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

This is a Cross Encoder model finetuned from jhu-clsp/ettin-encoder-150m on the msmarco 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: 512 tokens
Number of Output Labels: 1 label
Training Dataset:
- msmarco
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("tomaarsen/ms-marco-ettin-150m-reranker")
# Get scores for pairs of texts
pairs = [
    ['which constitutional amendment required that u.s. senators be directly elected by the people instead of being chosen by state legislatures?', 'Full text of the Constitution and Amendments. The Seventeenth Amendment (Amendment XVII) to the United States Constitution established the popular election of United States Senators by the people of the states. The amendment supersedes Article I, Â§3, Clauses 1 and 2 of the Constitution, under which senators were elected by state legislatures. It also alters the procedure for filling vacancies in the Senate, allowing for state legislatures to permit their governors to make temporary appointments until a special election can be held.'],
    ['where is the tigris river?', 'The Tigris is one of the two main rivers of Mesopotamia (modern Iraq). The Tigris is the river to the east (towards Persia [modern Iran]); the Euphrates, to the west. The Tigris runs from Lake Hazar, in the Taurus Mountains, in Turkey, joins the Euphrates, and flows into the Persian Gulf. The Encyclopedia Britannica says the Tigris is 1,180 miles (1,900 km) in length.'],
    ['what tectonic plate is japan on', 'Japan lies over 4 tectonic plates. These are: The North American Plate The Eurasian Plate The Philippine Sea Plate The Pacific Plate.+ 5 others found this useful.Nathaniel Preece.apan lies on the North American, Eurasian and Pacific plates, and is close to the Phillipine plate. Tokyo and Sendai, for example are on the North American plate.'],
    ['how many seasons of portlandia are there', 'We monitor the news to keep you updated on the release date of Portlandia season 7. To the delight of the fans, IFC has officially renewed the series. The release date has not been scheduled yet. If you want to get automatically notified of the showâ\x80\x99s premiere date, please, sign up for updates below.'],
    ['how to delete messenger messages from iphone', 'Tap the Facebook Messengerâ\x80\x9d application and select Messages tab. 2. Locate the message or messages that you wish to delete. Press and hold on the message until a list of options displays, including the option to delete or copy the message. 3. Choose the Delete tab, not the Archive tab. If you wish to permanently delete Facebook messages, tap the Delete option.'],
]
scores = model.predict(pairs)
print(scores.shape)
# (5,)

# Or rank different texts based on similarity to a single text
ranks = model.rank(
    'which constitutional amendment required that u.s. senators be directly elected by the people instead of being chosen by state legislatures?',
    [
        'Full text of the Constitution and Amendments. The Seventeenth Amendment (Amendment XVII) to the United States Constitution established the popular election of United States Senators by the people of the states. The amendment supersedes Article I, Â§3, Clauses 1 and 2 of the Constitution, under which senators were elected by state legislatures. It also alters the procedure for filling vacancies in the Senate, allowing for state legislatures to permit their governors to make temporary appointments until a special election can be held.',
        'The Tigris is one of the two main rivers of Mesopotamia (modern Iraq). The Tigris is the river to the east (towards Persia [modern Iran]); the Euphrates, to the west. The Tigris runs from Lake Hazar, in the Taurus Mountains, in Turkey, joins the Euphrates, and flows into the Persian Gulf. The Encyclopedia Britannica says the Tigris is 1,180 miles (1,900 km) in length.',
        'Japan lies over 4 tectonic plates. These are: The North American Plate The Eurasian Plate The Philippine Sea Plate The Pacific Plate.+ 5 others found this useful.Nathaniel Preece.apan lies on the North American, Eurasian and Pacific plates, and is close to the Phillipine plate. Tokyo and Sendai, for example are on the North American plate.',
        'We monitor the news to keep you updated on the release date of Portlandia season 7. To the delight of the fans, IFC has officially renewed the series. The release date has not been scheduled yet. If you want to get automatically notified of the showâ\x80\x99s premiere date, please, sign up for updates below.',
        'Tap the Facebook Messengerâ\x80\x9d application and select Messages tab. 2. Locate the message or messages that you wish to delete. Press and hold on the message until a list of options displays, including the option to delete or copy the message. 3. Choose the Delete tab, not the Archive tab. If you wish to permanently delete Facebook messages, tap the Delete option.',
    ]
)
# [{'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	0.6522 (+0.1627)	0.3763 (+0.1153)	0.7584 (+0.3388)
mrr@10	0.6477 (+0.1702)	0.6256 (+0.1258)	0.7881 (+0.3614)
ndcg@10	0.7180 (+0.1776)	0.4451 (+0.1201)	0.8011 (+0.3005)

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	0.5957 (+0.2056)
mrr@10	0.6871 (+0.2191)
ndcg@10	0.6548 (+0.1994)

Training Details

Training Dataset

msmarco

Dataset: msmarco at 9e329ed
Size: 39,770,704 training samples
Columns: query_id, positive_id, negative_id, and score

Approximate statistics based on the first 1000 samples:

	query_id	positive_id	negative_id	score
type	string	string	string	float
details	min: 10 characters mean: 34.72 characters max: 108 characters	min: 71 characters mean: 351.58 characters max: 919 characters	min: 81 characters mean: 344.41 characters max: 992 characters	min: -1.0 mean: 13.5 max: 22.59

Samples:

query_id	positive_id	negative_id	score
`where is jade city bc`	Jade City, British Columbia. From Wikipedia, the free encyclopedia. Jade City is a spot on the road in northwestern British Columbia, Canada, near the Yukon, located on Highway 37, west of Good Hope Lake and close to Cassiar, in the Cassiar Highlands.The region around Jade City is rich with serpentinite (a jade precursor), greenstone (jade look-a-likes), and jade.ade City is by road about 24 hours north of Vancouver, and 1 hour south of the Yukon border. As of 2015, it has a population of about 30 people. Jade City is a very small town.	`China. Few gems have the mystique of jade, a stone that has been revered in China for more than 4000 years. Jade is also one of the most misunderstood of gems -- there is widespread confusion about the types of jade, about the most valuable colors, and the standards used to grade it.`	`15.705843766530355`
`is asparagus good for your kidneys`	`Is Asparagus Good For Your Kidneys? Those who want to keep their kidneys functioning properly will definitely want to include certain foods in their diet, including asparagus. This particular vegetable is able to sooth the urinary system as well as increase urine production and support kidney function overall. Some of the different properties that asparagus has which makes it good for the kidneys includes asparagin, glycosides, glycolic acid, tyrosin, vitamin A, B, C, E and folic acid.`	Last year, I planted 20 asparagus crowns and only had 1 fern over the entire year. This year, I read a lot of articles on planting asparagus and decided to follow a recommendation to soak the crowns in luke warm water for 30 minutes before planting.reat article! Last year, I planted 20 asparagus crowns and only had 1 fern over the entire year. This year, I read a lot of articles on planting asparagus and decided to follow a recommendation to soak the crowns in luke warm water for 30 minutes before planting. Success! I now have ferns along the entire row!	`21.735484917958576`
`what does a urine culture tell you`	`A urine culture is a test to find germs (such as bacteria) in the urine that can cause an infection. Urine in the bladder is normally sterile. This means it does not contain any bacteria or other organisms (such as fungi). But bacteria can enter the urethra and cause a urinary tract infection (UTI).`	`What Is The Procedure To Conduct A Urine Culture Test? Urine culture refers to a urine test that is conducted to find bacteria that could cause a urinary tract infection. Bladder urine is supposed to be sterile and devoid of any bacteria or fungi, but sometimes bacteria enters the urine through the urethra, causing a urinary infection.`	`1.1982590357462568`

