langcache-embed-v3 / README.md

radoslavralev

Add new SentenceTransformer model

9fcad6e verified about 15 hours ago

preview code

raw

history blame contribute delete

37.6 kB

metadata

language:
  - en
license: apache-2.0
tags:
  - biencoder
  - sentence-transformers
  - text-classification
  - sentence-pair-classification
  - semantic-similarity
  - semantic-search
  - retrieval
  - reranking
  - generated_from_trainer
  - dataset_size:9233417
  - loss:ArcFaceInBatchLoss
base_model: answerdotai/ModernBERT-base
widget:
  - source_sentence: >-
      Hayley Vaughan portrayed Ripa on the ABC daytime soap opera , `` All My
      Children `` , between 1990 and 2002 .
    sentences:
      - >-
        Traxxpad is a music application for Sony 's PlayStation Portable
        published by Definitive Studios and developed by Eidos Interactive .
      - >-
        Between 1990 and 2002 , Hayley Vaughan Ripa portrayed in the ABC soap
        opera `` All My Children `` .
      - >-
        Between 1990 and 2002 , Ripa Hayley portrayed Vaughan in the ABC soap
        opera `` All My Children `` .
  - source_sentence: >-
      Olivella monilifera is a species of dwarf sea snail , small gastropod
      mollusk in the family Olivellidae , the marine olives .
    sentences:
      - >-
        Olivella monilifera is a species of the dwarf - sea snail , small
        gastropod mollusk in the Olivellidae family , the marine olives .
      - >-
        He was cut by the Browns after being signed by the Bills in 2013 . He
        was later released .
      - >-
        Olivella monilifera is a kind of sea snail , marine gastropod mollusk in
        the Olivellidae family , the dwarf olives .
  - source_sentence: >-
      Hayashi said that Mackey `` is a sort of `` of the original model for
      Tenchi .
    sentences:
      - >-
        In the summer of 2009 , Ellick shot a documentary about Malala Yousafzai
        .
      - >-
        Hayashi said that Mackey is `` sort of `` the original model for Tenchi
        .
      - >-
        Mackey said that Hayashi is `` sort of `` the original model for Tenchi
        .
  - source_sentence: >-
      Much of the film was shot on location in Los Angeles and in nearby Burbank
      and Glendale .
    sentences:
      - >-
        Much of the film was shot on location in Los Angeles and in nearby
        Burbank and Glendale .
      - >-
        Much of the film was shot on site in Burbank and Glendale and in the
        nearby Los Angeles .
      - >-
        Traxxpad is a music application for the Sony PlayStation Portable
        developed by the Definitive Studios and published by Eidos Interactive .
  - source_sentence: >-
      According to him , the earth is the carrier of his artistic work , which
      is only integrated into the creative process by minimal changes .
    sentences:
      - National players are Bold players .
      - >-
        According to him , earth is the carrier of his artistic work being
        integrated into the creative process only by minimal changes .
      - >-
        According to him , earth is the carrier of his creative work being
        integrated into the artistic process only by minimal changes .
datasets:
  - redis/langcache-sentencepairs-v2
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - cosine_accuracy@1
  - cosine_precision@1
  - cosine_recall@1
  - cosine_ndcg@10
  - cosine_mrr@1
  - cosine_map@100
model-index:
  - name: Redis fine-tuned BiEncoder model for semantic caching on LangCache
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: test
          type: test
        metrics:
          - type: cosine_accuracy@1
            value: 0.6032809198037179
            name: Cosine Accuracy@1
          - type: cosine_precision@1
            value: 0.6032809198037179
            name: Cosine Precision@1
          - type: cosine_recall@1
            value: 0.585771482488324
            name: Cosine Recall@1
          - type: cosine_ndcg@10
            value: 0.7747479314468421
            name: Cosine Ndcg@10
          - type: cosine_mrr@1
            value: 0.6032809198037179
            name: Cosine Mrr@1
          - type: cosine_map@100
            value: 0.7280398908979986
            name: Cosine Map@100

Redis fine-tuned BiEncoder model for semantic caching on LangCache

This is a sentence-transformers model finetuned from answerdotai/ModernBERT-base on the LangCache Sentence Pairs (all) dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for sentence pair similarity.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: answerdotai/ModernBERT-base
Maximum Sequence Length: 100 tokens
Output Dimensionality: 768 dimensions
Similarity Function: Cosine Similarity
Training Dataset:
- LangCache Sentence Pairs (all)
Language: en
License: apache-2.0

