Sentence Similarity
sentence-transformers
Safetensors
English
roberta
datadreamer
datadreamer-0.35.0
Synthetic
feature-extraction
text-embeddings-inference
Instructions to use StyleDistance/styledistance with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use StyleDistance/styledistance with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("StyleDistance/styledistance") sentences = [ "Did you hear about the Wales wing? He'll h8 2 withdraw due 2 injuries from future competitions.", "We're raising funds 2 improve our school's storage facilities and add new playground equipment!", "Did you hear about the Wales wing? He'll hate to withdraw due to injuries from future competitions." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Inference
- Notebooks
- Google Colab
- Kaggle
Pushed by DataDreamer
Browse filesUpdate training_args.json
- training_args.json +3 -3
training_args.json
CHANGED
|
@@ -13,13 +13,13 @@
|
|
| 13 |
"gradient_accumulation_steps": 1,
|
| 14 |
"eval_accumulation_steps": 1,
|
| 15 |
"eval_delay": 0,
|
| 16 |
-
"learning_rate": 0.
|
| 17 |
"weight_decay": 0.01,
|
| 18 |
"adam_beta1": 0.9,
|
| 19 |
"adam_beta2": 0.999,
|
| 20 |
"adam_epsilon": 1e-08,
|
| 21 |
"max_grad_norm": 1.0,
|
| 22 |
-
"num_train_epochs":
|
| 23 |
"max_steps": -1,
|
| 24 |
"lr_scheduler_type": "linear",
|
| 25 |
"lr_scheduler_kwargs": {},
|
|
@@ -28,7 +28,7 @@
|
|
| 28 |
"log_level": "passive",
|
| 29 |
"log_level_replica": "warning",
|
| 30 |
"log_on_each_node": true,
|
| 31 |
-
"logging_dir": "./output/train-styledistance-model/_checkpoints/runs/Jul17_08-
|
| 32 |
"logging_strategy": "steps",
|
| 33 |
"logging_first_step": false,
|
| 34 |
"logging_steps": 1,
|
|
|
|
| 13 |
"gradient_accumulation_steps": 1,
|
| 14 |
"eval_accumulation_steps": 1,
|
| 15 |
"eval_delay": 0,
|
| 16 |
+
"learning_rate": 0.0001,
|
| 17 |
"weight_decay": 0.01,
|
| 18 |
"adam_beta1": 0.9,
|
| 19 |
"adam_beta2": 0.999,
|
| 20 |
"adam_epsilon": 1e-08,
|
| 21 |
"max_grad_norm": 1.0,
|
| 22 |
+
"num_train_epochs": 10,
|
| 23 |
"max_steps": -1,
|
| 24 |
"lr_scheduler_type": "linear",
|
| 25 |
"lr_scheduler_kwargs": {},
|
|
|
|
| 28 |
"log_level": "passive",
|
| 29 |
"log_level_replica": "warning",
|
| 30 |
"log_on_each_node": true,
|
| 31 |
+
"logging_dir": "./output/train-styledistance-model/_checkpoints/runs/Jul17_08-37-06_nlpgpu04.seas.upenn.edu",
|
| 32 |
"logging_strategy": "steps",
|
| 33 |
"logging_first_step": false,
|
| 34 |
"logging_steps": 1,
|