Loss: MarginMSELoss with these parameters:

{
    "activation_fn": "torch.nn.modules.linear.Identity"
}

Evaluation Dataset

msmarco

Dataset: msmarco at 9e329ed
Size: 10,000 evaluation samples
Columns: query_id, positive_id, negative_id, and score

Approximate statistics based on the first 1000 samples:

	query_id	positive_id	negative_id	score
type	string	string	string	float
details	min: 8 characters mean: 34.72 characters max: 169 characters	min: 65 characters mean: 356.17 characters max: 968 characters	min: 36 characters mean: 340.3 characters max: 982 characters	min: -2.7 mean: 13.48 max: 22.44

Samples:

query_id	positive_id	negative_id	score
`which constitutional amendment required that u.s. senators be directly elected by the people instead of being chosen by state legislatures?`	Full text of the Constitution and Amendments. The Seventeenth Amendment (Amendment XVII) to the United States Constitution established the popular election of United States Senators by the people of the states. The amendment supersedes Article I, Â§3, Clauses 1 and 2 of the Constitution, under which senators were elected by state legislatures. It also alters the procedure for filling vacancies in the Senate, allowing for state legislatures to permit their governors to make temporary appointments until a special election can be held.	`Explanation: The original text of the Constitution called for the election of a state s senators to be dome by the state s legislature. This was changed in the 17th amendment that called for Senators to be elected directly by the people of the states.`	`-0.32251540819803814`
`where is the tigris river?`	`The Tigris is one of the two main rivers of Mesopotamia (modern Iraq). The Tigris is the river to the east (towards Persia [modern Iran]); the Euphrates, to the west. The Tigris runs from Lake Hazar, in the Taurus Mountains, in Turkey, joins the Euphrates, and flows into the Persian Gulf. The Encyclopedia Britannica says the Tigris is 1,180 miles (1,900 km) in length.`	The oldest known civilization in South America, as well as in the Western Hemisphere as a whole, the Norte Chico civilization-c. 3200 BC - 1800 BC-comprised several interconnected settlements on the Peruvian coast, including the urban centers at Aspero and Caral.he civilizations that emerged around these rivers are among the earliest known non-nomadic agrarian societies. Because Ubaid, Sumer, Akkad, Assyria and Babylon civilizations all emerged around the Tigris-Euphrates, the theory that Mesopotamia is the cradle of civilization is widely accepted.	`12.891789237658184`
`what tectonic plate is japan on`	`Japan lies over 4 tectonic plates. These are: The North American Plate The Eurasian Plate The Philippine Sea Plate The Pacific Plate.+ 5 others found this useful.Nathaniel Preece.apan lies on the North American, Eurasian and Pacific plates, and is close to the Phillipine plate. Tokyo and Sendai, for example are on the North American plate.`	`History[edit] In the past two decades the steel plate shear wall (SPSW), also known as the steel plate wall (SPW), has been used in a number of buildings in Japan and North America as part of the lateral force resisting system.`	`12.691253264745075`

Loss: MarginMSELoss with these parameters:

