---
base_model: agentlans/deberta-v3-xsmall-zyda-2
library_name: sentence-transformers
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:1079040
- loss:CoSENTLoss
widget:
- source_sentence: In recent years, Nigeria has been actively pursuing industrialization.
sentences:
- What are the effective ways to build your arm muscles?
- His first screen appearance as Glockner during the episode was broadcast on February
22 , 2013 .
- The album received a largely positive critical response compared to bands of the
60s , such as The Velvet Underground and The Grateful Dead .
- source_sentence: As a tree's diameter increases, the width of its growth rings generally
decreases.
sentences:
- Why we feel envy on others and how we can stop that?
- Will the ban on 500 and 1000 rupee notes prove to be a long-term solution to combat
the problem of black money?
- What has writing done for you?
- source_sentence: Same-sex marriages in New York were legalized on June 24, 2011
and were authorized to take place beginning 30 days thereafter.
sentences:
- '"Senator John McCain, who ran as the Republican candidate in 2008, claimed that
it revealed ''Senator Obama''s lack of experience and poor judgement''."'
- Set up the Victoria Conservancy and delivered lilies for planting.
- How do I regain my bone strength after delivery?
- source_sentence: Is there a way to permanently delete a Yahoo email account and
if so, how?
sentences:
- What is a compound sentence?
- Why do some British are so bent on pointing out Yankee Doodle was a British song?
- After the war, Otto Frank, Anne's father, found out that her diary had been preserved
upon his return to Amsterdam.
- source_sentence: The expansion of European colonies resulted in the dissemination
of their cultural ideas and institutions to other regions.
sentences:
- The team added a second car for Thed Björk in 2006 , and was replaced by Richard
Göransson in 2009 .
- What does your life signify?
- How long do dogs bleed during menstruation?
---
# SentenceTransformer based on agentlans/deberta-v3-xsmall-zyda-2
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [agentlans/deberta-v3-xsmall-zyda-2](https://huggingface.co/agentlans/deberta-v3-xsmall-zyda-2). 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.
It was finetuned in the same way as [agentlans/deberta-v3-base-zyda-2-v2](https://huggingface.co/agentlans/deberta-v3-base-zyda-2-v2).
However, the training loss is much higher probably due its small model size.
## Model Details
### Model Description
- **Model Type:** Sentence Transformer
- **Base model:** [agentlans/deberta-v3-xsmall-zyda-2](https://huggingface.co/agentlans/deberta-v3-xsmall-zyda-2)
- **Maximum Sequence Length:** 512 tokens
- **Output Dimensionality:** 384 tokens
- **Similarity Function:** Cosine Similarity
### Model Sources
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
### Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: DebertaV2Model
