Add new SentenceTransformer model.
Browse files- 1_Pooling/config.json +10 -0
- README.md +948 -0
- config.json +58 -0
- config_sentence_transformers.json +10 -0
- model.safetensors +3 -0
- modules.json +14 -0
- sentence_bert_config.json +4 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- vocab.txt +0 -0
1_Pooling/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"word_embedding_dimension": 768,
|
| 3 |
+
"pooling_mode_cls_token": false,
|
| 4 |
+
"pooling_mode_mean_tokens": true,
|
| 5 |
+
"pooling_mode_max_tokens": false,
|
| 6 |
+
"pooling_mode_mean_sqrt_len_tokens": false,
|
| 7 |
+
"pooling_mode_weightedmean_tokens": false,
|
| 8 |
+
"pooling_mode_lasttoken": false,
|
| 9 |
+
"include_prompt": true
|
| 10 |
+
}
|
README.md
ADDED
|
@@ -0,0 +1,948 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: []
|
| 3 |
+
library_name: sentence-transformers
|
| 4 |
+
tags:
|
| 5 |
+
- sentence-transformers
|
| 6 |
+
- sentence-similarity
|
| 7 |
+
- feature-extraction
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
- dataset_size:1115700
|
| 10 |
+
- loss:MatryoshkaLoss
|
| 11 |
+
- loss:MultipleNegativesRankingLoss
|
| 12 |
+
base_model: nomic-ai/nomic-embed-text-v1.5
|
| 13 |
+
datasets: []
|
| 14 |
+
metrics:
|
| 15 |
+
- pearson_cosine
|
| 16 |
+
- spearman_cosine
|
| 17 |
+
- pearson_manhattan
|
| 18 |
+
- spearman_manhattan
|
| 19 |
+
- pearson_euclidean
|
| 20 |
+
- spearman_euclidean
|
| 21 |
+
- pearson_dot
|
| 22 |
+
- spearman_dot
|
| 23 |
+
- pearson_max
|
| 24 |
+
- spearman_max
|
| 25 |
+
widget:
|
| 26 |
+
- source_sentence: Ndege mwenye mdomo mrefu katikati ya ndege.
|
| 27 |
+
sentences:
|
| 28 |
+
- Panya anayekimbia juu ya gurudumu.
|
| 29 |
+
- Mtu anashindana katika mashindano ya mbio.
|
| 30 |
+
- Ndege anayeruka.
|
| 31 |
+
- source_sentence: Msichana mchanga mwenye nywele nyeusi anakabili kamera na kushikilia
|
| 32 |
+
mfuko wa karatasi wakati amevaa shati la machungwa na mabawa ya kipepeo yenye
|
| 33 |
+
rangi nyingi.
|
| 34 |
+
sentences:
|
| 35 |
+
- Mwanamke mzee anakataa kupigwa picha.
|
| 36 |
+
- mtu akila na mvulana mdogo kwenye kijia cha jiji
|
| 37 |
+
- Msichana mchanga anakabili kamera.
|
| 38 |
+
- source_sentence: Wanawake na watoto wameketi nje katika kivuli wakati kikundi cha
|
| 39 |
+
watoto wadogo wameketi ndani katika kivuli.
|
| 40 |
+
sentences:
|
| 41 |
+
- Mwanamke na watoto na kukaa chini.
|
| 42 |
+
- Mwanamke huyo anakimbia.
|
| 43 |
+
- Watu wanasafiri kwa baiskeli.
|
| 44 |
+
- source_sentence: Mtoto mdogo anaruka mikononi mwa mwanamke aliyevalia suti nyeusi
|
| 45 |
+
ya kuogelea akiwa kwenye dimbwi.
|
| 46 |
+
sentences:
|
| 47 |
+
- Mtoto akiruka mikononi mwa mwanamke aliyevalia suti ya kuogelea kwenye dimbwi.
|
| 48 |
+
- Someone is holding oranges and walking
|
| 49 |
+
- Mama na binti wakinunua viatu.
