Hugging Face's logo

rahulseetharaman
/
reranker-ettin-encoder-17m-msmarco-bce-1m

Text Ranking
sentence-transformers
Safetensors
English
modernbert
cross-encoder
reranker
Generated from Trainer
dataset_size:990000
loss:BinaryCrossEntropyLoss
Eval Results
Model card Files Community
reranker-ettin-encoder-17m-msmarco-bce-1m / README.md
rahulseetharaman's picture
rahulseetharaman
Add new CrossEncoder model
34c9fc9 verified
preview code
|
raw
history blame contribute delete
68 kB
 ---
language:
- en
tags:
- sentence-transformers
- cross-encoder
- reranker
- generated_from_trainer
- dataset_size:990000
- loss:BinaryCrossEntropyLoss
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
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: 0.5817
name: Map
- type: mrr@10
value: 0.5753
name: Mrr@10
- type: ndcg@10
value: 0.6427
name: Ndcg@10
- task:
type: cross-encoder-reranking
name: Cross Encoder Reranking
dataset:
name: NanoNFCorpus R100
type: NanoNFCorpus_R100
metrics:
- type: map
value: 0.3167
name: Map
- type: mrr@10
value: 0.4952
name: Mrr@10
- type: ndcg@10
value: 0.334
name: Ndcg@10
- task:
type: cross-encoder-reranking
name: Cross Encoder Reranking
dataset:
name: NanoNQ R100
type: NanoNQ_R100
metrics:
- type: map
value: 0.5585
name: Map
- type: mrr@10
value: 0.5632
name: Mrr@10
- type: ndcg@10
value: 0.6215
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: 0.4856
name: Map
- type: mrr@10
value: 0.5446
name: Mrr@10
- type: ndcg@10
value: 0.5327
name: Ndcg@10
---
# CrossEncoder based on jhu-clsp/ettin-encoder-17m
This is a [Cross Encoder](https://www.sbert.net/docs/cross_encoder/usage/usage.html) model finetuned from [jhu-clsp/ettin-encoder-17m](https://huggingface.co/jhu-clsp/ettin-encoder-17m) on the [msmarco](https://huggingface.co/datasets/sentence-transformers/msmarco) dataset using the [sentence-transformers](https://www.SBERT.net) 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](https://huggingface.co/jhu-clsp/ettin-encoder-17m) <!-- at revision 987607455c61e7a5bbc85f7758e0512ea6d0ae4c -->
- **Maximum Sequence Length:** 7999 tokens
- **Number of Output Labels:** 1 label
- **Training Dataset:**
- [msmarco](https://huggingface.co/datasets/sentence-transformers/msmarco)
- **Language:** en
<!-- - **License:** Unknown -->
### Model Sources
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
- **Documentation:** [Cross Encoder Documentation](https://www.sbert.net/docs/cross_encoder/usage/usage.html)
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
- **Hugging Face:** [Cross Encoders on Hugging Face](https://huggingface.co/models?library=sentence-transformers&other=cross-encoder)
## Usage
### Direct Usage (Sentence Transformers)
First install the Sentence Transformers library:
```bash
pip install -U sentence-transformers
```
Then you can load this model and run inference.
```python
from sentence_transformers import CrossEncoder
# Download from the 🤗 Hub
model = CrossEncoder("rahulseetharaman/reranker-ettin-encoder-17m-msmarco-bce-1m")
# Get scores for pairs of texts
pairs = [
['star voyager cast', 'On August 25, 2012, data from Voyager 1 indicated that it had become the first human-made object to enter interstellar space, traveling further than anyone, or anything, in history. As of 2013, Voyager 1 was moving with a velocity of 17 kilometers per second (11 mi/s) relative to the Sun. Voyager 2 is expected to enter interstellar space by 2016, and its plasma spectrometer should provide the first direct measurements of the density and temperature of the interstellar plasma.'],
['physiologist who conducted the classical conditioning studies with dogs', "Classical Conditioning. The people who fed Pavlov's dogs wore lab coats. Pavlov noticed that the dogs began to drool whenever they saw lab coats, even if there was no food in sight. Pavlov wondered why the dogs salivated at lab coats, and not just at food."],
['is a written check considered a contract', 'If you bought a flat screen TV and are paying it off monthly, thatâ\x80\x99s considered recurring debt because you canâ\x80\x99t easily cancel your payments. If you subscribe to a magazine or have an Internet or phone contract, those obligations are not considered recurring debt because there is no fixed debt amount you are paying down and you can cancel your contract.'],
['definition of an actuator', 'An actuator is a type of motor that is responsible for moving or controlling a mechanism or system. It is operated by a source of energy, typically electric current, hydraulic fluid pressure, or pneumatic pressure, and converts that energy into motion. An actuator is the mechanism by which a control system acts upon an environment. The control system can be simple (a fixed mechanical or electronic system), software-based (e.g. a printer driver, robot control system), a human, or any other input.'],
['what are rheumatoid arthritis symptoms', 'While early RA symptoms can be mimicked by other diseases, the symptoms and signs are very characteristic of rheumatoid disease. The 15 early rheumatoid arthritis symptoms and signs discussed in this article include the following: Fatigue. Joint pain. Joint tenderness. Joint swelling. Joint redness. Joint warmth.'],
]
scores = model.predict(pairs)
print(scores.shape)
# (5,)
# Or rank different texts based on similarity to a single text
ranks = model.rank(
'star voyager cast',
[
'On August 25, 2012, data from Voyager 1 indicated that it had become the first human-made object to enter interstellar space, traveling further than anyone, or anything, in history. As of 2013, Voyager 1 was moving with a velocity of 17 kilometers per second (11 mi/s) relative to the Sun. Voyager 2 is expected to enter interstellar space by 2016, and its plasma spectrometer should provide the first direct measurements of the density and temperature of the interstellar plasma.',
"Classical Conditioning. The people who fed Pavlov's dogs wore lab coats. Pavlov noticed that the dogs began to drool whenever they saw lab coats, even if there was no food in sight. Pavlov wondered why the dogs salivated at lab coats, and not just at food.",
'If you bought a flat screen TV and are paying it off monthly, thatâ\x80\x99s considered recurring debt because you canâ\x80\x99t easily cancel your payments. If you subscribe to a magazine or have an Internet or phone contract, those obligations are not considered recurring debt because there is no fixed debt amount you are paying down and you can cancel your contract.',
'An actuator is a type of motor that is responsible for moving or controlling a mechanism or system. It is operated by a source of energy, typically electric current, hydraulic fluid pressure, or pneumatic pressure, and converts that energy into motion. An actuator is the mechanism by which a control system acts upon an environment. The control system can be simple (a fixed mechanical or electronic system), software-based (e.g. a printer driver, robot control system), a human, or any other input.',
'While early RA symptoms can be mimicked by other diseases, the symptoms and signs are very characteristic of rheumatoid disease. The 15 early rheumatoid arthritis symptoms and signs discussed in this article include the following: Fatigue. Joint pain. Joint tenderness. Joint swelling. Joint redness. Joint warmth.',
]
)
# [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...]
```
<!--
### Direct Usage (Transformers)
<details><summary>Click to see the direct usage in Transformers</summary>
</details>
-->
<!--
### Downstream Usage (Sentence Transformers)
You can finetune this model on your own dataset.