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': 100, 'do_lower_case': False, 'architecture': 'ModernBertModel'})
  (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("redis/langcache-embed-v3")
# Run inference
sentences = [
    'According to him , the earth is the carrier of his artistic work , which is only integrated into the creative process by minimal changes .',
    'According to him , earth is the carrier of his artistic work being integrated into the creative process only by minimal changes .',
    'According to him , earth is the carrier of his creative work being integrated into the artistic process only by minimal changes .',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.9180, 0.4531],
#         [0.9180, 1.0000, 0.4746],
#         [0.4531, 0.4746, 1.0000]], dtype=torch.bfloat16)

Evaluation

Metrics

Information Retrieval

Dataset: test
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.6033
cosine_precision@1	0.6033
cosine_recall@1	0.5858
cosine_ndcg@10	0.7747
cosine_mrr@1	0.6033
cosine_map@100	0.728

Training Details

Training Dataset

LangCache Sentence Pairs (all)

Dataset: LangCache Sentence Pairs (all)
Size: 126,938 training samples
Columns: anchor, positive, and negative

Approximate statistics based on the first 1000 samples:

	anchor	positive	negative
type	string	string	string
details	min: 8 tokens mean: 27.27 tokens max: 49 tokens	min: 8 tokens mean: 27.27 tokens max: 48 tokens	min: 7 tokens mean: 26.54 tokens max: 61 tokens

Samples:

anchor	positive	negative
`The newer Punts are still very much in existence today and race in the same fleets as the older boats .`	`The newer punts are still very much in existence today and run in the same fleets as the older boats .`	`how can I get financial freedom as soon as possible?`
`The newer punts are still very much in existence today and run in the same fleets as the older boats .`	`The newer Punts are still very much in existence today and race in the same fleets as the older boats .`	`The older Punts are still very much in existence today and race in the same fleets as the newer boats .`
`Turner Valley , was at the Turner Valley Bar N Ranch Airport , southwest of the Turner Valley Bar N Ranch , Alberta , Canada .`	`Turner Valley , , was located at Turner Valley Bar N Ranch Airport , southwest of Turner Valley Bar N Ranch , Alberta , Canada .`	`Turner Valley Bar N Ranch Airport , , was located at Turner Valley Bar N Ranch , southwest of Turner Valley , Alberta , Canada .`

Loss: losses.ArcFaceInBatchLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim",
    "gather_across_devices": false
}

Evaluation Dataset

LangCache Sentence Pairs (all)

Dataset: LangCache Sentence Pairs (all)
Size: 126,938 evaluation samples
Columns: anchor, positive, and negative

Approximate statistics based on the first 1000 samples:

	anchor	positive	negative
type	string	string	string
details	min: 8 tokens mean: 27.27 tokens max: 49 tokens	min: 8 tokens mean: 27.27 tokens max: 48 tokens	min: 7 tokens mean: 26.54 tokens max: 61 tokens

Samples:

anchor	positive	negative
`The newer Punts are still very much in existence today and race in the same fleets as the older boats .`	`The newer punts are still very much in existence today and run in the same fleets as the older boats .`	`how can I get financial freedom as soon as possible?`
`The newer punts are still very much in existence today and run in the same fleets as the older boats .`	`The newer Punts are still very much in existence today and race in the same fleets as the older boats .`	`The older Punts are still very much in existence today and race in the same fleets as the newer boats .`
`Turner Valley , was at the Turner Valley Bar N Ranch Airport , southwest of the Turner Valley Bar N Ranch , Alberta , Canada .`	`Turner Valley , , was located at Turner Valley Bar N Ranch Airport , southwest of Turner Valley Bar N Ranch , Alberta , Canada .`	`Turner Valley Bar N Ranch Airport , , was located at Turner Valley Bar N Ranch , southwest of Turner Valley , Alberta , Canada .`

