mrm8488/mxbai-embed-large-v1-ft-webinstruct

SentenceTransformer based on mixedbread-ai/mxbai-embed-large-v1

This is a sentence-transformers model finetuned from mixedbread-ai/mxbai-embed-large-v1 on the mathstackexchange, socratic and stackexchange datasets. It maps sentences & paragraphs to a 1024-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: mixedbread-ai/mxbai-embed-large-v1
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 1024 tokens
• Similarity Function: Cosine Similarity
• Training Datasets:
  • mathstackexchange
  • socratic
  • stackexchange

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: BertModel 
  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, '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("mrm8488/mxbai-embed-large-v1-ft-webinstruct")
# Run inference
sentences = [
    "What should I do if I'm not satisfied with the answers to a question for which I've offered a bounty?\n\nIn my case, I've put a bounty on a question, but the two responses I received don't address the issue effectively. I requested the original poster (OP) to provide an answer so I could reward them for the interesting question, but they haven't done so. \n\nAre there any acceptable actions in this scenario? For instance, can I post my own non-answer, award myself the bounty, and then start a new bounty on a different question? Or are there alternative suggestions?",
    "If all the provided answers do not adequately address your question, it's advisable to let the bounty expire. The system will handle the distribution of the bounty in such situations according to predefined rules.\n\nBounties carry a risk, as there is no guarantee that you will receive a satisfactory answer, even with the incentive. It's important to understand that you cannot reclaim your bounty once it's been offered. \n\nInstead of posting a non-answer, you might consider editing and clarifying your original question to attract better responses, or seeking assistance from the community through comments or chat. If needed, you can also start a new bounty on a different question, but ensure that it's clear and well-defined to increase the likelihood of receiving quality answers.",
    'The issue you\'re experiencing with your 40kHz crystal oscillator might be due to insufficient drive strength and an incorrect load capacitance. Here are two potential causes and solutions:\n\n1. High Series Resistance: The 150 kΩ series resistance in your circuit might be too high, which results in a low drive strength for the crystal. This can lead to a reduced overall loop gain and prevents the oscillator from properly starting. To resolve this, try using a lower resistance value as recommended in the crystal\'s datasheet.\n\n2. Incorrect Load Capacitance: Ensure that the 33 pF load capacitors you\'re using are compatible with your crystal. Some low-power "watch" crystals require only 5-10 pF load capacitors. Always refer to the crystal\'s datasheet to verify the appropriate load capacitance value.\n\nIn summary, carefully review the crystal\'s datasheet to determine the correct series resistance and load capacitance values, and make the necessary adjustments to your circuit. By doing so, you should be able to resolve the issue and get your oscillator functioning properly.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

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

Evaluation

Metrics

Semantic Similarity

• Dataset: sts-dev
• Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.7435
spearman_cosine	0.7806
pearson_manhattan	0.7437
spearman_manhattan	0.749
pearson_euclidean	0.7441
spearman_euclidean	0.7495
pearson_dot	0.6964
spearman_dot	0.7078
pearson_max	0.7441
spearman_max	0.7806

Training Details

Training Datasets

mathstackexchange

• Dataset: mathstackexchange
• Size: 1,484,629 training samples
• Columns: anchor and positive
• Approximate statistics based on the first 1000 samples:

  	anchor	positive
  type	string	string
  details	min: 10 tokens mean: 90.61 tokens max: 512 tokens	min: 9 tokens mean: 307.68 tokens max: 512 tokens

• Samples:

