metadata

base_model: sentence-transformers/all-mpnet-base-v2
datasets: []
language: []
library_name: sentence-transformers
metrics:
  - cosine_accuracy
  - cosine_accuracy_threshold
  - cosine_f1
  - cosine_f1_threshold
  - cosine_precision
  - cosine_recall
  - cosine_ap
  - dot_accuracy
  - dot_accuracy_threshold
  - dot_f1
  - dot_f1_threshold
  - dot_precision
  - dot_recall
  - dot_ap
  - manhattan_accuracy
  - manhattan_accuracy_threshold
  - manhattan_f1
  - manhattan_f1_threshold
  - manhattan_precision
  - manhattan_recall
  - manhattan_ap
  - euclidean_accuracy
  - euclidean_accuracy_threshold
  - euclidean_f1
  - euclidean_f1_threshold
  - euclidean_precision
  - euclidean_recall
  - euclidean_ap
  - max_accuracy
  - max_accuracy_threshold
  - max_f1
  - max_f1_threshold
  - max_precision
  - max_recall
  - max_ap
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:645861
  - loss:ContrastiveLoss
widget:
  - source_sentence: There was an Eye OS alert.
    sentences:
      - i see lots of tubes
      - On the door is lima mike zero twenty three north exit
      - EyeOS, that’s some kind of tech, right
  - source_sentence: how to use
    sentences:
      - how do i use it
      - This fallen panel might lead to the control room.
      - The rings appear to be completely unmoving now.
  - source_sentence: I'm unsure about this room's name how do I find out?
    sentences:
      - How do I identify the room I'm in without any obvious signs?
      - The door shows l m zero twenty three north exit
      - it reads Cryochamber Medical Support Systems
  - source_sentence: i see Cryochamber Atmospheric Sealing
    sentences:
      - Can you guide me on how to identify this room?
      - it's Laboratory Chemical Storage
      - it reads Cryochamber Atmospheric Sealing
  - source_sentence: floating up
    sentences:
      - All indicators are blue.
      - i can see an interface
      - Found a narrow corridor leading somewhere.
model-index:
  - name: SentenceTransformer based on sentence-transformers/all-mpnet-base-v2
    results:
      - task:
          type: binary-classification
          name: Binary Classification
        dataset:
          name: sts dev
          type: sts-dev
        metrics:
          - type: cosine_accuracy
            value: 0.9002097965885251
            name: Cosine Accuracy
          - type: cosine_accuracy_threshold
            value: 0.4494956135749817
            name: Cosine Accuracy Threshold
          - type: cosine_f1
            value: 0.8908462575859745
            name: Cosine F1
          - type: cosine_f1_threshold
            value: 0.41577932238578796
            name: Cosine F1 Threshold
          - type: cosine_precision
            value: 0.8739044154126013
            name: Cosine Precision
          - type: cosine_recall
            value: 0.908457968024755
            name: Cosine Recall
          - type: cosine_ap
            value: 0.9618224590785398
            name: Cosine Ap
          - type: dot_accuracy
            value: 0.9002097965885251
            name: Dot Accuracy
          - type: dot_accuracy_threshold
            value: 0.4494956135749817
            name: Dot Accuracy Threshold
          - type: dot_f1
            value: 0.8908462575859745
            name: Dot F1
          - type: dot_f1_threshold
            value: 0.4157792925834656
            name: Dot F1 Threshold
          - type: dot_precision
            value: 0.8739044154126013
            name: Dot Precision
          - type: dot_recall
            value: 0.908457968024755
            name: Dot Recall
          - type: dot_ap
            value: 0.961822458350164
            name: Dot Ap
          - type: manhattan_accuracy
            value: 0.8989979280958028
            name: Manhattan Accuracy
          - type: manhattan_accuracy_threshold
            value: 22.644113540649414
            name: Manhattan Accuracy Threshold
          - type: manhattan_f1
            value: 0.8901100449479366
            name: Manhattan F1
          - type: manhattan_f1_threshold
            value: 23.330610275268555
            name: Manhattan F1 Threshold
          - type: manhattan_precision
            value: 0.8757104438714686
            name: Manhattan Precision
          - type: manhattan_recall
            value: 0.9049911179875079
            name: Manhattan Recall
          - type: manhattan_ap
            value: 0.9615309074220045
            name: Manhattan Ap
          - type: euclidean_accuracy
            value: 0.9002097965885251
            name: Euclidean Accuracy
          - type: euclidean_accuracy_threshold
            value: 1.0492897033691406
            name: Euclidean Accuracy Threshold
          - type: euclidean_f1
            value: 0.8908462575859745
            name: Euclidean F1
          - type: euclidean_f1_threshold
            value: 1.080944538116455
            name: Euclidean F1 Threshold
          - type: euclidean_precision
            value: 0.8739044154126013
            name: Euclidean Precision
          - type: euclidean_recall
            value: 0.908457968024755
            name: Euclidean Recall
          - type: euclidean_ap
            value: 0.9618224553002042
            name: Euclidean Ap
          - type: max_accuracy
            value: 0.9002097965885251
            name: Max Accuracy
          - type: max_accuracy_threshold
            value: 22.644113540649414
            name: Max Accuracy Threshold
          - type: max_f1
            value: 0.8908462575859745
            name: Max F1
          - type: max_f1_threshold
            value: 23.330610275268555
            name: Max F1 Threshold
          - type: max_precision
            value: 0.8757104438714686
            name: Max Precision
          - type: max_recall
            value: 0.908457968024755
            name: Max Recall
          - type: max_ap
            value: 0.9618224590785398
            name: Max Ap

SentenceTransformer based on sentence-transformers/all-mpnet-base-v2

This is a sentence-transformers model finetuned from sentence-transformers/all-mpnet-base-v2. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: sentence-transformers/all-mpnet-base-v2
Maximum Sequence Length: 384 tokens
Output Dimensionality: 768 tokens
Similarity Function: Cosine Similarity

Model Sources

Documentation: Sentence Transformers Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 384, 'do_lower_case': False}) with Transformer model: MPNetModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
  (2): Normalize()
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("IconicAI/all-mpnet-base-v2-anteater")
# Run inference
sentences = [
    'floating up',
    'i can see an interface',
    'All indicators are blue.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Evaluation

