ms-marco-ettin-17m-reranker / README.md

tomaarsen HF Staff

Add new CrossEncoder model

5e03204 verified 13 days ago

preview code

raw

history blame contribute delete

116 kB

metadata

language:
  - en
tags:
  - sentence-transformers
  - cross-encoder
  - reranker
  - generated_from_trainer
  - dataset_size:39770704
  - loss:MarginMSELoss
base_model: jhu-clsp/ettin-encoder-17m
datasets:
  - sentence-transformers/msmarco
pipeline_tag: text-ranking
library_name: sentence-transformers
metrics:
  - map
  - mrr@10
  - ndcg@10
co2_eq_emissions:
  emissions: 1604.894253932601
  energy_consumed: 4.347723620604183
  source: codecarbon
  training_type: fine-tuning
  on_cloud: false
  cpu_model: AMD EPYC 7R13 Processor
  ram_total_size: 1999.9855194091797
  hours_used: 1.576
  hardware_used: 8 x NVIDIA H100 80GB HBM3
model-index:
  - name: CrossEncoder based on jhu-clsp/ettin-encoder-17m
    results:
      - task:
          type: cross-encoder-reranking
          name: Cross Encoder Reranking
        dataset:
          name: NanoMSMARCO R100
          type: NanoMSMARCO_R100
        metrics:
          - type: map
            value: 0.6239
            name: Map
          - type: mrr@10
            value: 0.6129
            name: Mrr@10
          - type: ndcg@10
            value: 0.6576
            name: Ndcg@10
      - task:
          type: cross-encoder-reranking
          name: Cross Encoder Reranking
        dataset:
          name: NanoNFCorpus R100
          type: NanoNFCorpus_R100
        metrics:
          - type: map
            value: 0.3478
            name: Map
          - type: mrr@10
            value: 0.5462
            name: Mrr@10
          - type: ndcg@10
            value: 0.3996
            name: Ndcg@10
      - task:
          type: cross-encoder-reranking
          name: Cross Encoder Reranking
        dataset:
          name: NanoNQ R100
          type: NanoNQ_R100
        metrics:
          - type: map
            value: 0.6263
            name: Map
          - type: mrr@10
            value: 0.6337
            name: Mrr@10
          - type: ndcg@10
            value: 0.672
            name: Ndcg@10
      - task:
          type: cross-encoder-nano-beir
          name: Cross Encoder Nano BEIR
        dataset:
          name: NanoBEIR R100 mean
          type: NanoBEIR_R100_mean
        metrics:
          - type: map
            value: 0.5327
            name: Map
          - type: mrr@10
            value: 0.5976
            name: Mrr@10
          - type: ndcg@10
            value: 0.5764
            name: Ndcg@10

CrossEncoder based on jhu-clsp/ettin-encoder-17m

This is a Cross Encoder model finetuned from jhu-clsp/ettin-encoder-17m 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-17m
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-17m-reranker")
# Get scores for pairs of texts
pairs = [
    ['the name olmec means', 'The name Olmec comes from the Nahuatl word for the Olmecs: Å\x8clmÄ\x93catl [oË\x90lË\x88meË\x90katÍ¡É¬] (singular) or Å\x8clmÄ\x93cah [oË\x90lË\x88meË\x90kaÊ\x94] (plural). This word is composed of the two words Å\x8dlli [Ë\x88oË\x90lË\x90i] , meaning rubber, and mÄ\x93catl [Ë\x88meË\x90katÍ¡É¬] , meaning people, so the word means rubber people.hey lived in the tropical lowlands of south-central Mexico, in the present-day states of Veracruz and Tabasco. It has been speculated that Olmec derive in part from neighboring Mokaya and/or Mixeâ\x80\x93Zoque.'],
    ['what causes hissing in the ears', 'The following medical conditions are some of the possible causes of Hissing in ears. There are likely to be other possible causes, so ask your doctor about your symptoms. 1  Acute ear infection.  Chronic ear infection.'],
    ['multiple birth sibling definition', 'multiple birth(Noun) a birth in which more than one baby are born. Multiple birth. A multiple birth occurs when more than one fetus is carried to term in a single pregnancy. Different names for multiple births are used, depending on the number of offspring.'],
    ['what cause fluid build up on the knee', 'No: The joint should not have any appreciable fluid in it normally. Fluid can be there from many reasons. Arthritis can cause fluid. Also surgery can cause some bleeding in the knee which can cause the fluid to build up. The fluid makes the joint stiff and makes it hard to get a good quad function. ...Read more.'],
    ['how long is the wait list for kidney transplant', 'At the center of this is the simple fact that organ transplantation is built upon altruism and public trust. Gift of Life works hard to ensure that this trust is maintained, through its commitment both to the donor family as well as to those on the waiting list. Average Median Wait Time to Transplant. Kidney â\x80\x93 5 years.'],
]
scores = model.predict(pairs)
print(scores.shape)
# (5,)

# Or rank different texts based on similarity to a single text
ranks = model.rank(
    'the name olmec means',
    [
        'The name Olmec comes from the Nahuatl word for the Olmecs: Å\x8clmÄ\x93catl [oË\x90lË\x88meË\x90katÍ¡É¬] (singular) or Å\x8clmÄ\x93cah [oË\x90lË\x88meË\x90kaÊ\x94] (plural). This word is composed of the two words Å\x8dlli [Ë\x88oË\x90lË\x90i] , meaning rubber, and mÄ\x93catl [Ë\x88meË\x90katÍ¡É¬] , meaning people, so the word means rubber people.hey lived in the tropical lowlands of south-central Mexico, in the present-day states of Veracruz and Tabasco. It has been speculated that Olmec derive in part from neighboring Mokaya and/or Mixeâ\x80\x93Zoque.',
        'The following medical conditions are some of the possible causes of Hissing in ears. There are likely to be other possible causes, so ask your doctor about your symptoms. 1  Acute ear infection.  Chronic ear infection.',
        'multiple birth(Noun) a birth in which more than one baby are born. Multiple birth. A multiple birth occurs when more than one fetus is carried to term in a single pregnancy. Different names for multiple births are used, depending on the number of offspring.',
        'No: The joint should not have any appreciable fluid in it normally. Fluid can be there from many reasons. Arthritis can cause fluid. Also surgery can cause some bleeding in the knee which can cause the fluid to build up. The fluid makes the joint stiff and makes it hard to get a good quad function. ...Read more.',
        'At the center of this is the simple fact that organ transplantation is built upon altruism and public trust. Gift of Life works hard to ensure that this trust is maintained, through its commitment both to the donor family as well as to those on the waiting list. Average Median Wait Time to Transplant. Kidney â\x80\x93 5 years.',
    ]
)
# [{'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	0.6239 (+0.1343)	0.3478 (+0.0868)	0.6263 (+0.2067)
mrr@10	0.6129 (+0.1354)	0.5462 (+0.0464)	0.6337 (+0.2070)
ndcg@10	0.6576 (+0.1172)	0.3996 (+0.0745)	0.6720 (+0.1714)

