IlhamEbdesk/bge-base-en-v1.5-finetuned_ragds_v2

SentenceTransformer based on BAAI/bge-base-en-v1.5

This is a sentence-transformers model finetuned from BAAI/bge-base-en-v1.5. 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: BAAI/bge-base-en-v1.5
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 768 tokens
• Similarity Function: Cosine Similarity

Model Sources

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

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel 
  (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:

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("IlhamEbdesk/bge-base-en-v1.5-finetuned_ragds_v2")
# Run inference
sentences = [
    "The Accident Which Proved That I'm A Dumbass\nI can't be expected to retell this same story over and over again to hundred of people, so therefore, I will blog about it. Yes, in all my life, I've never had the displeasure of saying that I've actually been in an accident. Yesterday, that all changed, thanks to a moron named Romdan in a Mazda van. I was slowing down towards the Batu Tiga toll plaza, when I noticed this dude in a van in front of me realizing that he was in the wrong lane. He initially cut into my lane, then pulled back in, so stupid me thinking that he saw me, went on along on my merry way. He then did the obvious, he swerved out just when I was going by him and rammed right into my rear right door. As you can tell, this is just stupid. But what's even more stupid is the conversation which ensued. Me: Are you blind? You cut across three lanes just so you'd hit me? Him: Aiyoh sorry la abang, tak nampak la. At this point I had to start speaking Bahasa Malaysia, which I absolutely detest. Me: You couldn't see? What's this for? *points at side mirrors* Him: Aiyoh sorry man...I'm just sorry. Me: Sorry? Wait, I need my ciggarette. Me: Okay, this is real simple. Even a blind policeman can tell this was your fault. So you either give me 500 bucks now, or I go straight to the police. Him: Aiyoh do need involve the police all la. Me: Gimme your wallet. *Opens his wallet to find 6 Ringgit. Yes, that's right, SIX. He doesn't even have an ATM card* Me: This is all you got? Six bucks?! Him: Aiyoh sorry man I was just bringing my kids for a joyride. Me: This is stupid. How are you going to give me the money? Him: Wait let me call my brother. Me: Does he have the money? Him: I got money wan, I just don't have it now. Me: Yeah sure you do. This is what you're gonna do. Follow me back to the police station. We'll wait for your brother there. If he doesn't show up in one hour, I'm walking in. Him: Aiyoh why la u have to be like this, no need la talk about police all. Me: You hit my car. And tomorrow's a holiday. *I take out his identification card* Me: Romdan bin Junis? Him: Call me Hashim. Me: So what's your name now, Rondam or Hashim? Him: Hashim. Me: Is this even your own I/C? Him: Yes. Me: So why the hell should I call you Hashim? Him: Aiyoh because everyone does la. Me: Trust me, the police will call you Romdan, not Hashim. Remember that. Him: Aiyoh I call my brother first la. Pity me la man, see my kids scared. I am not trying to cheat you wan. I will pay you. And for some stupid, incomprehensible reason, I believed him. I know, i'm a freaking gigantic moron, but I did. I actually believed that poor son of a bitch and said that he can get the money and meet up with me later on in the evening. OMG I still can't believe what a dumbass I was. Really, don't bother asking me, because if I could put a foot up my ass, I would. Naturally, he didn't show. Later on I called his mobile (which I made sure was his by making sure his phone rang in front of me). Me: Hello, Rondam? Girl: Who? Me: Who's this? Girl: Who are you looking for? Me: ... Me: Hashim. Girl: Hashim's not here. Me: Are you his daughter who was in the van earlier? Girl: Hashim's not here. Me: You tell your father or whoever he is that if he doesnt call me back about the money, he better start running, because I'm going to go to your house. Girl: Hashim's not here. GAHHHHHH. So anyway, he never picked up any of my subsequent calls. So naturally, I head on over to the police station to make a report. Here's a kicker, I reported that he was driving without a license, and that he ran out on me, hit-and-run style. Oh the joy. The coppers took pictures of my car, which is the norm, but this is the best part: I was driving around with an expired road tax. OH GOD THE BALLS. So listen, that's my story. Here's the lowdown. I will hunt this fucker's ass down. I have all the required details I need from him. I will bloody well make sure he gets an early visit from Santa this year. Those who want in, let me know. I plan to go in force.",
    'What happened when the author confronted the man who hit his car?',
    'What is the main goal of the program developed by PersonaGrata Consulting?',
]
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]

