Sentence Similarity
sentence-transformers
Safetensors
bert
feature-extraction
Generated from Trainer
dataset_size:6300
loss:CachedMultipleNegativesRankingLoss
text-embeddings-inference
Instructions to use truong1301/bi-encode-HG-DOCS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use truong1301/bi-encode-HG-DOCS with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("truong1301/bi-encode-HG-DOCS") sentences = [ "How can AnimateDiff, a motion adapter for pretrained diffusion models, be used to generate videos from images?", "Performs a single real input radix-2 transformation on the provided data Kind: instance method ofP2FFT The input data array The output data array The output offset The input offset The step", "AnimateDiffis an adapter model that inserts a motion module into a pretrained diffusion model to animate an image. The adapter is trained on video clips to learn motion which is used to condition the generation process to create a video. It is faster and easier to only train the adapter and it can be loaded into most diffusion models, effectively turning them into “video models”. Start by loading aMotionAdapter. Then load a finetuned Stable Diffusion model with theAnimateDiffPipeline. Create a prompt and generate the video.", "Utility class to handle streaming of tokens generated by whisper speech-to-text models. Callback functions are invoked when each of the following events occur: Kind: static class ofgeneration/streamers" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
Download trainer_state.json from truong1301/bi-encode-HG-DOCS: direct link, hf CLI and curl.
- Browser
- Download file 1.95 kB
-
https://huggingface.co/truong1301/bi-encode-HG-DOCS/resolve/main/trainer_state.json
- Command line
-
hf download hf://truong1301/bi-encode-HG-DOCS/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/truong1301/bi-encode-HG-DOCS/resolve/main/trainer_state.json
1.95 kB
| { | |
| "best_metric": 0.034021906554698944, | |
| "best_model_checkpoint": "models/HG/checkpoint-600", | |
| "epoch": 3.045685279187817, | |
| "eval_steps": 200, | |
| "global_step": 600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.015228426395939, | |
| "grad_norm": 0.2426794022321701, | |
| "learning_rate": 6.349206349206349e-06, | |
| "loss": 0.0262, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.015228426395939, | |
| "eval_loss": 0.037922926247119904, | |
| "eval_runtime": 1.4442, | |
| "eval_samples_per_second": 484.703, | |
| "eval_steps_per_second": 15.234, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.030456852791878, | |
| "grad_norm": 0.3046327233314514, | |
| "learning_rate": 1.2698412698412699e-05, | |
| "loss": 0.0159, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.030456852791878, | |
| "eval_loss": 0.03600747138261795, | |
| "eval_runtime": 1.4409, | |
| "eval_samples_per_second": 485.792, | |
| "eval_steps_per_second": 15.268, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.045685279187817, | |
| "grad_norm": 0.08811034262180328, | |
| "learning_rate": 1.904761904761905e-05, | |
| "loss": 0.0082, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.045685279187817, | |
| "eval_loss": 0.034021906554698944, | |
| "eval_runtime": 1.4347, | |
| "eval_samples_per_second": 487.892, | |
| "eval_steps_per_second": 15.334, | |
| "step": 600 | |
| } | |
| ], | |
| "logging_steps": 200, | |
| "max_steps": 985, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |