You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

SentenceTransformer based on lemon-mint/mMiniLMv2-L12-H384-Distilled-Iter12-final

This is a sentence-transformers model finetuned from lemon-mint/mMiniLMv2-L12-H384-Distilled-Iter12-final. It maps sentences & paragraphs to a 384-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: lemon-mint/mMiniLMv2-L12-H384-Distilled-Iter12-final
Maximum Sequence Length: 512 tokens
Output Dimensionality: 384 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': 512, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
  (1): Pooling({'word_embedding_dimension': 384, '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("lemon-mint/mMiniLMv2-L12-H384-Distilled-Iter14-final")
# Run inference
sentences = [
    'passage: British Rail produced a variety of railbuses, both as a means of acquiring new rolling stock cheaply, and to provide economical services on lightly-used lines. \n\nRailbuses are a very lightweight type of railcar designed specifically for passenger transport on little-used railway lines. As the name suggests, they share many aspects of their construction with a bus, usually having a bus body, or a modified bus body, and having four wheels on a fixed wheelbase, rather than bogies. Some units were equipped for operation as diesel multiple units.\n\nIn the late 1950s, British Rail tested a series of small railbuses, produced by a variety of manufacturers, for about £12,500 each (£261,000 at 2014 prices). These proved to be very economical (on test the Wickham bus was about ), but were somewhat unreliable. Most of the lines they worked on were closed following the Beeching Cuts and, being non-standard, they were all withdrawn in the mid-1960s, so they were never classified under the TOPS system.',
    'query: What aircraft were evaluated under the Advanced Tanker Cargo Aircraft Program?',
    'query: What do the results of the 2015 Ogun State House of Assembly election reveal about the political landscape of Ogun State?',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

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

Evaluation

Metrics

Semantic Similarity

Dataset: sts-dev
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.7886
spearman_cosine	0.7955
pearson_manhattan	0.793
spearman_manhattan	0.7947
pearson_euclidean	0.7937
spearman_euclidean	0.7955
pearson_dot	0.7886
spearman_dot	0.7955
pearson_max	0.7937
spearman_max	0.7955

Information Retrieval

Dataset: Ko-StrategyQA-dev
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.4932
cosine_accuracy@3	0.6334
cosine_accuracy@5	0.6774
cosine_accuracy@10	0.7399
cosine_precision@1	0.4932
cosine_precision@3	0.2843
cosine_precision@5	0.1986
cosine_precision@10	0.1147
cosine_recall@1	0.3179
cosine_recall@3	0.4988
cosine_recall@5	0.5588
cosine_recall@10	0.6419
cosine_ndcg@10	0.5481
cosine_mrr@10	0.5747
cosine_map@100	0.4962
dot_accuracy@1	0.4932
dot_accuracy@3	0.6334
dot_accuracy@5	0.6774
dot_accuracy@10	0.7399
dot_precision@1	0.4932
dot_precision@3	0.2843
dot_precision@5	0.1986
dot_precision@10	0.1147
dot_recall@1	0.3179
dot_recall@3	0.4988
dot_recall@5	0.5588
dot_recall@10	0.6419
dot_ndcg@10	0.5481
dot_mrr@10	0.5747
dot_map@100	0.4962

Semantic Similarity

Dataset: sts-test
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.718
spearman_cosine	0.7185
pearson_manhattan	0.7285
spearman_manhattan	0.7185
pearson_euclidean	0.7284
spearman_euclidean	0.7185
pearson_dot	0.718
spearman_dot	0.7185
pearson_max	0.7285
spearman_max	0.7185

Training Details

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 52
per_device_eval_batch_size: 4
learning_rate: 0.0001
num_train_epochs: 1
warmup_ratio: 0.05
fp16: True
push_to_hub: True
hub_model_id: lemon-mint/mMiniLMv2-L12-H384-Distilled-Iter14
hub_strategy: checkpoint
hub_private_repo: 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: 52
per_device_eval_batch_size: 4
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 1
eval_accumulation_steps: None
learning_rate: 0.0001
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: 0.05
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: 42
data_seed: None
jit_mode_eval: False
use_ipex: False
bf16: False
fp16: True
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: True
resume_from_checkpoint: None
hub_model_id: lemon-mint/mMiniLMv2-L12-H384-Distilled-Iter14
hub_strategy: checkpoint
hub_private_repo: True
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: False
batch_sampler: batch_sampler
multi_dataset_batch_sampler: proportional

Training Logs

Click to expand

Epoch	Step	Training Loss	loss	Ko-StrategyQA-dev_cosine_map@100	sts-dev_spearman_cosine	sts-test_spearman_cosine
0	0	-	-	0.4817	0.7919	-
0.0011	10	0.0007	-	-	-	-
0.0022	20	0.0007	-	-	-	-
0.0032	30	0.0007	-	-	-	-
0.0043	40	0.0007	-	-	-	-
0.0054	50	0.0007	-	-	-	-
0.0065	60	0.0007	-	-	-	-
0.0076	70	0.0007	-	-	-	-
0.0087	80	0.0007	-	-	-	-
0.0097	90	0.0007	-	-	-	-
0.0108	100	0.0007	-	-	-	-
0.0119	110	0.0007	-	-	-	-
0.0130	120	0.0007	-	-	-	-
0.0141	130	0.0007	-	-	-	-
0.0151	140	0.0007	-	-	-	-
0.0162	150	0.0007	-	-	-	-
0.0173	160	0.0007	-	-	-	-
0.0184	170	0.0007	-	-	-	-
0.0195	180	0.0007	-	-	-	-
0.0206	190	0.0007	-	-	-	-
0.0216	200	0.0007	-	-	-	-
0.0227	210	0.0007	-	-	-	-
0.0238	220	0.0007	-	-	-	-
0.0249	230	0.0007	-	-	-	-
0.0260	240	0.0007	-	-	-	-
0.0270	250	0.0007	-	-	-	-
0.0281	260	0.0007	-	-	-	-
0.0292	270	0.0007	-	-	-	-
0.0303	280	0.0007	-	-	-	-
0.0314	290	0.0007	-	-	-	-
0.0325	300	0.0007	-	-	-	-
0.0335	310	0.0007	-	-	-	-
0.0346	320	0.0007	-	-	-	-
0.0357	330	0.0007	-	-	-	-
0.0368	340	0.0007	-	-	-	-
0.0379	350	0.0007	-	-	-	-
0.0389	360	0.0007	-	-	-	-
0.0400	370	0.0007	-	-	-	-
0.0411	380	0.0007	-	-	-	-
0.0422	390	0.0007	-	-	-	-
0.0433	400	0.0007	-	-	-	-
0.0444	410	0.0007	-	-	-	-
0.0454	420	0.0007	-	-	-	-
0.0465	430	0.0007	-	-	-	-
0.0476	440	0.0007	-	-	-	-
0.0487	450	0.0007	-	-	-	-
0.0498	460	0.0007	-	-	-	-
0.0508	470	0.0007	-	-	-	-
0.0519	480	0.0007	-	-	-	-
0.0530	490	0.0007	-	-	-	-
0.0541	500	0.0007	-	-	-	-
0.0552	510	0.0007	-	-	-	-
0.0563	520	0.0007	-	-	-	-
0.0573	530	0.0007	-	-	-	-
0.0584	540	0.0007	-	-	-	-
0.0595	550	0.0007	-	-	-	-
0.0606	560	0.0007	-	-	-	-
0.0617	570	0.0007	-	-	-	-
0.0628	580	0.0007	-	-	-	-
0.0638	590	0.0007	-	-	-	-
0.0649	600	0.0007	-	-	-	-
0.0660	610	0.0007	-	-	-	-
0.0671	620	0.0007	-	-	-	-
0.0682	630	0.0007	-	-	-	-
0.0692	640	0.0007	-	-	-	-
0.0703	650	0.0007	-	-	-	-
0.0714	660	0.0007	-	-	-	-
0.0725	670	0.0007	-	-	-	-
0.0736	680	0.0007	-	-	-	-
0.0747	690	0.0007	-	-	-	-
0.0757	700	0.0007	-	-	-	-
0.0768	710	0.0007	-	-	-	-
0.0779	720	0.0007	-	-	-	-
0.0790	730	0.0007	-	-	-	-
0.0801	740	0.0007	-	-	-	-
0.0811	750	0.0007	-	-	-	-
0.0822	760	0.0007	-	-	-	-
0.0833	770	0.0007	-	-	-	-
0.0844	780	0.0007	-	-	-	-
0.0855	790	0.0007	-	-	-	-
0.0866	800	0.0007	-	-	-	-
0.0876	810	0.0007	-	-	-	-
0.0887	820	0.0007	-	-	-	-
0.0898	830	0.0007	-	-	-	-
0.0909	840	0.0007	-	-	-	-
0.0920	850	0.0007	-	-	-	-
0.0930	860	0.0007	-	-	-	-
0.0941	870	0.0007	-	-	-	-
0.0952	880	0.0007	-	-	-	-
0.0963	890	0.0007	-	-	-	-
0.0974	900	0.0007	-	-	-	-
0.0985	910	0.0007	-	-	-	-
0.0995	920	0.0007	-	-	-	-
0.1006	930	0.0007	-	-	-	-
0.1017	940	0.0007	-	-	-	-
0.1028	950	0.0007	-	-	-	-
0.1039	960	0.0007	-	-	-	-
0.1049	970	0.0007	-	-	-	-
0.1060	980	0.0007	-	-	-	-
0.1071	990	0.0007	-	-	-	-
0.1082	1000	0.0007	0.0007	0.4708	0.7900	-
0.1093	1010	0.0007	-	-	-	-
0.1104	1020	0.0007	-	-	-	-
0.1114	1030	0.0007	-	-	-	-
0.1125	1040	0.0007	-	-	-	-
0.1136	1050	0.0007	-	-	-	-
0.1147	1060	0.0007	-	-	-	-
0.1158	1070	0.0007	-	-	-	-
0.1168	1080	0.0007	-	-	-	-
0.1179	1090	0.0007	-	-	-	-
0.1190	1100	0.0007	-	-	-	-
0.1201	1110	0.0007	-	-	-	-
0.1212	1120	0.0007	-	-	-	-
0.1223	1130	0.0007	-	-	-	-
0.1233	1140	0.0007	-	-	-	-
0.1244	1150	0.0007	-	-	-	-
0.1255	1160	0.0007	-	-	-	-
0.1266	1170	0.0007	-	-	-	-
0.1277	1180	0.0007	-	-	-	-
0.1287	1190	0.0007	-	-	-	-
0.1298	1200	0.0007	-	-	-	-
0.1309	1210	0.0007	-	-	-	-
0.1320	1220	0.0007	-	-	-	-
0.1331	1230	0.0007	-	-	-	-
0.1342	1240	0.0007	-	-	-	-
0.1352	1250	0.0007	-	-	-	-
0.1363	1260	0.0007	-	-	-	-
0.1374	1270	0.0007	-	-	-	-
0.1385	1280	0.0007	-	-	-	-
0.1396	1290	0.0007	-	-	-	-
0.1406	1300	0.0007	-	-	-	-
0.1417	1310	0.0007	-	-	-	-
0.1428	1320	0.0007	-	-	-	-
0.1439	1330	0.0007	-	-	-	-
0.1450	1340	0.0007	-	-	-	-
0.1461	1350	0.0007	-	-	-	-
0.1471	1360	0.0007	-	-	-	-
0.1482	1370	0.0007	-	-	-	-
0.1493	1380	0.0007	-	-	-	-
0.1504	1390	0.0007	-	-	-	-
0.1515	1400	0.0007	-	-	-	-
0.1525	1410	0.0007	-	-	-	-
0.1536	1420	0.0007	-	-	-	-
0.1547	1430	0.0007	-	-	-	-
0.1558	1440	0.0007	-	-	-	-
0.1569	1450	0.0007	-	-	-	-
0.1580	1460	0.0007	-	-	-	-
0.1590	1470	0.0007	-	-	-	-
0.1601	1480	0.0007	-	-	-	-
0.1612	1490	0.0007	-	-	-	-
0.1623	1500	0.0007	-	-	-	-
0.1634	1510	0.0007	-	-	-	-
0.1644	1520	0.0007	-	-	-	-
0.1655	1530	0.0007	-	-	-	-
0.1666	1540	0.0007	-	-	-	-
0.1677	1550	0.0007	-	-	-	-
0.1688	1560	0.0007	-	-	-	-
0.1699	1570	0.0007	-	-	-	-
0.1709	1580	0.0007	-	-	-	-
0.1720	1590	0.0007	-	-	-	-
0.1731	1600	0.0007	-	-	-	-
0.1742	1610	0.0007	-	-	-	-
0.1753	1620	0.0007	-	-	-	-
0.1763	1630	0.0007	-	-	-	-
0.1774	1640	0.0007	-	-	-	-
0.1785	1650	0.0007	-	-	-	-
0.1796	1660	0.0007	-	-	-	-
0.1807	1670	0.0007	-	-	-	-
0.1818	1680	0.0007	-	-	-	-
0.1828	1690	0.0007	-	-	-	-
0.1839	1700	0.0007	-	-	-	-
0.1850	1710	0.0007	-	-	-	-
0.1861	1720	0.0007	-	-	-	-
0.1872	1730	0.0007	-	-	-	-
0.1883	1740	0.0007	-	-	-	-
0.1893	1750	0.0007	-	-	-	-
0.1904	1760	0.0007	-	-	-	-
0.1915	1770	0.0007	-	-	-	-
0.1926	1780	0.0007	-	-	-	-
0.1937	1790	0.0007	-	-	-	-
0.1947	1800	0.0007	-	-	-	-
0.1958	1810	0.0007	-	-	-	-
0.1969	1820	0.0007	-	-	-	-
0.1980	1830	0.0007	-	-	-	-
0.1991	1840	0.0007	-	-	-	-
0.2002	1850	0.0007	-	-	-	-
0.2012	1860	0.0007	-	-	-	-
0.2023	1870	0.0007	-	-	-	-
0.2034	1880	0.0007	-	-	-	-
0.2045	1890	0.0007	-	-	-	-
0.2056	1900	0.0007	-	-	-	-
0.2066	1910	0.0007	-	-	-	-
0.2077	1920	0.0007	-	-	-	-
0.2088	1930	0.0007	-	-	-	-
0.2099	1940	0.0007	-	-	-	-
0.2110	1950	0.0007	-	-	-	-
0.2121	1960	0.0007	-	-	-	-
0.2131	1970	0.0007	-	-	-	-
0.2142	1980	0.0007	-	-	-	-
0.2153	1990	0.0007	-	-	-	-
0.2164	2000	0.0007	0.0007	0.4757	0.7863	-
0.2175	2010	0.0007	-	-	-	-
0.2185	2020	0.0007	-	-	-	-
0.2196	2030	0.0007	-	-	-	-
0.2207	2040	0.0007	-	-	-	-
0.2218	2050	0.0007	-	-	-	-
0.2229	2060	0.0007	-	-	-	-
0.2240	2070	0.0007	-	-	-	-
0.2250	2080	0.0007	-	-	-	-
0.2261	2090	0.0007	-	-	-	-
0.2272	2100	0.0007	-	-	-	-
0.2283	2110	0.0007	-	-	-	-
0.2294	2120	0.0007	-	-	-	-
0.2304	2130	0.0007	-	-	-	-
0.2315	2140	0.0007	-	-	-	-
0.2326	2150	0.0007	-	-	-	-
0.2337	2160	0.0007	-	-	-	-
0.2348	2170	0.0007	-	-	-	-
0.2359	2180	0.0007	-	-	-	-
0.2369	2190	0.0007	-	-	-	-
0.2380	2200	0.0007	-	-	-	-
0.2391	2210	0.0007	-	-	-	-
0.2402	2220	0.0007	-	-	-	-
0.2413	2230	0.0007	-	-	-	-
0.2423	2240	0.0007	-	-	-	-
0.2434	2250	0.0007	-	-	-	-
0.2445	2260	0.0007	-	-	-	-
0.2456	2270	0.0007	-	-	-	-
0.2467	2280	0.0007	-	-	-	-
0.2478	2290	0.0007	-	-	-	-
0.2488	2300	0.0007	-	-	-	-
0.2499	2310	0.0007	-	-	-	-
0.2510	2320	0.0007	-	-	-	-
0.2521	2330	0.0007	-	-	-	-
0.2532	2340	0.0007	-	-	-	-
0.2542	2350	0.0007	-	-	-	-
0.2553	2360	0.0007	-	-	-	-
0.2564	2370	0.0007	-	-	-	-
0.2575	2380	0.0007	-	-	-	-
0.2586	2390	0.0007	-	-	-	-
0.2597	2400	0.0007	-	-	-	-
0.2607	2410	0.0007	-	-	-	-
0.2618	2420	0.0007	-	-	-	-
0.2629	2430	0.0007	-	-	-	-
0.2640	2440	0.0007	-	-	-	-
0.2651	2450	0.0007	-	-	-	-
0.2661	2460	0.0007	-	-	-	-
0.2672	2470	0.0007	-	-	-	-
0.2683	2480	0.0007	-	-	-	-
0.2694	2490	0.0007	-	-	-	-
0.2705	2500	0.0007	-	-	-	-
0.2716	2510	0.0007	-	-	-	-
0.2726	2520	0.0007	-	-	-	-
0.2737	2530	0.0007	-	-	-	-
0.2748	2540	0.0007	-	-	-	-
0.2759	2550	0.0007	-	-	-	-
0.2770	2560	0.0007	-	-	-	-
0.2780	2570	0.0007	-	-	-	-
0.2791	2580	0.0007	-	-	-	-
0.2802	2590	0.0007	-	-	-	-
0.2813	2600	0.0007	-	-	-	-
0.2824	2610	0.0007	-	-	-	-
0.2835	2620	0.0007	-	-	-	-
0.2845	2630	0.0007	-	-	-	-
0.2856	2640	0.0007	-	-	-	-
0.2867	2650	0.0007	-	-	-	-
0.2878	2660	0.0007	-	-	-	-
0.2889	2670	0.0007	-	-	-	-
0.2899	2680	0.0007	-	-	-	-
0.2910	2690	0.0007	-	-	-	-
0.2921	2700	0.0007	-	-	-	-
0.2932	2710	0.0007	-	-	-	-
0.2943	2720	0.0007	-	-	-	-
0.2954	2730	0.0007	-	-	-	-
0.2964	2740	0.0007	-	-	-	-
0.2975	2750	0.0007	-	-	-	-
0.2986	2760	0.0007	-	-	-	-
0.2997	2770	0.0007	-	-	-	-
0.3008	2780	0.0007	-	-	-	-
0.3019	2790	0.0007	-	-	-	-
0.3029	2800	0.0007	-	-	-	-
0.3040	2810	0.0007	-	-	-	-
0.3051	2820	0.0007	-	-	-	-
0.3062	2830	0.0007	-	-	-	-
0.3073	2840	0.0007	-	-	-	-
0.3083	2850	0.0007	-	-	-	-
0.3094	2860	0.0007	-	-	-	-
0.3105	2870	0.0007	-	-	-	-
0.3116	2880	0.0007	-	-	-	-
0.3127	2890	0.0007	-	-	-	-
0.3138	2900	0.0007	-	-	-	-
0.3148	2910	0.0007	-	-	-	-
0.3159	2920	0.0007	-	-	-	-
0.3170	2930	0.0007	-	-	-	-
0.3181	2940	0.0007	-	-	-	-
0.3192	2950	0.0007	-	-	-	-
0.3202	2960	0.0007	-	-	-	-
0.3213	2970	0.0007	-	-	-	-
0.3224	2980	0.0007	-	-	-	-
0.3235	2990	0.0007	-	-	-	-
0.3246	3000	0.0007	0.0007	0.4816	0.7941	-
0.3257	3010	0.0007	-	-	-	-
0.3267	3020	0.0007	-	-	-	-
0.3278	3030	0.0007	-	-	-	-
0.3289	3040	0.0007	-	-	-	-
0.3300	3050	0.0007	-	-	-	-
0.3311	3060	0.0007	-	-	-	-
0.3321	3070	0.0007	-	-	-	-
