SentenceTransformer based on thebajajra/RexBERT-base

This is a sentence-transformers model finetuned from thebajajra/RexBERT-base on the nomic-embed-unsupervised-data 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: thebajajra/RexBERT-base
Maximum Sequence Length: 1024 tokens
Output Dimensionality: 768 dimensions
Similarity Function: Cosine Similarity
Training Dataset:
- nomic-embed-unsupervised-data
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': 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
queries = [
    "Corners are still lifting.",
]
documents = [
    'Hello, I got my ender 3 a little over a year ago and have gotten many successful prints off of my machine. \n\nI have always had a problem with the corners of my prints lifting. I originally used a glass plate. That by itself was horrible, but then I added hairspray, and that worked. The problem was that on long prints, corners still lifted.\n\nAfter doing this for around 5 months I switched to a PEI sheet.\n\nThis worked comparably as well as the glass/hairspray combo, except the corners STILL LIFT on long prints.\n\nNow I have a PEI sheet on boro glass with an EZABL attached and the corners of my prints are STILL LIFTING.\n\nI don\'t know what i could possibly be doing wrong. The bed must be level. I get beautiful first layers, which I have tried to "smudge" around during printing and I can confirm that the plastic is being layed down solidly.\n\nIf anyone could enlighten me as to what is going on I would be thrilled.\n\nI do have my first layer printing at 30% speed with 150% layer width with the print cooling fan off as well. Printing PLA at 200C tool temp, 60C bed.',
    'These are awesome quart jars. They have a beautiful color, and I use them for storing soups, nuts and homemade nut milk. I would purchase them again.',
    'Great product. I purchased this item becuase my wrists would ache after triceps day at the gym. I would never be able to straighten my wrist and this helped in fixing that issue.',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 768] [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[0.5487, 0.0457, 0.1961]])

Training Details

Training Dataset

nomic-embed-unsupervised-data

Dataset: nomic-embed-unsupervised-data at 917bae6
Size: 221,599,363 training samples
Columns: query and document
Approximate statistics based on the first 1000 samples:
query document
type string string
details
min: 6 tokens
mean: 34.17 tokens
max: 1024 tokens

min: 8 tokens
mean: 166.07 tokens
max: 1024 tokens

	query	document
type	string	string
details	min: 6 tokens mean: 34.17 tokens max: 1024 tokens	min: 8 tokens mean: 166.07 tokens max: 1024 tokens

Samples:

query	document
`Effect of steam reforming on methane-fueled chemical looping combustion with Cu-based oxygen carrier`	Abstract The reduction characteristics of Cu-based oxygen carrier with H 2 , CO and CH 4 were investigated using a fixed bed reactor, TPR and TGA. Results showed that temperatures for the complete reduction of Cu-based oxygen carrier with H 2 and CO are 300 °C and 225 °C, respectively, while the corresponding temperature with CH 4 is 650 °C. The carbon deposition from CH 4 occurred at over 550 °C. CO-chemisorption experiments were also conducted on the oxygen carrier, and it was indicated that Cu-based oxygen carrier sinter seriously at 700 °C. In order to lower the required reduction temperature of oxygen carriers, a new chemical looping combustion (CLC) process with CH 4 steam reforming has been presented in this paper. The basic feasibility of the process was illustrated using CuO–SiO 2 . The new CLC process has the potential to replace the conventional gas-fired middle- and low-pressure steam and hot water boilers.
`who appointed onesicritus as chief pilot of the fleet`	by the king to hold a conference with the Indian philosophers or Gymnosophists, the details of which have been transmitted to us from his own account of the interview. It was Onesicritus, whom Alexander first sent to summon Dandamis to his court. When later Onesicritus returned empty-handed with the reply of Dandamis, the King went to forest to visit Dandamis. When Alexander constructed his fleet on the Hydaspes, he appointed Onesicritus to the important position of pilot of the king's ship, or chief pilot of the fleet (). Onesicritus held this position not only during the descent of the Indus,
`when did the madonna of foligno go to paris`	Madonna of Foligno hence the name. In 1799 it was carried to Paris, France by Napoleon. There, in 1802, the painting was transferred from panel to canvas by Hacquin and restored by Roser of Heidelberg. A note was made by the restorer: "Rapporto dei cittadini Guijon Vincent Tannay e Berthollet sul ristauro dei quadri di Raffaello conosciuto sotto il nome di Madonna di Foligno." In 1815, after the Battle of Waterloo, it was returned to Italy, where it was placed in the room with the Transfiguration in the Pinacoteca Vaticana of the Vatican Museum in the Vatican City. The painting is a "sacra