|
| 50 |
+
- source_sentence: Mwanamume na mwanamke wachanga waliovaa mikoba wanaweka au kuondoa
|
| 51 |
+
kitu kutoka kwenye mti mweupe wa zamani, huku watu wengine wamesimama au wameketi
|
| 52 |
+
nyuma.
|
| 53 |
+
sentences:
|
| 54 |
+
- tai huruka
|
| 55 |
+
- mwanamume na mwanamke wenye mikoba
|
| 56 |
+
- Wanaume wawili wameketi karibu na mwanamke.
|
| 57 |
+
pipeline_tag: sentence-similarity
|
| 58 |
+
model-index:
|
| 59 |
+
- name: SentenceTransformer based on nomic-ai/nomic-embed-text-v1.5
|
| 60 |
+
results:
|
| 61 |
+
- task:
|
| 62 |
+
type: semantic-similarity
|
| 63 |
+
name: Semantic Similarity
|
| 64 |
+
dataset:
|
| 65 |
+
name: sts test 768
|
| 66 |
+
type: sts-test-768
|
| 67 |
+
metrics:
|
| 68 |
+
- type: pearson_cosine
|
| 69 |
+
value: 0.6944960057464138
|
| 70 |
+
name: Pearson Cosine
|
| 71 |
+
- type: spearman_cosine
|
| 72 |
+
value: 0.6872396378196957
|
| 73 |
+
name: Spearman Cosine
|
| 74 |
+
- type: pearson_manhattan
|
| 75 |
+
value: 0.7086043588614903
|
| 76 |
+
name: Pearson Manhattan
|
| 77 |
+
- type: spearman_manhattan
|
| 78 |
+
value: 0.7136479613274518
|
| 79 |
+
name: Spearman Manhattan
|
| 80 |
+
- type: pearson_euclidean
|
| 81 |
+
value: 0.7084460037709435
|
| 82 |
+
name: Pearson Euclidean
|
| 83 |
+
- type: spearman_euclidean
|
| 84 |
+
value: 0.7128357831285198
|
| 85 |
+
name: Spearman Euclidean
|
| 86 |
+
- type: pearson_dot
|
| 87 |
+
value: 0.481902874304561
|
| 88 |
+
name: Pearson Dot
|
| 89 |
+
- type: spearman_dot
|
| 90 |
+
value: 0.46588918379526945
|
| 91 |
+
name: Spearman Dot
|
| 92 |
+
- type: pearson_max
|
| 93 |
+
value: 0.7086043588614903
|
| 94 |
+
name: Pearson Max
|
| 95 |
+
- type: spearman_max
|
| 96 |
+
value: 0.7136479613274518
|
| 97 |
+
name: Spearman Max
|
| 98 |
+
- task:
|
| 99 |
+
type: semantic-similarity
|
| 100 |
+
name: Semantic Similarity
|
| 101 |
+
dataset:
|
| 102 |
+
name: sts test 512
|
| 103 |
+
type: sts-test-512
|
| 104 |
+
metrics:
|
| 105 |
+
- type: pearson_cosine
|
| 106 |
+
value: 0.6925787246105148
|
| 107 |
+
name: Pearson Cosine
|
| 108 |
+
- type: spearman_cosine
|
| 109 |
+
value: 0.6859479129419207
|
| 110 |
+
name: Spearman Cosine
|
| 111 |
+
- type: pearson_manhattan
|
| 112 |
+
value: 0.7087290093387656
|
| 113 |
+
name: Pearson Manhattan
|
| 114 |
+
- type: spearman_manhattan
|
| 115 |
+
value: 0.7127968133455542
|
| 116 |
+
name: Spearman Manhattan
|
| 117 |
+
- type: pearson_euclidean
|
| 118 |
+
value: 0.7088805484816247
|
| 119 |
+
name: Pearson Euclidean
|
| 120 |
+
- type: spearman_euclidean
|
| 121 |
+
value: 0.7123606046721803
|
| 122 |
+
name: Spearman Euclidean
|
| 123 |
+
- type: pearson_dot
|
| 124 |
+
value: 0.4684333245586192
|
| 125 |
+
name: Pearson Dot
|
| 126 |
+
- type: spearman_dot
|
| 127 |
+
value: 0.45257836578849003
|
| 128 |
+
name: Spearman Dot
|
| 129 |
+
- type: pearson_max
|
| 130 |
+
value: 0.7088805484816247
|
| 131 |
+
name: Pearson Max
