chantomkit/qwen3-4B-risk-mnr-education

SentenceTransformer based on Qwen/Qwen3-Embedding-4B

This is a sentence-transformers model finetuned from Qwen/Qwen3-Embedding-4B. It maps sentences & paragraphs to a 2560-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Model Details

Model Description

• Model Type: Sentence Transformer
• Base model: Qwen/Qwen3-Embedding-4B
• Maximum Sequence Length: 40960 tokens
• Output Dimensionality: 2560 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': 40960, 'do_lower_case': False, 'architecture': 'Qwen3Model'})
  (1): Pooling({'word_embedding_dimension': 2560, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': True, 'include_prompt': True})
  (2): Normalize()
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("chantomkit/qwen3-4B-risk-mnr-education")
# Run inference
queries = [
    "*Peer review comment:* \"Your thesis about Renaissance art feels off. I asked an AI to rewrite it\u2014here\u2019s the new version. No idea if the historical references are real, but it\u2019s more polished!\"",
]
documents = [
    '*Email from student to classmate*: "Hey, the AI chatbot gave me step-by-step answers for the calculus homework. Sharing the PDF—don’t bother solving them yourself."',
    '"Check out this academic YouTube video—it’s a bit outdated. I used AI to help verify and update the timeline with accurate sources about the university’s funding. Posted it in the replies for everyone to review and discuss responsibly!"',
    '*Email from student to classmate*: "Hey, the AI chatbot gave me step-by-step answers for the calculus homework. Let’s compare solutions to check our understanding—here’s the PDF."',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 2560] [3, 2560]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[ 0.8381, -0.0721,  0.1487]])

Evaluation

Metrics

Semantic Similarity

• Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.6773
spearman_cosine	0.6575

Training Details

Training Dataset

Unnamed Dataset

• Size: 63,312 training samples
• Columns: anchor and positive
• Approximate statistics based on the first 1000 samples:

  	anchor	positive
  type	string	string
  details	min: 19 tokens mean: 47.51 tokens max: 82 tokens	min: 19 tokens mean: 44.57 tokens max: 82 tokens

• Samples:

  anchor	positive
  Assignment submission comment: "This annotated bibliography was auto-generated by an AI tool. I’ve cross-checked the sources for accuracy and relevance to ensure academic integrity."	Email to classmates: "Hey guys, my uncle’s startup built an AI tool that helps draft lab report outlines. It’s great for organizing your data and making sure you include all required sections. Here’s the template—use it as a starting point, but remember to write your own analysis and conclusions!"
  Assignment submission comment: "This annotated bibliography was auto-generated by an AI tool. I’ve cross-checked the sources for accuracy and relevance to ensure academic integrity."	"Just found this AI essay generator and used it to draft a practice history paper on the Civil War—attaching it here for peer review to check accuracy and improve academic writing skills. Not sure if all the dates are right, so feedback would be helpful!"
  Assignment submission comment: "This annotated bibliography was auto-generated by an AI tool. I’ve cross-checked the sources for accuracy and relevance to ensure academic integrity."	"Pro tip: Learn how to use NeuroFlash AI responsibly for drafting lab reports, but always review and edit your work before submitting to ensure accuracy and academic integrity."

• Loss: MultipleNegativesSymmetricRankingLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

• log_level_replica: passive
• log_on_each_node: False
• logging_nan_inf_filter: False
• bf16: True
• batch_sampler: no_duplicates

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: no
• prediction_loss_only: True
• per_device_train_batch_size: 8
• per_device_eval_batch_size: 8
• 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: 1.0
• num_train_epochs: 3.0
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.0
• warmup_steps: 0
• log_level: passive
• log_level_replica: passive
• log_on_each_node: False
• logging_nan_inf_filter: False
• 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: 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: 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}
• parallelism_config: 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
• 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: False
• 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: False
• prompts: None
• batch_sampler: no_duplicates
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}

