CrossEncoder based on jhu-clsp/ettin-encoder-32m

This is a Cross Encoder model finetuned from jhu-clsp/ettin-encoder-32m 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-32m
  • Maximum Sequence Length: 7999 tokens
  • Number of Output Labels: 1 label
  • Training Dataset:
  • Language: en

Model Sources

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("rahulseetharaman/reranker-msmarco-v1.1-ettin-encoder-32m-listnet")
# Get scores for pairs of texts
pairs = [
    ['incubation period for food poisoning', 'Symptoms of chicken food poisoning. The period of time from when the contaminated food is eaten to when the symptoms appear is called the ‘incubation period’. In most cases of food poisoning the symptoms appear between 24 and 48 hours. These include: 1  Fever. 2  Abdominal pains. 3  Upset stomach. 4  Nausea. 5  Vomit'],
    ['incubation period for food poisoning', 'The symptoms of food poisoning are diarrhea, nausea, vomiting, exhaustion and stomach cramps. The symptoms depend on the type of bacteria that cause the infection. It is very important to get yourself checked as there are certain bacteria that have incubation periods as long as 3-4 days. 3. Food poisoning is an illness caused by eating contaminated food. In most of the cases, the food is contaminated by bacteria and viruses or the food is cooked at the wrong temperatures. Although food poisoning is generally thought of as a mild illness, there are cases when it can develop into serious conditions.'],
    ['incubation period for food poisoning', 'The incubation period typically lasts 24-48 hours and the symptoms usually pass in a couple of days. In young children, the rotavirus is a common cause of infection from contaminated food. The symptoms usually develop within a week and pass in around five to seven days. The bacteria are usually found on raw or undercooked meat (particularly poultry), unpasteurised milk and untreated water. The incubation period (the time between eating contaminated food and the start of symptoms) for food poisoning caused by campylobacter is usually between two and five days. The symptoms usually last less than a week'],
    ['incubation period for food poisoning', 'Incubation Period. The period between when the contaminated food is ingested and the time when symptoms first appear is known as the incubation period, according to the CDC. The length of the incubation period depends on the quantity consumed and the type of organism. Incubation Period for Food Poisoning. Food poisoning is an extremely unpleasant condition that results from eating rotten or otherwise tainted food.'],
    ['incubation period for food poisoning', 'Foodborne illness (also foodborne disease and colloquially referred to as food poisoning) is any illness resulting from the food spoilage of contaminated food, pathogenic bacteria, viruses, or parasites that contaminate food, as well as chemical or natural toxins such as poisonous mushrooms. '],
]
scores = model.predict(pairs)
print(scores.shape)
# (5,)

# Or rank different texts based on similarity to a single text
ranks = model.rank(
    'incubation period for food poisoning',
    [
        'Symptoms of chicken food poisoning. The period of time from when the contaminated food is eaten to when the symptoms appear is called the ‘incubation period’. In most cases of food poisoning the symptoms appear between 24 and 48 hours. These include: 1  Fever. 2  Abdominal pains. 3  Upset stomach. 4  Nausea. 5  Vomit',
        'The symptoms of food poisoning are diarrhea, nausea, vomiting, exhaustion and stomach cramps. The symptoms depend on the type of bacteria that cause the infection. It is very important to get yourself checked as there are certain bacteria that have incubation periods as long as 3-4 days. 3. Food poisoning is an illness caused by eating contaminated food. In most of the cases, the food is contaminated by bacteria and viruses or the food is cooked at the wrong temperatures. Although food poisoning is generally thought of as a mild illness, there are cases when it can develop into serious conditions.',
        'The incubation period typically lasts 24-48 hours and the symptoms usually pass in a couple of days. In young children, the rotavirus is a common cause of infection from contaminated food. The symptoms usually develop within a week and pass in around five to seven days. The bacteria are usually found on raw or undercooked meat (particularly poultry), unpasteurised milk and untreated water. The incubation period (the time between eating contaminated food and the start of symptoms) for food poisoning caused by campylobacter is usually between two and five days. The symptoms usually last less than a week',
        'Incubation Period. The period between when the contaminated food is ingested and the time when symptoms first appear is known as the incubation period, according to the CDC. The length of the incubation period depends on the quantity consumed and the type of organism. Incubation Period for Food Poisoning. Food poisoning is an extremely unpleasant condition that results from eating rotten or otherwise tainted food.',
        'Foodborne illness (also foodborne disease and colloquially referred to as food poisoning) is any illness resulting from the food spoilage of contaminated food, pathogenic bacteria, viruses, or parasites that contaminate food, as well as chemical or natural toxins such as poisonous mushrooms. ',
    ]
)
# [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...]

Evaluation

Metrics

Cross Encoder Reranking

  • Datasets: NanoMSMARCO_R100, NanoNFCorpus_R100 and NanoNQ_R100
  • Evaluated with CrossEncoderRerankingEvaluator with these parameters:
    {
        "at_k": 10,
        "always_rerank_positives": true
    }
    
Metric NanoMSMARCO_R100 NanoNFCorpus_R100 NanoNQ_R100
map 0.4818 (-0.0078) 0.3292 (+0.0682) 0.5188 (+0.0992)
mrr@10 0.4698 (-0.0077) 0.5225 (+0.0226) 0.5268 (+0.1001)
ndcg@10 0.5348 (-0.0056) 0.3376 (+0.0126) 0.5534 (+0.0528)

Cross Encoder Nano BEIR

  • Dataset: NanoBEIR_R100_mean
  • Evaluated with CrossEncoderNanoBEIREvaluator with these parameters:
    {
        "dataset_names": [
            "msmarco",
            "nfcorpus",
            "nq"
        ],
        "rerank_k": 100,
        "at_k": 10,
        "always_rerank_positives": true
    }
    
Metric Value
map 0.4432 (+0.0532)
mrr@10 0.5064 (+0.0383)
ndcg@10 0.4753 (+0.0199)

