bansalaman18/reranker-msmarco-v1.1-ettin-encoder-150m-listnet

CrossEncoder based on jhu-clsp/ettin-encoder-150m

This is a Cross Encoder model finetuned from jhu-clsp/ettin-encoder-150m on the ms_marco dataset using the sentence-transformers library. It computes scores for pairs of texts, which can be used for text reranking and semantic search.

Model Details

Model Description

• Model Type: Cross Encoder
• Base model: jhu-clsp/ettin-encoder-150m
• Maximum Sequence Length: 7999 tokens
• Number of Output Labels: 1 label
• Training Dataset:
  • ms_marco
• Language: en

Model Sources

• Documentation: Sentence Transformers Documentation
• Documentation: Cross Encoder Documentation
• Repository: Sentence Transformers on GitHub
• Hugging Face: Cross Encoders on Hugging Face

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 CrossEncoder

# Download from the 🤗 Hub
model = CrossEncoder("bansalaman18/reranker-msmarco-v1.1-ettin-encoder-150m-listnet")
# Get scores for pairs of texts
pairs = [
    ['what is the definition of Chirality', 'Two enantiomers of a generic amino acid that is chiral. Chirality /kaɪˈraelɪtiː/ kaɪˈrælɪtiː is a property of symmetry important in several branches of. Science the word chirality is derived from The, greek (χειρ), kheir, hand a familiar chiral. object An object or a system is chiral if it is distinguishable from its mirror image; that is, it cannot be superposed onto it. Conversely, a mirror image of an achiral object, such as a sphere, cannot be distinguished from the object.'],
    ['what is the definition of Chirality', 'The symmetry of a molecule (or any other object) determines whether it is chiral. A molecule is achiral (not chiral) when an improper rotation, that is a combination of a rotation and a reflection in a plane, perpendicular to the axis of rotation, results in the same molecule. For tetrahedral molecules, the molecule is chiral if all four substituents are different. Chirality is important in context of ordered phases as well, for example the addition of a small amount of an optically active molecule to a nematic phase (a phase that has long range orientational order of molecules) transforms that phase to a chiral nematic phase (or cholesteric phase).'],
    ['what is the definition of Chirality', 'Chirality is when an object is present in two forms which are mirror images of each other. The two forms cannot be superimposed. Human hands are chiral. The left hand is a mirror image of the right hand. You cannot turn or move one of your hands to look exactly the same as the other. In chemistry, chirality refers to molecules. If a molecule is chiral it has two forms that are mirror images of each other but otherwise identical. Chemists call these enantiomers or optical isomers.'],
    ['what is the definition of Chirality', 'Chirality /kaɪˈraelɪtiː/ kaɪˈrælɪtiː is a property of symmetry important in several branches of. Science the word chirality is derived from The, greek (χειρ), kheir, hand a familiar chiral. Object an object or a system is chiral if it is distinguishable from its mirror; image that, is it cannot be superposed onto. it An object or a system is chiral if it is distinguishable from its mirror image; that is, it cannot be superposed onto it. Conversely, a mirror image of an achiral object, such as a sphere, cannot be distinguished from the object.'],
    ['what is the definition of Chirality', 'Normally, when a tetrahedral atom has four different substituents it is chiral. However, in rare cases, if two of the ligands differ from each other by being mirror images of each other, the mirror image of the molecule is identical to the original, and the molecule is achiral. Chirality is important in context of ordered phases as well, for example the addition of a small amount of an optically active molecule to a nematic phase (a phase that has long range orientational order of molecules) transforms that phase to a chiral nematic phase (or cholesteric phase).'],
]
scores = model.predict(pairs)
print(scores.shape)
# (5,)

