phrases-reranker-e5-base / README.md

adugeen

Upload folder using huggingface_hub

86eb18e verified 7 months ago

preview code

raw

history blame contribute delete

25.9 kB

metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:98660
  - loss:MultipleNegativesRankingLoss
base_model: intfloat/multilingual-e5-base
widget:
  - source_sentence: >-
      Instruct: Given a dialogue context, retrieve relevant followup phrase that
      align with the context

      Dialogue Context: bot_0: Do you like gaming. I am a big fan.

      bot_1: My kids play games but I don't play much. I love to watch movies!.

      bot_0: Oh really what is their favorite game?

      bot_1: I think it's called fortnite. I sometimes watch while cooking
      healthy meals. What's yours?

      bot_0: The best game I like to play is alistar.

      bot_1: Never heard of it. Old timer here! Just turned 30. What other
      things do you like?
    sentences:
      - >-
        Followup phrase: I usually only eat them when my kids want them, it's
        not something that I'll make for myself.  What's your favorite dip for
        chicken nuggets?
      - >-
        Followup phrase: My big doberman lays on me all the time and ripped mine
        off
      - 'Followup phrase: Yeah, he also got me into cars.'
  - source_sentence: >-
      Instruct: Given a dialogue context, retrieve relevant followup phrase that
      align with the context

      Dialogue Context: bot_0: Just sitting down to dinner after work. Steak!

      bot_1: Listening to my beethoven favorite, moonlight sonata..

      bot_0: Nice! I listen to music at work a lot. What do you do?

      bot_1: I practice shooting with both of my handgunds and watch british tv.
      You?

      bot_0: Sales. The playlist of black sabbath usually pumps me up to sell!
      Lol.

      bot_1: My grandma from italy came to visit, and iron man is her favorite
      song!

      bot_0: Your grandma rocks! Love italy, hope to visit but need to pay off
      some debt first.

      bot_1: I understand that. I want to travel in general but I can't at the
      moment..

      bot_0: Hopefully you will! I’m so focused on my career, travel is a low
      priority at this point.

      bot_1: Same for me! I barely paid off my volkswagen beetle.

      bot_0: Love that car. What color?
    sentences:
      - >-
        Followup phrase: I hope so. I just try to keep positive, eat healthy and
        drink lots of water.
      - >-
        Followup phrase: I just made a seafood chowder lately! It tastes great.
        What's your favourite dish to cook at your restuarant?
      - >-
        Followup phrase: Do you speak any other languages? I enjoy learning
        them.
  - source_sentence: >-
      Instruct: Given a dialogue context, retrieve relevant followup phrase that
      align with the context

      Dialogue Context: bot_0: Hello how are you doing today?

      bot_1: Very well thank you. How are you?

      bot_0: Going to head out soon to play some baseball. I really like the
      game.
    sentences:
      - >-
        Followup phrase: It teaches discipline too. I'm an er nurse so I don't
        see my son that much
      - 'Followup phrase: I take a boat to work! What about you?'
      - 'Followup phrase: Yes 3 but they live out of state.. You?'
  - source_sentence: >-
      Instruct: Given a dialogue context, retrieve relevant followup phrase that
      align with the context

      Dialogue Context: bot_0: Hello, I am in college for marketing. What do you
      do?

      bot_1: Hi. Right now an entrepreneur, freelance. I was an accountant
      before.

      bot_0: Cool, did you not like being an accountant?

      bot_1: Not really, I am ready for a new life, new career. Do you have a
      job?

      bot_0: No, but I am hoping to design ads one day!
    sentences:
      - 'Followup phrase: Nice. Any pets? I have a dog, he is my best friend..'
      - >-
        Followup phrase: Yes! I like to have a little "me" time in the morning
        to play games before I have to get up for work. It's so relaxing. When
        do you usually play games?
      - >-
        Followup phrase: I am a full time student but I work construction in the
        summer months for
  - source_sentence: >-
      Instruct: Given a dialogue context, retrieve relevant followup phrase that
      align with the context

      Dialogue Context: bot_0: Hello, I just got back from class. What are you
      doing?

      bot_1: I just got done working out at the gym.

      bot_0: Cool, what is your favorite exercise?

      bot_1: Do you have your own vehicle?

      bot_0: No, I am a student. I walk everywhere or I take the bus.

      bot_1: Oh wow, that must get tiring. Do you have a significant other?

      bot_0: It's not, I even have energy to play baseball. I do not, I am
      single.

      bot_1: Thats awesome that you have the energy. My significant other is a
      lawyer. We're married..