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: 33.46 characters
    • max: 101 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
    how is obsidian formed ['OBSIDIAN-Formed from rapid cooling of felsic lavas, high in silica and aluminum. Obsidian is an extrusive igneous rock, formed from the extremely rapid cooling of felsic lav … a which includes orthoclase, quartz, and mica. Obsidian is a volcanic glass, meaning that the mineral constituents from which it formed did not have time to crystallize due to the rapid cooling.', 'OBSIDIAN-Formed from rapid cooling of felsic lavas, high in silica and aluminum. Obsidian is an extrusive igneous rock, formed from the extremely rapid cooling of felsic lava which includes orthoclase, quartz, and mica.', 'Obsidian is an igneous rock that forms when molten rock cools very rapidly. The result is a rock that cooled so fast, crystals did not get a chance to form. Obsidian is a volcanic glass with a smooth and uniform structure.', 'Obsidian is an igneous rock that forms when molten rock material cools so rapidly that atoms are unable to arrange themselves into a crystalline structure. It is an amorphous ... [1, 0, 0, 0, 0, ...]
    estimated construction cost per square foot ['by Jay Behm-A very basic way to estimate the cost of building a detached garage is to simply apply a typical average per square foot construction of $30 to $40. That is for an average cost basis for having a contractor / builder build a basic one story garage for you on your property. If you are in an area with higher-than-average cost of living you can use $50 to $55. If there are complications or you prefer top quality materials and components the price can go up.So, generally speaking, a 24 ft.sq., two car, basic garage will cost in the range of $17,000 to $23,000.', 'An average commercial steel building costs between $16 and $20 per square foot, including building package (I-Beams, purlins, girts etc.) , delivery, foundation and the cost of construction. Since many retail & commercial buildings require additional finishing like insulation or facade façade, customization the cost may rise to$ 30 or$ 40 per square (FOOT). sf', 'Since many retail & commercial buildings require addit... [1, 0, 0, 0, 0, ...]
    what is a cove ['cove 1 n 1 a small sheltered bay in the shoreline of a sea river or lake 2 a a recess or small valley in the side of a mountain b a cave or cavern 3 cove 1 1 a small indentation or recess in the shoreline of a sea lake or river 2 a sheltered nook 3 a hollow or recess in a mountain cavern 4 a narrow pass or sheltered area between woods or hills 5 a concave architectural surface or molding esp one linking a ceiling and a wall', 'a cove is a small type of bay or coastal inlet coves usually have narrow restricted entrances are often circular or oval and are often situated within a larger bay small narrow sheltered bays inlets creeks or recesses in a coast are often considered coves ', 'cove s name comes from the niche created by the base of mt fanny mill creek and the ridges to the south our views are stunning our sunsets beautiful and our soil rich sunset in cove mt fanny a 7150 foot peak in the wallowa range dominates the eastward view about cove cove is a little slice of heaven locate... [1, 1, 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: 10 characters
    • mean: 34.41 characters
    • max: 99 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
    incubation period for food poisoning ['Symptoms of chicken food poisoning. The period of time from when the contaminated food is eaten to when the symptoms appear is called the ‘incubation period’. In most cases of food poisoning the symptoms appear between 24 and 48 hours. These include: 1 Fever. 2 Abdominal pains. 3 Upset stomach. 4 Nausea. 5 Vomit', 'The symptoms of food poisoning are diarrhea, nausea, vomiting, exhaustion and stomach cramps. The symptoms depend on the type of bacteria that cause the infection. It is very important to get yourself checked as there are certain bacteria that have incubation periods as long as 3-4 days. 3. Food poisoning is an illness caused by eating contaminated food. In most of the cases, the food is contaminated by bacteria and viruses or the food is cooked at the wrong temperatures. Although food poisoning is generally thought of as a mild illness, there are cases when it can develop into serious conditions.', 'The incubation period typically lasts 24-48 hours and the symptoms u... [1, 0, 0, 0, 0, ...]
    what are nenet tents made from ['Nenets herders live in tepee style tents ‘mya’ the covers of which are made from reindeer skin for use in winter and canvas in the summer. Their herding involves seasonal migrations with their reindeer. For the Nenets who migrate up to the north the Yamal Peninsula, migrations can be as long as 1,000km each way. TUNDRA NENETS. With a population of over 41,000, the Nenets are one of the largest of the indigenous groups in Northern Siberia. Their territory covers a vast area that stretches from the Kanin Peninsula at the White Sea in the west, all the way to the Taymyr Peninsula, a distance of more than 2,000 km.', 'The Yamal-Nenets are a nomadic people and herders of reindeer in the vast northern reaches of Siberia. They live in Chums (pronounced chooms), which are large Tipi-like tents made from tall poles and reindeer hides. “…The traditional chum consists of reindeer hides sewn together and wrapped around wooden poles that are organized in a circle…” Wikipedia – Chum. On its right ... [1, 0, 0, 0, 0, ...]
    does the draft include women ["Based on our numbers for a worst-case scenario, if we had to do such a draft, it would include women or you just won't get the numbers of health care workers you needed, said Lew Brodsky, director of congressional and government affairs for the SSS. But I think culturally there might be a lot of negative feelings among political parts of the spectrum, and possibly more among men than women.. Can't Live With Them, Can't Live Without Them. Health care workers were part of the draft between 1950 and 1973 to fight the Korean and Vietnam wars.", 'Females may be included in the Selective Service and qualify for a potential draft should one be ordered by the president, Defense Secretary Leon Panetta said. In doing so, it may force Congress or the president to include women or scrap the Selective Service, analysts said. “That, frankly, could be true,” Nancy Duff Campbell, co-president of the National Women’s Law Center in Washington, D.C., told Military.com.', "Now that women can serve in co... [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}
  • 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
  • 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: batch_sampler
  • multi_dataset_batch_sampler: proportional
  • router_mapping: {}
  • learning_rate_mapping: {}