Metrics

Binary Classification

Dataset: sts-dev
Evaluated with BinaryClassificationEvaluator

Metric	Value
cosine_accuracy	0.9002
cosine_accuracy_threshold	0.4495
cosine_f1	0.8908
cosine_f1_threshold	0.4158
cosine_precision	0.8739
cosine_recall	0.9085
cosine_ap	0.9618
dot_accuracy	0.9002
dot_accuracy_threshold	0.4495
dot_f1	0.8908
dot_f1_threshold	0.4158
dot_precision	0.8739
dot_recall	0.9085
dot_ap	0.9618
manhattan_accuracy	0.899
manhattan_accuracy_threshold	22.6441
manhattan_f1	0.8901
manhattan_f1_threshold	23.3306
manhattan_precision	0.8757
manhattan_recall	0.905
manhattan_ap	0.9615
euclidean_accuracy	0.9002
euclidean_accuracy_threshold	1.0493
euclidean_f1	0.8908
euclidean_f1_threshold	1.0809
euclidean_precision	0.8739
euclidean_recall	0.9085
euclidean_ap	0.9618
max_accuracy	0.9002
max_accuracy_threshold	22.6441
max_f1	0.8908
max_f1_threshold	23.3306
max_precision	0.8757
max_recall	0.9085
max_ap	0.9618

Training Details

Training Dataset

Unnamed Dataset

Size: 645,861 training samples
Columns: example1, example2, and label
Approximate statistics based on the first 1000 samples:
example1 example2 label
type string string int
details
min: 3 tokens
mean: 9.02 tokens
max: 25 tokens

min: 3 tokens
mean: 9.19 tokens
max: 23 tokens

1: 100.00%

	example1	example2	label
type	string	string	int
details	min: 3 tokens mean: 9.02 tokens max: 25 tokens	min: 3 tokens mean: 9.19 tokens max: 23 tokens	1: 100.00%

Samples:

example1	example2	label
`Drones are present all around here.`	`What are those drones doing buzzing around here?`	`1`
`am i the only one`	`am i the only one alive on this ship`	`1`
`I’m in a room with a door in front of me and a terminal on the wall`	`mechanics room`	`1`

Loss: ContrastiveLoss with these parameters:

{
    "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
    "margin": 1.0,
    "size_average": true
}

Evaluation Dataset

Unnamed Dataset

Size: 76,741 evaluation samples
Columns: example1, example2, and label
Approximate statistics based on the first 1000 samples:
example1 example2 label
type string string int
details
min: 3 tokens
mean: 9.25 tokens
max: 21 tokens

min: 3 tokens
mean: 9.15 tokens
max: 19 tokens

1: 100.00%

	example1	example2	label
type	string	string	int
details	min: 3 tokens mean: 9.25 tokens max: 21 tokens	min: 3 tokens mean: 9.15 tokens max: 19 tokens	1: 100.00%

Samples:

example1	example2	label
`Not much, how about you?`	`Nothing, you?`	`1`
`Rings stopped moving.`	`I notice the rings are not spinning anymore.`	`1`
`it's Laboratory Chemical Storage`	`the switch is Laboratory Chemical Storage`	`1`

Loss: ContrastiveLoss with these parameters:

{
    "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
    "margin": 1.0,
    "size_average": true
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 256
per_device_eval_batch_size: 256
learning_rate: 1e-07
weight_decay: 0.01
max_grad_norm: 0.02
num_train_epochs: 5
warmup_steps: 100
bf16: True
eval_on_start: 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: 1e-07
weight_decay: 0.01
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 0.02
num_train_epochs: 5
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.0
warmup_steps: 100
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: 42
data_seed: None
jit_mode_eval: False
use_ipex: False
bf16: True
fp16: False
fp16_opt_level: O1
half_precision_backend: auto
bf16_full_eval: False
fp16_full_eval: False
tf32: None
local_rank: 0
ddp_backend: None
tpu_num_cores: None
tpu_metrics_debug: False
debug: []
dataloader_drop_last: False
dataloader_num_workers: 0
dataloader_prefetch_factor: None
past_index: -1
disable_tqdm: False
remove_unused_columns: True
label_names: None
load_best_model_at_end: False
ignore_data_skip: False
fsdp: []
fsdp_min_num_params: 0
fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
fsdp_transformer_layer_cls_to_wrap: None
accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
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: False
hub_always_push: False
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_inputs_for_metrics: False
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
dispatch_batches: None
split_batches: 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: True
use_liger_kernel: False
eval_use_gather_object: False
batch_sampler: batch_sampler
multi_dataset_batch_sampler: proportional

