bobox

n_layers_per_step = 1, last_layer_weight = 1 * model_layers,, prior_layers_weight= 0.05, kl_div_weight = 2, kl_temperature= 0.9,

aa1484c verified over 1 year ago

preview code

raw

history blame contribute delete

23.6 kB

metadata

language:
  - en
library_name: sentence-transformers
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:67190
  - loss:AdaptiveLayerLoss
  - loss:MultipleNegativesRankingLoss
base_model: microsoft/deberta-v3-small
datasets:
  - stanfordnlp/snli
metrics:
  - cosine_accuracy
  - cosine_accuracy_threshold
  - cosine_f1
  - cosine_f1_threshold
  - cosine_precision
  - cosine_recall
  - cosine_ap
  - dot_accuracy
  - dot_accuracy_threshold
  - dot_f1
  - dot_f1_threshold
  - dot_precision
  - dot_recall
  - dot_ap
  - manhattan_accuracy
  - manhattan_accuracy_threshold
  - manhattan_f1
  - manhattan_f1_threshold
  - manhattan_precision
  - manhattan_recall
  - manhattan_ap
  - euclidean_accuracy
  - euclidean_accuracy_threshold
  - euclidean_f1
  - euclidean_f1_threshold
  - euclidean_precision
  - euclidean_recall
  - euclidean_ap
  - max_accuracy
  - max_accuracy_threshold
  - max_f1
  - max_f1_threshold
  - max_precision
  - max_recall
  - max_ap
widget:
  - source_sentence: A man is walking past a large sign that says E.S.E. Electronics.
    sentences:
      - a child opens a present on his birthday
      - The man works at E.S.E Electronics.
      - The soccer team in blue plays soccer.
  - source_sentence: This child is on the library steps.
    sentences:
      - A mother dog checking up on her baby puppy.
      - A guy bites into a freshly opened marshmallow chick
      - The child is on the steps inside the library.
  - source_sentence: Two men are standing in a boat.
    sentences:
      - People are watching the flowers blossom
      - The couple is married.
      - A few men are fishing on a boat.
  - source_sentence: >-
      Four men playing drums in very orange lighting while one of them is also
      drinking something out of a bottle.
    sentences:
      - four men play drums
      - The man puts something on the other mans head.
      - The dogs are in the backyard.
  - source_sentence: >-
      First Lady Laura Bush at podium, in front of seated audience, at the White
      House Conference on Global Literacy.
    sentences:
      - Some people are exercising outside.
      - The former First Lady is at the podium for a conference.
      - This person is going to the waterfall
pipeline_tag: sentence-similarity
model-index:
  - name: SentenceTransformer based on microsoft/deberta-v3-small
    results:
      - task:
          type: binary-classification
          name: Binary Classification
        dataset:
          name: Unknown
          type: unknown
        metrics:
          - type: cosine_accuracy
            value: 0.6651071536371869
            name: Cosine Accuracy
          - type: cosine_accuracy_threshold
            value: 0.687929630279541
            name: Cosine Accuracy Threshold
          - type: cosine_f1
            value: 0.7077349458301839
            name: Cosine F1
          - type: cosine_f1_threshold
            value: 0.6304811239242554
            name: Cosine F1 Threshold
          - type: cosine_precision
            value: 0.6222862206468763
            name: Cosine Precision
          - type: cosine_recall
            value: 0.8203855140186916
            name: Cosine Recall
          - type: cosine_ap
            value: 0.7058220689813709
            name: Cosine Ap
          - type: dot_accuracy
            value: 0.6313009357078176
            name: Dot Accuracy
          - type: dot_accuracy_threshold
            value: 135.98495483398438
            name: Dot Accuracy Threshold
          - type: dot_f1
            value: 0.6997334569475027
            name: Dot F1
          - type: dot_f1_threshold
            value: 115.54609680175781
            name: Dot F1 Threshold
          - type: dot_precision
            value: 0.5800192122958694
            name: Dot Precision
          - type: dot_recall
            value: 0.8817172897196262
            name: Dot Recall
          - type: dot_ap
            value: 0.6554755795160082
            name: Dot Ap
          - type: manhattan_accuracy
            value: 0.6708421370359191
            name: Manhattan Accuracy
          - type: manhattan_accuracy_threshold
            value: 219.32388305664062
            name: Manhattan Accuracy Threshold
          - type: manhattan_f1
            value: 0.7119951778179626
            name: Manhattan F1
          - type: manhattan_f1_threshold
            value: 262.314697265625
            name: Manhattan F1 Threshold
          - type: manhattan_precision
            value: 0.6062410182714022
            name: Manhattan Precision
          - type: manhattan_recall
            value: 0.8624415887850467
            name: Manhattan Recall
          - type: manhattan_ap
            value: 0.7135236162968746
            name: Manhattan Ap
          - type: euclidean_accuracy
            value: 0.6652580742529429
            name: Euclidean Accuracy
          - type: euclidean_accuracy_threshold
            value: 11.506816864013672
            name: Euclidean Accuracy Threshold
          - type: euclidean_f1
            value: 0.7080090384132564
            name: Euclidean F1
          - type: euclidean_f1_threshold
            value: 12.478536605834961
            name: Euclidean F1 Threshold
          - type: euclidean_precision
            value: 0.6208718626155878
            name: Euclidean Precision
          - type: euclidean_recall
            value: 0.8235981308411215
            name: Euclidean Recall
          - type: euclidean_ap
            value: 0.7090362803652147
            name: Euclidean Ap
          - type: max_accuracy
            value: 0.6708421370359191
            name: Max Accuracy
          - type: max_accuracy_threshold
            value: 219.32388305664062
            name: Max Accuracy Threshold
          - type: max_f1
            value: 0.7119951778179626
            name: Max F1
          - type: max_f1_threshold
            value: 262.314697265625
            name: Max F1 Threshold
          - type: max_precision
            value: 0.6222862206468763
            name: Max Precision
          - type: max_recall
            value: 0.8817172897196262
            name: Max Recall
          - type: max_ap
            value: 0.7135236162968746
            name: Max Ap