Training Logs

Click to expand
Epoch Step Training Loss Validation Loss NanoMSMARCO_R100_ndcg@10 NanoNFCorpus_R100_ndcg@10 NanoNQ_R100_ndcg@10 NanoBEIR_R100_mean_ndcg@10
-1 -1 - - 0.0376 (-0.5028) 0.2282 (-0.0968) 0.0589 (-0.4418) 0.1082 (-0.3471)
0.0002 1 2.7963 - - - - -
0.0203 100 2.1145 2.0870 0.0684 (-0.4720) 0.2264 (-0.0986) 0.0688 (-0.4318) 0.1212 (-0.3341)
0.0407 200 2.0886 2.0854 0.1009 (-0.4395) 0.2918 (-0.0333) 0.0767 (-0.4239) 0.1565 (-0.2989)
0.0610 300 2.0848 2.0833 0.1941 (-0.3464) 0.2859 (-0.0391) 0.2033 (-0.2973) 0.2278 (-0.2276)
0.0813 400 2.0868 2.0803 0.3491 (-0.1914) 0.3215 (-0.0036) 0.3451 (-0.1555) 0.3386 (-0.1168)
0.1016 500 2.0738 2.0791 0.4083 (-0.1321) 0.3161 (-0.0089) 0.2742 (-0.2265) 0.3329 (-0.1225)
0.1220 600 2.0713 2.0782 0.3870 (-0.1535) 0.3123 (-0.0128) 0.4370 (-0.0636) 0.3787 (-0.0766)
0.1423 700 2.0773 2.0774 0.4714 (-0.0690) 0.3296 (+0.0045) 0.4619 (-0.0387) 0.4209 (-0.0344)
0.1626 800 2.0787 2.0773 0.4514 (-0.0891) 0.3190 (-0.0060) 0.3891 (-0.1115) 0.3865 (-0.0689)
0.1830 900 2.0752 2.0767 0.5139 (-0.0266) 0.3340 (+0.0090) 0.5190 (+0.0183) 0.4556 (+0.0002)
0.2033 1000 2.0708 2.0765 0.5015 (-0.0389) 0.3230 (-0.0021) 0.4995 (-0.0012) 0.4413 (-0.0141)
0.2236 1100 2.0783 2.0761 0.5063 (-0.0341) 0.3357 (+0.0107) 0.4689 (-0.0318) 0.4370 (-0.0184)
0.2440 1200 2.0787 2.0762 0.5090 (-0.0315) 0.3288 (+0.0037) 0.4525 (-0.0481) 0.4301 (-0.0253)
0.2643 1300 2.0766 2.0758 0.4617 (-0.0787) 0.3072 (-0.0179) 0.4633 (-0.0373) 0.4107 (-0.0447)
0.2846 1400 2.0844 2.0756 0.4658 (-0.0746) 0.3033 (-0.0218) 0.4700 (-0.0306) 0.4130 (-0.0424)
0.3049 1500 2.0761 2.0760 0.4577 (-0.0827) 0.2975 (-0.0276) 0.4457 (-0.0550) 0.4003 (-0.0551)
0.3253 1600 2.0808 2.0755 0.4687 (-0.0718) 0.3286 (+0.0036) 0.4494 (-0.0513) 0.4155 (-0.0398)
0.3456 1700 2.0709 2.0758 0.4946 (-0.0458) 0.3453 (+0.0203) 0.5006 (-0.0001) 0.4468 (-0.0085)
0.3659 1800 2.0726 2.0752 0.4985 (-0.0420) 0.3204 (-0.0047) 0.4795 (-0.0212) 0.4328 (-0.0226)
0.3863 1900 2.0742 2.0750 0.5397 (-0.0007) 0.3118 (-0.0133) 0.5320 (+0.0314) 0.4612 (+0.0058)
0.4066 2000 2.0774 2.0749 0.4848 (-0.0556) 0.3152 (-0.0098) 0.4612 (-0.0395) 0.4204 (-0.0350)
0.4269 2100 2.0702 2.0745 0.5070 (-0.0334) 0.3170 (-0.0080) 0.4962 (-0.0044) 0.4401 (-0.0153)
0.4472 2200 2.0819 2.0747 0.5502 (+0.0098) 0.3376 (+0.0125) 0.5164 (+0.0157) 0.4681 (+0.0127)
0.4676 2300 2.0843 2.0748 0.5100 (-0.0305) 0.3142 (-0.0108) 0.4956 (-0.0051) 0.4399 (-0.0154)
0.4879 2400 2.0634 2.0754 0.4906 (-0.0498) 0.3158 (-0.0093) 0.4698 (-0.0309) 0.4254 (-0.0300)
0.5082 2500 2.0633 2.0751 0.4884 (-0.0520) 0.3159 (-0.0092) 0.4937 (-0.0070) 0.4327 (-0.0227)
0.5286 2600 2.0679 2.0749 0.5111 (-0.0294) 0.2948 (-0.0302) 0.4877 (-0.0129) 0.4312 (-0.0242)
0.5489 2700 2.078 2.0742 0.5502 (+0.0098) 0.2811 (-0.0439) 0.4596 (-0.0410) 0.4303 (-0.0251)
0.5692 2800 2.0715 2.0740 0.5301 (-0.0103) 0.2918 (-0.0332) 0.4736 (-0.0271) 0.4318 (-0.0235)
0.5896 2900 2.0773 2.0739 0.4941 (-0.0464) 0.3095 (-0.0155) 0.4572 (-0.0434) 0.4203 (-0.0351)
0.6099 3000 2.074 2.0741 0.5228 (-0.0177) 0.3135 (-0.0115) 0.5534 (+0.0528) 0.4632 (+0.0079)
0.6302 3100 2.0782 2.0744 0.5411 (+0.0007) 0.3301 (+0.0050) 0.4187 (-0.0820) 0.4300 (-0.0254)
0.6505 3200 2.0695 2.0743 0.5349 (-0.0056) 0.3122 (-0.0129) 0.4977 (-0.0029) 0.4483 (-0.0071)
0.6709 3300 2.0696 2.0740 0.5406 (+0.0002) 0.3174 (-0.0076) 0.5236 (+0.0229) 0.4605 (+0.0052)
0.6912 3400 2.0802 2.0735 0.5588 (+0.0183) 0.3232 (-0.0018) 0.4908 (-0.0099) 0.4576 (+0.0022)
0.7115 3500 2.069 2.0735 0.5023 (-0.0381) 0.3388 (+0.0138) 0.5123 (+0.0117) 0.4511 (-0.0042)
0.7319 3600 2.0745 2.0736 0.5291 (-0.0113) 0.3195 (-0.0056) 0.5064 (+0.0057) 0.4517 (-0.0037)
0.7522 3700 2.073 2.0734 0.5346 (-0.0059) 0.3209 (-0.0042) 0.5047 (+0.0041) 0.4534 (-0.0020)
0.7725 3800 2.0747 2.0737 0.5076 (-0.0328) 0.3164 (-0.0086) 0.5414 (+0.0407) 0.4551 (-0.0002)
0.7928 3900 2.076 2.0733 0.4968 (-0.0437) 0.3312 (+0.0061) 0.4606 (-0.0400) 0.4295 (-0.0259)
0.8132 4000 2.0817 2.0735 0.4961 (-0.0443) 0.3446 (+0.0196) 0.4805 (-0.0202) 0.4404 (-0.0150)