Training Logs

Click to expand

Epoch	Step	Training Loss	loss	sts-dev_max_ap
0	0	-	0.0764	0.9175
0.0040	10	0.0772	-	-
0.0079	20	0.0783	-	-
0.0119	30	0.0775	-	-
0.0159	40	0.0756	-	-
0.0198	50	0.075	-	-
0.0238	60	0.0777	-	-
0.0277	70	0.0784	-	-
0.0317	80	0.0721	-	-
0.0357	90	0.0755	-	-
0.0396	100	0.0778	-	-
0.0436	110	0.0735	-	-
0.0476	120	0.0753	-	-
0.0515	130	0.0741	-	-
0.0555	140	0.0791	-	-
0.0595	150	0.0753	-	-
0.0634	160	0.0748	-	-
0.0674	170	0.0709	-	-
0.0713	180	0.0738	-	-
0.0753	190	0.0759	-	-
0.0793	200	0.0703	-	-
0.0832	210	0.0724	-	-
0.0872	220	0.0726	-	-
0.0912	230	0.0734	-	-
0.0951	240	0.0718	-	-
0.0991	250	0.0776	-	-
0.1031	260	0.0757	-	-
0.1070	270	0.0722	-	-
0.1110	280	0.0746	-	-
0.1149	290	0.0718	-	-
0.1189	300	0.0733	-	-
0.1229	310	0.0725	-	-
0.1268	320	0.0724	-	-
0.1308	330	0.0681	-	-
0.1348	340	0.0735	-	-
0.1387	350	0.0716	-	-
0.1427	360	0.0698	-	-
0.1467	370	0.072	-	-
0.1506	380	0.071	-	-
0.1546	390	0.0713	-	-
0.1585	400	0.073	-	-
0.1625	410	0.077	-	-
0.1665	420	0.072	-	-
0.1704	430	0.0689	-	-
0.1744	440	0.0708	-	-
0.1784	450	0.0687	-	-
0.1823	460	0.0692	-	-
0.1863	470	0.0715	-	-
0.1902	480	0.0707	-	-
0.1942	490	0.0671	-	-
0.1982	500	0.0741	0.0703	0.9245
0.2021	510	0.0681	-	-
0.2061	520	0.0749	-	-
0.2101	530	0.0718	-	-
0.2140	540	0.0689	-	-
0.2180	550	0.0733	-	-
0.2220	560	0.067	-	-
0.2259	570	0.0685	-	-
0.2299	580	0.07	-	-
0.2338	590	0.0683	-	-
0.2378	600	0.0693	-	-
0.2418	610	0.0705	-	-
0.2457	620	0.0707	-	-
0.2497	630	0.0703	-	-
0.2537	640	0.068	-	-
0.2576	650	0.0682	-	-
0.2616	660	0.0654	-	-
0.2656	670	0.0682	-	-
0.2695	680	0.0698	-	-
0.2735	690	0.0701	-	-
0.2774	700	0.0674	-	-
0.2814	710	0.0669	-	-
0.2854	720	0.0677	-	-
0.2893	730	0.0674	-	-
0.2933	740	0.0682	-	-
0.2973	750	0.0677	-	-
0.3012	760	0.0661	-	-
0.3052	770	0.0634	-	-
0.3092	780	0.0658	-	-
0.3131	790	0.0687	-	-
0.3171	800	0.069	-	-
0.3210	810	0.0665	-	-
0.3250	820	0.0648	-	-
0.3290	830	0.0656	-	-
0.3329	840	0.0672	-	-
0.3369	850	0.0663	-	-
0.3409	860	0.0666	-	-
0.3448	870	0.0644	-	-
0.3488	880	0.065	-	-
0.3528	890	0.0666	-	-
0.3567	900	0.0657	-	-
0.3607	910	0.0636	-	-
0.3646	920	0.0681	-	-
0.3686	930	0.0671	-	-
0.3726	940	0.0653	-	-
0.3765	950	0.0643	-	-
0.3805	960	0.0637	-	-
0.3845	970	0.066	-	-
0.3884	980	0.0645	-	-
0.3924	990	0.0628	-	-
0.3964	1000	0.0627	0.0653	0.9325
0.4003	1010	0.0647	-	-
0.4043	1020	0.0649	-	-
0.4082	1030	0.0637	-	-
0.4122	1040	0.0648	-	-
0.4162	1050	0.0647	-	-
0.4201	1060	0.0646	-	-
0.4241	1070	0.0659	-	-
0.4281	1080	0.0641	-	-
0.4320	1090	0.0609	-	-
0.4360	1100	0.0642	-	-
0.4400	1110	0.0614	-	-
0.4439	1120	0.0603	-	-
0.4479	1130	0.0613	-	-
0.4518	1140	0.0646	-	-
0.4558	1150	0.0619	-	-
0.4598	1160	0.0611	-	-
0.4637	1170	0.0638	-	-
0.4677	1180	0.0636	-	-
0.4717	1190	0.0647	-	-
0.4756	1200	0.0622	-	-
0.4796	1210	0.0642	-	-
0.4836	1220	0.0607	-	-
0.4875	1230	0.0623	-	-
0.4915	1240	0.0614	-	-
0.4954	1250	0.0643	-	-
0.4994	1260	0.0614	-	-
0.5034	1270	0.0599	-	-
0.5073	1280	0.0615	-	-
0.5113	1290	0.0595	-	-
0.5153	1300	0.061	-	-
0.5192	1310	0.0623	-	-
0.5232	1320	0.0646	-	-
0.5272	1330	0.0621	-	-
0.5311	1340	0.0606	-	-
0.5351	1350	0.0597	-	-
0.5390	1360	0.0621	-	-
0.5430	1370	0.0586	-	-
0.5470	1380	0.0618	-	-
0.5509	1390	0.0601	-	-
0.5549	1400	0.0578	-	-
0.5589	1410	0.0628	-	-
0.5628	1420	0.0595	-	-
0.5668	1430	0.0576	-	-
0.5707	1440	0.0606	-	-
0.5747	1450	0.0618	-	-
0.5787	1460	0.0591	-	-
0.5826	1470	0.0598	-	-
0.5866	1480	0.0611	-	-
0.5906	1490	0.0594	-	-
0.5945	1500	0.0616	0.0619	0.9393
0.5985	1510	0.0592	-	-
0.6025	1520	0.0597	-	-
0.6064	1530	0.0619	-	-
0.6104	1540	0.0595	-	-
0.6143	1550	0.0598	-	-
0.6183	1560	0.0609	-	-
0.6223	1570	0.059	-	-
0.6262	1580	0.0601	-	-
0.6302	1590	0.0595	-	-
0.6342	1600	0.059	-	-
0.6381	1610	0.0606	-	-
0.6421	1620	0.0591	-	-
0.6461	1630	0.0617	-	-
0.6500	1640	0.0592	-	-
0.6540	1650	0.0588	-	-
0.6579	1660	0.0587	-	-
0.6619	1670	0.0585	-	-
0.6659	1680	0.0558	-	-
0.6698	1690	0.057	-	-
0.6738	1700	0.0598	-	-
0.6778	1710	0.0567	-	-