Training Details

Training Dataset

Unnamed Dataset

• Size: 1,000 training samples
• Columns: positive and anchor
• Approximate statistics based on the first 1000 samples:

  	positive	anchor
  type	string	string
  details	min: 172 tokens mean: 467.87 tokens max: 512 tokens	min: 7 tokens mean: 18.68 tokens max: 43 tokens

• Samples:

  positive	anchor
  Caption: Tasmanian berry grower Nic Hansen showing Macau chef Antimo Merone around his property as part of export engagement activities. THE RISE and rise of the Australian strawberry, raspberry and blackberry industries has seen the sectors redouble their international trade focus, with the release of a dedicated export plan to grow their global presence over the next 10 years. Driven by significant grower input, the Berry Export Summary 2028 maps the sectors’ current position, where they want to be, high-opportunity markets and next steps. Hort Innovation trade manager Jenny Van de Meeberg said the value and volume of raspberry and blackberry exports rose by 100 per cent between 2016 and 2017. She said the Australian strawberry industry experienced similar success with an almost 30 per cent rise in export volume and a 26 per cent rise in value to $32.6M over the same period. “Australian berry sectors are in a firm position at the moment,” she said. “Production, adoption of protected substrate cropping, improved genetics and an expanding geographic footprint have all helped put Aussie berries on a positive trajectory. “We are seeing a real transition point. Broad industry interest and a strong commercial appetite for export market development combined with the potential to capitalise on existing trade agreements and build new trade partnerships has created this perfect environment for growth.” High-income countries across Europe, North America and Northern Asia have been identified as having a palate for Australian grown berries with more than 4244 tonnes of fresh berries exported in the last financial year alone. The strategy identified the best short-term prospect markets for the Australian blackberry and raspberry industry as Hong Kong, Singapore, The United Arab Emirates and Canada. The strongest short-term trade options identified for the strawberry sector were Thailand, Malaysia, New Zealand and Macau. The strategy focuses heavily on growing the existing strawberry export market from 4 per cent to at least 8 per cent of national production by volume, in markets with a capacity and willingness to pay a premium for quality fruit. For raspberries and blackberries, the sectors aim to achieve a 5 per cent boost in exports assessed by volume across identified markets by 2021. Tasmanian raspberry exporter Nic Hansen said Australia offers some of the sweetest and most attractive berries in the world, and this combined with our stringent food safety standards across all stages of the supply chain puts growers in a solid position. “We have a great product, we are hungry to expand trade and now with this new plan in place, we have a clear roadmap towards driving growth,” Mr Hansen said. He said it is exciting to see new export market prospects for raspberries: “The more options we have for export the better. Now we just have to get on with the job of ensuring industry has all the tools it needs, such as supporting data and relationship building opportunities, to thrive in new markets.” This project was commissioned by Hort Innovation, and developed by market analysts and research consultants Auspex Strategic Advisory and AgInfinity. Hort Innovation will work now with berry sectors to determine levy-funded activities to support trade. See a summary of the strategy on the Hort Innovation website. For more information on the berry industries, refer to the Horticulture Statistics Handbook and the Strategic Investment Plans for strawberries, raspberries and blackberries. Growers seeking more information should email trade@horticulture.com.au	What is the Berry Export Summary 2028 and what is its purpose?
  RWSN Collaborations Southern Africa Self-supply Study Review of Self-supply and its support services in African countries A lady in Zimbabwe proudly shows off her onions - watered from her self-supply well © 2015 André Olschewski • Skat Project starts: 2015 Project finished: 2016 Collaborators & Partners:. Project Description UNICEF and Skat have collaborated on a). Perspectives Reach and benefits: - Self-supply is practised by millions of rural households in Sub-Sahara Africa as well as in Europe, USA and other areas of the world. - Benefits reported from having access to Self-supply water sources include convenience, less time spent for fetching water and access to more and better quality water. In some areas, Self-supply sources offer important added values such as water for productive use, income generation, family safety and improved food security. - Sustainability of services from Self-supply is high as there is strong ownership by people investing in own sources. - As Self-supply sources are shared sources, many people, including poor and vulnerable households, benefit from investments in Self-supply, often at no costs. This means that Self-supply can be effective in reaching the hard-to-reach. - For millions of people in rural areas of Africa, supported Self-supply will be the most cost effective service delivery model to provide access to safe water. This also includes those parts of the population which actually have poor access as they e.g. cannot afford water from communal supplies. - However, in areas where external support for Self-supply is lacking, only marginal improvements can usually be achieved, and the quality of services is lower than in areas where a dedicated support effort was made. Costs and business model for supported Self-supply - In many rural contexts, supported Self-supply is the most cost effective approach for water service delivery. However, as it is not applicable in all contexts, a blended approach combining communal water supply and supported Self-supply models should be followed. - Based on a Life Cycle Cost (LCC) analysis of different service delivery approaches, the LCC for communal supplies are about 40 US$/capita served in the study countries, whereas the LCC for supported Self-supply is about 10 U$/capita. - In sparsely populated