Sentence Similarity
sentence-transformers
Safetensors
English
onet
occupation-classification
job-title-normalization
soc-codes
career-exploration
resume-parsing
reranker
riasec
Instructions to use BenjaminChan12/onet-match with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use BenjaminChan12/onet-match with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("BenjaminChan12/onet-match") sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
Download biencoder/training.json from BenjaminChan12/onet-match: direct link, hf CLI and curl.
- Browser
- Download file 10.5 kB
-
https://huggingface.co/BenjaminChan12/onet-match/resolve/main/biencoder/training.json
- Command line
-
hf download hf://BenjaminChan12/onet-match/biencoder/training.json
-
curl -L -o training.json https://huggingface.co/BenjaminChan12/onet-match/resolve/main/biencoder/training.json
10.5 kB
| { | |
| "base_model": "BAAI/bge-base-en-v1.5", | |
| "examples": 86430, | |
| "columns": [ | |
| "anchor", | |
| "positive", | |
| "negative" | |
| ], | |
| "epochs": 1.0, | |
| "max_steps": -1, | |
| "batch_size": 32, | |
| "learning_rate": 2e-05, | |
| "max_seq_length": 256, | |
| "bf16": true, | |
| "train_seconds": 3487.3421123339795, | |
| "steps": 2700, | |
| "loss_history": [ | |
| { | |
| "loss": 1.90216064453125, | |
| "grad_norm": 8.813470840454102, | |
| "learning_rate": 3.6296296296296302e-06, | |
| "epoch": 0.018518518518518517, | |
| "step": 50 | |
| }, | |
| { | |
| "loss": 1.5914712524414063, | |
| "grad_norm": 8.136347770690918, | |
| "learning_rate": 7.333333333333333e-06, | |
| "epoch": 0.037037037037037035, | |
| "step": 100 | |
| }, | |
| { | |
| "loss": 1.3720103454589845, | |
| "grad_norm": 9.455537796020508, | |
| "learning_rate": 1.1037037037037036e-05, | |
| "epoch": 0.05555555555555555, | |
| "step": 150 | |
| }, | |
| { | |
| "loss": 1.2407678985595703, | |
| "grad_norm": 9.676878929138184, | |
| "learning_rate": 1.4740740740740741e-05, | |
| "epoch": 0.07407407407407407, | |
| "step": 200 | |
| }, | |
| { | |
| "loss": 1.193242645263672, | |
| "grad_norm": 10.449532508850098, | |
| "learning_rate": 1.8444444444444448e-05, | |
| "epoch": 0.09259259259259259, | |
| "step": 250 | |
| }, | |
| { | |
| "loss": 1.1975428771972656, | |
| "grad_norm": 6.2368316650390625, | |
| "learning_rate": 1.9761316872427985e-05, | |
| "epoch": 0.1111111111111111, | |
| "step": 300 | |
| }, | |
| { | |
| "loss": 1.1544525146484375, | |
| "grad_norm": 10.520587921142578, | |
| "learning_rate": 1.934979423868313e-05, | |
| "epoch": 0.12962962962962962, | |
| "step": 350 | |
| }, | |
| { | |
| "loss": 1.1772991180419923, | |
| "grad_norm": 9.233002662658691, | |
| "learning_rate": 1.8938271604938275e-05, | |
| "epoch": 0.14814814814814814, | |
| "step": 400 | |
| }, | |
| { | |
| "loss": 1.1016326904296876, | |
| "grad_norm": 8.162128448486328, | |
| "learning_rate": 1.8526748971193416e-05, | |
| "epoch": 0.16666666666666666, | |