0.6817	1720	0.0555	-	-
0.6857	1730	0.0604	-	-
0.6897	1740	0.0558	-	-
0.6936	1750	0.0572	-	-
0.6976	1760	0.0577	-	-
0.7015	1770	0.0587	-	-
0.7055	1780	0.0589	-	-
0.7095	1790	0.0598	-	-
0.7134	1800	0.0583	-	-
0.7174	1810	0.058	-	-
0.7214	1820	0.0564	-	-
0.7253	1830	0.0589	-	-
0.7293	1840	0.0557	-	-
0.7333	1850	0.0586	-	-
0.7372	1860	0.0601	-	-
0.7412	1870	0.0556	-	-
0.7451	1880	0.0572	-	-
0.7491	1890	0.0574	-	-
0.7531	1900	0.0583	-	-
0.7570	1910	0.0573	-	-
0.7610	1920	0.0555	-	-
0.7650	1930	0.0561	-	-
0.7689	1940	0.0579	-	-
0.7729	1950	0.0557	-	-
0.7769	1960	0.0558	-	-
0.7808	1970	0.0589	-	-
0.7848	1980	0.0572	-	-
0.7887	1990	0.0572	-	-
0.7927	2000	0.0549	0.0592	0.9444
0.7967	2010	0.0548	-	-
0.8006	2020	0.0569	-	-
0.8046	2030	0.058	-	-
0.8086	2040	0.0581	-	-
0.8125	2050	0.0585	-	-
0.8165	2060	0.0542	-	-
0.8205	2070	0.0558	-	-
0.8244	2080	0.0569	-	-
0.8284	2090	0.0564	-	-
0.8323	2100	0.0552	-	-
0.8363	2110	0.0559	-	-
0.8403	2120	0.0534	-	-
0.8442	2130	0.0543	-	-
0.8482	2140	0.0573	-	-
0.8522	2150	0.0546	-	-
0.8561	2160	0.0554	-	-
0.8601	2170	0.0568	-	-
0.8641	2180	0.0544	-	-
0.8680	2190	0.0547	-	-
0.8720	2200	0.0549	-	-
0.8759	2210	0.0544	-	-
0.8799	2220	0.058	-	-
0.8839	2230	0.0557	-	-
0.8878	2240	0.0551	-	-
0.8918	2250	0.0558	-	-
0.8958	2260	0.0554	-	-
0.8997	2270	0.053	-	-
0.9037	2280	0.0552	-	-
0.9076	2290	0.0549	-	-
0.9116	2300	0.0533	-	-
0.9156	2310	0.0543	-	-
0.9195	2320	0.0531	-	-
0.9235	2330	0.0553	-	-
0.9275	2340	0.0542	-	-
0.9314	2350	0.0537	-	-
0.9354	2360	0.0536	-	-
0.9394	2370	0.055	-	-
0.9433	2380	0.0551	-	-
0.9473	2390	0.0532	-	-
0.9512	2400	0.0556	-	-
0.9552	2410	0.0548	-	-
0.9592	2420	0.0533	-	-
0.9631	2430	0.0536	-	-
0.9671	2440	0.0549	-	-
0.9711	2450	0.0548	-	-
0.9750	2460	0.0557	-	-
0.9790	2470	0.055	-	-
0.9830	2480	0.0535	-	-
0.9869	2490	0.0564	-	-
0.9909	2500	0.0526	0.0572	0.9482
0.9948	2510	0.0547	-	-
0.9988	2520	0.054	-	-
1.0028	2530	0.0527	-	-
1.0067	2540	0.0522	-	-
1.0107	2550	0.0535	-	-
1.0147	2560	0.0557	-	-
1.0186	2570	0.052	-	-
1.0226	2580	0.055	-	-
1.0266	2590	0.0542	-	-
1.0305	2600	0.0539	-	-
1.0345	2610	0.0523	-	-
1.0384	2620	0.0507	-	-
1.0424	2630	0.0517	-	-
1.0464	2640	0.0543	-	-
1.0503	2650	0.0543	-	-
1.0543	2660	0.054	-	-
1.0583	2670	0.0536	-	-
1.0622	2680	0.0531	-	-
1.0662	2690	0.0537	-	-
1.0702	2700	0.0521	-	-
1.0741	2710	0.054	-	-
1.0781	2720	0.0513	-	-
1.0820	2730	0.0496	-	-
1.0860	2740	0.0519	-	-
1.0900	2750	0.0529	-	-
1.0939	2760	0.0542	-	-
1.0979	2770	0.0526	-	-
1.1019	2780	0.051	-	-
1.1058	2790	0.0531	-	-
1.1098	2800	0.0539	-	-
1.1138	2810	0.0521	-	-
1.1177	2820	0.0539	-	-
1.1217	2830	0.0505	-	-
1.1256	2840	0.0513	-	-
1.1296	2850	0.0521	-	-
1.1336	2860	0.0537	-	-
1.1375	2870	0.0514	-	-
1.1415	2880	0.0511	-	-
1.1455	2890	0.0495	-	-
1.1494	2900	0.0505	-	-
1.1534	2910	0.0517	-	-
1.1574	2920	0.0509	-	-
1.1613	2930	0.0507	-	-
1.1653	2940	0.0535	-	-
1.1692	2950	0.0511	-	-
1.1732	2960	0.0507	-	-
1.1772	2970	0.052	-	-
1.1811	2980	0.0494	-	-
1.1851	2990	0.0524	-	-
1.1891	3000	0.052	0.0555	0.9512
1.1930	3010	0.0536	-	-
1.1970	3020	0.0502	-	-
1.2010	3030	0.0504	-	-
1.2049	3040	0.0532	-	-
1.2089	3050	0.0529	-	-
1.2128	3060	0.0514	-	-
1.2168	3070	0.0504	-	-
1.2208	3080	0.0501	-	-
1.2247	3090	0.0493	-	-
1.2287	3100	0.0507	-	-
1.2327	3110	0.0501	-	-
1.2366	3120	0.0502	-	-
1.2406	3130	0.0491	-	-
1.2446	3140	0.0495	-	-
1.2485	3150	0.051	-	-
1.2525	3160	0.0495	-	-
1.2564	3170	0.0534	-	-
1.2604	3180	0.0483	-	-
1.2644	3190	0.049	-	-
1.2683	3200	0.0532	-	-
1.2723	3210	0.0481	-	-
1.2763	3220	0.0496	-	-
1.2802	3230	0.0504	-	-
1.2842	3240	0.0477	-	-
1.2881	3250	0.0483	-	-
1.2921	3260	0.0493	-	-
1.2961	3270	0.0491	-	-
1.3000	3280	0.0489	-	-
1.3040	3290	0.0493	-	-
1.3080	3300	0.0507	-	-
1.3119	3310	0.0482	-	-
1.3159	3320	0.0506	-	-
1.3199	3330	0.0486	-	-
1.3238	3340	0.0487	-	-
1.3278	3350	0.0482	-	-
1.3317	3360	0.0492	-	-
1.3357	3370	0.049	-	-
1.3397	3380	0.0485	-	-
1.3436	3390	0.0501	-	-
1.3476	3400	0.0505	-	-
1.3516	3410	0.0508	-	-
1.3555	3420	0.0481	-	-