Loss: MultipleNegativesRankingLoss with these parameters:

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

Evaluation Dataset

nomic-embed-unsupervised-data

Dataset: nomic-embed-unsupervised-data at 917bae6
Size: 1,113,579 evaluation samples
Columns: query and document
Approximate statistics based on the first 1000 samples:
query document
type string string
details
min: 5 tokens
mean: 31.98 tokens
max: 1024 tokens

min: 6 tokens
mean: 161.48 tokens
max: 1024 tokens

	query	document
type	string	string
details	min: 5 tokens mean: 31.98 tokens max: 1024 tokens	min: 6 tokens mean: 161.48 tokens max: 1024 tokens

Samples:

query	document
`Concise methods for the synthesis of chiral polyoxazolines and their application in asymmetric hydrosilylation`	Seven polyoxazoline ligands were synthesized in high yield in a one-pot reaction by heating polycarboxylic acids or their esters and chiral β-amino alcohols under reflux with concomitant removal of water or the alcohol produced in the reaction. The method is much simpler and more efficient in comparison to those methods reported in the literature.The compounds were used as chiral ligands in the rhodium-catalyzed asymmetric hydrosilylation of aromatic ketones, and the effects of the linkers and the substituents present on the oxazoline rings on the yield and enantioselectivity investigated. Compound 2 was identified as the best ligand of this family for the hydrosilylation of aromatic ketones.
`On the road to a stronger public health workforce: visual tools to address complex challenges.`	`The Public Health Workforce Taxonomy: Revisions and Recommendations for Implementation`
`140mm Jetflo fan availability?`	`I recently purchased a Nepton 280L, and would like to install an additional pair of 140mm Jetflo fans. Unfortunately they don't seem to be currently available, will they be in the future? Thank you so much! PS - I'm loving the cooling system!`

Loss: MultipleNegativesRankingLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 384
per_device_eval_batch_size: 128
learning_rate: 1e-05
num_train_epochs: 4
warmup_steps: 1000
bf16: True
dataloader_num_workers: 20
dataloader_prefetch_factor: 4
ddp_find_unused_parameters: False

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 384
per_device_eval_batch_size: 128
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: 1e-05
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1.0
num_train_epochs: 4
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.0
warmup_steps: 1000
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
bf16: True
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: True
dataloader_num_workers: 20
dataloader_prefetch_factor: 4
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}
parallelism_config: None
deepspeed: None
label_smoothing_factor: 0.0
optim: adamw_torch_fused
optim_args: None
adafactor: False
group_by_length: False
length_column_name: length
project: huggingface
trackio_space_id: trackio
ddp_find_unused_parameters: False
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
hub_revision: None
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
include_tokens_per_second: False
include_num_input_tokens_seen: no
neftune_noise_alpha: None
optim_target_modules: None
batch_eval_metrics: False
eval_on_start: False
use_liger_kernel: False
liger_kernel_config: None
eval_use_gather_object: False
average_tokens_across_devices: True
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: proportional
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Click to expand