<details><summary>Click to expand</summary>
</details>
-->
<!--
### Out-of-Scope Use
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
-->
## Evaluation
### Metrics
#### Cross Encoder Reranking
* Datasets: `NanoMSMARCO_R100`, `NanoNFCorpus_R100` and `NanoNQ_R100`
* Evaluated with [<code>CrossEncoderRerankingEvaluator</code>](https://sbert.net/docs/package_reference/cross_encoder/evaluation.html#sentence_transformers.cross_encoder.evaluation.CrossEncoderRerankingEvaluator) with these parameters:
```json
{
"at_k": 10,
"always_rerank_positives": true
}
```
| Metric | NanoMSMARCO_R100 | NanoNFCorpus_R100 | NanoNQ_R100 |
|:------------|:---------------------|:---------------------|:---------------------|
| map | 0.5817 (+0.0921) | 0.3167 (+0.0557) | 0.5585 (+0.1388) |
| mrr@10 | 0.5753 (+0.0978) | 0.4952 (-0.0046) | 0.5632 (+0.1366) |
| **ndcg@10** | **0.6427 (+0.1023)** | **0.3340 (+0.0089)** | **0.6215 (+0.1208)** |
#### Cross Encoder Nano BEIR
* Dataset: `NanoBEIR_R100_mean`
* Evaluated with [<code>CrossEncoderNanoBEIREvaluator</code>](https://sbert.net/docs/package_reference/cross_encoder/evaluation.html#sentence_transformers.cross_encoder.evaluation.CrossEncoderNanoBEIREvaluator) with these parameters:
```json
{
"dataset_names": [
"msmarco",
"nfcorpus",
"nq"
],
"rerank_k": 100,
"at_k": 10,
"always_rerank_positives": true
}
```
| Metric | Value |
|:------------|:---------------------|
| map | 0.4856 (+0.0956) |
| mrr@10 | 0.5446 (+0.0766) |
| **ndcg@10** | **0.5327 (+0.0773)** |
<!--
## Bias, Risks and Limitations
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
-->
<!--
### Recommendations
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
-->
## Training Details
### Training Dataset
#### msmarco
* Dataset: [msmarco](https://huggingface.co/datasets/sentence-transformers/msmarco) at [9e329ed](https://huggingface.co/datasets/sentence-transformers/msmarco/tree/9e329ed2e649c9d37b0d91dd6b764ff6fe671d83)
* Size: 990,000 training samples
* Columns: <code>query</code>, <code>passage</code>, and <code>score</code>
* Approximate statistics based on the first 1000 samples:
| | query | passage | score |
|:--------|:------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------|:--------------------------------------------------------------|
| type | string | string | float |
| details | <ul><li>min: 10 characters</li><li>mean: 34.06 characters</li><li>max: 103 characters</li></ul> | <ul><li>min: 55 characters</li><li>mean: 341.02 characters</li><li>max: 943 characters</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.5</li><li>max: 1.0</li></ul> |
* Samples:
| query | passage | score |
|:----------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------|
| <code>can a urinalysis detect kidney disease</code> | <code>A urinalysis is a simple, inexpensive test that can help to detect problems in many parts of the body, including the kidneys, urinary tract, heart, and liver. A urinalysis can include a visual examination of a urine sample, microscopic examination, and a dipstick test.</code> | <code>1.0</code> |
| <code>what is the hamsa hand</code> | <code>Answer by Mikereptile. Confidence votes 60. It takes about 6-8 weeks to heal, depending on the type of injury sustained. (Keep the finger as still as you can !!!!). When broken place the hand in ice cold water for about 5 min.s then take it and wrap the whole hand in a soft wrap (anything that is a soft colth) .Take the wraped hand and hold it above or upright to the head.hen broken place the hand in ice cold water for about 5 min.s then take it and wrap the whole hand in a soft wrap (anything that is a soft colth) . Take the wraped hand and hold it above or upright to the head.</code> | <code>0.0</code> |
| <code>was white tiger in the us zoo killed?</code> | <code>Cubby is a male American black bear born at the Chahinkapa Zoo in North Dakota. He was transferred to the Hogle Zoo (Salt Lake City, Utah) in 2003, and arrived at the Oregon Zoo in May 2010.</code> | <code>0.0</code> |
* Loss: [<code>BinaryCrossEntropyLoss</code>](https://sbert.net/docs/package_reference/cross_encoder/losses.html#binarycrossentropyloss) with these parameters:
```json
{
"activation_fn": "torch.nn.modules.linear.Identity",
"pos_weight": null
}
```
### Evaluation Dataset
#### msmarco
* Dataset: [msmarco](https://huggingface.co/datasets/sentence-transformers/msmarco) at [9e329ed](https://huggingface.co/datasets/sentence-transformers/msmarco/tree/9e329ed2e649c9d37b0d91dd6b764ff6fe671d83)
* Size: 10,000 evaluation samples
* Columns: <code>query</code>, <code>passage</code>, and <code>score</code>
* Approximate statistics based on the first 1000 samples:
| | query | passage | score |
|:--------|:------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------|:---------------------------------------------------------------|
| type | string | string | float |
| details | <ul><li>min: 10 characters</li><li>mean: 33.97 characters</li><li>max: 121 characters</li></ul> | <ul><li>min: 70 characters</li><li>mean: 345.9 characters</li><li>max: 946 characters</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.48</li><li>max: 1.0</li></ul> |
* Samples:
| query | passage | score |
|:-------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------|
| <code>star voyager cast</code> | <code>On August 25, 2012, data from Voyager 1 indicated that it had become the first human-made object to enter interstellar space, traveling further than anyone, or anything, in history. As of 2013, Voyager 1 was moving with a velocity of 17 kilometers per second (11 mi/s) relative to the Sun. Voyager 2 is expected to enter interstellar space by 2016, and its plasma spectrometer should provide the first direct measurements of the density and temperature of the interstellar plasma.</code> | <code>0.0</code> |