{
    "activation_fn": "torch.nn.modules.linear.Identity"
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 128
per_device_eval_batch_size: 128
learning_rate: 2e-05
num_train_epochs: 1
warmup_ratio: 0.1
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: 128
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: 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: 1
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.1
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
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: 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}
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: 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: 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	NanoMSMARCO_R100_ndcg@10	NanoNFCorpus_R100_ndcg@10	NanoNQ_R100_ndcg@10	NanoBEIR_R100_mean_ndcg@10
-1	-1	-	-	0.0321 (-0.5083)	0.1979 (-0.1271)	0.0227 (-0.4780)	0.0842 (-0.3711)
0.0000	1	207.4745	-	-	-	-	-
0.0020	78	208.2147	-	-	-	-	-
0.0040	156	206.6548	-	-	-	-	-
0.0060	234	200.7388	-	-	-	-	-
0.0080	312	182.4953	-	-	-	-	-
0.0100	389	-	75.3840	0.3932 (-0.1472)	0.2493 (-0.0758)	0.4066 (-0.0940)	0.3497 (-0.1057)
0.0100	390	130.2694	-	-	-	-	-
0.0121	468	43.6472	-	-	-	-	-
0.0141	546	24.7341	-	-	-	-	-
0.0161	624	18.6241	-	-	-	-	-
0.0181	702	15.3865	-	-	-	-	-
0.0200	778	-	12.5421	0.6049 (+0.0645)	0.3811 (+0.0561)	0.6413 (+0.1406)	0.5424 (+0.0871)
0.0201	780	13.24	-	-	-	-	-
0.0221	858	11.5539	-	-	-	-	-
0.0241	936	10.4097	-	-	-	-	-
0.0261	1014	9.5802	-	-	-	-	-
0.0281	1092	8.8313	-	-	-	-	-
0.0300	1167	-	8.2054	0.6507 (+0.1103)	0.3997 (+0.0746)	0.7045 (+0.2039)	0.5850 (+0.1296)
0.0301	1170	8.3729	-	-	-	-	-
0.0321	1248	7.8437	-	-	-	-	-
0.0341	1326	7.4383	-	-	-	-	-
0.0362	1404	6.9899	-	-	-	-	-
0.0382	1482	6.7353	-	-	-	-	-
0.0401	1556	-	6.4089	0.6421 (+0.1016)	0.4112 (+0.0861)	0.7289 (+0.2283)	0.5941 (+0.1387)
0.0402	1560	6.4088	-	-	-	-	-
0.0422	1638	6.1957	-	-	-	-	-
0.0442	1716	6.0008	-	-	-	-	-
0.0462	1794	5.7517	-	-	-	-	-
0.0482	1872	5.5172	-	-	-	-	-
0.0501	1945	-	5.5248	0.6704 (+0.1300)	0.4163 (+0.0913)	0.7344 (+0.2337)	0.6070 (+0.1517)
0.0502	1950	5.38	-	-	-	-	-
0.0522	2028	5.3785	-	-	-	-	-
0.0542	2106	5.1515	-	-	-	-	-
0.0562	2184	5.0263	-	-	-	-	-
0.0582	2262	4.9028	-	-	-	-	-
0.0601	2334	-	4.8510	0.6637 (+0.1233)	0.4187 (+0.0936)	0.7418 (+0.2412)	0.6081 (+0.1527)
0.0603	2340	4.8283	-	-	-	-	-
0.0623	2418	4.6962	-	-	-	-	-
0.0643	2496	4.6482	-	-	-	-	-
0.0663	2574	4.5224	-	-	-	-	-
0.0683	2652	4.4137	-	-	-	-	-
0.0701	2723	-	4.4682	0.6785 (+0.1381)	0.4142 (+0.0892)	0.7679 (+0.2672)	0.6202 (+0.1648)
0.0703	2730	4.3639	-	-	-	-	-
0.0723	2808	4.2902	-	-	-	-	-
0.0743	2886	4.2308	-	-	-	-	-
0.0763	2964	4.1607	-	-	-	-	-
0.0783	3042	4.0809	-	-	-	-	-
0.0801	3112	-	3.9937	0.6766 (+0.1362)	0.4238 (+0.0988)	0.7817 (+0.2810)	0.6274 (+0.1720)
0.0803	3120	4.0516	-	-	-	-	-
0.0823	3198	3.9772	-	-	-	-	-
0.0844	3276	3.9662	-	-	-	-	-
0.0864	3354	3.8161	-	-	-	-	-
0.0884	3432	3.8557	-	-	-	-	-
0.0901	3501	-	3.9840	0.6680 (+0.1276)	0.4198 (+0.0947)	0.7710 (+0.2703)	0.6196 (+0.1642)
0.0904	3510	3.7875	-	-	-	-	-
0.0924	3588	3.7164	-	-	-	-	-
0.0944	3666	3.6808	-	-	-	-	-
0.0964	3744	3.6347	-	-	-	-	-
0.0984	3822	3.5847	-	-	-	-	-
0.1002	3890	-	3.6954	0.6761 (+0.1357)	0.4364 (+0.1114)	0.7863 (+0.2856)	0.6329 (+0.1776)
0.1004	3900	3.5902	-	-	-	-	-
0.1024	3978	3.509	-	-	-	-	-
0.1044	4056	3.5064	-	-	-	-	-
0.1064	4134	3.4219	-	-	-	-	-
0.1085	4212	3.366	-	-	-	-	-
0.1102	4279	-	3.3804	0.6863 (+0.1459)	0.4224 (+0.0973)	0.7947 (+0.2941)	0.6345 (+0.1791)
0.1105	4290	3.3347	-	-	-	-	-
0.1125	4368	3.3026	-	-	-	-	-
0.1145	4446	3.2498	-	-	-	-	-
0.1165	4524	3.255	-	-	-	-	-
0.1185	4602	3.1982	-	-	-	-	-
0.1202	4668	-	3.2256	0.7017 (+0.1613)	0.4293 (+0.1043)	0.7822 (+0.2816)	0.6377 (+0.1824)
0.1205	4680	3.1525	-	-	-	-	-
0.1225	4758	3.1405	-	-	-	-	-
0.1245	4836	3.0912	-	-	-	-	-
0.1265	4914	3.0559	-	-	-	-	-
0.1285	4992	3.0431	-	-	-	-	-
0.1302	5057	-	3.0894	0.6808 (+0.1404)	0.4356 (+0.1106)	0.7973 (+0.2967)	0.6379 (+0.1825)
0.1305	5070	3.0138	-	-	-	-	-
0.1326	5148	3.0115	-	-	-	-	-
0.1346	5226	2.9885	-	-	-	-	-
0.1366	5304	2.933	-	-	-	-	-
0.1386	5382	2.885	-	-	-	-	-
0.1402	5446	-	2.9048	0.7014 (+0.1610)	0.4382 (+0.1131)	0.7868 (+0.2861)	0.6421 (+0.1867)
0.1406	5460	2.8851	-	-	-	-	-