| "step": 450 | |
| }, | |
| { | |
| "loss": 1.0493043518066407, | |
| "grad_norm": 9.731849670410156, | |
| "learning_rate": 1.811522633744856e-05, | |
| "epoch": 0.18518518518518517, | |
| "step": 500 | |
| }, | |
| { | |
| "loss": 1.0801094055175782, | |
| "grad_norm": 9.363628387451172, | |
| "learning_rate": 1.7703703703703706e-05, | |
| "epoch": 0.2037037037037037, | |
| "step": 550 | |
| }, | |
| { | |
| "loss": 1.0625296783447267, | |
| "grad_norm": 9.028554916381836, | |
| "learning_rate": 1.7292181069958848e-05, | |
| "epoch": 0.2222222222222222, | |
| "step": 600 | |
| }, | |
| { | |
| "loss": 1.0570863342285157, | |
| "grad_norm": 9.345087051391602, | |
| "learning_rate": 1.6880658436213993e-05, | |
| "epoch": 0.24074074074074073, | |
| "step": 650 | |
| }, | |
| { | |
| "loss": 1.0371737670898438, | |
| "grad_norm": 9.374702453613281, | |
| "learning_rate": 1.6469135802469135e-05, | |
| "epoch": 0.25925925925925924, | |
| "step": 700 | |
| }, | |
| { | |
| "loss": 1.024561767578125, | |
| "grad_norm": 8.52325439453125, | |
| "learning_rate": 1.6057613168724283e-05, | |
| "epoch": 0.2777777777777778, | |
| "step": 750 | |
| }, | |
| { | |
| "loss": 1.0370603179931641, | |
| "grad_norm": 8.593149185180664, | |
| "learning_rate": 1.5646090534979425e-05, | |
| "epoch": 0.2962962962962963, | |
| "step": 800 | |
| }, | |
| { | |
| "loss": 1.0390088653564453, | |
| "grad_norm": 12.433076858520508, | |
| "learning_rate": 1.523456790123457e-05, | |
| "epoch": 0.3148148148148148, | |
| "step": 850 | |
| }, | |
| { | |
| "loss": 1.0581689453125, | |
| "grad_norm": 10.47889232635498, | |
| "learning_rate": 1.4823045267489713e-05, | |
| "epoch": 0.3333333333333333, | |
| "step": 900 | |
| }, | |
| { | |
| "loss": 0.9768775939941406, | |
| "grad_norm": 9.974201202392578, | |
| "learning_rate": 1.4411522633744856e-05, | |
| "epoch": 0.35185185185185186, | |
| "step": 950 | |
| }, | |
| { | |
| "loss": 1.0329425048828125, | |
| "grad_norm": 9.894181251525879, | |
| "learning_rate": 1.4e-05, | |
| "epoch": 0.37037037037037035, | |
| "step": 1000 | |
| }, | |
| { | |
| "loss": 0.9404330444335938, | |
| "grad_norm": 8.047454833984375, | |
| "learning_rate": 1.3588477366255147e-05, | |
| "epoch": 0.3888888888888889, | |
| "step": 1050 | |
| }, | |
| { | |
| "loss": 0.9647300720214844, | |
| "grad_norm": 8.719392776489258, | |
| "learning_rate": 1.317695473251029e-05, | |
| "epoch": 0.4074074074074074, | |
| "step": 1100 | |
| }, | |
| { | |
| "loss": 0.9528901672363281, | |
| "grad_norm": 8.965869903564453, | |
| "learning_rate": 1.2765432098765433e-05, | |
| "epoch": 0.42592592592592593, | |
| "step": 1150 | |
| }, | |
| { | |
| "loss": 0.9591020202636719, | |
| "grad_norm": 7.550216197967529, | |
| "learning_rate": 1.2353909465020576e-05, | |
| "epoch": 0.4444444444444444, | |
| "step": 1200 | |
| }, | |
| { | |
| "loss": 0.9727952575683594, | |
| "grad_norm": 8.96568489074707, | |
