---
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:2806
- loss:TripletLoss
base_model: intfloat/e5-large-v2
widget:
- source_sentence: What kind of interests do Joanna and Nate share?
sentences:
- '[4:21 pm on 16 July, 2023] John: John scored 40 points in a game last week, his
highest ever.'
- '[2:01 pm on 23 January, 2022] Nate: Thanks! The turtles might be small, but both
sure have big personalities. I really reccomend having something like these little
guys for times of stress.'
- '[11:54 am on 2 May, 2022] Joanna: Joanna has been working on some projects and
testing dairy-free dessert recipes for friends and family.'
- source_sentence: What is Dave's favorite activity?
sentences:
- '[11:53 am on 23 March, 2023] Calvin: I''m so excited to learn about Japanese
culture and get a chance to expand.'
- '[2:55 pm on 31 August, 2023] Calvin: Yeah, Dave! It''s like every mark and strum
holds a story. Take a look.'
- '[3:13 pm on 8 October, 2023] Dave: Restoring things can be tough for Dave, but
the feeling of accomplishment it gives him is great.'
- source_sentence: What health issue did Sam face that motivated him to change his
lifestyle?
sentences:
- '[12:17 am on 10 January, 2024] Sam: Sam planned to make an appointment with the
doctor to get advice on a balanced diet plan and low-impact exercises.'
- '[1:32 pm on 6 January, 2024] Evan: Thanks, Sam! Catch you later. Have a great
one!'
- '[4:25 pm on 26 December, 2023] Evan: Evan created a painting that reflects a
sense of joy and freedom.'
- source_sentence: When is Evan planning a big family reunion?
sentences:
- '[3:55 pm on 6 June, 2023] Evan: Awesome, Sam! Let me know how it goes. Making
small changes can really help you live a healthier life. Don''t forget - every
step matters!'
- '[1:45 pm on 9 December, 2023] Evan: Evan is planning a big family reunion next
summer to create more memories with family.'
- '[2:42 pm on 2 April, 2023] Andrew: Thanks! Fingers crossed for the apartment
and that furry friend.'
- source_sentence: When did Evan finish the painting that's hanging in the exhibit?
sentences:
- '[6:48 pm on 17 December, 2023] Evan: Yeah, trying something new and succeeding
gives a great feeling of accomplishment. Give it a go, even if it''s just a little
thing. You''ll be amazed!'
- '[7:52 pm on 7 August, 2023] Evan: Yep, Sam! Consistency and perseverance will
get us far. Great chat!'
- '[1:24 pm on 25 May, 2023] Maria: Maria is busy at the shelter preparing for a
fundraiser to cover basic needs for the homeless.'
pipeline_tag: sentence-similarity
library_name: sentence-transformers
---
# SentenceTransformer based on intfloat/e5-large-v2
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [intfloat/e5-large-v2](https://huggingface.co/intfloat/e5-large-v2). It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for retrieval.
## Model Details
### Model Description
- **Model Type:** Sentence Transformer
- **Base model:** [intfloat/e5-large-v2](https://huggingface.co/intfloat/e5-large-v2)
- **Maximum Sequence Length:** 512 tokens
- **Output Dimensionality:** 1024 dimensions
- **Similarity Function:** Cosine Similarity
- **Supported Modality:** Text
### Model Sources
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
- **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/sentence-transformers)
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
### Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'BertModel'})
(1): Pooling({'embedding_dimension': 1024, 'pooling_mode': 'mean', 'include_prompt': True})
(2): Normalize({})
)
```
## 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("ainativestudio/locomo-e5-large-finetuned")
# Run inference
sentences = [
"When did Evan finish the painting that's hanging in the exhibit?",
"[6:48 pm on 17 December, 2023] Evan: Yeah, trying something new and succeeding gives a great feeling of accomplishment. Give it a go, even if it's just a little thing. You'll be amazed!",
'[7:52 pm on 7 August, 2023] Evan: Yep, Sam! Consistency and perseverance will get us far. Great chat!',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]
# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[ 1.0000, -0.9972, -0.9972],
# [-0.9972, 1.0000, 1.0000],
# [-0.9972, 1.0000, 1.0000]])
```
## Training Details
### Training Dataset
#### Unnamed Dataset
* Size: 2,806 training samples
* Columns: sentence_0, sentence_1, and sentence_2
* Approximate statistics based on the first 100 samples:
| | sentence_0 | sentence_1 | sentence_2 |
|:---------|:---------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
| type | string | string | string |
| modality | text | text | text |
| details | - min: 6 tokens
- mean: 12.6 tokens
- max: 20 tokens
| - min: 24 tokens
- mean: 35.69 tokens
- max: 79 tokens
| - min: 21 tokens
- mean: 40.93 tokens
- max: 92 tokens
|
* Samples:
| sentence_0 | sentence_1 | sentence_2 |
|:-----------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| When did Caroline pass the adoption interview? | [9:55 am on 22 October, 2023] Caroline: Caroline passed the adoption agency interviews last Friday and is excited about building her own family through adoption. | [7:55 pm on 9 June, 2023] Melanie: Melanie is supportive of Caroline and proud of her for spreading awareness and inspiring others in the LGBTQ community. |
| How many dogs does Andrew have? | [6:12 pm on 19 October, 2023] Andrew: Andrew adopted another pup from a shelter and named him Buddy. | [1:10 pm on 27 March, 2023] Andrew: Fox Hollow is a great trail to hike on weekends; the views are awesome! |
| Why did Audrey think positive reinforcement training is important for pets? | [2:03 pm on 11 May, 2023] Audrey: Audrey believes in using positive reinforcement rather than punishment to train pets. | [5:41 pm on 3 May, 2023] Audrey: Audrey's dogs wear party hats for fun and treats. |
* Loss: [TripletLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#tripletloss) with these parameters:
```json
{
"distance_metric": "TripletDistanceMetric.EUCLIDEAN",
"triplet_margin": 5
}
```
### Training Hyperparameters
#### Non-Default Hyperparameters
- `per_device_train_batch_size`: 2
- `per_device_eval_batch_size`: 2
- `multi_dataset_batch_sampler`: round_robin
#### All Hyperparameters
Click to expand
- `overwrite_output_dir`: False
- `do_predict`: False
- `prediction_loss_only`: True
- `per_device_train_batch_size`: 2
- `per_device_eval_batch_size`: 2
- `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`: None
- `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
- `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}
- `parallelism_config`: None
- `deepspeed`: None
- `label_smoothing_factor`: 0.0
- `optim`: adamw_torch_fused
- `optim_args`: None
- `adafactor`: False
- `group_by_length`: False
- `length_column_name`: length
- `project`: huggingface
- `trackio_space_id`: trackio
- `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`: no
- `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`: True
- `prompts`: None
- `batch_sampler`: batch_sampler
- `multi_dataset_batch_sampler`: round_robin
- `router_mapping`: {}
- `learning_rate_mapping`: {}