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	0.5327 (+0.1426)
mrr@10	0.5976 (+0.1296)
ndcg@10	0.5764 (+0.1210)

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: 11 characters mean: 33.5 characters max: 98 characters	min: 68 characters mean: 358.26 characters max: 988 characters	min: 50 characters mean: 346.46 characters max: 969 characters	min: -3.69 mean: 13.4 max: 22.15

Samples:

query_id	positive_id	negative_id	score
`how do you attach a sanding screen to a floor buffer`	`Lay the buffer on the floor so you can get underneath the housing and hook the screening brush to the central spindle. Center a sanding screen on the brush and push on it so it stays in place, then right the buffer and allow the housing to rest on the floor. Plug in the machine and grasp the handles with both hands before you turn it on.`	The random orbital sander used an offset drive bearing that causes the pad to also move in an elliptical pattern. These pad movements are used in combination, randomly of course to help reduce the swirls that a non-random sheet sander might leave behind. Mechanics aside, a mojor difference is in the sanding medium. Most random orbital sanders use sanding disks, typically in a 5-inch diameter. They are attached to the sander's pad using hook & loop connections. The sanding disks have holes in them that match-up with the dust collection holes in the sander's pad.	`15.936323801676433`
`define method overriding`	`Method overriding is when a child class redefines the same method as a parent class, with the same parameters. For example, the standard Java class java.util.LinkedHashSet eâ¦xtends java.util.HashSet. The method add() is overridden in LinkedHashSet.`	`In spite of its limitations, the MET concept provides a convenient method to describe the functional capacity or exercise tolerance of an individual as determined from progressive exercise testing and to define a repertoire of physical activities in which a person may participate safely, without exceeding a prescribed intensity level. PMID: 2204507`	`19.40437730153402`
`toxic effects of constipation`	`by Jane Kriese. The colon is the part of the large intestine extending from the cecum to the rectum. And the most common sign of having a toxic colon is a condition called constipation. An accumulation of waste food byproducts in the colon can lead to constipation, toxic build up, weight gain and low energy.`	`In Summary. Commonly reported side effects of tizanidine include: bradycardia, dizziness, drowsiness, hypotension, asthenia, fatigue, and xerostomia. Other side effects include: constipation, and increased liver enzymes. See below for a comprehensive list of adverse effects.`	`7.669035658240318`

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: 10 characters mean: 34.37 characters max: 116 characters	min: 61 characters mean: 341.63 characters max: 952 characters	min: 73 characters mean: 346.27 characters max: 1350 characters	min: -0.85 mean: 13.13 max: 22.52

Samples:

query_id	positive_id	negative_id	score
`the name olmec means`	The name Olmec comes from the Nahuatl word for the Olmecs: ÅlmÄcatl [oËlËmeËkatÍ¡É¬] (singular) or ÅlmÄcah [oËlËmeËkaÊ] (plural). This word is composed of the two words Ålli [ËoËlËi] , meaning rubber, and mÄcatl [ËmeËkatÍ¡É¬] , meaning people, so the word means rubber people.hey lived in the tropical lowlands of south-central Mexico, in the present-day states of Veracruz and Tabasco. It has been speculated that Olmec derive in part from neighboring Mokaya and/or MixeâZoque.	`Jai: Glory to, Joy, Hail. Guru; Gu - means darkness, and Ru - means a remover. So, Guru means a remover of darkness. Deva; means a shining one and is the source of the English word, Divine. So when we say Jai Guru Deva we are giving thanks to whoever we feel is the source of knowledge to us.`	`19.567786693572998`
`what causes hissing in the ears`	`The following medical conditions are some of the possible causes of Hissing in ears. There are likely to be other possible causes, so ask your doctor about your symptoms. 1 Acute ear infection. Chronic ear infection.`	`There are many possible causes of itchy ears. Although the annoyance of itchy ears is not usually found to be serious, the condition is very real no matter the reason for the uncomfortable nuisance. Poking objects like cotton swabs, pencils, and paperclips in the ears to relieve the irritation is a dangerous and non-effective method for relief.`	`10.332231203715006`
`multiple birth sibling definition`	`multiple birth(Noun) a birth in which more than one baby are born. Multiple birth. A multiple birth occurs when more than one fetus is carried to term in a single pregnancy. Different names for multiple births are used, depending on the number of offspring.`	`From Wikipedia, the free encyclopedia. Not to be confused with Life unworthy of life or Wrongful birth. Wrongful life is the name given to a legal action in which someone is sued by a severely disabled child (through the child's legal guardian) for failing to prevent the child's birth.1 1 Definition.rongful life is the name given to a legal action in which someone is sued by a severely disabled child (through the child's legal guardian) for failing to prevent the child's birth. Contents.`	`16.912671327590942`