| <code>physiologist who conducted the classical conditioning studies with dogs</code> | <code>Classical Conditioning. The people who fed Pavlov's dogs wore lab coats. Pavlov noticed that the dogs began to drool whenever they saw lab coats, even if there was no food in sight. Pavlov wondered why the dogs salivated at lab coats, and not just at food.</code> | <code>0.0</code> |
| <code>is a written check considered a contract</code> | <code>If you bought a flat screen TV and are paying it off monthly, that’s considered recurring debt because you can’t easily cancel your payments. If you subscribe to a magazine or have an Internet or phone contract, those obligations are not considered recurring debt because there is no fixed debt amount you are paying down and you can cancel your contract.</code> | <code>0.0</code> |
* Loss: [<code>BinaryCrossEntropyLoss</code>](https://sbert.net/docs/package_reference/cross_encoder/losses.html#binarycrossentropyloss) with these parameters:
```json
{
"activation_fn": "torch.nn.modules.linear.Identity",
"pos_weight": null
}
```
### Training Hyperparameters
#### Non-Default Hyperparameters
- `eval_strategy`: steps
- `per_device_train_batch_size`: 16
- `per_device_eval_batch_size`: 16
- `learning_rate`: 2e-05
- `num_train_epochs`: 4
- `warmup_ratio`: 0.1
- `seed`: 12
- `bf16`: True
- `dataloader_num_workers`: 4
- `load_best_model_at_end`: True
#### All Hyperparameters
<details><summary>Click to expand</summary>
- `overwrite_output_dir`: False
- `do_predict`: False
- `eval_strategy`: steps
- `prediction_loss_only`: True
- `per_device_train_batch_size`: 16
- `per_device_eval_batch_size`: 16
- `per_gpu_train_batch_size`: None
- `per_gpu_eval_batch_size`: None
- `gradient_accumulation_steps`: 1
- `eval_accumulation_steps`: None
- `torch_empty_cache_steps`: None
- `learning_rate`: 2e-05
- `weight_decay`: 0.0
- `adam_beta1`: 0.9
- `adam_beta2`: 0.999
- `adam_epsilon`: 1e-08
- `max_grad_norm`: 1.0
- `num_train_epochs`: 4
- `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
- `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`: 4
- `dataloader_prefetch_factor`: None
- `past_index`: -1
- `disable_tqdm`: False
- `remove_unused_columns`: True
- `label_names`: None
- `load_best_model_at_end`: True
- `ignore_data_skip`: False
- `fsdp`: []
- `fsdp_min_num_params`: 0
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
- `fsdp_transformer_layer_cls_to_wrap`: None
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
- `deepspeed`: None
- `label_smoothing_factor`: 0.0
- `optim`: adamw_torch
- `optim_args`: None
- `adafactor`: False
- `group_by_length`: False
- `length_column_name`: length
- `ddp_find_unused_parameters`: None
- `ddp_bucket_cap_mb`: None
- `ddp_broadcast_buffers`: False
- `dataloader_pin_memory`: True
- `dataloader_persistent_workers`: False
- `skip_memory_metrics`: True
- `use_legacy_prediction_loop`: False
- `push_to_hub`: False
- `resume_from_checkpoint`: None
- `hub_model_id`: None
- `hub_strategy`: every_save
- `hub_private_repo`: None
- `hub_always_push`: False
- `hub_revision`: None
- `gradient_checkpointing`: False
- `gradient_checkpointing_kwargs`: None
- `include_inputs_for_metrics`: False
- `include_for_metrics`: []
- `eval_do_concat_batches`: True
- `fp16_backend`: auto
- `push_to_hub_model_id`: None
- `push_to_hub_organization`: None
- `mp_parameters`:
- `auto_find_batch_size`: False
- `full_determinism`: False
- `torchdynamo`: None
- `ray_scope`: last
- `ddp_timeout`: 1800
- `torch_compile`: False
- `torch_compile_backend`: None
- `torch_compile_mode`: None
- `include_tokens_per_second`: False
- `include_num_input_tokens_seen`: False
- `neftune_noise_alpha`: None
- `optim_target_modules`: None
- `batch_eval_metrics`: False
- `eval_on_start`: False
- `use_liger_kernel`: False
- `liger_kernel_config`: None
- `eval_use_gather_object`: False
- `average_tokens_across_devices`: False
- `prompts`: None
- `batch_sampler`: batch_sampler
- `multi_dataset_batch_sampler`: proportional
- `router_mapping`: {}
- `learning_rate_mapping`: {}
</details>
### Training Logs
<details><summary>Click to expand</summary>
| 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 | - | - | 0.0063 (-0.5341) | 0.1891 (-0.1359) | 0.0144 (-0.4863) | 0.0699 (-0.3854) |
| 0.0000 | 1 | 1.2012 | - | - | - | - | - |
| 0.0162 | 1000 | 0.9995 | 0.7650 | 0.0209 (-0.5195) | 0.1857 (-0.1393) | 0.0357 (-0.4649) | 0.0808 (-0.3746) |
| 0.0323 | 2000 | 0.7166 | 0.6700 | 0.0632 (-0.4772) | 0.1887 (-0.1363) | 0.0668 (-0.4338) | 0.1063 (-0.3491) |
| 0.0485 | 3000 | 0.6672 | 0.6422 | 0.1130 (-0.4275) | 0.2264 (-0.0986) | 0.0824 (-0.4182) | 0.1406 (-0.3148) |
| 0.0646 | 4000 | 0.6315 | 0.5913 | 0.2003 (-0.3401) | 0.2182 (-0.1069) | 0.1436 (-0.3570) | 0.1874 (-0.2680) |
| 0.0808 | 5000 | 0.5006 | 0.4275 | 0.4365 (-0.1040) | 0.3056 (-0.0194) | 0.3410 (-0.1597) | 0.3610 (-0.0944) |
| 0.0970 | 6000 | 0.4132 | 0.3963 | 0.4640 (-0.0764) | 0.2955 (-0.0295) | 0.4103 (-0.0904) | 0.3899 (-0.0654) |
| 0.1131 | 7000 | 0.3903 | 0.3809 | 0.4609 (-0.0795) | 0.3152 (-0.0098) | 0.4142 (-0.0865) | 0.3968 (-0.0586) |
| 0.1293 | 8000 | 0.3775 | 0.3585 | 0.5074 (-0.0330) | 0.3235 (-0.0015) | 0.4683 (-0.0323) | 0.4331 (-0.0223) |
| 0.1455 | 9000 | 0.3585 | 0.3420 | 0.5153 (-0.0251) | 0.3215 (-0.0035) | 0.4795 (-0.0212) | 0.4388 (-0.0166) |