Epoch	Step	Training Loss	Validation Loss
0.0014	100	4.5665	-
0.0028	200	2.223	-
0.0042	300	0.3767	-
0.0055	400	0.1622	-
0.0069	500	0.1154	-
0.0083	600	0.0934	-
0.0097	700	0.0797	-
0.0111	800	0.0704	-
0.0125	900	0.0625	-
0.0139	1000	0.0582	-
0.0152	1100	0.0535	-
0.0166	1200	0.0492	-
0.0180	1300	0.0463	-
0.0194	1400	0.044	-
0.0208	1500	0.0416	-
0.0222	1600	0.0395	-
0.0236	1700	0.0381	-
0.0250	1800	0.0367	-
0.0263	1900	0.0358	-
0.0277	2000	0.0345	-
0.0291	2100	0.0335	-
0.0305	2200	0.0319	-
0.0319	2300	0.0318	-
0.0333	2400	0.0304	-
0.0347	2500	0.0301	-
0.0360	2600	0.0291	-
0.0374	2700	0.0293	-
0.0388	2800	0.0281	-
0.0402	2900	0.0277	-
0.0416	3000	0.0266	-
0.0430	3100	0.0265	-
0.0444	3200	0.0261	-
0.0457	3300	0.0253	-
0.0471	3400	0.0256	-
0.0485	3500	0.0247	-
0.0499	3600	0.0239	-
0.0513	3700	0.0239	-
0.0527	3800	0.0235	-
0.0541	3900	0.0233	-
0.0555	4000	0.0229	-
0.0568	4100	0.0227	-
0.0582	4200	0.0226	-
0.0596	4300	0.0221	-
0.0610	4400	0.0219	-
0.0624	4500	0.0211	-
0.0638	4600	0.0212	-
0.0652	4700	0.021	-
0.0665	4800	0.0205	-
0.0679	4900	0.0202	-
0.0693	5000	0.0206	-
0.0707	5100	0.0199	-
0.0721	5200	0.0202	-
0.0735	5300	0.0194	-
0.0749	5400	0.0195	-
0.0762	5500	0.0189	-
0.0776	5600	0.0194	-
0.0790	5700	0.0189	-
0.0804	5800	0.0183	-
0.0818	5900	0.0184	-
0.0832	6000	0.0183	-
0.0846	6100	0.018	-
0.0859	6200	0.0178	-
0.0873	6300	0.018	-
0.0887	6400	0.0174	-
0.0901	6500	0.0175	-
0.0915	6600	0.0176	-
0.0929	6700	0.0171	-
0.0943	6800	0.0168	-
0.0957	6900	0.0174	-
0.0970	7000	0.0171	-
0.0984	7100	0.0169	-
0.0998	7200	0.0167	-
0.1012	7300	0.0165	-
0.1026	7400	0.0166	-
0.1040	7500	0.0162	-
0.1054	7600	0.0164	-
0.1067	7700	0.0159	-
0.1081	7800	0.0159	-
0.1095	7900	0.0162	-
0.1109	8000	0.0157	-
0.1123	8100	0.0157	-
0.1137	8200	0.0155	-
0.1151	8300	0.0154	-
0.1164	8400	0.0155	-
0.1178	8500	0.0154	-
0.1192	8600	0.015	-
0.1206	8700	0.0151	-
0.1220	8800	0.0149	-
0.1234	8900	0.015	-
0.1248	9000	0.0146	-
0.1262	9100	0.015	-
0.1275	9200	0.0148	-
0.1289	9300	0.0145	-
0.1303	9400	0.0146	-
0.1317	9500	0.0148	-
0.1331	9600	0.0143	-
0.1345	9700	0.0144	-
0.1359	9800	0.0142	-
0.1372	9900	0.0142	-
0.1386	10000	0.0141	-
0.1400	10100	0.0139	-
0.1414	10200	0.0141	-
0.1428	10300	0.0139	-
0.1442	10400	0.0136	-
0.1456	10500	0.0135	-
0.1469	10600	0.0135	-
0.1483	10700	0.0134	-
0.1497	10800	0.0136	-
0.1511	10900	0.0133	-
0.1525	11000	0.0135	-
0.1539	11100	0.0133	-
0.1553	11200	0.0134	-
0.1567	11300	0.0133	-
0.1580	11400	0.0134	-
0.1594	11500	0.013	-
0.1608	11600	0.0131	-
0.1622	11700	0.0129	-
0.1636	11800	0.0127	-
0.1650	11900	0.0129	-
0.1664	12000	0.0125	-
0.1677	12100	0.0129	-
0.1691	12200	0.013	-
0.1705	12300	0.013	-
0.1719	12400	0.013	-
0.1733	12500	0.0125	-