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: 256
per_device_eval_batch_size: 256
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: 256
per_device_eval_batch_size: 256
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	-	-	0.0277 (-0.5127)	0.3408 (+0.0157)	0.0189 (-0.4817)	0.1291 (-0.3262)
0.0001	1	203.5639	-	-	-	-	-
0.0020	39	206.4834	-	-	-	-	-
0.0040	78	202.3608	-	-	-	-	-
0.0060	117	197.2066	-	-	-	-	-
0.0080	156	189.4029	-	-	-	-	-
0.0100	195	180.9973	174.2619	0.0536 (-0.4868)	0.2671 (-0.0580)	0.0676 (-0.4330)	0.1294 (-0.3259)
0.0121	234	172.5803	-	-	-	-	-
0.0141	273	165.2367	-	-	-	-	-
0.0161	312	157.6653	-	-	-	-	-
0.0181	351	147.8596	-	-	-	-	-
0.0201	390	129.2817	113.0435	0.1823 (-0.3581)	0.2122 (-0.1128)	0.2045 (-0.2961)	0.1997 (-0.2557)
0.0221	429	97.5978	-	-	-	-	-
0.0241	468	67.4161	-	-	-	-	-
0.0261	507	52.7053	-	-	-	-	-
0.0281	546	45.7155	-	-	-	-	-
0.0301	585	41.9731	41.3247	0.4712 (-0.0692)	0.2975 (-0.0275)	0.4695 (-0.0311)	0.4127 (-0.0426)
0.0321	624	39.3177	-	-	-	-	-
0.0341	663	36.7606	-	-	-	-	-
0.0362	702	34.6954	-	-	-	-	-
0.0382	741	33.4444	-	-	-	-	-
0.0402	780	31.8238	31.8207	0.5084 (-0.0320)	0.3346 (+0.0096)	0.5137 (+0.0131)	0.4522 (-0.0031)
0.0422	819	30.6819	-	-	-	-	-
0.0442	858	29.4152	-	-	-	-	-
0.0462	897	28.4563	-	-	-	-	-
0.0482	936	27.38	-	-	-	-	-
0.0502	975	26.8008	27.3043	0.4982 (-0.0422)	0.3449 (+0.0198)	0.5200 (+0.0194)	0.4544 (-0.0010)
0.0522	1014	26.0336	-	-	-	-	-
0.0542	1053	25.3375	-	-	-	-	-
0.0562	1092	24.9918	-	-	-	-	-
0.0582	1131	24.1657	-	-	-	-	-
0.0603	1170	24.4028	24.2684	0.5504 (+0.0100)	0.3672 (+0.0422)	0.5478 (+0.0471)	0.4885 (+0.0331)
0.0623	1209	23.3062	-	-	-	-	-
0.0643	1248	22.7702	-	-	-	-	-
0.0663	1287	22.4086	-	-	-	-	-
0.0683	1326	21.9251	-	-	-	-	-
0.0703	1365	21.9175	21.9635	0.5852 (+0.0448)	0.3549 (+0.0299)	0.5656 (+0.0649)	0.5019 (+0.0465)
0.0723	1404	20.9865	-	-	-	-	-
0.0743	1443	20.8581	-	-	-	-	-
0.0763	1482	20.584	-	-	-	-	-
0.0783	1521	19.8788	-	-	-	-	-
0.0803	1560	19.6365	19.9889	0.5988 (+0.0583)	0.3533 (+0.0283)	0.5369 (+0.0362)	0.4963 (+0.0409)
0.0823	1599	19.2009	-	-	-	-	-
0.0844	1638	18.9352	-	-	-	-	-
0.0864	1677	18.7044	-	-	-	-	-
0.0884	1716	18.3696	-	-	-	-	-
0.0904	1755	18.223	18.6559	0.6300 (+0.0896)	0.3561 (+0.0311)	0.5659 (+0.0652)	0.5173 (+0.0620)
0.0924	1794	18.1149	-	-	-	-	-
0.0944	1833	17.5771	-	-	-	-	-
0.0964	1872	17.2442	-	-	-	-	-
0.0984	1911	16.8317	-	-	-	-	-
0.1004	1950	16.8462	17.0786	0.6294 (+0.0890)	0.3552 (+0.0302)	0.5643 (+0.0637)	0.5163 (+0.0609)
0.1024	1989	16.5298	-	-	-	-	-
0.1044	2028	16.4289	-	-	-	-	-
0.1064	2067	16.0292	-	-	-	-	-
0.1085	2106	15.8428	-	-	-	-	-
0.1105	2145	15.7437	16.0163	0.6269 (+0.0865)	0.3538 (+0.0287)	0.5752 (+0.0746)	0.5186 (+0.0633)
0.1125	2184	15.7076	-	-	-	-	-
0.1145	2223	15.3865	-	-	-	-	-
0.1165	2262	15.174	-	-	-	-	-
0.1185	2301	15.0104	-	-	-	-	-
0.1205	2340	14.8128	14.9314	0.6112 (+0.0708)	0.3625 (+0.0375)	0.5936 (+0.0929)	0.5225 (+0.0671)
0.1225	2379	14.407	-	-	-	-	-
0.1245	2418	14.3549	-	-	-	-	-
0.1265	2457	14.3104	-	-	-	-	-
0.1285	2496	14.0911	-	-	-	-	-
0.1305	2535	13.8692	14.5249	0.6153 (+0.0749)	0.3644 (+0.0393)	0.5976 (+0.0969)	0.5258 (+0.0704)
0.1326	2574	13.9886	-	-	-	-	-
0.1346	2613	13.5694	-	-	-	-	-
0.1366	2652	13.6723	-	-	-	-	-
0.1386	2691	13.5047	-	-	-	-	-
0.1406	2730	13.3759	13.6388	0.6318 (+0.0914)	0.3578 (+0.0327)	0.5819 (+0.0812)	0.5238 (+0.0685)
0.1426	2769	13.042	-	-	-	-	-
0.1446	2808	13.2039	-	-	-	-	-
0.1466	2847	12.9865	-	-	-	-	-
0.1486	2886	13.0293	-	-	-	-	-
0.1506	2925	12.7206	12.6907	0.6392 (+0.0988)	0.3649 (+0.0399)	0.5919 (+0.0912)	0.5320 (+0.0766)
0.1526	2964	12.5802	-	-	-	-	-
0.1546	3003	12.7734	-	-	-	-	-
0.1567	3042	12.4192	-	-	-	-	-