Loss: losses.ArcFaceInBatchLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim",
    "gather_across_devices": false
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 128
per_device_eval_batch_size: 128
weight_decay: 0.001
adam_beta2: 0.98
adam_epsilon: 1e-06
max_steps: 100000
warmup_ratio: 0.1
load_best_model_at_end: True
optim: stable_adamw
ddp_find_unused_parameters: False
push_to_hub: True
hub_model_id: redis/langcache-embed-v3
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: 128
per_device_eval_batch_size: 128
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: 0.001
adam_beta1: 0.9
adam_beta2: 0.98
adam_epsilon: 1e-06
max_grad_norm: 1.0
num_train_epochs: 3.0
max_steps: 100000
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: 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}
parallelism_config: None
deepspeed: None
label_smoothing_factor: 0.0
optim: stable_adamw
optim_args: None
adafactor: False
group_by_length: False
length_column_name: length
ddp_find_unused_parameters: False
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: redis/langcache-embed-v3
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: False
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: False
prompts: None
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Click to expand

Epoch	Step	Training Loss	Validation Loss	test_cosine_ndcg@10
-1	-1	-	-	0.5952
0.0069	500	3.4812	0.6932	0.6810
0.0139	1000	0.6045	0.4804	0.7354
0.0208	1500	0.3127	0.4128	0.7437
0.0277	2000	0.2424	0.4077	0.7440
0.0347	2500	0.2027	0.3707	0.7501
0.0416	3000	0.1752	0.3453	0.7551
0.0485	3500	0.1622	0.3380	0.7540
0.0555	4000	0.1466	0.3185	0.7583
0.0624	4500	0.1392	0.3092	0.7588
0.0693	5000	0.1342	0.3054	0.7566
0.0762	5500	0.1291	0.2960	0.7582
0.0832	6000	0.1291	0.2856	0.7616
0.0901	6500	0.1199	0.2803	0.7624
0.0970	7000	0.1171	0.2692	0.7648
0.1040	7500	0.1097	0.2811	0.7629
0.1109	8000	0.1089	0.2901	0.7621
0.1178	8500	0.1088	0.2986	0.7568
0.1248	9000	0.109	0.2806	0.7628
0.1317	9500	0.1046	0.3050	0.7587
0.1386	10000	0.1035	0.2925	0.7596
0.1456	10500	0.1041	0.2940	0.7573
0.1525	11000	0.1023	0.2790	0.7632
0.1594	11500	0.0992	0.3293	0.7542
0.1664	12000	0.0996	0.2876	0.7570
0.1733	12500	0.0949	0.2881	0.7591
0.1802	13000	0.0921	0.2861	0.7598
0.1871	13500	0.0912	0.2763	0.7632
0.1941	14000	0.0912	0.2785	0.7643
0.2010	14500	0.0909	0.3198	0.7629
0.2079	15000	0.0911	0.3015	0.7575
0.2149	15500	0.0861	0.3029	0.7597
0.2218	16000	0.0857	0.3271	0.7568
0.2287	16500	0.0843	0.2579	0.7645
0.2357	17000	0.085	0.2923	0.7625
0.2426	17500	0.0846	0.3241	0.7598
0.2495	18000	0.083	0.3128	0.7616
0.2565	18500	0.0794	0.2926	0.7611
0.2634	19000	0.0806	0.2665	0.7640
0.2703	19500	0.0782	0.2963	0.7615
0.2773	20000	0.0786	0.2771	0.7611
0.2842	20500	0.0761	0.2853	0.7623
0.2911	21000	0.0752	0.2782	0.7626