0.1747	12600	0.0125	-
0.1761	12700	0.0122	-
0.1774	12800	0.0124	-
0.1788	12900	0.0124	-
0.1802	13000	0.0121	-
0.1816	13100	0.0124	-
0.1830	13200	0.0122	-
0.1844	13300	0.0123	-
0.1858	13400	0.0121	-
0.1871	13500	0.012	-
0.1885	13600	0.0118	-
0.1899	13700	0.0119	-
0.1913	13800	0.0117	-
0.1927	13900	0.0119	-
0.1941	14000	0.0119	-
0.1955	14100	0.0117	-
0.1969	14200	0.0119	-
0.1982	14300	0.0116	-
0.1996	14400	0.0116	-
0.2	14427	-	0.0044
0.2010	14500	0.012	-
0.2024	14600	0.0116	-
0.2038	14700	0.0118	-
0.2052	14800	0.0116	-
0.2066	14900	0.0118	-
0.2079	15000	0.0118	-
0.2093	15100	0.0113	-
0.2107	15200	0.0114	-
0.2121	15300	0.0115	-
0.2135	15400	0.0116	-
0.2149	15500	0.0113	-
0.2163	15600	0.0115	-
0.2176	15700	0.0112	-
0.2190	15800	0.0112	-
0.2204	15900	0.0114	-
0.2218	16000	0.0111	-
0.2232	16100	0.0112	-
0.2246	16200	0.0111	-
0.2260	16300	0.011	-
0.2274	16400	0.011	-
0.2287	16500	0.0109	-
0.2301	16600	0.0106	-
0.2315	16700	0.011	-
0.2329	16800	0.011	-
0.2343	16900	0.0108	-
0.2357	17000	0.0106	-
0.2371	17100	0.0108	-
0.2384	17200	0.0107	-
0.2398	17300	0.0105	-
0.2412	17400	0.0107	-
0.2426	17500	0.011	-
0.2440	17600	0.0105	-
0.2454	17700	0.0107	-
0.2468	17800	0.0106	-
0.2481	17900	0.0108	-
0.2495	18000	0.0106	-
0.2509	18100	0.0105	-
0.2523	18200	0.0103	-
0.2537	18300	0.0104	-
0.2551	18400	0.0105	-
0.2565	18500	0.0103	-
0.2578	18600	0.0104	-
0.2592	18700	0.0103	-
0.2606	18800	0.0102	-
0.2620	18900	0.0101	-
0.2634	19000	0.0102	-
0.2648	19100	0.0103	-
0.2662	19200	0.01	-
0.2676	19300	0.0103	-
0.2689	19400	0.0101	-
0.2703	19500	0.0103	-
0.2717	19600	0.0101	-
0.2731	19700	0.0103	-
0.2745	19800	0.0102	-
0.2759	19900	0.0102	-
0.2773	20000	0.0103	-
0.2786	20100	0.0101	-
0.2800	20200	0.0102	-
0.2814	20300	0.0099	-
0.2828	20400	0.0099	-
0.2842	20500	0.0099	-
0.2856	20600	0.0098	-
0.2870	20700	0.0099	-
0.2883	20800	0.0097	-
0.2897	20900	0.0101	-
0.2911	21000	0.0098	-
0.2925	21100	0.0099	-
0.2939	21200	0.0099	-
0.2953	21300	0.0098	-
0.2967	21400	0.0096	-
0.2981	21500	0.0097	-
0.2994	21600	0.0097	-
0.3008	21700	0.0099	-
0.3022	21800	0.0098	-
0.3036	21900	0.0096	-
0.3050	22000	0.0097	-
0.3064	22100	0.0098	-
0.3078	22200	0.0094	-
0.3091	22300	0.0096	-
0.3105	22400	0.0095	-
0.3119	22500	0.0098	-
0.3133	22600	0.0096	-
0.3147	22700	0.0094	-
0.3161	22800	0.0095	-
0.3175	22900	0.0093	-
0.3188	23000	0.0093	-
0.3202	23100	0.0093	-
0.3216	23200	0.0094	-
0.3230	23300	0.0094	-
0.3244	23400	0.0093	-
0.3258	23500	0.0091	-
0.3272	23600	0.0093	-
0.3286	23700	0.0093	-
0.3299	23800	0.0093	-
0.3313	23900	0.0093	-
0.3327	24000	0.0093	-
0.3341	24100	0.009	-
0.3355	24200	0.0093	-
0.3369	24300	0.0089	-
0.3383	24400	0.0089	-
0.3396	24500	0.0092	-
0.3410	24600	0.009	-