0.3332	3080	0.0007	-	-	-	-
0.3343	3090	0.0007	-	-	-	-
0.3354	3100	0.0007	-	-	-	-
0.3365	3110	0.0007	-	-	-	-
0.3376	3120	0.0007	-	-	-	-
0.3386	3130	0.0007	-	-	-	-
0.3397	3140	0.0007	-	-	-	-
0.3408	3150	0.0007	-	-	-	-
0.3419	3160	0.0007	-	-	-	-
0.3430	3170	0.0007	-	-	-	-
0.3440	3180	0.0007	-	-	-	-
0.3451	3190	0.0007	-	-	-	-
0.3462	3200	0.0007	-	-	-	-
0.3473	3210	0.0007	-	-	-	-
0.3484	3220	0.0007	-	-	-	-
0.3495	3230	0.0007	-	-	-	-
0.3505	3240	0.0007	-	-	-	-
0.3516	3250	0.0007	-	-	-	-
0.3527	3260	0.0007	-	-	-	-
0.3538	3270	0.0007	-	-	-	-
0.3549	3280	0.0007	-	-	-	-
0.3559	3290	0.0007	-	-	-	-
0.3570	3300	0.0007	-	-	-	-
0.3581	3310	0.0007	-	-	-	-
0.3592	3320	0.0007	-	-	-	-
0.3603	3330	0.0007	-	-	-	-
0.3614	3340	0.0007	-	-	-	-
0.3624	3350	0.0007	-	-	-	-
0.3635	3360	0.0007	-	-	-	-
0.3646	3370	0.0007	-	-	-	-
0.3657	3380	0.0007	-	-	-	-
0.3668	3390	0.0007	-	-	-	-
0.3678	3400	0.0007	-	-	-	-
0.3689	3410	0.0007	-	-	-	-
0.3700	3420	0.0007	-	-	-	-
0.3711	3430	0.0007	-	-	-	-
0.3722	3440	0.0007	-	-	-	-
0.3733	3450	0.0007	-	-	-	-
0.3743	3460	0.0007	-	-	-	-
0.3754	3470	0.0007	-	-	-	-
0.3765	3480	0.0007	-	-	-	-
0.3776	3490	0.0007	-	-	-	-
0.3787	3500	0.0007	-	-	-	-
0.3797	3510	0.0007	-	-	-	-
0.3808	3520	0.0007	-	-	-	-
0.3819	3530	0.0007	-	-	-	-
0.3830	3540	0.0007	-	-	-	-
0.3841	3550	0.0007	-	-	-	-
0.3852	3560	0.0007	-	-	-	-
0.3862	3570	0.0007	-	-	-	-
0.3873	3580	0.0007	-	-	-	-
0.3884	3590	0.0007	-	-	-	-
0.3895	3600	0.0007	-	-	-	-
0.3906	3610	0.0007	-	-	-	-
0.3916	3620	0.0007	-	-	-	-
0.3927	3630	0.0007	-	-	-	-
0.3938	3640	0.0007	-	-	-	-
0.3949	3650	0.0007	-	-	-	-
0.3960	3660	0.0007	-	-	-	-
0.3971	3670	0.0007	-	-	-	-
0.3981	3680	0.0007	-	-	-	-
0.3992	3690	0.0007	-	-	-	-
0.4003	3700	0.0007	-	-	-	-
0.4014	3710	0.0007	-	-	-	-
0.4025	3720	0.0007	-	-	-	-
0.4035	3730	0.0007	-	-	-	-
0.4046	3740	0.0007	-	-	-	-
0.4057	3750	0.0007	-	-	-	-
0.4068	3760	0.0007	-	-	-	-
0.4079	3770	0.0007	-	-	-	-
0.4090	3780	0.0007	-	-	-	-
0.4100	3790	0.0007	-	-	-	-
0.4111	3800	0.0007	-	-	-	-
0.4122	3810	0.0007	-	-	-	-
0.4133	3820	0.0007	-	-	-	-
0.4144	3830	0.0007	-	-	-	-
0.4154	3840	0.0007	-	-	-	-
0.4165	3850	0.0007	-	-	-	-
0.4176	3860	0.0007	-	-	-	-
0.4187	3870	0.0007	-	-	-	-
0.4198	3880	0.0007	-	-	-	-
0.4209	3890	0.0007	-	-	-	-
0.4219	3900	0.0007	-	-	-	-
0.4230	3910	0.0007	-	-	-	-
0.4241	3920	0.0007	-	-	-	-
0.4252	3930	0.0007	-	-	-	-
0.4263	3940	0.0007	-	-	-	-
0.4274	3950	0.0007	-	-	-	-
0.4284	3960	0.0007	-	-	-	-
0.4295	3970	0.0007	-	-	-	-
0.4306	3980	0.0007	-	-	-	-
0.4317	3990	0.0007	-	-	-	-
0.4328	4000	0.0007	0.0007	0.4878	0.7932	-
0.4338	4010	0.0007	-	-	-	-
0.4349	4020	0.0007	-	-	-	-
0.4360	4030	0.0007	-	-	-	-
0.4371	4040	0.0007	-	-	-	-
0.4382	4050	0.0007	-	-	-	-
0.4393	4060	0.0007	-	-	-	-
0.4403	4070	0.0007	-	-	-	-
0.4414	4080	0.0007	-	-	-	-
0.4425	4090	0.0007	-	-	-	-
0.4436	4100	0.0007	-	-	-	-
0.4447	4110	0.0007	-	-	-	-
0.4457	4120	0.0007	-	-	-	-
0.4468	4130	0.0007	-	-	-	-
0.4479	4140	0.0007	-	-	-	-
0.4490	4150	0.0007	-	-	-	-
0.4501	4160	0.0007	-	-	-	-
0.4512	4170	0.0007	-	-	-	-
0.4522	4180	0.0007	-	-	-	-
0.4533	4190	0.0007	-	-	-	-
0.4544	4200	0.0007	-	-	-	-
0.4555	4210	0.0007	-	-	-	-
0.4566	4220	0.0007	-	-	-	-
0.4576	4230	0.0007	-	-	-	-
0.4587	4240	0.0007	-	-	-	-
0.4598	4250	0.0006	-	-	-	-
0.4609	4260	0.0007	-	-	-	-
0.4620	4270	0.0007	-	-	-	-
0.4631	4280	0.0007	-	-	-	-
0.4641	4290	0.0007	-	-	-	-
0.4652	4300	0.0007	-	-	-	-
0.4663	4310	0.0007	-	-	-	-
0.4674	4320	0.0007	-	-	-	-
0.4685	4330	0.0007	-	-	-	-
0.4695	4340	0.0007	-	-	-	-
0.4706	4350	0.0007	-	-	-	-
0.4717	4360	0.0007	-	-	-	-
0.4728	4370	0.0007	-	-	-	-
0.4739	4380	0.0007	-	-	-	-
0.4750	4390	0.0007	-	-	-	-
0.4760	4400	0.0007	-	-	-	-
0.4771	4410	0.0007	-	-	-	-
0.4782	4420	0.0007	-	-	-	-
0.4793	4430	0.0007	-	-	-	-
0.4804	4440	0.0007	-	-	-	-
0.4814	4450	0.0007	-	-	-	-
0.4825	4460	0.0007	-	-	-	-
0.4836	4470	0.0007	-	-	-	-
0.4847	4480	0.0007	-	-	-	-
0.4858	4490	0.0007	-	-	-	-
0.4869	4500	0.0007	-	-	-	-
0.4879	4510	0.0007	-	-	-	-
0.4890	4520	0.0007	-	-	-	-
0.4901	4530	0.0007	-	-	-	-
0.4912	4540	0.0007	-	-	-	-
0.4923	4550	0.0007	-	-	-	-
0.4933	4560	0.0007	-	-	-	-
0.4944	4570	0.0007	-	-	-	-
0.4955	4580	0.0007	-	-	-	-
0.4966	4590	0.0007	-	-	-	-
0.4977	4600	0.0007	-	-	-	-
0.4988	4610	0.0007	-	-	-	-
0.4998	4620	0.0007	-	-	-	-