  anchor	positive
  Suppose $A$ is a normal subgroup of a group $B$, and the quotient group $B/A$ is cyclic with infinite order. How can we demonstrate, using the correspondence theorem, that for every positive integer $k$, $B$ has a normal subgroup of index $k$?	The correspondence theorem relates subgroups of the quotient group $B/A$ to subgroups of $B$ containing $A$. Since $B/A$ is isomorphic to the infinite cyclic group $\mathbb{Z}$, it has subgroups of every finite index. To find a normal subgroup of $B$ with index $k$, we can follow these steps: 1. Identify a subgroup $M/A$ of $B/A$ with index $k$. This is possible since $\mathbb{Z}$ has subgroups of index $k$ for any positive integer $k$ (for instance, the subgroup generated by $k$ times the generator of $\mathbb{Z}$). 2. By the correspondence theorem, there exists an intermediate subgroup $M$ such that $A \leq M \leq B$ with $M/A \cong M/A$. 3. Now, consider the index of $M$ in $B$: $[B:M] = [B/A : M/A] = k$, as desired. Thus, using the correspondence theorem and exploiting the properties of $\mathbb{Z}$, we can construct a normal subgroup of $B$ with index $k$ for any positive integer $k$.
  If $z$ is a complex number and $a$ is a real number, can we say $	az
  What is the remainder when $x^{2007}$ is divided by $x^2-x+1$?	To find the remainder when $x^{2007}$ is divided by $x^2-x+1$, we can use polynomial long division or synthetic division. Alternatively, we can utilize the properties of the polynomial $x^2-x+1$. Since $x^2-x+1$ is a factor of $x^3+1$, we have $x^3 \equiv -1 \pmod{x^2-x+1}$. Therefore, we can express $x^{2007}$ as $x^{3\cdot669}$, and thus: $$x^{2007} = (x^3)^{669} \equiv (-1)^{669} \pmod{x^2-x+1}$$ Now, since $669$ is odd, $(-1)^{669} = -1$. Hence, the remainder is $-1$. Alternatively, we can perform polynomial long division to obtain: $$\frac{x^{2007}}{x^2-x+1} = a(x) - \frac{x+1}{x^2-x+1}$$ where $a(x)$ is the quotient polynomial. Since we only care about the remainder, we have: $$x^{2007} \equiv -1 \pmod{x^2-x+1}$$

• Loss: MultipleNegativesRankingLoss with these parameters:

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

socratic

• Dataset: socratic
• Size: 533,383 training samples
• Columns: anchor and positive
• Approximate statistics based on the first 1000 samples:

  	anchor	positive
  type	string	string
  details	min: 8 tokens mean: 30.75 tokens max: 167 tokens	min: 3 tokens mean: 207.41 tokens max: 512 tokens

• Samples:

  anchor	positive
  What is an activated complex?	The activated complex is formed when the reactants collide with each other and begin to rearrange their atoms and bonds to form the products. This process requires energy, which is why the activated complex has a higher energy than the reactants. The energy required to reach the activated complex is called the activation energy. Once the activated complex is formed, it can either decompose back into the reactants or proceed to form the products. The probability of the activated complex decomposing back into the reactants is determined by the activation energy. If the activation energy is high, then the activated complex is more likely to decompose back into the reactants. If the activation energy is low, then the activated complex is more likely to proceed to form the products. The activated complex is a key concept in understanding chemical reactions. It helps to explain why some reactions occur quickly and others occur slowly. It also helps to explain why some reactions require a catalyst to occur. #### An activated complex is a high-energy, unstable intermediate state that forms during a chemical reaction. It is the transition state between the reactants and the products. The activated complex has a higher energy than both the reactants and the products, and it represents the maximum energy that must be overcome for the reaction to occur.
  Why does gravity cause planets to be round?	The gravitational force of a planet pulls matter towards its center. This force is strongest at the center of the planet and weakest at the surface. As a result, matter is pulled towards the center of the planet, causing it to take on a spherical shape. A sphere is the shape with the lowest surface area for a given volume. This means that a planet with a spherical shape has the least amount of potential energy. Potential energy is the energy that an object has due to its position or condition. In the case of a planet, its potential energy is due to its gravitational force. The lower the potential energy of a planet, the more stable it is. This is because a planet with a lower potential energy is less likely to change its shape. As a result, planets tend to be spherical in shape. #### Gravity causes planets to be round because a sphere is the shape with the lowest surface area for a given volume. This means that a planet with a spherical shape has the least amount of potential energy, which is the energy that an object has due to its position or condition. Gravity pulls matter towards the center of a planet, and this force is strongest at the center. As a result, matter is pulled towards the center of the planet, causing it to take on a spherical shape.
  How many carbon atoms are present in a 5.85-gram sample of carbon tetrabromide (CBr4)?	There are approximately (1 \times 10^{22}) carbon atoms in the given sample. Explanation: To determine the number of carbon atoms, we first need to calculate the molar amount of CBr4. The molar mass of CBr4 is 331.63 g/mol. So, we have: [ \frac{5.85\ g}{331.63\ g/mol} = 0.0176\ mol ] Since one molecule of CBr4 contains one carbon atom and four bromine atoms, there are: [ 1 \times 0.0176\ mol = 0.0176\ mol\ of\ carbon\ atoms ] Now, multiplying the molar quantity by Avogadro's number (6.022 × 10^23 mol^(-1)) gives us the number of individual carbon atoms: [ 0.0176\ mol \times 6.022 \times 10^{23}\ mol^{-1} = 1.06 \times 10^{22}\ carbon\ atoms ] Therefore, there are approximately (1 \times 10^{22}) carbon atoms in a 5.85-gram sample of CBr4.