0.3424	24700	0.0092	-
0.3438	24800	0.009	-
0.3452	24900	0.0091	-
0.3466	25000	0.0088	-
0.3480	25100	0.009	-
0.3493	25200	0.0089	-
0.3507	25300	0.0088	-
0.3521	25400	0.0089	-
0.3535	25500	0.0089	-
0.3549	25600	0.009	-
0.3563	25700	0.0092	-
0.3577	25800	0.0089	-
0.3590	25900	0.0089	-
0.3604	26000	0.009	-
0.3618	26100	0.0088	-
0.3632	26200	0.0088	-
0.3646	26300	0.0091	-
0.3660	26400	0.0088	-
0.3674	26500	0.0089	-
0.3688	26600	0.0087	-
0.3701	26700	0.0089	-
0.3715	26800	0.0087	-
0.3729	26900	0.0088	-
0.3743	27000	0.0086	-
0.3757	27100	0.0088	-
0.3771	27200	0.0087	-
0.3785	27300	0.0085	-
0.3798	27400	0.0085	-
0.3812	27500	0.0086	-
0.3826	27600	0.0088	-
0.3840	27700	0.0084	-
0.3854	27800	0.0086	-
0.3868	27900	0.0085	-
0.3882	28000	0.0085	-
0.3895	28100	0.0086	-
0.3909	28200	0.0085	-
0.3923	28300	0.0086	-
0.3937	28400	0.0088	-
0.3951	28500	0.0086	-
0.3965	28600	0.0085	-
0.3979	28700	0.0086	-
0.3993	28800	0.0085	-
0.4	28854	-	0.0031
0.4006	28900	0.0084	-
0.4020	29000	0.0084	-
0.4034	29100	0.0085	-
0.4048	29200	0.0083	-
0.4062	29300	0.0084	-
0.4076	29400	0.0084	-
0.4090	29500	0.0084	-
0.4103	29600	0.0082	-
0.4117	29700	0.0085	-
0.4131	29800	0.0083	-
0.4145	29900	0.0081	-
0.4159	30000	0.0084	-
0.4173	30100	0.0085	-
0.4187	30200	0.0081	-
0.4200	30300	0.0084	-
0.4214	30400	0.0084	-
0.4228	30500	0.0082	-
0.4242	30600	0.0084	-
0.4256	30700	0.0084	-
0.4270	30800	0.0082	-
0.4284	30900	0.0081	-
0.4297	31000	0.0081	-
0.4311	31100	0.0079	-
0.4325	31200	0.0082	-
0.4339	31300	0.0082	-
0.4353	31400	0.0082	-
0.4367	31500	0.0079	-
0.4381	31600	0.0079	-
0.4395	31700	0.0081	-
0.4408	31800	0.008	-
0.4422	31900	0.0081	-
0.4436	32000	0.0081	-
0.4450	32100	0.0081	-
0.4464	32200	0.0078	-
0.4478	32300	0.0079	-
0.4492	32400	0.0081	-
0.4505	32500	0.0081	-
0.4519	32600	0.0081	-
0.4533	32700	0.0079	-
0.4547	32800	0.0079	-
0.4561	32900	0.0079	-
0.4575	33000	0.0079	-
0.4589	33100	0.0079	-
0.4602	33200	0.0078	-
0.4616	33300	0.0077	-
0.4630	33400	0.008	-
0.4644	33500	0.0079	-
0.4658	33600	0.008	-
0.4672	33700	0.0079	-
0.4686	33800	0.0078	-
0.4700	33900	0.008	-
0.4713	34000	0.0077	-
0.4727	34100	0.0077	-
0.4741	34200	0.0078	-
0.4755	34300	0.0076	-
0.4769	34400	0.0078	-
0.4783	34500	0.0078	-
0.4797	34600	0.0078	-
0.4810	34700	0.0079	-
0.4824	34800	0.0078	-
0.4838	34900	0.0077	-
0.4852	35000	0.0075	-
0.4866	35100	0.0076	-
0.4880	35200	0.0078	-
0.4894	35300	0.0076	-
0.4907	35400	0.0078	-
0.4921	35500	0.0077	-
0.4935	35600	0.0076	-
0.4949	35700	0.0076	-
0.4963	35800	0.0077	-
0.4977	35900	0.0076	-
0.4991	36000	0.0077	-
0.5005	36100	0.0077	-
0.5018	36200	0.0077	-
0.5032	36300	0.0077	-
0.5046	36400	0.0076	-
0.5060	36500	0.0076	-
0.5074	36600	0.0077	-
0.5088	36700	0.0076	-