| 0.1616 | 10000 | 0.349 | 0.3378 | 0.4864 (-0.0540) | 0.3254 (+0.0003) | 0.4724 (-0.0283) | 0.4281 (-0.0273) |
| 0.1778 | 11000 | 0.3372 | 0.3344 | 0.5150 (-0.0254) | 0.3350 (+0.0099) | 0.4981 (-0.0026) | 0.4494 (-0.0060) |
| 0.1939 | 12000 | 0.3412 | 0.3288 | 0.5079 (-0.0325) | 0.3427 (+0.0177) | 0.5165 (+0.0158) | 0.4557 (+0.0003) |
| 0.2101 | 13000 | 0.3251 | 0.3159 | 0.5217 (-0.0188) | 0.3469 (+0.0218) | 0.4914 (-0.0093) | 0.4533 (-0.0021) |
| 0.2263 | 14000 | 0.3215 | 0.3537 | 0.5656 (+0.0252) | 0.3489 (+0.0239) | 0.4858 (-0.0149) | 0.4668 (+0.0114) |
| 0.2424 | 15000 | 0.3206 | 0.3624 | 0.5834 (+0.0430) | 0.3456 (+0.0206) | 0.5339 (+0.0333) | 0.4877 (+0.0323) |
| 0.2586 | 16000 | 0.3111 | 0.2994 | 0.5477 (+0.0073) | 0.3369 (+0.0119) | 0.5215 (+0.0209) | 0.4687 (+0.0133) |
| 0.2747 | 17000 | 0.2941 | 0.2937 | 0.5408 (+0.0004) | 0.3294 (+0.0044) | 0.5369 (+0.0363) | 0.4691 (+0.0137) |
| 0.2909 | 18000 | 0.3002 | 0.3144 | 0.5402 (-0.0003) | 0.3493 (+0.0242) | 0.5800 (+0.0794) | 0.4898 (+0.0344) |
| 0.3071 | 19000 | 0.2965 | 0.2866 | 0.5768 (+0.0364) | 0.3442 (+0.0191) | 0.5298 (+0.0292) | 0.4836 (+0.0282) |
| 0.3232 | 20000 | 0.2943 | 0.3069 | 0.5180 (-0.0224) | 0.3354 (+0.0104) | 0.5441 (+0.0434) | 0.4658 (+0.0105) |
| 0.3394 | 21000 | 0.29 | 0.2872 | 0.5530 (+0.0126) | 0.3484 (+0.0233) | 0.5690 (+0.0684) | 0.4901 (+0.0348) |
| 0.3556 | 22000 | 0.2793 | 0.2769 | 0.5690 (+0.0285) | 0.3357 (+0.0107) | 0.5312 (+0.0305) | 0.4786 (+0.0232) |
| 0.3717 | 23000 | 0.2954 | 0.2957 | 0.5798 (+0.0394) | 0.3536 (+0.0286) | 0.5581 (+0.0574) | 0.4972 (+0.0418) |
| 0.3879 | 24000 | 0.2841 | 0.3262 | 0.5342 (-0.0062) | 0.3391 (+0.0141) | 0.5265 (+0.0259) | 0.4666 (+0.0112) |
| 0.4040 | 25000 | 0.2755 | 0.2752 | 0.5600 (+0.0196) | 0.3442 (+0.0192) | 0.5782 (+0.0776) | 0.4942 (+0.0388) |
| 0.4202 | 26000 | 0.281 | 0.2740 | 0.5068 (-0.0336) | 0.3384 (+0.0133) | 0.5443 (+0.0437) | 0.4632 (+0.0078) |
| 0.4364 | 27000 | 0.2814 | 0.2854 | 0.5585 (+0.0180) | 0.3446 (+0.0196) | 0.5681 (+0.0674) | 0.4904 (+0.0350) |
| 0.4525 | 28000 | 0.2742 | 0.2584 | 0.5493 (+0.0089) | 0.3570 (+0.0319) | 0.5762 (+0.0755) | 0.4942 (+0.0388) |
| 0.4687 | 29000 | 0.2675 | 0.2589 | 0.5494 (+0.0089) | 0.3492 (+0.0242) | 0.5686 (+0.0680) | 0.4891 (+0.0337) |
| 0.4848 | 30000 | 0.2619 | 0.2538 | 0.5808 (+0.0404) | 0.3527 (+0.0276) | 0.5401 (+0.0394) | 0.4912 (+0.0358) |
| 0.5010 | 31000 | 0.2713 | 0.2515 | 0.5652 (+0.0248) | 0.3298 (+0.0048) | 0.5801 (+0.0795) | 0.4917 (+0.0363) |
| 0.5172 | 32000 | 0.2574 | 0.3014 | 0.5480 (+0.0076) | 0.3563 (+0.0312) | 0.5725 (+0.0718) | 0.4922 (+0.0369) |
| 0.5333 | 33000 | 0.2567 | 0.2510 | 0.5727 (+0.0323) | 0.3499 (+0.0249) | 0.5636 (+0.0629) | 0.4954 (+0.0400) |
| 0.5495 | 34000 | 0.2572 | 0.2535 | 0.5568 (+0.0164) | 0.3467 (+0.0217) | 0.5839 (+0.0832) | 0.4958 (+0.0404) |
| 0.5657 | 35000 | 0.2582 | 0.2554 | 0.5660 (+0.0255) | 0.3351 (+0.0101) | 0.5824 (+0.0818) | 0.4945 (+0.0391) |
| 0.5818 | 36000 | 0.2499 | 0.2409 | 0.5643 (+0.0239) | 0.3227 (-0.0023) | 0.5719 (+0.0712) | 0.4863 (+0.0309) |
| 0.5980 | 37000 | 0.2479 | 0.2562 | 0.5324 (-0.0081) | 0.3309 (+0.0058) | 0.6002 (+0.0995) | 0.4878 (+0.0324) |
| 0.6141 | 38000 | 0.2438 | 0.2474 | 0.5324 (-0.0080) | 0.3232 (-0.0018) | 0.5799 (+0.0793) | 0.4785 (+0.0232) |
| 0.6303 | 39000 | 0.2472 | 0.2624 | 0.5241 (-0.0163) | 0.3193 (-0.0058) | 0.5838 (+0.0832) | 0.4757 (+0.0204) |
| 0.6465 | 40000 | 0.248 | 0.2449 | 0.5447 (+0.0042) | 0.3325 (+0.0074) | 0.6142 (+0.1136) | 0.4971 (+0.0418) |
| 0.6626 | 41000 | 0.2417 | 0.2689 | 0.5267 (-0.0138) | 0.3330 (+0.0080) | 0.5971 (+0.0965) | 0.4856 (+0.0302) |
| 0.6788 | 42000 | 0.2415 | 0.2299 | 0.5760 (+0.0356) | 0.3361 (+0.0111) | 0.6060 (+0.1053) | 0.5060 (+0.0507) |
| 0.6949 | 43000 | 0.2385 | 0.2430 | 0.5601 (+0.0197) | 0.3342 (+0.0092) | 0.5737 (+0.0731) | 0.4894 (+0.0340) |
| 0.7111 | 44000 | 0.2373 | 0.2401 | 0.5565 (+0.0161) | 0.3133 (-0.0117) | 0.5520 (+0.0513) | 0.4739 (+0.0186) |
| 0.7273 | 45000 | 0.2372 | 0.2372 | 0.5837 (+0.0432) | 0.3290 (+0.0039) | 0.5807 (+0.0801) | 0.4978 (+0.0424) |
| 0.7434 | 46000 | 0.2398 | 0.2250 | 0.5616 (+0.0212) | 0.3155 (-0.0095) | 0.5714 (+0.0707) | 0.4829 (+0.0275) |
| 0.7596 | 47000 | 0.2382 | 0.2331 | 0.5780 (+0.0376) | 0.3371 (+0.0121) | 0.5730 (+0.0723) | 0.4961 (+0.0407) |
| 0.7758 | 48000 | 0.2381 | 0.2221 | 0.5442 (+0.0038) | 0.3196 (-0.0055) | 0.5807 (+0.0801) | 0.4815 (+0.0261) |
| 0.7919 | 49000 | 0.2293 | 0.2382 | 0.5726 (+0.0322) | 0.3517 (+0.0266) | 0.5834 (+0.0828) | 0.5026 (+0.0472) |
| 0.8081 | 50000 | 0.239 | 0.2202 | 0.5722 (+0.0318) | 0.3275 (+0.0024) | 0.5660 (+0.0654) | 0.4886 (+0.0332) |
| 0.8242 | 51000 | 0.2425 | 0.2179 | 0.5374 (-0.0031) | 0.3320 (+0.0070) | 0.5491 (+0.0484) | 0.4728 (+0.0174) |
| 0.8404 | 52000 | 0.2322 | 0.2232 | 0.5853 (+0.0448) | 0.3212 (-0.0038) | 0.5989 (+0.0982) | 0.5018 (+0.0464) |
| 0.8566 | 53000 | 0.2334 | 0.2197 | 0.5998 (+0.0593) | 0.3418 (+0.0168) | 0.5764 (+0.0758) | 0.5060 (+0.0506) |
| 0.8727 | 54000 | 0.2311 | 0.2162 | 0.5865 (+0.0461) | 0.3334 (+0.0084) | 0.6019 (+0.1012) | 0.5073 (+0.0519) |
| 0.8889 | 55000 | 0.2335 | 0.2430 | 0.5883 (+0.0478) | 0.3460 (+0.0210) | 0.5884 (+0.0878) | 0.5076 (+0.0522) |
| 0.9051 | 56000 | 0.2363 | 0.2256 | 0.5912 (+0.0508) | 0.3414 (+0.0163) | 0.6453 (+0.1446) | 0.5260 (+0.0706) |
| 0.9212 | 57000 | 0.2282 | 0.2139 | 0.6185 (+0.0780) | 0.3479 (+0.0228) | 0.6282 (+0.1276) | 0.5315 (+0.0762) |
| 0.9374 | 58000 | 0.2255 | 0.2128 | 0.5609 (+0.0204) | 0.3350 (+0.0100) | 0.6497 (+0.1490) | 0.5152 (+0.0598) |
