colbert-small-v1 trained on climatecheck

This is a Cross Encoder model finetuned from answerdotai/answerai-colbert-small-v1 using the sentence-transformers library. It computes scores for pairs of texts, which can be used for text reranking and semantic search.

Model Details

Model Description

Model Type: Cross Encoder
Base model: answerdotai/answerai-colbert-small-v1
Maximum Sequence Length: 512 tokens
Number of Output Labels: 1 label
Language: en
License: apache-2.0

Model Sources

Documentation: Sentence Transformers Documentation
Documentation: Cross Encoder Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Cross Encoders on Hugging Face

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import CrossEncoder

# Download from the 🤗 Hub
model = CrossEncoder("gmguarino/answerai-colbert-small-v1-climatecheck-chunks")
# Get scores for pairs of texts
pairs = [
    ['Turns out, species that can adapt easily to different environments are often the ones that can survive in a wide variety of places. Interesting, right?', 'Welcome to the city Human populations are shifting en masse to cities, which is leading to rapid increases in the number and extent of urban areas. Such changes are well known to cause declines in many species, but they can also act as alternative selection pressures to which some species are able to adapt. Johnson and Munshi-South review the suite of pressures that urban environments exert, the ways in which species may (or may not) adapt, and the larger impact of these evolutionary events on natural processes and human populations. Understanding such urban evolution patterns will improve our ability to foster species persistence in the face of urbanization and to mitigate some of the challenges, such as disease, that adaptation can bring.'],
    ['Turns out, species that can adapt easily to different environments are often the ones that can survive in a wide variety of places. Interesting, right?', 'Science, this issue p. eaam8327 BACKGROUND The extent of urban areas is increasing around the world, and most humans now live in cities. Urbanization results in dramatic environmental change, including increased temperatures, more impervious surface cover, altered hydrology, and elevated pollution. Urban areas also host more non-native species and reduced abundance and diversity of many native species. These environmental changes brought by global urbanization are creating novel ecosystems with unknown consequences for the evolution of life. Here, we consider how early human settlements led to the evolution of human commensals, including some of the most notorious pests and disease vectors. We also comprehensively review how contemporary urbanization affects the evolution of species that coinhabit cities.'],
    ['Turns out, species that can adapt easily to different environments are often the ones that can survive in a wide variety of places. Interesting, right?', 'We also comprehensively review how contemporary urbanization affects the evolution of species that coinhabit cities. ADVANCES A recent surge of research shows that urbanization affects both nonadaptive and adaptive evolution. Some of the clearest results of urban evolution show that cities elevate the strength of random genetic drift (stochastic changes in allele frequencies) and restrict gene flow (the movement of alleles between populations due to dispersal and mating). Populations of native species in cities often represent either relicts that predate urbanization or populations that established after a city formed. Both scenarios frequently result in a loss of genetic diversity within populations and increased differentiation between populations.'],
    ['Turns out, species that can adapt easily to different environments are often the ones that can survive in a wide variety of places. Interesting, right?', 'Both scenarios frequently result in a loss of genetic diversity within populations and increased differentiation between populations. Fragmentation and urban infrastructure also create barriers to dispersal, and consequently, gene flow is often reduced among city populations, which further contributes to genetic differentiation between populations. The influence of urbanization on mutation and adaptive evolution are less clear. A small number of studies suggest that industrial pollution can elevate mutation rates, but the pervasiveness of this effect is unknown. A better studied phenomenon are the effects of urbanization on evolution by natural selection. A growing number of studies show that plant and animal populations experience divergent selection between urban and nonurban environments.'],
    ['Turns out, species that can adapt easily to different environments are often the ones that can survive in a wide variety of places. Interesting, right?', 'A growing number of studies show that plant and animal populations experience divergent selection between urban and nonurban environments. This divergent selection has led to adaptive evolution in life history, morphology, physiology, behavior, and reproductive traits. These adaptations typically evolve in response to pesticide use, pollution, local climate, or the physical structure of cities. Despite these important results, the genetic basis of adaptive evolution is known from only a few cases. Most studies also examine only a few populations in one city, and experimental validation is rare. OUTLOOK The study of evolution in urban areas provides insights into both fundamental and applied problems in biology.'],
]
scores = model.predict(pairs)
print(scores.shape)
# (5,)

