Dataologist/gte_large_op

SentenceTransformer based on thenlper/gte-large

This is a sentence-transformers model finetuned from thenlper/gte-large. 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: thenlper/gte-large
• Maximum Sequence Length: 512 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': 512, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 1024, '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})
  (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("Dataologist/gte_large_op")
# Run inference
sentences = [
    '\'American Bandstand\' is a 8.71/10 rated T.V. Show, starring Dick Clark. It is about American Bandstand was an American music-performance show that aired in various versions from 1952 to 1989 and was hosted from 1956 until its final season by Dick Clark, who also served as producer. The show featured teenagers dancing to Top 40 music introduced by Clark; at least one popular musical act—over the decades, running the gamut from Jerry Lee Lewis to Run DMC—would usually appear in person to lip-sync one of their latest singles. Freddy "Boom Boom" Cannon holds the record for most appearances at 110.\n\nThe show\'s popularity helped Dick Clark become an American media mogul and inspired similar long-running music programs, such as Soul Train and Top of the Pops. Clark eventually assumed ownership of the program through his Dick Clark Productions company..',
    '\'American Bandstand\' is a 8.71/10 rated T.V. Show, starring Dick Clark. It is about American Bandstand was an American music-performance show that aired in various versions from 1952 to 1989 and was hosted from 1956 until its final season by Dick Clark, who also served as producer. The show featured teenagers dancing to Top 40 music introduced by Clark; at least one popular musical act—over the decades, running the gamut from Jerry Lee Lewis to Run DMC—would usually appear in person to lip-sync one of their latest singles. Freddy "Boom Boom" Cannon holds the record for most appearances at 110.\n\nThe show\'s popularity helped Dick Clark become an American media mogul and inspired similar long-running music programs, such as Soul Train and Top of the Pops. Clark eventually assumed ownership of the program through his Dick Clark Productions company..',
    "'White Lies' is a No Rating/10 rated T.V. Show, starring Natalie Dormer, Brendon Daniels, Daniel Schultz, Morgan Santo, Langley Kirkwood. It is about Edie Hansen, who is set in the affluent Cape Town neighborhood of Bishopscourt, is drawn into the gritty underbelly of the city, which hides beneath its gorgeous beauty and takes her back to a stormy past..",
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Training Details

Training Dataset

Unnamed Dataset

• Size: 602,010 training samples
• Columns: sentence_0 and sentence_1
• Approximate statistics based on the first 1000 samples:

  	sentence_0	sentence_1
  type	string	string
  details	min: 23 tokens mean: 95.98 tokens max: 368 tokens	min: 23 tokens mean: 95.98 tokens max: 368 tokens

• Samples:

  sentence_0	sentence_1
  'Down Stream Highway' is a No Rating/10 rated Movie, starring . It is about Narrated by Bill Slater, this short black & white educational film is about sporting and outdoor activities on the majestic Hudson River in New York State..	'Down Stream Highway' is a No Rating/10 rated Movie, starring . It is about Narrated by Bill Slater, this short black & white educational film is about sporting and outdoor activities on the majestic Hudson River in New York State..
  'La joueuse d'orgue' is a No Rating/10 rated Movie, starring Marcelle Géniat, Pierre Larquey, Jacques Varennes, Gaby Triquet, France Ellys. It is about Robert Bernier murdered his brother with the complicity of a worker. The only witness to the tragedy, Veronique was injured while rescuing her boss and remains blind. Later, cured by an operation, she denounces the criminal whose voice she recognized and who had taken over the factory..	'La joueuse d'orgue' is a No Rating/10 rated Movie, starring Marcelle Géniat, Pierre Larquey, Jacques Varennes, Gaby Triquet, France Ellys. It is about Robert Bernier murdered his brother with the complicity of a worker. The only witness to the tragedy, Veronique was injured while rescuing her boss and remains blind. Later, cured by an operation, she denounces the criminal whose voice she recognized and who had taken over the factory..
  'Disoriented' is a 8.0/10 rated Movie, starring . It is about Twenty-something West Cordova is trapped in a waking nightmare. His overbearing mother is bent on molding him into a MD. His crazy, "wannabe-a-supermodel," Japanese girlfriend craves blonde hair and round eyes. And his long lost, jock brother just returned home having traded his high tops for high heels. If young "Doctor" Cordova can pass pre-med, mend his fractured family and revive his romance, he may just discover the cure for his own unraveling identity..	'Disoriented' is a 8.0/10 rated Movie, starring . It is about Twenty-something West Cordova is trapped in a waking nightmare. His overbearing mother is bent on molding him into a MD. His crazy, "wannabe-a-supermodel," Japanese girlfriend craves blonde hair and round eyes. And his long lost, jock brother just returned home having traded his high tops for high heels. If young "Doctor" Cordova can pass pre-med, mend his fractured family and revive his romance, he may just discover the cure for his own unraveling identity..