| 0.9535 | 59000 | 0.2187 | 0.2262 | 0.6041 (+0.0637) | 0.3355 (+0.0104) | 0.5946 (+0.0940) | 0.5114 (+0.0560) |
| 0.9697 | 60000 | 0.2275 | 0.2034 | 0.6085 (+0.0681) | 0.3471 (+0.0220) | 0.5953 (+0.0946) | 0.5169 (+0.0616) |
| 0.9859 | 61000 | 0.2214 | 0.2146 | 0.5883 (+0.0479) | 0.3304 (+0.0053) | 0.6115 (+0.1109) | 0.5101 (+0.0547) |
| 1.0020 | 62000 | 0.2186 | 0.2428 | 0.5690 (+0.0285) | 0.3374 (+0.0123) | 0.6002 (+0.0996) | 0.5022 (+0.0468) |
| 1.0182 | 63000 | 0.1915 | 0.2645 | 0.5836 (+0.0432) | 0.3490 (+0.0239) | 0.6123 (+0.1116) | 0.5150 (+0.0596) |
| 1.0343 | 64000 | 0.1927 | 0.2274 | 0.5768 (+0.0364) | 0.3428 (+0.0178) | 0.6025 (+0.1018) | 0.5074 (+0.0520) |
| 1.0505 | 65000 | 0.196 | 0.2261 | 0.5649 (+0.0245) | 0.3589 (+0.0339) | 0.5758 (+0.0751) | 0.4999 (+0.0445) |
| 1.0667 | 66000 | 0.1863 | 0.2654 | 0.5368 (-0.0036) | 0.3309 (+0.0058) | 0.5418 (+0.0411) | 0.4698 (+0.0144) |
| 1.0828 | 67000 | 0.183 | 0.2627 | 0.5583 (+0.0179) | 0.3401 (+0.0151) | 0.5778 (+0.0772) | 0.4921 (+0.0367) |
| 1.0990 | 68000 | 0.1935 | 0.2293 | 0.5624 (+0.0220) | 0.3434 (+0.0184) | 0.6066 (+0.1059) | 0.5041 (+0.0487) |
| 1.1152 | 69000 | 0.1803 | 0.2406 | 0.5785 (+0.0381) | 0.3147 (-0.0103) | 0.5747 (+0.0740) | 0.4893 (+0.0339) |
| 1.1313 | 70000 | 0.194 | 0.2325 | 0.5985 (+0.0581) | 0.3146 (-0.0105) | 0.5678 (+0.0671) | 0.4936 (+0.0382) |
| 1.1475 | 71000 | 0.188 | 0.2536 | 0.5940 (+0.0536) | 0.3316 (+0.0065) | 0.6098 (+0.1091) | 0.5118 (+0.0564) |
| 1.1636 | 72000 | 0.1912 | 0.2714 | 0.5749 (+0.0345) | 0.3357 (+0.0106) | 0.6128 (+0.1121) | 0.5078 (+0.0524) |
| 1.1798 | 73000 | 0.1917 | 0.3131 | 0.5765 (+0.0361) | 0.3401 (+0.0150) | 0.6241 (+0.1235) | 0.5136 (+0.0582) |
| 1.1960 | 74000 | 0.1898 | 0.2505 | 0.5942 (+0.0538) | 0.3556 (+0.0305) | 0.5866 (+0.0860) | 0.5121 (+0.0568) |
| 1.2121 | 75000 | 0.1892 | 0.2275 | 0.5775 (+0.0371) | 0.3611 (+0.0361) | 0.5633 (+0.0626) | 0.5006 (+0.0453) |
| 1.2283 | 76000 | 0.1907 | 0.2238 | 0.5260 (-0.0145) | 0.3336 (+0.0085) | 0.5666 (+0.0660) | 0.4754 (+0.0200) |
| 1.2444 | 77000 | 0.1866 | 0.2380 | 0.4978 (-0.0426) | 0.3180 (-0.0070) | 0.5704 (+0.0697) | 0.4621 (+0.0067) |
| 1.2606 | 78000 | 0.1897 | 0.2428 | 0.5492 (+0.0088) | 0.3408 (+0.0157) | 0.5884 (+0.0878) | 0.4928 (+0.0374) |
| 1.2768 | 79000 | 0.1875 | 0.2627 | 0.5643 (+0.0239) | 0.3465 (+0.0215) | 0.6214 (+0.1207) | 0.5107 (+0.0554) |
| 1.2929 | 80000 | 0.1915 | 0.2186 | 0.5827 (+0.0422) | 0.3416 (+0.0166) | 0.6193 (+0.1186) | 0.5145 (+0.0591) |
| 1.3091 | 81000 | 0.1932 | 0.2225 | 0.5645 (+0.0241) | 0.3313 (+0.0062) | 0.6047 (+0.1040) | 0.5002 (+0.0448) |
| 1.3253 | 82000 | 0.1897 | 0.2206 | 0.5730 (+0.0325) | 0.3219 (-0.0031) | 0.6044 (+0.1038) | 0.4998 (+0.0444) |
| 1.3414 | 83000 | 0.1889 | 0.2299 | 0.5975 (+0.0571) | 0.3430 (+0.0179) | 0.5976 (+0.0970) | 0.5127 (+0.0573) |
| 1.3576 | 84000 | 0.194 | 0.2273 | 0.5971 (+0.0566) | 0.3427 (+0.0176) | 0.5943 (+0.0937) | 0.5114 (+0.0560) |
| 1.3737 | 85000 | 0.1881 | 0.2402 | 0.5706 (+0.0302) | 0.3492 (+0.0241) | 0.6197 (+0.1190) | 0.5132 (+0.0578) |
| 1.3899 | 86000 | 0.1855 | 0.2405 | 0.5710 (+0.0306) | 0.3261 (+0.0010) | 0.6067 (+0.1060) | 0.5012 (+0.0459) |
| 1.4061 | 87000 | 0.19 | 0.2249 | 0.5385 (-0.0019) | 0.3298 (+0.0047) | 0.5906 (+0.0899) | 0.4863 (+0.0309) |
| 1.4222 | 88000 | 0.1853 | 0.2323 | 0.5497 (+0.0092) | 0.3367 (+0.0117) | 0.5880 (+0.0874) | 0.4915 (+0.0361) |
| 1.4384 | 89000 | 0.1808 | 0.2654 | 0.5643 (+0.0239) | 0.3418 (+0.0168) | 0.5835 (+0.0829) | 0.4965 (+0.0412) |
| 1.4545 | 90000 | 0.182 | 0.2609 | 0.5526 (+0.0122) | 0.3624 (+0.0374) | 0.5771 (+0.0765) | 0.4974 (+0.0420) |
| 1.4707 | 91000 | 0.1931 | 0.2237 | 0.5589 (+0.0185) | 0.3429 (+0.0178) | 0.5927 (+0.0920) | 0.4982 (+0.0428) |
| 1.4869 | 92000 | 0.1925 | 0.2430 | 0.5416 (+0.0012) | 0.3413 (+0.0163) | 0.6082 (+0.1076) | 0.4971 (+0.0417) |
| 1.5030 | 93000 | 0.1861 | 0.2241 | 0.5313 (-0.0091) | 0.3340 (+0.0090) | 0.6134 (+0.1127) | 0.4929 (+0.0375) |
| 1.5192 | 94000 | 0.189 | 0.2293 | 0.5509 (+0.0104) | 0.3488 (+0.0237) | 0.6448 (+0.1441) | 0.5148 (+0.0594) |
| 1.5354 | 95000 | 0.1816 | 0.2433 | 0.5640 (+0.0235) | 0.3529 (+0.0279) | 0.6121 (+0.1114) | 0.5096 (+0.0543) |
| 1.5515 | 96000 | 0.1901 | 0.2338 | 0.5411 (+0.0007) | 0.3238 (-0.0013) | 0.5729 (+0.0722) | 0.4793 (+0.0239) |
| 1.5677 | 97000 | 0.1921 | 0.2261 | 0.5831 (+0.0427) | 0.3173 (-0.0077) | 0.5830 (+0.0824) | 0.4945 (+0.0391) |
| 1.5838 | 98000 | 0.1854 | 0.2105 | 0.6028 (+0.0624) | 0.3176 (-0.0075) | 0.5702 (+0.0695) | 0.4969 (+0.0415) |
| 1.6 | 99000 | 0.1788 | 0.2330 | 0.5942 (+0.0537) | 0.3395 (+0.0144) | 0.5930 (+0.0923) | 0.5089 (+0.0535) |
| 1.6162 | 100000 | 0.1857 | 0.2230 | 0.5520 (+0.0116) | 0.3475 (+0.0225) | 0.5789 (+0.0782) | 0.4928 (+0.0374) |
| 1.6323 | 101000 | 0.1862 | 0.2140 | 0.5523 (+0.0118) | 0.3507 (+0.0256) | 0.5693 (+0.0686) | 0.4907 (+0.0354) |
| 1.6485 | 102000 | 0.1875 | 0.2310 | 0.5887 (+0.0483) | 0.3360 (+0.0110) | 0.6228 (+0.1221) | 0.5158 (+0.0605) |
| 1.6646 | 103000 | 0.1829 | 0.2354 | 0.6083 (+0.0678) | 0.3242 (-0.0008) | 0.5638 (+0.0632) | 0.4988 (+0.0434) |
| 1.6808 | 104000 | 0.1833 | 0.2270 | 0.6003 (+0.0599) | 0.3294 (+0.0043) | 0.5684 (+0.0677) | 0.4994 (+0.0440) |
| 1.6970 | 105000 | 0.1835 | 0.2339 | 0.5815 (+0.0411) | 0.3336 (+0.0086) | 0.5867 (+0.0861) | 0.5006 (+0.0452) |
| 1.7131 | 106000 | 0.1866 | 0.2264 | 0.6492 (+0.1088) | 0.3375 (+0.0125) | 0.5975 (+0.0969) | 0.5281 (+0.0727) |
| 1.7293 | 107000 | 0.184 | 0.2233 | 0.6022 (+0.0618) | 0.3240 (-0.0010) | 0.5915 (+0.0909) | 0.5059 (+0.0505) |
| 1.7455 | 108000 | 0.1777 | 0.2284 | 0.5873 (+0.0468) | 0.3303 (+0.0052) | 0.5723 (+0.0717) | 0.4966 (+0.0412) |
| 1.7616 | 109000 | 0.1853 | 0.2155 | 0.6158 (+0.0754) | 0.3256 (+0.0006) | 0.6262 (+0.1255) | 0.5225 (+0.0672) |
| 1.7778 | 110000 | 0.1825 | 0.2223 | 0.5893 (+0.0489) | 0.3247 (-0.0003) | 0.6125 (+0.1119) | 0.5088 (+0.0535) |
| 1.7939 | 111000 | 0.1807 | 0.2361 | 0.6071 (+0.0667) | 0.3243 (-0.0007) | 0.5889 (+0.0883) | 0.5068 (+0.0514) |
| 1.8101 | 112000 | 0.1771 | 0.2227 | 0.5861 (+0.0457) | 0.3113 (-0.0137) | 0.5967 (+0.0960) | 0.4980 (+0.0426) |
| 1.8263 | 113000 | 0.1805 | 0.2499 | 0.5885 (+0.0480) | 0.3377 (+0.0126) | 0.5991 (+0.0985) | 0.5084 (+0.0531) |
| 1.8424 | 114000 | 0.1805 | 0.2228 | 0.5795 (+0.0391) | 0.3346 (+0.0095) | 0.5950 (+0.0943) | 0.5030 (+0.0477) |
| 1.8586 | 115000 | 0.1758 | 0.2367 | 0.6095 (+0.0690) | 0.3278 (+0.0028) | 0.6161 (+0.1155) | 0.5178 (+0.0624) |
| **1.8747** | **116000** | **0.1822** | **0.2063** | **0.6427 (+0.1023)** | **0.3340 (+0.0089)** | **0.6215 (+0.1208)** | **0.5327 (+0.0773)** |
| 1.8909 | 117000 | 0.1729 | 0.2290 | 0.6042 (+0.0638) | 0.3210 (-0.0041) | 0.6162 (+0.1156) | 0.5138 (+0.0584) |
| 1.9071 | 118000 | 0.1776 | 0.2273 | 0.6076 (+0.0672) | 0.3143 (-0.0108) | 0.5745 (+0.0739) | 0.4988 (+0.0434) |
| 1.9232 | 119000 | 0.1948 | 0.2064 | 0.6132 (+0.0727) | 0.3107 (-0.0143) | 0.6221 (+0.1214) | 0.5153 (+0.0599) |
| 1.9394 | 120000 | 0.1794 | 0.2492 | 0.6051 (+0.0646) | 0.3194 (-0.0057) | 0.6195 (+0.1189) | 0.5147 (+0.0593) |
| 1.9556 | 121000 | 0.1856 | 0.2207 | 0.6279 (+0.0875) | 0.3173 (-0.0077) | 0.6120 (+0.1113) | 0.5191 (+0.0637) |
| 1.9717 | 122000 | 0.1824 | 0.2219 | 0.6085 (+0.0680) | 0.3222 (-0.0029) | 0.6116 (+0.1110) | 0.5141 (+0.0587) |
| 1.9879 | 123000 | 0.1862 | 0.2265 | 0.6011 (+0.0606) | 0.3196 (-0.0054) | 0.6012 (+0.1005) | 0.5073 (+0.0519) |
| 2.0040 | 124000 | 0.1665 | 0.2642 | 0.6196 (+0.0792) | 0.3263 (+0.0012) | 0.5959 (+0.0952) | 0.5139 (+0.0586) |
| 2.0202 | 125000 | 0.1217 | 0.2795 | 0.5885 (+0.0481) | 0.3190 (-0.0061) | 0.6079 (+0.1073) | 0.5051 (+0.0498) |
| 2.0364 | 126000 | 0.1255 | 0.2832 | 0.5844 (+0.0440) | 0.3073 (-0.0178) | 0.6131 (+0.1125) | 0.5016 (+0.0462) |
| 2.0525 | 127000 | 0.1369 | 0.2737 | 0.5447 (+0.0043) | 0.3070 (-0.0181) | 0.6152 (+0.1146) | 0.4890 (+0.0336) |
| 2.0687 | 128000 | 0.1385 | 0.2814 | 0.5753 (+0.0349) | 0.3213 (-0.0037) | 0.6019 (+0.1013) | 0.4995 (+0.0441) |
| 2.0848 | 129000 | 0.1321 | 0.2771 | 0.5796 (+0.0391) | 0.3065 (-0.0185) | 0.6127 (+0.1121) | 0.4996 (+0.0442) |
| 2.1010 | 130000 | 0.1355 | 0.2672 | 0.5828 (+0.0424) | 0.3000 (-0.0251) | 0.6200 (+0.1193) | 0.5009 (+0.0455) |
| 2.1172 | 131000 | 0.1409 | 0.2741 | 0.5764 (+0.0359) | 0.3017 (-0.0234) | 0.5737 (+0.0731) | 0.4839 (+0.0285) |
| 2.1333 | 132000 | 0.1353 | 0.2903 | 0.5817 (+0.0413) | 0.2942 (-0.0308) | 0.5888 (+0.0882) | 0.4882 (+0.0329) |
| 2.1495 | 133000 | 0.1349 | 0.2781 | 0.6183 (+0.0779) | 0.3143 (-0.0108) | 0.6174 (+0.1167) | 0.5166 (+0.0613) |
| 2.1657 | 134000 | 0.1353 | 0.2813 | 0.5824 (+0.0419) | 0.2992 (-0.0259) | 0.6121 (+0.1114) | 0.4979 (+0.0425) |
| 2.1818 | 135000 | 0.1393 | 0.2697 | 0.5742 (+0.0337) | 0.2872 (-0.0378) | 0.6198 (+0.1192) | 0.4937 (+0.0384) |
| 2.1980 | 136000 | 0.1358 | 0.2652 | 0.5871 (+0.0466) | 0.2904 (-0.0346) | 0.5772 (+0.0765) | 0.4849 (+0.0295) |
| 2.2141 | 137000 | 0.1344 | 0.2832 | 0.5790 (+0.0385) | 0.2886 (-0.0365) | 0.5628 (+0.0622) | 0.4768 (+0.0214) |
| 2.2303 | 138000 | 0.1381 | 0.3081 | 0.5981 (+0.0577) | 0.3093 (-0.0157) | 0.6085 (+0.1078) | 0.5053 (+0.0499) |
| 2.2465 | 139000 | 0.1435 | 0.2777 | 0.6116 (+0.0712) | 0.2936 (-0.0314) | 0.5767 (+0.0761) | 0.4940 (+0.0386) |
| 2.2626 | 140000 | 0.1298 | 0.3054 | 0.5784 (+0.0380) | 0.3057 (-0.0193) | 0.5560 (+0.0553) | 0.4801 (+0.0247) |
| 2.2788 | 141000 | 0.1315 | 0.2758 | 0.5764 (+0.0360) | 0.3106 (-0.0144) | 0.5835 (+0.0829) | 0.4902 (+0.0348) |
| 2.2949 | 142000 | 0.134 | 0.2992 | 0.5487 (+0.0083) | 0.2944 (-0.0307) | 0.5572 (+0.0566) | 0.4668 (+0.0114) |
| 2.3111 | 143000 | 0.15 | 0.2720 | 0.5721 (+0.0316) | 0.3137 (-0.0113) | 0.5728 (+0.0721) | 0.4862 (+0.0308) |
| 2.3273 | 144000 | 0.1354 | 0.2829 | 0.5791 (+0.0387) | 0.2974 (-0.0276) | 0.5915 (+0.0909) | 0.4894 (+0.0340) |
| 2.3434 | 145000 | 0.1272 | 0.2927 | 0.5753 (+0.0349) | 0.3033 (-0.0218) | 0.5872 (+0.0866) | 0.4886 (+0.0332) |
| 2.3596 | 146000 | 0.1338 | 0.2961 | 0.5794 (+0.0389) | 0.2933 (-0.0318) | 0.5739 (+0.0733) | 0.4822 (+0.0268) |
| 2.3758 | 147000 | 0.1387 | 0.3044 | 0.5813 (+0.0409) | 0.3085 (-0.0165) | 0.5873 (+0.0867) | 0.4924 (+0.0370) |
| 2.3919 | 148000 | 0.1406 | 0.2855 | 0.5816 (+0.0412) | 0.3095 (-0.0156) | 0.5665 (+0.0658) | 0.4859 (+0.0305) |
| 2.4081 | 149000 | 0.1229 | 0.2821 | 0.5972 (+0.0568) | 0.3052 (-0.0199) | 0.5942 (+0.0936) | 0.4989 (+0.0435) |
| 2.4242 | 150000 | 0.1268 | 0.2976 | 0.6010 (+0.0605) | 0.3117 (-0.0134) | 0.5665 (+0.0658) | 0.4930 (+0.0377) |
| 2.4404 | 151000 | 0.1261 | 0.3029 | 0.5922 (+0.0518) | 0.2956 (-0.0295) | 0.5407 (+0.0401) | 0.4762 (+0.0208) |
| 2.4566 | 152000 | 0.14 | 0.2785 | 0.5712 (+0.0308) | 0.3156 (-0.0094) | 0.5456 (+0.0450) | 0.4775 (+0.0221) |
| 2.4727 | 153000 | 0.1356 | 0.2922 | 0.5613 (+0.0209) | 0.3257 (+0.0007) | 0.5472 (+0.0465) | 0.4781 (+0.0227) |
| 2.4889 | 154000 | 0.1447 | 0.2794 | 0.5772 (+0.0367) | 0.3222 (-0.0028) | 0.5601 (+0.0595) | 0.4865 (+0.0311) |
| 2.5051 | 155000 | 0.1301 | 0.2889 | 0.5896 (+0.0491) | 0.3132 (-0.0119) | 0.5609 (+0.0603) | 0.4879 (+0.0325) |
| 2.5212 | 156000 | 0.1227 | 0.2884 | 0.5784 (+0.0380) | 0.2961 (-0.0289) | 0.5469 (+0.0462) | 0.4738 (+0.0185) |