0.1426	5538	2.9002	-	-	-	-	-
0.1446	5616	2.8765	-	-	-	-	-
0.1466	5694	2.8202	-	-	-	-	-
0.1486	5772	2.847	-	-	-	-	-
0.1502	5835	-	2.9050	0.7169 (+0.1764)	0.4233 (+0.0983)	0.7844 (+0.2838)	0.6415 (+0.1862)
0.1506	5850	2.8285	-	-	-	-	-
0.1526	5928	2.7882	-	-	-	-	-
0.1546	6006	2.7507	-	-	-	-	-
0.1567	6084	2.7457	-	-	-	-	-
0.1587	6162	2.7313	-	-	-	-	-
0.1603	6224	-	2.7971	0.7180 (+0.1776)	0.4451 (+0.1201)	0.8011 (+0.3005)	0.6548 (+0.1994)
0.1607	6240	2.7239	-	-	-	-	-
0.1627	6318	2.6975	-	-	-	-	-
0.1647	6396	2.6854	-	-	-	-	-
0.1667	6474	2.6714	-	-	-	-	-
0.1687	6552	2.6476	-	-	-	-	-
0.1703	6613	-	2.6787	0.7106 (+0.1702)	0.4325 (+0.1075)	0.7970 (+0.2964)	0.6467 (+0.1914)
0.1707	6630	2.6565	-	-	-	-	-
0.1727	6708	2.5863	-	-	-	-	-
0.1747	6786	2.6027	-	-	-	-	-
0.1767	6864	2.606	-	-	-	-	-
0.1787	6942	2.5634	-	-	-	-	-
0.1803	7002	-	2.6158	0.7166 (+0.1762)	0.4361 (+0.1111)	0.7984 (+0.2977)	0.6504 (+0.1950)
0.1808	7020	2.548	-	-	-	-	-
0.1828	7098	2.5719	-	-	-	-	-
0.1848	7176	2.5375	-	-	-	-	-
0.1868	7254	2.5263	-	-	-	-	-
0.1888	7332	2.5312	-	-	-	-	-
0.1903	7391	-	2.5446	0.7002 (+0.1598)	0.4387 (+0.1137)	0.7865 (+0.2859)	0.6418 (+0.1864)
0.1908	7410	2.4945	-	-	-	-	-
0.1928	7488	2.4464	-	-	-	-	-
0.1948	7566	2.4738	-	-	-	-	-
0.1968	7644	2.4752	-	-	-	-	-
0.1988	7722	2.4583	-	-	-	-	-
0.2003	7780	-	2.4624	0.6970 (+0.1565)	0.4396 (+0.1145)	0.7976 (+0.2970)	0.6447 (+0.1893)
0.2008	7800	2.4284	-	-	-	-	-
0.2028	7878	2.4296	-	-	-	-	-
0.2049	7956	2.4268	-	-	-	-	-
0.2069	8034	2.4424	-	-	-	-	-
0.2089	8112	2.4084	-	-	-	-	-
0.2103	8169	-	2.4326	0.6985 (+0.1580)	0.4347 (+0.1097)	0.7968 (+0.2961)	0.6433 (+0.1879)
0.2109	8190	2.3929	-	-	-	-	-
0.2129	8268	2.3961	-	-	-	-	-
0.2149	8346	2.3766	-	-	-	-	-
0.2169	8424	2.3712	-	-	-	-	-
0.2189	8502	2.3447	-	-	-	-	-
0.2204	8558	-	2.3136	0.7005 (+0.1600)	0.4400 (+0.1149)	0.7844 (+0.2837)	0.6416 (+0.1862)
0.2209	8580	2.3248	-	-	-	-	-
0.2229	8658	2.3181	-	-	-	-	-
0.2249	8736	2.3264	-	-	-	-	-
0.2269	8814	2.3092	-	-	-	-	-
0.2290	8892	2.2868	-	-	-	-	-
0.2304	8947	-	2.3536	0.7082 (+0.1678)	0.4401 (+0.1150)	0.7904 (+0.2897)	0.6462 (+0.1908)
0.2310	8970	2.2946	-	-	-	-	-
0.2330	9048	2.2849	-	-	-	-	-
0.2350	9126	2.2389	-	-	-	-	-
0.2370	9204	2.2426	-	-	-	-	-
0.2390	9282	2.2654	-	-	-	-	-
0.2404	9336	-	2.2665	0.6990 (+0.1586)	0.4479 (+0.1229)	0.7904 (+0.2898)	0.6458 (+0.1904)
0.2410	9360	2.2348	-	-	-	-	-
0.2430	9438	2.2268	-	-	-	-	-
0.2450	9516	2.2216	-	-	-	-	-
0.2470	9594	2.2366	-	-	-	-	-
0.2490	9672	2.2292	-	-	-	-	-
0.2504	9725	-	2.2219	0.7040 (+0.1636)	0.4322 (+0.1071)	0.7859 (+0.2853)	0.6407 (+0.1853)
0.2510	9750	2.2018	-	-	-	-	-
0.2531	9828	2.1947	-	-	-	-	-
0.2551	9906	2.1809	-	-	-	-	-
0.2571	9984	2.2151	-	-	-	-	-
0.2591	10062	2.1765	-	-	-	-	-
0.2604	10114	-	2.1775	0.6820 (+0.1415)	0.4325 (+0.1075)	0.7861 (+0.2855)	0.6335 (+0.1782)
0.2611	10140	2.1634	-	-	-	-	-
0.2631	10218	2.1752	-	-	-	-	-
0.2651	10296	2.1746	-	-	-	-	-
0.2671	10374	2.129	-	-	-	-	-
0.2691	10452	2.1452	-	-	-	-	-
0.2704	10503	-	2.1497	0.7014 (+0.1610)	0.4440 (+0.1190)	0.7896 (+0.2890)	0.6450 (+0.1896)
0.2711	10530	2.1273	-	-	-	-	-
0.2731	10608	2.1441	-	-	-	-	-
0.2751	10686	2.1364	-	-	-	-	-
0.2772	10764	2.1504	-	-	-	-	-
0.2792	10842	2.116	-	-	-	-	-
0.2804	10892	-	2.1506	0.7022 (+0.1618)	0.4360 (+0.1109)	0.7891 (+0.2885)	0.6424 (+0.1871)
0.2812	10920	2.1029	-	-	-	-	-
0.2832	10998	2.0787	-	-	-	-	-
0.2852	11076	2.1119	-	-	-	-	-
0.2872	11154	2.0874	-	-	-	-	-
0.2892	11232	2.0925	-	-	-	-	-
0.2905	11281	-	2.1008	0.6965 (+0.1560)	0.4397 (+0.1146)	0.7937 (+0.2931)	0.6433 (+0.1879)
0.2912	11310	2.067	-	-	-	-	-
0.2932	11388	2.0569	-	-	-	-	-
0.2952	11466	2.0698	-	-	-	-	-
0.2972	11544	2.061	-	-	-	-	-
0.2992	11622	2.0437	-	-	-	-	-
0.3005	11670	-	2.1165	0.6991 (+0.1587)	0.4332 (+0.1082)	0.7979 (+0.2973)	0.6434 (+0.1880)
0.3013	11700	2.0703	-	-	-	-	-
0.3033	11778	2.0376	-	-	-	-	-
0.3053	11856	2.0282	-	-	-	-	-
0.3073	11934	2.0309	-	-	-	-	-
0.3093	12012	2.0278	-	-	-	-	-
0.3105	12059	-	2.0215	0.7035 (+0.1631)	0.4328 (+0.1078)	0.8016 (+0.3010)	0.6460 (+0.1906)
0.3113	12090	2.02	-	-	-	-	-
0.3133	12168	2.0036	-	-	-	-	-
0.3153	12246	1.9998	-	-	-	-	-
0.3173	12324	1.9902	-	-	-	-	-
0.3193	12402	2.0017	-	-	-	-	-
0.3205	12448	-	2.0026	0.7053 (+0.1649)	0.4374 (+0.1124)	0.7872 (+0.2865)	0.6433 (+0.1879)
0.3213	12480	1.9936	-	-	-	-	-
0.3233	12558	1.9797	-	-	-	-	-