• Loss: MultipleNegativesRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim"
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 4
• per_device_eval_batch_size: 4
• multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: no
• prediction_loss_only: True
• per_device_train_batch_size: 4
• per_device_eval_batch_size: 4
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 1
• eval_accumulation_steps: None
• torch_empty_cache_steps: None
• learning_rate: 5e-05
• weight_decay: 0.0
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• max_grad_norm: 1
• num_train_epochs: 3
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.0
• warmup_steps: 0
• log_level: passive
• log_level_replica: warning
• log_on_each_node: True
• logging_nan_inf_filter: True
• save_safetensors: True
• save_on_each_node: False
• save_only_model: False
• restore_callback_states_from_checkpoint: False
• no_cuda: False
• use_cpu: False
• use_mps_device: False
• seed: 42
• data_seed: None
• jit_mode_eval: False
• use_ipex: False
• bf16: False
• fp16: False
• fp16_opt_level: O1
• half_precision_backend: auto
• bf16_full_eval: False
• fp16_full_eval: False
• tf32: None
• local_rank: 0
• ddp_backend: None
• tpu_num_cores: None
• tpu_metrics_debug: False
• debug: []
• dataloader_drop_last: False
• dataloader_num_workers: 0
• dataloader_prefetch_factor: None
• past_index: -1
• disable_tqdm: False
• remove_unused_columns: True
• label_names: None
• load_best_model_at_end: False
• ignore_data_skip: False
• fsdp: []
• fsdp_min_num_params: 0
• fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
• fsdp_transformer_layer_cls_to_wrap: None
• accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
• deepspeed: None
• label_smoothing_factor: 0.0
• optim: adamw_torch
• optim_args: None
• adafactor: False
• group_by_length: False
• length_column_name: length
• ddp_find_unused_parameters: None
• ddp_bucket_cap_mb: None
• ddp_broadcast_buffers: False
• dataloader_pin_memory: True
• dataloader_persistent_workers: False
• skip_memory_metrics: True
• use_legacy_prediction_loop: False
• push_to_hub: False
• resume_from_checkpoint: None
• hub_model_id: None
• hub_strategy: every_save
• hub_private_repo: None
• hub_always_push: False
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• include_inputs_for_metrics: False
• include_for_metrics: []
• eval_do_concat_batches: True
• fp16_backend: auto
• push_to_hub_model_id: None
• push_to_hub_organization: None
• mp_parameters:
• auto_find_batch_size: False
• full_determinism: False
• torchdynamo: None
• ray_scope: last
• ddp_timeout: 1800
• torch_compile: False
• torch_compile_backend: None
• torch_compile_mode: None
• dispatch_batches: None
• split_batches: None
• include_tokens_per_second: False
• include_num_input_tokens_seen: False
• neftune_noise_alpha: None
• optim_target_modules: None
• batch_eval_metrics: False
• eval_on_start: False
• use_liger_kernel: False
• eval_use_gather_object: False
• average_tokens_across_devices: False
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: round_robin

