File size: 24,511 Bytes
5f50c1d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 |
---
base_model: distilbert/distilroberta-base
datasets: []
language: []
library_name: sentence-transformers
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:4093
- loss:TripletLoss
widget:
- source_sentence: I am angry about an incident at the supermarket, and it has been
bothering me for the last three or four days. The person involved was flirting
with me, and I think they should apologize. I didn't ask for an apology or indicate
that I was upset during the conversation because I felt it would be inappropriate.
I believe they should call me and set aside an appropriate time to apologize.
sentences:
- If you are a counsellor, please answer the questions based on the description
of the patient.
- It seems like this incident really impacted you and you believe that an apology
is necessary for closure. It's understandable that you didn't address it on the
spot if you felt it was inappropriate. However, people sometimes don't realize
they've upset someone unless it's brought to their attention. Since you feel so
strongly about this, have you considered reaching out to the person to express
your feelings and provide them an opportunity to apologize?
- It sounds like you have built a strong support system in San Diego with meaningful
relationships and emotional investments. It's natural to feel apprehensive about
moving away from that. Maybe you could consider the potential opportunities that
LA has to offer and weigh them against what you would be leaving behind in San
Diego. Additionally, think about the ways you can stay connected with your loved
ones after moving. Just remember that it's a difficult decision, and it's important
to give yourself time to make the best choice for you.
- source_sentence: Lately, I've been feeling a bit overwhelmed with everything going
on in my life. I've been hearing things that aren't really there, like whispers
and someone calling my name, but it's not happening all the time, just occasionally.
I also find myself getting a bit disorganized, but I wouldn't say I'm completely
disorganized. Sometimes, I just feel disconnected with what is happening around
me. I've been like this for a couple of weeks now. My parents said that I've been
acting differently, but I don't know, maybe I'm just overreacting? Can you help
me with this?
sentences:
- If you are a counsellor, please answer the questions based on the description
of the patient.
- Thank you for sharing your experience with me. I can understand how hearing things
and feeling disorganized might be confusing and concerning for you. It's important
to discuss these symptoms and feelings in order to provide proper support. Can
you tell me if you've experienced any changes in your mood, daily activities,
or sleep habits during this time? Also, have you noticed any patterns or triggers
for when you hear the whispers or feel disconnected from what's happening around
you?
- I appreciate you sharing your feelings and experiences with me. It sounds like
you're going through a challenging period in your life, dealing with stress and
worry. It's important to understand the factors contributing to your stress and
how they might be influencing your thoughts and emotions. Could you provide some
more specific examples of the situations that have caused you to feel stressed
and worried? Additionally, have you noticed any patterns or triggers that seem
to make your worries more intense?
- source_sentence: I've been experiencing anxiety due to the difficult transition
from being at home, taking care of my son, to moving back into the work world.
I've been trying to manage this anxiety by paying attention to nutrition, exercise,
and practicing gratitude. Although I feel like I'm managing better now than when
I first started, I'm still struggling.
sentences:
- It's great to hear that you've made some progress in managing your anxiety through
healthy practices like focusing on nutrition, exercise, and gratitude. It's common
for individuals to face challenges while transitioning between roles, and it might
take more time for you to adjust fully. If you still find yourself struggling,
consider seeking additional support through therapy or support groups. Is there
a specific aspect of this transition that continues to cause you worry?
- If you are a counsellor, please answer the questions based on the description
of the patient.
- It's great to hear that you have a strong drive for self-improvement and setting
ambitious goals for yourself. Acknowledging this inner motivation is an essential
step towards achieving what you desire. Remember, it's important to embrace the
process of learning and growing, and not to put too much pressure on yourself
to reach an end goal quickly. Take it one step at a time, and don't forget to
celebrate your milestones along the way.
- source_sentence: Recently, I have been experiencing difficulties while learning.
Sometimes it's quite challenging, and I feel upset with myself to the point of
crying. However, at other times, I find it easy and feel a sense of accomplishment
when I finally get things right.
sentences:
- If you are a counsellor, please answer the questions based on the description
of the patient.