0.3254	12636	1.9993	-	-	-	-	-
0.3274	12714	1.9675	-	-	-	-	-
0.3294	12792	1.9707	-	-	-	-	-
0.3305	12837	-	1.9845	0.6987 (+0.1583)	0.4428 (+0.1177)	0.7978 (+0.2972)	0.6464 (+0.1911)
0.3314	12870	1.9597	-	-	-	-	-
0.3334	12948	1.972	-	-	-	-	-
0.3354	13026	1.9621	-	-	-	-	-
0.3374	13104	1.9656	-	-	-	-	-
0.3394	13182	1.942	-	-	-	-	-
0.3405	13226	-	1.9720	0.7032 (+0.1627)	0.4371 (+0.1120)	0.7909 (+0.2903)	0.6437 (+0.1884)
0.3414	13260	1.9184	-	-	-	-	-
0.3434	13338	1.9362	-	-	-	-	-
0.3454	13416	1.9075	-	-	-	-	-
0.3474	13494	1.9191	-	-	-	-	-
0.3495	13572	1.9234	-	-	-	-	-
0.3506	13615	-	1.9565	0.7179 (+0.1774)	0.4441 (+0.1191)	0.7873 (+0.2866)	0.6498 (+0.1944)
0.3515	13650	1.9019	-	-	-	-	-
0.3535	13728	1.9003	-	-	-	-	-
0.3555	13806	1.9249	-	-	-	-	-
0.3575	13884	1.9253	-	-	-	-	-
0.3595	13962	1.9325	-	-	-	-	-
0.3606	14004	-	1.8728	0.6957 (+0.1552)	0.4306 (+0.1055)	0.7976 (+0.2970)	0.6413 (+0.1859)
0.3615	14040	1.8806	-	-	-	-	-
0.3635	14118	1.877	-	-	-	-	-
0.3655	14196	1.8853	-	-	-	-	-
0.3675	14274	1.8759	-	-	-	-	-
0.3695	14352	1.8652	-	-	-	-	-
0.3706	14393	-	1.8743	0.7072 (+0.1668)	0.4305 (+0.1054)	0.7942 (+0.2936)	0.6440 (+0.1886)
0.3715	14430	1.8737	-	-	-	-	-
0.3736	14508	1.8627	-	-	-	-	-
0.3756	14586	1.8504	-	-	-	-	-
0.3776	14664	1.8553	-	-	-	-	-
0.3796	14742	1.8819	-	-	-	-	-
0.3806	14782	-	1.8626	0.6979 (+0.1575)	0.4347 (+0.1097)	0.7939 (+0.2932)	0.6422 (+0.1868)
0.3816	14820	1.8535	-	-	-	-	-
0.3836	14898	1.8452	-	-	-	-	-
0.3856	14976	1.8402	-	-	-	-	-
0.3876	15054	1.8568	-	-	-	-	-
0.3896	15132	1.828	-	-	-	-	-
0.3906	15171	-	1.8430	0.7060 (+0.1656)	0.4412 (+0.1162)	0.7855 (+0.2848)	0.6442 (+0.1888)
0.3916	15210	1.835	-	-	-	-	-
0.3936	15288	1.8453	-	-	-	-	-
0.3956	15366	1.8354	-	-	-	-	-
0.3977	15444	1.8252	-	-	-	-	-
0.3997	15522	1.8272	-	-	-	-	-
0.4006	15560	-	1.8492	0.7016 (+0.1612)	0.4332 (+0.1082)	0.7863 (+0.2857)	0.6404 (+0.1850)
0.4017	15600	1.8083	-	-	-	-	-
0.4037	15678	1.8132	-	-	-	-	-
0.4057	15756	1.7857	-	-	-	-	-
0.4077	15834	1.8222	-	-	-	-	-
0.4097	15912	1.7911	-	-	-	-	-
0.4107	15949	-	1.7805	0.6863 (+0.1459)	0.4452 (+0.1201)	0.7911 (+0.2904)	0.6408 (+0.1855)
0.4117	15990	1.8027	-	-	-	-	-
0.4137	16068	1.8112	-	-	-	-	-
0.4157	16146	1.795	-	-	-	-	-
0.4177	16224	1.7912	-	-	-	-	-
0.4197	16302	1.7574	-	-	-	-	-
0.4207	16338	-	1.7685	0.6899 (+0.1495)	0.4375 (+0.1124)	0.7935 (+0.2928)	0.6403 (+0.1849)
0.4218	16380	1.7746	-	-	-	-	-
0.4238	16458	1.7878	-	-	-	-	-
0.4258	16536	1.7794	-	-	-	-	-
0.4278	16614	1.7586	-	-	-	-	-
0.4298	16692	1.7565	-	-	-	-	-
0.4307	16727	-	1.7783	0.6999 (+0.1595)	0.4433 (+0.1182)	0.7836 (+0.2829)	0.6423 (+0.1869)
0.4318	16770	1.7578	-	-	-	-	-
0.4338	16848	1.7402	-	-	-	-	-
0.4358	16926	1.7549	-	-	-	-	-
0.4378	17004	1.7556	-	-	-	-	-
0.4398	17082	1.7479	-	-	-	-	-
0.4407	17116	-	1.7780	0.6830 (+0.1426)	0.4377 (+0.1127)	0.7820 (+0.2814)	0.6343 (+0.1789)
0.4418	17160	1.7505	-	-	-	-	-
0.4438	17238	1.7515	-	-	-	-	-
0.4459	17316	1.7301	-	-	-	-	-
0.4479	17394	1.7521	-	-	-	-	-
0.4499	17472	1.7397	-	-	-	-	-
0.4507	17505	-	1.7556	0.6781 (+0.1377)	0.4357 (+0.1107)	0.8007 (+0.3001)	0.6382 (+0.1828)
0.4519	17550	1.734	-	-	-	-	-
0.4539	17628	1.7251	-	-	-	-	-
0.4559	17706	1.7292	-	-	-	-	-
0.4579	17784	1.7269	-	-	-	-	-
0.4599	17862	1.6889	-	-	-	-	-
0.4607	17894	-	1.7416	0.6845 (+0.1441)	0.4323 (+0.1072)	0.7945 (+0.2938)	0.6371 (+0.1817)
0.4619	17940	1.7034	-	-	-	-	-
0.4639	18018	1.6913	-	-	-	-	-
0.4659	18096	1.7312	-	-	-	-	-
0.4679	18174	1.6997	-	-	-	-	-
0.4700	18252	1.6941	-	-	-	-	-
0.4708	18283	-	1.6900	0.6796 (+0.1392)	0.4382 (+0.1132)	0.7881 (+0.2874)	0.6353 (+0.1799)
0.4720	18330	1.6976	-	-	-	-	-
0.4740	18408	1.7138	-	-	-	-	-
0.4760	18486	1.6885	-	-	-	-	-
0.4780	18564	1.7152	-	-	-	-	-
0.4800	18642	1.6676	-	-	-	-	-
0.4808	18672	-	1.6843	0.6842 (+0.1438)	0.4380 (+0.1129)	0.7832 (+0.2826)	0.6351 (+0.1798)
0.4820	18720	1.7004	-	-	-	-	-
0.4840	18798	1.6834	-	-	-	-	-
0.4860	18876	1.6955	-	-	-	-	-
0.4880	18954	1.6971	-	-	-	-	-
0.4900	19032	1.7012	-	-	-	-	-
0.4908	19061	-	1.6958	0.6969 (+0.1565)	0.4353 (+0.1103)	0.7831 (+0.2824)	0.6384 (+0.1831)
0.4920	19110	1.699	-	-	-	-	-
0.4941	19188	1.6602	-	-	-	-	-
0.4961	19266	1.6515	-	-	-	-	-
0.4981	19344	1.6488	-	-	-	-	-
0.5001	19422	1.6533	-	-	-	-	-
0.5008	19450	-	1.6820	0.6937 (+0.1533)	0.4359 (+0.1108)	0.7847 (+0.2841)	0.6381 (+0.1827)