Training Logs

Click to expand

Epoch	Step	Training Loss
0.0033	500	0.0483
0.0066	1000	0.0
0.0100	1500	0.0
0.0133	2000	0.0
0.0166	2500	0.0
0.0199	3000	0.0
0.0233	3500	0.0
0.0266	4000	0.0
0.0299	4500	0.0
0.0332	5000	0.0
0.0365	5500	0.0
0.0399	6000	0.0
0.0432	6500	0.0
0.0465	7000	0.0
0.0498	7500	0.0
0.0532	8000	0.0
0.0565	8500	0.0
0.0598	9000	0.0
0.0631	9500	0.0
0.0664	10000	0.0
0.0698	10500	0.0
0.0731	11000	0.0
0.0764	11500	0.0
0.0797	12000	0.0
0.0831	12500	0.0
0.0864	13000	0.0
0.0897	13500	0.0
0.0930	14000	0.0
0.0963	14500	0.0
0.0997	15000	0.0
0.1030	15500	0.0
0.1063	16000	0.0
0.1096	16500	0.0
0.1130	17000	0.0
0.1163	17500	0.0
0.1196	18000	0.0
0.1229	18500	0.0
0.1262	19000	0.0
0.1296	19500	0.0
0.1329	20000	0.0
0.1362	20500	0.0
0.1395	21000	0.0
0.1429	21500	0.0
0.1462	22000	0.0
0.1495	22500	0.0
0.1528	23000	0.0
0.1561	23500	0.0
0.1595	24000	0.0
0.1628	24500	0.0
0.1661	25000	0.0
0.1694	25500	0.0
0.1728	26000	0.0
0.1761	26500	0.0
0.1794	27000	0.0
0.1827	27500	0.0
0.1860	28000	0.0
0.1894	28500	0.0
0.1927	29000	0.0
0.1960	29500	0.0
0.1993	30000	0.0
0.2027	30500	0.0
0.2060	31000	0.0
0.2093	31500	0.0
0.2126	32000	0.0
0.2159	32500	0.0
0.2193	33000	0.0
0.2226	33500	0.0
0.2259	34000	0.0
0.2292	34500	0.0
0.2326	35000	0.0
0.2359	35500	0.0
0.2392	36000	0.0
0.2425	36500	0.0
0.2458	37000	0.0
0.2492	37500	0.0
0.2525	38000	0.0
0.2558	38500	0.0
0.2591	39000	0.0
0.2625	39500	0.0
0.2658	40000	0.0
0.2691	40500	0.0
0.2724	41000	0.0
0.2757	41500	0.0
0.2791	42000	0.0
0.2824	42500	0.0
0.2857	43000	0.0
0.2890	43500	0.0
0.2924	44000	0.0
0.2957	44500	0.0
0.2990	45000	0.0
0.3023	45500	0.0
0.3056	46000	0.0
0.3090	46500	0.0
0.3123	47000	0.0
0.3156	47500	0.0
0.3189	48000	0.0
0.3223	48500	0.0
0.3256	49000	0.0
0.3289	49500	0.0
0.3322	50000	0.0
0.3355	50500	0.0
0.3389	51000	0.0
0.3422	51500	0.0
0.3455	52000	0.0
0.3488	52500	0.0
0.3522	53000	0.0
0.3555	53500	0.0
0.3588	54000	0.0
0.3621	54500	0.0
0.3654	55000	0.0
0.3688	55500	0.0
0.3721	56000	0.0
0.3754	56500	0.0
0.3787	57000	0.0
0.3821	57500	0.0
0.3854	58000	0.0
0.3887	58500	0.0
0.3920	59000	0.0
0.3953	59500	0.0
0.3987	60000	0.0
0.4020	60500	0.0
0.4053	61000	0.0
0.4086	61500	0.0
0.4120	62000	0.0
0.4153	62500	0.0
0.4186	63000	0.0
0.4219	63500	0.0
0.4252	64000	0.0
0.4286	64500	0.0
0.4319	65000	0.0
0.4352	65500	0.0
0.4385	66000	0.0
0.4419	66500	0.0
0.4452	67000	0.0
0.4485	67500	0.0
0.4518	68000	0.0
0.4551	68500	0.0
0.4585	69000	0.0
0.4618	69500	0.0
0.4651	70000	0.0
0.4684	70500	0.0
0.4718	71000	0.0
0.4751	71500	0.0
0.4784	72000	0.0
0.4817	72500	0.0
0.4850	73000	0.0
0.4884	73500	0.0
0.4917	74000	0.0
0.4950	74500	0.0
0.4983	75000	0.0
0.5017	75500	0.0
0.5050	76000	0.0
0.5083	76500	0.0
0.5116	77000	0.0
0.5149	77500	0.0
0.5183	78000	0.0
0.5216	78500	0.0
0.5249	79000	0.0