|
| 132 |
+
- type: spearman_max
|
| 133 |
+
value: 0.7127968133455542
|
| 134 |
+
name: Spearman Max
|
| 135 |
+
- task:
|
| 136 |
+
type: semantic-similarity
|
| 137 |
+
name: Semantic Similarity
|
| 138 |
+
dataset:
|
| 139 |
+
name: sts test 256
|
| 140 |
+
type: sts-test-256
|
| 141 |
+
metrics:
|
| 142 |
+
- type: pearson_cosine
|
| 143 |
+
value: 0.6876956481856266
|
| 144 |
+
name: Pearson Cosine
|
| 145 |
+
- type: spearman_cosine
|
| 146 |
+
value: 0.6814892249857147
|
| 147 |
+
name: Spearman Cosine
|
| 148 |
+
- type: pearson_manhattan
|
| 149 |
+
value: 0.7083882582081078
|
| 150 |
+
name: Pearson Manhattan
|
| 151 |
+
- type: spearman_manhattan
|
| 152 |
+
value: 0.7097524143994903
|
| 153 |
+
name: Spearman Manhattan
|
| 154 |
+
- type: pearson_euclidean
|
| 155 |
+
value: 0.7094190252305796
|
| 156 |
+
name: Pearson Euclidean
|
| 157 |
+
- type: spearman_euclidean
|
| 158 |
+
value: 0.7104287347206688
|
| 159 |
+
name: Spearman Euclidean
|
| 160 |
+
- type: pearson_dot
|
| 161 |
+
value: 0.4438925722484721
|
| 162 |
+
name: Pearson Dot
|
| 163 |
+
- type: spearman_dot
|
| 164 |
+
value: 0.4255299982188107
|
| 165 |
+
name: Spearman Dot
|
| 166 |
+
- type: pearson_max
|
| 167 |
+
value: 0.7094190252305796
|
| 168 |
+
name: Pearson Max
|
| 169 |
+
- type: spearman_max
|
| 170 |
+
value: 0.7104287347206688
|
| 171 |
+
name: Spearman Max
|
| 172 |
+
- task:
|
| 173 |
+
type: semantic-similarity
|
| 174 |
+
name: Semantic Similarity
|
| 175 |
+
dataset:
|
| 176 |
+
name: sts test 128
|
| 177 |
+
type: sts-test-128
|
| 178 |
+
metrics:
|
| 179 |
+
- type: pearson_cosine
|
| 180 |
+
value: 0.6708560165075523
|
| 181 |
+
name: Pearson Cosine
|
| 182 |
+
- type: spearman_cosine
|
| 183 |
+
value: 0.6669935075512006
|
| 184 |
+
name: Spearman Cosine
|
| 185 |
+
- type: pearson_manhattan
|
| 186 |
+
value: 0.7041961281711793
|
| 187 |
+
name: Pearson Manhattan
|
| 188 |
+
- type: spearman_manhattan
|
| 189 |
+
value: 0.7000807688296651
|
| 190 |
+
name: Spearman Manhattan
|
| 191 |
+
- type: pearson_euclidean
|
| 192 |
+
value: 0.7055061381768357
|
| 193 |
+
name: Pearson Euclidean
|
| 194 |
+
- type: spearman_euclidean
|
| 195 |
+
value: 0.7022686907818495
|
| 196 |
+
name: Spearman Euclidean
|
| 197 |
+
- type: pearson_dot
|
| 198 |
+
value: 0.37855771167572094
|
| 199 |
+
name: Pearson Dot
|
| 200 |
+
- type: spearman_dot
|
| 201 |
+
value: 0.35930717422088765
|
| 202 |
+
name: Spearman Dot
|
| 203 |
+
- type: pearson_max
|
| 204 |
+
value: 0.7055061381768357
|
| 205 |
+
name: Pearson Max
|
| 206 |
+
- type: spearman_max
|
| 207 |
+
value: 0.7022686907818495
|
| 208 |
+
name: Spearman Max
|
| 209 |
+
- task:
|
| 210 |
+
type: semantic-similarity
|
| 211 |
+
name: Semantic Similarity
|
| 212 |
+
dataset:
|
| 213 |
+
name: sts test 64
|
| 214 |
+
type: sts-test-64
|
| 215 |
+
metrics:
|
| 216 |
+
- type: pearson_cosine
|
| 217 |
+
value: 0.6533817775144477
|