# Or rank different texts based on similarity to a single text
ranks = model.rank(
    'what is the definition of Chirality',
    [
        'Two enantiomers of a generic amino acid that is chiral. Chirality /kaɪˈraelɪtiː/ kaɪˈrælɪtiː is a property of symmetry important in several branches of. Science the word chirality is derived from The, greek (χειρ), kheir, hand a familiar chiral. object An object or a system is chiral if it is distinguishable from its mirror image; that is, it cannot be superposed onto it. Conversely, a mirror image of an achiral object, such as a sphere, cannot be distinguished from the object.',
        'The symmetry of a molecule (or any other object) determines whether it is chiral. A molecule is achiral (not chiral) when an improper rotation, that is a combination of a rotation and a reflection in a plane, perpendicular to the axis of rotation, results in the same molecule. For tetrahedral molecules, the molecule is chiral if all four substituents are different. Chirality is important in context of ordered phases as well, for example the addition of a small amount of an optically active molecule to a nematic phase (a phase that has long range orientational order of molecules) transforms that phase to a chiral nematic phase (or cholesteric phase).',
        'Chirality is when an object is present in two forms which are mirror images of each other. The two forms cannot be superimposed. Human hands are chiral. The left hand is a mirror image of the right hand. You cannot turn or move one of your hands to look exactly the same as the other. In chemistry, chirality refers to molecules. If a molecule is chiral it has two forms that are mirror images of each other but otherwise identical. Chemists call these enantiomers or optical isomers.',
        'Chirality /kaɪˈraelɪtiː/ kaɪˈrælɪtiː is a property of symmetry important in several branches of. Science the word chirality is derived from The, greek (χειρ), kheir, hand a familiar chiral. Object an object or a system is chiral if it is distinguishable from its mirror; image that, is it cannot be superposed onto. it An object or a system is chiral if it is distinguishable from its mirror image; that is, it cannot be superposed onto it. Conversely, a mirror image of an achiral object, such as a sphere, cannot be distinguished from the object.',
        'Normally, when a tetrahedral atom has four different substituents it is chiral. However, in rare cases, if two of the ligands differ from each other by being mirror images of each other, the mirror image of the molecule is identical to the original, and the molecule is achiral. Chirality is important in context of ordered phases as well, for example the addition of a small amount of an optically active molecule to a nematic phase (a phase that has long range orientational order of molecules) transforms that phase to a chiral nematic phase (or cholesteric phase).',
    ]
)
# [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...]

Training Details

Training Dataset

ms_marco

• Dataset: ms_marco at a47ee7a
• Size: 78,704 training samples
• Columns: query, docs, and labels
• Approximate statistics based on the first 1000 samples:

  	query	docs	labels
  type	string	list	list
  details	min: 11 characters mean: 34.52 characters max: 112 characters	min: 2 elements mean: 6.00 elements max: 10 elements	min: 2 elements mean: 6.00 elements max: 10 elements

• Samples:

  query	docs	labels
  what tissues does the respiratory membrane consist of	['Confidence votes 2.3K. The respiratory membrane consists of the epithelial cells of the alveolus, the endothelial cells of the capillary, and the two fused basement membranes of these layers. ', 'Membranes. Body membranes are thin sheets of tissue that cover the body, line body cavities, and cover organs within the cavities in hollow organs. They can be categorized into epithelial and connective tissue membrane. Synovial membranes are connective tissue membranes that line the cavities of the freely movable joints such as the shoulder, elbow, and knee. Like serous membranes, they line cavities that do not open to the outside.', 'On another level, epithelia and connective tissues combine to form membranes that cover and protect other structures and tissues. Types of membranes: 1 Mucous membranes line cavities that connect with the exterior, including the digestive, respiratory, reproductive, and urinary tracts. 2 The epithelial surfaces are kept moist at all times. 3 The connective ...	[1, 0, 0, 0, 0, ...]
  where is the human stomach located	['All rights reserved. The stomach is a muscular organ located on the left side of the upper abdomen. The stomach receives food from the esophagus. As food reaches the end of the esophagus, it enters the stomach through a muscular valve called the lower esophageal sphincter. The stomach secretes acid and enzymes that digest food. ', 'Stomach. The stomach is a muscular, J-shaped organ in the abdomen. Part of the digestive system, the stomach stores and digests food through gastric juices and a specialized churning action created by folds on its inside. The stomach is located in the upper-left area of the abdomen below the liver and next to the spleen. It’s main function is store and breakdown foods and liquids that we consume before those contents travel to other organs to be further digested. When the stomach is empty, the inside has small folds called rugae.', 'The. Encyclopaedia Encyclopædia, Britannica. Inc the human stomach is Roughly-j shaped and is located in the upper left side ...	[1, 0, 0, 0, 0, ...]
  brick wall cost per linear foot	['The garden is to be enclosed by a stone wall costing $26 per linear foot. The interior wall is to be constructed with brick costing $8 per linear foot. I need to make a quote for a garden wall. The wall is to be one brick thick, 8 metres long and 0.75 meters high above ground level. the ground in the area is good quality top soil to a depth of 500mm and below is solid chalk.', 'Our free calculator uses recent, trusted data to estimate costs for your Concrete Block Wall Cap Installation project. For a basic 25 feet project in zip code 47474, the benchmark cost to Install a Concrete Block Wall Cap ranges between $13.26 - $16.36 per linear foot. To estimate costs for your project: 1. Set Project Zip Code Enter the Zip Code for the location where labor is hired and materials purchased. 2.', 'The cost of an eight foot tall brick fence will be $7.50 a linear foot. This cost is inclusive of material only. It is always best to consult a local building contractor to get a proper estimate of t...	[1, 0, 0, 0, 0, ...]