0.5021	19500	1.6465	-	-	-	-	-
0.5041	19578	1.6682	-	-	-	-	-
0.5061	19656	1.6591	-	-	-	-	-
0.5081	19734	1.6603	-	-	-	-	-
0.5101	19812	1.6469	-	-	-	-	-
0.5108	19839	-	1.6590	0.7084 (+0.1680)	0.4303 (+0.1053)	0.7996 (+0.2990)	0.6461 (+0.1907)
0.5121	19890	1.6462	-	-	-	-	-
0.5141	19968	1.648	-	-	-	-	-
0.5161	20046	1.6577	-	-	-	-	-
0.5182	20124	1.6456	-	-	-	-	-
0.5202	20202	1.6321	-	-	-	-	-
0.5208	20228	-	1.6421	0.7064 (+0.1660)	0.4300 (+0.1050)	0.7759 (+0.2753)	0.6375 (+0.1821)
0.5222	20280	1.6187	-	-	-	-	-
0.5242	20358	1.6326	-	-	-	-	-
0.5262	20436	1.6286	-	-	-	-	-
0.5282	20514	1.6071	-	-	-	-	-
0.5302	20592	1.6112	-	-	-	-	-
0.5308	20617	-	1.6292	0.7030 (+0.1626)	0.4334 (+0.1083)	0.7812 (+0.2806)	0.6392 (+0.1838)
0.5322	20670	1.6242	-	-	-	-	-
0.5342	20748	1.613	-	-	-	-	-
0.5362	20826	1.6209	-	-	-	-	-
0.5382	20904	1.6224	-	-	-	-	-
0.5402	20982	1.5982	-	-	-	-	-
0.5409	21006	-	1.6298	0.7073 (+0.1669)	0.4342 (+0.1092)	0.7795 (+0.2789)	0.6403 (+0.1850)
0.5423	21060	1.6032	-	-	-	-	-
0.5443	21138	1.6099	-	-	-	-	-
0.5463	21216	1.599	-	-	-	-	-
0.5483	21294	1.6098	-	-	-	-	-
0.5503	21372	1.5978	-	-	-	-	-
0.5509	21395	-	1.6169	0.6832 (+0.1428)	0.4393 (+0.1142)	0.7890 (+0.2883)	0.6372 (+0.1818)
0.5523	21450	1.6116	-	-	-	-	-
0.5543	21528	1.5971	-	-	-	-	-
0.5563	21606	1.5883	-	-	-	-	-
0.5583	21684	1.5852	-	-	-	-	-
0.5603	21762	1.6024	-	-	-	-	-
0.5609	21784	-	1.5942	0.6892 (+0.1488)	0.4323 (+0.1072)	0.7858 (+0.2851)	0.6357 (+0.1804)
0.5623	21840	1.6046	-	-	-	-	-
0.5643	21918	1.5723	-	-	-	-	-
0.5664	21996	1.5583	-	-	-	-	-
0.5684	22074	1.5917	-	-	-	-	-
0.5704	22152	1.5819	-	-	-	-	-
0.5709	22173	-	1.5676	0.6901 (+0.1496)	0.4377 (+0.1127)	0.7944 (+0.2938)	0.6407 (+0.1854)
0.5724	22230	1.5842	-	-	-	-	-
0.5744	22308	1.5815	-	-	-	-	-
0.5764	22386	1.5972	-	-	-	-	-
0.5784	22464	1.568	-	-	-	-	-
0.5804	22542	1.5798	-	-	-	-	-
0.5809	22562	-	1.5817	0.6882 (+0.1478)	0.4352 (+0.1102)	0.7858 (+0.2852)	0.6364 (+0.1810)
0.5824	22620	1.5523	-	-	-	-	-
0.5844	22698	1.5821	-	-	-	-	-
0.5864	22776	1.5812	-	-	-	-	-
0.5884	22854	1.5837	-	-	-	-	-
0.5905	22932	1.5731	-	-	-	-	-
0.5909	22951	-	1.5726	0.6916 (+0.1512)	0.4291 (+0.1041)	0.7904 (+0.2898)	0.6370 (+0.1817)
0.5925	23010	1.588	-	-	-	-	-
0.5945	23088	1.5709	-	-	-	-	-
0.5965	23166	1.5522	-	-	-	-	-
0.5985	23244	1.5469	-	-	-	-	-
0.6005	23322	1.549	-	-	-	-	-
0.6010	23340	-	1.5656	0.6924 (+0.1520)	0.4289 (+0.1039)	0.7854 (+0.2847)	0.6356 (+0.1802)
0.6025	23400	1.5528	-	-	-	-	-
0.6045	23478	1.5671	-	-	-	-	-
0.6065	23556	1.5491	-	-	-	-	-
0.6085	23634	1.558	-	-	-	-	-
0.6105	23712	1.5406	-	-	-	-	-
0.6110	23729	-	1.5599	0.6984 (+0.1580)	0.4335 (+0.1084)	0.7815 (+0.2809)	0.6378 (+0.1825)
0.6125	23790	1.5491	-	-	-	-	-
0.6146	23868	1.5452	-	-	-	-	-
0.6166	23946	1.5455	-	-	-	-	-
0.6186	24024	1.5487	-	-	-	-	-
0.6206	24102	1.5639	-	-	-	-	-
0.6210	24118	-	1.5381	0.6892 (+0.1488)	0.4343 (+0.1092)	0.7861 (+0.2855)	0.6365 (+0.1812)
0.6226	24180	1.5223	-	-	-	-	-
0.6246	24258	1.5293	-	-	-	-	-
0.6266	24336	1.5441	-	-	-	-	-
0.6286	24414	1.535	-	-	-	-	-
0.6306	24492	1.5151	-	-	-	-	-
0.6310	24507	-	1.5285	0.6896 (+0.1492)	0.4347 (+0.1097)	0.7967 (+0.2960)	0.6403 (+0.1850)
0.6326	24570	1.524	-	-	-	-	-
0.6346	24648	1.5383	-	-	-	-	-
0.6366	24726	1.5218	-	-	-	-	-
0.6387	24804	1.5176	-	-	-	-	-
0.6407	24882	1.5136	-	-	-	-	-
0.6410	24896	-	1.5087	0.6776 (+0.1372)	0.4326 (+0.1076)	0.7880 (+0.2874)	0.6327 (+0.1774)
0.6427	24960	1.5151	-	-	-	-	-
0.6447	25038	1.5177	-	-	-	-	-
0.6467	25116	1.5054	-	-	-	-	-
0.6487	25194	1.5206	-	-	-	-	-
0.6507	25272	1.4956	-	-	-	-	-
0.6510	25285	-	1.5238	0.6972 (+0.1568)	0.4325 (+0.1075)	0.7842 (+0.2836)	0.6380 (+0.1826)
0.6527	25350	1.4985	-	-	-	-	-
0.6547	25428	1.51	-	-	-	-	-
0.6567	25506	1.4913	-	-	-	-	-
0.6587	25584	1.5001	-	-	-	-	-
0.6607	25662	1.4997	-	-	-	-	-
0.6611	25674	-	1.5059	0.6950 (+0.1546)	0.4310 (+0.1060)	0.7887 (+0.2881)	0.6382 (+0.1829)
0.6628	25740	1.492	-	-	-	-	-
0.6648	25818	1.4816	-	-	-	-	-
0.6668	25896	1.4959	-	-	-	-	-
0.6688	25974	1.5026	-	-	-	-	-
0.6708	26052	1.4936	-	-	-	-	-
0.6711	26063	-	1.4728	0.6938 (+0.1534)	0.4373 (+0.1123)	0.7935 (+0.2929)	0.6416 (+0.1862)
0.6728	26130	1.481	-	-	-	-	-
0.6748	26208	1.4999	-	-	-	-	-
0.6768	26286	1.5008	-	-	-	-	-
0.6788	26364	1.47	-	-	-	-	-
0.6808	26442	1.4855	-	-	-	-	-