SentenceTransformer based on microsoft/deberta-v3-small

This is a sentence-transformers model finetuned from microsoft/deberta-v3-small on the stanfordnlp/snli dataset. 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: microsoft/deberta-v3-small
Maximum Sequence Length: 512 tokens
Output Dimensionality: 768 tokens
Similarity Function: Cosine Similarity
Training Dataset:
- stanfordnlp/snli
Language: en

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: DebertaV2Model 
  (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})
)

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("bobox/DeBERTaV3-small-ST-AdaptiveLayer-Norm-ep2")
# Run inference
sentences = [
    'First Lady Laura Bush at podium, in front of seated audience, at the White House Conference on Global Literacy.',
    'The former First Lady is at the podium for a conference.',
    'This person is going to the waterfall',
]
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	0.6651
cosine_accuracy_threshold	0.6879
cosine_f1	0.7077
cosine_f1_threshold	0.6305
cosine_precision	0.6223
cosine_recall	0.8204
cosine_ap	0.7058
dot_accuracy	0.6313
dot_accuracy_threshold	135.985
dot_f1	0.6997
dot_f1_threshold	115.5461
dot_precision	0.58
dot_recall	0.8817
dot_ap	0.6555
manhattan_accuracy	0.6708
manhattan_accuracy_threshold	219.3239
manhattan_f1	0.712
manhattan_f1_threshold	262.3147
manhattan_precision	0.6062
manhattan_recall	0.8624
manhattan_ap	0.7135
euclidean_accuracy	0.6653
euclidean_accuracy_threshold	11.5068
euclidean_f1	0.708
euclidean_f1_threshold	12.4785
euclidean_precision	0.6209
euclidean_recall	0.8236
euclidean_ap	0.709
max_accuracy	0.6708
max_accuracy_threshold	219.3239
max_f1	0.712
max_f1_threshold	262.3147
max_precision	0.6223
max_recall	0.8817
max_ap	0.7135

Training Details

Training Dataset

stanfordnlp/snli

Dataset: stanfordnlp/snli at cdb5c3d
Size: 67,190 training samples
Columns: sentence1, sentence2, and label
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 label
type string string int
details
min: 4 tokens
mean: 21.19 tokens
max: 133 tokens

min: 4 tokens
mean: 11.77 tokens
max: 49 tokens

0: 100.00%

	sentence1	sentence2	label
type	string	string	int
details	min: 4 tokens mean: 21.19 tokens max: 133 tokens	min: 4 tokens mean: 11.77 tokens max: 49 tokens	0: 100.00%

Samples:

sentence1	sentence2	label
`Without a placebo group, we still won't know if any of the treatments are better than nothing and therefore worth giving.`	`It is necessary to use a controlled method to ensure the treatments are worthwhile.`	`0`
`It was conducted in silence.`	`It was done silently.`	`0`
`oh Lewisville any decent food in your cafeteria up there`	`Is there any decent food in your cafeteria up there in Lewisville?`	`0`

Loss: AdaptiveLayerLoss with these parameters:

{
    "loss": "MultipleNegativesRankingLoss",
    "n_layers_per_step": 1,
    "last_layer_weight": 1,
    "prior_layers_weight": 0.05,
    "kl_div_weight": 2,
    "kl_temperature": 0.9
}

Evaluation Dataset

stanfordnlp/snli

Dataset: stanfordnlp/snli at cdb5c3d
Size: 6,626 evaluation samples
Columns: premise, hypothesis, and label
Approximate statistics based on the first 1000 samples:
premise hypothesis label
type string string int
details
min: 6 tokens
mean: 17.28 tokens
max: 59 tokens

min: 4 tokens
mean: 10.53 tokens
max: 32 tokens

0: ~48.70%
1: ~51.30%

	premise	hypothesis	label
type	string	string	int
details	min: 6 tokens mean: 17.28 tokens max: 59 tokens	min: 4 tokens mean: 10.53 tokens max: 32 tokens	0: ~48.70% 1: ~51.30%

Samples:

premise	hypothesis	label
`This church choir sings to the masses as they sing joyous songs from the book at a church.`	`The church has cracks in the ceiling.`	`0`
`This church choir sings to the masses as they sing joyous songs from the book at a church.`	`The church is filled with song.`	`1`
`A woman with a green headscarf, blue shirt and a very big grin.`	`The woman is young.`	`0`

Loss: AdaptiveLayerLoss with these parameters:

{
    "loss": "MultipleNegativesRankingLoss",
    "n_layers_per_step": 1,
    "last_layer_weight": 1,
    "prior_layers_weight": 0.05,
    "kl_div_weight": 2,
    "kl_temperature": 0.9
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 45
per_device_eval_batch_size: 22
learning_rate: 3e-06
weight_decay: 1e-09
num_train_epochs: 2
lr_scheduler_type: cosine
warmup_ratio: 0.5
save_safetensors: False
fp16: True
push_to_hub: True
hub_model_id: bobox/DeBERTaV3-small-ST-AdaptiveLayer-Norm-ep2-checkpoints
hub_strategy: checkpoint
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 45
per_device_eval_batch_size: 22
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 1
eval_accumulation_steps: None
learning_rate: 3e-06
weight_decay: 1e-09
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1.0
num_train_epochs: 2
max_steps: -1
lr_scheduler_type: cosine
lr_scheduler_kwargs: {}
warmup_ratio: 0.5
warmup_steps: 0
log_level: passive
log_level_replica: warning
log_on_each_node: True
logging_nan_inf_filter: True
save_safetensors: False
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: 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: True
resume_from_checkpoint: None
hub_model_id: bobox/DeBERTaV3-small-ST-AdaptiveLayer-Norm-ep2-checkpoints
hub_strategy: checkpoint
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
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	loss	max_ap
0.1004	150	4.5827	-	-
0.2001	299	-	3.5735	0.6133
0.2008	300	3.5451	-	-
0.3012	450	2.9066	-	-
0.4003	598	-	2.8785	0.6561
0.4016	600	2.5141	-	-
0.5020	750	2.0248	-	-
0.6004	897	-	2.1300	0.6917
0.6024	900	1.6782	-	-
0.7028	1050	1.4187	-	-
0.8005	1196	-	1.7111	0.7051
0.8032	1200	1.2446	-	-
0.9036	1350	1.1078	-	-
1.0007	1495	-	1.4859	0.7108
1.0040	1500	0.9827	-	-
1.1044	1650	0.9335	-	-
1.2008	1794	-	1.3516	0.7121
1.2048	1800	0.8595	-	-
1.3052	1950	0.8362	-	-
1.4009	2093	-	1.2659	0.7147
1.4056	2100	0.8167	-	-
1.5060	2250	0.7695	-	-
1.6011	2392	-	1.2218	0.7135
1.6064	2400	0.7544	-	-
1.7068	2550	0.7625	-	-
1.8012	2691	-	1.2073	0.7135
1.8072	2700	0.7366	-	-
1.9076	2850	0.7348	-	-

Framework Versions

Python: 3.10.13
Sentence Transformers: 3.0.1
Transformers: 4.41.2
PyTorch: 2.1.2
Accelerate: 0.30.1
Datasets: 2.19.2
Tokenizers: 0.19.1

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",
}

AdaptiveLayerLoss

@misc{li20242d,
    title={2D Matryoshka Sentence Embeddings}, 
    author={Xianming Li and Zongxi Li and Jing Li and Haoran Xie and Qing Li},
    year={2024},
    eprint={2402.14776},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}

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}
}