| 218 |
+
name: Pearson Cosine
|
| 219 |
+
- type: spearman_cosine
|
| 220 |
+
value: 0.6523997361414113
|
| 221 |
+
name: Spearman Cosine
|
| 222 |
+
- type: pearson_manhattan
|
| 223 |
+
value: 0.6919834348567717
|
| 224 |
+
name: Pearson Manhattan
|
| 225 |
+
- type: spearman_manhattan
|
| 226 |
+
value: 0.6857245312336051
|
| 227 |
+
name: Spearman Manhattan
|
| 228 |
+
- type: pearson_euclidean
|
| 229 |
+
value: 0.6950438027503257
|
| 230 |
+
name: Pearson Euclidean
|
| 231 |
+
- type: spearman_euclidean
|
| 232 |
+
value: 0.6899151458827059
|
| 233 |
+
name: Spearman Euclidean
|
| 234 |
+
- type: pearson_dot
|
| 235 |
+
value: 0.33502302384042637
|
| 236 |
+
name: Pearson Dot
|
| 237 |
+
- type: spearman_dot
|
| 238 |
+
value: 0.3097469345046609
|
| 239 |
+
name: Spearman Dot
|
| 240 |
+
- type: pearson_max
|
| 241 |
+
value: 0.6950438027503257
|
| 242 |
+
name: Pearson Max
|
| 243 |
+
- type: spearman_max
|
| 244 |
+
value: 0.6899151458827059
|
| 245 |
+
name: Spearman Max
|
| 246 |
+
---
|
| 247 |
+
|
| 248 |
+
# SentenceTransformer based on nomic-ai/nomic-embed-text-v1.5
|
| 249 |
+
|
| 250 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [nomic-ai/nomic-embed-text-v1.5](https://huggingface.co/nomic-ai/nomic-embed-text-v1.5) on the Mollel/swahili-n_li-triplet-swh-eng dataset. 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.
|
| 251 |
+
|
| 252 |
+
## Model Details
|
| 253 |
+
|
| 254 |
+
### Model Description
|
| 255 |
+
- **Model Type:** Sentence Transformer
|
| 256 |
+
- **Base model:** [nomic-ai/nomic-embed-text-v1.5](https://huggingface.co/nomic-ai/nomic-embed-text-v1.5) <!-- at revision b0753ae76394dd36bcfb912a46018088bca48be0 -->
|
| 257 |
+
- **Maximum Sequence Length:** 8192 tokens
|
| 258 |
+
- **Output Dimensionality:** 768 tokens
|
| 259 |
+
- **Similarity Function:** Cosine Similarity
|
| 260 |
+
- **Training Dataset:**
|
| 261 |
+
- Mollel/swahili-n_li-triplet-swh-eng
|
| 262 |
+
<!-- - **Language:** Unknown -->
|
| 263 |
+
<!-- - **License:** Unknown -->
|
| 264 |
+
|
| 265 |
+
### Model Sources
|
| 266 |
+
|
| 267 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
| 268 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
| 269 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
| 270 |
+
|
| 271 |
+
### Full Model Architecture
|
| 272 |
+
|
| 273 |
+
```
|
| 274 |
+
SentenceTransformer(
|
| 275 |
+
(0): Transformer({'max_seq_length': 8192, 'do_lower_case': False}) with Transformer model: NomicBertModel
|
| 276 |
+
(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})
|
| 277 |
+
)
|
| 278 |
+
```
|
| 279 |
+
|
| 280 |
+
## Usage
|
| 281 |
+
|
| 282 |
+
### Direct Usage (Sentence Transformers)
|
| 283 |
+
|
| 284 |
+
First install the Sentence Transformers library:
|
| 285 |
+
|
| 286 |
+
```bash
|
| 287 |
+
pip install -U sentence-transformers
|
| 288 |
+
```
|
| 289 |
+
|
| 290 |
+
Then you can load this model and run inference.