0.1587	3081	12.3157	-	-	-	-	-
0.1607	3120	12.384	12.5061	0.6382 (+0.0978)	0.3784 (+0.0533)	0.5907 (+0.0901)	0.5358 (+0.0804)
0.1627	3159	12.0562	-	-	-	-	-
0.1647	3198	12.1539	-	-	-	-	-
0.1667	3237	12.0754	-	-	-	-	-
0.1687	3276	11.8814	-	-	-	-	-
0.1707	3315	11.7829	11.9039	0.6371 (+0.0967)	0.3818 (+0.0568)	0.5998 (+0.0992)	0.5396 (+0.0842)
0.1727	3354	11.8772	-	-	-	-	-
0.1747	3393	11.8422	-	-	-	-	-
0.1767	3432	11.6353	-	-	-	-	-
0.1787	3471	11.584	-	-	-	-	-
0.1808	3510	11.443	11.8674	0.6317 (+0.0912)	0.3828 (+0.0578)	0.6080 (+0.1073)	0.5408 (+0.0854)
0.1828	3549	11.475	-	-	-	-	-
0.1848	3588	11.1514	-	-	-	-	-
0.1868	3627	11.3053	-	-	-	-	-
0.1888	3666	11.0035	-	-	-	-	-
0.1908	3705	11.1834	11.4955	0.6333 (+0.0928)	0.3642 (+0.0392)	0.6094 (+0.1087)	0.5356 (+0.0803)
0.1928	3744	10.8977	-	-	-	-	-
0.1948	3783	10.9302	-	-	-	-	-
0.1968	3822	10.8946	-	-	-	-	-
0.1988	3861	10.821	-	-	-	-	-
0.2008	3900	10.8044	11.0295	0.6262 (+0.0858)	0.3784 (+0.0533)	0.6098 (+0.1091)	0.5381 (+0.0828)
0.2028	3939	10.6379	-	-	-	-	-
0.2049	3978	10.6515	-	-	-	-	-
0.2069	4017	10.4407	-	-	-	-	-
0.2089	4056	10.4732	-	-	-	-	-
0.2109	4095	10.3832	10.6019	0.6286 (+0.0882)	0.3631 (+0.0381)	0.6167 (+0.1161)	0.5362 (+0.0808)
0.2129	4134	10.4307	-	-	-	-	-
0.2149	4173	10.3511	-	-	-	-	-
0.2169	4212	10.2797	-	-	-	-	-
0.2189	4251	10.2157	-	-	-	-	-
0.2209	4290	10.2122	10.3425	0.6281 (+0.0877)	0.3868 (+0.0617)	0.5901 (+0.0895)	0.5350 (+0.0796)
0.2229	4329	10.185	-	-	-	-	-
0.2249	4368	10.163	-	-	-	-	-
0.2269	4407	10.1477	-	-	-	-	-
0.2290	4446	9.9438	-	-	-	-	-
0.2310	4485	9.9041	10.1282	0.6452 (+0.1048)	0.3772 (+0.0522)	0.6136 (+0.1130)	0.5454 (+0.0900)
0.2330	4524	9.8034	-	-	-	-	-
0.2350	4563	9.7994	-	-	-	-	-
0.2370	4602	9.9711	-	-	-	-	-
0.2390	4641	9.7652	-	-	-	-	-
0.2410	4680	9.6757	9.7409	0.6364 (+0.0960)	0.3800 (+0.0550)	0.6095 (+0.1088)	0.5420 (+0.0866)
0.2430	4719	9.558	-	-	-	-	-
0.2450	4758	9.6791	-	-	-	-	-
0.2470	4797	9.5759	-	-	-	-	-
0.2490	4836	9.4958	-	-	-	-	-
0.2510	4875	9.487	9.5897	0.6479 (+0.1075)	0.3734 (+0.0484)	0.6261 (+0.1255)	0.5492 (+0.0938)
0.2531	4914	9.4796	-	-	-	-	-
0.2551	4953	9.3878	-	-	-	-	-
0.2571	4992	9.3888	-	-	-	-	-
0.2591	5031	9.2657	-	-	-	-	-
0.2611	5070	9.1936	9.2371	0.6296 (+0.0892)	0.3857 (+0.0607)	0.6220 (+0.1213)	0.5458 (+0.0904)
0.2631	5109	9.2403	-	-	-	-	-
0.2651	5148	9.1963	-	-	-	-	-
0.2671	5187	9.066	-	-	-	-	-
0.2691	5226	9.1684	-	-	-	-	-
0.2711	5265	9.1036	9.1932	0.6188 (+0.0784)	0.3803 (+0.0552)	0.6280 (+0.1274)	0.5424 (+0.0870)
0.2731	5304	9.0206	-	-	-	-	-
0.2751	5343	9.2051	-	-	-	-	-
0.2772	5382	9.1335	-	-	-	-	-
0.2792	5421	8.9798	-	-	-	-	-
0.2812	5460	8.9199	9.0195	0.6210 (+0.0805)	0.3939 (+0.0688)	0.6178 (+0.1172)	0.5442 (+0.0888)
0.2832	5499	8.8599	-	-	-	-	-
0.2852	5538	8.7977	-	-	-	-	-
0.2872	5577	8.7378	-	-	-	-	-
0.2892	5616	8.7338	-	-	-	-	-
0.2912	5655	8.6566	8.8711	0.6308 (+0.0904)	0.3885 (+0.0635)	0.6194 (+0.1188)	0.5463 (+0.0909)
0.2932	5694	8.8228	-	-	-	-	-
0.2952	5733	8.6837	-	-	-	-	-
0.2972	5772	8.6967	-	-	-	-	-
0.2992	5811	8.6721	-	-	-	-	-
0.3013	5850	8.5856	8.4996	0.6424 (+0.1020)	0.3820 (+0.0569)	0.6268 (+0.1261)	0.5504 (+0.0950)
0.3033	5889	8.5552	-	-	-	-	-
0.3053	5928	8.4364	-	-	-	-	-
0.3073	5967	8.4726	-	-	-	-	-
0.3093	6006	8.6169	-	-	-	-	-
0.3113	6045	8.4303	8.4561	0.6142 (+0.0738)	0.3720 (+0.0470)	0.6226 (+0.1220)	0.5363 (+0.0809)
0.3133	6084	8.5336	-	-	-	-	-
0.3153	6123	8.3723	-	-	-	-	-
0.3173	6162	8.358	-	-	-	-	-
0.3193	6201	8.3435	-	-	-	-	-
0.3213	6240	8.2638	8.3670	0.6346 (+0.0941)	0.3838 (+0.0587)	0.6229 (+0.1222)	0.5471 (+0.0917)
0.3233	6279	8.2994	-	-	-	-	-
0.3254	6318	8.1733	-	-	-	-	-
0.3274	6357	8.2564	-	-	-	-	-
0.3294	6396	8.212	-	-	-	-	-