| 2.5374 | 157000 | 0.1456 | 0.2811 | 0.5837 (+0.0433) | 0.3226 (-0.0024) | 0.5322 (+0.0315) | 0.4795 (+0.0241) |
| 2.5535 | 158000 | 0.1267 | 0.2814 | 0.5618 (+0.0214) | 0.2990 (-0.0261) | 0.5391 (+0.0384) | 0.4666 (+0.0113) |
| 2.5697 | 159000 | 0.1384 | 0.2766 | 0.5157 (-0.0247) | 0.2953 (-0.0297) | 0.5655 (+0.0648) | 0.4588 (+0.0035) |
| 2.5859 | 160000 | 0.1376 | 0.2551 | 0.5692 (+0.0288) | 0.3165 (-0.0086) | 0.5702 (+0.0695) | 0.4853 (+0.0299) |
| 2.6020 | 161000 | 0.135 | 0.2806 | 0.5441 (+0.0037) | 0.3067 (-0.0183) | 0.5562 (+0.0555) | 0.4690 (+0.0136) |
| 2.6182 | 162000 | 0.1238 | 0.2837 | 0.5706 (+0.0302) | 0.3354 (+0.0103) | 0.5629 (+0.0623) | 0.4896 (+0.0343) |
| 2.6343 | 163000 | 0.1415 | 0.2692 | 0.5609 (+0.0205) | 0.3097 (-0.0153) | 0.5377 (+0.0371) | 0.4695 (+0.0141) |
| 2.6505 | 164000 | 0.1263 | 0.2765 | 0.5712 (+0.0308) | 0.3281 (+0.0030) | 0.5770 (+0.0764) | 0.4921 (+0.0367) |
| 2.6667 | 165000 | 0.1324 | 0.2749 | 0.6011 (+0.0607) | 0.3207 (-0.0043) | 0.5744 (+0.0737) | 0.4987 (+0.0434) |
| 2.6828 | 166000 | 0.1423 | 0.2678 | 0.6125 (+0.0721) | 0.3053 (-0.0197) | 0.5662 (+0.0656) | 0.4947 (+0.0393) |
| 2.6990 | 167000 | 0.1423 | 0.2559 | 0.5863 (+0.0459) | 0.3002 (-0.0249) | 0.5810 (+0.0803) | 0.4892 (+0.0338) |
| 2.7152 | 168000 | 0.1346 | 0.2770 | 0.5778 (+0.0374) | 0.2766 (-0.0484) | 0.5617 (+0.0610) | 0.4720 (+0.0166) |
| 2.7313 | 169000 | 0.1325 | 0.2672 | 0.6102 (+0.0698) | 0.3027 (-0.0223) | 0.5584 (+0.0578) | 0.4905 (+0.0351) |
| 2.7475 | 170000 | 0.1326 | 0.2758 | 0.5907 (+0.0502) | 0.2944 (-0.0306) | 0.5679 (+0.0673) | 0.4843 (+0.0290) |
| 2.7636 | 171000 | 0.1294 | 0.2883 | 0.5948 (+0.0543) | 0.2997 (-0.0253) | 0.5692 (+0.0685) | 0.4879 (+0.0325) |
| 2.7798 | 172000 | 0.1324 | 0.2726 | 0.5822 (+0.0418) | 0.3114 (-0.0136) | 0.5872 (+0.0865) | 0.4936 (+0.0382) |
| 2.7960 | 173000 | 0.1277 | 0.2952 | 0.5982 (+0.0578) | 0.3125 (-0.0126) | 0.5706 (+0.0699) | 0.4937 (+0.0384) |
| 2.8121 | 174000 | 0.141 | 0.2667 | 0.5414 (+0.0010) | 0.3050 (-0.0201) | 0.5682 (+0.0676) | 0.4715 (+0.0162) |
| 2.8283 | 175000 | 0.1333 | 0.2919 | 0.5904 (+0.0500) | 0.3201 (-0.0049) | 0.5575 (+0.0569) | 0.4893 (+0.0340) |
| 2.8444 | 176000 | 0.1404 | 0.2595 | 0.5767 (+0.0362) | 0.3267 (+0.0016) | 0.5602 (+0.0596) | 0.4878 (+0.0325) |
| 2.8606 | 177000 | 0.1336 | 0.2627 | 0.5864 (+0.0460) | 0.3270 (+0.0020) | 0.5723 (+0.0716) | 0.4952 (+0.0399) |
| 2.8768 | 178000 | 0.1332 | 0.2693 | 0.5712 (+0.0308) | 0.3232 (-0.0018) | 0.5559 (+0.0553) | 0.4834 (+0.0281) |
| 2.8929 | 179000 | 0.1312 | 0.2787 | 0.5789 (+0.0384) | 0.3174 (-0.0076) | 0.5793 (+0.0787) | 0.4919 (+0.0365) |
| 2.9091 | 180000 | 0.1334 | 0.2802 | 0.5858 (+0.0454) | 0.3225 (-0.0025) | 0.5590 (+0.0584) | 0.4891 (+0.0337) |
| 2.9253 | 181000 | 0.1355 | 0.2633 | 0.5710 (+0.0306) | 0.3228 (-0.0023) | 0.5589 (+0.0583) | 0.4842 (+0.0289) |
| 2.9414 | 182000 | 0.1316 | 0.2558 | 0.5826 (+0.0422) | 0.3148 (-0.0103) | 0.5822 (+0.0815) | 0.4932 (+0.0378) |
| 2.9576 | 183000 | 0.127 | 0.2664 | 0.5810 (+0.0406) | 0.3292 (+0.0042) | 0.5818 (+0.0811) | 0.4973 (+0.0419) |
| 2.9737 | 184000 | 0.1263 | 0.2644 | 0.5628 (+0.0224) | 0.3188 (-0.0062) | 0.5828 (+0.0821) | 0.4881 (+0.0328) |
| 2.9899 | 185000 | 0.1249 | 0.2677 | 0.5822 (+0.0417) | 0.3205 (-0.0045) | 0.5944 (+0.0937) | 0.4990 (+0.0436) |
| 3.0061 | 186000 | 0.1201 | 0.2773 | 0.5477 (+0.0073) | 0.3231 (-0.0019) | 0.5501 (+0.0495) | 0.4737 (+0.0183) |
| 3.0222 | 187000 | 0.0894 | 0.3084 | 0.5308 (-0.0096) | 0.3063 (-0.0188) | 0.5241 (+0.0235) | 0.4537 (-0.0016) |
| 3.0384 | 188000 | 0.0882 | 0.3015 | 0.5399 (-0.0005) | 0.3187 (-0.0063) | 0.5277 (+0.0271) | 0.4621 (+0.0067) |
| 3.0545 | 189000 | 0.0905 | 0.2996 | 0.5312 (-0.0092) | 0.3222 (-0.0028) | 0.5122 (+0.0116) | 0.4552 (-0.0001) |
| 3.0707 | 190000 | 0.0876 | 0.3274 | 0.5587 (+0.0183) | 0.3288 (+0.0037) | 0.5245 (+0.0238) | 0.4707 (+0.0153) |
| 3.0869 | 191000 | 0.0939 | 0.3178 | 0.5134 (-0.0270) | 0.3153 (-0.0098) | 0.5361 (+0.0354) | 0.4549 (-0.0005) |
| 3.1030 | 192000 | 0.0827 | 0.3202 | 0.5354 (-0.0050) | 0.3181 (-0.0069) | 0.5403 (+0.0396) | 0.4646 (+0.0092) |
| 3.1192 | 193000 | 0.0849 | 0.3090 | 0.5108 (-0.0296) | 0.3074 (-0.0177) | 0.5307 (+0.0300) | 0.4496 (-0.0058) |
| 3.1354 | 194000 | 0.0793 | 0.3166 | 0.5744 (+0.0339) | 0.2947 (-0.0303) | 0.5409 (+0.0402) | 0.4700 (+0.0146) |
| 3.1515 | 195000 | 0.0948 | 0.3167 | 0.5533 (+0.0129) | 0.3095 (-0.0156) | 0.5299 (+0.0293) | 0.4642 (+0.0089) |
| 3.1677 | 196000 | 0.0862 | 0.3205 | 0.5398 (-0.0007) | 0.3268 (+0.0018) | 0.5316 (+0.0310) | 0.4661 (+0.0107) |
| 3.1838 | 197000 | 0.0796 | 0.3461 | 0.5088 (-0.0316) | 0.3223 (-0.0027) | 0.5168 (+0.0162) | 0.4493 (-0.0061) |
| 3.2 | 198000 | 0.0859 | 0.3405 | 0.5260 (-0.0145) | 0.3212 (-0.0038) | 0.5128 (+0.0121) | 0.4533 (-0.0020) |
| 3.2162 | 199000 | 0.0931 | 0.3190 | 0.5334 (-0.0070) | 0.3172 (-0.0079) | 0.5014 (+0.0007) | 0.4507 (-0.0047) |
| 3.2323 | 200000 | 0.0841 | 0.3424 | 0.4810 (-0.0594) | 0.3052 (-0.0198) | 0.5032 (+0.0025) | 0.4298 (-0.0256) |
| 3.2485 | 201000 | 0.0833 | 0.3342 | 0.5190 (-0.0215) | 0.3027 (-0.0223) | 0.5219 (+0.0213) | 0.4479 (-0.0075) |
| 3.2646 | 202000 | 0.0884 | 0.3203 | 0.5242 (-0.0163) | 0.3077 (-0.0173) | 0.5191 (+0.0185) | 0.4503 (-0.0050) |
| 3.2808 | 203000 | 0.0854 | 0.3206 | 0.5158 (-0.0247) | 0.3060 (-0.0190) | 0.5173 (+0.0166) | 0.4464 (-0.0090) |
| 3.2970 | 204000 | 0.0859 | 0.3242 | 0.5242 (-0.0163) | 0.3189 (-0.0062) | 0.5198 (+0.0191) | 0.4543 (-0.0011) |