|
| 291 |
+
```python
|
| 292 |
+
from sentence_transformers import SentenceTransformer
|
| 293 |
+
|
| 294 |
+
# Download from the 🤗 Hub
|
| 295 |
+
model = SentenceTransformer("Mollel/MultiLinguSwahili-nomic-embed-text-v1.5-nli-matryoshka")
|
| 296 |
+
# Run inference
|
| 297 |
+
sentences = [
|
| 298 |
+
'Mwanamume na mwanamke wachanga waliovaa mikoba wanaweka au kuondoa kitu kutoka kwenye mti mweupe wa zamani, huku watu wengine wamesimama au wameketi nyuma.',
|
| 299 |
+
'mwanamume na mwanamke wenye mikoba',
|
| 300 |
+
'tai huruka',
|
| 301 |
+
]
|
| 302 |
+
embeddings = model.encode(sentences)
|
| 303 |
+
print(embeddings.shape)
|
| 304 |
+
# [3, 768]
|
| 305 |
+
|
| 306 |
+
# Get the similarity scores for the embeddings
|
| 307 |
+
similarities = model.similarity(embeddings, embeddings)
|
| 308 |
+
print(similarities.shape)
|
| 309 |
+
# [3, 3]
|
| 310 |
+
```
|
| 311 |
+
|
| 312 |
+
<!--
|
| 313 |
+
### Direct Usage (Transformers)
|
| 314 |
+
|
| 315 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
| 316 |
+
|
| 317 |
+
</details>
|
| 318 |
+
-->
|
| 319 |
+
|
| 320 |
+
<!--
|
| 321 |
+
### Downstream Usage (Sentence Transformers)
|
| 322 |
+
|
| 323 |
+
You can finetune this model on your own dataset.
|
| 324 |
+
|
| 325 |
+
<details><summary>Click to expand</summary>
|
| 326 |
+
|
| 327 |
+
</details>
|
| 328 |
+
-->
|
| 329 |
+
|
| 330 |
+
<!--
|
| 331 |
+
### Out-of-Scope Use
|
| 332 |
+
|
| 333 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
| 334 |
+
-->
|
| 335 |
+
|
| 336 |
+
## Evaluation
|
| 337 |
+
|
| 338 |
+
### Metrics
|
| 339 |
+
|
| 340 |
+
#### Semantic Similarity
|
| 341 |
+
* Dataset: `sts-test-768`
|
| 342 |
+
* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
|
| 343 |
+
|
| 344 |
+
| Metric | Value |
|
| 345 |
+
|:--------------------|:-----------|
|
| 346 |
+
| pearson_cosine | 0.6945 |
|
| 347 |
+
| **spearman_cosine** | **0.6872** |
|
| 348 |
+
| pearson_manhattan | 0.7086 |
|
| 349 |
+
| spearman_manhattan | 0.7136 |
|
| 350 |
+
| pearson_euclidean | 0.7084 |
|
| 351 |
+
| spearman_euclidean | 0.7128 |
|
| 352 |
+
| pearson_dot | 0.4819 |
|
| 353 |
+
| spearman_dot | 0.4659 |
|
| 354 |
+
| pearson_max | 0.7086 |
|
| 355 |
+
| spearman_max | 0.7136 |
|
| 356 |
+
|
| 357 |
+
#### Semantic Similarity
|
| 358 |
+
* Dataset: `sts-test-512`
|
| 359 |
+
* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
|
| 360 |
+
|
| 361 |
+
| Metric | Value |
|
| 362 |
+
|:--------------------|:-----------|
|
| 363 |
+
| pearson_cosine | 0.6926 |
|
| 364 |
+
| **spearman_cosine** | **0.6859** |
|
| 365 |
+
| pearson_manhattan | 0.7087 |
|
| 366 |
+
| spearman_manhattan | 0.7128 |
|
| 367 |
+
| pearson_euclidean | 0.7089 |
|
| 368 |
+
| spearman_euclidean | 0.7124 |
|
| 369 |
+
| pearson_dot | 0.4684 |
|
| 370 |
+