(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})
)
```
## 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 SentenceTransformer
# Download from the 🤗 Hub
model = SentenceTransformer("agentlans/deberta-v3-xsmall-zyda-2-v2")
# Run inference
sentences = [
'The expansion of European colonies resulted in the dissemination of their cultural ideas and institutions to other regions.',
'How long do dogs bleed during menstruation?',
'The team added a second car for Thed Björk in 2006 , and was replaced by Richard Göransson in 2009 .',
]
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]
```
## Training Details
### Training Dataset
#### Unnamed Dataset
* Size: 1,079,040 training samples
* Columns: sentence_0, sentence_1, and label
* Approximate statistics based on the first 1000 samples:
| | sentence_0 | sentence_1 | label |
|:--------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
| type | string | string | float |
| details | - min: 7 tokens
- mean: 22.43 tokens
- max: 104 tokens
| - min: 7 tokens
- mean: 20.92 tokens
- max: 77 tokens
| - min: 0.0
- mean: 0.33
- max: 1.0
|
* Samples:
| sentence_0 | sentence_1 | label |
|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------|
| Can attaching a CAR with cab companies such as OLA, Taxi for Sure, and Meru Cabs result in financial gain? What are the final returns after factoring in all practical earnings and expenses? | A problem is regarded as inherently difficult if its solution requires significant resources, whatever the algorithm used. | 0.0 |
| She was loaned the money with the specific aim of providing for the child's needs. | The Army's training and doctrine command spokesperson, Maj. Mike Kenfield, stated that the program had been recognized for its role in reducing non-lethal operations and that there were plans to expand the team's reach beyond Iraq and Afghanistan. | 0.0 |
| Two rotavirus vaccines against Rotavirus A infection are safe and effective in children : Rotarix by GlaxoSmithKline and RotaTeq by Merck . | contact lists were wiped after the makers of the game enjoyed by . | 0.0 |
* Loss: [CoSENTLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
```json
{
"scale": 20.0,
"similarity_fct": "pairwise_cos_sim"
}
```
### Training Hyperparameters
#### Non-Default Hyperparameters
- `per_device_train_batch_size`: 16
- `per_device_eval_batch_size`: 16
- `multi_dataset_batch_sampler`: round_robin
#### All Hyperparameters
Click to expand
- `overwrite_output_dir`: False
- `do_predict`: False
- `eval_strategy`: no
- `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`: 5e-05
- `weight_decay`: 0.0
- `adam_beta1`: 0.9
- `adam_beta2`: 0.999
- `adam_epsilon`: 1e-08
- `max_grad_norm`: 1
- `num_train_epochs`: 3
- `max_steps`: -1
- `lr_scheduler_type`: linear
- `lr_scheduler_kwargs`: {}
- `warmup_ratio`: 0.0
- `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`: 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`: False