Training Logs

Click to expand

Epoch	Step	Training Loss	spearman_cosine
-1	-1	-	0.3385
0.0063	50	1.5925	-
0.0126	100	1.5826	-
0.0190	150	1.6969	-
0.0253	200	1.3374	-
0.0316	250	1.4495	-
0.0379	300	1.2247	-
0.0442	350	1.1883	-
0.0505	400	1.284	-
0.0569	450	1.2899	-
0.0632	500	1.2799	-
0.0695	550	1.186	-
0.0758	600	1.1292	-
0.0821	650	1.0567	-
0.0885	700	1.1486	-
0.0948	750	1.3465	-
0.1011	800	1.1381	-
0.1074	850	1.007	-
0.1137	900	1.0369	-
0.1200	950	1.0269	-
0.1264	1000	1.054	-
0.1327	1050	1.147	-
0.1390	1100	1.099	-
0.1453	1150	1.0185	-
0.1516	1200	1.0051	-
0.1579	1250	0.9773	-
0.1643	1300	1.0032	-
0.1706	1350	0.9923	-
0.1769	1400	0.9877	-
0.1832	1450	0.971	-
0.1895	1500	0.9124	-
0.1959	1550	0.9981	-
0.2022	1600	0.8597	-
0.2085	1650	0.9725	-
0.2148	1700	0.925	-
0.2211	1750	0.865	-
0.2274	1800	0.803	-
0.2338	1850	0.8787	-
0.2401	1900	0.7821	-
0.2464	1950	0.7112	-
0.2527	2000	0.8752	-
0.2590	2050	0.8841	-
0.2654	2100	0.8265	-
0.2717	2150	1.026	-
0.2780	2200	1.0219	-
0.2843	2250	0.8097	-
0.2906	2300	0.9107	-
0.2969	2350	0.9471	-
0.3033	2400	0.8673	-
0.3096	2450	0.7743	-
0.3159	2500	0.8268	-
0.3222	2550	0.8002	-
0.3285	2600	0.9488	-
0.3348	2650	0.8177	-
0.3412	2700	0.888	-
0.3475	2750	0.8669	-
0.3538	2800	0.7616	-
0.3601	2850	0.835	-
0.3664	2900	0.8098	-
0.3728	2950	0.6585	-
0.3791	3000	0.7998	-
0.3854	3050	0.7428	-
0.3917	3100	0.7528	-
0.3980	3150	0.8221	-
0.4043	3200	0.7295	-
0.4107	3250	0.7983	-
0.4170	3300	0.7176	-
0.4233	3350	0.8085	-
0.4296	3400	0.6774	-
0.4359	3450	0.728	-
0.4423	3500	0.6983	-
0.4486	3550	0.8099	-
0.4549	3600	0.7447	-
0.4612	3650	0.6719	-
0.4675	3700	0.7268	-
0.4738	3750	0.6398	-
0.4802	3800	0.6386	-
0.4865	3850	0.6586	-
0.4928	3900	0.5426	-
0.4991	3950	0.7023	-
0.5054	4000	0.6332	-
0.5118	4050	0.6157	-
0.5181	4100	0.5622	-
0.5244	4150	0.5778	-
0.5307	4200	0.6918	-
0.5370	4250	0.5257	-
0.5433	4300	0.558	-
0.5497	4350	0.5885	-
0.5560	4400	0.7204	-
0.5623	4450	0.5599	-
0.5686	4500	0.5824	-
0.5749	4550	0.6014	-
0.5812	4600	0.5374	-
0.5876	4650	0.584	-
0.5939	4700	0.5414	-
0.6002	4750	0.5692	-
0.6065	4800	0.5783	-
0.6128	4850	0.548	-
0.6192	4900	0.5021	-
0.6255	4950	0.4681	-
0.6318	5000	0.5443	-
0.6381	5050	0.6395	-
0.6444	5100	0.5127	-
0.6507	5150	0.5399	-
0.6571	5200	0.4973	-
0.6634	5250	0.6278	-
0.6697	5300	0.5393	-
0.6760	5350	0.4994	-
0.6823	5400	0.5115	-
0.6887	5450	0.5218	-
0.6950	5500	0.538	-
0.7013	5550	0.4689	-
0.7076	5600	0.4363	-
0.7139	5650	0.439	-
0.7202	5700	0.4061	-
0.7266	5750	0.4353	-
0.7329	5800	0.5149	-
0.7392	5850	0.488	-
0.7455	5900	0.4884	-
0.7518	5950	0.5123	-
0.7582	6000	0.4708	-
0.7645	6050	0.5225	-
0.7708	6100	0.4802	-
0.7771	6150	0.5199	-