0.8335 4100 2.0713 2.0733 0.5315 (-0.0089) 0.3370 (+0.0120) 0.5393 (+0.0386) 0.4693 (+0.0139)
0.8538 4200 2.0718 2.0735 0.4998 (-0.0406) 0.3226 (-0.0025) 0.5128 (+0.0121) 0.4451 (-0.0103)
0.8742 4300 2.0626 2.0730 0.5063 (-0.0341) 0.3376 (+0.0126) 0.5289 (+0.0282) 0.4576 (+0.0022)
0.8945 4400 2.0721 2.0731 0.4800 (-0.0604) 0.3110 (-0.0141) 0.5302 (+0.0295) 0.4404 (-0.0150)
0.9148 4500 2.0751 2.0731 0.4781 (-0.0624) 0.3241 (-0.0010) 0.5010 (+0.0003) 0.4344 (-0.0210)
0.9351 4600 2.0716 2.0727 0.4995 (-0.0409) 0.3046 (-0.0205) 0.5238 (+0.0231) 0.4426 (-0.0127)
0.9555 4700 2.0658 2.0729 0.4740 (-0.0664) 0.3319 (+0.0069) 0.5070 (+0.0063) 0.4376 (-0.0177)
0.9758 4800 2.0814 2.0731 0.5199 (-0.0205) 0.3372 (+0.0121) 0.4906 (-0.0101) 0.4492 (-0.0061)
0.9961 4900 2.0752 2.0728 0.5175 (-0.0230) 0.3347 (+0.0097) 0.5366 (+0.0359) 0.4629 (+0.0075)
1.0165 5000 2.07 2.0732 0.5194 (-0.0210) 0.3356 (+0.0105) 0.5315 (+0.0308) 0.4622 (+0.0068)
1.0368 5100 2.067 2.0730 0.4784 (-0.0620) 0.3256 (+0.0005) 0.5260 (+0.0254) 0.4433 (-0.0120)
1.0571 5200 2.0633 2.0729 0.4808 (-0.0597) 0.3371 (+0.0120) 0.4634 (-0.0372) 0.4271 (-0.0283)
1.0775 5300 2.0699 2.0728 0.4909 (-0.0495) 0.3280 (+0.0029) 0.5489 (+0.0483) 0.4559 (+0.0006)
1.0978 5400 2.0734 2.0733 0.4490 (-0.0914) 0.3351 (+0.0100) 0.5282 (+0.0276) 0.4374 (-0.0179)
1.1181 5500 2.0673 2.0737 0.4821 (-0.0583) 0.3540 (+0.0289) 0.5481 (+0.0475) 0.4614 (+0.0060)
1.1384 5600 2.0729 2.0738 0.5275 (-0.0129) 0.3228 (-0.0023) 0.5187 (+0.0180) 0.4563 (+0.0009)
1.1588 5700 2.0699 2.0742 0.5283 (-0.0121) 0.3190 (-0.0060) 0.5340 (+0.0334) 0.4604 (+0.0051)
1.1791 5800 2.0637 2.0727 0.5147 (-0.0257) 0.3491 (+0.0240) 0.5184 (+0.0177) 0.4607 (+0.0054)
1.1994 5900 2.0752 2.0734 0.5300 (-0.0104) 0.2904 (-0.0347) 0.5503 (+0.0496) 0.4569 (+0.0015)
1.2198 6000 2.0731 2.0727 0.5173 (-0.0231) 0.2854 (-0.0396) 0.5343 (+0.0336) 0.4457 (-0.0097)
1.2401 6100 2.0713 2.0732 0.4748 (-0.0656) 0.2927 (-0.0324) 0.5062 (+0.0055) 0.4246 (-0.0308)
1.2604 6200 2.0716 2.0723 0.4342 (-0.1063) 0.3092 (-0.0159) 0.5108 (+0.0101) 0.4180 (-0.0373)
1.2807 6300 2.0649 2.0729 0.5001 (-0.0403) 0.3297 (+0.0046) 0.5548 (+0.0541) 0.4615 (+0.0062)
1.3011 6400 2.079 2.0731 0.4775 (-0.0629) 0.3333 (+0.0082) 0.5325 (+0.0319) 0.4478 (-0.0076)
1.3214 6500 2.0719 2.0731 0.4518 (-0.0887) 0.3119 (-0.0131) 0.4969 (-0.0037) 0.4202 (-0.0352)
1.3417 6600 2.0667 2.0744 0.4899 (-0.0505) 0.3422 (+0.0172) 0.5327 (+0.0320) 0.4549 (-0.0004)
1.3621 6700 2.0592 2.0735 0.4711 (-0.0693) 0.3202 (-0.0049) 0.5357 (+0.0350) 0.4423 (-0.0131)
1.3824 6800 2.0716 2.0735 0.4858 (-0.0546) 0.3707 (+0.0457) 0.5436 (+0.0429) 0.4667 (+0.0113)
1.4027 6900 2.0745 2.0735 0.4789 (-0.0615) 0.3401 (+0.0151) 0.4967 (-0.0040) 0.4386 (-0.0168)
1.4231 7000 2.0752 2.0737 0.4825 (-0.0579) 0.3319 (+0.0069) 0.5618 (+0.0611) 0.4588 (+0.0034)
1.4434 7100 2.0693 2.0734 0.4729 (-0.0675) 0.3591 (+0.0341) 0.4829 (-0.0178) 0.4383 (-0.0171)
1.4637 7200 2.0618 2.0741 0.4753 (-0.0651) 0.3582 (+0.0332) 0.4849 (-0.0158) 0.4395 (-0.0159)
1.4840 7300 2.0713 2.0746 0.4826 (-0.0578) 0.3443 (+0.0193) 0.5181 (+0.0175) 0.4483 (-0.0070)
1.5044 7400 2.0617 2.0751 0.5096 (-0.0309) 0.3586 (+0.0335) 0.5143 (+0.0136) 0.4608 (+0.0054)
1.5247 7500 2.0721 2.0733 0.4808 (-0.0597) 0.3472 (+0.0221) 0.4730 (-0.0277) 0.4336 (-0.0217)
1.5450 7600 2.0693 2.0733 0.4759 (-0.0645) 0.3290 (+0.0039) 0.4984 (-0.0022) 0.4344 (-0.0209)
1.5654 7700 2.0702 2.0732 0.4611 (-0.0793) 0.3515 (+0.0264) 0.4963 (-0.0043) 0.4363 (-0.0191)
1.5857 7800 2.0649 2.0728 0.4951 (-0.0453) 0.3599 (+0.0348) 0.5251 (+0.0245) 0.4600 (+0.0047)
1.6060 7900 2.0647 2.0731 0.4860 (-0.0544) 0.3500 (+0.0250) 0.5253 (+0.0246) 0.4538 (-0.0016)
1.6263 8000 2.0681 2.0731 0.5348 (-0.0056) 0.3376 (+0.0126) 0.5534 (+0.0528) 0.4753 (+0.0199)
1.6467 8100 2.0681 2.0730 0.4773 (-0.0632) 0.3389 (+0.0139) 0.4954 (-0.0052) 0.4372 (-0.0182)
1.6670 8200 2.0557 2.0728 0.4691 (-0.0713) 0.3126 (-0.0125) 0.5073 (+0.0067) 0.4297 (-0.0257)
1.6873 8300 2.0599 2.0735 0.4843 (-0.0561) 0.3188 (-0.0062) 0.5367 (+0.0361) 0.4466 (-0.0087)