• Loss: ListNetLoss with these parameters:

  {
      "activation_fn": "torch.nn.modules.linear.Identity",
      "mini_batch_size": 16
  }
  

Evaluation Dataset

ms_marco

• Dataset: ms_marco at a47ee7a
• Size: 1,000 evaluation samples
• Columns: query, docs, and labels
• Approximate statistics based on the first 1000 samples:

  	query	docs	labels
  type	string	list	list
  details	min: 11 characters mean: 33.78 characters max: 91 characters	min: 3 elements mean: 6.50 elements max: 10 elements	min: 3 elements mean: 6.50 elements max: 10 elements

• Samples:

  query	docs	labels
  what is the definition of Chirality	['Two enantiomers of a generic amino acid that is chiral. Chirality /kaɪˈraelɪtiː/ kaɪˈrælɪtiː is a property of symmetry important in several branches of. Science the word chirality is derived from The, greek (χειρ), kheir, hand a familiar chiral. object An object or a system is chiral if it is distinguishable from its mirror image; that is, it cannot be superposed onto it. Conversely, a mirror image of an achiral object, such as a sphere, cannot be distinguished from the object.', 'The symmetry of a molecule (or any other object) determines whether it is chiral. A molecule is achiral (not chiral) when an improper rotation, that is a combination of a rotation and a reflection in a plane, perpendicular to the axis of rotation, results in the same molecule. For tetrahedral molecules, the molecule is chiral if all four substituents are different. Chirality is important in context of ordered phases as well, for example the addition of a small amount of an optically active molecule to a nem...	[1, 0, 0, 0, 0, ...]
  what is secularism	['Secularism is a code of duty pertaining to this life, founded on considerations purely human, and intended mainly for those who find theology indefinite or inadequate, unreliable or unbelievable. Its essential principles are three: (1) The improvement of this life by material means. In political terms, secularism is a movement towards the separation of religion and government (often termed the separation of church and state).', 'Secularism is about democracy and fairness. In a secular democracy all citizens are equal before the law and parliament. No religious or political affiliation gives advantages or disadvantages and religious believers are citizens with the same rights and obligations as anyone else. Secularism champions human rights above discriminatory religious demands. Secularism seeks to ensure and protect freedom of religious belief and practice for all citizens. Secularism is not about curtailing religious freedoms; it is about ensuring that the freedoms of thought and c...	[1, 0, 0, 0, 0, ...]
  possible permanent side effects of testosterone injections	['Common side effects of Depo-Testosterone include nausea, vomiting, headache, anxiety, depression, skin color changes, increased/decreased sexual interest, oily skin, hair loss, breast swelling in men, numbness or tingly feeling, and acne. Pain, swelling, and redness at the injection site may also occur. This is not a complete list of side effects and others may occur. Tell your doctor about any unusual or bothersome side effect. You may report side effects to FDA at 1-800-FDA-1088. Read the entire detailed patient monograph for Depo-Testosterone (Testosterone Cypionate Injection).', 'What causes side effects. Hormone therapies for prostate cancer cause side effects because they reduce the levels of male hormones in the body. Some side effects are common to all hormone therapies used for prostate cancer. Some effects vary from drug to drug', 'Testosterone replacement therapy is designed to restore your testosterone to normal levels. It is administered through injections, patches, or g...	[1, 0, 0, 0, 0, ...]

