--- tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:5900 - loss:MultipleNegativesRankingLoss base_model: Alibaba-NLP/gte-multilingual-base widget: - source_sentence: How can I add the program to my antivirus exception list to stop these "Access is denied" errors when saving files? sentences: - 'Title: Russian Federation "Google Tax" Answer: Payment of Taxes to the Russian Federation Residents from the Russian Federation need to pay tax on their online purchases.This 20% tax is one that is forced upon all online sales to the Russian Federation.We as a seller are obliged to pay this tax to your country for each purchase in our web shop by citizens of the Russian Federation.[I](https://tax.thomsonreuters.com/blog/tax/indirect-tax/google-tax-is-coming-to-russia/)mage-Line Support Team' - 'Document_title: Tools Menu File_name: menu_tools.htm Heading_hierarchy: [Tools Menu] Anchor_id: [none] [Image: Top menu bar with text options | Ref: img_shot/menu_bar_selecttools.png] The Tools menu contains useful tools for working with channels, patterns, effects and provides the ability to use external applications as tools inside FL Studio.' - 'Title: Cannot create file / Access is denied / Unable to write to / Couldn''t create the file / Please check that no other application is currently using it Answer: Anti virus programs can trigger one or more of the following error messages: Error messages: Cannot create file ''C:\Users\[USER]\Documents\Image-Line\FLEX\Images\[Filename].jpg''. Access is denied. Cannot create file ''C:\Users\[USER]\Documents\Image-Line\FL Studio\Audio\Sliced audio\[Filename].wav''. Access is denied. Cannot create file "C:\Users\[USER]\Documents\Image-Line\FL Studio\Presets\Clipboard files\Audio clipboard.wav". Access is denied. Unable to write to C:\Users\[USER]\Documents\Image-Line\FLEX\Packs\[Filename].ini. Couldn''t create the file ''[Filename].wav''. Please check that no other application is currently using it. As [USER] for example: John (your Windows account name)As [Filename] for example: Arksun Cityscape-1.jpg, Arksun Cityscape-1.ini, recording.wav Symptoms: Can''t render audio, "Couldn''t create the file ''[Filename].wav''. Please check that no other application is currently using it." error is showing up. FLEX doesn''t work, "Cannot create file ''C:\Users\[USER]\Documents\Image-Line\FLEX\Images\[Filename].jpg''. Access is denied.", "Unable to write to C:\Users\[USER]\Documents\Image-Line\FLEX\Packs\[Filename].ini." error is showing up. You can''t drag and drop files from NewTone, NewTime or Edison into FL Studio. You can''t use "paste from clipboard" as "Cannot create file "C:\Users\[USER]\Documents\Image-Line\FL Studio\Presets\Clipboard files\Audio clipboard.wav". Access is denied." error is showing up. You can''t consolidate or quickrender tracks or patterns as "Couldn''t create the file ''[Filename].wav''. Please check that no other application is currently using it." error is showing up. You try to render audio and the file is not showing up, this could also be caused by an Antivirus. Please check if Avast or AVG Anti-virus is installed. Avast and AVG block the usage of the document folder for FL Studio. The solution is to add FL Studio to the exception list. Fix for Avast: 1: Open Avast and navigate to the Avast dashboard 2: Click Menu and click the Settings tab. Click the Exclusions tab under the General tab 3: Add > add the path of the installation folder from FL Studio > add to Avast whitelist Fix for AVG: 1: Open the AVG Dashboard > Menu > Settings 2: Click on General > Exceptions > Add Exception 3: Click on Browse > navigate to the installation folder of FL Studio Other solutions: If the solutions above does not help, these could be some issues, have a look at the article linked below: Wrong user data location Controlled Folder Access is activated [FL Studio | Failed to create user data folder / Unable to create file / Errors saving data](https://support.image-line.com/action/knowledgebase?ans=646) Please report this issue to your Antivirus provider, so they are able to add FL Studio to their database. As FL Studio is always evolving, the code signature/fingerprint AVG and Avast is using changes and will again be blocked in the future. Image-Line Support Team' - source_sentence: Can I use the Gate parameter to create a staccato effect by cutting off the sound immediately when I release a key? sentences: - 'Document_title: Plucked! File_name: plugins/Plucked!.htm Heading_hierarchy: [Plucked! -> Parameters] Anchor_id: [none] • Decay knob - Changes the decay time of the plucked sound. • Color knob - Changes the tone of the plucked sound from dark (left) to