      bot_0: Awe, I hope to have a job designing ads one day.

      bot_1: That sounds neat. Are you a vegetarian?

      bot_0: No, but have thought about it!
    sentences:
      - 'Followup phrase: I do not. My husband wants a boy, he is in the army.'
      - 'Followup phrase: I am amazing, except I found out I am allergic to fish!'
      - >-
        Followup phrase: Yeah they can be, single with no kids, which is great!!
        Living off the land
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - cosine_accuracy
  - cosine_accuracy_threshold
  - cosine_f1
  - cosine_f1_threshold
  - cosine_precision
  - cosine_recall
  - cosine_ap
  - cosine_mcc
model-index:
  - name: SentenceTransformer based on intfloat/multilingual-e5-base
    results:
      - task:
          type: binary-classification
          name: Binary Classification
        dataset:
          name: Unknown
          type: unknown
        metrics:
          - type: cosine_accuracy
            value: 0.9324928469241774
            name: Cosine Accuracy
          - type: cosine_accuracy_threshold
            value: 0.6963315010070801
            name: Cosine Accuracy Threshold
          - type: cosine_f1
            value: 0.7932711614832003
            name: Cosine F1
          - type: cosine_f1_threshold
            value: 0.6896486282348633
            name: Cosine F1 Threshold
          - type: cosine_precision
            value: 0.791752026365013
            name: Cosine Precision
          - type: cosine_recall
            value: 0.7947961373390557
            name: Cosine Recall
          - type: cosine_ap
            value: 0.8751572160892609
            name: Cosine Ap
          - type: cosine_mcc
            value: 0.7518321554060445
            name: Cosine Mcc

SentenceTransformer based on intfloat/multilingual-e5-base

This is a sentence-transformers model finetuned from intfloat/multilingual-e5-base. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: intfloat/multilingual-e5-base
Maximum Sequence Length: 512 tokens
Output Dimensionality: 768 dimensions
Similarity Function: Cosine Similarity

Model Sources

Documentation: Sentence Transformers Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
  (2): Normalize()
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("sentence_transformers_model_id")
# Run inference
sentences = [
    "Instruct: Given a dialogue context, retrieve relevant followup phrase that align with the context\nDialogue Context: bot_0: Hello, I just got back from class. What are you doing?\nbot_1: I just got done working out at the gym.\nbot_0: Cool, what is your favorite exercise?\nbot_1: Do you have your own vehicle?\nbot_0: No, I am a student. I walk everywhere or I take the bus.\nbot_1: Oh wow, that must get tiring. Do you have a significant other?\nbot_0: It's not, I even have energy to play baseball. I do not, I am single.\nbot_1: Thats awesome that you have the energy. My significant other is a lawyer. We're married..\nbot_0: Awe, I hope to have a job designing ads one day.\nbot_1: That sounds neat. Are you a vegetarian?\nbot_0: No, but have thought about it!",
    'Followup phrase: I do not. My husband wants a boy, he is in the army.',
    'Followup phrase: I am amazing, except I found out I am allergic to fish!',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

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

Evaluation

Metrics

Binary Classification

Evaluated with BinaryClassificationEvaluator

Metric	Value
cosine_accuracy	0.9325
cosine_accuracy_threshold	0.6963
cosine_f1	0.7933
cosine_f1_threshold	0.6896
cosine_precision	0.7918
cosine_recall	0.7948
cosine_ap	0.8752
cosine_mcc	0.7518

Training Details

Training Dataset

Unnamed Dataset

Size: 98,660 training samples
Columns: sentence1 and sentence2
Approximate statistics based on the first 1000 samples:
sentence1 sentence2
type string string
details
min: 35 tokens
mean: 144.27 tokens
max: 319 tokens

min: 10 tokens
mean: 22.54 tokens
max: 41 tokens

	sentence1	sentence2
type	string	string
details	min: 35 tokens mean: 144.27 tokens max: 319 tokens	min: 10 tokens mean: 22.54 tokens max: 41 tokens

Samples:

sentence1	sentence2
`Instruct: Given a dialogue context, retrieve relevant followup phrase that align with the context Dialogue Context: bot_0: What kind of car do you own? I have a jeep.`	`Followup phrase: I don't own my own car! I actually really enjoying walking and running, but then again, I live in a small town and semi-close to work.`
`Instruct: Given a dialogue context, retrieve relevant followup phrase that align with the context Dialogue Context: bot_0: What kind of car do you own? I have a jeep. bot_1: I don't own my own car! I actually really enjoying walking and running, but then again, I live in a small town and semi-close to work.`	`Followup phrase: Ah I see! I like going to the gym to work out.`
`Instruct: Given a dialogue context, retrieve relevant followup phrase that align with the context Dialogue Context: bot_0: What kind of car do you own? I have a jeep. bot_1: I don't own my own car! I actually really enjoying walking and running, but then again, I live in a small town and semi-close to work. bot_0: Ah I see! I like going to the gym to work out.`	`Followup phrase: I'm a computer programmer. What do you do for work.`