• Loss: ListNetLoss with these parameters:

  {
      "activation_fn": "torch.nn.modules.linear.Identity",
      "mini_batch_size": 16
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 16
• per_device_eval_batch_size: 16
• learning_rate: 2e-05
• num_train_epochs: 5
• seed: 12
• bf16: True
• load_best_model_at_end: True

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 16
• per_device_eval_batch_size: 16
• 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: 2e-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: 5
• 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: 12
• 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: True
• 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}
• tp_size: 0
• 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
• 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: proportional
• router_mapping: {}
• learning_rate_mapping: {}

Training Logs

Click to expand

Epoch	Step	Training Loss	Validation Loss
0.0002	1	2.0508	-
0.0203	100	2.0905	2.0813
0.0407	200	2.0766	2.0785
0.0610	300	2.0884	2.0743
0.0813	400	2.0738	2.0717
0.1016	500	2.0676	2.0702
0.1220	600	2.0728	2.0696
0.1423	700	2.0738	2.0684
0.1626	800	2.0699	2.0685
0.1830	900	2.076	2.0677
0.2033	1000	2.0652	2.0672
0.2236	1100	2.0695	2.0673
0.2440	1200	2.0762	2.0674
0.2643	1300	2.0673	2.0673
0.2846	1400	2.07	2.0670
0.3049	1500	2.0751	2.0664
0.3253	1600	2.0785	2.0664
0.3456	1700	2.0732	2.0663
0.3659	1800	2.0793	2.0659
0.3863	1900	2.0739	2.0664
0.4066	2000	2.0715	2.0658
0.4269	2100	2.0693	2.0663
0.4472	2200	2.0735	2.0659
0.4676	2300	2.0787	2.0652
0.4879	2400	2.0748	2.0650
0.5082	2500	2.0683	2.0649
0.5286	2600	2.0693	2.0648
0.5489	2700	2.063	2.0644
0.5692	2800	2.0729	2.0646
0.5896	2900	2.067	2.0650
0.6099	3000	2.0696	2.0644
0.6302	3100	2.0676	2.0648
0.6505	3200	2.0724	2.0651
0.6709	3300	2.0698	2.0650
0.6912	3400	2.071	2.0653
0.7115	3500	2.0713	2.0649
0.7319	3600	2.068	2.0644
0.7522	3700	2.0736	2.0644
0.7725	3800	2.079	2.0639
0.7928	3900	2.0716	2.0640
0.8132	4000	2.0747	2.0640
0.8335	4100	2.0715	2.0642
0.8538	4200	2.0724	2.0642
0.8742	4300	2.0686	2.0641
0.8945	4400	2.0714	2.0643
0.9148	4500	2.0731	2.0639
0.9351	4600	2.0696	2.0640
0.9555	4700	2.0656	2.0638
0.9758	4800	2.0719	2.0638
0.9961	4900	2.0642	2.0636
1.0165	5000	2.067	2.0639
1.0368	5100	2.0655	2.0645
1.0571	5200	2.0665	2.0648
1.0775	5300	2.0653	2.0651
1.0978	5400	2.0609	2.0649
1.1181	5500	2.0572	2.0663
1.1384	5600	2.0667	2.0660
1.1588	5700	2.0639	2.0652
1.1791	5800	2.06	2.0655
1.1994	5900	2.0566	2.0649
1.2198	6000	2.0735	2.0649
1.2401	6100	2.0657	2.0658
1.2604	6200	2.0621	2.0648
1.2807	6300	2.0659	2.0650
1.3011	6400	2.0591	2.0654
1.3214	6500	2.0674	2.0648
1.3417	6600	2.0586	2.0648