bright (right). • Normalize - Tries to make the decay the same for all semitones. Otherwise higher notes have a shorter decay. • Gate - Stops the voices abruptly when released. Otherwise the decay keeps going. • Widen - Enriches the stereo panorama of the sound.' - 'Document_title: Minihost Modular (DEPRECIATED) File_name: plugins/Minihost Modular.htm Heading_hierarchy: [Minihost Modular (DEPRECIATED) -> Zones] Anchor_id: [none] The Piano roll Module can hold 1 or more Zones. A Zone is a named musical sequence which reacts to a given MIDI keyboard range, on a specific MIDI Channel or all MIDI Channels (Omni). It can also play one or more graphical envelopes, routed to different destinations.' - "Document_title: Harmor \nFile_name: plugins/Harmor.htm\nHeading_hierarchy: [Harmor\ \ -> Formats]\nAnchor_id: [none]\nDrag & Drop audio Files (WAV, AIFF, WavPack,\ \ MP3, OGG, REX1&2): • Onto the oscillator shapes: converts wav to oscillator\ \ (1 or 2). • Onto the image editor: import wav for resynthesis. Original file\ \ IS linked to, & not embedded in FLPs. • Anywhere or onto the channel button:\ \ Harmor will detect\nwhether it's a single-cycle or long wav (>50ms), & import\ \ as an oscillator (the one 'selected') or the image. Drag & drop Images: ➤ Bitmap\ \ file (bmp/jpg): imports the image (in image mode, obviously). Original file\ \ is NOT linked to, it's embedded. Drag & drop scala tuning files: ➤ Scalar files\ \ are\nsupported, drop .scl files onto Harmor. .scl Scala tuning file: imports\ \ the tuning file into the pitch envelope. There is also a \"just intonation\"\ \ pitch kb mapping that can be loaded." - source_sentence: How do I access the FL Keys online help file from within the program? sentences: - 'Title: What is Firebase and what data does it collect? Answer: What is Firebase? [Firebase](https://support.google.com/firebase/answer/6318039?hl=en&ref_topic=6317497) is a tool developed and managed by Google. It communicates with Google servers to both enable online cloud services (such as content delivery) and also compiles information about how a user interacts with an Application and its surrounding services. Firebase works on Android and iOS operating systems. We use it to receive information about how you use FL Studio Mobile, to help us improve the user experience. FL Studio Mobile included Firebase functionality commencing May 2021. Why do we use it? When we develop an App like FL Studio Mobile, we put it in an App store and have very little connection with the users. Your relationship is more between Apple, Google and Microsoft (as the vendor of the OS you are using and App store) than it is with us. And so, we find it difficult to know how our mobile applications are performing, beyond the review system on the App stores. It can help us greatly if we know more about how and where people are using FL Studio Mobile. What information does Firebase collect? How many times the App is opened and when How long the App is open The Operating system being used The device model the App is being used on The country you are in When the app was first installed and first opened If and when the App was updated What In-app purchases are made Crashes and their type That one of our mobile App customers has visited our website or clicked on our ads. This helps our developers to better understand the nature of the devices in use, and where our App is being used. They can then make better decisions about how to improve functionality and performance. Do we spy on you? No. We do not and can not track your precise location or see any of your personal files (even those in FL Studio Mobile). We can''t see specific user activities on the device other than those listed. Nor are we interested! Firebase does log if you click on any Google Advertising. We are particularly interested if you click on any of our Google Advertising. We can''t specifically identify you. Just that an FL Studio Mobile user has clicked on one of our advertisements or visited our website. We are generally interested in how closely our Mobile customers also interact with our online presence (Website, Advertisements, Social Media etc). We use this to decide where we should advertise to find more people like you - people who may be interested in purchasing FL Studio Mobile. For the full list of data Firebase may collect see [General overview](https://support.google.com/firebase/answer/6318039?hl=en&ref_topic=6317497), [Automatically Collected Data](https://support.google.com/firebase/answer/9234069?visit_id=637547267264620717-2374579154&rd=1) and [User related information](https://support.google.com/firebase/answer/9268042?visit_id=637547267264620717-2374579154&rd=1) Image-Line' - "Document_title: MIDI Scripting Device API reference \nFile_name: midi_scripting.htm\n\ Heading_hierarchy: [MIDI Scripting Device API reference -> PME flags]\nAnchor_id:\ \ pmeFlags\nParameter Value Documentation PME_System 2 Can do system stuff (play/pause..