screen(strng):
            """Format a string for screen printing.

            This removes some latex-type format codes."""
            # Paragraph continue
            par_re = re.compile(r'\\$',re.MULTILINE)
            strng = par_re.sub('',strng)
            return strng
      - |-
        def do_striptags(value):
            """Strip SGML/XML tags and replace adjacent whitespace by one space.
            """
            if hasattr(value, '__html__'):
                value = value.__html__()
            return Markup(unicode(value)).striptags()
      - |-
        def _replace_file(path, content):
          """Writes a file if it doesn't already exist with the same content.

          This is useful because cargo uses timestamps to decide whether to compile things."""
          if os.path.exists(path):
            with open(path, 'r') as f:
              if content == f.read():
                print("Not overwriting {} because it is unchanged".format(path), file=sys.stderr)
                return

          with open(path, 'w') as f:
            f.write(content)
  - source_sentence: python out of range float values are not json compliant
    sentences:
      - |-
        def show():
            """Show (print out) current environment variables."""
            env = get_environment()

            for key, val in sorted(env.env.items(), key=lambda item: item[0]):
                click.secho('%s = %s' % (key, val))
      - |-
        def default_number_converter(number_str):
            """
            Converts the string representation of a json number into its python object equivalent, an
            int, long, float or whatever type suits.
            """
            is_int = (number_str.startswith('-') and number_str[1:].isdigit()) or number_str.isdigit()
            # FIXME: this handles a wider range of numbers than allowed by the json standard,
            # etc.: float('nan') and float('inf'). But is this a problem?
            return int(number_str) if is_int else float(number_str)
      - |-
        def __get_float(section, name):
            """Get the forecasted float from json section."""
            try:
                return float(section[name])
            except (ValueError, TypeError, KeyError):
                return float(0)
  - source_sentence: python openclipboard access is denied win32clipboard
    sentences:
      - "def set_time(filename, mod_time):\n\t\"\"\"\n\tSet the modified time of a file\n\t\"\"\"\n\tlog.debug('Setting modified time to %s', mod_time)\n\tmtime = calendar.timegm(mod_time.utctimetuple())\n\t# utctimetuple discards microseconds, so restore it (for consistency)\n\tmtime += mod_time.microsecond / 1000000\n\tatime = os.stat(filename).st_atime\n\tos.utime(filename, (atime, mtime))"
      - |-
        def paste(cmd=paste_cmd, stdout=PIPE):
            """Returns system clipboard contents.
            """
            return Popen(cmd, stdout=stdout).communicate()[0].decode('utf-8')
      - |-
        def paste(xsel=False):
            """Returns system clipboard contents."""
            selection = "primary" if xsel else "clipboard"
            try:
                return subprocess.Popen(["xclip", "-selection", selection, "-o"], stdout=subprocess.PIPE).communicate()[0].decode("utf-8")
            except OSError as why:
                raise XclipNotFound
  - source_sentence: python strftime miliseconds fixed width
    sentences:
      - |-
        def fmt_duration(secs):
            """Format a duration in seconds."""
            return ' '.join(fmt.human_duration(secs, 0, precision=2, short=True).strip().split())
      - |-
        def check_hash_key(query_on, key):
            """Only allows == against query_on.hash_key"""
            return (
                isinstance(key, BaseCondition) and
                (key.operation == "==") and
                (key.column is query_on.hash_key)
            )
      - |-
        def seconds_to_hms(seconds):
            """
            Converts seconds float to 'hh:mm:ss.ssssss' format.
            """
            hours = int(seconds / 3600.0)
            minutes = int((seconds / 60.0) % 60.0)
            secs = float(seconds % 60.0)
            return "{0:02d}:{1:02d}:{2:02.6f}".format(hours, minutes, secs)
datasets:
  - benjamintli/cosqa-llm-filtered-hard-negatives
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - cosine_accuracy@1
  - cosine_accuracy@3
  - 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@10
  - cosine_mrr@10
  - cosine_map@100
model-index:
  - name: SentenceTransformer based on benjamintli/modernbert-cosqa
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: eval
          type: eval
        metrics:
          - type: cosine_accuracy@1
            value: 0.5520504731861199
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8598467778278504
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.9310500225326723
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.975214060387562
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.5520504731861199
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.2866155926092835
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.18621000450653444
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09752140603875618
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.5520504731861199
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.8598467778278504
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.9310500225326723
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.975214060387562
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.778855811581032
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7140104937874189
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.7154223269913967
            name: Cosine Map@100

SentenceTransformer based on benjamintli/modernbert-cosqa

This is a sentence-transformers model finetuned from benjamintli/modernbert-cosqa on the cosqa-llm-filtered-hard-negatives dataset. 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: benjamintli/modernbert-cosqa
Maximum Sequence Length: 512 tokens
Output Dimensionality: 768 dimensions
Similarity Function: Cosine Similarity
Training Dataset:
- cosqa-llm-filtered-hard-negatives
Language: en

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': 512, 'do_lower_case': False, 'architecture': 'OptimizedModule'})
  (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("modernbert-cosqa-hard-negatives")
# Run inference
sentences = [
    'python strftime miliseconds fixed width',
    'def fmt_duration(secs):\n    """Format a duration in seconds."""\n    return \' \'.join(fmt.human_duration(secs, 0, precision=2, short=True).strip().split())',
    'def seconds_to_hms(seconds):\n    """\n    Converts seconds float to \'hh:mm:ss.ssssss\' format.\n    """\n    hours = int(seconds / 3600.0)\n    minutes = int((seconds / 60.0) % 60.0)\n    secs = float(seconds % 60.0)\n    return "{0:02d}:{1:02d}:{2:02.6f}".format(hours, minutes, secs)',
]
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, 0.7076, 0.6960],
#         [0.7076, 1.0000, 0.7423],
#         [0.6960, 0.7423, 1.0000]])

Evaluation

Metrics

Information Retrieval

Dataset: eval
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.5521
cosine_accuracy@3	0.8598
cosine_accuracy@5	0.9311
cosine_accuracy@10	0.9752
cosine_precision@1	0.5521
cosine_precision@3	0.2866
cosine_precision@5	0.1862
cosine_precision@10	0.0975
cosine_recall@1	0.5521
cosine_recall@3	0.8598
cosine_recall@5	0.9311
cosine_recall@10	0.9752
cosine_ndcg@10	0.7789
cosine_mrr@10	0.714
cosine_map@100	0.7154

Training Details

Training Dataset

cosqa-llm-filtered-hard-negatives

Dataset: cosqa-llm-filtered-hard-negatives at 1585731
Size: 19,963 training samples
Columns: anchor, positive, and negative

Approximate statistics based on the first 1000 samples:

	anchor	positive	negative
type	string	string	string
details	min: 6 tokens mean: 9.57 tokens max: 22 tokens	min: 37 tokens mean: 88.3 tokens max: 512 tokens	min: 36 tokens mean: 94.31 tokens max: 512 tokens

Samples:

anchor	positive	negative
`python 2d array to dict`	`def to_dicts(recarray): """convert record array to a dictionaries""" for rec in recarray: yield dict(zip(recarray.dtype.names, rec.tolist()))`	`def multidict_to_dict(d): """ Turns a werkzeug.MultiDict or django.MultiValueDict into a dict with list values :param d: a MultiDict or MultiValueDict instance :return: a dict instance """ return dict((k, v[0] if len(v) == 1 else v) for k, v in iterlists(d))`
`how to send dns request message in python`	`def _request_modify_dns_record(self, record): """Sends Modify_DNS_Record request""" return self._request_internal("Modify_DNS_Record", domain=self.domain, record=record)`	`def request(self, method, url, body=None, headers={}): """Send a complete request to the server.""" self._send_request(method, url, body, headers)`
`how to cast string to uint8 in python`	`def b2u(string): """ bytes to unicode """ if (isinstance(string, bytes) or (PY2 and isinstance(string, str))): return string.decode('utf-8') return string`	`def to_bytes(s, encoding="utf-8"): """Convert a string to bytes.""" if isinstance(s, six.binary_type): return s if six.PY3: return bytes(s, encoding) return s.encode(encoding)`

Loss: CachedMultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim",
    "mini_batch_size": 64,
    "gather_across_devices": false,
    "directions": [
        "query_to_doc"
    ],
    "partition_mode": "joint",
    "hardness_mode": null,
    "hardness_strength": 0.0
}

Evaluation Dataset

cosqa-llm-filtered-hard-negatives

Dataset: cosqa-llm-filtered-hard-negatives at 1585731
Size: 2,219 evaluation samples
Columns: anchor, positive, and negative

Approximate statistics based on the first 1000 samples:

	anchor	positive	negative
type	string	string	string
details	min: 6 tokens mean: 9.65 tokens max: 21 tokens	min: 35 tokens mean: 88.87 tokens max: 512 tokens	min: 37 tokens mean: 94.56 tokens max: 512 tokens

Samples:

anchor	positive	negative
`way to change the string "python" to have all uppercase letters`	`def uppercase_chars(string: any) -> str: """Return all (and only) the uppercase chars in the given string.""" return ''.join([c if c.isupper() else '' for c in str(string)])`	`def to_capitalized_camel_case(snake_case_string): """ Convert a string from snake case to camel case with the first letter capitalized. For example, "some_var" would become "SomeVar". :param snake_case_string: Snake-cased string to convert to camel case. :returns: Camel-cased version of snake_case_string. """ parts = snake_case_string.split('_') return ''.join([i.title() for i in parts])`
`how to make intercept zero in python`	`def prox_zero(X, step): """Proximal operator to project onto zero """ return np.zeros(X.shape, dtype=X.dtype)`	`def _adjust_offset(self, real_wave_mfcc, algo_parameters): """ OFFSET """ self.log(u"Called _adjust_offset") self._apply_offset(offset=algo_parameters[0])`
`stop running function and passing to other variable python`	`def stop(self) -> None: """Stops the analysis as soon as possible.""" if self._stop and not self._posted_kork: self._stop() self._stop = None`	`def stop(self, dummy_signum=None, dummy_frame=None): """ Shutdown process (this method is also a signal handler) """ logging.info('Shutting down ...') self.socket.close() sys.exit(0)`

Loss: CachedMultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim",
    "mini_batch_size": 64,
    "gather_across_devices": false,
    "directions": [
        "query_to_doc"
    ],
    "partition_mode": "joint",
    "hardness_mode": null,
    "hardness_strength": 0.0
}

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 1024
num_train_epochs: 10
learning_rate: 2e-06
warmup_steps: 0.1
bf16: True
eval_strategy: epoch
per_device_eval_batch_size: 1024
push_to_hub: True
hub_model_id: modernbert-cosqa-hard-negatives
load_best_model_at_end: True
dataloader_num_workers: 4
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

per_device_train_batch_size: 1024
num_train_epochs: 10
max_steps: -1
learning_rate: 2e-06
lr_scheduler_type: linear
lr_scheduler_kwargs: None
warmup_steps: 0.1
optim: adamw_torch_fused
optim_args: None
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
optim_target_modules: None
gradient_accumulation_steps: 1
average_tokens_across_devices: True
max_grad_norm: 1.0
label_smoothing_factor: 0.0
bf16: True
fp16: False
bf16_full_eval: False
fp16_full_eval: False
tf32: None
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
use_liger_kernel: False
liger_kernel_config: None
use_cache: False
neftune_noise_alpha: None
torch_empty_cache_steps: None
auto_find_batch_size: False
log_on_each_node: True
logging_nan_inf_filter: True
include_num_input_tokens_seen: no
log_level: passive
log_level_replica: warning
disable_tqdm: False
project: huggingface
trackio_space_id: trackio
eval_strategy: epoch
per_device_eval_batch_size: 1024
prediction_loss_only: True
eval_on_start: False
eval_do_concat_batches: True
eval_use_gather_object: False
eval_accumulation_steps: None
include_for_metrics: []
batch_eval_metrics: False
save_only_model: False
save_on_each_node: False
enable_jit_checkpoint: False
push_to_hub: True
hub_private_repo: None
hub_model_id: modernbert-cosqa-hard-negatives
hub_strategy: every_save
hub_always_push: False
hub_revision: None
load_best_model_at_end: True
ignore_data_skip: False
restore_callback_states_from_checkpoint: False
full_determinism: False
seed: 42
data_seed: None
use_cpu: False
accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
parallelism_config: None
dataloader_drop_last: False
dataloader_num_workers: 4
dataloader_pin_memory: True
dataloader_persistent_workers: False
dataloader_prefetch_factor: None
remove_unused_columns: True
label_names: None
train_sampling_strategy: random
length_column_name: length
ddp_find_unused_parameters: None
ddp_bucket_cap_mb: None
ddp_broadcast_buffers: False
ddp_backend: None
ddp_timeout: 1800
fsdp: []
fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
deepspeed: None
debug: []
skip_memory_metrics: True
do_predict: False
resume_from_checkpoint: None
warmup_ratio: None
local_rank: -1
prompts: None
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss	Validation Loss	eval_cosine_ndcg@10
0.5	10	1.5380	-	-
1.0	20	1.4167	0.9702	0.7440
1.5	30	1.4515	-	-
2.0	40	1.3789	0.9269	0.7499
2.5	50	1.3920	-	-
3.0	60	1.2849	0.8898	0.7581
3.5	70	1.3585	-	-
4.0	80	1.2197	0.8572	0.7653
4.5	90	1.2825	-	-
5.0	100	1.2078	0.8350	0.7686
5.5	110	1.2496	-	-
6.0	120	1.1569	0.8104	0.7720
6.5	130	1.2119	-	-
7.0	140	1.1278	0.7952	0.7754
7.5	150	1.1812	-	-
8.0	160	1.1018	0.7835	0.7770
8.5	170	1.1696	-	-
9.0	180	1.0972	0.7788	0.7786
9.5	190	1.1655	-	-
10.0	200	1.0796	0.7755	0.7789

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.12.12
Sentence Transformers: 5.3.0
Transformers: 5.3.0
PyTorch: 2.10.0+cu128
Accelerate: 1.13.0
Datasets: 4.8.2
Tokenizers: 0.22.2

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",
}

CachedMultipleNegativesRankingLoss

@misc{gao2021scaling,
    title={Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup},
    author={Luyu Gao and Yunyi Zhang and Jiawei Han and Jamie Callan},
    year={2021},
    eprint={2101.06983},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}