0.3314	6435	8.1111	8.3150	0.6385 (+0.0981)	0.3828 (+0.0578)	0.6353 (+0.1346)	0.5522 (+0.0968)
0.3334	6474	8.1655	-	-	-	-	-
0.3354	6513	8.0391	-	-	-	-	-
0.3374	6552	8.0784	-	-	-	-	-
0.3394	6591	8.0369	-	-	-	-	-
0.3414	6630	8.012	8.0672	0.6191 (+0.0787)	0.3899 (+0.0648)	0.6482 (+0.1475)	0.5524 (+0.0970)
0.3434	6669	7.9809	-	-	-	-	-
0.3454	6708	8.0001	-	-	-	-	-
0.3474	6747	8.009	-	-	-	-	-
0.3495	6786	7.9692	-	-	-	-	-
0.3515	6825	7.8565	7.9072	0.6220 (+0.0815)	0.3866 (+0.0616)	0.6154 (+0.1147)	0.5413 (+0.0859)
0.3535	6864	7.9108	-	-	-	-	-
0.3555	6903	7.7341	-	-	-	-	-
0.3575	6942	7.8442	-	-	-	-	-
0.3595	6981	7.912	-	-	-	-	-
0.3615	7020	7.7133	8.0526	0.6389 (+0.0985)	0.3991 (+0.0740)	0.6408 (+0.1402)	0.5596 (+0.1042)
0.3635	7059	7.8985	-	-	-	-	-
0.3655	7098	7.6834	-	-	-	-	-
0.3675	7137	7.7494	-	-	-	-	-
0.3695	7176	7.7146	-	-	-	-	-
0.3715	7215	7.6553	7.8366	0.6338 (+0.0934)	0.3992 (+0.0742)	0.6253 (+0.1247)	0.5528 (+0.0974)
0.3736	7254	7.612	-	-	-	-	-
0.3756	7293	7.6707	-	-	-	-	-
0.3776	7332	7.716	-	-	-	-	-
0.3796	7371	7.7436	-	-	-	-	-
0.3816	7410	7.6003	7.6881	0.6307 (+0.0902)	0.4029 (+0.0779)	0.6334 (+0.1327)	0.5556 (+0.1003)
0.3836	7449	7.5153	-	-	-	-	-
0.3856	7488	7.5351	-	-	-	-	-
0.3876	7527	7.5687	-	-	-	-	-
0.3896	7566	7.5155	-	-	-	-	-
0.3916	7605	7.4451	7.6049	0.6321 (+0.0916)	0.3914 (+0.0664)	0.6358 (+0.1352)	0.5531 (+0.0977)
0.3936	7644	7.5113	-	-	-	-	-
0.3956	7683	7.5135	-	-	-	-	-
0.3977	7722	7.4258	-	-	-	-	-
0.3997	7761	7.458	-	-	-	-	-
0.4017	7800	7.3602	7.4536	0.6472 (+0.1067)	0.4034 (+0.0783)	0.6372 (+0.1365)	0.5626 (+0.1072)
0.4037	7839	7.4779	-	-	-	-	-
0.4057	7878	7.4154	-	-	-	-	-
0.4077	7917	7.2897	-	-	-	-	-
0.4097	7956	7.3614	-	-	-	-	-
0.4117	7995	7.2537	7.4876	0.6298 (+0.0893)	0.3999 (+0.0749)	0.6318 (+0.1312)	0.5538 (+0.0985)
0.4137	8034	7.2474	-	-	-	-	-
0.4157	8073	7.2166	-	-	-	-	-
0.4177	8112	7.2344	-	-	-	-	-
0.4197	8151	7.2647	-	-	-	-	-
0.4218	8190	7.2618	7.4345	0.6347 (+0.0943)	0.4057 (+0.0806)	0.6289 (+0.1282)	0.5564 (+0.1010)
0.4238	8229	7.2227	-	-	-	-	-
0.4258	8268	7.2384	-	-	-	-	-
0.4278	8307	7.2133	-	-	-	-	-
0.4298	8346	7.1558	-	-	-	-	-
0.4318	8385	7.0712	7.2899	0.6523 (+0.1119)	0.4027 (+0.0777)	0.6341 (+0.1335)	0.5631 (+0.1077)
0.4338	8424	7.1063	-	-	-	-	-
0.4358	8463	7.0908	-	-	-	-	-
0.4378	8502	7.1122	-	-	-	-	-
0.4398	8541	7.1549	-	-	-	-	-
0.4418	8580	7.0516	7.2487	0.6553 (+0.1148)	0.3955 (+0.0705)	0.6399 (+0.1392)	0.5635 (+0.1082)
0.4438	8619	7.0792	-	-	-	-	-
0.4459	8658	7.0351	-	-	-	-	-
0.4479	8697	7.0315	-	-	-	-	-
0.4499	8736	6.9912	-	-	-	-	-
0.4519	8775	7.0102	7.0829	0.6569 (+0.1165)	0.3949 (+0.0698)	0.6534 (+0.1527)	0.5684 (+0.1130)
0.4539	8814	6.9478	-	-	-	-	-
0.4559	8853	6.9741	-	-	-	-	-
0.4579	8892	7.0344	-	-	-	-	-
0.4599	8931	6.907	-	-	-	-	-
0.4619	8970	6.9089	7.0948	0.6369 (+0.0964)	0.3976 (+0.0725)	0.6367 (+0.1360)	0.5570 (+0.1017)
0.4639	9009	6.9295	-	-	-	-	-
0.4659	9048	6.863	-	-	-	-	-
0.4679	9087	6.9167	-	-	-	-	-
0.4700	9126	6.9123	-	-	-	-	-
0.4720	9165	6.8659	6.9749	0.6478 (+0.1073)	0.3977 (+0.0727)	0.6420 (+0.1414)	0.5625 (+0.1071)
0.4740	9204	6.8238	-	-	-	-	-
0.4760	9243	6.7847	-	-	-	-	-
0.4780	9282	6.7687	-	-	-	-	-
0.4800	9321	6.8748	-	-	-	-	-
0.4820	9360	6.7392	6.9672	0.6469 (+0.1064)	0.4037 (+0.0787)	0.6375 (+0.1369)	0.5627 (+0.1073)
0.4840	9399	6.6911	-	-	-	-	-
0.4860	9438	6.6688	-	-	-	-	-
0.4880	9477	6.7891	-	-	-	-	-
0.4900	9516	6.7704	-	-	-	-	-
0.4920	9555	6.7022	6.8938	0.6519 (+0.1115)	0.4040 (+0.0789)	0.6484 (+0.1477)	0.5681 (+0.1127)
0.4941	9594	6.7143	-	-	-	-	-
0.4961	9633	6.6628	-	-	-	-	-
0.4981	9672	6.7368	-	-	-	-	-
0.5001	9711	6.5205	-	-	-	-	-
0.5021	9750	6.6955	6.8142	0.6485 (+0.1081)	0.3968 (+0.0718)	0.6302 (+0.1296)	0.5585 (+0.1032)