0.5009	4630	0.0007	-	-	-	-
0.5020	4640	0.0007	-	-	-	-
0.5031	4650	0.0007	-	-	-	-
0.5042	4660	0.0007	-	-	-	-
0.5052	4670	0.0007	-	-	-	-
0.5063	4680	0.0007	-	-	-	-
0.5074	4690	0.0007	-	-	-	-
0.5085	4700	0.0007	-	-	-	-
0.5096	4710	0.0007	-	-	-	-
0.5107	4720	0.0007	-	-	-	-
0.5117	4730	0.0007	-	-	-	-
0.5128	4740	0.0007	-	-	-	-
0.5139	4750	0.0007	-	-	-	-
0.5150	4760	0.0007	-	-	-	-
0.5161	4770	0.0007	-	-	-	-
0.5171	4780	0.0007	-	-	-	-
0.5182	4790	0.0007	-	-	-	-
0.5193	4800	0.0007	-	-	-	-
0.5204	4810	0.0007	-	-	-	-
0.5215	4820	0.0007	-	-	-	-
0.5226	4830	0.0006	-	-	-	-
0.5236	4840	0.0007	-	-	-	-
0.5247	4850	0.0007	-	-	-	-
0.5258	4860	0.0007	-	-	-	-
0.5269	4870	0.0007	-	-	-	-
0.5280	4880	0.0007	-	-	-	-
0.5290	4890	0.0007	-	-	-	-
0.5301	4900	0.0007	-	-	-	-
0.5312	4910	0.0007	-	-	-	-
0.5323	4920	0.0007	-	-	-	-
0.5334	4930	0.0007	-	-	-	-
0.5345	4940	0.0007	-	-	-	-
0.5355	4950	0.0007	-	-	-	-
0.5366	4960	0.0007	-	-	-	-
0.5377	4970	0.0007	-	-	-	-
0.5388	4980	0.0007	-	-	-	-
0.5399	4990	0.0007	-	-	-	-
0.5409	5000	0.0007	0.0006	0.4867	0.7951	-
0.5420	5010	0.0007	-	-	-	-
0.5431	5020	0.0007	-	-	-	-
0.5442	5030	0.0007	-	-	-	-
0.5453	5040	0.0007	-	-	-	-
0.5464	5050	0.0007	-	-	-	-
0.5474	5060	0.0007	-	-	-	-
0.5485	5070	0.0007	-	-	-	-
0.5496	5080	0.0007	-	-	-	-
0.5507	5090	0.0007	-	-	-	-
0.5518	5100	0.0006	-	-	-	-
0.5529	5110	0.0007	-	-	-	-
0.5539	5120	0.0007	-	-	-	-
0.5550	5130	0.0007	-	-	-	-
0.5561	5140	0.0007	-	-	-	-
0.5572	5150	0.0007	-	-	-	-
0.5583	5160	0.0007	-	-	-	-
0.5593	5170	0.0007	-	-	-	-
0.5604	5180	0.0007	-	-	-	-
0.5615	5190	0.0007	-	-	-	-
0.5626	5200	0.0007	-	-	-	-
0.5637	5210	0.0007	-	-	-	-
0.5648	5220	0.0007	-	-	-	-
0.5658	5230	0.0007	-	-	-	-
0.5669	5240	0.0007	-	-	-	-
0.5680	5250	0.0007	-	-	-	-
0.5691	5260	0.0007	-	-	-	-
0.5702	5270	0.0007	-	-	-	-
0.5712	5280	0.0007	-	-	-	-
0.5723	5290	0.0007	-	-	-	-
0.5734	5300	0.0007	-	-	-	-
0.5745	5310	0.0007	-	-	-	-
0.5756	5320	0.0007	-	-	-	-
0.5767	5330	0.0007	-	-	-	-
0.5777	5340	0.0006	-	-	-	-
0.5788	5350	0.0007	-	-	-	-
0.5799	5360	0.0007	-	-	-	-
0.5810	5370	0.0007	-	-	-	-
0.5821	5380	0.0006	-	-	-	-
0.5831	5390	0.0007	-	-	-	-
0.5842	5400	0.0007	-	-	-	-
0.5853	5410	0.0007	-	-	-	-
0.5864	5420	0.0007	-	-	-	-
0.5875	5430	0.0007	-	-	-	-
0.5886	5440	0.0007	-	-	-	-
0.5896	5450	0.0006	-	-	-	-
0.5907	5460	0.0007	-	-	-	-
0.5918	5470	0.0007	-	-	-	-
0.5929	5480	0.0007	-	-	-	-
0.5940	5490	0.0007	-	-	-	-
0.5950	5500	0.0007	-	-	-	-
0.5961	5510	0.0007	-	-	-	-
0.5972	5520	0.0007	-	-	-	-
0.5983	5530	0.0007	-	-	-	-
0.5994	5540	0.0007	-	-	-	-
0.6005	5550	0.0007	-	-	-	-
0.6015	5560	0.0007	-	-	-	-
0.6026	5570	0.0007	-	-	-	-
0.6037	5580	0.0007	-	-	-	-
0.6048	5590	0.0007	-	-	-	-
0.6059	5600	0.0007	-	-	-	-
0.6069	5610	0.0007	-	-	-	-
0.6080	5620	0.0007	-	-	-	-
0.6091	5630	0.0007	-	-	-	-
0.6102	5640	0.0007	-	-	-	-
0.6113	5650	0.0007	-	-	-	-
0.6124	5660	0.0007	-	-	-	-
0.6134	5670	0.0007	-	-	-	-
0.6145	5680	0.0007	-	-	-	-
0.6156	5690	0.0007	-	-	-	-
0.6167	5700	0.0007	-	-	-	-
0.6178	5710	0.0007	-	-	-	-
0.6188	5720	0.0007	-	-	-	-
0.6199	5730	0.0007	-	-	-	-
0.6210	5740	0.0007	-	-	-	-
0.6221	5750	0.0007	-	-	-	-
0.6232	5760	0.0007	-	-	-	-
0.6243	5770	0.0007	-	-	-	-
0.6253	5780	0.0007	-	-	-	-
0.6264	5790	0.0007	-	-	-	-
0.6275	5800	0.0007	-	-	-	-
0.6286	5810	0.0007	-	-	-	-
0.6297	5820	0.0007	-	-	-	-
0.6307	5830	0.0007	-	-	-	-
0.6318	5840	0.0007	-	-	-	-
0.6329	5850	0.0007	-	-	-	-
0.6340	5860	0.0007	-	-	-	-
0.6351	5870	0.0007	-	-	-	-
0.6362	5880	0.0007	-	-	-	-
0.6372	5890	0.0006	-	-	-	-
0.6383	5900	0.0006	-	-	-	-
0.6394	5910	0.0007	-	-	-	-
0.6405	5920	0.0007	-	-	-	-
0.6416	5930	0.0007	-	-	-	-
0.6426	5940	0.0007	-	-	-	-
0.6437	5950	0.0007	-	-	-	-
0.6448	5960	0.0007	-	-	-	-
0.6459	5970	0.0007	-	-	-	-
0.6470	5980	0.0007	-	-	-	-
0.6481	5990	0.0007	-	-	-	-
0.6491	6000	0.0007	0.0006	0.4981	0.7961	-
0.6502	6010	0.0006	-	-	-	-
0.6513	6020	0.0007	-	-	-	-
0.6524	6030	0.0007	-	-	-	-
0.6535	6040	0.0007	-	-	-	-
0.6545	6050	0.0007	-	-	-	-
0.6556	6060	0.0007	-	-	-	-
0.6567	6070	0.0007	-	-	-	-
0.6578	6080	0.0007	-	-	-	-
0.6589	6090	0.0007	-	-	-	-
0.6600	6100	0.0007	-	-	-	-
0.6610	6110	0.0007	-	-	-	-
0.6621	6120	0.0007	-	-	-	-
0.6632	6130	0.0007	-	-	-	-
0.6643	6140	0.0007	-	-	-	-
0.6654	6150	0.0007	-	-	-	-
0.6665	6160	0.0007	-	-	-	-