• Loss: MultipleNegativesRankingLoss with these parameters:

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

stackexchange

• Dataset: stackexchange
• Size: 317,208 training samples
• Columns: anchor and positive
• Approximate statistics based on the first 1000 samples:

  	anchor	positive
  type	string	string
  details	min: 12 tokens mean: 64.07 tokens max: 512 tokens	min: 50 tokens mean: 264.62 tokens max: 512 tokens

• Samples:

  anchor	positive
  Should I use a tip activator to recoat the worn protective coating on my iron tip, or is it better to replace the tip entirely? My 48W ZD99 Solder Station's tip is showing signs of peeling due to moisture exposure and inadequate care. Can the tip activator effectively restore the tip, or should I opt for a new one?	To address the issue, first clean the iron tip with a wire brush to remove any debris. Then, apply flux and tin the tip to protect it and maintain its performance. Tip activators are available as a means to recoat tips, but their effectiveness may vary. While they can be a viable solution, it's essential to ensure proper tip care to prevent future wear. If the tip's condition significantly deteriorates despite these efforts, consider replacing it with a new one.
  What are the fundamental limits, if any, for the speed of sound in different materials, and how do these limits relate to the speed of light?	The speed of sound is limited by the properties of the material it travels through and the fundamental principles of physics. In a theoretical sense, the maximum speed of sound is constrained by the speed of light (approximately 299,792 km/s in vacuum), which is the maximum speed at which information can propagate. This limit is reached when the material has an incompressible equation of state, such as in the core of a neutron star, where the strong nuclear force creates immense pressure resistance. For an ideal gas, where particles do not interact, the equation of state is the softest possible with $P = \rho c^2/3$, where $P$ is pressure, $\rho$ is density, and $c$ is the speed of light. In this case, the maximum speed of sound would be $c/\sqrt{3}$. It's important to note that in practice, materials with extremely high sound speeds are unlikely to exist due to the conditions required for an incompressible equation of state. In reality, materials like solids and liquids generally have faster sound speeds than gases, but they are still far below the speed of light. When dealing with exotic materials, such as short-lived isotopes or neutron stars, the speed of sound may be even more challenging to determine due to the unique properties and states involved. However, the underlying principles remain the same: the speed of sound is determined by the material's properties, and it cannot exceed the speed of light in a vacuum.
  What could be causing a 1996 Honda Civic to stop running suddenly, and how can it be started?	A potential issue is a faulty ignition switch. When you attempt to start the car, the switch might be malfunctioning in such a way that it disrupts power to the engine ignition system, causing the dash lights to go out and preventing the car from starting. However, when you perform a push start (crash start), the car starts because the ignition switch remains in position 2, providing power to the engine. Another possibility is a problem with the battery or its connections. If the battery terminals have a poor connection, it might lead to high resistance, making it difficult for the car to start. Alternatively, if the battery is weak, it might not supply enough power to crank the engine effectively. In this case, the starter motor would sound sluggish as it tries to turn the engine. To resolve the issue, inspect the ignition switch, battery connections, and consider testing or replacing the battery if necessary.