0.5041	9789	6.6244	-	-	-	-	-
0.5061	9828	6.6949	-	-	-	-	-
0.5081	9867	6.5489	-	-	-	-	-
0.5101	9906	6.6067	-	-	-	-	-
0.5121	9945	6.5962	6.7924	0.6574 (+0.1170)	0.3910 (+0.0660)	0.6459 (+0.1452)	0.5648 (+0.1094)
0.5141	9984	6.5248	-	-	-	-	-
0.5161	10023	6.5204	-	-	-	-	-
0.5182	10062	6.5291	-	-	-	-	-
0.5202	10101	6.5512	-	-	-	-	-
0.5222	10140	6.4731	6.7636	0.6638 (+0.1234)	0.3973 (+0.0722)	0.6433 (+0.1426)	0.5681 (+0.1128)
0.5242	10179	6.5327	-	-	-	-	-
0.5262	10218	6.5019	-	-	-	-	-
0.5282	10257	6.5113	-	-	-	-	-
0.5302	10296	6.5181	-	-	-	-	-
0.5322	10335	6.4987	6.6856	0.6656 (+0.1252)	0.3946 (+0.0695)	0.6501 (+0.1494)	0.5701 (+0.1147)
0.5342	10374	6.4575	-	-	-	-	-
0.5362	10413	6.4239	-	-	-	-	-
0.5382	10452	6.4181	-	-	-	-	-
0.5402	10491	6.3535	-	-	-	-	-
0.5423	10530	6.4066	6.6634	0.6482 (+0.1078)	0.3993 (+0.0743)	0.6449 (+0.1442)	0.5641 (+0.1088)
0.5443	10569	6.4005	-	-	-	-	-
0.5463	10608	6.4521	-	-	-	-	-
0.5483	10647	6.4178	-	-	-	-	-
0.5503	10686	6.3495	-	-	-	-	-
0.5523	10725	6.3246	6.6161	0.6434 (+0.1030)	0.3915 (+0.0664)	0.6426 (+0.1420)	0.5592 (+0.1038)
0.5543	10764	6.4175	-	-	-	-	-
0.5563	10803	6.3035	-	-	-	-	-
0.5583	10842	6.2432	-	-	-	-	-
0.5603	10881	6.3024	-	-	-	-	-
0.5623	10920	6.4134	6.4813	0.6441 (+0.1037)	0.3936 (+0.0685)	0.6392 (+0.1386)	0.5590 (+0.1036)
0.5643	10959	6.2943	-	-	-	-	-
0.5664	10998	6.2934	-	-	-	-	-
0.5684	11037	6.3379	-	-	-	-	-
0.5704	11076	6.2481	-	-	-	-	-
0.5724	11115	6.256	6.4519	0.6371 (+0.0967)	0.3985 (+0.0735)	0.6343 (+0.1336)	0.5566 (+0.1013)
0.5744	11154	6.2639	-	-	-	-	-
0.5764	11193	6.2727	-	-	-	-	-
0.5784	11232	6.2347	-	-	-	-	-
0.5804	11271	6.3073	-	-	-	-	-
0.5824	11310	6.2281	6.3956	0.6336 (+0.0932)	0.3973 (+0.0723)	0.6454 (+0.1448)	0.5588 (+0.1034)
0.5844	11349	6.0973	-	-	-	-	-
0.5864	11388	6.282	-	-	-	-	-
0.5884	11427	6.1308	-	-	-	-	-
0.5905	11466	6.0991	-	-	-	-	-
0.5925	11505	6.2648	6.3232	0.6362 (+0.0958)	0.3943 (+0.0693)	0.6527 (+0.1520)	0.5611 (+0.1057)
0.5945	11544	6.1303	-	-	-	-	-
0.5965	11583	6.2142	-	-	-	-	-
0.5985	11622	6.115	-	-	-	-	-
0.6005	11661	6.1109	-	-	-	-	-
0.6025	11700	6.2147	6.3124	0.6190 (+0.0785)	0.3905 (+0.0654)	0.6544 (+0.1538)	0.5546 (+0.0993)
0.6045	11739	6.1101	-	-	-	-	-
0.6065	11778	6.1246	-	-	-	-	-
0.6085	11817	6.0777	-	-	-	-	-
0.6105	11856	6.1565	-	-	-	-	-
0.6125	11895	5.9654	6.2800	0.6371 (+0.0967)	0.3990 (+0.0740)	0.6534 (+0.1528)	0.5632 (+0.1078)
0.6146	11934	6.0115	-	-	-	-	-
0.6166	11973	6.0402	-	-	-	-	-
0.6186	12012	6.1312	-	-	-	-	-
0.6206	12051	6.0977	-	-	-	-	-
0.6226	12090	6.1147	6.2629	0.6438 (+0.1033)	0.3997 (+0.0746)	0.6595 (+0.1589)	0.5676 (+0.1123)
0.6246	12129	6.0727	-	-	-	-	-
0.6266	12168	6.0468	-	-	-	-	-
0.6286	12207	6.022	-	-	-	-	-
0.6306	12246	5.9995	-	-	-	-	-
0.6326	12285	6.0553	6.2714	0.6511 (+0.1107)	0.3965 (+0.0714)	0.6490 (+0.1483)	0.5655 (+0.1102)
0.6346	12324	6.0713	-	-	-	-	-
0.6366	12363	5.9443	-	-	-	-	-
0.6387	12402	6.0045	-	-	-	-	-
0.6407	12441	5.9835	-	-	-	-	-
0.6427	12480	5.9936	6.1741	0.6330 (+0.0926)	0.3993 (+0.0743)	0.6452 (+0.1446)	0.5592 (+0.1038)
0.6447	12519	5.9637	-	-	-	-	-
0.6467	12558	5.9407	-	-	-	-	-
0.6487	12597	5.8556	-	-	-	-	-
0.6507	12636	6.0084	-	-	-	-	-
0.6527	12675	6.0038	6.1379	0.6555 (+0.1150)	0.3981 (+0.0731)	0.6501 (+0.1495)	0.5679 (+0.1125)
0.6547	12714	5.8648	-	-	-	-	-
0.6567	12753	5.9154	-	-	-	-	-
0.6587	12792	5.9591	-	-	-	-	-
0.6607	12831	5.9369	-	-	-	-	-
0.6628	12870	5.8238	6.1443	0.6430 (+0.1026)	0.3945 (+0.0694)	0.6621 (+0.1614)	0.5665 (+0.1111)
0.6648	12909	5.8622	-	-	-	-	-
0.6668	12948	5.9296	-	-	-	-	-
0.6688	12987	5.8676	-	-	-	-	-
0.6708	13026	5.8811	-	-	-	-	-
0.6728	13065	5.9176	6.0863	0.6422 (+0.1018)	0.3931 (+0.0681)	0.6651 (+0.1644)	0.5668 (+0.1114)