| "learning_rate": 1.1942386831275721e-05, | |
| "epoch": 0.46296296296296297, | |
| "step": 1250 | |
| }, | |
| { | |
| "loss": 0.9985672760009766, | |
| "grad_norm": 9.428631782531738, | |
| "learning_rate": 1.1530864197530865e-05, | |
| "epoch": 0.48148148148148145, | |
| "step": 1300 | |
| }, | |
| { | |
| "loss": 0.91361083984375, | |
| "grad_norm": 9.939436912536621, | |
| "learning_rate": 1.1119341563786008e-05, | |
| "epoch": 0.5, | |
| "step": 1350 | |
| }, | |
| { | |
| "loss": 0.9103067779541015, | |
| "grad_norm": 8.720749855041504, | |
| "learning_rate": 1.0707818930041153e-05, | |
| "epoch": 0.5185185185185185, | |
| "step": 1400 | |
| }, | |
| { | |
| "loss": 0.9731829833984375, | |
| "grad_norm": 9.771732330322266, | |
| "learning_rate": 1.0296296296296298e-05, | |
| "epoch": 0.5370370370370371, | |
| "step": 1450 | |
| }, | |
| { | |
| "loss": 0.9493965148925781, | |
| "grad_norm": 8.45134449005127, | |
| "learning_rate": 9.884773662551441e-06, | |
| "epoch": 0.5555555555555556, | |
| "step": 1500 | |
| }, | |
| { | |
| "loss": 0.9376078796386719, | |
| "grad_norm": 9.039739608764648, | |
| "learning_rate": 9.473251028806585e-06, | |
| "epoch": 0.5740740740740741, | |
| "step": 1550 | |
| }, | |
| { | |
| "loss": 0.9816674041748047, | |
| "grad_norm": 7.672746658325195, | |
| "learning_rate": 9.06172839506173e-06, | |
| "epoch": 0.5925925925925926, | |
| "step": 1600 | |
| }, | |
| { | |
| "loss": 0.9149788665771484, | |
| "grad_norm": 8.232927322387695, | |
| "learning_rate": 8.650205761316873e-06, | |
| "epoch": 0.6111111111111112, | |
| "step": 1650 | |
| }, | |
| { | |
| "loss": 0.8861636352539063, | |
| "grad_norm": 8.584454536437988, | |
| "learning_rate": 8.238683127572016e-06, | |
| "epoch": 0.6296296296296297, | |
| "step": 1700 | |
| }, | |
| { | |
| "loss": 0.91272216796875, | |
| "grad_norm": 9.116938591003418, | |
| "learning_rate": 7.82716049382716e-06, | |
| "epoch": 0.6481481481481481, | |
| "step": 1750 | |
| }, | |
| { | |
| "loss": 0.9235337829589844, | |
| "grad_norm": 8.22610092163086, | |
| "learning_rate": 7.415637860082306e-06, | |
| "epoch": 0.6666666666666666, | |
| "step": 1800 | |
| }, | |
| { | |
| "loss": 0.8774665069580078, | |
| "grad_norm": 8.568593978881836, | |
| "learning_rate": 7.004115226337449e-06, | |
| "epoch": 0.6851851851851852, | |
| "step": 1850 | |
| }, | |
| { | |
| "loss": 0.94243896484375, | |
| "grad_norm": 9.386469841003418, | |
| "learning_rate": 6.592592592592592e-06, | |
| "epoch": 0.7037037037037037, | |
| "step": 1900 | |
| }, | |
| { | |
| "loss": 0.9301541137695313, | |
| "grad_norm": 8.318994522094727, | |
| "learning_rate": 6.181069958847737e-06, | |
| "epoch": 0.7222222222222222, | |
| "step": 1950 | |
| }, | |
| { | |
| "loss": 0.8816480255126953, | |
| "grad_norm": 9.569400787353516, | |
| "learning_rate": 5.769547325102881e-06, | |
| "epoch": 0.7407407407407407, | |
| "step": 2000 | |
| }, | |
| { | |