# Or rank different texts based on similarity to a single text
ranks = model.rank(
    'Turns out, species that can adapt easily to different environments are often the ones that can survive in a wide variety of places. Interesting, right?',
    [
        'Welcome to the city Human populations are shifting en masse to cities, which is leading to rapid increases in the number and extent of urban areas. Such changes are well known to cause declines in many species, but they can also act as alternative selection pressures to which some species are able to adapt. Johnson and Munshi-South review the suite of pressures that urban environments exert, the ways in which species may (or may not) adapt, and the larger impact of these evolutionary events on natural processes and human populations. Understanding such urban evolution patterns will improve our ability to foster species persistence in the face of urbanization and to mitigate some of the challenges, such as disease, that adaptation can bring.',
        'Science, this issue p. eaam8327 BACKGROUND The extent of urban areas is increasing around the world, and most humans now live in cities. Urbanization results in dramatic environmental change, including increased temperatures, more impervious surface cover, altered hydrology, and elevated pollution. Urban areas also host more non-native species and reduced abundance and diversity of many native species. These environmental changes brought by global urbanization are creating novel ecosystems with unknown consequences for the evolution of life. Here, we consider how early human settlements led to the evolution of human commensals, including some of the most notorious pests and disease vectors. We also comprehensively review how contemporary urbanization affects the evolution of species that coinhabit cities.',
        'We also comprehensively review how contemporary urbanization affects the evolution of species that coinhabit cities. ADVANCES A recent surge of research shows that urbanization affects both nonadaptive and adaptive evolution. Some of the clearest results of urban evolution show that cities elevate the strength of random genetic drift (stochastic changes in allele frequencies) and restrict gene flow (the movement of alleles between populations due to dispersal and mating). Populations of native species in cities often represent either relicts that predate urbanization or populations that established after a city formed. Both scenarios frequently result in a loss of genetic diversity within populations and increased differentiation between populations.',
        'Both scenarios frequently result in a loss of genetic diversity within populations and increased differentiation between populations. Fragmentation and urban infrastructure also create barriers to dispersal, and consequently, gene flow is often reduced among city populations, which further contributes to genetic differentiation between populations. The influence of urbanization on mutation and adaptive evolution are less clear. A small number of studies suggest that industrial pollution can elevate mutation rates, but the pervasiveness of this effect is unknown. A better studied phenomenon are the effects of urbanization on evolution by natural selection. A growing number of studies show that plant and animal populations experience divergent selection between urban and nonurban environments.',
        'A growing number of studies show that plant and animal populations experience divergent selection between urban and nonurban environments. This divergent selection has led to adaptive evolution in life history, morphology, physiology, behavior, and reproductive traits. These adaptations typically evolve in response to pesticide use, pollution, local climate, or the physical structure of cities. Despite these important results, the genetic basis of adaptive evolution is known from only a few cases. Most studies also examine only a few populations in one city, and experimental validation is rare. OUTLOOK The study of evolution in urban areas provides insights into both fundamental and applied problems in biology.',
    ]
)
# [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...]

Training Details

Training Dataset

Unnamed Dataset

Size: 3,952 training samples
Columns: anchor, passage, and label

Approximate statistics based on the first 1000 samples:

	anchor	passage	label
type	string	string	float
details	min: 30 characters mean: 107.43 characters max: 209 characters	min: 83 characters mean: 598.79 characters max: 954 characters	min: 0.0 mean: 0.53 max: 1.0

Samples:

anchor	passage	label
`Turns out, species that can adapt easily to different environments are often the ones that can survive in a wide variety of places. Interesting, right?`	Welcome to the city Human populations are shifting en masse to cities, which is leading to rapid increases in the number and extent of urban areas. Such changes are well known to cause declines in many species, but they can also act as alternative selection pressures to which some species are able to adapt. Johnson and Munshi-South review the suite of pressures that urban environments exert, the ways in which species may (or may not) adapt, and the larger impact of these evolutionary events on natural processes and human populations. Understanding such urban evolution patterns will improve our ability to foster species persistence in the face of urbanization and to mitigate some of the challenges, such as disease, that adaptation can bring.	`0.0`
`Turns out, species that can adapt easily to different environments are often the ones that can survive in a wide variety of places. Interesting, right?`	Science, this issue p. eaam8327 BACKGROUND The extent of urban areas is increasing around the world, and most humans now live in cities. Urbanization results in dramatic environmental change, including increased temperatures, more impervious surface cover, altered hydrology, and elevated pollution. Urban areas also host more non-native species and reduced abundance and diversity of many native species. These environmental changes brought by global urbanization are creating novel ecosystems with unknown consequences for the evolution of life. Here, we consider how early human settlements led to the evolution of human commensals, including some of the most notorious pests and disease vectors. We also comprehensively review how contemporary urbanization affects the evolution of species that coinhabit cities.	`0.0`
`Turns out, species that can adapt easily to different environments are often the ones that can survive in a wide variety of places. Interesting, right?`	We also comprehensively review how contemporary urbanization affects the evolution of species that coinhabit cities. ADVANCES A recent surge of research shows that urbanization affects both nonadaptive and adaptive evolution. Some of the clearest results of urban evolution show that cities elevate the strength of random genetic drift (stochastic changes in allele frequencies) and restrict gene flow (the movement of alleles between populations due to dispersal and mating). Populations of native species in cities often represent either relicts that predate urbanization or populations that established after a city formed. Both scenarios frequently result in a loss of genetic diversity within populations and increased differentiation between populations.	`0.0`

Loss: BinaryCrossEntropyLoss with these parameters:

{
    "activation_fn": "torch.nn.modules.linear.Identity",
    "pos_weight": null
}

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 16
learning_rate: 2e-05
num_train_epochs: 5
warmup_ratio: 0.1
fp16: True
dataloader_num_workers: 2

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: 8
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: 5
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: 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: 2
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}
tp_size: 0
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
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
eval_use_gather_object: False
average_tokens_across_devices: False
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: proportional

Training Logs