0.6748	13104	5.8536	-	-	-	-	-
0.6768	13143	5.8865	-	-	-	-	-
0.6788	13182	5.7893	-	-	-	-	-
0.6808	13221	5.8791	-	-	-	-	-
0.6828	13260	5.8686	6.0588	0.6384 (+0.0979)	0.3980 (+0.0730)	0.6555 (+0.1548)	0.5640 (+0.1086)
0.6848	13299	5.8052	-	-	-	-	-
0.6869	13338	5.8452	-	-	-	-	-
0.6889	13377	5.8033	-	-	-	-	-
0.6909	13416	5.7734	-	-	-	-	-
0.6929	13455	5.7619	5.9937	0.6524 (+0.1120)	0.3965 (+0.0714)	0.6505 (+0.1498)	0.5664 (+0.1111)
0.6949	13494	5.7637	-	-	-	-	-
0.6969	13533	5.7513	-	-	-	-	-
0.6989	13572	5.8172	-	-	-	-	-
0.7009	13611	5.8323	-	-	-	-	-
0.7029	13650	5.76	5.9823	0.6451 (+0.1047)	0.4061 (+0.0810)	0.6428 (+0.1421)	0.5646 (+0.1093)
0.7049	13689	5.7541	-	-	-	-	-
0.7069	13728	5.7465	-	-	-	-	-
0.7089	13767	5.8207	-	-	-	-	-
0.7110	13806	5.7531	-	-	-	-	-
0.7130	13845	5.7436	5.9584	0.6417 (+0.1012)	0.4021 (+0.0771)	0.6469 (+0.1462)	0.5636 (+0.1082)
0.7150	13884	5.6921	-	-	-	-	-
0.7170	13923	5.6492	-	-	-	-	-
0.7190	13962	5.7005	-	-	-	-	-
0.7210	14001	5.7808	-	-	-	-	-
0.7230	14040	5.7058	5.9436	0.6403 (+0.0998)	0.3904 (+0.0654)	0.6602 (+0.1595)	0.5636 (+0.1083)
0.7250	14079	5.7288	-	-	-	-	-
0.7270	14118	5.6235	-	-	-	-	-
0.7290	14157	5.6438	-	-	-	-	-
0.7310	14196	5.6733	-	-	-	-	-
0.7330	14235	5.7588	5.9466	0.6583 (+0.1179)	0.3944 (+0.0693)	0.6479 (+0.1473)	0.5669 (+0.1115)
0.7351	14274	5.6172	-	-	-	-	-
0.7371	14313	5.649	-	-	-	-	-
0.7391	14352	5.7198	-	-	-	-	-
0.7411	14391	5.627	-	-	-	-	-
0.7431	14430	5.6958	5.8615	0.6463 (+0.1058)	0.3905 (+0.0654)	0.6619 (+0.1613)	0.5662 (+0.1109)
0.7451	14469	5.6216	-	-	-	-	-
0.7471	14508	5.5954	-	-	-	-	-
0.7491	14547	5.5794	-	-	-	-	-
0.7511	14586	5.6821	-	-	-	-	-
0.7531	14625	5.5987	5.8702	0.6436 (+0.1032)	0.3936 (+0.0685)	0.6563 (+0.1557)	0.5645 (+0.1091)
0.7551	14664	5.6134	-	-	-	-	-
0.7571	14703	5.6476	-	-	-	-	-
0.7592	14742	5.679	-	-	-	-	-
0.7612	14781	5.6292	-	-	-	-	-
0.7632	14820	5.6129	5.8149	0.6454 (+0.1049)	0.3949 (+0.0699)	0.6553 (+0.1546)	0.5652 (+0.1098)
0.7652	14859	5.5883	-	-	-	-	-
0.7672	14898	5.6431	-	-	-	-	-
0.7692	14937	5.5464	-	-	-	-	-
0.7712	14976	5.6273	-	-	-	-	-
0.7732	15015	5.6428	5.8067	0.6576 (+0.1172)	0.3996 (+0.0745)	0.6720 (+0.1714)	0.5764 (+0.1210)
0.7752	15054	5.4733	-	-	-	-	-
0.7772	15093	5.5618	-	-	-	-	-
0.7792	15132	5.5804	-	-	-	-	-
0.7812	15171	5.5858	-	-	-	-	-
0.7833	15210	5.4994	5.7438	0.6424 (+0.1019)	0.3973 (+0.0722)	0.6573 (+0.1566)	0.5656 (+0.1103)
0.7853	15249	5.5405	-	-	-	-	-
0.7873	15288	5.5032	-	-	-	-	-
0.7893	15327	5.5755	-	-	-	-	-
0.7913	15366	5.4816	-	-	-	-	-
0.7933	15405	5.4922	5.7130	0.6523 (+0.1118)	0.3851 (+0.0601)	0.6633 (+0.1626)	0.5669 (+0.1115)
0.7953	15444	5.5049	-	-	-	-	-
0.7973	15483	5.5061	-	-	-	-	-
0.7993	15522	5.5243	-	-	-	-	-
0.8013	15561	5.4995	-	-	-	-	-
0.8033	15600	5.5222	5.7124	0.6440 (+0.1035)	0.3981 (+0.0731)	0.6695 (+0.1689)	0.5705 (+0.1152)
0.8053	15639	5.5646	-	-	-	-	-
0.8074	15678	5.5963	-	-	-	-	-
0.8094	15717	5.5167	-	-	-	-	-
0.8114	15756	5.5645	-	-	-	-	-
0.8134	15795	5.4805	5.7093	0.6571 (+0.1167)	0.3948 (+0.0697)	0.6566 (+0.1560)	0.5695 (+0.1141)
0.8154	15834	5.5332	-	-	-	-	-
0.8174	15873	5.4952	-	-	-	-	-
0.8194	15912	5.5312	-	-	-	-	-
0.8214	15951	5.5023	-	-	-	-	-
0.8234	15990	5.3999	5.6825	0.6641 (+0.1237)	0.3984 (+0.0734)	0.6575 (+0.1569)	0.5733 (+0.1180)
0.8254	16029	5.4961	-	-	-	-	-
0.8274	16068	5.5271	-	-	-	-	-
0.8294	16107	5.4806	-	-	-	-	-
0.8315	16146	5.4955	-	-	-	-	-
0.8335	16185	5.4969	5.6419	0.6576 (+0.1172)	0.4014 (+0.0763)	0.6578 (+0.1572)	0.5723 (+0.1169)
0.8355	16224	5.4633	-	-	-	-	-
0.8375	16263	5.4822	-	-	-	-	-
0.8395	16302	5.4476	-	-	-	-	-
0.8415	16341	5.4727	-	-	-	-	-
0.8435	16380	5.4001	5.5943	0.6513 (+0.1109)	0.4057 (+0.0806)	0.6477 (+0.1471)	0.5682 (+0.1129)