- `eval_use_gather_object`: False
- `batch_sampler`: batch_sampler
- `multi_dataset_batch_sampler`: round_robin
Click to expand
| Epoch | Step | Training Loss |
|:------:|:------:|:-------------:|
| 0.0074 | 500 | 2.6583 |
| 0.0148 | 1000 | 1.5993 |
| 0.0222 | 1500 | 1.0375 |
| 0.0297 | 2000 | 0.8232 |
| 0.0371 | 2500 | 0.6996 |
| 0.0445 | 3000 | 0.6607 |
| 0.0519 | 3500 | 0.6087 |
| 0.0593 | 4000 | 0.5447 |
| 0.0667 | 4500 | 0.5691 |
| 0.0741 | 5000 | 0.5576 |
| 0.0816 | 5500 | 0.5405 |
| 0.0890 | 6000 | 0.4901 |
| 0.0964 | 6500 | 0.5432 |
| 0.1038 | 7000 | 0.4969 |
| 0.1112 | 7500 | 0.5058 |
| 0.1186 | 8000 | 0.4935 |
| 0.1260 | 8500 | 0.5072 |
| 0.1335 | 9000 | 0.4525 |
| 0.1409 | 9500 | 0.5121 |
| 0.1483 | 10000 | 0.5217 |
| 0.1557 | 10500 | 0.5012 |
| 0.1631 | 11000 | 0.4475 |
| 0.1705 | 11500 | 0.4788 |
| 0.1779 | 12000 | 0.4687 |
| 0.1853 | 12500 | 0.4651 |
| 0.1928 | 13000 | 0.4056 |
| 0.2002 | 13500 | 0.485 |
| 0.2076 | 14000 | 0.4738 |
| 0.2150 | 14500 | 0.4194 |
| 0.2224 | 15000 | 0.4522 |
| 0.2298 | 15500 | 0.5182 |
| 0.2372 | 16000 | 0.4746 |
| 0.2447 | 16500 | 0.4762 |
| 0.2521 | 17000 | 0.4804 |
| 0.2595 | 17500 | 0.4041 |
| 0.2669 | 18000 | 0.4 |
| 0.2743 | 18500 | 0.4459 |
| 0.2817 | 19000 | 0.4258 |
| 0.2891 | 19500 | 0.4218 |
| 0.2966 | 20000 | 0.4951 |
| 0.3040 | 20500 | 0.4687 |
| 0.3114 | 21000 | 0.446 |
| 0.3188 | 21500 | 0.5007 |
| 0.3262 | 22000 | 0.4506 |
| 0.3336 | 22500 | 0.4916 |
| 0.3410 | 23000 | 0.403 |
| 0.3485 | 23500 | 0.4527 |
| 0.3559 | 24000 | 0.4052 |
| 0.3633 | 24500 | 0.4387 |
| 0.3707 | 25000 | 0.4238 |
| 0.3781 | 25500 | 0.4208 |
| 0.3855 | 26000 | 0.4363 |
| 0.3929 | 26500 | 0.429 |
| 0.4004 | 27000 | 0.4837 |
| 0.4078 | 27500 | 0.4042 |
| 0.4152 | 28000 | 0.465 |
| 0.4226 | 28500 | 0.4259 |
| 0.4300 | 29000 | 0.4342 |
| 0.4374 | 29500 | 0.4521 |
| 0.4448 | 30000 | 0.397 |
| 0.4523 | 30500 | 0.4213 |
| 0.4597 | 31000 | 0.4309 |
| 0.4671 | 31500 | 0.473 |
| 0.4745 | 32000 | 0.4081 |
| 0.4819 | 32500 | 0.3937 |
| 0.4893 | 33000 | 0.4402 |
| 0.4967 | 33500 | 0.4685 |
| 0.5042 | 34000 | 0.4309 |
| 0.5116 | 34500 | 0.4349 |
| 0.5190 | 35000 | 0.4357 |
| 0.5264 | 35500 | 0.5066 |
| 0.5338 | 36000 | 0.4424 |
| 0.5412 | 36500 | 0.4532 |
| 0.5486 | 37000 | 0.4576 |
| 0.5560 | 37500 | 0.4634 |
| 0.5635 | 38000 | 0.4742 |
| 0.5709 | 38500 | 0.4565 |
| 0.5783 | 39000 | 0.4613 |
| 0.5857 | 39500 | 0.385 |
| 0.5931 | 40000 | 0.4613 |
| 0.6005 | 40500 | 0.4129 |
| 0.6079 | 41000 | 0.4066 |
| 0.6154 | 41500 | 0.4372 |
| 0.6228 | 42000 | 0.4426 |
| 0.6302 | 42500 | 0.4561 |
| 0.6376 | 43000 | 0.4557 |
| 0.6450 | 43500 | 0.4163 |
| 0.6524 | 44000 | 0.3948 |
| 0.6598 | 44500 | 0.4461 |
| 0.6673 | 45000 | 0.4717 |
| 0.6747 | 45500 | 0.3877 |
| 0.6821 | 46000 | 0.4421 |
| 0.6895 | 46500 | 0.4977 |
| 0.6969 | 47000 | 0.433 |
| 0.7043 | 47500 | 0.4292 |
| 0.7117 | 48000 | 0.4749 |
| 0.7192 | 48500 | 0.4418 |