0.2980	21500	0.0777	0.2680	0.7612
0.3050	22000	0.0782	0.2731	0.7636
0.3119	22500	0.0785	0.2627	0.7627
0.3188	23000	0.0741	0.2714	0.7613
0.3258	23500	0.0741	0.2713	0.7661
0.3327	24000	0.072	0.2630	0.7636
0.3396	24500	0.0739	0.2839	0.7648
0.3466	25000	0.07	0.2860	0.7634
0.3535	25500	0.0715	0.2612	0.7666
0.3604	26000	0.0711	0.2531	0.7671
0.3674	26500	0.0701	0.2682	0.7638
0.3743	27000	0.0733	0.2708	0.7635
0.3812	27500	0.0705	0.2873	0.7636
0.3882	28000	0.0663	0.2831	0.7647
0.3951	28500	0.0678	0.2825	0.7643
0.4020	29000	0.0691	0.2733	0.7654
0.4089	29500	0.0696	0.2831	0.7621
0.4159	30000	0.0708	0.2893	0.7643
0.4228	30500	0.0663	0.2758	0.7653
0.4297	31000	0.064	0.2589	0.7666
0.4367	31500	0.0636	0.2491	0.7681
0.4436	32000	0.0644	0.2601	0.7650
0.4505	32500	0.0655	0.2611	0.7668
0.4575	33000	0.0643	0.2597	0.7664
0.4644	33500	0.066	0.2696	0.7677
0.4713	34000	0.0664	0.2489	0.7690
0.4783	34500	0.0654	0.2644	0.7649
0.4852	35000	0.0653	0.2704	0.7665
0.4921	35500	0.0657	0.2578	0.7689
0.4991	36000	0.0634	0.2629	0.7669
0.5060	36500	0.0609	0.2631	0.7663
0.5129	37000	0.0646	0.2586	0.7667
0.5198	37500	0.0634	0.2572	0.7657
0.5268	38000	0.0607	0.2624	0.7664
0.5337	38500	0.0621	0.2622	0.7668
0.5406	39000	0.0614	0.2562	0.7676
0.5476	39500	0.0621	0.2560	0.7673
0.5545	40000	0.0608	0.2506	0.7684
0.5614	40500	0.0621	0.2718	0.7666
0.5684	41000	0.0598	0.2599	0.7700
0.5753	41500	0.06	0.2706	0.7687
0.5822	42000	0.0618	0.2635	0.7694
0.5892	42500	0.0604	0.2743	0.7660
0.5961	43000	0.0576	0.2733	0.7661
0.6030	43500	0.0597	0.2644	0.7712
0.6100	44000	0.0592	0.2516	0.7694
0.6169	44500	0.0599	0.2461	0.7688
0.6238	45000	0.056	0.2438	0.7686
0.6307	45500	0.0573	0.2513	0.7703
0.6377	46000	0.0571	0.2526	0.7694
0.6446	46500	0.0573	0.2529	0.7702
0.6515	47000	0.0553	0.2529	0.7694
0.6585	47500	0.0541	0.2518	0.7707
0.6654	48000	0.0561	0.2471	0.7725
0.6723	48500	0.0558	0.2440	0.7710
0.6793	49000	0.0555	0.2556	0.7691
0.6862	49500	0.056	0.2479	0.7721
0.6931	50000	0.0564	0.2463	0.7723
0.7001	50500	0.0539	0.2561	0.7728
0.7070	51000	0.0526	0.2416	0.7725
0.7139	51500	0.0561	0.2501	0.7723
0.7209	52000	0.0545	0.2316	0.7732
0.7278	52500	0.0545	0.2352	0.7739
0.7347	53000	0.05	0.2278	0.7734
0.7416	53500	0.0515	0.2308	0.7730
0.7486	54000	0.0528	0.2524	0.7727
0.7555	54500	0.0509	0.2645	0.7717
0.7624	55000	0.0514	0.2659	0.7708
0.7694	55500	0.0503	0.2570	0.7725
0.7763	56000	0.0538	0.2524	0.7724
0.7832	56500	0.0477	0.2537	0.7719
0.7902	57000	0.0514	0.2333	0.7733
0.7971	57500	0.05	0.2420	0.7722
0.8040	58000	0.0518	0.2342	0.7734
0.8110	58500	0.0508	0.2402	0.7730
0.8179	59000	0.0474	0.2477	0.7711
0.8248	59500	0.0493	0.2465	0.7723
0.8318	60000	0.0492	0.2448	0.7731
0.8387	60500	0.0496	0.2498	0.7733
0.8456	61000	0.0479	0.2505	0.7721
0.8525	61500	0.0445	0.2449	0.7745
0.8595	62000	0.0477	0.2507	0.7748
0.8664	62500	0.0491	0.2551	0.7716