\ \ mostly safe things) PME_System_Safe 4 Can do critical system stuff (add markers..\ \ things that can't be done when a modal\n window is shown) PME_PreviewNote\ \ 8 note trigger previews notes | controls stuff PME_FromHost 16 when the app\ \ is hosted PME_FromMIDI 32 coming from MIDI event" - "Title: FL Keys - general information \nAnswer: Please visit the [FL Keys online\ \ help](https://www.image-line.com/support/flstudio_online_manual/html/plugins/FL%20Keys.htm)\ \ file for extra information" - source_sentence: What kind of sample properties can I adjust using the F2 shortcut in Edison? sentences: - "Document_title: Edison \nFile_name: plugins/Edison_4.htm\nHeading_hierarchy:\ \ [Edison -> Sample Properties ( F2 )]\nAnchor_id: [none]\nF2 \n[Edison -> Sample\ \ Properties ( F2 )]" - 'Title: TS404 - general information Answer: The TS404 plugin no longer is available.' - 'Title: Fruity Parametric EQ - general information Answer: Please visit the [Fruity Parametric EQ online help](https://www.image-line.com/support/flstudio_online_manual/html/plugins/Fruity%20Parametric%20EQ.htm) file for extra information' - source_sentence: If I save the project after clicking "Continue," will the missing files be automatically relinked or do I need to fix the file paths manually? sentences: - "Document_title: The Playlist \nFile_name: playlist.htm\nHeading_hierarchy: [The\ \ Playlist -> Universal Clip Editing Methods]\nAnchor_id: [none]\n• Snap settings\ \ ( [Image: Horseshoe magnet icon, gray background | Ref: img_glob/flicon_snap.png]\ \ ) - Snap controls how Clips move on the Playlist grid and many of the other\ \ editing functions below. Set this to ' line ' if you want the Clips to snap\ \ to bar boundaries or to ' none ' if you want to\nfreely position & slice Clips.\ \ • Inserting Clips - To insert a Clip, select the Clip you want to place from\ \ the Clip Source menu (indicated above) OR Right-Click the Clip focus selectors\ \ (indicated above) to choose Clips of the type selected. Next, in Draw ( [Image:\ \ Gray pencil drawing/editing tool\nicon | Ref: img_glob/flicon_pencilup.png]\ \ ) or Paint ( [Image: Paintbrush dripping with liquid icon | Ref: img_glob/flicon_paint.png]\ \ ) mode, Left-click on an empty area of a Clips track where you want to place\ \ the Clip. Paint mode allows you to paint multiple instances of the Clip at once\ \ (hold the\nMouse button & drag). • Insert time into the Playlist (shift Clips\ \ to the right) - Hold ( Ctrl ), click and drag on the time-line at the top of\ \ the Playlist starting from the point you want to insert space into the timeline\ \ AND for the duration of the insertion you want. With ( Ctrl ) still held press\ \ the ( Ins\nert ) key on your keyboard. Insert time into the Playlist (slice\ \ and move Clips to the right) - Make a time selection as above, then hold ( Ctrl+Alt\ \ ) and press the ( Insert ) key on your keyboard. The slice point will be at\ \ the start of the selection. • Delete a time selection - Hold ( Ctrl ), click\ \ and\ndrag on the time-line at the\n top of the Playlist to select the region\ \ to be deleted. Press ( Ctrl+Del ) to delete all patterns in the current selection\ \ and move Clips to the right of the selection into the gap. • Select Clips -\ \ To make a selection of more than one Clip. Use the [Image: Dashed square crop\ \ selection icon | Ref:\nimg_glob/flicon_select.png] Select tool and click and\ \ drag a rectangle around the Clips to be selected. To add Clips to this selection\ \ hold the ( Shift ) key and make further selections. OR if you are in Draw or\ \ Paint mode, hold ( Ctrl ) key and you will drop into Select mode while the\ \ ( Ctrl ) key is\nheld. Holding the ( Ctrl+Shift ) keys will allow you to add\ \ and remove Clips to / from an existing selection. OR use the Magic lasso feature.\ \ Move your Mouse pointer in a loop that encloses the Clips you want to select\ \ (no clicking required, it's 'magic' remember). Make sure you have no Clips\n\ selected before you perform the lasso action (Right-Click the empty Playlist to\ \ deselect all Clips and make another selection). • Zoom to area - ( Ctrl+Right-Click\ \ ) and drag over a selection of the Playlist. Un-Zoom area - ( Ctrl+Right-Click\ \ ) anywhere\n on the Playlist (don't drag). • Zoom to a Clip - ( Ctrl+Shift+Right-Click\ \ ) on a Clip will maximize the zoom\n of the Playlist to the selected Clip.