| 0.7266 | 49000 | 0.4091 |
| 0.7340 | 49500 | 0.412 |
| 0.7414 | 50000 | 0.465 |
| 0.7488 | 50500 | 0.4649 |
| 0.7562 | 51000 | 0.4311 |
| 0.7636 | 51500 | 0.4238 |
| 0.7711 | 52000 | 0.4228 |
| 0.7785 | 52500 | 0.4491 |
| 0.7859 | 53000 | 0.4434 |
| 0.7933 | 53500 | 0.4364 |
| 0.8007 | 54000 | 0.435 |
| 0.8081 | 54500 | 0.4196 |
| 0.8155 | 55000 | 0.4866 |
| 0.8230 | 55500 | 0.4684 |
| 0.8304 | 56000 | 0.4264 |
| 0.8378 | 56500 | 0.4061 |
| 0.8452 | 57000 | 0.4813 |
| 0.8526 | 57500 | 0.4596 |
| 0.8600 | 58000 | 0.4602 |
| 0.8674 | 58500 | 0.4342 |
| 0.8749 | 59000 | 0.4358 |
| 0.8823 | 59500 | 0.4693 |
| 0.8897 | 60000 | 0.4794 |
| 0.8971 | 60500 | 0.4515 |
| 0.9045 | 61000 | 0.4574 |
| 0.9119 | 61500 | 0.388 |
| 0.9193 | 62000 | 0.408 |
| 0.9267 | 62500 | 0.4204 |
| 0.9342 | 63000 | 0.4001 |
| 0.9416 | 63500 | 0.4995 |
| 0.9490 | 64000 | 0.477 |
| 0.9564 | 64500 | 0.4395 |
| 0.9638 | 65000 | 0.4498 |
| 0.9712 | 65500 | 0.4893 |
| 0.9786 | 66000 | 0.4205 |
| 0.9861 | 66500 | 0.4511 |
| 0.9935 | 67000 | 0.4393 |
| 1.0009 | 67500 | 0.4694 |
| 1.0083 | 68000 | 0.4305 |
| 1.0157 | 68500 | 0.4272 |
| 1.0231 | 69000 | 0.3722 |
| 1.0305 | 69500 | 0.4147 |
| 1.0380 | 70000 | 0.4019 |
| 1.0454 | 70500 | 0.4306 |
| 1.0528 | 71000 | 0.4514 |
| 1.0602 | 71500 | 0.4377 |
| 1.0676 | 72000 | 0.4222 |
| 1.0750 | 72500 | 0.4682 |
| 1.0824 | 73000 | 0.4684 |
| 1.0899 | 73500 | 0.4234 |
| 1.0973 | 74000 | 0.4583 |
| 1.1047 | 74500 | 0.4659 |
| 1.1121 | 75000 | 0.4413 |
| 1.1195 | 75500 | 0.4591 |
| 1.1269 | 76000 | 0.4363 |
| 1.1343 | 76500 | 0.4202 |
| 1.1418 | 77000 | 0.4485 |
| 1.1492 | 77500 | 0.4817 |
| 1.1566 | 78000 | 0.4796 |
| 1.1640 | 78500 | 0.4041 |
| 1.1714 | 79000 | 0.3975 |
| 1.1788 | 79500 | 0.4199 |
| 1.1862 | 80000 | 0.4582 |
| 1.1937 | 80500 | 0.4115 |
| 1.2011 | 81000 | 0.4636 |
| 1.2085 | 81500 | 0.4611 |
| 1.2159 | 82000 | 0.4025 |
| 1.2233 | 82500 | 0.4725 |
| 1.2307 | 83000 | 0.4905 |
| 1.2381 | 83500 | 0.4346 |
| 1.2456 | 84000 | 0.4832 |
| 1.2530 | 84500 | 0.465 |
| 1.2604 | 85000 | 0.3884 |
| 1.2678 | 85500 | 0.4228 |
| 1.2752 | 86000 | 0.4086 |
| 1.2826 | 86500 | 0.4548 |
| 1.2900 | 87000 | 0.4022 |
| 1.2974 | 87500 | 0.5155 |
| 1.3049 | 88000 | 0.4158 |
| 1.3123 | 88500 | 0.4638 |
| 1.3197 | 89000 | 0.4645 |
| 1.3271 | 89500 | 0.4357 |
| 1.3345 | 90000 | 0.4144 |
| 1.3419 | 90500 | 0.412 |
| 1.3493 | 91000 | 0.3951 |
| 1.3568 | 91500 | 0.4384 |
| 1.3642 | 92000 | 0.4292 |
| 1.3716 | 92500 | 0.391 |
| 1.3790 | 93000 | 0.4262 |
| 1.3864 | 93500 | 0.4783 |
| 1.3938 | 94000 | 0.4474 |
| 1.4012 | 94500 | 0.4367 |
| 1.4087 | 95000 | 0.4055 |
| 1.4161 | 95500 | 0.4471 |
| 1.4235 | 96000 | 0.4472 |
| 1.4309 | 96500 | 0.4555 |
| 1.4383 | 97000 | 0.4854 |
| 1.4457 | 97500 | 0.389 |
| 1.4531 | 98000 | 0.4308 |
| 1.4606 | 98500 | 0.4565 |
| 1.4680 | 99000 | 0.4344 |
| 1.4754 | 99500 | 0.4332 |
| 1.4828 | 100000 | 0.4179 |
| 1.4902 | 100500 | 0.4546 |
| 1.4976 | 101000 | 0.4667 |