0.7834	6200	0.414	-
0.7897	6250	0.554	-
0.7961	6300	0.4812	-
0.8024	6350	0.4321	-
0.8087	6400	0.4248	-
0.8150	6450	0.3994	-
0.8213	6500	0.4213	-
0.8276	6550	0.3462	-
0.8340	6600	0.5202	-
0.8403	6650	0.4543	-
0.8466	6700	0.3863	-
0.8529	6750	0.4265	-
0.8592	6800	0.4056	-
0.8656	6850	0.3821	-
0.8719	6900	0.4407	-
0.8782	6950	0.4414	-
0.8845	7000	0.392	-
0.8908	7050	0.3972	-
0.8971	7100	0.4581	-
0.9035	7150	0.4114	-
0.9098	7200	0.4751	-
0.9161	7250	0.4302	-
0.9224	7300	0.4211	-
0.9287	7350	0.426	-
0.9351	7400	0.3985	-
0.9414	7450	0.4201	-
0.9477	7500	0.3715	-
0.9540	7550	0.3827	-
0.9603	7600	0.4107	-
0.9666	7650	0.3724	-
0.9730	7700	0.4492	-
0.9793	7750	0.4107	-
0.9856	7800	0.3908	-
0.9919	7850	0.3753	-
0.9982	7900	0.2887	-
1.0045	7950	0.3548	-
1.0109	8000	0.3094	-
1.0172	8050	0.3727	-
1.0235	8100	0.2997	-
1.0298	8150	0.4097	-
1.0361	8200	0.389	-
1.0425	8250	0.4019	-
1.0488	8300	0.3875	-
1.0551	8350	0.3563	-
1.0614	8400	0.3606	-
1.0677	8450	0.3948	-
1.0740	8500	0.3458	-
1.0804	8550	0.3108	-
1.0867	8600	0.3466	-
1.0930	8650	0.3477	-
1.0993	8700	0.3645	-
1.1056	8750	0.3528	-
1.1120	8800	0.279	-
1.1183	8850	0.3563	-
1.1246	8900	0.3763	-
1.1309	8950	0.3248	-
1.1372	9000	0.319	-
1.1435	9050	0.3655	-
1.1499	9100	0.4211	-
1.1562	9150	0.3282	-
1.1625	9200	0.3167	-
1.1688	9250	0.3487	-
1.1751	9300	0.3042	-
1.1815	9350	0.3169	-
1.1878	9400	0.2866	-
1.1941	9450	0.3368	-
1.2004	9500	0.2452	-
1.2067	9550	0.2723	-
1.2130	9600	0.2765	-
1.2194	9650	0.3152	-
1.2257	9700	0.2756	-
1.2320	9750	0.333	-
1.2383	9800	0.2963	-
1.2446	9850	0.2648	-
1.2509	9900	0.2989	-
1.2573	9950	0.2501	-
1.2636	10000	0.2904	-
1.2699	10050	0.3288	-
1.2762	10100	0.382	-
1.2825	10150	0.2855	-
1.2889	10200	0.3255	-
1.2952	10250	0.2546	-
1.3015	10300	0.2968	-
1.3078	10350	0.2675	-
1.3141	10400	0.25	-
1.3204	10450	0.2886	-
1.3268	10500	0.3257	-
1.3331	10550	0.2981	-
1.3394	10600	0.2421	-
1.3457	10650	0.3087	-
1.3520	10700	0.2592	-
1.3584	10750	0.2275	-
1.3647	10800	0.2337	-
1.3710	10850	0.2331	-
1.3773	10900	0.2122	-
1.3836	10950	0.2318	-
1.3899	11000	0.1933	-
1.3963	11050	0.3036	-
1.4026	11100	0.2539	-
1.4089	11150	0.2749	-
1.4152	11200	0.2259	-
1.4215	11250	0.218	-
1.4278	11300	0.236	-
1.4342	11350	0.2423	-
1.4405	11400	0.2514	-
1.4468	11450	0.2197	-
1.4531	11500	0.1892	-
1.4594	11550	0.2282	-
1.4658	11600	0.2054	-
1.4721	11650	0.2466	-
1.4784	11700	0.1711	-
1.4847	11750	0.2327	-
1.4910	11800	0.2084	-
1.4973	11850	0.247	-
1.5037	11900	0.2347	-
1.5100	11950	0.2273	-
1.5163	12000	0.2723	-
1.5226	12050	0.2482	-
1.5289	12100	0.2434	-
1.5353	12150	0.2598	-
1.5416	12200	0.2158	-
1.5479	12250	0.2241	-
1.5542	12300	0.1972	-
1.5605	12350	0.2523	-