Loss: MultipleNegativesRankingLoss with these parameters:

{
    "scale": 100,
    "similarity_fct": "cos_sim"
}

Evaluation Dataset

Unnamed Dataset

Size: 67,104 evaluation samples
Columns: sentence1, sentence2, and label
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 label
type string string int
details
min: 38 tokens
mean: 137.57 tokens
max: 290 tokens

min: 11 tokens
mean: 31.57 tokens
max: 106 tokens

0: ~83.30%
1: ~16.70%

	sentence1	sentence2	label
type	string	string	int
details	min: 38 tokens mean: 137.57 tokens max: 290 tokens	min: 11 tokens mean: 31.57 tokens max: 106 tokens	0: ~83.30% 1: ~16.70%

Samples:

sentence1	sentence2	label
`Instruct: Given a dialogue context, retrieve relevant followup phrase that align with the context Dialogue Context: bot_0: Do you like music?`	`Followup phrase: Yes, you could say it is a great source of joy for me.`	`1`
`Instruct: Given a dialogue context, retrieve relevant followup phrase that align with the context Dialogue Context: bot_0: Do you like music?`	`Followup phrase: That sounds amazing! But I was thinking of going to mexico this summer and was going to ask if you were going to be there? Would your timeshare be available?`	`0`
`Instruct: Given a dialogue context, retrieve relevant followup phrase that align with the context Dialogue Context: bot_0: Do you like music?`	`Followup phrase: Mostly just authentic mexican food, with lots of spice.`	`0`

Loss: MultipleNegativesRankingLoss with these parameters:

{
    "scale": 100,
    "similarity_fct": "cos_sim"
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: epoch
per_device_train_batch_size: 100
per_device_eval_batch_size: 100
weight_decay: 0.01
num_train_epochs: 5
bf16: True
load_best_model_at_end: True
prompts: {'sentence1': 'Instruct: Given a dialogue context, retrieve relevant followup phrase that align with the context\nDialogue Context: ', 'sentence2': 'Followup phrase: '}
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: epoch
prediction_loss_only: True
per_device_train_batch_size: 100
per_device_eval_batch_size: 100
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: 0.01
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: 0.0
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: 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: 0
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
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: {'sentence1': 'Instruct: Given a dialogue context, retrieve relevant followup phrase that align with the context\nDialogue Context: ', 'sentence2': 'Followup phrase: '}
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	Validation Loss	cosine_ap
0.1013	100	1.8292	-	-
0.2026	200	1.4433	-	-
0.3040	300	1.2605	-	-
0.4053	400	1.1947	-	-
0.5066	500	1.1714	-	-
0.6079	600	1.1106	-	-
0.7092	700	1.0978	-	-
0.8105	800	1.0527	-	-
0.9119	900	1.0524	-	-
1.0	987	-	8.1109	0.8790
1.0132	1000	1.0068	-	-
1.1145	1100	0.949	-	-
1.2158	1200	0.9519	-	-
1.3171	1300	0.9364	-	-
1.4184	1400	0.9253	-	-
1.5198	1500	0.9724	-	-
1.6211	1600	0.9227	-	-
1.7224	1700	0.9169	-	-
1.8237	1800	0.9146	-	-
1.9250	1900	0.9029	-	-
2.0	1974	-	8.4529	0.8727
2.0263	2000	0.9073	-	-
2.1277	2100	0.8685	-	-
2.2290	2200	0.8413	-	-
2.3303	2300	0.8763	-	-
2.4316	2400	0.8524	-	-
2.5329	2500	0.8729	-	-
2.6342	2600	0.856	-	-
2.7356	2700	0.8652	-	-
2.8369	2800	0.8768	-	-
2.9382	2900	0.8477	-	-
3.0	2961	-	8.7662	0.8752

Framework Versions

Python: 3.10.18
Sentence Transformers: 4.1.0
Transformers: 4.52.4
PyTorch: 2.7.1+cu128
Accelerate: 1.7.0
Datasets: 3.6.0
Tokenizers: 0.21.1

Citation

BibTeX

Sentence Transformers

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

MultipleNegativesRankingLoss

@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply},
    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}