• Loss: MultipleNegativesRankingLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 32
• per_device_eval_batch_size: 32
• num_train_epochs: 1
• warmup_ratio: 0.1
• bf16: True
• batch_sampler: no_duplicates
• multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 32
• per_device_eval_batch_size: 32
• 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: 1.0
• num_train_epochs: 1
• 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: 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: 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: False
• resume_from_checkpoint: None
• hub_model_id: None
• hub_strategy: every_save
• 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
• eval_on_start: False
• eval_use_gather_object: False
• batch_sampler: no_duplicates
• multi_dataset_batch_sampler: round_robin

Training Logs

Click to expand

Epoch	Step	Training Loss	sts-dev_spearman_cosine
0.0034	100	0.1339	-
0.0067	200	0.0535	-
0.0101	300	0.0372	-
0.0135	400	0.0329	-
0.0168	500	0.0277	-
0.0202	600	0.0287	-
0.0235	700	0.0217	-
0.0269	800	0.0257	-
0.0303	900	0.0262	-
0.0336	1000	0.02	0.8994
0.0370	1100	0.0196	-
0.0404	1200	0.0231	-
0.0437	1300	0.0228	-
0.0471	1400	0.0187	-
0.0504	1500	0.0197	-
0.0538	1600	0.0245	-
0.0572	1700	0.028	-
0.0605	1800	0.0242	-
0.0639	1900	0.0255	-
0.0673	2000	0.0324	0.8936
0.0706	2100	0.0231	-
0.0740	2200	0.0335	-
0.0773	2300	0.0221	-
0.0807	2400	0.0285	-
0.0841	2500	0.0394	-
0.0874	2600	0.0306	-
0.0908	2700	0.0305	-
0.0942	2800	0.0349	-
0.0975	2900	0.0327	-
0.1009	3000	0.0241	0.8788
0.1042	3100	0.0344	-
0.1076	3200	0.0315	-
0.1110	3300	0.035	-
0.1143	3400	0.0365	-
0.1177	3500	0.0363	-
0.1211	3600	0.0402	-
0.1244	3700	0.0332	-
0.1278	3800	0.0317	-
0.1311	3900	0.0292	-
0.1345	4000	0.0357	0.8686
0.1379	4100	0.0365	-
0.1412	4200	0.0349	-
0.1446	4300	0.0344	-
0.1480	4400	0.0295	-
0.1513	4500	0.0356	-
0.1547	4600	0.036	-
0.1580	4700	0.0301	-
0.1614	4800	0.039	-
0.1648	4900	0.0279	-
0.1681	5000	0.0388	0.8635
0.1715	5100	0.0261	-
0.1749	5200	0.0308	-
0.1782	5300	0.0404	-
0.1816	5400	0.0315	-
0.1849	5500	0.0397	-
0.1883	5600	0.0361	-
0.1917	5700	0.031	-
0.1950	5800	0.0271	-
0.1984	5900	0.0287	-
0.2018	6000	0.0356	0.8571
0.2051	6100	0.0243	-
0.2085	6200	0.0193	-
0.2118	6300	0.0232	-
0.2152	6400	0.032	-
0.2186	6500	0.0282	-
0.2219	6600	0.0275	-
0.2253	6700	0.026	-
0.2287	6800	0.0333	-
0.2320	6900	0.0298	-
0.2354	7000	0.033	0.8218
0.2387	7100	0.0265	-
0.2421	7200	0.0247	-
0.2455	7300	0.0233	-
0.2488	7400	0.0303	-
0.2522	7500	0.0272	-
0.2556	7600	0.028	-
0.2589	7700	0.0259	-
0.2623	7800	0.0305	-
0.2656	7900	0.0237	-