| "loss": 0.8695026397705078, | |
| "grad_norm": 9.273565292358398, | |
| "learning_rate": 5.358024691358025e-06, | |
| "epoch": 0.7592592592592593, | |
| "step": 2050 | |
| }, | |
| { | |
| "loss": 0.9352601623535156, | |
| "grad_norm": 7.18208122253418, | |
| "learning_rate": 4.946502057613169e-06, | |
| "epoch": 0.7777777777777778, | |
| "step": 2100 | |
| }, | |
| { | |
| "loss": 0.8622205352783203, | |
| "grad_norm": 8.226902961730957, | |
| "learning_rate": 4.534979423868313e-06, | |
| "epoch": 0.7962962962962963, | |
| "step": 2150 | |
| }, | |
| { | |
| "loss": 0.8260211944580078, | |
| "grad_norm": 6.862387657165527, | |
| "learning_rate": 4.123456790123457e-06, | |
| "epoch": 0.8148148148148148, | |
| "step": 2200 | |
| }, | |
| { | |
| "loss": 0.8789755249023438, | |
| "grad_norm": 7.918735980987549, | |
| "learning_rate": 3.711934156378601e-06, | |
| "epoch": 0.8333333333333334, | |
| "step": 2250 | |
| }, | |
| { | |
| "loss": 0.8760028839111328, | |
| "grad_norm": 8.552267074584961, | |
| "learning_rate": 3.3004115226337452e-06, | |
| "epoch": 0.8518518518518519, | |
| "step": 2300 | |
| }, | |
| { | |
| "loss": 0.8948245239257813, | |
| "grad_norm": 10.386996269226074, | |
| "learning_rate": 2.888888888888889e-06, | |
| "epoch": 0.8703703703703703, | |
| "step": 2350 | |
| }, | |
| { | |
| "loss": 0.8505097198486328, | |
| "grad_norm": 7.5803303718566895, | |
| "learning_rate": 2.477366255144033e-06, | |
| "epoch": 0.8888888888888888, | |
| "step": 2400 | |
| }, | |
| { | |
| "loss": 0.8824570465087891, | |
| "grad_norm": 7.346485614776611, | |
| "learning_rate": 2.065843621399177e-06, | |
| "epoch": 0.9074074074074074, | |
| "step": 2450 | |
| }, | |
| { | |
| "loss": 0.8907173156738282, | |
| "grad_norm": 6.8943634033203125, | |
| "learning_rate": 1.6543209876543213e-06, | |
| "epoch": 0.9259259259259259, | |
| "step": 2500 | |
| }, | |
| { | |
| "loss": 0.818727798461914, | |
| "grad_norm": 7.4995036125183105, | |
| "learning_rate": 1.242798353909465e-06, | |
| "epoch": 0.9444444444444444, | |
| "step": 2550 | |
| }, | |
| { | |
| "loss": 0.8896253967285156, | |
| "grad_norm": 9.3857421875, | |
| "learning_rate": 8.312757201646091e-07, | |
| "epoch": 0.9629629629629629, | |
| "step": 2600 | |
| }, | |
| { | |
| "loss": 0.8606999969482422, | |
| "grad_norm": 8.371380805969238, | |
| "learning_rate": 4.197530864197531e-07, | |
| "epoch": 0.9814814814814815, | |
| "step": 2650 | |
| }, | |
| { | |
| "loss": 0.8769384765625, | |
| "grad_norm": 9.072931289672852, | |
| "learning_rate": 8.23045267489712e-09, | |
| "epoch": 1.0, | |
| "step": 2700 | |
| } | |
| ], | |
| "sources": [ | |
| "title", | |
| "task", | |
| "dwa", | |
| "composite", | |
| "synthetic" | |
| ], | |
| "hard_negatives": true, | |
| "fraction": 1.0, | |
| "pairs_by_source": { | |
| "title": 37034, | |
| "task": 15059, | |
| "synthetic": 14574, | |
| "dwa": 10898, | |
| "composite": 9133 | |
| } | |
| } |