| 3.3131 | 205000 | 0.0792 | 0.3199 | 0.5466 (+0.0062) | 0.3244 (-0.0007) | 0.5304 (+0.0297) | 0.4671 (+0.0118) |
| 3.3293 | 206000 | 0.0807 | 0.3319 | 0.5147 (-0.0257) | 0.3065 (-0.0185) | 0.5222 (+0.0216) | 0.4478 (-0.0076) |
| 3.3455 | 207000 | 0.093 | 0.3156 | 0.5335 (-0.0070) | 0.3238 (-0.0012) | 0.5571 (+0.0565) | 0.4715 (+0.0161) |
| 3.3616 | 208000 | 0.0863 | 0.3112 | 0.5509 (+0.0105) | 0.3298 (+0.0047) | 0.5360 (+0.0353) | 0.4722 (+0.0168) |
| 3.3778 | 209000 | 0.09 | 0.3119 | 0.5378 (-0.0026) | 0.3214 (-0.0036) | 0.5683 (+0.0676) | 0.4758 (+0.0205) |
| 3.3939 | 210000 | 0.0825 | 0.3204 | 0.5283 (-0.0121) | 0.3320 (+0.0069) | 0.5684 (+0.0678) | 0.4762 (+0.0209) |
| 3.4101 | 211000 | 0.0892 | 0.3258 | 0.5251 (-0.0153) | 0.3241 (-0.0010) | 0.5902 (+0.0896) | 0.4798 (+0.0244) |
| 3.4263 | 212000 | 0.0859 | 0.3206 | 0.5333 (-0.0071) | 0.3317 (+0.0067) | 0.5668 (+0.0662) | 0.4773 (+0.0219) |
| 3.4424 | 213000 | 0.0878 | 0.3257 | 0.5274 (-0.0131) | 0.3291 (+0.0041) | 0.5588 (+0.0582) | 0.4718 (+0.0164) |
| 3.4586 | 214000 | 0.0808 | 0.3211 | 0.5236 (-0.0168) | 0.3292 (+0.0042) | 0.5526 (+0.0519) | 0.4685 (+0.0131) |
| 3.4747 | 215000 | 0.0835 | 0.3229 | 0.5421 (+0.0017) | 0.3196 (-0.0054) | 0.5881 (+0.0875) | 0.4833 (+0.0279) |
| 3.4909 | 216000 | 0.0868 | 0.3234 | 0.5167 (-0.0238) | 0.3201 (-0.0050) | 0.5500 (+0.0494) | 0.4623 (+0.0069) |
| 3.5071 | 217000 | 0.089 | 0.3203 | 0.4906 (-0.0498) | 0.3113 (-0.0137) | 0.5616 (+0.0610) | 0.4545 (-0.0009) |
| 3.5232 | 218000 | 0.0924 | 0.3159 | 0.4943 (-0.0462) | 0.3161 (-0.0089) | 0.5527 (+0.0521) | 0.4544 (-0.0010) |
| 3.5394 | 219000 | 0.0842 | 0.3210 | 0.4828 (-0.0576) | 0.3244 (-0.0007) | 0.5631 (+0.0625) | 0.4568 (+0.0014) |
| 3.5556 | 220000 | 0.0949 | 0.3237 | 0.4744 (-0.0661) | 0.3305 (+0.0054) | 0.5512 (+0.0506) | 0.4520 (-0.0034) |
| 3.5717 | 221000 | 0.0868 | 0.3301 | 0.4696 (-0.0708) | 0.3246 (-0.0004) | 0.5772 (+0.0765) | 0.4571 (+0.0018) |
| 3.5879 | 222000 | 0.0916 | 0.3169 | 0.4640 (-0.0765) | 0.3198 (-0.0052) | 0.5576 (+0.0569) | 0.4471 (-0.0082) |
| 3.6040 | 223000 | 0.0777 | 0.3233 | 0.4836 (-0.0568) | 0.3176 (-0.0075) | 0.5704 (+0.0698) | 0.4572 (+0.0018) |
| 3.6202 | 224000 | 0.0835 | 0.3241 | 0.4951 (-0.0454) | 0.3154 (-0.0097) | 0.5418 (+0.0412) | 0.4507 (-0.0046) |
| 3.6364 | 225000 | 0.0847 | 0.3132 | 0.5080 (-0.0324) | 0.3166 (-0.0084) | 0.5148 (+0.0141) | 0.4465 (-0.0089) |
| 3.6525 | 226000 | 0.0926 | 0.3103 | 0.5045 (-0.0359) | 0.3038 (-0.0213) | 0.5156 (+0.0150) | 0.4413 (-0.0141) |
| 3.6687 | 227000 | 0.0872 | 0.3166 | 0.5252 (-0.0152) | 0.3148 (-0.0103) | 0.5197 (+0.0191) | 0.4532 (-0.0021) |
| 3.6848 | 228000 | 0.0886 | 0.3052 | 0.5165 (-0.0239) | 0.3175 (-0.0076) | 0.5331 (+0.0324) | 0.4557 (+0.0003) |
| 3.7010 | 229000 | 0.083 | 0.3027 | 0.5035 (-0.0369) | 0.3152 (-0.0098) | 0.5355 (+0.0348) | 0.4514 (-0.0040) |
| 3.7172 | 230000 | 0.0895 | 0.3073 | 0.4985 (-0.0419) | 0.3188 (-0.0062) | 0.5595 (+0.0589) | 0.4589 (+0.0036) |
| 3.7333 | 231000 | 0.0811 | 0.3080 | 0.4988 (-0.0416) | 0.3174 (-0.0077) | 0.5379 (+0.0373) | 0.4514 (-0.0040) |
| 3.7495 | 232000 | 0.0864 | 0.3043 | 0.4941 (-0.0463) | 0.3128 (-0.0123) | 0.5237 (+0.0230) | 0.4435 (-0.0119) |
| 3.7657 | 233000 | 0.0843 | 0.3153 | 0.4882 (-0.0522) | 0.3208 (-0.0043) | 0.5363 (+0.0356) | 0.4484 (-0.0070) |
| 3.7818 | 234000 | 0.0799 | 0.3184 | 0.5038 (-0.0366) | 0.3251 (+0.0000) | 0.5385 (+0.0379) | 0.4558 (+0.0004) |
| 3.7980 | 235000 | 0.0928 | 0.3122 | 0.4960 (-0.0444) | 0.3238 (-0.0013) | 0.5420 (+0.0413) | 0.4539 (-0.0014) |
| 3.8141 | 236000 | 0.0839 | 0.3112 | 0.4922 (-0.0482) | 0.3237 (-0.0014) | 0.5428 (+0.0422) | 0.4529 (-0.0025) |
| 3.8303 | 237000 | 0.0935 | 0.3060 | 0.4979 (-0.0426) | 0.3231 (-0.0020) | 0.5460 (+0.0454) | 0.4556 (+0.0003) |
| 3.8465 | 238000 | 0.0836 | 0.3101 | 0.4940 (-0.0464) | 0.3270 (+0.0020) | 0.5564 (+0.0558) | 0.4592 (+0.0038) |
| 3.8626 | 239000 | 0.0843 | 0.3151 | 0.4935 (-0.0469) | 0.3238 (-0.0012) | 0.5671 (+0.0664) | 0.4615 (+0.0061) |
| 3.8788 | 240000 | 0.0902 | 0.3118 | 0.5045 (-0.0359) | 0.3238 (-0.0012) | 0.5640 (+0.0634) | 0.4641 (+0.0088) |
| 3.8949 | 241000 | 0.0778 | 0.3151 | 0.4964 (-0.0440) | 0.3235 (-0.0015) | 0.5551 (+0.0544) | 0.4583 (+0.0030) |
| 3.9111 | 242000 | 0.0907 | 0.3097 | 0.4915 (-0.0489) | 0.3208 (-0.0043) | 0.5656 (+0.0650) | 0.4593 (+0.0039) |
| 3.9273 | 243000 | 0.0794 | 0.3191 | 0.4831 (-0.0573) | 0.3213 (-0.0038) | 0.5608 (+0.0602) | 0.4551 (-0.0003) |
| 3.9434 | 244000 | 0.0791 | 0.3155 | 0.4972 (-0.0432) | 0.3235 (-0.0015) | 0.5604 (+0.0597) | 0.4604 (+0.0050) |
| 3.9596 | 245000 | 0.0852 | 0.3161 | 0.4801 (-0.0603) | 0.3222 (-0.0028) | 0.5619 (+0.0612) | 0.4547 (-0.0006) |
| 3.9758 | 246000 | 0.094 | 0.3100 | 0.4905 (-0.0499) | 0.3259 (+0.0008) | 0.5688 (+0.0682) | 0.4617 (+0.0064) |
| 3.9919 | 247000 | 0.0756 | 0.3123 | 0.4814 (-0.0590) | 0.3238 (-0.0012) | 0.5674 (+0.0668) | 0.4575 (+0.0022) |
| -1 | -1 | - | - | 0.6427 (+0.1023) | 0.3340 (+0.0089) | 0.6215 (+0.1208) | 0.5327 (+0.0773) |
* The bold row denotes the saved checkpoint.
</details>
### Framework Versions
- Python: 3.10.18
- Sentence Transformers: 5.0.0
- Transformers: 4.56.0.dev0
- PyTorch: 2.7.1+cu126
- Accelerate: 1.9.0
- Datasets: 4.0.0
- Tokenizers: 0.21.4
## Citation
### BibTeX
#### Sentence Transformers
```bibtex
@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",
}
```
<!--
## Glossary
*Clearly define terms in order to be accessible across audiences.*
-->
<!--
## Model Card Authors
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
-->
<!--
## Model Card Contact
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
-->