0.5102	36800	0.0075	-
0.5115	36900	0.0077	-
0.5129	37000	0.0076	-
0.5143	37100	0.0075	-
0.5157	37200	0.0074	-
0.5171	37300	0.0074	-
0.5185	37400	0.0075	-
0.5199	37500	0.0075	-
0.5212	37600	0.0074	-
0.5226	37700	0.0074	-
0.5240	37800	0.0072	-
0.5254	37900	0.0076	-
0.5268	38000	0.0075	-
0.5282	38100	0.0072	-
0.5296	38200	0.0074	-
0.5309	38300	0.0073	-
0.5323	38400	0.0073	-
0.5337	38500	0.0074	-
0.5351	38600	0.0073	-
0.5365	38700	0.0073	-
0.5379	38800	0.0074	-
0.5393	38900	0.0072	-
0.5407	39000	0.0076	-
0.5420	39100	0.0072	-
0.5434	39200	0.0073	-
0.5448	39300	0.0071	-
0.5462	39400	0.0072	-
0.5476	39500	0.0073	-
0.5490	39600	0.0074	-
0.5504	39700	0.0072	-
0.5517	39800	0.0072	-
0.5531	39900	0.0073	-
0.5545	40000	0.0071	-
0.5559	40100	0.0072	-
0.5573	40200	0.0072	-
0.5587	40300	0.0071	-
0.5601	40400	0.0072	-
0.5614	40500	0.0071	-
0.5628	40600	0.0073	-
0.5642	40700	0.0073	-
0.5656	40800	0.0072	-
0.5670	40900	0.0071	-
0.5684	41000	0.0073	-
0.5698	41100	0.0072	-
0.5712	41200	0.0071	-
0.5725	41300	0.0074	-
0.5739	41400	0.0072	-
0.5753	41500	0.0071	-
0.5767	41600	0.0071	-
0.5781	41700	0.007	-
0.5795	41800	0.0071	-
0.5809	41900	0.0071	-
0.5822	42000	0.0073	-
0.5836	42100	0.0071	-
0.5850	42200	0.0069	-
0.5864	42300	0.0071	-
0.5878	42400	0.0072	-
0.5892	42500	0.0073	-
0.5906	42600	0.0071	-
0.5919	42700	0.0071	-
0.5933	42800	0.0072	-
0.5947	42900	0.0071	-
0.5961	43000	0.0072	-
0.5975	43100	0.007	-
0.5989	43200	0.0072	-
0.6	43281	-	0.0026
0.6003	43300	0.0071	-
0.6016	43400	0.0069	-
0.6030	43500	0.007	-
0.6044	43600	0.0069	-
0.6058	43700	0.007	-
0.6072	43800	0.0068	-
0.6086	43900	0.0071	-
0.6100	44000	0.0069	-
0.6114	44100	0.0069	-
0.6127	44200	0.0069	-
0.6141	44300	0.0071	-
0.6155	44400	0.0071	-
0.6169	44500	0.007	-
0.6183	44600	0.0069	-
0.6197	44700	0.0069	-
0.6211	44800	0.007	-
0.6224	44900	0.0068	-
0.6238	45000	0.0069	-
0.6252	45100	0.0069	-
0.6266	45200	0.0069	-
0.6280	45300	0.0068	-
0.6294	45400	0.0069	-
0.6308	45500	0.007	-
0.6321	45600	0.0068	-
0.6335	45700	0.0068	-
0.6349	45800	0.0068	-
0.6363	45900	0.0069	-
0.6377	46000	0.007	-
0.6391	46100	0.0067	-
0.6405	46200	0.0066	-
0.6419	46300	0.0069	-
0.6432	46400	0.0068	-
0.6446	46500	0.007	-
0.6460	46600	0.0069	-
0.6474	46700	0.0069	-
0.6488	46800	0.0068	-
0.6502	46900	0.007	-
0.6516	47000	0.0069	-
0.6529	47100	0.0067	-
0.6543	47200	0.0068	-
0.6557	47300	0.0065	-
0.6571	47400	0.0067	-
0.6585	47500	0.007	-
0.6599	47600	0.0067	-
0.6613	47700	0.0067	-
0.6626	47800	0.0068	-
0.6640	47900	0.0067	-
0.6654	48000	0.0066	-
0.6668	48100	0.0069	-
0.6682	48200	0.0067	-
0.6696	48300	0.0067	-
0.6710	48400	0.0067	-
0.6724	48500	0.0069	-
0.6737	48600	0.0066	-
0.6751	48700	0.0066	-
0.6765	48800	0.0068	-