| spearman_dot | 0.4526 |
|
| 371 |
+
| pearson_max | 0.7089 |
|
| 372 |
+
| spearman_max | 0.7128 |
|
| 373 |
+
|
| 374 |
+
#### Semantic Similarity
|
| 375 |
+
* Dataset: `sts-test-256`
|
| 376 |
+
* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
|
| 377 |
+
|
| 378 |
+
| Metric | Value |
|
| 379 |
+
|:--------------------|:-----------|
|
| 380 |
+
| pearson_cosine | 0.6877 |
|
| 381 |
+
| **spearman_cosine** | **0.6815** |
|
| 382 |
+
| pearson_manhattan | 0.7084 |
|
| 383 |
+
| spearman_manhattan | 0.7098 |
|
| 384 |
+
| pearson_euclidean | 0.7094 |
|
| 385 |
+
| spearman_euclidean | 0.7104 |
|
| 386 |
+
| pearson_dot | 0.4439 |
|
| 387 |
+
| spearman_dot | 0.4255 |
|
| 388 |
+
| pearson_max | 0.7094 |
|
| 389 |
+
| spearman_max | 0.7104 |
|
| 390 |
+
|
| 391 |
+
#### Semantic Similarity
|
| 392 |
+
* Dataset: `sts-test-128`
|
| 393 |
+
* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
|
| 394 |
+
|
| 395 |
+
| Metric | Value |
|
| 396 |
+
|:--------------------|:----------|
|
| 397 |
+
| pearson_cosine | 0.6709 |
|
| 398 |
+
| **spearman_cosine** | **0.667** |
|
| 399 |
+
| pearson_manhattan | 0.7042 |
|
| 400 |
+
| spearman_manhattan | 0.7001 |
|
| 401 |
+
| pearson_euclidean | 0.7055 |
|
| 402 |
+
| spearman_euclidean | 0.7023 |
|
| 403 |
+
| pearson_dot | 0.3786 |
|
| 404 |
+
| spearman_dot | 0.3593 |
|
| 405 |
+
| pearson_max | 0.7055 |
|
| 406 |
+
| spearman_max | 0.7023 |
|
| 407 |
+
|
| 408 |
+
#### Semantic Similarity
|
| 409 |
+
* Dataset: `sts-test-64`
|
| 410 |
+
* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
|
| 411 |
+
|
| 412 |
+
| Metric | Value |
|
| 413 |
+
|:--------------------|:-----------|
|
| 414 |
+
| pearson_cosine | 0.6534 |
|
| 415 |
+
| **spearman_cosine** | **0.6524** |
|
| 416 |
+
| pearson_manhattan | 0.692 |
|
| 417 |
+
| spearman_manhattan | 0.6857 |
|
| 418 |
+
| pearson_euclidean | 0.695 |
|
| 419 |
+
| spearman_euclidean | 0.6899 |
|
| 420 |
+
| pearson_dot | 0.335 |
|
| 421 |
+
| spearman_dot | 0.3097 |
|
| 422 |
+
| pearson_max | 0.695 |
|
| 423 |
+
| spearman_max | 0.6899 |
|
| 424 |
+
|
| 425 |
+
<!--
|
| 426 |
+
## Bias, Risks and Limitations
|
| 427 |
+
|
| 428 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
| 429 |
+
-->
|
| 430 |
+
|
| 431 |
+
<!--
|
| 432 |
+
### Recommendations
|
| 433 |
+
|
| 434 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
| 435 |
+
-->
|
| 436 |
+
|
| 437 |
+
## Training Details
|
| 438 |
+
|
| 439 |
+
### Training Dataset
|
| 440 |
+
|
| 441 |
+
#### Mollel/swahili-n_li-triplet-swh-eng
|
| 442 |
+
|
| 443 |
+
* Dataset: Mollel/swahili-n_li-triplet-swh-eng
|
| 444 |
+
* Size: 1,115,700 training samples
|
| 445 |
+
* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
|
| 446 |
+
* Approximate statistics based on the first 1000 samples:
|
| 447 |
+