1.7077 8400 2.0629 2.0730 0.4820 (-0.0584) 0.3386 (+0.0135) 0.4855 (-0.0151) 0.4354 (-0.0200)
1.7280 8500 2.0563 2.0732 0.4585 (-0.0819) 0.3454 (+0.0203) 0.5089 (+0.0083) 0.4376 (-0.0178)
1.7483 8600 2.0647 2.0731 0.4738 (-0.0666) 0.3337 (+0.0087) 0.5027 (+0.0020) 0.4367 (-0.0186)
1.7687 8700 2.0631 2.0733 0.4690 (-0.0714) 0.3416 (+0.0165) 0.5090 (+0.0083) 0.4398 (-0.0155)
1.7890 8800 2.0682 2.0733 0.4720 (-0.0685) 0.3311 (+0.0061) 0.5388 (+0.0382) 0.4473 (-0.0081)
1.8093 8900 2.0547 2.0728 0.4871 (-0.0533) 0.3332 (+0.0082) 0.5293 (+0.0286) 0.4499 (-0.0055)
1.8296 9000 2.0667 2.0731 0.5003 (-0.0401) 0.3305 (+0.0054) 0.4953 (-0.0053) 0.4420 (-0.0133)
1.8500 9100 2.0588 2.0731 0.5349 (-0.0055) 0.3523 (+0.0272) 0.5115 (+0.0108) 0.4662 (+0.0109)
1.8703 9200 2.0591 2.0736 0.4988 (-0.0417) 0.3434 (+0.0183) 0.5140 (+0.0134) 0.4521 (-0.0033)
1.8906 9300 2.0666 2.0741 0.4989 (-0.0416) 0.3505 (+0.0255) 0.5558 (+0.0552) 0.4684 (+0.0130)
1.9110 9400 2.0684 2.0737 0.4941 (-0.0463) 0.3548 (+0.0298) 0.5593 (+0.0587) 0.4694 (+0.0140)
1.9313 9500 2.0706 2.0732 0.5112 (-0.0292) 0.3536 (+0.0286) 0.5367 (+0.0360) 0.4672 (+0.0118)
1.9516 9600 2.076 2.0731 0.4762 (-0.0642) 0.3367 (+0.0117) 0.5014 (+0.0008) 0.4381 (-0.0172)
1.9719 9700 2.0686 2.0735 0.4828 (-0.0577) 0.3201 (-0.0050) 0.5317 (+0.0310) 0.4448 (-0.0105)
1.9923 9800 2.0685 2.0731 0.4866 (-0.0538) 0.3322 (+0.0072) 0.5527 (+0.0520) 0.4572 (+0.0018)
2.0126 9900 2.0659 2.0744 0.4655 (-0.0749) 0.3583 (+0.0333) 0.5306 (+0.0299) 0.4515 (-0.0039)
2.0329 10000 2.057 2.0743 0.4423 (-0.0981) 0.3313 (+0.0063) 0.5204 (+0.0198) 0.4314 (-0.0240)
2.0533 10100 2.0551 2.0751 0.4247 (-0.1157) 0.3349 (+0.0099) 0.5259 (+0.0252) 0.4285 (-0.0269)
2.0736 10200 2.0609 2.0763 0.4395 (-0.1009) 0.3424 (+0.0174) 0.5479 (+0.0473) 0.4433 (-0.0121)
2.0939 10300 2.0467 2.0758 0.4182 (-0.1222) 0.3349 (+0.0099) 0.5230 (+0.0224) 0.4254 (-0.0300)
2.1143 10400 2.0578 2.0760 0.4218 (-0.1187) 0.3301 (+0.0051) 0.5107 (+0.0101) 0.4209 (-0.0345)
2.1346 10500 2.0549 2.0755 0.4439 (-0.0966) 0.3400 (+0.0150) 0.5085 (+0.0078) 0.4308 (-0.0246)
2.1549 10600 2.0538 2.0761 0.4437 (-0.0967) 0.3527 (+0.0277) 0.5051 (+0.0045) 0.4338 (-0.0215)
2.1752 10700 2.0626 2.0755 0.4528 (-0.0876) 0.3517 (+0.0266) 0.5538 (+0.0532) 0.4528 (-0.0026)
2.1956 10800 2.0543 2.0754 0.4374 (-0.1030) 0.3586 (+0.0336) 0.5347 (+0.0341) 0.4436 (-0.0118)
2.2159 10900 2.0636 2.0762 0.4296 (-0.1109) 0.3473 (+0.0222) 0.5240 (+0.0234) 0.4336 (-0.0218)
2.2362 11000 2.0584 2.0762 0.4410 (-0.0995) 0.3428 (+0.0177) 0.5112 (+0.0105) 0.4316 (-0.0237)
2.2566 11100 2.0562 2.0756 0.4393 (-0.1011) 0.3392 (+0.0142) 0.5114 (+0.0108) 0.4300 (-0.0254)
2.2769 11200 2.0563 2.0776 0.4329 (-0.1075) 0.3552 (+0.0301) 0.5034 (+0.0027) 0.4305 (-0.0249)
2.2972 11300 2.0534 2.0762 0.4060 (-0.1345) 0.3490 (+0.0240) 0.5336 (+0.0330) 0.4295 (-0.0258)
2.3175 11400 2.0626 2.0769 0.4111 (-0.1293) 0.3346 (+0.0095) 0.5408 (+0.0402) 0.4288 (-0.0266)
2.3379 11500 2.0621 2.0764 0.4310 (-0.1094) 0.3317 (+0.0067) 0.5368 (+0.0361) 0.4332 (-0.0222)
2.3582 11600 2.0647 2.0765 0.4479 (-0.0925) 0.3271 (+0.0021) 0.5405 (+0.0398) 0.4385 (-0.0169)
2.3785 11700 2.0625 2.0767 0.4282 (-0.1122) 0.3414 (+0.0164) 0.5072 (+0.0066) 0.4256 (-0.0298)
2.3989 11800 2.054 2.0778 0.4244 (-0.1160) 0.3420 (+0.0170) 0.5139 (+0.0133) 0.4268 (-0.0286)
2.4192 11900 2.0559 2.0756 0.4251 (-0.1153) 0.3303 (+0.0053) 0.5061 (+0.0055) 0.4205 (-0.0349)
2.4395 12000 2.0612 2.0758 0.4456 (-0.0948) 0.3406 (+0.0155) 0.5353 (+0.0347) 0.4405 (-0.0149)
2.4598 12100 2.0574 2.0770 0.4485 (-0.0919) 0.3359 (+0.0109) 0.5220 (+0.0214) 0.4355 (-0.0199)
2.4802 12200 2.0598 2.0751 0.4582 (-0.0823) 0.3468 (+0.0218) 0.5405 (+0.0398) 0.4485 (-0.0069)
2.5005 12300 2.0578 2.0764 0.4600 (-0.0804) 0.3446 (+0.0195) 0.5276 (+0.0270) 0.4441 (-0.0113)
2.5208 12400 2.0493 2.0759 0.4580 (-0.0824) 0.3220 (-0.0030) 0.5147 (+0.0140) 0.4316 (-0.0238)
2.5412 12500 2.0574 2.0767 0.4741 (-0.0663) 0.3381 (+0.0131) 0.5110 (+0.0104) 0.4411 (-0.0143)