areas, communal supplies (e.g. handpumps) are even more costly (up to 100 U$/capita served) as only few people can be served with one additional unit. Serving all rural people with communal supply is therefore not financially viable. - Considering the applicability of Self-supply technologies, in Zambia and Zimbabwe, the cost saving of following a blended approach using both communal supplies and supported Self-supply is almost 50% of the total LCC for reaching 100% of the population by 2030. These cost savings are equivalent to more than 330 million US$ in Zambia and more than 260 million US$ in Zimbabwe. Support services needed - Supported Self-supply is a service delivery model putting support services in place to improve Self-supply, so it is not about a particular technology. - Supported Self-supply is aligned with the Human Rights to Water and Sanitation, which allows a progressive realisation of the universal access to safe water. However, supported Self-supply is not a way to exempt government from its duties: Government has specific roles to play to ensure that everybody will have access to safe water finally. - To sustain and to take Self-supply to scale there is need for contextualised support as well as long-term engagement, capacity development at all levels, M&E and technical support, reliable funding and learning and sharing. - Interministerial cooperation and champions within government agencies are needed to ensure sustainable embedding and for taking Self-supply further, particularly in remote rural areas. - There is no-one-size-fits-all solution for supported Self-supply – for each programme, it needs a contextualized design and follow-up to achieve desired impact. - Hygiene promotion, including Household Water Treatment and Safe Storage (HWTS), is highly recommended for any non-piped water supply services, including Self-supply water sources. - The huge potential for substantially improving the level of water supply for millions of people in rural areas should be accessed through supported Self-supply. Some countries have endorsed supported Self-supply as service delivery model, such as Zimbabwe or Sierra Leone, and in Ethiopia, Self-supply is now being scaled up at national level. More Information » Review of Self-supply and its support services in African countries: Synthesis Report).	What are some of the benefits reported from having access to Self-supply water sources?
  All Android applications categories Description Coolands for Twitter is a revolutionary twitter client. It has many unique features, gives you the best mobile twitter experience you never imagined before. The first unique feature is Real-Time. You can’t find any refresh button in this app, because you absolutely don’t need to. Every time you open it, you’ll get the latest tweets and while you’re reading, you’ll get incoming tweets in Real-Time. So if your friend mentioned you, you can reply instantly. The second unique feature is Avatar Indicator. Avatar Indicator is small avatars showed on the title bar to indicate that you’ve got new message/tweet/mention. Since it’s real-time, you’ll keep getting incoming tweets while you’re reading your older timeline, Avatar-Indicator will let you know who’s tweet you’ve just got, and decide whether to check it out right away. The third unique feature is Direct Link I think it is obviously the most intuitive and convenient way to open a link. When you want to open a link, just click it in the time line . You can also click a username to open a profile window, click a hash tag to open a search result window. Different kind of links displayed in different colors, you can change it to whatever color you like. The fourth unique feature is Smart Bookmark Have you ever experienced this scenario? When you are reading your home timeline, the app notified you that you’ve got some new tweets, you click “go-to-top” button to read the newest tweets, and then you want to get back to the previous position to continue your reading. How can you do this? In other twitter clients you have to scroll down all the way to find where you were, a lot of time wasted. But in this app, “go-to-top” button will appear when you scrolling up, click it, you can got to top, read the newest tweets. After that when you scrolling down, Smart Bookmark button will appear at the corner. Click it, you can get back to exactly where you were. The fifth unique feature is User Level Notification Notification for all your new tweets is meaningless, if you following more than a few users, you’ll get new tweets all the time. What if you only want to be notified when someone you most care about posted a new tweet? In this app, it’s easy. You can change your friend’s notification setting directly in his/her profile screen. You can also set different notification ringtone for your friends respectively. So when you heard a notification ringtone, you’ll know who he/she is without the need to open your phone. And you can manage all the enabled User-Level-Notification settings in one place. Also has most of the basic twitter client features, like post/delete tweets, retweet, retweet with comment, reply, quote, send/delete direct message, subscribe/unsubscribe lists, follow/unfollow user, multiple accounts support, append picture with your tweets, mention auto complete, recent search auto complete, conversation view. Please give me feedbacks if you have tried it, and I PROMISE to reply all your emails. 1.30-1.36 update: *Ad-Free. *3 times faster when launching and loading older tweets. *Support unlimited accounts rather than 3 accounts. *Support notifications for all accounts rather than only for the current account. *Improved mention suggestion feature. *Use URL link to do RT with comment, so you can comment more characters. *Conversation view, click the orange(you can change the color) username in replied tweet to show conversation view. *Support longer tweet, longer tweet will be converted to a picture automatically. You really should try it out your self. *Refined tweet composing view, to support longer tweet. *Support handle text shared by other app. from 103 reviews Download Coolands for Twitter Free - V1.38 - 298K Sorry ... This app is no longer available. Share this app Screenshots	What are the unique features of the Coolands for Twitter app?