| 1.5050 | 101500 | 0.4418 |
| 1.5125 | 102000 | 0.4462 |
| 1.5199 | 102500 | 0.4841 |
| 1.5273 | 103000 | 0.4768 |
| 1.5347 | 103500 | 0.4072 |
| 1.5421 | 104000 | 0.453 |
| 1.5495 | 104500 | 0.4863 |
| 1.5569 | 105000 | 0.5193 |
| 1.5644 | 105500 | 0.4476 |
| 1.5718 | 106000 | 0.4141 |
| 1.5792 | 106500 | 0.4454 |
| 1.5866 | 107000 | 0.4072 |
| 1.5940 | 107500 | 0.4339 |
| 1.6014 | 108000 | 0.4519 |
| 1.6088 | 108500 | 0.4432 |
| 1.6163 | 109000 | 0.4408 |
| 1.6237 | 109500 | 0.4438 |
| 1.6311 | 110000 | 0.4188 |
| 1.6385 | 110500 | 0.4621 |
| 1.6459 | 111000 | 0.3997 |
| 1.6533 | 111500 | 0.3953 |
| 1.6607 | 112000 | 0.4459 |
| 1.6681 | 112500 | 0.4905 |
| 1.6756 | 113000 | 0.4067 |
| 1.6830 | 113500 | 0.4705 |
| 1.6904 | 114000 | 0.4883 |
| 1.6978 | 114500 | 0.4553 |
| 1.7052 | 115000 | 0.4644 |
| 1.7126 | 115500 | 0.4733 |
| 1.7200 | 116000 | 0.4591 |
| 1.7275 | 116500 | 0.4112 |
| 1.7349 | 117000 | 0.4354 |
| 1.7423 | 117500 | 0.4771 |
| 1.7497 | 118000 | 0.4418 |
| 1.7571 | 118500 | 0.4927 |
| 1.7645 | 119000 | 0.4273 |
| 1.7719 | 119500 | 0.4424 |
| 1.7794 | 120000 | 0.4979 |
| 1.7868 | 120500 | 0.4479 |
| 1.7942 | 121000 | 0.4344 |
| 1.8016 | 121500 | 0.4285 |
| 1.8090 | 122000 | 0.444 |
| 1.8164 | 122500 | 0.4389 |
| 1.8238 | 123000 | 0.4661 |
| 1.8313 | 123500 | 0.4203 |
| 1.8387 | 124000 | 0.4452 |
| 1.8461 | 124500 | 0.4731 |
| 1.8535 | 125000 | 0.4654 |
| 1.8609 | 125500 | 0.4802 |
| 1.8683 | 126000 | 0.445 |
| 1.8757 | 126500 | 0.4279 |
| 1.8832 | 127000 | 0.4832 |
| 1.8906 | 127500 | 0.4754 |
| 1.8980 | 128000 | 0.4675 |
| 1.9054 | 128500 | 0.4248 |
| 1.9128 | 129000 | 0.4189 |
| 1.9202 | 129500 | 0.4098 |
| 1.9276 | 130000 | 0.4308 |
| 1.9351 | 130500 | 0.4118 |
| 1.9425 | 131000 | 0.4508 |
| 1.9499 | 131500 | 0.4327 |
| 1.9573 | 132000 | 0.4557 |
| 1.9647 | 132500 | 0.4688 |
| 1.9721 | 133000 | 0.4743 |
| 1.9795 | 133500 | 0.4362 |
| 1.9870 | 134000 | 0.4782 |
| 1.9944 | 134500 | 0.4441 |
| 2.0018 | 135000 | 0.4344 |
| 2.0092 | 135500 | 0.4414 |
| 2.0166 | 136000 | 0.4432 |
| 2.0240 | 136500 | 0.3841 |
| 2.0314 | 137000 | 0.4706 |
| 2.0388 | 137500 | 0.455 |
| 2.0463 | 138000 | 0.4336 |
| 2.0537 | 138500 | 0.4215 |
| 2.0611 | 139000 | 0.4369 |
| 2.0685 | 139500 | 0.4539 |
| 2.0759 | 140000 | 0.4395 |
| 2.0833 | 140500 | 0.4303 |
| 2.0907 | 141000 | 0.4272 |
| 2.0982 | 141500 | 0.4857 |
| 2.1056 | 142000 | 0.4832 |
| 2.1130 | 142500 | 0.4579 |
| 2.1204 | 143000 | 0.4695 |
| 2.1278 | 143500 | 0.4174 |
| 2.1352 | 144000 | 0.4167 |
| 2.1426 | 144500 | 0.4766 |
| 2.1501 | 145000 | 0.4676 |
| 2.1575 | 145500 | 0.4878 |
| 2.1649 | 146000 | 0.4259 |
| 2.1723 | 146500 | 0.4185 |
| 2.1797 | 147000 | 0.4656 |
| 2.1871 | 147500 | 0.4278 |
| 2.1945 | 148000 | 0.4322 |
| 2.2020 | 148500 | 0.4321 |
| 2.2094 | 149000 | 0.439 |
| 2.2168 | 149500 | 0.4254 |
| 2.2242 | 150000 | 0.5099 |
| 2.2316 | 150500 | 0.4311 |
| 2.2390 | 151000 | 0.4404 |
| 2.2464 | 151500 | 0.4868 |