0.5282	79500	0.0
0.5316	80000	0.0
0.5349	80500	0.0
0.5382	81000	0.0
0.5415	81500	0.0
0.5448	82000	0.0
0.5482	82500	0.0
0.5515	83000	0.0
0.5548	83500	0.0
0.5581	84000	0.0
0.5615	84500	0.0
0.5648	85000	0.0
0.5681	85500	0.0
0.5714	86000	0.0
0.5747	86500	0.0
0.5781	87000	0.0
0.5814	87500	0.0
0.5847	88000	0.0
0.5880	88500	0.0
0.5914	89000	0.0
0.5947	89500	0.0
0.5980	90000	0.0
0.6013	90500	0.0
0.6046	91000	0.0
0.6080	91500	0.0
0.6113	92000	0.0
0.6146	92500	0.0
0.6179	93000	0.0
0.6213	93500	0.0
0.6246	94000	0.0
0.6279	94500	0.0
0.6312	95000	0.0
0.6345	95500	0.0
0.6379	96000	0.0
0.6412	96500	0.0
0.6445	97000	0.0
0.6478	97500	0.0
0.6511	98000	0.0
0.6545	98500	0.0
0.6578	99000	0.0
0.6611	99500	0.0
0.6644	100000	0.0
0.6678	100500	0.0
0.6711	101000	0.0
0.6744	101500	0.0
0.6777	102000	0.0
0.6810	102500	0.0
0.6844	103000	0.0
0.6877	103500	0.0
0.6910	104000	0.0
0.6943	104500	0.0
0.6977	105000	0.0
0.7010	105500	0.0
0.7043	106000	0.0
0.7076	106500	0.0
0.7109	107000	0.0
0.7143	107500	0.0
0.7176	108000	0.0
0.7209	108500	0.0
0.7242	109000	0.0
0.7276	109500	0.0
0.7309	110000	0.0
0.7342	110500	0.0
0.7375	111000	0.0
0.7408	111500	0.0
0.7442	112000	0.0
0.7475	112500	0.0
0.7508	113000	0.0
0.7541	113500	0.0
0.7575	114000	0.0
0.7608	114500	0.0
0.7641	115000	0.0
0.7674	115500	0.0
0.7707	116000	0.0
0.7741	116500	0.0
0.7774	117000	0.0
0.7807	117500	0.0
0.7840	118000	0.0
0.7874	118500	0.0
0.7907	119000	0.0
0.7940	119500	0.0
0.7973	120000	0.0
0.8006	120500	0.0
0.8040	121000	0.0
0.8073	121500	0.0
0.8106	122000	0.0
0.8139	122500	0.0
0.8173	123000	0.0
0.8206	123500	0.0
0.8239	124000	0.0
0.8272	124500	0.0
0.8305	125000	0.0
0.8339	125500	0.0
0.8372	126000	0.0
0.8405	126500	0.0
0.8438	127000	0.0
0.8472	127500	0.0
0.8505	128000	0.0
0.8538	128500	0.0
0.8571	129000	0.0
0.8604	129500	0.0
0.8638	130000	0.0
0.8671	130500	0.0
0.8704	131000	0.0
0.8737	131500	0.0
0.8771	132000	0.0
0.8804	132500	0.0
0.8837	133000	0.0
0.8870	133500	0.0
0.8903	134000	0.0
0.8937	134500	0.0
0.8970	135000	0.0
0.9003	135500	0.0
0.9036	136000	0.0
0.9070	136500	0.0
0.9103	137000	0.0
0.9136	137500	0.0
0.9169	138000	0.0
0.9202	138500	0.0
0.9236	139000	0.0
0.9269	139500	0.0
0.9302	140000	0.0
0.9335	140500	0.0
0.9369	141000	0.0
0.9402	141500	0.0
0.9435	142000	0.0
0.9468	142500	0.0
0.9501	143000	0.0
0.9535	143500	0.0
0.9568	144000	0.0
0.9601	144500	0.0
0.9634	145000	0.0
0.9668	145500	0.0
0.9701	146000	0.0
0.9734	146500	0.0
0.9767	147000	0.0
0.9800	147500	0.0
0.9834	148000	0.0
0.9867	148500	0.0
0.9900	149000	0.0
0.9933	149500	0.0
0.9967	150000	0.0
1.0000	150500	0.0
1.0033	151000	0.0
1.0066	151500	0.0
1.0099	152000	0.0
1.0133	152500	0.0
1.0166	153000	0.0
1.0199	153500	0.0
1.0232	154000	0.0
1.0266	154500	0.0
1.0299	155000	0.0
1.0332	155500	0.0