0.2690	8000	0.0227	0.8368
0.2724	8100	0.0216	-
0.2757	8200	0.0277	-
0.2791	8300	0.0197	-
0.2825	8400	0.0231	-
0.2858	8500	0.0232	-
0.2892	8600	0.0315	-
0.2925	8700	0.0198	-
0.2959	8800	0.0236	-
0.2993	8900	0.0243	-
0.3026	9000	0.0213	0.8118
0.3060	9100	0.0264	-
0.3094	9200	0.0218	-
0.3127	9300	0.0232	-
0.3161	9400	0.0192	-
0.3194	9500	0.018	-
0.3228	9600	0.0225	-
0.3262	9700	0.0225	-
0.3295	9800	0.0207	-
0.3329	9900	0.0264	-
0.3363	10000	0.0314	0.8286
0.3396	10100	0.0246	-
0.3430	10200	0.0224	-
0.3463	10300	0.0246	-
0.3497	10400	0.0212	-
0.3531	10500	0.0166	-
0.3564	10600	0.0253	-
0.3598	10700	0.0221	-
0.3632	10800	0.0175	-
0.3665	10900	0.0254	-
0.3699	11000	0.0181	0.7995
0.3732	11100	0.0176	-
0.3766	11200	0.0196	-
0.3800	11300	0.02	-
0.3833	11400	0.0219	-
0.3867	11500	0.0265	-
0.3901	11600	0.0217	-
0.3934	11700	0.0161	-
0.3968	11800	0.0145	-
0.4001	11900	0.0184	-
0.4035	12000	0.0166	0.8185
0.4069	12100	0.0177	-
0.4102	12200	0.0231	-
0.4136	12300	0.0215	-
0.4170	12400	0.0226	-
0.4203	12500	0.0144	-
0.4237	12600	0.0174	-
0.4270	12700	0.0176	-
0.4304	12800	0.0214	-
0.4338	12900	0.0206	-
0.4371	13000	0.0197	0.7957
0.4405	13100	0.0216	-
0.4439	13200	0.0211	-
0.4472	13300	0.0198	-
0.4506	13400	0.0161	-
0.4539	13500	0.0123	-
0.4573	13600	0.0168	-
0.4607	13700	0.0188	-
0.4640	13800	0.0145	-
0.4674	13900	0.0221	-
0.4708	14000	0.0207	0.8036
0.4741	14100	0.0186	-
0.4775	14200	0.0199	-
0.4809	14300	0.0219	-
0.4842	14400	0.0131	-
0.4876	14500	0.0152	-
0.4909	14600	0.0159	-
0.4943	14700	0.0165	-
0.4977	14800	0.0145	-
0.5010	14900	0.0143	-
0.5044	15000	0.0135	0.7920
0.5078	15100	0.0159	-
0.5111	15200	0.0111	-
0.5145	15300	0.0198	-
0.5178	15400	0.0142	-
0.5212	15500	0.0167	-
0.5246	15600	0.0118	-
0.5279	15700	0.0151	-
0.5313	15800	0.0172	-
0.5347	15900	0.0135	-
0.5380	16000	0.0159	0.8073
0.5414	16100	0.0146	-
0.5447	16200	0.0127	-
0.5481	16300	0.0158	-
0.5515	16400	0.0138	-
0.5548	16500	0.0102	-
0.5582	16600	0.0127	-
0.5616	16700	0.0166	-
0.5649	16800	0.0137	-
0.5683	16900	0.0127	-
0.5716	17000	0.014	0.7942
0.5750	17100	0.0151	-
0.5784	17200	0.0134	-
0.5817	17300	0.0119	-
0.5851	17400	0.0096	-
0.5885	17500	0.0129	-
0.5918	17600	0.0133	-
0.5952	17700	0.0084	-
0.5985	17800	0.0114	-
0.6019	17900	0.0123	-
0.6053	18000	0.0115	0.7615
0.6086	18100	0.0109	-
0.6120	18200	0.0098	-
0.6154	18300	0.0167	-
0.6187	18400	0.0117	-
0.6221	18500	0.0133	-
0.6254	18600	0.0089	-
0.6288	18700	0.0125	-
0.6322	18800	0.0101	-
0.6355	18900	0.0143	-
0.6389	19000	0.0108	0.8011
0.6423	19100	0.0164	-
0.6456	19200	0.0099	-
0.6490	19300	0.0112	-
0.6523	19400	0.0184	-