1.3595	3430	0.049	-	-
1.3635	3440	0.0495	-	-
1.3674	3450	0.0507	-	-
1.3714	3460	0.0478	-	-
1.3753	3470	0.0522	-	-
1.3793	3480	0.0505	-	-
1.3833	3490	0.0489	-	-
1.3872	3500	0.0504	0.0541	0.9537
1.3912	3510	0.0492	-	-
1.3952	3520	0.0469	-	-
1.3991	3530	0.0495	-	-
1.4031	3540	0.0486	-	-
1.4071	3550	0.0506	-	-
1.4110	3560	0.0506	-	-
1.4150	3570	0.0475	-	-
1.4189	3580	0.0483	-	-
1.4229	3590	0.0471	-	-
1.4269	3600	0.0477	-	-
1.4308	3610	0.0494	-	-
1.4348	3620	0.0481	-	-
1.4388	3630	0.0484	-	-
1.4427	3640	0.0505	-	-
1.4467	3650	0.0498	-	-
1.4507	3660	0.0482	-	-
1.4546	3670	0.0488	-	-
1.4586	3680	0.0458	-	-
1.4625	3690	0.0479	-	-
1.4665	3700	0.0474	-	-
1.4705	3710	0.0471	-	-
1.4744	3720	0.0498	-	-
1.4784	3730	0.0495	-	-
1.4824	3740	0.0505	-	-
1.4863	3750	0.0487	-	-
1.4903	3760	0.0485	-	-
1.4943	3770	0.0479	-	-
1.4982	3780	0.0475	-	-
1.5022	3790	0.0462	-	-
1.5061	3800	0.0487	-	-
1.5101	3810	0.0476	-	-
1.5141	3820	0.0485	-	-
1.5180	3830	0.0489	-	-
1.5220	3840	0.0475	-	-
1.5260	3850	0.0484	-	-
1.5299	3860	0.0465	-	-
1.5339	3870	0.0491	-	-
1.5379	3880	0.0477	-	-
1.5418	3890	0.0475	-	-
1.5458	3900	0.0489	-	-
1.5497	3910	0.0459	-	-
1.5537	3920	0.0488	-	-
1.5577	3930	0.0475	-	-
1.5616	3940	0.049	-	-
1.5656	3950	0.0469	-	-
1.5696	3960	0.0493	-	-
1.5735	3970	0.0481	-	-
1.5775	3980	0.0478	-	-
1.5815	3990	0.0456	-	-
1.5854	4000	0.047	0.0528	0.9556
1.5894	4010	0.0481	-	-
1.5933	4020	0.0468	-	-
1.5973	4030	0.0467	-	-
1.6013	4040	0.0448	-	-
1.6052	4050	0.0491	-	-
1.6092	4060	0.0476	-	-
1.6132	4070	0.0459	-	-
1.6171	4080	0.0456	-	-
1.6211	4090	0.0476	-	-
1.6250	4100	0.0443	-	-
1.6290	4110	0.0477	-	-
1.6330	4120	0.0476	-	-
1.6369	4130	0.0466	-	-
1.6409	4140	0.0457	-	-
1.6449	4150	0.0468	-	-
1.6488	4160	0.0462	-	-
1.6528	4170	0.0476	-	-
1.6568	4180	0.0464	-	-
1.6607	4190	0.0467	-	-
1.6647	4200	0.0455	-	-
1.6686	4210	0.0455	-	-
1.6726	4220	0.0474	-	-
1.6766	4230	0.0469	-	-
1.6805	4240	0.0453	-	-
1.6845	4250	0.0464	-	-
1.6885	4260	0.0448	-	-
1.6924	4270	0.0448	-	-
1.6964	4280	0.0461	-	-
1.7004	4290	0.0444	-	-
1.7043	4300	0.045	-	-
1.7083	4310	0.047	-	-
1.7122	4320	0.0473	-	-
1.7162	4330	0.0453	-	-
1.7202	4340	0.0461	-	-
1.7241	4350	0.0464	-	-
1.7281	4360	0.0474	-	-
1.7321	4370	0.0444	-	-
1.7360	4380	0.0465	-	-
1.7400	4390	0.0454	-	-
1.7440	4400	0.045	-	-
1.7479	4410	0.0444	-	-
1.7519	4420	0.0451	-	-
1.7558	4430	0.0454	-	-
1.7598	4440	0.0471	-	-
1.7638	4450	0.0467	-	-
1.7677	4460	0.0466	-	-
1.7717	4470	0.0452	-	-
1.7757	4480	0.0466	-	-
1.7796	4490	0.046	-	-
1.7836	4500	0.0462	0.0518	0.9570
1.7876	4510	0.0459	-	-
1.7915	4520	0.0455	-	-
1.7955	4530	0.0456	-	-
1.7994	4540	0.0476	-	-
1.8034	4550	0.0465	-	-
1.8074	4560	0.0447	-	-
1.8113	4570	0.0438	-	-
1.8153	4580	0.0463	-	-
1.8193	4590	0.0452	-	-
1.8232	4600	0.0454	-	-
1.8272	4610	0.0459	-	-
1.8312	4620	0.044	-	-
1.8351	4630	0.0445	-	-
1.8391	4640	0.0435	-	-
1.8430	4650	0.0435	-	-
1.8470	4660	0.0442	-	-
1.8510	4670	0.0424	-	-
1.8549	4680	0.0438	-	-
1.8589	4690	0.0451	-	-
1.8629	4700	0.0451	-	-
1.8668	4710	0.0455	-	-
1.8708	4720	0.0441	-	-
1.8748	4730	0.0432	-	-
1.8787	4740	0.0445	-	-
1.8827	4750	0.0482	-	-
1.8866	4760	0.045	-	-
1.8906	4770	0.0443	-	-
1.8946	4780	0.0451	-	-
1.8985	4790	0.0446	-	-
1.9025	4800	0.0432	-	-
1.9065	4810	0.0432	-	-
1.9104	4820	0.0465	-	-
1.9144	4830	0.0462	-	-
1.9184	4840	0.0443	-	-
1.9223	4850	0.0447	-	-
1.9263	4860	0.0459	-	-
1.9302	4870	0.043	-	-
1.9342	4880	0.0456	-	-
1.9382	4890	0.0444	-	-
1.9421	4900	0.0455	-	-
1.9461	4910	0.0427	-	-
1.9501	4920	0.0461	-	-
1.9540	4930	0.0454	-	-
1.9580	4940	0.0447	-	-
1.9620	4950	0.0434	-	-
1.9659	4960	0.0444	-	-
1.9699	4970	0.0451	-	-
1.9738	4980	0.044	-	-
1.9778	4990	0.0444	-	-
1.9818	5000	0.0439	0.0508	0.9581
1.9857	5010	0.0427	-	-
1.9897	5020	0.0439	-	-
1.9937	5030	0.0427	-	-
1.9976	5040	0.0435	-	-
2.0016	5050	0.0445	-	-
2.0055	5060	0.0433	-	-
2.0095	5070	0.0433	-	-
2.0135	5080	0.0435	-	-
2.0174	5090	0.0438	-	-
2.0214	5100	0.0431	-	-
2.0254	5110	0.0422	-	-
2.0293	5120	0.0436	-	-
2.0333	5130	0.0455	-	-