0.6811	26452	-	1.4808	0.6864 (+0.1460)	0.4343 (+0.1092)	0.7736 (+0.2729)	0.6314 (+0.1761)
0.6828	26520	1.479	-	-	-	-	-
0.6848	26598	1.4814	-	-	-	-	-
0.6869	26676	1.4696	-	-	-	-	-
0.6889	26754	1.4776	-	-	-	-	-
0.6909	26832	1.4662	-	-	-	-	-
0.6911	26841	-	1.4597	0.6842 (+0.1438)	0.4369 (+0.1119)	0.7928 (+0.2922)	0.6380 (+0.1826)
0.6929	26910	1.4744	-	-	-	-	-
0.6949	26988	1.4684	-	-	-	-	-
0.6969	27066	1.4658	-	-	-	-	-
0.6989	27144	1.4686	-	-	-	-	-
0.7009	27222	1.4785	-	-	-	-	-
0.7011	27230	-	1.4598	0.6980 (+0.1576)	0.4330 (+0.1080)	0.7886 (+0.2879)	0.6399 (+0.1845)
0.7029	27300	1.4823	-	-	-	-	-
0.7049	27378	1.4697	-	-	-	-	-
0.7069	27456	1.4564	-	-	-	-	-
0.7089	27534	1.4506	-	-	-	-	-
0.7110	27612	1.4452	-	-	-	-	-
0.7111	27619	-	1.4513	0.7083 (+0.1679)	0.4298 (+0.1048)	0.7848 (+0.2842)	0.6410 (+0.1856)
0.7130	27690	1.4585	-	-	-	-	-
0.7150	27768	1.4485	-	-	-	-	-
0.7170	27846	1.4641	-	-	-	-	-
0.7190	27924	1.4557	-	-	-	-	-
0.7210	28002	1.4573	-	-	-	-	-
0.7211	28008	-	1.4622	0.6934 (+0.1530)	0.4379 (+0.1128)	0.7971 (+0.2964)	0.6428 (+0.1874)
0.7230	28080	1.4557	-	-	-	-	-
0.7250	28158	1.4568	-	-	-	-	-
0.7270	28236	1.4508	-	-	-	-	-
0.7290	28314	1.459	-	-	-	-	-
0.7310	28392	1.4636	-	-	-	-	-
0.7312	28397	-	1.4458	0.6894 (+0.1490)	0.4323 (+0.1072)	0.7942 (+0.2935)	0.6386 (+0.1832)
0.7330	28470	1.4486	-	-	-	-	-
0.7351	28548	1.4706	-	-	-	-	-
0.7371	28626	1.4511	-	-	-	-	-
0.7391	28704	1.4665	-	-	-	-	-
0.7411	28782	1.4437	-	-	-	-	-
0.7412	28786	-	1.4317	0.6888 (+0.1483)	0.4374 (+0.1124)	0.7952 (+0.2945)	0.6405 (+0.1851)
0.7431	28860	1.4436	-	-	-	-	-
0.7451	28938	1.4211	-	-	-	-	-
0.7471	29016	1.4313	-	-	-	-	-
0.7491	29094	1.4353	-	-	-	-	-
0.7511	29172	1.4218	-	-	-	-	-
0.7512	29175	-	1.4379	0.6906 (+0.1502)	0.4371 (+0.1120)	0.7900 (+0.2893)	0.6392 (+0.1838)
0.7531	29250	1.4302	-	-	-	-	-
0.7551	29328	1.4294	-	-	-	-	-
0.7571	29406	1.4255	-	-	-	-	-
0.7592	29484	1.4374	-	-	-	-	-
0.7612	29562	1.4278	-	-	-	-	-
0.7612	29564	-	1.4246	0.6983 (+0.1579)	0.4328 (+0.1077)	0.7886 (+0.2879)	0.6399 (+0.1845)
0.7632	29640	1.4133	-	-	-	-	-
0.7652	29718	1.4351	-	-	-	-	-
0.7672	29796	1.4215	-	-	-	-	-
0.7692	29874	1.4331	-	-	-	-	-
0.7712	29952	1.4226	-	-	-	-	-
0.7712	29953	-	1.4197	0.7034 (+0.1630)	0.4313 (+0.1063)	0.7938 (+0.2932)	0.6428 (+0.1875)
0.7732	30030	1.4374	-	-	-	-	-
0.7752	30108	1.4181	-	-	-	-	-
0.7772	30186	1.4228	-	-	-	-	-
0.7792	30264	1.4054	-	-	-	-	-
0.7812	30342	1.4225	1.4250	0.7096 (+0.1692)	0.4364 (+0.1114)	0.7905 (+0.2899)	0.6455 (+0.1902)
0.7833	30420	1.4216	-	-	-	-	-
0.7853	30498	1.4137	-	-	-	-	-
0.7873	30576	1.4233	-	-	-	-	-
0.7893	30654	1.4139	-	-	-	-	-
0.7913	30731	-	1.4091	0.6835 (+0.1430)	0.4351 (+0.1101)	0.7894 (+0.2887)	0.6360 (+0.1806)
0.7913	30732	1.4071	-	-	-	-	-
0.7933	30810	1.4261	-	-	-	-	-
0.7953	30888	1.4255	-	-	-	-	-
0.7973	30966	1.4011	-	-	-	-	-
0.7993	31044	1.4125	-	-	-	-	-
0.8013	31120	-	1.4071	0.6894 (+0.1489)	0.4338 (+0.1088)	0.7784 (+0.2777)	0.6339 (+0.1785)
0.8013	31122	1.4023	-	-	-	-	-
0.8033	31200	1.4043	-	-	-	-	-
0.8053	31278	1.4123	-	-	-	-	-
0.8074	31356	1.4206	-	-	-	-	-
0.8094	31434	1.4043	-	-	-	-	-
0.8113	31509	-	1.3989	0.6856 (+0.1452)	0.4354 (+0.1103)	0.7752 (+0.2746)	0.6321 (+0.1767)
0.8114	31512	1.4099	-	-	-	-	-
0.8134	31590	1.3995	-	-	-	-	-
0.8154	31668	1.4002	-	-	-	-	-
0.8174	31746	1.3961	-	-	-	-	-
0.8194	31824	1.3848	-	-	-	-	-
0.8213	31898	-	1.3922	0.6864 (+0.1460)	0.4341 (+0.1090)	0.7734 (+0.2728)	0.6313 (+0.1760)
0.8214	31902	1.418	-	-	-	-	-
0.8234	31980	1.4076	-	-	-	-	-
0.8254	32058	1.3818	-	-	-	-	-
0.8274	32136	1.3747	-	-	-	-	-
0.8294	32214	1.3872	-	-	-	-	-
0.8313	32287	-	1.3914	0.6930 (+0.1526)	0.4386 (+0.1135)	0.7725 (+0.2718)	0.6347 (+0.1793)
0.8315	32292	1.3882	-	-	-	-	-
0.8335	32370	1.4111	-	-	-	-	-
0.8355	32448	1.3677	-	-	-	-	-
0.8375	32526	1.3726	-	-	-	-	-
0.8395	32604	1.377	-	-	-	-	-
0.8413	32676	-	1.3778	0.6842 (+0.1438)	0.4387 (+0.1136)	0.7823 (+0.2817)	0.6351 (+0.1797)
0.8415	32682	1.3853	-	-	-	-	-
0.8435	32760	1.3851	-	-	-	-	-
0.8455	32838	1.3724	-	-	-	-	-
0.8475	32916	1.3845	-	-	-	-	-
0.8495	32994	1.3827	-	-	-	-	-
0.8514	33065	-	1.3790	0.6848 (+0.1443)	0.4374 (+0.1124)	0.7797 (+0.2791)	0.6340 (+0.1786)
0.8515	33072	1.388	-	-	-	-	-
0.8535	33150	1.377	-	-	-	-	-
0.8556	33228	1.3762	-	-	-	-	-
0.8576	33306	1.3716	-	-	-	-	-
0.8596	33384	1.3763	-	-	-	-	-