\ \ To Un-Zoom Clip - ( Ctrl+Right-Click ) anywhere\n on the Playlist (don't\ \ drag in this mode since that is how to zoom to selection). • Delete/Erase a\ \ Clip - Right-Click the target Clip or use the left Mouse button if you are in\ \ erase ( [Image: Circular gray \"no entry\" symbol icon | Ref: img_glob/flicon_delete.png]\ \ ) mode. • Copy/Paste Clips - Make\na selection, release the Mouse and any keys\ \ held, then hold the ( Shift ) key, then click on the selection and drag. A copy\ \ of the selection will follow the Mouse cursor. Release the selection when the\ \ Clips are in the alternative location. NOTE: In ' Slice tool ' mode this will\ \ initiate a slice, not\ncopy. OR Make a selection, press ( Ctrl+C ) to copy,\ \ then scroll the Playlist so that the starting bar for the paste location is\ \ at the left edge of the Playlist and press ( Ctrl+V ). • Duplicate selection\ \ - Make a selection and press ( Ctrl+B ). The selection, or all Clips if no selection\ \ is made, will be\nduplicated to the right of the original selection." - 'Title: If I use the academic version of FL Studio, do I own copyright to the music I make with it? Answer: Yes.However, this does not allow you to sell the music or rent it for hire. Please see this article: [What about commercial use of the music produced with FL Studio educational? In other words, can produced music be sold?](https://support.image-line.com/action/knowledgebase/?ans=381)' - 'Title: Error: no disk in drive Answer: Issue This error usually occurs when an FLP (FL Studio project) looks for a sample/file in a location that doesn''t exist (disconnected/offline drives or renamed drives) or one that doesn''t have a disc inserted (DVD drive for example). Solution Click "Continue" and let the FLP load until the end. Save the project and the message should no longer present for that project. Note: If the error still presents itself after following the above steps try restarting your computer. Image-Line Support Team' pipeline_tag: sentence-similarity library_name: sentence-transformers metrics: - cosine_accuracy@1 - cosine_accuracy@3 - cosine_accuracy@5 - cosine_accuracy@10 - cosine_precision@1 - cosine_precision@3 - cosine_precision@5 - cosine_precision@10 - cosine_recall@1 - cosine_recall@3 - cosine_recall@5 - cosine_recall@10 - cosine_ndcg@10 - cosine_mrr@10 - cosine_map@100 model-index: - name: SentenceTransformer based on Alibaba-NLP/gte-multilingual-base results: - task: type: information-retrieval name: Information Retrieval dataset: name: Unknown type: unknown metrics: - type: cosine_accuracy@1 value: 0.8225371120107963 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.9547908232118758 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.9763832658569501 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.9919028340080972 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.8225371120107963 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.31826360773729195 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.19527665317139 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.09919028340080972 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.8225371120107963 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.9547908232118758 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.9763832658569501 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.9919028340080972 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.9156891710634836 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.8902882205513788 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.8908073502880158 name: Cosine Map@100 --- # SentenceTransformer based on Alibaba-NLP/gte-multilingual-base This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Alibaba-NLP/gte-multilingual-base](https://huggingface.co/Alibaba-NLP/gte-multilingual-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:** [Alibaba-NLP/gte-multilingual-base](https://huggingface.co/Alibaba-NLP/gte-multilingual-base) - **Maximum Sequence Length:** 8192 tokens - **Output Dimensionality:** 768 dimensions - **Similarity Function:** Cosine Similarity ### Model Sources - **Documentation:** [Sentence Transformers Documentation](https://sbert.net) - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers) - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers) ### Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 8192, 'do_lower_case': False}) with Transformer model: NewModel (1): Pooling({'word_embedding_dimension': 768, '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}) (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("sentence_transformers_model_id") # Run