0.6675	6170	0.0006	-	-	-	-
0.6686	6180	0.0007	-	-	-	-
0.6697	6190	0.0007	-	-	-	-
0.6708	6200	0.0007	-	-	-	-
0.6719	6210	0.0007	-	-	-	-
0.6729	6220	0.0007	-	-	-	-
0.6740	6230	0.0007	-	-	-	-
0.6751	6240	0.0007	-	-	-	-
0.6762	6250	0.0007	-	-	-	-
0.6773	6260	0.0007	-	-	-	-
0.6784	6270	0.0007	-	-	-	-
0.6794	6280	0.0007	-	-	-	-
0.6805	6290	0.0007	-	-	-	-
0.6816	6300	0.0007	-	-	-	-
0.6827	6310	0.0007	-	-	-	-
0.6838	6320	0.0007	-	-	-	-
0.6848	6330	0.0007	-	-	-	-
0.6859	6340	0.0007	-	-	-	-
0.6870	6350	0.0007	-	-	-	-
0.6881	6360	0.0007	-	-	-	-
0.6892	6370	0.0007	-	-	-	-
0.6903	6380	0.0007	-	-	-	-
0.6913	6390	0.0007	-	-	-	-
0.6924	6400	0.0007	-	-	-	-
0.6935	6410	0.0007	-	-	-	-
0.6946	6420	0.0006	-	-	-	-
0.6957	6430	0.0006	-	-	-	-
0.6967	6440	0.0007	-	-	-	-
0.6978	6450	0.0006	-	-	-	-
0.6989	6460	0.0007	-	-	-	-
0.7000	6470	0.0007	-	-	-	-
0.7011	6480	0.0006	-	-	-	-
0.7022	6490	0.0007	-	-	-	-
0.7032	6500	0.0006	-	-	-	-
0.7043	6510	0.0007	-	-	-	-
0.7054	6520	0.0007	-	-	-	-
0.7065	6530	0.0007	-	-	-	-
0.7076	6540	0.0007	-	-	-	-
0.7086	6550	0.0007	-	-	-	-
0.7097	6560	0.0007	-	-	-	-
0.7108	6570	0.0007	-	-	-	-
0.7119	6580	0.0007	-	-	-	-
0.7130	6590	0.0007	-	-	-	-
0.7141	6600	0.0007	-	-	-	-
0.7151	6610	0.0006	-	-	-	-
0.7162	6620	0.0007	-	-	-	-
0.7173	6630	0.0007	-	-	-	-
0.7184	6640	0.0007	-	-	-	-
0.7195	6650	0.0007	-	-	-	-
0.7205	6660	0.0007	-	-	-	-
0.7216	6670	0.0007	-	-	-	-
0.7227	6680	0.0007	-	-	-	-
0.7238	6690	0.0007	-	-	-	-
0.7249	6700	0.0007	-	-	-	-
0.7260	6710	0.0007	-	-	-	-
0.7270	6720	0.0007	-	-	-	-
0.7281	6730	0.0007	-	-	-	-
0.7292	6740	0.0007	-	-	-	-
0.7303	6750	0.0007	-	-	-	-
0.7314	6760	0.0006	-	-	-	-
0.7324	6770	0.0007	-	-	-	-
0.7335	6780	0.0007	-	-	-	-
0.7346	6790	0.0006	-	-	-	-
0.7357	6800	0.0007	-	-	-	-
0.7368	6810	0.0006	-	-	-	-
0.7379	6820	0.0006	-	-	-	-
0.7389	6830	0.0006	-	-	-	-
0.7400	6840	0.0007	-	-	-	-
0.7411	6850	0.0007	-	-	-	-
0.7422	6860	0.0007	-	-	-	-
0.7433	6870	0.0006	-	-	-	-
0.7443	6880	0.0007	-	-	-	-
0.7454	6890	0.0007	-	-	-	-
0.7465	6900	0.0007	-	-	-	-
0.7476	6910	0.0006	-	-	-	-
0.7487	6920	0.0007	-	-	-	-
0.7498	6930	0.0006	-	-	-	-
0.7508	6940	0.0007	-	-	-	-
0.7519	6950	0.0007	-	-	-	-
0.7530	6960	0.0007	-	-	-	-
0.7541	6970	0.0007	-	-	-	-
0.7552	6980	0.0007	-	-	-	-
0.7562	6990	0.0007	-	-	-	-
0.7573	7000	0.0006	0.0006	0.4935	0.7972	-
0.7584	7010	0.0007	-	-	-	-
0.7595	7020	0.0007	-	-	-	-
0.7606	7030	0.0007	-	-	-	-
0.7617	7040	0.0007	-	-	-	-
0.7627	7050	0.0007	-	-	-	-
0.7638	7060	0.0006	-	-	-	-
0.7649	7070	0.0007	-	-	-	-
0.7660	7080	0.0007	-	-	-	-
0.7671	7090	0.0007	-	-	-	-
0.7681	7100	0.0007	-	-	-	-
0.7692	7110	0.0007	-	-	-	-
0.7703	7120	0.0007	-	-	-	-
0.7714	7130	0.0007	-	-	-	-
0.7725	7140	0.0006	-	-	-	-
0.7736	7150	0.0006	-	-	-	-
0.7746	7160	0.0007	-	-	-	-
0.7757	7170	0.0006	-	-	-	-
0.7768	7180	0.0007	-	-	-	-
0.7779	7190	0.0007	-	-	-	-
0.7790	7200	0.0007	-	-	-	-
0.7800	7210	0.0006	-	-	-	-
0.7811	7220	0.0007	-	-	-	-
0.7822	7230	0.0007	-	-	-	-
0.7833	7240	0.0006	-	-	-	-
0.7844	7250	0.0007	-	-	-	-
0.7855	7260	0.0007	-	-	-	-
0.7865	7270	0.0006	-	-	-	-
0.7876	7280	0.0007	-	-	-	-
0.7887	7290	0.0007	-	-	-	-
0.7898	7300	0.0006	-	-	-	-
0.7909	7310	0.0007	-	-	-	-
0.7920	7320	0.0007	-	-	-	-
0.7930	7330	0.0007	-	-	-	-
0.7941	7340	0.0007	-	-	-	-
0.7952	7350	0.0007	-	-	-	-
0.7963	7360	0.0006	-	-	-	-
0.7974	7370	0.0007	-	-	-	-
0.7984	7380	0.0006	-	-	-	-
0.7995	7390	0.0007	-	-	-	-
0.8006	7400	0.0006	-	-	-	-
0.8017	7410	0.0007	-	-	-	-
0.8028	7420	0.0007	-	-	-	-
0.8039	7430	0.0007	-	-	-	-
0.8049	7440	0.0007	-	-	-	-
0.8060	7450	0.0006	-	-	-	-
0.8071	7460	0.0006	-	-	-	-
0.8082	7470	0.0007	-	-	-	-
0.8093	7480	0.0007	-	-	-	-
0.8103	7490	0.0007	-	-	-	-
0.8114	7500	0.0007	-	-	-	-
0.8125	7510	0.0007	-	-	-	-
0.8136	7520	0.0007	-	-	-	-
0.8147	7530	0.0007	-	-	-	-
0.8158	7540	0.0007	-	-	-	-
0.8168	7550	0.0006	-	-	-	-
0.8179	7560	0.0007	-	-	-	-
0.8190	7570	0.0006	-	-	-	-
0.8201	7580	0.0007	-	-	-	-
0.8212	7590	0.0006	-	-	-	-
0.8222	7600	0.0007	-	-	-	-
0.8233	7610	0.0006	-	-	-	-
0.8244	7620	0.0007	-	-	-	-
0.8255	7630	0.0007	-	-	-	-
0.8266	7640	0.0007	-	-	-	-
0.8277	7650	0.0007	-	-	-	-
0.8287	7660	0.0007	-	-	-	-
0.8298	7670	0.0007	-	-	-	-
0.8309	7680	0.0007	-	-	-	-
0.8320	7690	0.0007	-	-	-	-
0.8331	7700	0.0007	-	-	-	-
0.8341	7710	0.0006	-	-	-	-