0.6557	19500	0.0178	-
0.6591	19600	0.0111	-
0.6624	19700	0.0101	-
0.6658	19800	0.0146	-
0.6692	19900	0.0149	-
0.6725	20000	0.0139	0.8151
0.6759	20100	0.0146	-
0.6792	20200	0.0086	-
0.6826	20300	0.0168	-
0.6860	20400	0.0101	-
0.6893	20500	0.0101	-
0.6927	20600	0.0086	-
0.6961	20700	0.0108	-
0.6994	20800	0.0092	-
0.7028	20900	0.0119	-
0.7061	21000	0.0136	0.8046
0.7095	21100	0.0106	-
0.7129	21200	0.0123	-
0.7162	21300	0.0108	-
0.7196	21400	0.0112	-
0.7230	21500	0.0096	-
0.7263	21600	0.0074	-
0.7297	21700	0.0104	-
0.7330	21800	0.0079	-
0.7364	21900	0.0061	-
0.7398	22000	0.0064	0.7948
0.7431	22100	0.0091	-
0.7465	22200	0.0091	-
0.7499	22300	0.006	-
0.7532	22400	0.0081	-
0.7566	22500	0.0084	-
0.7599	22600	0.0109	-
0.7633	22700	0.0124	-
0.7667	22800	0.0108	-
0.7700	22900	0.009	-
0.7734	23000	0.0118	0.7956
0.7768	23100	0.011	-
0.7801	23200	0.0093	-
0.7835	23300	0.0097	-
0.7868	23400	0.0069	-
0.7902	23500	0.0081	-
0.7936	23600	0.0092	-
0.7969	23700	0.01	-
0.8003	23800	0.0112	-
0.8037	23900	0.0076	-
0.8070	24000	0.0098	0.8005
0.8104	24100	0.0083	-
0.8137	24200	0.0089	-
0.8171	24300	0.0125	-
0.8205	24400	0.0051	-
0.8238	24500	0.009	-
0.8272	24600	0.0086	-
0.8306	24700	0.0075	-
0.8339	24800	0.0069	-
0.8373	24900	0.0065	-
0.8406	25000	0.0092	0.7830
0.8440	25100	0.0077	-
0.8474	25200	0.0049	-
0.8507	25300	0.0061	-
0.8541	25400	0.0115	-
0.8575	25500	0.0086	-
0.8608	25600	0.006	-
0.8642	25700	0.0083	-
0.8675	25800	0.0067	-
0.8709	25900	0.0069	-
0.8743	26000	0.0083	0.7734
0.8776	26100	0.007	-
0.8810	26200	0.0086	-
0.8844	26300	0.0077	-
0.8877	26400	0.0138	-
0.8911	26500	0.0054	-
0.8944	26600	0.008	-
0.8978	26700	0.0076	-
0.9012	26800	0.0094	-
0.9045	26900	0.0069	-
0.9079	27000	0.0066	0.7821
0.9113	27100	0.0068	-
0.9146	27200	0.0056	-
0.9180	27300	0.0067	-
0.9213	27400	0.0061	-
0.9247	27500	0.0072	-
0.9281	27600	0.0086	-
0.9314	27700	0.006	-
0.9348	27800	0.0063	-
0.9382	27900	0.0095	-
0.9415	28000	0.007	0.7833
0.9449	28100	0.0128	-
0.9482	28200	0.0081	-
0.9516	28300	0.0059	-
0.9550	28400	0.0067	-
0.9583	28500	0.0059	-
0.9617	28600	0.0057	-
0.9651	28700	0.0055	-
0.9684	28800	0.0065	-
0.9718	28900	0.0065	-
0.9752	29000	0.0072	0.7806
0.9785	29100	0.0107	-
0.9819	29200	0.0083	-
0.9852	29300	0.01	-
0.9886	29400	0.0044	-
0.9920	29500	0.0056	-
0.9953	29600	0.0053	-
0.9987	29700	0.0081	-

Framework Versions

• Python: 3.10.12
• Sentence Transformers: 3.0.1
• Transformers: 4.44.2
• PyTorch: 2.4.0+cu121
• Accelerate: 0.34.0
• Datasets: 2.21.0
• 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",
}

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}
}