inference sentences = [ 'If I save the project after clicking "Continue," will the missing files be automatically relinked or do I need to fix the file paths manually?', 'Title: Error: no disk in drive\nAnswer: Issue This error usually occurs when an FLP (FL Studio project) looks for a sample/file in a location that doesn\'t exist (disconnected/offline drives or renamed drives) or one that doesn\'t have a disc inserted (DVD drive for example). Solution Click "Continue" and let the FLP load until the end. Save the project and the message should no longer present for that project. Note: If the error still presents itself after following the above steps try restarting your computer. Image-Line Support Team', 'Document_title: The Playlist \nFile_name: playlist.htm\nHeading_hierarchy: [The Playlist -> Universal Clip Editing Methods]\nAnchor_id: [none]\n• Snap settings ( [Image: Horseshoe magnet icon, gray background | Ref: img_glob/flicon_snap.png] ) - Snap controls how Clips move on the Playlist grid and many of the other editing functions below. Set this to \' line \' if you want the Clips to snap to bar boundaries or to \' none \' if you want to\nfreely position & slice Clips. • Inserting Clips - To insert a Clip, select the Clip you want to place from the Clip Source menu (indicated above) OR Right-Click the Clip focus selectors (indicated above) to choose Clips of the type selected. Next, in Draw ( [Image: Gray pencil drawing/editing tool\nicon | Ref: img_glob/flicon_pencilup.png] ) or Paint ( [Image: Paintbrush dripping with liquid icon | Ref: img_glob/flicon_paint.png] ) mode, Left-click on an empty area of a Clips track where you want to place the Clip. Paint mode allows you to paint multiple instances of the Clip at once (hold the\nMouse button & drag). • Insert time into the Playlist (shift Clips to the right) - Hold ( Ctrl ), click and drag on the time-line at the top of the Playlist starting from the point you want to insert space into the timeline AND for the duration of the insertion you want. With ( Ctrl ) still held press the ( Ins\nert ) key on your keyboard. Insert time into the Playlist (slice and move Clips to the right) - Make a time selection as above, then hold ( Ctrl+Alt ) and press the ( Insert ) key on your keyboard. The slice point will be at the start of the selection. • Delete a time selection - Hold ( Ctrl ), click and\ndrag on the time-line at the\n top of the Playlist to select the region to be deleted. Press ( Ctrl+Del ) to delete all patterns in the current selection and move Clips to the right of the selection into the gap. • Select Clips - To make a selection of more than one Clip. Use the [Image: Dashed square crop selection icon | Ref:\nimg_glob/flicon_select.png] Select tool and click and drag a rectangle around the Clips to be selected. To add Clips to this selection hold the ( Shift ) key and make further selections. OR if you are in Draw or Paint mode, hold ( Ctrl ) key and you will drop into Select mode while the ( Ctrl ) key is\nheld. Holding the ( Ctrl+Shift ) keys will allow you to add and remove Clips to / from an existing selection. OR use the Magic lasso feature. Move your Mouse pointer in a loop that encloses the Clips you want to select (no clicking required, it\'s \'magic\' remember). Make sure you have no Clips\nselected before you perform the lasso action (Right-Click the empty Playlist to deselect all Clips and make another selection). • Zoom to area - ( Ctrl+Right-Click ) and drag over a selection of the Playlist. Un-Zoom area - ( Ctrl+Right-Click ) anywhere\n on the Playlist (don\'t drag). • Zoom to a Clip - ( Ctrl+Shift+Right-Click ) on a Clip will maximize the zoom\n of the Playlist to the selected Clip. To Un-Zoom Clip - ( Ctrl+Right-Click ) anywhere\n on the Playlist (don\'t drag in this mode since that is how to zoom to selection). • Delete/Erase a Clip - Right-Click the target Clip or use the left Mouse button if you are in erase ( [Image: Circular gray "no entry" symbol icon | Ref: img_glob/flicon_delete.png] ) mode. • Copy/Paste Clips - Make\na selection, release the Mouse and any keys held, then hold the ( Shift ) key, then click on the selection and drag. A copy of the selection will follow the Mouse cursor. Release the selection when the Clips are in the alternative location. NOTE: In \' Slice tool \' mode this will initiate a slice, not\ncopy. OR Make a selection, press ( Ctrl+C ) to copy, then scroll the Playlist so that the starting bar for the paste location is at the left edge of the Playlist and press ( Ctrl+V ). • Duplicate selection - Make a selection and press ( Ctrl+B ). The selection, or