1.0365	156000	0.0
1.0398	156500	0.0
1.0432	157000	0.0
1.0465	157500	0.0
1.0498	158000	0.0
1.0531	158500	0.0
1.0565	159000	0.0
1.0598	159500	0.0
1.0631	160000	0.0
1.0664	160500	0.0
1.0697	161000	0.0
1.0731	161500	0.0
1.0764	162000	0.0
1.0797	162500	0.0
1.0830	163000	0.0
1.0864	163500	0.0
1.0897	164000	0.0
1.0930	164500	0.0
1.0963	165000	0.0
1.0996	165500	0.0
1.1030	166000	0.0
1.1063	166500	0.0
1.1096	167000	0.0
1.1129	167500	0.0
1.1163	168000	0.0
1.1196	168500	0.0
1.1229	169000	0.0
1.1262	169500	0.0
1.1295	170000	0.0
1.1329	170500	0.0
1.1362	171000	0.0
1.1395	171500	0.0
1.1428	172000	0.0
1.1462	172500	0.0
1.1495	173000	0.0
1.1528	173500	0.0
1.1561	174000	0.0
1.1594	174500	0.0
1.1628	175000	0.0
1.1661	175500	0.0
1.1694	176000	0.0
1.1727	176500	0.0
1.1761	177000	0.0
1.1794	177500	0.0
1.1827	178000	0.0
1.1860	178500	0.0
1.1893	179000	0.0
1.1927	179500	0.0
1.1960	180000	0.0
1.1993	180500	0.0
1.2026	181000	0.0
1.2060	181500	0.0
1.2093	182000	0.0
1.2126	182500	0.0
1.2159	183000	0.0
1.2192	183500	0.0
1.2226	184000	0.0
1.2259	184500	0.0
1.2292	185000	0.0
1.2325	185500	0.0
1.2359	186000	0.0
1.2392	186500	0.0
1.2425	187000	0.0
1.2458	187500	0.0
1.2491	188000	0.0
1.2525	188500	0.0
1.2558	189000	0.0
1.2591	189500	0.0
1.2624	190000	0.0
1.2658	190500	0.0
1.2691	191000	0.0
1.2724	191500	0.0
1.2757	192000	0.0
1.2790	192500	0.0
1.2824	193000	0.0
1.2857	193500	0.0
1.2890	194000	0.0
1.2923	194500	0.0
1.2957	195000	0.0
1.2990	195500	0.0
1.3023	196000	0.0
1.3056	196500	0.0
1.3089	197000	0.0
1.3123	197500	0.0
1.3156	198000	0.0
1.3189	198500	0.0
1.3222	199000	0.0
1.3256	199500	0.0
1.3289	200000	0.0
1.3322	200500	0.0
1.3355	201000	0.0
1.3388	201500	0.0
1.3422	202000	0.0
1.3455	202500	0.0
1.3488	203000	0.0
1.3521	203500	0.0
1.3555	204000	0.0
1.3588	204500	0.0
1.3621	205000	0.0
1.3654	205500	0.0
1.3687	206000	0.0
1.3721	206500	0.0
1.3754	207000	0.0
1.3787	207500	0.0
1.3820	208000	0.0
1.3854	208500	0.0
1.3887	209000	0.0
1.3920	209500	0.0
1.3953	210000	0.0
1.3986	210500	0.0
1.4020	211000	0.0
1.4053	211500	0.0
1.4086	212000	0.0
1.4119	212500	0.0
1.4153	213000	0.0
1.4186	213500	0.0
1.4219	214000	0.0
1.4252	214500	0.0
1.4285	215000	0.0
1.4319	215500	0.0
1.4352	216000	0.0
1.4385	216500	0.0
1.4418	217000	0.0
1.4452	217500	0.0
1.4485	218000	0.0
1.4518	218500	0.0
1.4551	219000	0.0
1.4584	219500	0.0
1.4618	220000	0.0
1.4651	220500	0.0
1.4684	221000	0.0
1.4717	221500	0.0
1.4751	222000	0.0
1.4784	222500	0.0
1.4817	223000	0.0
1.4850	223500	0.0
1.4883	224000	0.0
1.4917	224500	0.0
1.4950	225000	0.0
1.4983	225500	0.0
1.5016	226000	0.0
1.5050	226500	0.0
1.5083	227000	0.0
1.5116	227500	0.0
1.5149	228000	0.0
1.5182	228500	0.0
1.5216	229000	0.0
1.5249	229500	0.0
1.5282	230000	0.0
1.5315	230500	0.0
1.5349	231000	0.0