| 2.2539 | 152000 | 0.4572 |
| 2.2613 | 152500 | 0.3887 |
| 2.2687 | 153000 | 0.4222 |
| 2.2761 | 153500 | 0.4465 |
| 2.2835 | 154000 | 0.4298 |
| 2.2909 | 154500 | 0.4386 |
| 2.2983 | 155000 | 0.5101 |
| 2.3058 | 155500 | 0.4677 |
| 2.3132 | 156000 | 0.4299 |
| 2.3206 | 156500 | 0.4585 |
| 2.3280 | 157000 | 0.4335 |
| 2.3354 | 157500 | 0.4298 |
| 2.3428 | 158000 | 0.4167 |
| 2.3502 | 158500 | 0.4132 |
| 2.3577 | 159000 | 0.4135 |
| 2.3651 | 159500 | 0.4453 |
| 2.3725 | 160000 | 0.4093 |
| 2.3799 | 160500 | 0.4249 |
| 2.3873 | 161000 | 0.4968 |
| 2.3947 | 161500 | 0.4763 |
| 2.4021 | 162000 | 0.4496 |
| 2.4095 | 162500 | 0.452 |
| 2.4170 | 163000 | 0.4688 |
| 2.4244 | 163500 | 0.3847 |
| 2.4318 | 164000 | 0.4752 |
| 2.4392 | 164500 | 0.4463 |
| 2.4466 | 165000 | 0.3764 |
| 2.4540 | 165500 | 0.4515 |
| 2.4614 | 166000 | 0.4342 |
| 2.4689 | 166500 | 0.4163 |
| 2.4763 | 167000 | 0.4306 |
| 2.4837 | 167500 | 0.4131 |
| 2.4911 | 168000 | 0.4657 |
| 2.4985 | 168500 | 0.446 |
| 2.5059 | 169000 | 0.4342 |
| 2.5133 | 169500 | 0.4293 |
| 2.5208 | 170000 | 0.4388 |
| 2.5282 | 170500 | 0.4935 |
| 2.5356 | 171000 | 0.4124 |
| 2.5430 | 171500 | 0.4519 |
| 2.5504 | 172000 | 0.4886 |
| 2.5578 | 172500 | 0.4552 |
| 2.5652 | 173000 | 0.4628 |
| 2.5727 | 173500 | 0.4277 |
| 2.5801 | 174000 | 0.4048 |
| 2.5875 | 174500 | 0.434 |
| 2.5949 | 175000 | 0.43 |
| 2.6023 | 175500 | 0.4637 |
| 2.6097 | 176000 | 0.4151 |
| 2.6171 | 176500 | 0.4334 |
| 2.6246 | 177000 | 0.4592 |
| 2.6320 | 177500 | 0.4548 |
| 2.6394 | 178000 | 0.4622 |
| 2.6468 | 178500 | 0.3954 |
| 2.6542 | 179000 | 0.417 |
| 2.6616 | 179500 | 0.4429 |
| 2.6690 | 180000 | 0.4639 |
| 2.6765 | 180500 | 0.3764 |
| 2.6839 | 181000 | 0.4809 |
| 2.6913 | 181500 | 0.4518 |
| 2.6987 | 182000 | 0.4526 |
| 2.7061 | 182500 | 0.464 |
| 2.7135 | 183000 | 0.4487 |
| 2.7209 | 183500 | 0.4213 |
| 2.7284 | 184000 | 0.3954 |
| 2.7358 | 184500 | 0.4081 |
| 2.7432 | 185000 | 0.4707 |
| 2.7506 | 185500 | 0.4218 |
| 2.7580 | 186000 | 0.4552 |
| 2.7654 | 186500 | 0.4371 |
| 2.7728 | 187000 | 0.4286 |
| 2.7802 | 187500 | 0.4626 |
| 2.7877 | 188000 | 0.4075 |
| 2.7951 | 188500 | 0.4263 |
| 2.8025 | 189000 | 0.4215 |
| 2.8099 | 189500 | 0.428 |
| 2.8173 | 190000 | 0.4919 |
| 2.8247 | 190500 | 0.459 |
| 2.8321 | 191000 | 0.4122 |
| 2.8396 | 191500 | 0.4404 |
| 2.8470 | 192000 | 0.4358 |
| 2.8544 | 192500 | 0.472 |
| 2.8618 | 193000 | 0.4541 |
| 2.8692 | 193500 | 0.4378 |
| 2.8766 | 194000 | 0.4281 |
| 2.8840 | 194500 | 0.4745 |
| 2.8915 | 195000 | 0.4642 |
| 2.8989 | 195500 | 0.4637 |
| 2.9063 | 196000 | 0.4311 |
| 2.9137 | 196500 | 0.3999 |
| 2.9211 | 197000 | 0.4125 |
| 2.9285 | 197500 | 0.426 |
| 2.9359 | 198000 | 0.4357 |
| 2.9434 | 198500 | 0.4743 |
| 2.9508 | 199000 | 0.4519 |
| 2.9582 | 199500 | 0.4294 |
| 2.9656 | 200000 | 0.4603 |
| 2.9730 | 200500 | 0.4824 |
| 2.9804 | 201000 | 0.4003 |
| 2.9878 | 201500 | 0.4161 |
| 2.9953 | 202000 | 0.4853 |