• Loss: MultipleNegativesRankingLoss with these parameters:

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

Evaluation Dataset

Unnamed Dataset

• Size: 8,598 evaluation samples
• Columns: positive and anchor
• Approximate statistics based on the first 1000 samples:

  	positive	anchor
  type	string	string
  details	min: 163 tokens mean: 462.59 tokens max: 512 tokens	min: 9 tokens mean: 18.61 tokens max: 58 tokens

• Samples:

  positive	anchor
  Beaver Creek is a great blend of rural scenery and modern amenities. Guests looking to swim can visit a free public beach found just outside of the campgrounds themselves, while dog enthusiasts can enjoy the over 20 miles of trails found in the area while they tucker out their canine for the evening. Camping is done here in 42 total sites, all of which provide ample space for a family with a pack of canines in tow to grill out and enjoy the stars at night. Picnic tables and fire pits are provided, as well as the option to rent a group site for an additional $52 per evening. The group area sleeps up to 35 individuals comfortably but features no extra amenities. Drinking water taps can be found just outside of the public restrooms. Although these sites provide some additional breathing room for guests, it's still crucial that you keep any visiting canines on a leash and inside of your tent overnight. Bears are a regular concern in the Idaho Panhandle National Forest, which Beaver Creek is a part of. Beaver Creek offers some great chances for dog walking and hiking. If you're a guest who's looking for a bit of a challenge, perhaps try the Navigational Trail, an almost 10-mile stretch that leads guests to the nearby Upper Preist Lake. There's also the shorter Lakeside Trail, which is more well-known for its scenic mountainside sights and easier terrain. Whichever of these you choose to explore with your dog, make sure to keep Fido on a strong restraint and pack emergency essentials for your journey in case you stumble off the beaten path or twist an ankle. Occasionally, these trails see riders on horseback, which makes consistent leash use doubly important here. Whether you want to reconnect with nature or just need a weekend getaway from the daily grind, Beaver Creek Campground is the pawfect place for your next vacay!	What amenities are provided at the Beaver Creek campgrounds?
  Presentado por: Jeff DiFazzio Estados Unidos Privilege 495 Presentado por: Jeff DiFazzio Estados Unidos Descripción 2009 Privilege 495 - Never Chartered, Circumnavigation Ready After having circumnavigated 15 years ago on another well-known make of catamaran, my wife and I felt the Privilege 495 had the perfect blend of comfort and speed to introduce our 10-year old daughter to the life of cruising. We purchased Dragonfly from the original owners in Australia in January 2016, and planned to spend 1 year cruising the Queensland Coast, but after settling in and enjoying our time onboard Dragonfly, we decided to extend our trip and explore the waters of Indonesia, Malaysia and Thailand. Having stretched our sabbatical past our initial deadline, we've decided it's now time to find Dragonfly a new owner. We are the second owners of Dragonfly, a 2009 Privilege 495. She is in very good condition and has never been chartered. Dragonfly's layout is galley up, with a spacious master cabin with large en suite. There are three additional cabins, two with en suites. Dragonfly is fully equipped with features including a 7kVA Onan Cummins genset, 100L/H water maker, Sovereign stainless steel BBQ, bow sprit with gennaker, 40kg/88lb Rocna Vulcan anchor, two 54hp Yanmar engines, and much, much more. Dragonfly is solidly built (Category A / Ocean-Going - "designed for sailing, under normal conditions of use, in wind forces exceeding 8 on the Beaufort scale"), with a high attention to design and comfort, which makes passage making or at anchor relaxing and pleasurable. Dragonfly is currently in the Phuket/Langkawi area. We are still living aboard so she is completely turn-key for anyone interested in setting sail immediately. Serious inquiries only please. Navigation Systems Raymarine integrated system - AIS, Autopilot (ST 7002), Chartplotter, Depth, Radar, Speed, Wind. Additional GPS - Furuno GP-32. Accommodations Dragonfly's layout is galley up, with a spacious master cabin with large en suite. There are three additional cabins, two are en suite. The cockpit is open and is great for entertaining. - Cabins/Berths: 4, 3 en suite - Shower: 4 - Heads: 4, Jabsco electric toilets Galley Equipment Galley-up, fully equipped - plates, utensils, chef quality knives, blender, Nespresso machine, etc. There is both a refrigerator and a freezer. - Refrigeration: Frigoboat - Freezer: Frigoboat - Stove: Sharp convection microwave - Water Capacity: 570l / 150gal - Water Maker: PureWater 100l / 26gal per hour - Hot Water System: 40l / 10.5gal Additional Equipment Sail Inventory - Mainsail: Incidences 80m2 - Headsail: Incidences 52.5m2 - Staysail: Incidences 22.5m2 - Gennaker: Incidences 86m2 - 3x ProFurl: Headsail/Staysail/Gennaker Electrics - Batteries: House: 8 x 120A, 12V / Engine: 2 x 100A, 12V / Genset: 1x 100A - Battery Charger/Inverter: Mastervolt Mass Combi 2000W / spare universal battery charger 40AMP (installed and ready for use) - Genset: Onan Cummins: 7MDKBL 7KVA, 220V, 50Hz - Sat Phone/TV: KVH Tracphone V3 and KVH Tracvision M5 - Solar: 3x Sunpower 330W, 12V, Victron Bluetooth 60 AMP Regulator - Shore Power Capacity: 50 AMP - Transformer: 4/5 kVA 110V-220V - Washing Machine: Siemens Wash & Dry 1200 Safety Gear - AIS transponder - Dyneema, 3-level lifelines - Bilge Pumps - Manual and Automatic - Life Raft - PlastimoTransocean 6-person - Epirb - GME AccuSat 406 CAT 2 - Life Jackets - 10 - Flares - Fire extinguishers Mechanical Equipment - Engine: Yanmar 54hp - 4JH4AE - Number of Engines: 2 - Engine Hours: 1865/1850 - Fuel Capacity: 650l / 170gal - Fuel Type: Diesel - Genset: Onan Cummins: 7MDKBL 7KVA, 220V, 50Hz - Propulsion: Yanmar SD50, Flexofold 3-blade folding props Total Power 108.0 kw Presentado por: Jeff DiFazzio Estados Unidos Presentado por: Jeff DiFazzio Estados Unidos Servicios - SeguroSeguro - Transporte de barcosTransporte de barcos	Who are the current owners of the Privilege 495 named Dragonfly and where did they purchase it from?