all Clips if no selection is made, will be\nduplicated to the right of the original selection.', ] 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 #### Information Retrieval * Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) | Metric | Value | |:--------------------|:-----------| | cosine_accuracy@1 | 0.8225 | | cosine_accuracy@3 | 0.9548 | | cosine_accuracy@5 | 0.9764 | | cosine_accuracy@10 | 0.9919 | | cosine_precision@1 | 0.8225 | | cosine_precision@3 | 0.3183 | | cosine_precision@5 | 0.1953 | | cosine_precision@10 | 0.0992 | | cosine_recall@1 | 0.8225 | | cosine_recall@3 | 0.9548 | | cosine_recall@5 | 0.9764 | | cosine_recall@10 | 0.9919 | | **cosine_ndcg@10** | **0.9157** | | cosine_mrr@10 | 0.8903 | | cosine_map@100 | 0.8908 | ## Training Details ### Training Dataset #### Unnamed Dataset * Size: 5,900 training samples * Columns: sentence_0 and sentence_1 * Approximate statistics based on the first 1000 samples: | | sentence_0 | sentence_1 | |:--------|:-----------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------| | type | string | string | | details | | | * Samples: | sentence_0 | sentence_1 | |:----------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | How long does it usually take for the payment status to update from 'unpaid' to 'processed' on the site? | Title: My payment at my online bank page shows as processed, but your site still says 'unpaid'.
Answer: Please allow our site and servers a few minutes to process your orders payment. Communication and verification between the different servers can take some time.There are different companies involved. They include your own bank, your credit card company, our 3rd party payment processors Verifone (2Checkout) & PayPal and our own registration servers. If you have the order status page still open, were you were forwarded after your purchase, hit the 'refresh' button of your browser (or the F5 key of your keyboard) to see the latest payment processing
information.FL Studio Support Team
| | If refreshing the order status page doesn't update the payment status, what should I do next? | Title: My payment at my online bank page shows as processed, but your site still says 'unpaid'.
Answer: Please allow our site and servers a few minutes to process your orders payment. Communication and verification between the different servers can take some time.There are different companies involved. They include your own bank, your credit card company, our 3rd party payment processors Verifone (2Checkout) & PayPal and our own registration servers. If you have the order status page still open, were you were forwarded after your purchase, hit the 'refresh' button of your browser (or the F5 key of your keyboard) to see the latest payment processing
information.FL Studio Support Team
| | Why do delay echoes not work properly with BooBass? | Document_title: BooBass
File_name: plugins/BooBass.htm
Heading_hierarchy: [BooBass -> Notes & Tips]
Anchor_id: [none]
Since BooBass is monophonic, delay echoes will not work properly (see [Function Settings](https://www.image-line.com/fl-studio-learning/fl-studio-online-manual/html/chansettings_misc.htm) ). Plugin Credits: David Billen
| * Loss: [MultipleNegativesRankingLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "cos_sim" } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `eval_strategy`: steps - `per_device_train_batch_size`: 10 - `per_device_eval_batch_size`: 10 - `num_train_epochs`: 2 - `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`: 10 - `per_device_eval_batch_size`: 10 - `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`: 2 - `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`: 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} - `tp_size`: 0 - `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`: None - `batch_sampler`: batch_sampler - `multi_dataset_batch_sampler`: round_robin
### Training Logs | Epoch | Step | Training Loss | cosine_ndcg@10 | |:------:|:----:|:-------------:|:--------------:| | 0.0847 | 50 | - | 0.8699 | | 0.1695 | 100 | - | 0.8846 | | 0.2542 | 150 | - | 0.8902 | | 0.3390 | 200 | - | 0.9001 | | 0.4237 | 250 | - | 0.9052 | | 0.5085 | 300 | - | 0.9056 | | 0.5932 | 350 | - | 0.9073 | | 0.6780 | 400 | - | 0.9108 | | 0.7627 | 450 | - | 0.9097 | | 0.8475 | 500 | 0.0591 | 0.9157 | ### Framework Versions - Python: 3.11.12 - Sentence Transformers: 3.4.1 - Transformers: 4.51.3 - PyTorch: 2.6.0+cu124 - Accelerate: 1.6.0 - Datasets: 3.6.0 - Tokenizers: 0.21.1 ## Citation ### BibTeX #### Sentence Transformers ```bibtex @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 ```bibtex @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} } ```