2.0373	5140	0.044	-	-
2.0412	5150	0.0423	-	-
2.0452	5160	0.045	-	-
2.0491	5170	0.0422	-	-
2.0531	5180	0.0435	-	-
2.0571	5190	0.0419	-	-
2.0610	5200	0.0427	-	-
2.0650	5210	0.0447	-	-
2.0690	5220	0.0443	-	-
2.0729	5230	0.0429	-	-
2.0769	5240	0.0436	-	-
2.0809	5250	0.0436	-	-
2.0848	5260	0.0439	-	-
2.0888	5270	0.0433	-	-
2.0927	5280	0.0434	-	-
2.0967	5290	0.0428	-	-
2.1007	5300	0.0431	-	-
2.1046	5310	0.0441	-	-
2.1086	5320	0.0443	-	-
2.1126	5330	0.0442	-	-
2.1165	5340	0.044	-	-
2.1205	5350	0.0431	-	-
2.1245	5360	0.0432	-	-
2.1284	5370	0.0421	-	-
2.1324	5380	0.0439	-	-
2.1363	5390	0.0436	-	-
2.1403	5400	0.0428	-	-
2.1443	5410	0.044	-	-
2.1482	5420	0.0428	-	-
2.1522	5430	0.0428	-	-
2.1562	5440	0.0418	-	-
2.1601	5450	0.0439	-	-
2.1641	5460	0.0415	-	-
2.1681	5470	0.0415	-	-
2.1720	5480	0.0418	-	-
2.1760	5490	0.042	-	-
2.1799	5500	0.0418	0.0500	0.9591
2.1839	5510	0.0434	-	-
2.1879	5520	0.0424	-	-
2.1918	5530	0.0425	-	-
2.1958	5540	0.0427	-	-
2.1998	5550	0.0418	-	-
2.2037	5560	0.04	-	-
2.2077	5570	0.0426	-	-
2.2117	5580	0.0413	-	-
2.2156	5590	0.0429	-	-
2.2196	5600	0.0428	-	-
2.2235	5610	0.044	-	-
2.2275	5620	0.0423	-	-
2.2315	5630	0.0398	-	-
2.2354	5640	0.0427	-	-
2.2394	5650	0.0419	-	-
2.2434	5660	0.0424	-	-
2.2473	5670	0.0422	-	-
2.2513	5680	0.0426	-	-
2.2553	5690	0.0434	-	-
2.2592	5700	0.044	-	-
2.2632	5710	0.0427	-	-
2.2671	5720	0.0431	-	-
2.2711	5730	0.0416	-	-
2.2751	5740	0.0428	-	-
2.2790	5750	0.0418	-	-
2.2830	5760	0.0418	-	-
2.2870	5770	0.0421	-	-
2.2909	5780	0.041	-	-
2.2949	5790	0.0419	-	-
2.2989	5800	0.0422	-	-
2.3028	5810	0.0428	-	-
2.3068	5820	0.0432	-	-
2.3107	5830	0.043	-	-
2.3147	5840	0.0424	-	-
2.3187	5850	0.0396	-	-
2.3226	5860	0.0433	-	-
2.3266	5870	0.0413	-	-
2.3306	5880	0.0436	-	-
2.3345	5890	0.0399	-	-
2.3385	5900	0.0426	-	-
2.3424	5910	0.0405	-	-
2.3464	5920	0.0423	-	-
2.3504	5930	0.0409	-	-
2.3543	5940	0.0412	-	-
2.3583	5950	0.0401	-	-
2.3623	5960	0.042	-	-
2.3662	5970	0.0397	-	-
2.3702	5980	0.0422	-	-
2.3742	5990	0.0416	-	-
2.3781	6000	0.0422	0.0493	0.9599
2.3821	6010	0.041	-	-
2.3860	6020	0.0404	-	-
2.3900	6030	0.0404	-	-
2.3940	6040	0.0412	-	-
2.3979	6050	0.0424	-	-
2.4019	6060	0.043	-	-
2.4059	6070	0.0416	-	-
2.4098	6080	0.0405	-	-
2.4138	6090	0.0408	-	-
2.4178	6100	0.0413	-	-
2.4217	6110	0.0408	-	-
2.4257	6120	0.0407	-	-
2.4296	6130	0.041	-	-
2.4336	6140	0.0387	-	-
2.4376	6150	0.0408	-	-
2.4415	6160	0.0413	-	-
2.4455	6170	0.0429	-	-
2.4495	6180	0.0394	-	-
2.4534	6190	0.041	-	-
2.4574	6200	0.0419	-	-
2.4614	6210	0.0395	-	-
2.4653	6220	0.0405	-	-
2.4693	6230	0.0412	-	-
2.4732	6240	0.0439	-	-
2.4772	6250	0.0423	-	-
2.4812	6260	0.0423	-	-
2.4851	6270	0.0406	-	-
2.4891	6280	0.0402	-	-
2.4931	6290	0.0428	-	-
2.4970	6300	0.0422	-	-
2.5010	6310	0.0399	-	-
2.5050	6320	0.0409	-	-
2.5089	6330	0.0412	-	-
2.5129	6340	0.0403	-	-
2.5168	6350	0.04	-	-
2.5208	6360	0.0412	-	-
2.5248	6370	0.0424	-	-
2.5287	6380	0.0409	-	-
2.5327	6390	0.0409	-	-
2.5367	6400	0.0418	-	-
2.5406	6410	0.0403	-	-
2.5446	6420	0.0413	-	-
2.5486	6430	0.038	-	-
2.5525	6440	0.0414	-	-
2.5565	6450	0.0409	-	-
2.5604	6460	0.0407	-	-
2.5644	6470	0.0406	-	-
2.5684	6480	0.0392	-	-
2.5723	6490	0.0417	-	-
2.5763	6500	0.0391	0.0487	0.9605
2.5803	6510	0.039	-	-
2.5842	6520	0.0414	-	-
2.5882	6530	0.0411	-	-
2.5922	6540	0.0395	-	-
2.5961	6550	0.0405	-	-
2.6001	6560	0.0392	-	-
2.6040	6570	0.041	-	-
2.6080	6580	0.0387	-	-
2.6120	6590	0.0409	-	-
2.6159	6600	0.0416	-	-
2.6199	6610	0.0399	-	-
2.6239	6620	0.0395	-	-
2.6278	6630	0.0416	-	-
2.6318	6640	0.0397	-	-
2.6358	6650	0.041	-	-
2.6397	6660	0.0422	-	-
2.6437	6670	0.0404	-	-
2.6476	6680	0.0405	-	-
2.6516	6690	0.0413	-	-
2.6556	6700	0.0405	-	-
2.6595	6710	0.04	-	-
2.6635	6720	0.0383	-	-
2.6675	6730	0.0412	-	-
2.6714	6740	0.0416	-	-
2.6754	6750	0.0405	-	-
2.6793	6760	0.0423	-	-
2.6833	6770	0.0419	-	-
2.6873	6780	0.0405	-	-
2.6912	6790	0.0409	-	-
2.6952	6800	0.04	-	-
2.6992	6810	0.0397	-	-
2.7031	6820	0.039	-	-
2.7071	6830	0.0393	-	-
2.7111	6840	0.0413	-	-