0.8352	7720	0.0007	-	-	-	-
0.8363	7730	0.0007	-	-	-	-
0.8374	7740	0.0006	-	-	-	-
0.8385	7750	0.0007	-	-	-	-
0.8396	7760	0.0007	-	-	-	-
0.8406	7770	0.0007	-	-	-	-
0.8417	7780	0.0007	-	-	-	-
0.8428	7790	0.0007	-	-	-	-
0.8439	7800	0.0006	-	-	-	-
0.8450	7810	0.0007	-	-	-	-
0.8460	7820	0.0007	-	-	-	-
0.8471	7830	0.0007	-	-	-	-
0.8482	7840	0.0007	-	-	-	-
0.8493	7850	0.0006	-	-	-	-
0.8504	7860	0.0006	-	-	-	-
0.8515	7870	0.0007	-	-	-	-
0.8525	7880	0.0006	-	-	-	-
0.8536	7890	0.0007	-	-	-	-
0.8547	7900	0.0006	-	-	-	-
0.8558	7910	0.0006	-	-	-	-
0.8569	7920	0.0006	-	-	-	-
0.8579	7930	0.0006	-	-	-	-
0.8590	7940	0.0006	-	-	-	-
0.8601	7950	0.0007	-	-	-	-
0.8612	7960	0.0007	-	-	-	-
0.8623	7970	0.0007	-	-	-	-
0.8634	7980	0.0006	-	-	-	-
0.8644	7990	0.0007	-	-	-	-
0.8655	8000	0.0006	0.0006	0.4942	0.7970	-
0.8666	8010	0.0007	-	-	-	-
0.8677	8020	0.0007	-	-	-	-
0.8688	8030	0.0007	-	-	-	-
0.8698	8040	0.0006	-	-	-	-
0.8709	8050	0.0007	-	-	-	-
0.8720	8060	0.0006	-	-	-	-
0.8731	8070	0.0007	-	-	-	-
0.8742	8080	0.0007	-	-	-	-
0.8753	8090	0.0006	-	-	-	-
0.8763	8100	0.0007	-	-	-	-
0.8774	8110	0.0006	-	-	-	-
0.8785	8120	0.0007	-	-	-	-
0.8796	8130	0.0006	-	-	-	-
0.8807	8140	0.0006	-	-	-	-
0.8817	8150	0.0007	-	-	-	-
0.8828	8160	0.0006	-	-	-	-
0.8839	8170	0.0007	-	-	-	-
0.8850	8180	0.0006	-	-	-	-
0.8861	8190	0.0007	-	-	-	-
0.8872	8200	0.0006	-	-	-	-
0.8882	8210	0.0007	-	-	-	-
0.8893	8220	0.0006	-	-	-	-
0.8904	8230	0.0007	-	-	-	-
0.8915	8240	0.0006	-	-	-	-
0.8926	8250	0.0007	-	-	-	-
0.8936	8260	0.0007	-	-	-	-
0.8947	8270	0.0007	-	-	-	-
0.8958	8280	0.0007	-	-	-	-
0.8969	8290	0.0007	-	-	-	-
0.8980	8300	0.0007	-	-	-	-
0.8991	8310	0.0006	-	-	-	-
0.9001	8320	0.0007	-	-	-	-
0.9012	8330	0.0006	-	-	-	-
0.9023	8340	0.0007	-	-	-	-
0.9034	8350	0.0006	-	-	-	-
0.9045	8360	0.0007	-	-	-	-
0.9056	8370	0.0007	-	-	-	-
0.9066	8380	0.0007	-	-	-	-
0.9077	8390	0.0007	-	-	-	-
0.9088	8400	0.0006	-	-	-	-
0.9099	8410	0.0006	-	-	-	-
0.9110	8420	0.0007	-	-	-	-
0.9120	8430	0.0006	-	-	-	-
0.9131	8440	0.0007	-	-	-	-
0.9142	8450	0.0006	-	-	-	-
0.9153	8460	0.0007	-	-	-	-
0.9164	8470	0.0006	-	-	-	-
0.9175	8480	0.0006	-	-	-	-
0.9185	8490	0.0006	-	-	-	-
0.9196	8500	0.0007	-	-	-	-
0.9207	8510	0.0006	-	-	-	-
0.9218	8520	0.0007	-	-	-	-
0.9229	8530	0.0007	-	-	-	-
0.9239	8540	0.0006	-	-	-	-
0.9250	8550	0.0007	-	-	-	-
0.9261	8560	0.0006	-	-	-	-
0.9272	8570	0.0007	-	-	-	-
0.9283	8580	0.0006	-	-	-	-
0.9294	8590	0.0006	-	-	-	-
0.9304	8600	0.0006	-	-	-	-
0.9315	8610	0.0007	-	-	-	-
0.9326	8620	0.0007	-	-	-	-
0.9337	8630	0.0007	-	-	-	-
0.9348	8640	0.0006	-	-	-	-
0.9358	8650	0.0006	-	-	-	-
0.9369	8660	0.0006	-	-	-	-
0.9380	8670	0.0007	-	-	-	-
0.9391	8680	0.0007	-	-	-	-
0.9402	8690	0.0007	-	-	-	-
0.9413	8700	0.0007	-	-	-	-
0.9423	8710	0.0006	-	-	-	-
0.9434	8720	0.0006	-	-	-	-
0.9445	8730	0.0007	-	-	-	-
0.9456	8740	0.0006	-	-	-	-
0.9467	8750	0.0006	-	-	-	-
0.9477	8760	0.0006	-	-	-	-
0.9488	8770	0.0006	-	-	-	-
0.9499	8780	0.0006	-	-	-	-
0.9510	8790	0.0006	-	-	-	-
0.9521	8800	0.0006	-	-	-	-
0.9532	8810	0.0007	-	-	-	-
0.9542	8820	0.0006	-	-	-	-
0.9553	8830	0.0006	-	-	-	-
0.9564	8840	0.0006	-	-	-	-
0.9575	8850	0.0006	-	-	-	-
0.9586	8860	0.0007	-	-	-	-
0.9596	8870	0.0007	-	-	-	-
0.9607	8880	0.0007	-	-	-	-
0.9618	8890	0.0007	-	-	-	-
0.9629	8900	0.0007	-	-	-	-
0.9640	8910	0.0007	-	-	-	-
0.9651	8920	0.0007	-	-	-	-
0.9661	8930	0.0007	-	-	-	-
0.9672	8940	0.0007	-	-	-	-
0.9683	8950	0.0006	-	-	-	-
0.9694	8960	0.0007	-	-	-	-
0.9705	8970	0.0007	-	-	-	-
0.9715	8980	0.0006	-	-	-	-
0.9726	8990	0.0007	-	-	-	-
0.9737	9000	0.0007	0.0006	0.4973	0.7955	-
0.9748	9010	0.0006	-	-	-	-
0.9759	9020	0.0006	-	-	-	-
0.9770	9030	0.0006	-	-	-	-
0.9780	9040	0.0007	-	-	-	-
0.9791	9050	0.0007	-	-	-	-
0.9802	9060	0.0007	-	-	-	-
0.9813	9070	0.0007	-	-	-	-
0.9824	9080	0.0007	-	-	-	-
0.9834	9090	0.0006	-	-	-	-
0.9845	9100	0.0007	-	-	-	-
0.9856	9110	0.0007	-	-	-	-
0.9867	9120	0.0007	-	-	-	-
0.9878	9130	0.0007	-	-	-	-
0.9889	9140	0.0006	-	-	-	-
0.9899	9150	0.0007	-	-	-	-
0.9910	9160	0.0007	-	-	-	-
0.9921	9170	0.0006	-	-	-	-
0.9932	9180	0.0007	-	-	-	-
0.9943	9190	0.0007	-	-	-	-
0.9953	9200	0.0007	-	-	-	-
0.9964	9210	0.0007	-	-	-	-
0.9975	9220	0.0007	-	-	-	-
0.9986	9230	0.0007	-	-	-	-
0.9997	9240	0.0007	-	-	-	-
1.0	9243	-	-	0.4962	-	0.7185