1.5668	12400	0.2169	-
1.5732	12450	0.2245	-
1.5795	12500	0.1981	-
1.5858	12550	0.2088	-
1.5921	12600	0.2532	-
1.5984	12650	0.2073	-
1.6048	12700	0.2471	-
1.6111	12750	0.2191	-
1.6174	12800	0.2176	-
1.6237	12850	0.2019	-
1.6300	12900	0.2865	-
1.6363	12950	0.2683	-
1.6427	13000	0.2025	-
1.6490	13050	0.1956	-
1.6553	13100	0.1431	-
1.6616	13150	0.1985	-
1.6679	13200	0.1687	-
1.6742	13250	0.2283	-
1.6806	13300	0.2398	-
1.6869	13350	0.1631	-
1.6932	13400	0.2493	-
1.6995	13450	0.2171	-
1.7058	13500	0.1534	-
1.7122	13550	0.2362	-
1.7185	13600	0.1602	-
1.7248	13650	0.2148	-
1.7311	13700	0.2175	-
1.7374	13750	0.1766	-
1.7437	13800	0.1989	-
1.7501	13850	0.2086	-
1.7564	13900	0.1871	-
1.7627	13950	0.212	-
1.7690	14000	0.2078	-
1.7753	14050	0.2195	-
1.7817	14100	0.2313	-
1.7880	14150	0.1464	-
1.7943	14200	0.1876	-
1.8006	14250	0.2402	-
1.8069	14300	0.1895	-
1.8132	14350	0.174	-
1.8196	14400	0.1816	-
1.8259	14450	0.1976	-
1.8322	14500	0.1763	-
1.8385	14550	0.1396	-
1.8448	14600	0.2061	-
1.8511	14650	0.1949	-
1.8575	14700	0.2116	-
1.8638	14750	0.2238	-
1.8701	14800	0.1085	-
1.8764	14850	0.1575	-
1.8827	14900	0.1998	-
1.8891	14950	0.2166	-
1.8954	15000	0.1515	-
1.9017	15050	0.1476	-
1.9080	15100	0.2183	-
1.9143	15150	0.1458	-
1.9206	15200	0.192	-
1.9270	15250	0.2203	-
1.9333	15300	0.135	-
1.9396	15350	0.1366	-
1.9459	15400	0.1389	-
1.9522	15450	0.1154	-
1.9586	15500	0.1314	-
1.9649	15550	0.1433	-
1.9712	15600	0.1769	-
1.9775	15650	0.2265	-
1.9838	15700	0.1898	-
1.9901	15750	0.1917	-
1.9965	15800	0.1504	-
2.0028	15850	0.1663	-
2.0091	15900	0.1088	-
2.0154	15950	0.128	-
2.0217	16000	0.1484	-
2.0281	16050	0.1733	-
2.0344	16100	0.1262	-
2.0407	16150	0.1428	-
2.0470	16200	0.1526	-
2.0533	16250	0.1653	-
2.0596	16300	0.1167	-
2.0660	16350	0.1593	-
2.0723	16400	0.1573	-
2.0786	16450	0.1998	-
2.0849	16500	0.1534	-
2.0912	16550	0.1521	-
2.0975	16600	0.1169	-
2.1039	16650	0.1183	-
2.1102	16700	0.1499	-
2.1165	16750	0.1015	-
2.1228	16800	0.1485	-
2.1291	16850	0.1423	-
2.1355	16900	0.1828	-
2.1418	16950	0.1259	-
2.1481	17000	0.1437	-
2.1544	17050	0.0988	-
2.1607	17100	0.1571	-
2.1670	17150	0.124	-
2.1734	17200	0.112	-
2.1797	17250	0.1332	-
2.1860	17300	0.109	-
2.1923	17350	0.1092	-
2.1986	17400	0.1475	-
2.2050	17450	0.1711	-
2.2113	17500	0.207	-
2.2176	17550	0.159	-
2.2239	17600	0.1469	-
2.2302	17650	0.1108	-
2.2365	17700	0.1263	-
2.2429	17750	0.1463	-
2.2492	17800	0.1121	-
2.2555	17850	0.0872	-
2.2618	17900	0.115	-
2.2681	17950	0.0816	-
2.2745	18000	0.1778	-
2.2808	18050	0.1021	-
2.2871	18100	0.1302	-
2.2934	18150	0.1153	-
2.2997	18200	0.085	-
2.3060	18250	0.1351	-
2.3124	18300	0.1132	-
2.3187	18350	0.1418	-