  It’s been a while since my last post (sorry!!). I’ve hand my hands full these past few weeks with finals, Coco, and Thanksgiving. Now that things are a little bit back to normal and I am officially on winter break, I have time to write a long post about what I’ve been up to. My finals in Studio Issues and Stitch, Object as Language went really well! I’ll start with what I did in my Stitch class. I finished three 12 X 6 canvases of embroidery. The title of the piece is called Time Frames and each canvas represents a season. I finished Summer for my midterm and then I finished Fall and Winter for my final. I still have to do Spring and am planning on having it finished by the end of December. As you can see they were very time consuming and I’m very proud of how they turned out. The seasons informed my colors and thought process for each piece. I did a lot of writing while I embroidered these pieces, but am only going to share a little bit of what I was thinking. My work is moving into the realm of collective memory so my personal memories are becoming obsolete for my viewers. I think writing about both personal and collective memory is very important to my work, but part of it is just for me. Fall – I was thinking a lot about changes and how nature starts to change but at the same time the structure is still the same. The frames haven’t completely lost their shape, but have changed in a distinctive way. The forms are starting to hollow out and prepare for the next step. The colors aren’t flat and the same like they were in Summer. They are blended, vibrant and consistent. Certain colors are the same throughout all the seasons and I kept this the same in my embroidery. Winter – This is where things are drastically changed. The structure is the most important and most seen element in the winter. This is where things start to distort and deconstruct. I thought a lot about a quiet still moment in the winter. The moment where the leaves are all gone and the branches finally get to be seen. Snow is sitting on the branches and it’s a perfect winter moment. There are areas of extreme change and consistency. If you look carefully you see an image of a face, but at first glance you aren’t really sure what you are seeing. Again, these colors are appropriate to the season but a few of them are in the other two seasons as well. Here is a detail of Winter. This is where I need your feedback. I’m not sure if I should hang these horizontal or vertical. So when you have a change please let me know what you prefer. Now moving on to my Studio Issues final. I worked on simple daily drawings as part of my thought process on how to start translating my work into metal. Since I didn’t have the resources to work with metal yet I did a lot of studies (paper and drawing) so that next quarter I will have a good idea of what I want to make. I also continued to work with my screen printing compositions. I decided to present them in shadow boxes and make a collage with different prints. I was thinking about dressers and vanities and how people put precious objects on them. Sometimes they put boxes with precious objects in them on either a dresser or vanity. I’ve been researching the Victorian era, mourning jewelry, and artists like Joseph Cornell and Anne Wilson. I’ve always had a fascination with tiny precious objects so that is the direction my work is going. These are the last of my daily drawings which makes 70 (one for each day of the quarter). YAY!!! These are my metal studies. I cut forms out of paper and then painted and stitched them together. Next quarter when I’m in my metals and jewelry class I want to make objects like these. This is my final presentation for my Studio Issues class. Right after finals were over I went to the Columbia Museum of Art in Columbia, SC. It was a charming little art museum. I went to see Dale Chihuly’s Seaforms exhibition. It was set up as clusters of sea forms and some of his drawings were on display as well. The colors were beautiful and his compositions were inspirational. I was really excited that I got to see his work and hopefully will see it again sometime. This week I’m going to Sarasota, FL to visit my aunt and uncle. I’ll also be going to the American Craft Show in Sarasota. I’m really excited to be able to visit family and see this show! I’m going to leave you with a few new pictures of Coco and I’ll post again when I’m back in Savannah. Abby~I like your new posting. I know that you spent hours on your canvases. I think that I like them hung horizontally the best. Your metal studies are very interesting. Coco is precious!	What is the title of the embroidery piece the author created in their Stitch class?