0.6779	48900	0.0067	-
0.6793	49000	0.0067	-
0.6807	49100	0.0068	-
0.6821	49200	0.0066	-
0.6834	49300	0.0067	-
0.6848	49400	0.0065	-
0.6862	49500	0.0067	-
0.6876	49600	0.0066	-
0.6890	49700	0.0065	-
0.6904	49800	0.0067	-
0.6918	49900	0.0066	-
0.6931	50000	0.0066	-
0.6945	50100	0.0066	-
0.6959	50200	0.0065	-
0.6973	50300	0.0068	-
0.6987	50400	0.0068	-
0.7001	50500	0.0066	-
0.7015	50600	0.0067	-
0.7028	50700	0.0068	-
0.7042	50800	0.0066	-
0.7056	50900	0.0065	-
0.7070	51000	0.0065	-
0.7084	51100	0.0065	-
0.7098	51200	0.0066	-
0.7112	51300	0.0065	-
0.7126	51400	0.0064	-
0.7139	51500	0.0063	-
0.7153	51600	0.0064	-
0.7167	51700	0.0063	-
0.7181	51800	0.0064	-
0.7195	51900	0.0065	-
0.7209	52000	0.0065	-
0.7223	52100	0.0065	-
0.7236	52200	0.0065	-
0.7250	52300	0.0065	-
0.7264	52400	0.0065	-
0.7278	52500	0.0065	-
0.7292	52600	0.0064	-
0.7306	52700	0.0065	-
0.7320	52800	0.0064	-
0.7333	52900	0.0064	-
0.7347	53000	0.0065	-
0.7361	53100	0.0063	-
0.7375	53200	0.0063	-
0.7389	53300	0.0064	-
0.7403	53400	0.0064	-
0.7417	53500	0.0064	-
0.7431	53600	0.0066	-
0.7444	53700	0.0064	-
0.7458	53800	0.0063	-
0.7472	53900	0.0064	-
0.7486	54000	0.0063	-
0.7500	54100	0.0063	-
0.7514	54200	0.0062	-
0.7528	54300	0.0064	-
0.7541	54400	0.0063	-
0.7555	54500	0.0063	-
0.7569	54600	0.0062	-
0.7583	54700	0.0063	-
0.7597	54800	0.0062	-
0.7611	54900	0.0062	-
0.7625	55000	0.0063	-
0.7638	55100	0.0065	-
0.7652	55200	0.0064	-
0.7666	55300	0.0062	-
0.7680	55400	0.0064	-
0.7694	55500	0.0063	-
0.7708	55600	0.0063	-
0.7722	55700	0.0062	-
0.7735	55800	0.0063	-
0.7749	55900	0.0062	-
0.7763	56000	0.0063	-
0.7777	56100	0.0064	-
0.7791	56200	0.0062	-
0.7805	56300	0.0065	-
0.7819	56400	0.006	-
0.7833	56500	0.0065	-
0.7846	56600	0.006	-
0.7860	56700	0.0062	-
0.7874	56800	0.0064	-
0.7888	56900	0.0061	-
0.7902	57000	0.0063	-
0.7916	57100	0.0062	-
0.7930	57200	0.0062	-
0.7943	57300	0.0062	-
0.7957	57400	0.0062	-
0.7971	57500	0.0062	-
0.7985	57600	0.0061	-
0.7999	57700	0.0061	-
0.8	57708	-	0.0022
0.8013	57800	0.0064	-
0.8027	57900	0.0062	-
0.8040	58000	0.0063	-
0.8054	58100	0.0061	-
0.8068	58200	0.0061	-
0.8082	58300	0.0063	-
0.8096	58400	0.0062	-
0.8110	58500	0.0062	-
0.8124	58600	0.0061	-
0.8138	58700	0.0062	-
0.8151	58800	0.0061	-
0.8165	58900	0.0061	-
0.8179	59000	0.0062	-
0.8193	59100	0.0062	-
0.8207	59200	0.0061	-
0.8221	59300	0.006	-
0.8235	59400	0.0061	-
0.8248	59500	0.006	-
0.8262	59600	0.006	-
0.8276	59700	0.0061	-
0.8290	59800	0.0062	-
0.8304	59900	0.0059	-
0.8318	60000	0.006	-
0.8332	60100	0.006	-
0.8345	60200	0.0061	-
0.8359	60300	0.006	-
0.8373	60400	0.0059	-
0.8387	60500	0.0061	-
0.8401	60600	0.006	-
0.8415	60700	0.0059	-
0.8429	60800	0.006	-
0.8443	60900	0.0061	-