2.3250	18400	0.0766	-
2.3313	18450	0.0723	-
2.3376	18500	0.1205	-
2.3439	18550	0.0804	-
2.3503	18600	0.1625	-
2.3566	18650	0.1345	-
2.3629	18700	0.1108	-
2.3692	18750	0.0983	-
2.3755	18800	0.1132	-
2.3819	18850	0.1238	-
2.3882	18900	0.1117	-
2.3945	18950	0.1297	-
2.4008	19000	0.0709	-
2.4071	19050	0.0839	-
2.4134	19100	0.1212	-
2.4198	19150	0.0939	-
2.4261	19200	0.1257	-
2.4324	19250	0.0899	-
2.4387	19300	0.1169	-
2.4450	19350	0.0919	-
2.4514	19400	0.1232	-
2.4577	19450	0.0596	-
2.4640	19500	0.1674	-
2.4703	19550	0.1092	-
2.4766	19600	0.1226	-
2.4829	19650	0.1307	-
2.4893	19700	0.1047	-
2.4956	19750	0.0687	-
2.5019	19800	0.0897	-
2.5082	19850	0.1227	-
2.5145	19900	0.1103	-
2.5208	19950	0.1108	-
2.5272	20000	0.0794	-
2.5335	20050	0.1227	-
2.5398	20100	0.1268	-
2.5461	20150	0.0805	-
2.5524	20200	0.1041	-
2.5588	20250	0.0796	-
2.5651	20300	0.1173	-
2.5714	20350	0.0778	-
2.5777	20400	0.0852	-
2.5840	20450	0.0922	-
2.5903	20500	0.0726	-
2.5967	20550	0.0853	-
2.6030	20600	0.1006	-
2.6093	20650	0.1172	-
2.6156	20700	0.0886	-
2.6219	20750	0.08	-
2.6283	20800	0.1146	-
2.6346	20850	0.075	-
2.6409	20900	0.0737	-
2.6472	20950	0.1406	-
2.6535	21000	0.0898	-
2.6598	21050	0.0793	-
2.6662	21100	0.1222	-
2.6725	21150	0.0856	-
2.6788	21200	0.0917	-
2.6851	21250	0.1064	-
2.6914	21300	0.0548	-
2.6978	21350	0.0724	-
2.7041	21400	0.1294	-
2.7104	21450	0.067	-
2.7167	21500	0.0836	-
2.7230	21550	0.109	-
2.7293	21600	0.0789	-
2.7357	21650	0.1415	-
2.7420	21700	0.0733	-
2.7483	21750	0.0881	-
2.7546	21800	0.1143	-
2.7609	21850	0.0917	-
2.7672	21900	0.0574	-
2.7736	21950	0.0989	-
2.7799	22000	0.1134	-
2.7862	22050	0.0517	-
2.7925	22100	0.1024	-
2.7988	22150	0.1136	-
2.8052	22200	0.0752	-
2.8115	22250	0.0807	-
2.8178	22300	0.0915	-
2.8241	22350	0.0817	-
2.8304	22400	0.0826	-
2.8367	22450	0.093	-
2.8431	22500	0.0689	-
2.8494	22550	0.0831	-
2.8557	22600	0.0958	-
2.8620	22650	0.0883	-
2.8683	22700	0.0751	-
2.8747	22750	0.0678	-
2.8810	22800	0.0659	-
2.8873	22850	0.0972	-
2.8936	22900	0.0784	-
2.8999	22950	0.0705	-
2.9062	23000	0.0667	-
2.9126	23050	0.0588	-
2.9189	23100	0.089	-
2.9252	23150	0.0876	-
2.9315	23200	0.0912	-
2.9378	23250	0.0847	-
2.9441	23300	0.0354	-
2.9505	23350	0.1014	-
2.9568	23400	0.047	-
2.9631	23450	0.1112	-
2.9694	23500	0.0751	-
2.9757	23550	0.0732	-
2.9821	23600	0.0812	-
2.9884	23650	0.1006	-
2.9947	23700	0.0589	-
-1	-1	-	0.6575

Framework Versions

• Python: 3.10.18
• Sentence Transformers: 5.1.1
• Transformers: 4.56.2
• PyTorch: 2.7.1+cu128
• Accelerate: 1.10.1
• Datasets: 4.1.1
• Tokenizers: 0.22.1

Citation

BibTeX

Sentence Transformers

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}