0.8733	63000	0.0474	0.2451	0.7743
0.8803	63500	0.0452	0.2464	0.7741
0.8872	64000	0.0482	0.2412	0.7742
0.8941	64500	0.0483	0.2444	0.7736
0.9011	65000	0.0485	0.2456	0.7724
0.9080	65500	0.045	0.2493	0.7730
0.9149	66000	0.0496	0.2499	0.7721
0.9219	66500	0.0461	0.2474	0.7748
0.9288	67000	0.0465	0.2432	0.7743
0.9357	67500	0.0477	0.2432	0.7729
0.9427	68000	0.0425	0.2491	0.7740
0.9496	68500	0.0452	0.2445	0.7736
0.9565	69000	0.046	0.2397	0.7742
0.9634	69500	0.0449	0.2539	0.7731
0.9704	70000	0.0462	0.2446	0.7745
0.9773	70500	0.0435	0.2385	0.7742
0.9842	71000	0.0469	0.2334	0.7750
0.9912	71500	0.0447	0.2312	0.7745
0.9981	72000	0.0465	0.2361	0.7737
1.0050	72500	0.0341	0.2359	0.7728
1.0120	73000	0.03	0.2405	0.7727
1.0189	73500	0.029	0.2241	0.7724
1.0258	74000	0.0284	0.2297	0.7740
1.0328	74500	0.0273	0.2317	0.7735
1.0397	75000	0.0291	0.2352	0.7727
1.0466	75500	0.0286	0.2439	0.7724
1.0536	76000	0.0268	0.2336	0.7732
1.0605	76500	0.0276	0.2298	0.7728
1.0674	77000	0.0279	0.2268	0.7726
1.0743	77500	0.0283	0.2206	0.7738
1.0813	78000	0.0277	0.2263	0.7733
1.0882	78500	0.0285	0.2228	0.7740
1.0951	79000	0.0283	0.2250	0.7729
1.1021	79500	0.0276	0.2200	0.7730
1.1090	80000	0.0276	0.2221	0.7739
1.1159	80500	0.0268	0.2279	0.7730
1.1229	81000	0.0274	0.2302	0.7733
1.1298	81500	0.0281	0.2286	0.7736
1.1367	82000	0.0267	0.2306	0.7733
1.1437	82500	0.0267	0.2348	0.7731
1.1506	83000	0.0278	0.2301	0.7729
1.1575	83500	0.028	0.2240	0.7738
1.1645	84000	0.0282	0.2196	0.7744
1.1714	84500	0.0264	0.2241	0.7737
1.1783	85000	0.0258	0.2252	0.7736
1.1852	85500	0.027	0.2196	0.7742
1.1922	86000	0.0256	0.2189	0.7739
1.1991	86500	0.0259	0.2174	0.7749
1.2060	87000	0.0262	0.2209	0.7751
1.2130	87500	0.0265	0.2202	0.7739
1.2199	88000	0.025	0.2228	0.7737
1.2268	88500	0.0266	0.2233	0.7739
1.2338	89000	0.0261	0.2255	0.7736
1.2407	89500	0.0271	0.2219	0.7746
1.2476	90000	0.0256	0.2185	0.7757
1.2546	90500	0.0257	0.2190	0.7758
1.2615	91000	0.0239	0.2210	0.7750
1.2684	91500	0.0252	0.2236	0.7743
1.2754	92000	0.0245	0.2238	0.7743
1.2823	92500	0.0267	0.2234	0.7747
1.2892	93000	0.025	0.2235	0.7746
1.2961	93500	0.0246	0.2298	0.7740
1.3031	94000	0.0266	0.2239	0.7744
1.3100	94500	0.0256	0.2231	0.7740
1.3169	95000	0.0265	0.2214	0.7744
1.3239	95500	0.0253	0.2221	0.7747
1.3308	96000	0.0251	0.2222	0.7742
1.3377	96500	0.0244	0.2211	0.7748
1.3447	97000	0.0249	0.2216	0.7750
1.3516	97500	0.0257	0.2215	0.7745
1.3585	98000	0.0263	0.2215	0.7749
1.3655	98500	0.0258	0.2209	0.7749
1.3724	99000	0.0255	0.2212	0.7748
1.3793	99500	0.0252	0.2213	0.7751
1.3863	100000	0.0257	0.2213	0.7747

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.12.3
Sentence Transformers: 5.1.0
Transformers: 4.56.0
PyTorch: 2.8.0+cu128
Accelerate: 1.10.1
Datasets: 4.0.0
Tokenizers: 0.22.0

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",
}