1.3621	6700	2.0627	2.0648
1.3824	6800	2.0667	2.0647
1.4027	6900	2.0616	2.0649
1.4231	7000	2.0613	2.0659
1.4434	7100	2.0674	2.0654
1.4637	7200	2.0622	2.0649
1.4840	7300	2.0636	2.0654
1.5044	7400	2.0751	2.0644
1.5247	7500	2.062	2.0646
1.5450	7600	2.067	2.0642
1.5654	7700	2.0722	2.0643
1.5857	7800	2.0651	2.0645
1.6060	7900	2.0654	2.0643
1.6263	8000	2.072	2.0648
1.6467	8100	2.0608	2.0640
1.6670	8200	2.0597	2.0642
1.6873	8300	2.0661	2.0645
1.7077	8400	2.0712	2.0637
1.7280	8500	2.0573	2.0644
1.7483	8600	2.0656	2.0642
1.7687	8700	2.066	2.0639
1.7890	8800	2.0656	2.0645
1.8093	8900	2.0704	2.0645
1.8296	9000	2.0649	2.0646
1.8500	9100	2.0699	2.0645
1.8703	9200	2.0598	2.0654
1.8906	9300	2.0742	2.0643
1.9110	9400	2.0596	2.0638
1.9313	9500	2.052	2.0642
1.9516	9600	2.0582	2.0656
1.9719	9700	2.0686	2.0647
1.9923	9800	2.0625	2.0642
2.0126	9900	2.0558	2.0672
2.0329	10000	2.058	2.0690
2.0533	10100	2.0551	2.0695
2.0736	10200	2.0553	2.0673
2.0939	10300	2.0497	2.0685
2.1143	10400	2.0504	2.0697
2.1346	10500	2.0447	2.0695
2.1549	10600	2.0488	2.0695
2.1752	10700	2.0366	2.0678
2.1956	10800	2.0566	2.0682
2.2159	10900	2.0512	2.0699
2.2362	11000	2.0515	2.0697
2.2566	11100	2.0534	2.0686
2.2769	11200	2.0594	2.0690
2.2972	11300	2.0484	2.0695
2.3175	11400	2.0511	2.0692
2.3379	11500	2.0497	2.0698
2.3582	11600	2.0507	2.0696
2.3785	11700	2.0445	2.0695
2.3989	11800	2.0504	2.0695
2.4192	11900	2.0548	2.0684
2.4395	12000	2.0449	2.0698
2.4598	12100	2.0601	2.0697
2.4802	12200	2.0446	2.0692
2.5005	12300	2.0414	2.0718
2.5208	12400	2.0618	2.0681
2.5412	12500	2.0601	2.0692
2.5615	12600	2.0496	2.0711
2.5818	12700	2.0554	2.0709
2.6022	12800	2.0409	2.0687
2.6225	12900	2.0408	2.0720
2.6428	13000	2.056	2.0719
2.6631	13100	2.0492	2.0685
2.6835	13200	2.0514	2.0687
2.7038	13300	2.0569	2.0698
2.7241	13400	2.0464	2.0698
2.7445	13500	2.0581	2.0720
2.7648	13600	2.0522	2.0717
2.7851	13700	2.05	2.0720
2.8054	13800	2.0421	2.0695
2.8258	13900	2.0503	2.0707
2.8461	14000	2.0446	2.0689
2.8664	14100	2.0507	2.0695
2.8868	14200	2.0501	2.0700
2.9071	14300	2.0569	2.0688
2.9274	14400	2.0574	2.0689
2.9478	14500	2.0489	2.0701
2.9681	14600	2.0532	2.0700
2.9884	14700	2.0552	2.0699
3.0087	14800	2.046	2.0751
3.0291	14900	2.0256	2.0747
3.0494	15000	2.0334	2.0753
3.0697	15100	2.0359	2.0773
3.0901	15200	2.0256	2.0750
3.1104	15300	2.0296	2.0749
3.1307	15400	2.0353	2.0748
3.1510	15500	2.0256	2.0748
3.1714	15600	2.0295	2.0759
3.1917	15700	2.0238	2.0745
3.2120	15800	2.0259	2.0781
3.2324	15900	2.0373	2.0754
3.2527	16000	2.0358	2.0751
3.2730	16100	2.027	2.0769
3.2934	16200	2.0316	2.0760
3.3137	16300	2.0392	2.0751
3.3340	16400	2.0391	2.0759
3.3543	16500	2.0327	2.0749
3.3747	16600	2.0317	2.0768
3.3950	16700	2.0386	2.0758