1.5382	231500	0.0
1.5415	232000	0.0
1.5448	232500	0.0
1.5481	233000	0.0
1.5515	233500	0.0
1.5548	234000	0.0
1.5581	234500	0.0
1.5614	235000	0.0
1.5648	235500	0.0
1.5681	236000	0.0
1.5714	236500	0.0
1.5747	237000	0.0
1.5780	237500	0.0
1.5814	238000	0.0
1.5847	238500	0.0
1.5880	239000	0.0
1.5913	239500	0.0
1.5947	240000	0.0
1.5980	240500	0.0
1.6013	241000	0.0
1.6046	241500	0.0
1.6079	242000	0.0
1.6113	242500	0.0
1.6146	243000	0.0
1.6179	243500	0.0
1.6212	244000	0.0
1.6246	244500	0.0
1.6279	245000	0.0
1.6312	245500	0.0
1.6345	246000	0.0
1.6378	246500	0.0
1.6412	247000	0.0
1.6445	247500	0.0
1.6478	248000	0.0
1.6511	248500	0.0
1.6545	249000	0.0
1.6578	249500	0.0
1.6611	250000	0.0
1.6644	250500	0.0
1.6677	251000	0.0
1.6711	251500	0.0
1.6744	252000	0.0
1.6777	252500	0.0
1.6810	253000	0.0
1.6844	253500	0.0
1.6877	254000	0.0
1.6910	254500	0.0
1.6943	255000	0.0
1.6976	255500	0.0
1.7010	256000	0.0
1.7043	256500	0.0
1.7076	257000	0.0
1.7109	257500	0.0
1.7143	258000	0.0
1.7176	258500	0.0
1.7209	259000	0.0
1.7242	259500	0.0
1.7275	260000	0.0
1.7309	260500	0.0
1.7342	261000	0.0
1.7375	261500	0.0
1.7408	262000	0.0
1.7442	262500	0.0
1.7475	263000	0.0
1.7508	263500	0.0
1.7541	264000	0.0
1.7574	264500	0.0
1.7608	265000	0.0
1.7641	265500	0.0
1.7674	266000	0.0
1.7707	266500	0.0
1.7741	267000	0.0
1.7774	267500	0.0
1.7807	268000	0.0
1.7840	268500	0.0
1.7873	269000	0.0
1.7907	269500	0.0
1.7940	270000	0.0
1.7973	270500	0.0
1.8006	271000	0.0
1.8040	271500	0.0
1.8073	272000	0.0
1.8106	272500	0.0
1.8139	273000	0.0
1.8172	273500	0.0
1.8206	274000	0.0
1.8239	274500	0.0
1.8272	275000	0.0
1.8305	275500	0.0
1.8339	276000	0.0
1.8372	276500	0.0
1.8405	277000	0.0
1.8438	277500	0.0
1.8471	278000	0.0
1.8505	278500	0.0
1.8538	279000	0.0
1.8571	279500	0.0
1.8604	280000	0.0
1.8638	280500	0.0
1.8671	281000	0.0
1.8704	281500	0.0
1.8737	282000	0.0
1.8770	282500	0.0
1.8804	283000	0.0
1.8837	283500	0.0
1.8870	284000	0.0
1.8903	284500	0.0
1.8936	285000	0.0
1.8970	285500	0.0
1.9003	286000	0.0
1.9036	286500	0.0
1.9069	287000	0.0
1.9103	287500	0.0
1.9136	288000	0.0
1.9169	288500	0.0
1.9202	289000	0.0
1.9235	289500	0.0
1.9269	290000	0.0
1.9302	290500	0.0
1.9335	291000	0.0
1.9368	291500	0.0
1.9402	292000	0.0
1.9435	292500	0.0
1.9468	293000	0.0
1.9501	293500	0.0
1.9534	294000	0.0
1.9568	294500	0.0
1.9601	295000	0.0
1.9634	295500	0.0
1.9667	296000	0.0
1.9701	296500	0.0
1.9734	297000	0.0
1.9767	297500	0.0
1.9800	298000	0.0
1.9833	298500	0.0
1.9867	299000	0.0
1.9900	299500	0.0
1.9933	300000	0.0
1.9966	300500	0.0
2.0000	301000	0.0
2.0033	301500	0.0
2.0066	302000	0.0
2.0099	302500	0.0
2.0132	303000	0.0
2.0166	303500	0.0
2.0199	304000	0.0
2.0232	304500	0.0
2.0265	305000	0.0
2.0299	305500	0.0
2.0332	306000	0.0
2.0365	306500	0.0
2.0398	307000	0.0