- Thank you for sharing that with me. I'm glad you're feeling better now that you're
here. Sometimes waiting can cause anxiety or stress, so it's important to find
ways to manage these feelings. If you'd like, we can discuss some coping strategies
for dealing with stress while waiting or in similar situations.
- It seems like you've been having ups and downs with your learning experience.
It's great that you sometimes feel accomplished when you finally understand something.
When you're feeling upset or frustrated, it might be helpful to take a break and
come back to it later, as you've mentioned. This can give you a fresh perspective
and may help reduce stress. It's also important to remember that learning is a
process, and it's okay to experience difficulties along the way.
- source_sentence: I remember generating alternative predictions. We said that I might
get nervous but if I stay focused on what I want to do, I can probably do it.
It's just hard to believe when I'm in this situation.
sentences:
- It seems like you've been dealing with unexpected expenses and some impulsive
spending habits. By planning for a stricter budget and understanding the difference
between essential and non-essential expenses, you can start to develop healthy
financial habits. Have you considered creating a budget plan and setting aside
a specific amount for unexpected expenses to help manage your spending?
- It's normal to feel nervous in difficult situations. As a counsellor, I suggest
continuing to test these alternative predictions directly in real-life experiences.
As you encounter situations where you manage to handle things even while nervous,
your belief in your abilities and the predictions will strengthen. Remember to
stay focused and trust yourself.
- If you are a counsellor, please answer the questions based on the description
of the patient.
---
# SentenceTransformer based on distilbert/distilroberta-base
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [distilbert/distilroberta-base](https://huggingface.co/distilbert/distilroberta-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:** [distilbert/distilroberta-base](https://huggingface.co/distilbert/distilroberta-base) <!-- at revision fb53ab8802853c8e4fbdbcd0529f21fc6f459b2b -->
- **Maximum Sequence Length:** 512 tokens
- **Output Dimensionality:** 768 tokens
- **Similarity Function:** Cosine Similarity
<!-- - **Training Dataset:** Unknown -->
<!-- - **Language:** Unknown -->
<!-- - **License:** Unknown -->
### 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': 512, 'do_lower_case': False}) with Transformer model: RobertaModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)
```
## Usage
### Direct Usage (Sentence Transformers)
First install the Sentence Transformers library:
```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("iqrakiran/my-sentence-transformer-model")
# Run inference
sentences = [
"I remember generating alternative predictions. We said that I might get nervous but if I stay focused on what I want to do, I can probably do it. It's just hard to believe when I'm in this situation.",
"It's normal to feel nervous in difficult situations. As a counsellor, I suggest continuing to test these alternative predictions directly in real-life experiences. As you encounter situations where you manage to handle things even while nervous, your belief in your abilities and the predictions will strengthen. Remember to stay focused and trust yourself.",
'If you are a counsellor, please answer the questions based on the description of the patient.',
]
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]
```
<!--
### Direct Usage (Transformers)
<details><summary>Click to see the direct usage in Transformers</summary>
</details>
-->
<!--
### Downstream Usage (Sentence Transformers)
You can finetune this model on your own dataset.