3.4153	16800	2.0331	2.0758
3.4357	16900	2.0393	2.0770
3.4560	17000	2.0277	2.0777
3.4763	17100	2.0353	2.0763
3.4966	17200	2.026	2.0786
3.5170	17300	2.0412	2.0785
3.5373	17400	2.039	2.0776
3.5576	17500	2.0306	2.0772
3.5780	17600	2.0303	2.0774
3.5983	17700	2.0361	2.0751
3.6186	17800	2.0366	2.0751
3.6390	17900	2.0389	2.0772
3.6593	18000	2.0327	2.0765
3.6796	18100	2.036	2.0756
3.6999	18200	2.0258	2.0758
3.7203	18300	2.0256	2.0758
3.7406	18400	2.038	2.0763
3.7609	18500	2.0391	2.0762
3.7813	18600	2.0246	2.0772
3.8016	18700	2.0269	2.0764
3.8219	18800	2.0311	2.0761
3.8422	18900	2.0366	2.0759
3.8626	19000	2.0325	2.0759
3.8829	19100	2.0427	2.0756
3.9032	19200	2.029	2.0765
3.9236	19300	2.0338	2.0760
3.9439	19400	2.0232	2.0748
3.9642	19500	2.0286	2.0776
3.9845	19600	2.0364	2.0758
4.0049	19700	2.0325	2.0766
4.0252	19800	2.0158	2.0773
4.0455	19900	2.0176	2.0789
4.0659	20000	2.0193	2.0796
4.0862	20100	2.0159	2.0805
4.1065	20200	2.0283	2.0809
4.1269	20300	2.0176	2.0796
4.1472	20400	2.0129	2.0788
4.1675	20500	2.0225	2.0805
4.1878	20600	2.0185	2.0792
4.2082	20700	2.0146	2.0792
4.2285	20800	2.0225	2.0797
4.2488	20900	2.0167	2.0815
4.2692	21000	2.0203	2.0799
4.2895	21100	2.021	2.0807
4.3098	21200	2.0217	2.0804
4.3301	21300	2.0242	2.0802
4.3505	21400	2.0191	2.0807
4.3708	21500	2.0157	2.0794
4.3911	21600	2.0184	2.0814
4.4115	21700	2.0241	2.0802
4.4318	21800	2.0162	2.0801
4.4521	21900	2.0156	2.0808
4.4725	22000	2.0195	2.0805
4.4928	22100	2.0147	2.0817
4.5131	22200	2.0247	2.0804
4.5334	22300	2.019	2.0815
4.5538	22400	2.0155	2.0806
4.5741	22500	2.0177	2.0810
4.5944	22600	2.0285	2.0809
4.6148	22700	2.0239	2.0805
4.6351	22800	2.0288	2.0810
4.6554	22900	2.0094	2.0815
4.6757	23000	2.019	2.0810
4.6961	23100	2.0235	2.0812
4.7164	23200	2.01	2.0807
4.7367	23300	2.0246	2.0812
4.7571	23400	2.0229	2.0812
4.7774	23500	2.0239	2.0806
4.7977	23600	2.0193	2.0806
4.8181	23700	2.0196	2.0808
4.8384	23800	2.0222	2.0805
4.8587	23900	2.0253	2.0813
4.8790	24000	2.0182	2.0812
4.8994	24100	2.0201	2.0811
4.9197	24200	2.0225	2.0807
4.9400	24300	2.0265	2.0813
4.9604	24400	2.0142	2.0809
4.9807	24500	2.0077	2.0806

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.11.13
• Sentence Transformers: 5.0.0
• Transformers: 4.51.0
• PyTorch: 2.9.1+cu126
• Accelerate: 1.8.1
• Datasets: 3.6.0
• Tokenizers: 0.21.4-dev.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",
}

ListNetLoss

@inproceedings{cao2007learning,
    title={Learning to Rank: From Pairwise Approach to Listwise Approach},
    author={Cao, Zhe and Qin, Tao and Liu, Tie-Yan and Tsai, Ming-Feng and Li, Hang},
    booktitle={Proceedings of the 24th international conference on Machine learning},
    pages={129--136},
    year={2007}
}