2.0431	307500	0.0
2.0465	308000	0.0
2.0498	308500	0.0
2.0531	309000	0.0
2.0564	309500	0.0
2.0598	310000	0.0
2.0631	310500	0.0
2.0664	311000	0.0
2.0697	311500	0.0
2.0730	312000	0.0
2.0764	312500	0.0
2.0797	313000	0.0
2.0830	313500	0.0
2.0863	314000	0.0
2.0897	314500	0.0
2.0930	315000	0.0
2.0963	315500	0.0
2.0996	316000	0.0
2.1029	316500	0.0
2.1063	317000	0.0
2.1096	317500	0.0
2.1129	318000	0.0
2.1162	318500	0.0
2.1196	319000	0.0
2.1229	319500	0.0
2.1262	320000	0.0
2.1295	320500	0.0
2.1328	321000	0.0
2.1362	321500	0.0
2.1395	322000	0.0
2.1428	322500	0.0
2.1461	323000	0.0
2.1495	323500	0.0
2.1528	324000	0.0
2.1561	324500	0.0
2.1594	325000	0.0
2.1627	325500	0.0
2.1661	326000	0.0
2.1694	326500	0.0
2.1727	327000	0.0
2.1760	327500	0.0
2.1794	328000	0.0
2.1827	328500	0.0
2.1860	329000	0.0
2.1893	329500	0.0
2.1926	330000	0.0
2.1960	330500	0.0
2.1993	331000	0.0
2.2026	331500	0.0
2.2059	332000	0.0
2.2093	332500	0.0
2.2126	333000	0.0
2.2159	333500	0.0
2.2192	334000	0.0
2.2225	334500	0.0
2.2259	335000	0.0
2.2292	335500	0.0
2.2325	336000	0.0
2.2358	336500	0.0
2.2392	337000	0.0
2.2425	337500	0.0
2.2458	338000	0.0
2.2491	338500	0.0
2.2524	339000	0.0
2.2558	339500	0.0
2.2591	340000	0.0
2.2624	340500	0.0
2.2657	341000	0.0
2.2691	341500	0.0
2.2724	342000	0.0
2.2757	342500	0.0
2.2790	343000	0.0
2.2823	343500	0.0
2.2857	344000	0.0
2.2890	344500	0.0
2.2923	345000	0.0
2.2956	345500	0.0
2.2990	346000	0.0
2.3023	346500	0.0
2.3056	347000	0.0
2.3089	347500	0.0
2.3122	348000	0.0
2.3156	348500	0.0
2.3189	349000	0.0
2.3222	349500	0.0
2.3255	350000	0.0
2.3289	350500	0.0
2.3322	351000	0.0
2.3355	351500	0.0
2.3388	352000	0.0
2.3421	352500	0.0
2.3455	353000	0.0
2.3488	353500	0.0
2.3521	354000	0.0
2.3554	354500	0.0
2.3588	355000	0.0
2.3621	355500	0.0
2.3654	356000	0.0
2.3687	356500	0.0
2.3720	357000	0.0
2.3754	357500	0.0
2.3787	358000	0.0
2.3820	358500	0.0
2.3853	359000	0.0
2.3887	359500	0.0
2.3920	360000	0.0
2.3953	360500	0.0
2.3986	361000	0.0
2.4019	361500	0.0
2.4053	362000	0.0
2.4086	362500	0.0
2.4119	363000	0.0
2.4152	363500	0.0
2.4186	364000	0.0
2.4219	364500	0.0
2.4252	365000	0.0
2.4285	365500	0.0
2.4318	366000	0.0
2.4352	366500	0.0
2.4385	367000	0.0
2.4418	367500	0.0
2.4451	368000	0.0
2.4485	368500	0.0
2.4518	369000	0.0
2.4551	369500	0.0
2.4584	370000	0.0
2.4617	370500	0.0
2.4651	371000	0.0
2.4684	371500	0.0
2.4717	372000	0.0
2.4750	372500	0.0
2.4784	373000	0.0
2.4817	373500	0.0
2.4850	374000	0.0
2.4883	374500	0.0
2.4916	375000	0.0
2.4950	375500	0.0
2.4983	376000	0.0
2.5016	376500	0.0
2.5049	377000	0.0
2.5083	377500	0.0
2.5116	378000	0.0
2.5149	378500	0.0
2.5182	379000	0.0
2.5215	379500	0.0
2.5249	380000	0.0
2.5282	380500	0.0
2.5315	381000	0.0
2.5348	381500	0.0
2.5382	382000	0.0
2.5415	382500	0.0