Framework Versions

Python: 3.10.12
Sentence Transformers: 3.0.1
Transformers: 4.42.3
PyTorch: 2.1.1+cu121
Accelerate: 0.32.1
Datasets: 2.20.0
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",
}

MSELoss

@inproceedings{reimers-2020-multilingual-sentence-bert,
    title = "Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2020",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/2004.09813",
}

Downloads last month: 0

Safetensors

Model size

118M params

Tensor type

F32

Inference Examples

Sentence Similarity

This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for lemon-mint/mMiniLMv2-L12-H384-Distilled-Iter14-final

Base model

lemon-mint/mMiniLMv2-L12-H384-Distilled-Iter11-final

Finetuned

lemon-mint/mMiniLMv2-L12-H384-Distilled-Iter12-final

Finetuned

(1)

this model

Evaluation results

Pearson Cosine on sts dev
self-reported

0.789
Spearman Cosine on sts dev
self-reported

0.796
Pearson Manhattan on sts dev
self-reported

0.793
Spearman Manhattan on sts dev
self-reported

0.795
Pearson Euclidean on sts dev
self-reported

0.794
Spearman Euclidean on sts dev
self-reported

0.796
Pearson Dot on sts dev
self-reported

0.789
Spearman Dot on sts dev
self-reported

0.796
Pearson Max on sts dev
self-reported

0.794
Spearman Max on sts dev
self-reported

0.796

View on Papers With Code