0.8614	33454	-	1.3811	0.6874 (+0.1469)	0.4388 (+0.1138)	0.7727 (+0.2721)	0.6330 (+0.1776)
0.8616	33462	1.3755	-	-	-	-	-
0.8636	33540	1.3733	-	-	-	-	-
0.8656	33618	1.3621	-	-	-	-	-
0.8676	33696	1.3648	-	-	-	-	-
0.8696	33774	1.3665	-	-	-	-	-
0.8714	33843	-	1.3638	0.6905 (+0.1500)	0.4394 (+0.1143)	0.7755 (+0.2749)	0.6351 (+0.1797)
0.8716	33852	1.3636	-	-	-	-	-
0.8736	33930	1.3654	-	-	-	-	-
0.8756	34008	1.365	-	-	-	-	-
0.8776	34086	1.3769	-	-	-	-	-
0.8797	34164	1.3679	-	-	-	-	-
0.8814	34232	-	1.3558	0.6891 (+0.1486)	0.4378 (+0.1128)	0.7802 (+0.2796)	0.6357 (+0.1803)
0.8817	34242	1.3614	-	-	-	-	-
0.8837	34320	1.3672	-	-	-	-	-
0.8857	34398	1.3632	-	-	-	-	-
0.8877	34476	1.3759	-	-	-	-	-
0.8897	34554	1.3704	-	-	-	-	-
0.8914	34621	-	1.3621	0.6851 (+0.1447)	0.4381 (+0.1131)	0.7810 (+0.2804)	0.6348 (+0.1794)
0.8917	34632	1.3523	-	-	-	-	-
0.8937	34710	1.3444	-	-	-	-	-
0.8957	34788	1.3419	-	-	-	-	-
0.8977	34866	1.3616	-	-	-	-	-
0.8997	34944	1.3519	-	-	-	-	-
0.9014	35010	-	1.3627	0.6878 (+0.1474)	0.4377 (+0.1127)	0.7732 (+0.2726)	0.6329 (+0.1776)
0.9017	35022	1.3614	-	-	-	-	-
0.9038	35100	1.3606	-	-	-	-	-
0.9058	35178	1.3401	-	-	-	-	-
0.9078	35256	1.3503	-	-	-	-	-
0.9098	35334	1.3422	-	-	-	-	-
0.9115	35399	-	1.3563	0.6938 (+0.1534)	0.4382 (+0.1132)	0.7775 (+0.2768)	0.6365 (+0.1811)
0.9118	35412	1.3397	-	-	-	-	-
0.9138	35490	1.3592	-	-	-	-	-
0.9158	35568	1.3687	-	-	-	-	-
0.9178	35646	1.3452	-	-	-	-	-
0.9198	35724	1.3685	-	-	-	-	-
0.9215	35788	-	1.3459	0.6877 (+0.1473)	0.4330 (+0.1080)	0.7924 (+0.2917)	0.6377 (+0.1824)
0.9218	35802	1.3542	-	-	-	-	-
0.9238	35880	1.3567	-	-	-	-	-
0.9258	35958	1.3627	-	-	-	-	-
0.9279	36036	1.3476	-	-	-	-	-
0.9299	36114	1.3556	-	-	-	-	-
0.9315	36177	-	1.3442	0.6951 (+0.1547)	0.4382 (+0.1132)	0.7749 (+0.2742)	0.6361 (+0.1807)
0.9319	36192	1.3444	-	-	-	-	-
0.9339	36270	1.3625	-	-	-	-	-
0.9359	36348	1.3428	-	-	-	-	-
0.9379	36426	1.3575	-	-	-	-	-
0.9399	36504	1.3592	-	-	-	-	-
0.9415	36566	-	1.3468	0.6848 (+0.1443)	0.4389 (+0.1138)	0.7922 (+0.2916)	0.6386 (+0.1832)
0.9419	36582	1.3317	-	-	-	-	-
0.9439	36660	1.3394	-	-	-	-	-
0.9459	36738	1.3411	-	-	-	-	-
0.9479	36816	1.339	-	-	-	-	-
0.9499	36894	1.3346	-	-	-	-	-
0.9515	36955	-	1.3424	0.6877 (+0.1473)	0.4382 (+0.1132)	0.7851 (+0.2845)	0.6370 (+0.1816)
0.9520	36972	1.348	-	-	-	-	-
0.9540	37050	1.3462	-	-	-	-	-
0.9560	37128	1.3339	-	-	-	-	-
0.9580	37206	1.3218	-	-	-	-	-
0.9600	37284	1.3461	-	-	-	-	-
0.9615	37344	-	1.3382	0.6877 (+0.1473)	0.4390 (+0.1139)	0.7851 (+0.2845)	0.6373 (+0.1819)
0.9620	37362	1.3392	-	-	-	-	-
0.9640	37440	1.3415	-	-	-	-	-
0.9660	37518	1.3423	-	-	-	-	-
0.9680	37596	1.3357	-	-	-	-	-
0.9700	37674	1.333	-	-	-	-	-
0.9715	37733	-	1.3409	0.6877 (+0.1473)	0.4394 (+0.1144)	0.7825 (+0.2819)	0.6366 (+0.1812)
0.9720	37752	1.3111	-	-	-	-	-
0.9740	37830	1.3506	-	-	-	-	-
0.9761	37908	1.3472	-	-	-	-	-
0.9781	37986	1.3273	-	-	-	-	-
0.9801	38064	1.337	-	-	-	-	-
0.9816	38122	-	1.3355	0.6877 (+0.1473)	0.4383 (+0.1133)	0.7751 (+0.2745)	0.6337 (+0.1784)
0.9821	38142	1.3393	-	-	-	-	-
0.9841	38220	1.3205	-	-	-	-	-
0.9861	38298	1.3313	-	-	-	-	-
0.9881	38376	1.3408	-	-	-	-	-
0.9901	38454	1.3463	-	-	-	-	-
0.9916	38511	-	1.3325	0.6877 (+0.1473)	0.4366 (+0.1115)	0.7751 (+0.2745)	0.6331 (+0.1778)
0.9921	38532	1.3356	-	-	-	-	-
0.9941	38610	1.3352	-	-	-	-	-
0.9961	38688	1.3489	-	-	-	-	-
0.9981	38766	1.3365	-	-	-	-	-
-1	-1	-	-	0.7180 (+0.1776)	0.4451 (+0.1201)	0.8011 (+0.3005)	0.6548 (+0.1994)

The bold row denotes the saved checkpoint.

Environmental Impact

Carbon emissions were measured using CodeCarbon.

Energy Consumed: 24.402 kWh
Carbon Emitted: 9.008 kg of CO2
Hours Used: 4.849 hours

Training Hardware

On Cloud: No
GPU Model: 8 x NVIDIA H100 80GB HBM3
CPU Model: AMD EPYC 7R13 Processor
RAM Size: 1999.99 GB

Framework Versions

Python: 3.10.14
Sentence Transformers: 5.1.2
Transformers: 4.57.1
PyTorch: 2.9.1+cu126
Accelerate: 1.12.0
Datasets: 4.4.1
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",
}

MarginMSELoss

@misc{hofstätter2021improving,
    title={Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation},
    author={Sebastian Hofstätter and Sophia Althammer and Michael Schröder and Mete Sertkan and Allan Hanbury},
    year={2021},
    eprint={2010.02666},
    archivePrefix={arXiv},
    primaryClass={cs.IR}
}