2.5615 12600 2.0598 2.0768 0.4541 (-0.0863) 0.3234 (-0.0016) 0.5136 (+0.0129) 0.4304 (-0.0250)
2.5818 12700 2.0715 2.0763 0.4693 (-0.0711) 0.3467 (+0.0217) 0.5193 (+0.0187) 0.4451 (-0.0103)
2.6022 12800 2.0566 2.0763 0.4747 (-0.0657) 0.3480 (+0.0230) 0.5208 (+0.0202) 0.4478 (-0.0075)
2.6225 12900 2.0607 2.0761 0.4511 (-0.0894) 0.3319 (+0.0069) 0.4955 (-0.0051) 0.4262 (-0.0292)
2.6428 13000 2.0574 2.0752 0.4574 (-0.0831) 0.3564 (+0.0313) 0.4903 (-0.0104) 0.4347 (-0.0207)
2.6631 13100 2.0625 2.0772 0.4609 (-0.0796) 0.3451 (+0.0201) 0.5293 (+0.0287) 0.4451 (-0.0103)
2.6835 13200 2.054 2.0770 0.4526 (-0.0878) 0.3378 (+0.0128) 0.5307 (+0.0300) 0.4404 (-0.0150)
2.7038 13300 2.0601 2.0769 0.4493 (-0.0912) 0.3382 (+0.0132) 0.5327 (+0.0320) 0.4400 (-0.0153)
2.7241 13400 2.0557 2.0758 0.4387 (-0.1018) 0.3422 (+0.0171) 0.5319 (+0.0312) 0.4376 (-0.0178)
2.7445 13500 2.0509 2.0770 0.4426 (-0.0978) 0.3303 (+0.0053) 0.4979 (-0.0028) 0.4236 (-0.0318)
2.7648 13600 2.0502 2.0769 0.4530 (-0.0874) 0.3406 (+0.0156) 0.5257 (+0.0250) 0.4398 (-0.0156)
2.7851 13700 2.0585 2.0760 0.4333 (-0.1072) 0.3447 (+0.0196) 0.5122 (+0.0116) 0.4300 (-0.0253)
2.8054 13800 2.0602 2.0761 0.4400 (-0.1004) 0.3388 (+0.0138) 0.5119 (+0.0113) 0.4303 (-0.0251)
2.8258 13900 2.0523 2.0782 0.4115 (-0.1289) 0.3512 (+0.0261) 0.5118 (+0.0111) 0.4248 (-0.0305)
2.8461 14000 2.0546 2.0771 0.4530 (-0.0874) 0.3560 (+0.0309) 0.5273 (+0.0267) 0.4454 (-0.0099)
2.8664 14100 2.0515 2.0764 0.4159 (-0.1245) 0.3488 (+0.0238) 0.5244 (+0.0238) 0.4297 (-0.0257)
2.8868 14200 2.0548 2.0757 0.4290 (-0.1115) 0.3576 (+0.0326) 0.5564 (+0.0558) 0.4477 (-0.0077)
2.9071 14300 2.0531 2.0759 0.4341 (-0.1063) 0.3574 (+0.0323) 0.5224 (+0.0218) 0.4380 (-0.0174)
2.9274 14400 2.0682 2.0766 0.4335 (-0.1069) 0.3535 (+0.0285) 0.5039 (+0.0032) 0.4303 (-0.0251)
2.9478 14500 2.0547 2.0769 0.4308 (-0.1096) 0.3521 (+0.0271) 0.4970 (-0.0037) 0.4266 (-0.0287)
2.9681 14600 2.0563 2.0751 0.4190 (-0.1214) 0.3396 (+0.0145) 0.4882 (-0.0124) 0.4156 (-0.0398)
2.9884 14700 2.0611 2.0767 0.4186 (-0.1219) 0.3486 (+0.0236) 0.5440 (+0.0434) 0.4371 (-0.0183)
3.0087 14800 2.0523 2.0781 0.4008 (-0.1396) 0.3537 (+0.0286) 0.4994 (-0.0013) 0.4179 (-0.0374)
3.0291 14900 2.0472 2.0788 0.3772 (-0.1633) 0.3552 (+0.0301) 0.5034 (+0.0028) 0.4119 (-0.0434)
3.0494 15000 2.0432 2.0790 0.4011 (-0.1393) 0.3429 (+0.0178) 0.4759 (-0.0247) 0.4066 (-0.0487)
3.0697 15100 2.041 2.0807 0.3915 (-0.1489) 0.3361 (+0.0111) 0.4776 (-0.0230) 0.4018 (-0.0536)
3.0901 15200 2.0505 2.0820 0.3796 (-0.1609) 0.3365 (+0.0115) 0.5330 (+0.0323) 0.4163 (-0.0390)
3.1104 15300 2.0542 2.0816 0.3552 (-0.1852) 0.3331 (+0.0081) 0.4838 (-0.0168) 0.3907 (-0.0646)
3.1307 15400 2.0346 2.0796 0.3655 (-0.1749) 0.3405 (+0.0154) 0.4532 (-0.0474) 0.3864 (-0.0690)
3.1510 15500 2.0384 2.0810 0.3707 (-0.1697) 0.3496 (+0.0246) 0.4960 (-0.0046) 0.4054 (-0.0499)
3.1714 15600 2.0481 2.0800 0.3712 (-0.1692) 0.3249 (-0.0002) 0.4778 (-0.0229) 0.3913 (-0.0641)
3.1917 15700 2.0423 2.0804 0.4017 (-0.1387) 0.3351 (+0.0100) 0.4836 (-0.0171) 0.4068 (-0.0486)
3.2120 15800 2.0428 2.0811 0.3726 (-0.1678) 0.3299 (+0.0049) 0.4817 (-0.0190) 0.3948 (-0.0606)
3.2324 15900 2.04 2.0792 0.3549 (-0.1855) 0.3298 (+0.0048) 0.4805 (-0.0201) 0.3884 (-0.0670)
3.2527 16000 2.0401 2.0810 0.3865 (-0.1539) 0.3375 (+0.0125) 0.4841 (-0.0165) 0.4027 (-0.0526)
3.2730 16100 2.049 2.0807 0.3778 (-0.1626) 0.3410 (+0.0159) 0.4833 (-0.0173) 0.4007 (-0.0547)
3.2934 16200 2.0434 2.0801 0.3910 (-0.1494) 0.3415 (+0.0165) 0.4817 (-0.0189) 0.4048 (-0.0506)
3.3137 16300 2.0478 2.0795 0.3813 (-0.1592) 0.3448 (+0.0198) 0.4504 (-0.0503) 0.3921 (-0.0632)
3.3340 16400 2.0405 2.0803 0.3730 (-0.1674) 0.3376 (+0.0126) 0.4523 (-0.0484) 0.3876 (-0.0677)
3.3543 16500 2.0416 2.0799 0.3515 (-0.1889) 0.3478 (+0.0228) 0.4594 (-0.0412) 0.3863 (-0.0691)
3.3747 16600 2.0511 2.0814 0.3559 (-0.1846) 0.3309 (+0.0059) 0.4547 (-0.0460) 0.3805 (-0.0749)
3.3950 16700 2.0449 2.0808 0.3683 (-0.1721) 0.3321 (+0.0070) 0.4841 (-0.0166) 0.3948 (-0.0606)
3.4153 16800 2.0442 2.0817 0.3908 (-0.1497) 0.3318 (+0.0067) 0.4735 (-0.0272) 0.3987 (-0.0567)