2.7150	6850	0.039	-	-
2.7190	6860	0.04	-	-
2.7229	6870	0.0409	-	-
2.7269	6880	0.0403	-	-
2.7309	6890	0.0397	-	-
2.7348	6900	0.0404	-	-
2.7388	6910	0.0396	-	-
2.7428	6920	0.04	-	-
2.7467	6930	0.0397	-	-
2.7507	6940	0.0393	-	-
2.7547	6950	0.037	-	-
2.7586	6960	0.0383	-	-
2.7626	6970	0.04	-	-
2.7665	6980	0.0406	-	-
2.7705	6990	0.0394	-	-
2.7745	7000	0.0385	0.0482	0.9609
2.7784	7010	0.0383	-	-
2.7824	7020	0.0403	-	-
2.7864	7030	0.04	-	-
2.7903	7040	0.0395	-	-
2.7943	7050	0.039	-	-
2.7983	7060	0.0398	-	-
2.8022	7070	0.0401	-	-
2.8062	7080	0.0401	-	-
2.8101	7090	0.0395	-	-
2.8141	7100	0.0396	-	-
2.8181	7110	0.0395	-	-
2.8220	7120	0.0411	-	-
2.8260	7130	0.0386	-	-
2.8300	7140	0.0382	-	-
2.8339	7150	0.0386	-	-
2.8379	7160	0.0389	-	-
2.8419	7170	0.0396	-	-
2.8458	7180	0.0394	-	-
2.8498	7190	0.04	-	-
2.8537	7200	0.0401	-	-
2.8577	7210	0.0412	-	-
2.8617	7220	0.0383	-	-
2.8656	7230	0.0392	-	-
2.8696	7240	0.0394	-	-
2.8736	7250	0.0399	-	-
2.8775	7260	0.0403	-	-
2.8815	7270	0.0384	-	-
2.8855	7280	0.0397	-	-
2.8894	7290	0.0407	-	-
2.8934	7300	0.0386	-	-
2.8973	7310	0.0385	-	-
2.9013	7320	0.0405	-	-
2.9053	7330	0.0389	-	-
2.9092	7340	0.0362	-	-
2.9132	7350	0.0397	-	-
2.9172	7360	0.0393	-	-
2.9211	7370	0.0397	-	-
2.9251	7380	0.0386	-	-
2.9291	7390	0.0388	-	-
2.9330	7400	0.0366	-	-
2.9370	7410	0.0394	-	-
2.9409	7420	0.0396	-	-
2.9449	7430	0.0393	-	-
2.9489	7440	0.0401	-	-
2.9528	7450	0.0391	-	-
2.9568	7460	0.0388	-	-
2.9608	7470	0.0386	-	-
2.9647	7480	0.0391	-	-
2.9687	7490	0.037	-	-
2.9727	7500	0.0386	0.0477	0.9613
2.9766	7510	0.0392	-	-
2.9806	7520	0.0399	-	-
2.9845	7530	0.0385	-	-
2.9885	7540	0.0381	-	-
2.9925	7550	0.0392	-	-
2.9964	7560	0.0386	-	-
3.0004	7570	0.0394	-	-
3.0044	7580	0.0401	-	-
3.0083	7590	0.0404	-	-
3.0123	7600	0.0384	-	-
3.0163	7610	0.0381	-	-
3.0202	7620	0.0383	-	-
3.0242	7630	0.0389	-	-
3.0281	7640	0.0364	-	-
3.0321	7650	0.0399	-	-
3.0361	7660	0.0383	-	-
3.0400	7670	0.0401	-	-
3.0440	7680	0.0388	-	-
3.0480	7690	0.0389	-	-
3.0519	7700	0.036	-	-
3.0559	7710	0.0403	-	-
3.0598	7720	0.0376	-	-
3.0638	7730	0.0387	-	-
3.0678	7740	0.0405	-	-
3.0717	7750	0.0399	-	-
3.0757	7760	0.0382	-	-
3.0797	7770	0.0376	-	-
3.0836	7780	0.0393	-	-
3.0876	7790	0.0388	-	-
3.0916	7800	0.0395	-	-
3.0955	7810	0.0391	-	-
3.0995	7820	0.0392	-	-
3.1034	7830	0.0371	-	-
3.1074	7840	0.039	-	-
3.1114	7850	0.0395	-	-
3.1153	7860	0.0385	-	-
3.1193	7870	0.0362	-	-
3.1233	7880	0.0375	-	-
3.1272	7890	0.0376	-	-
3.1312	7900	0.0384	-	-
3.1352	7910	0.0378	-	-
3.1391	7920	0.0393	-	-
3.1431	7930	0.0378	-	-
3.1470	7940	0.0404	-	-
3.1510	7950	0.0361	-	-
3.1550	7960	0.0369	-	-
3.1589	7970	0.0396	-	-
3.1629	7980	0.0404	-	-
3.1669	7990	0.0386	-	-
3.1708	8000	0.038	0.0473	0.9616
3.1748	8010	0.0372	-	-
3.1788	8020	0.0373	-	-
3.1827	8030	0.0369	-	-
3.1867	8040	0.0371	-	-
3.1906	8050	0.0386	-	-
3.1946	8060	0.038	-	-
3.1986	8070	0.0366	-	-
3.2025	8080	0.0378	-	-
3.2065	8090	0.0379	-	-
3.2105	8100	0.038	-	-
3.2144	8110	0.0374	-	-
3.2184	8120	0.0388	-	-
3.2224	8130	0.038	-	-
3.2263	8140	0.0363	-	-
3.2303	8150	0.0369	-	-
3.2342	8160	0.0371	-	-
3.2382	8170	0.0377	-	-
3.2422	8180	0.0364	-	-
3.2461	8190	0.0372	-	-
3.2501	8200	0.0403	-	-
3.2541	8210	0.0385	-	-
3.2580	8220	0.0385	-	-
3.2620	8230	0.0386	-	-
3.2660	8240	0.0369	-	-
3.2699	8250	0.039	-	-
3.2739	8260	0.0365	-	-
3.2778	8270	0.0382	-	-
3.2818	8280	0.0354	-	-
3.2858	8290	0.0393	-	-
3.2897	8300	0.0387	-	-
3.2937	8310	0.0366	-	-
3.2977	8320	0.0391	-	-
3.3016	8330	0.0382	-	-
3.3056	8340	0.0377	-	-
3.3096	8350	0.0369	-	-
3.3135	8360	0.0384	-	-
3.3175	8370	0.0379	-	-
3.3214	8380	0.0372	-	-
3.3254	8390	0.0391	-	-
3.3294	8400	0.0378	-	-
3.3333	8410	0.0393	-	-
3.3373	8420	0.0373	-	-
3.3413	8430	0.0394	-	-
3.3452	8440	0.0367	-	-
3.3492	8450	0.0373	-	-
3.3532	8460	0.0362	-	-
3.3571	8470	0.0372	-	-
3.3611	8480	0.0396	-	-
3.3650	8490	0.0392	-	-
3.3690	8500	0.0374	0.0470	0.9616
3.3730	8510	0.0378	-	-
3.3769	8520	0.0385	-	-
3.3809	8530	0.0375	-	-
3.3849	8540	0.0392	-	-
3.3888	8550	0.0378	-	-