2.5448	383000	0.0
2.5481	383500	0.0
2.5514	384000	0.0
2.5548	384500	0.0
2.5581	385000	0.0
2.5614	385500	0.0
2.5647	386000	0.0
2.5681	386500	0.0
2.5714	387000	0.0
2.5747	387500	0.0
2.5780	388000	0.0
2.5813	388500	0.0
2.5847	389000	0.0
2.5880	389500	0.0
2.5913	390000	0.0
2.5946	390500	0.0
2.5980	391000	0.0
2.6013	391500	0.0
2.6046	392000	0.0
2.6079	392500	0.0
2.6112	393000	0.0
2.6146	393500	0.0
2.6179	394000	0.0
2.6212	394500	0.0
2.6245	395000	0.0
2.6279	395500	0.0
2.6312	396000	0.0
2.6345	396500	0.0
2.6378	397000	0.0
2.6411	397500	0.0
2.6445	398000	0.0
2.6478	398500	0.0
2.6511	399000	0.0
2.6544	399500	0.0
2.6578	400000	0.0
2.6611	400500	0.0
2.6644	401000	0.0
2.6677	401500	0.0
2.6710	402000	0.0
2.6744	402500	0.0
2.6777	403000	0.0
2.6810	403500	0.0
2.6843	404000	0.0
2.6877	404500	0.0
2.6910	405000	0.0
2.6943	405500	0.0
2.6976	406000	0.0
2.7009	406500	0.0
2.7043	407000	0.0
2.7076	407500	0.0
2.7109	408000	0.0
2.7142	408500	0.0
2.7176	409000	0.0
2.7209	409500	0.0
2.7242	410000	0.0
2.7275	410500	0.0
2.7308	411000	0.0
2.7342	411500	0.0
2.7375	412000	0.0
2.7408	412500	0.0
2.7441	413000	0.0
2.7475	413500	0.0
2.7508	414000	0.0
2.7541	414500	0.0
2.7574	415000	0.0
2.7607	415500	0.0
2.7641	416000	0.0
2.7674	416500	0.0
2.7707	417000	0.0
2.7740	417500	0.0
2.7774	418000	0.0
2.7807	418500	0.0
2.7840	419000	0.0
2.7873	419500	0.0
2.7906	420000	0.0
2.7940	420500	0.0
2.7973	421000	0.0
2.8006	421500	0.0
2.8039	422000	0.0
2.8073	422500	0.0
2.8106	423000	0.0
2.8139	423500	0.0
2.8172	424000	0.0
2.8205	424500	0.0
2.8239	425000	0.0
2.8272	425500	0.0
2.8305	426000	0.0
2.8338	426500	0.0
2.8372	427000	0.0
2.8405	427500	0.0
2.8438	428000	0.0
2.8471	428500	0.0
2.8504	429000	0.0
2.8538	429500	0.0
2.8571	430000	0.0
2.8604	430500	0.0
2.8637	431000	0.0
2.8671	431500	0.0
2.8704	432000	0.0
2.8737	432500	0.0
2.8770	433000	0.0
2.8803	433500	0.0
2.8837	434000	0.0
2.8870	434500	0.0
2.8903	435000	0.0
2.8936	435500	0.0
2.8970	436000	0.0
2.9003	436500	0.0
2.9036	437000	0.0
2.9069	437500	0.0
2.9102	438000	0.0
2.9136	438500	0.0
2.9169	439000	0.0
2.9202	439500	0.0
2.9235	440000	0.0
2.9269	440500	0.0
2.9302	441000	0.0
2.9335	441500	0.0
2.9368	442000	0.0
2.9401	442500	0.0
2.9435	443000	0.0
2.9468	443500	0.0
2.9501	444000	0.0
2.9534	444500	0.0
2.9568	445000	0.0
2.9601	445500	0.0
2.9634	446000	0.0
2.9667	446500	0.0
2.9700	447000	0.0
2.9734	447500	0.0
2.9767	448000	0.0
2.9800	448500	0.0
2.9833	449000	0.0
2.9867	449500	0.0
2.9900	450000	0.0
2.9933	450500	0.0
2.9966	451000	0.0
2.9999	451500	0.0

Framework Versions

• Python: 3.11.11
• Sentence Transformers: 3.4.1
• Transformers: 4.48.3
• PyTorch: 2.5.1+cu124
• Accelerate: 1.3.0
• Datasets: 3.3.2
• Tokenizers: 0.21.0

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}
}