<details><summary>Click to expand</summary>
</details>
-->
<!--
### Out-of-Scope Use
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
-->
<!--
## Bias, Risks and Limitations
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
-->
<!--
### Recommendations
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
-->
## Training Details
### Training Dataset
#### Unnamed Dataset
* Size: 4,093 training samples
* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>sentence_2</code>
* Approximate statistics based on the first 1000 samples:
| | sentence_0 | sentence_1 | sentence_2 |
|:--------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
| type | string | string | string |
| details | <ul><li>min: 11 tokens</li><li>mean: 57.82 tokens</li><li>max: 197 tokens</li></ul> | <ul><li>min: 30 tokens</li><li>mean: 76.95 tokens</li><li>max: 149 tokens</li></ul> | <ul><li>min: 22 tokens</li><li>mean: 22.0 tokens</li><li>max: 22 tokens</li></ul> |
* Samples:
| sentence_0 | sentence_1 | sentence_2 |
|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------|
| <code>Lately, I've been feeling really stressed out and I keep having this thought that my partner might be cheating on me. It started when I noticed changes in their behavior a couple of months ago. At times, I feel like my partner acts distant, but when I confront them about it, they assure me that everything is fine between us. I feel like maybe it's not a strong enough thought to be classified as a delusion, but it's really bothering me and affecting our relationship.</code> | <code>Thank you for sharing your concerns and feelings with me. It's important to know that it's normal for people to experience doubts and insecurities in relationships sometimes. I understand that feeling stressed and having negative thoughts is difficult to deal with. If you're open to it, perhaps we could explore these thoughts and feelings further to better understand their origin and find ways to cope with them. Additionally, involving your partner in a constructive conversation about your feelings and concerns might help to improve your relationship and provide reassurance.</code> | <code>If you are a counsellor, please answer the questions based on the description of the patient.</code> |
| <code>I think counting would mean that somebody cares about me and I matter to them. In my life, for example, I think Ms. Jones is upset that I am not as involved or doing the things that she saw me do last year. So I guess I matter to her.</code> | <code>It's important to recognize that feeling valued and cared for by others can contribute to our overall well-being. It's great that you have someone like Ms. Jones in your life who notices your changes and seems to care about you. Can you tell me more about your relationship with Ms. Jones or the changes that have occurred in the past year?</code> | <code>If you are a counsellor, please answer the questions based on the description of the patient.</code> |
| <code>Lately, I've been feeling quite down, and it's been affecting my daily life. I've also been having a hard time concentrating and making decisions, and often find myself lost in thought. On top of that, I've started hearing voices that aren't there, but it only happens occasionally. It all started when I moved to a new city a few months ago. I feel so isolated, and the stress of adjusting to a new environment might be causing these issues.</code> | <code>Thank you for sharing your feelings and experiences with me. It sounds like you are struggling with some challenging emotions and experiences since your move to a new city. Adjusting to a new environment can be a significant source of stress. It's essential to acknowledge what you're going through and understand that seeking help is healthy. Can you provide further details about the voices you've been hearing? How often do they occur, and how exactly do they affect your daily life? Also, can you share your previous mental health history, if any? Your additional information will help me get a better understanding of your situation and provide the best support possible.</code> | <code>If you are a counsellor, please answer the questions based on the description of the patient.</code> |
* Loss: [<code>TripletLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#tripletloss) with these parameters:
```json
{
"distance_metric": "TripletDistanceMetric.EUCLIDEAN",
"triplet_margin": 5
}
```
### Training Hyperparameters
#### Non-Default Hyperparameters
- `per_device_train_batch_size`: 16
- `per_device_eval_batch_size`: 16
- `num_train_epochs`: 10
- `multi_dataset_batch_sampler`: round_robin
#### All Hyperparameters
<details><summary>Click to expand</summary>
- `overwrite_output_dir`: False
- `do_predict`: False
- `eval_strategy`: no
- `prediction_loss_only`: True
- `per_device_train_batch_size`: 16
- `per_device_eval_batch_size`: 16
- `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`: 10
- `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}
- `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`: batch_sampler
- `multi_dataset_batch_sampler`: round_robin
</details>
### Training Logs
| Epoch | Step | Training Loss |
|:------:|:----:|:-------------:|
| 1.9531 | 500 | 0.2321 |
| 3.9062 | 1000 | 0.0 |
| 5.8594 | 1500 | 0.0001 |
| 7.8125 | 2000 | 0.0 |
| 9.7656 | 2500 | 0.0 |
### Framework Versions
- Python: 3.10.12
- Sentence Transformers: 3.0.1
- Transformers: 4.44.2
- PyTorch: 2.4.0+cu121
- Accelerate: 0.33.0
- Datasets: 2.21.0
- Tokenizers: 0.19.1
## 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",
}
```
#### TripletLoss
```bibtex
@misc{hermans2017defense,
title={In Defense of the Triplet Loss for Person Re-Identification},
author={Alexander Hermans and Lucas Beyer and Bastian Leibe},
year={2017},
eprint={1703.07737},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
```
<!--
## Glossary
*Clearly define terms in order to be accessible across audiences.*
-->
<!--
## Model Card Authors
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
-->
<!--
## Model Card Contact
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
--> |