3.3928	8560	0.0366	-	-
3.3967	8570	0.0383	-	-
3.4007	8580	0.0372	-	-
3.4047	8590	0.038	-	-
3.4086	8600	0.0384	-	-
3.4126	8610	0.0359	-	-
3.4166	8620	0.0377	-	-
3.4205	8630	0.0387	-	-
3.4245	8640	0.0365	-	-
3.4285	8650	0.0359	-	-
3.4324	8660	0.0358	-	-
3.4364	8670	0.0366	-	-
3.4403	8680	0.0369	-	-
3.4443	8690	0.0365	-	-
3.4483	8700	0.0366	-	-
3.4522	8710	0.0357	-	-
3.4562	8720	0.036	-	-
3.4602	8730	0.0365	-	-
3.4641	8740	0.0381	-	-
3.4681	8750	0.0399	-	-
3.4721	8760	0.0388	-	-
3.4760	8770	0.0366	-	-
3.4800	8780	0.0346	-	-
3.4839	8790	0.0371	-	-
3.4879	8800	0.0376	-	-
3.4919	8810	0.0374	-	-
3.4958	8820	0.0354	-	-
3.4998	8830	0.0363	-	-
3.5038	8840	0.0374	-	-
3.5077	8850	0.0373	-	-
3.5117	8860	0.0347	-	-
3.5157	8870	0.0374	-	-
3.5196	8880	0.0349	-	-
3.5236	8890	0.0376	-	-
3.5275	8900	0.0363	-	-
3.5315	8910	0.036	-	-
3.5355	8920	0.0378	-	-
3.5394	8930	0.0376	-	-
3.5434	8940	0.039	-	-
3.5474	8950	0.0373	-	-
3.5513	8960	0.0361	-	-
3.5553	8970	0.0356	-	-
3.5593	8980	0.0357	-	-
3.5632	8990	0.0371	-	-
3.5672	9000	0.0374	0.0468	0.9617
3.5711	9010	0.0372	-	-
3.5751	9020	0.0369	-	-
3.5791	9030	0.0362	-	-
3.5830	9040	0.0367	-	-
3.5870	9050	0.0388	-	-
3.5910	9060	0.0369	-	-
3.5949	9070	0.0375	-	-
3.5989	9080	0.0374	-	-
3.6029	9090	0.0365	-	-
3.6068	9100	0.0363	-	-
3.6108	9110	0.0396	-	-
3.6147	9120	0.0372	-	-
3.6187	9130	0.0363	-	-
3.6227	9140	0.0363	-	-
3.6266	9150	0.0366	-	-
3.6306	9160	0.0352	-	-
3.6346	9170	0.038	-	-
3.6385	9180	0.0359	-	-
3.6425	9190	0.0374	-	-
3.6465	9200	0.0363	-	-
3.6504	9210	0.0356	-	-
3.6544	9220	0.0354	-	-
3.6583	9230	0.0377	-	-
3.6623	9240	0.0361	-	-
3.6663	9250	0.0374	-	-
3.6702	9260	0.0373	-	-
3.6742	9270	0.0357	-	-
3.6782	9280	0.0359	-	-
3.6821	9290	0.037	-	-
3.6861	9300	0.0366	-	-
3.6901	9310	0.0374	-	-
3.6940	9320	0.0376	-	-
3.6980	9330	0.0373	-	-
3.7019	9340	0.0363	-	-
3.7059	9350	0.0381	-	-
3.7099	9360	0.0353	-	-
3.7138	9370	0.0363	-	-
3.7178	9380	0.0377	-	-
3.7218	9390	0.0364	-	-
3.7257	9400	0.0378	-	-
3.7297	9410	0.0376	-	-
3.7337	9420	0.0376	-	-
3.7376	9430	0.0368	-	-
3.7416	9440	0.0381	-	-
3.7455	9450	0.0358	-	-
3.7495	9460	0.0362	-	-
3.7535	9470	0.038	-	-
3.7574	9480	0.0371	-	-
3.7614	9490	0.0371	-	-
3.7654	9500	0.0353	0.0465	0.9617
3.7693	9510	0.0381	-	-
3.7733	9520	0.0362	-	-
3.7772	9530	0.0352	-	-
3.7812	9540	0.0363	-	-
3.7852	9550	0.0352	-	-
3.7891	9560	0.0367	-	-
3.7931	9570	0.035	-	-
3.7971	9580	0.0367	-	-
3.8010	9590	0.0369	-	-
3.8050	9600	0.0365	-	-
3.8090	9610	0.0369	-	-
3.8129	9620	0.0359	-	-
3.8169	9630	0.0367	-	-
3.8208	9640	0.0384	-	-
3.8248	9650	0.0359	-	-
3.8288	9660	0.0368	-	-
3.8327	9670	0.0363	-	-
3.8367	9680	0.0374	-	-
3.8407	9690	0.0372	-	-
3.8446	9700	0.0361	-	-
3.8486	9710	0.0381	-	-
3.8526	9720	0.0342	-	-
3.8565	9730	0.0348	-	-
3.8605	9740	0.0372	-	-
3.8644	9750	0.0377	-	-
3.8684	9760	0.0356	-	-
3.8724	9770	0.0365	-	-
3.8763	9780	0.0368	-	-
3.8803	9790	0.0366	-	-
3.8843	9800	0.0383	-	-
3.8882	9810	0.0353	-	-
3.8922	9820	0.0377	-	-
3.8962	9830	0.0364	-	-
3.9001	9840	0.0362	-	-
3.9041	9850	0.0351	-	-
3.9080	9860	0.0381	-	-
3.9120	9870	0.0368	-	-
3.9160	9880	0.0361	-	-
3.9199	9890	0.0356	-	-
3.9239	9900	0.035	-	-
3.9279	9910	0.0345	-	-
3.9318	9920	0.0378	-	-
3.9358	9930	0.036	-	-
3.9398	9940	0.0367	-	-
3.9437	9950	0.0356	-	-
3.9477	9960	0.034	-	-
3.9516	9970	0.0377	-	-
3.9556	9980	0.0379	-	-
3.9596	9990	0.0388	-	-
3.9635	10000	0.0362	0.0463	0.9618

Framework Versions

Python: 3.10.10
Sentence Transformers: 3.0.1
Transformers: 4.45.0.dev0
PyTorch: 2.2.1+cu121
Accelerate: 0.34.2
Datasets: 2.21.0
Tokenizers: 0.19.1

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",
}

ContrastiveLoss

@inproceedings{hadsell2006dimensionality,
    author={Hadsell, R. and Chopra, S. and LeCun, Y.},
    booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)}, 
    title={Dimensionality Reduction by Learning an Invariant Mapping}, 
    year={2006},
    volume={2},
    number={},
    pages={1735-1742},
    doi={10.1109/CVPR.2006.100}
}