0.8455	16419	5.4684	-	-	-	-	-
0.8475	16458	5.4463	-	-	-	-	-
0.8495	16497	5.4672	-	-	-	-	-
0.8515	16536	5.4415	-	-	-	-	-
0.8535	16575	5.4633	5.6234	0.6645 (+0.1241)	0.3943 (+0.0693)	0.6620 (+0.1614)	0.5736 (+0.1183)
0.8556	16614	5.3845	-	-	-	-	-
0.8576	16653	5.4805	-	-	-	-	-
0.8596	16692	5.4391	-	-	-	-	-
0.8616	16731	5.382	-	-	-	-	-
0.8636	16770	5.4113	5.5914	0.6645 (+0.1241)	0.3938 (+0.0688)	0.6598 (+0.1591)	0.5727 (+0.1173)
0.8656	16809	5.4142	-	-	-	-	-
0.8676	16848	5.3805	-	-	-	-	-
0.8696	16887	5.4068	-	-	-	-	-
0.8716	16926	5.392	-	-	-	-	-
0.8736	16965	5.4121	5.5925	0.6592 (+0.1188)	0.4029 (+0.0779)	0.6473 (+0.1466)	0.5698 (+0.1144)
0.8756	17004	5.3969	-	-	-	-	-
0.8776	17043	5.4349	-	-	-	-	-
0.8797	17082	5.3231	-	-	-	-	-
0.8817	17121	5.3217	-	-	-	-	-
0.8837	17160	5.3942	5.5690	0.6619 (+0.1215)	0.3941 (+0.0690)	0.6603 (+0.1597)	0.5721 (+0.1167)
0.8857	17199	5.3824	-	-	-	-	-
0.8877	17238	5.3817	-	-	-	-	-
0.8897	17277	5.3159	-	-	-	-	-
0.8917	17316	5.3866	-	-	-	-	-
0.8937	17355	5.3396	5.5496	0.6645 (+0.1241)	0.3996 (+0.0745)	0.6525 (+0.1518)	0.5722 (+0.1168)
0.8957	17394	5.4085	-	-	-	-	-
0.8977	17433	5.3788	-	-	-	-	-
0.8997	17472	5.3739	-	-	-	-	-
0.9017	17511	5.3322	-	-	-	-	-
0.9038	17550	5.3472	5.5212	0.6513 (+0.1109)	0.4041 (+0.0791)	0.6607 (+0.1601)	0.5721 (+0.1167)
0.9058	17589	5.3451	-	-	-	-	-
0.9078	17628	5.3297	-	-	-	-	-
0.9098	17667	5.3158	-	-	-	-	-
0.9118	17706	5.363	-	-	-	-	-
0.9138	17745	5.3346	5.5014	0.6650 (+0.1245)	0.3989 (+0.0739)	0.6602 (+0.1595)	0.5747 (+0.1193)
0.9158	17784	5.3702	-	-	-	-	-
0.9178	17823	5.4226	-	-	-	-	-
0.9198	17862	5.3099	-	-	-	-	-
0.9218	17901	5.3468	-	-	-	-	-
0.9238	17940	5.3903	5.5093	0.6523 (+0.1118)	0.4000 (+0.0750)	0.6624 (+0.1618)	0.5716 (+0.1162)
0.9258	17979	5.3288	-	-	-	-	-
0.9279	18018	5.3464	-	-	-	-	-
0.9299	18057	5.2696	-	-	-	-	-
0.9319	18096	5.3532	-	-	-	-	-
0.9339	18135	5.3093	5.4815	0.6518 (+0.1114)	0.4021 (+0.0771)	0.6689 (+0.1683)	0.5743 (+0.1189)
0.9359	18174	5.3378	-	-	-	-	-
0.9379	18213	5.3576	-	-	-	-	-
0.9399	18252	5.3102	-	-	-	-	-
0.9419	18291	5.3322	-	-	-	-	-
0.9439	18330	5.3015	5.4963	0.6645 (+0.1241)	0.3980 (+0.0729)	0.6573 (+0.1566)	0.5732 (+0.1179)
0.9459	18369	5.2332	-	-	-	-	-
0.9479	18408	5.2934	-	-	-	-	-
0.9499	18447	5.3187	-	-	-	-	-
0.9520	18486	5.2961	-	-	-	-	-
0.9540	18525	5.2884	5.4628	0.6654 (+0.1250)	0.3982 (+0.0731)	0.6628 (+0.1621)	0.5754 (+0.1201)
0.9560	18564	5.277	-	-	-	-	-
0.9580	18603	5.3364	-	-	-	-	-
0.9600	18642	5.2839	-	-	-	-	-
0.9620	18681	5.2503	-	-	-	-	-
0.9640	18720	5.2547	5.4463	0.6596 (+0.1192)	0.3981 (+0.0730)	0.6642 (+0.1635)	0.5740 (+0.1186)
0.9660	18759	5.2803	-	-	-	-	-
0.9680	18798	5.3167	-	-	-	-	-
0.9700	18837	5.2781	-	-	-	-	-
0.9720	18876	5.2809	-	-	-	-	-
0.9740	18915	5.2917	5.4579	0.6596 (+0.1192)	0.4000 (+0.0749)	0.6689 (+0.1683)	0.5762 (+0.1208)
0.9761	18954	5.2893	-	-	-	-	-
0.9781	18993	5.3301	-	-	-	-	-
0.9801	19032	5.2753	-	-	-	-	-
0.9821	19071	5.2079	-	-	-	-	-
0.9841	19110	5.2672	5.4520	0.6592 (+0.1188)	0.3989 (+0.0738)	0.6689 (+0.1683)	0.5757 (+0.1203)
0.9861	19149	5.268	-	-	-	-	-
0.9881	19188	5.224	-	-	-	-	-
0.9901	19227	5.3047	-	-	-	-	-
0.9921	19266	5.2771	-	-	-	-	-
0.9941	19305	5.233	5.4545	0.6592 (+0.1188)	0.4003 (+0.0752)	0.6689 (+0.1683)	0.5761 (+0.1208)
0.9961	19344	5.2459	-	-	-	-	-
0.9981	19383	5.3069	-	-	-	-	-
-1	-1	-	-	0.6576 (+0.1172)	0.3996 (+0.0745)	0.6720 (+0.1714)	0.5764 (+0.1210)

The bold row denotes the saved checkpoint.

Environmental Impact

Carbon emissions were measured using CodeCarbon.

Energy Consumed: 4.348 kWh
Carbon Emitted: 1.605 kg of CO2
Hours Used: 1.576 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}
}