• 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: 20
• per_device_eval_batch_size: 20
• num_train_epochs: 1
• warmup_ratio: 0.1
• fp16: True
• 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: 20
• per_device_eval_batch_size: 20
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 1
• eval_accumulation_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: 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: 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
• batch_sampler: no_duplicates
• multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	loss
0.01	1	-	0.1747
0.04	2	-	0.1662
0.06	3	-	0.1445
0.08	4	-	0.1257
0.1	5	0.2123	0.1112
0.12	6	-	0.0996
0.14	7	-	0.0915
0.16	8	-	0.0859
0.18	9	-	0.0818
0.2	10	0.1144	0.0782
0.22	11	-	0.0752
0.24	12	-	0.0728
0.26	13	-	0.0709
0.28	14	-	0.0696
0.3	15	0.0478	0.0686
0.32	16	-	0.0680
0.34	17	-	0.0675
0.36	18	-	0.0672
0.38	19	-	0.0671
0.4	20	0.17	0.0668
0.42	21	-	0.0665
0.44	22	-	0.0664
0.46	23	-	0.0663
0.48	24	-	0.0661
0.5	25	0.0925	0.0660
0.52	26	-	0.0657
0.54	27	-	0.0656
0.56	28	-	0.0654
0.58	29	-	0.0651
0.6	30	0.0643	0.0648
0.62	31	-	0.0646
0.64	32	-	0.0644
0.66	33	-	0.0642
0.68	34	-	0.0639
0.7	35	0.0565	0.0637
0.72	36	-	0.0635
0.74	37	-	0.0632
0.76	38	-	0.0630
0.78	39	-	0.0628
0.8	40	0.0649	0.0627
0.82	41	-	0.0626
0.84	42	-	0.0624
0.86	43	-	0.0623
0.88	44	-	0.0621
0.9	45	0.1115	0.0620
0.92	46	-	0.0619
0.94	47	-	0.0618
0.96	48	-	0.0617
0.98	49	-	0.0616
1.0	50	0.157	0.0616

Framework Versions

• Python: 3.10.12
• Sentence Transformers: 3.0.1
• Transformers: 4.42.4
• PyTorch: 2.3.1+cu121
• Accelerate: 0.27.0
• Datasets: 2.20.0
• 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}
}