3.4357 16900 2.0436 2.0806 0.4016 (-0.1388) 0.3215 (-0.0035) 0.4638 (-0.0368) 0.3957 (-0.0597)
3.4560 17000 2.0542 2.0803 0.3913 (-0.1491) 0.3333 (+0.0082) 0.4499 (-0.0507) 0.3915 (-0.0639)
3.4763 17100 2.0527 2.0802 0.3967 (-0.1437) 0.3430 (+0.0179) 0.4714 (-0.0292) 0.4037 (-0.0517)
3.4966 17200 2.0435 2.0801 0.3727 (-0.1678) 0.3320 (+0.0069) 0.4553 (-0.0454) 0.3866 (-0.0687)
3.5170 17300 2.0449 2.0798 0.3930 (-0.1474) 0.3325 (+0.0075) 0.4417 (-0.0590) 0.3891 (-0.0663)
3.5373 17400 2.0527 2.0796 0.3849 (-0.1555) 0.3438 (+0.0188) 0.4356 (-0.0651) 0.3881 (-0.0673)
3.5576 17500 2.0492 2.0814 0.4077 (-0.1327) 0.3351 (+0.0100) 0.4579 (-0.0427) 0.4002 (-0.0551)
3.5780 17600 2.0472 2.0803 0.4048 (-0.1356) 0.3323 (+0.0073) 0.4294 (-0.0713) 0.3888 (-0.0665)
3.5983 17700 2.0484 2.0801 0.3831 (-0.1573) 0.3271 (+0.0020) 0.4581 (-0.0426) 0.3894 (-0.0660)
3.6186 17800 2.0529 2.0794 0.3879 (-0.1525) 0.3381 (+0.0130) 0.4335 (-0.0672) 0.3865 (-0.0689)
3.6390 17900 2.0402 2.0810 0.3675 (-0.1729) 0.3263 (+0.0013) 0.4520 (-0.0486) 0.3819 (-0.0734)
3.6593 18000 2.0498 2.0788 0.3902 (-0.1503) 0.3411 (+0.0161) 0.3960 (-0.1046) 0.3758 (-0.0796)
3.6796 18100 2.048 2.0807 0.3882 (-0.1523) 0.3259 (+0.0008) 0.4099 (-0.0907) 0.3746 (-0.0807)
3.6999 18200 2.0464 2.0797 0.3804 (-0.1601) 0.3259 (+0.0009) 0.4418 (-0.0589) 0.3827 (-0.0727)
3.7203 18300 2.0503 2.0816 0.3630 (-0.1774) 0.3278 (+0.0028) 0.4371 (-0.0635) 0.3760 (-0.0794)
3.7406 18400 2.0401 2.0805 0.3580 (-0.1824) 0.3216 (-0.0035) 0.4336 (-0.0670) 0.3711 (-0.0843)
3.7609 18500 2.0383 2.0820 0.3589 (-0.1816) 0.3269 (+0.0019) 0.4634 (-0.0373) 0.3831 (-0.0723)
3.7813 18600 2.0454 2.0801 0.3806 (-0.1598) 0.3215 (-0.0036) 0.4354 (-0.0652) 0.3792 (-0.0762)
3.8016 18700 2.0457 2.0811 0.3678 (-0.1727) 0.3135 (-0.0116) 0.4221 (-0.0785) 0.3678 (-0.0876)
3.8219 18800 2.0449 2.0813 0.3762 (-0.1642) 0.3113 (-0.0137) 0.4399 (-0.0608) 0.3758 (-0.0796)
3.8422 18900 2.0451 2.0797 0.3705 (-0.1699) 0.3155 (-0.0095) 0.4345 (-0.0662) 0.3735 (-0.0819)
3.8626 19000 2.045 2.0802 0.3937 (-0.1467) 0.3086 (-0.0164) 0.4491 (-0.0516) 0.3838 (-0.0716)
3.8829 19100 2.0551 2.0801 0.3814 (-0.1590) 0.3164 (-0.0087) 0.4643 (-0.0363) 0.3874 (-0.0680)
3.9032 19200 2.0368 2.0795 0.3833 (-0.1571) 0.3175 (-0.0076) 0.4464 (-0.0542) 0.3824 (-0.0730)
3.9236 19300 2.046 2.0798 0.3885 (-0.1519) 0.3074 (-0.0177) 0.4416 (-0.0590) 0.3792 (-0.0762)
3.9439 19400 2.0507 2.0802 0.3913 (-0.1491) 0.3150 (-0.0100) 0.4341 (-0.0665) 0.3801 (-0.0752)
3.9642 19500 2.0555 2.0811 0.3892 (-0.1513) 0.3141 (-0.0109) 0.4466 (-0.0540) 0.3833 (-0.0721)
3.9845 19600 2.0433 2.0810 0.3827 (-0.1577) 0.3124 (-0.0126) 0.4482 (-0.0525) 0.3811 (-0.0743)
4.0049 19700 2.0403 2.0836 0.4009 (-0.1396) 0.3096 (-0.0154) 0.4474 (-0.0532) 0.3860 (-0.0694)
4.0252 19800 2.0413 2.0828 0.3905 (-0.1499) 0.3221 (-0.0030) 0.4009 (-0.0998) 0.3712 (-0.0842)
4.0455 19900 2.0321 2.0827 0.3910 (-0.1494) 0.3286 (+0.0035) 0.4228 (-0.0778) 0.3808 (-0.0746)
4.0659 20000 2.0293 2.0832 0.3854 (-0.1550) 0.3256 (+0.0006) 0.4328 (-0.0679) 0.3813 (-0.0741)
4.0862 20100 2.0347 2.0832 0.3677 (-0.1727) 0.3254 (+0.0003) 0.4106 (-0.0900) 0.3679 (-0.0875)
4.1065 20200 2.0377 2.0843 0.3814 (-0.1590) 0.3097 (-0.0154) 0.4060 (-0.0947) 0.3657 (-0.0897)
4.1269 20300 2.0335 2.0832 0.3756 (-0.1648) 0.3149 (-0.0101) 0.3943 (-0.1063) 0.3616 (-0.0937)
4.1472 20400 2.0417 2.0828 0.3596 (-0.1808) 0.3171 (-0.0080) 0.3837 (-0.1170) 0.3535 (-0.1019)
4.1675 20500 2.0369 2.0829 0.3665 (-0.1739) 0.3166 (-0.0084) 0.3854 (-0.1152) 0.3562 (-0.0992)
4.1878 20600 2.0362 2.0849 0.3731 (-0.1673) 0.3201 (-0.0049) 0.4080 (-0.0927) 0.3671 (-0.0883)
4.2082 20700 2.0323 2.0836 0.3580 (-0.1824) 0.3278 (+0.0027) 0.3857 (-0.1149) 0.3572 (-0.0982)
4.2285 20800 2.0383 2.0850 0.3620 (-0.1784) 0.3230 (-0.0021) 0.4202 (-0.0804) 0.3684 (-0.0870)
4.2488 20900 2.0286 2.0844 0.3646 (-0.1759) 0.3286 (+0.0036) 0.4114 (-0.0893) 0.3682 (-0.0872)
4.2692 21000 2.0305 2.0839 0.3681 (-0.1723) 0.3274 (+0.0023) 0.4230 (-0.0776) 0.3729 (-0.0825)