0.8456	61000	0.0062	-
0.8470	61100	0.006	-
0.8484	61200	0.006	-
0.8498	61300	0.0059	-
0.8512	61400	0.0059	-
0.8526	61500	0.006	-
0.8540	61600	0.006	-
0.8553	61700	0.0059	-
0.8567	61800	0.006	-
0.8581	61900	0.0059	-
0.8595	62000	0.0059	-
0.8609	62100	0.0059	-
0.8623	62200	0.0059	-
0.8637	62300	0.0062	-
0.8650	62400	0.0061	-
0.8664	62500	0.0059	-
0.8678	62600	0.006	-
0.8692	62700	0.0061	-
0.8706	62800	0.0059	-
0.8720	62900	0.0061	-
0.8734	63000	0.006	-
0.8747	63100	0.0059	-
0.8761	63200	0.0059	-
0.8775	63300	0.0057	-
0.8789	63400	0.006	-
0.8803	63500	0.0058	-
0.8817	63600	0.0059	-
0.8831	63700	0.0058	-
0.8845	63800	0.0058	-
0.8858	63900	0.0059	-
0.8872	64000	0.0059	-
0.8886	64100	0.0059	-
0.8900	64200	0.0058	-
0.8914	64300	0.0058	-
0.8928	64400	0.006	-
0.8942	64500	0.0059	-
0.8955	64600	0.0059	-
0.8969	64700	0.0059	-
0.8983	64800	0.0058	-
0.8997	64900	0.0059	-
0.9011	65000	0.0059	-
0.9025	65100	0.0058	-
0.9039	65200	0.0058	-
0.9052	65300	0.0058	-
0.9066	65400	0.0059	-
0.9080	65500	0.0057	-
0.9094	65600	0.0057	-
0.9108	65700	0.0059	-
0.9122	65800	0.0059	-
0.9136	65900	0.0058	-
0.9150	66000	0.0058	-
0.9163	66100	0.0058	-
0.9177	66200	0.0057	-
0.9191	66300	0.0057	-
0.9205	66400	0.0059	-
0.9219	66500	0.0056	-
0.9233	66600	0.0058	-
0.9247	66700	0.0057	-
0.9260	66800	0.0058	-
0.9274	66900	0.0056	-
0.9288	67000	0.0057	-
0.9302	67100	0.0057	-
0.9316	67200	0.0055	-
0.9330	67300	0.0058	-
0.9344	67400	0.0058	-
0.9357	67500	0.0058	-
0.9371	67600	0.0057	-
0.9385	67700	0.0058	-
0.9399	67800	0.0056	-
0.9413	67900	0.0057	-
0.9427	68000	0.0058	-
0.9441	68100	0.0058	-
0.9454	68200	0.0057	-
0.9468	68300	0.0057	-
0.9482	68400	0.0057	-
0.9496	68500	0.0057	-
0.9510	68600	0.0057	-
0.9524	68700	0.0057	-
0.9538	68800	0.0059	-
0.9552	68900	0.0058	-
0.9565	69000	0.0058	-
0.9579	69100	0.0056	-
0.9593	69200	0.0057	-
0.9607	69300	0.0057	-
0.9621	69400	0.0057	-
0.9635	69500	0.0058	-
0.9649	69600	0.0056	-
0.9662	69700	0.0059	-
0.9676	69800	0.0055	-
0.9690	69900	0.0057	-
0.9704	70000	0.0054	-
0.9718	70100	0.0055	-
0.9732	70200	0.0055	-
0.9746	70300	0.0057	-
0.9759	70400	0.0057	-
0.9773	70500	0.0057	-
0.9787	70600	0.0056	-
0.9801	70700	0.0058	-
0.9815	70800	0.0054	-
0.9829	70900	0.0057	-
0.9843	71000	0.0056	-
0.9857	71100	0.0057	-
0.9870	71200	0.0057	-
0.9884	71300	0.0056	-
0.9898	71400	0.0057	-
0.9912	71500	0.0055	-
0.9926	71600	0.0055	-
0.9940	71700	0.0057	-
0.9954	71800	0.0057	-
0.9967	71900	0.0056	-
0.9981	72000	0.0058	-
0.9995	72100	0.0056	-
1.0	72135	-	0.0020

Framework Versions

Python: 3.11.13
Sentence Transformers: 5.1.2
Transformers: 4.57.1
PyTorch: 2.8.0+cu129
Accelerate: 1.11.0
Datasets: 4.3.0
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}
}