4.2895 21100 2.0381 2.0835 0.3720 (-0.1684) 0.3228 (-0.0023) 0.4009 (-0.0998) 0.3652 (-0.0902)
4.3098 21200 2.036 2.0837 0.3654 (-0.1750) 0.3177 (-0.0074) 0.4037 (-0.0969) 0.3622 (-0.0931)
4.3301 21300 2.0409 2.0843 0.3596 (-0.1808) 0.3207 (-0.0044) 0.4013 (-0.0993) 0.3605 (-0.0948)
4.3505 21400 2.0454 2.0842 0.3745 (-0.1659) 0.3199 (-0.0051) 0.4009 (-0.0997) 0.3651 (-0.0902)
4.3708 21500 2.0349 2.0839 0.3685 (-0.1720) 0.3237 (-0.0013) 0.3973 (-0.1033) 0.3632 (-0.0922)
4.3911 21600 2.0437 2.0832 0.3719 (-0.1685) 0.3228 (-0.0022) 0.4007 (-0.1000) 0.3651 (-0.0902)
4.4115 21700 2.034 2.0838 0.3768 (-0.1636) 0.3313 (+0.0063) 0.4150 (-0.0857) 0.3744 (-0.0810)
4.4318 21800 2.0308 2.0837 0.3719 (-0.1685) 0.3264 (+0.0014) 0.4148 (-0.0858) 0.3711 (-0.0843)
4.4521 21900 2.0427 2.0847 0.3695 (-0.1709) 0.3210 (-0.0040) 0.4038 (-0.0968) 0.3648 (-0.0906)
4.4725 22000 2.034 2.0845 0.3745 (-0.1659) 0.3207 (-0.0043) 0.3993 (-0.1013) 0.3648 (-0.0905)
4.4928 22100 2.0393 2.0827 0.3685 (-0.1719) 0.3208 (-0.0042) 0.3833 (-0.1173) 0.3576 (-0.0978)
4.5131 22200 2.0426 2.0834 0.3743 (-0.1661) 0.3167 (-0.0084) 0.4092 (-0.0914) 0.3667 (-0.0887)
4.5334 22300 2.0323 2.0839 0.3595 (-0.1809) 0.3165 (-0.0086) 0.3945 (-0.1061) 0.3568 (-0.0985)
4.5538 22400 2.0361 2.0834 0.3695 (-0.1709) 0.3190 (-0.0061) 0.4070 (-0.0937) 0.3652 (-0.0902)
4.5741 22500 2.0424 2.0838 0.3448 (-0.1957) 0.3169 (-0.0081) 0.3964 (-0.1043) 0.3527 (-0.1027)
4.5944 22600 2.038 2.0833 0.3617 (-0.1787) 0.3170 (-0.0081) 0.3965 (-0.1041) 0.3584 (-0.0970)
4.6148 22700 2.0406 2.0833 0.3707 (-0.1697) 0.3188 (-0.0063) 0.4003 (-0.1003) 0.3633 (-0.0921)
4.6351 22800 2.0396 2.0831 0.3710 (-0.1694) 0.3206 (-0.0044) 0.4028 (-0.0978) 0.3648 (-0.0905)
4.6554 22900 2.0362 2.0839 0.3639 (-0.1766) 0.3210 (-0.0040) 0.3956 (-0.1050) 0.3602 (-0.0952)
4.6757 23000 2.0508 2.0838 0.3545 (-0.1859) 0.3205 (-0.0045) 0.4059 (-0.0948) 0.3603 (-0.0951)
4.6961 23100 2.0443 2.0840 0.3719 (-0.1685) 0.3198 (-0.0052) 0.3937 (-0.1069) 0.3618 (-0.0936)
4.7164 23200 2.0316 2.0837 0.3773 (-0.1631) 0.3199 (-0.0051) 0.3951 (-0.1056) 0.3641 (-0.0913)
4.7367 23300 2.0444 2.0844 0.3749 (-0.1655) 0.3179 (-0.0072) 0.4029 (-0.0977) 0.3652 (-0.0901)
4.7571 23400 2.0464 2.0838 0.3596 (-0.1808) 0.3167 (-0.0083) 0.4037 (-0.0969) 0.3600 (-0.0953)
4.7774 23500 2.0297 2.0841 0.3694 (-0.1710) 0.3165 (-0.0086) 0.4087 (-0.0919) 0.3649 (-0.0905)
4.7977 23600 2.0305 2.0838 0.3628 (-0.1777) 0.3192 (-0.0058) 0.4024 (-0.0983) 0.3615 (-0.0939)
4.8181 23700 2.0421 2.0839 0.3559 (-0.1845) 0.3185 (-0.0065) 0.3963 (-0.1043) 0.3569 (-0.0984)
4.8384 23800 2.0331 2.0843 0.3645 (-0.1759) 0.3176 (-0.0074) 0.4027 (-0.0979) 0.3616 (-0.0937)
4.8587 23900 2.0331 2.0840 0.3628 (-0.1776) 0.3184 (-0.0067) 0.4042 (-0.0964) 0.3618 (-0.0936)
4.8790 24000 2.0361 2.0838 0.3623 (-0.1782) 0.3171 (-0.0080) 0.4024 (-0.0982) 0.3606 (-0.0948)
4.8994 24100 2.029 2.0842 0.3628 (-0.1777) 0.3192 (-0.0058) 0.4028 (-0.0979) 0.3616 (-0.0938)
4.9197 24200 2.0257 2.0844 0.3642 (-0.1763) 0.3224 (-0.0027) 0.3956 (-0.1050) 0.3607 (-0.0947)
4.9400 24300 2.0298 2.0842 0.3685 (-0.1719) 0.3193 (-0.0057) 0.3964 (-0.1043) 0.3614 (-0.0939)
4.9604 24400 2.0412 2.0841 0.3663 (-0.1742) 0.3161 (-0.0090) 0.4009 (-0.0997) 0.3611 (-0.0943)
4.9807 24500 2.0376 2.0840 0.3636 (-0.1768) 0.3156 (-0.0095) 0.4008 (-0.0998) 0.3600 (-0.0954)
-1 -1 - - 0.5348 (-0.0056) 0.3376 (+0.0126) 0.5534 (+0.0528) 0.4753 (+0.0199)
  • The bold row denotes the saved checkpoint.

Framework Versions

  • Python: 3.10.18
  • Sentence Transformers: 5.0.0
  • Transformers: 4.56.0.dev0
  • PyTorch: 2.7.1+cu126
  • Accelerate: 1.9.0
  • Datasets: 4.0.0
  • Tokenizers: 0.21.4

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}
}
Downloads last month
3
Safetensors
Model size
32M params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for rahulseetharaman/reranker-msmarco-v1.1-ettin-encoder-32m-listnet

Finetuned
(8)
this model

Dataset used to train rahulseetharaman/reranker-msmarco-v1.1-ettin-encoder-32m-listnet

Evaluation results