| | anchor | positive | negative |
|
| 448 |
+
|:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
|
| 449 |
+
| type | string | string | string |
|
| 450 |
+
| details | <ul><li>min: 7 tokens</li><li>mean: 15.18 tokens</li><li>max: 80 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 18.53 tokens</li><li>max: 52 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 17.8 tokens</li><li>max: 53 tokens</li></ul> |
|
| 451 |
+
* Samples:
|
| 452 |
+
| anchor | positive | negative |
|
| 453 |
+
|:----------------------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------------------|
|
| 454 |
+
| <code>A person on a horse jumps over a broken down airplane.</code> | <code>A person is outdoors, on a horse.</code> | <code>A person is at a diner, ordering an omelette.</code> |
|
| 455 |
+
| <code>Mtu aliyepanda farasi anaruka juu ya ndege iliyovunjika.</code> | <code>Mtu yuko nje, juu ya farasi.</code> | <code>Mtu yuko kwenye mkahawa, akiagiza omelette.</code> |
|
| 456 |
+
| <code>Children smiling and waving at camera</code> | <code>There are children present</code> | <code>The kids are frowning</code> |
|
| 457 |
+
* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
|
| 458 |
+
```json
|
| 459 |
+
{
|
| 460 |
+
"loss": "MultipleNegativesRankingLoss",
|
| 461 |
+
"matryoshka_dims": [
|
| 462 |
+
768,
|
| 463 |
+
512,
|
| 464 |
+
256,
|
| 465 |
+
128,
|
| 466 |
+
64
|
| 467 |
+
],
|
| 468 |
+
"matryoshka_weights": [
|
| 469 |
+
1,
|
| 470 |
+
1,
|
| 471 |
+
1,
|
| 472 |
+
1,
|
| 473 |
+
1
|
| 474 |
+
],
|
| 475 |
+
"n_dims_per_step": -1
|
| 476 |
+
}
|
| 477 |
+
```
|
| 478 |
+
|
| 479 |
+
### Evaluation Dataset
|
| 480 |
+
|
| 481 |
+
#### Mollel/swahili-n_li-triplet-swh-eng
|
| 482 |
+
|
| 483 |
+
* Dataset: Mollel/swahili-n_li-triplet-swh-eng
|
| 484 |
+
* Size: 13,168 evaluation samples
|
| 485 |
+
* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
|
| 486 |
+
* Approximate statistics based on the first 1000 samples:
|
| 487 |
+
| | anchor | positive | negative |
|
| 488 |
+
|:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
|
| 489 |
+
| type | string | string | string |
|
| 490 |
+
| details | <ul><li>min: 6 tokens</li><li>mean: 26.43 tokens</li><li>max: 94 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 13.37 tokens</li><li>max: 65 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 14.7 tokens</li><li>max: 54 tokens</li></ul> |
|
| 491 |
+
* Samples:
|
| 492 |
+
| anchor | positive | negative |
|
| 493 |
+
|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------|:-------------------------------------------------------------------|
|
| 494 |
+
| <code>Two women are embracing while holding to go packages.</code> | <code>Two woman are holding packages.</code> | <code>The men are fighting outside a deli.</code> |
|
| 495 |
+
| <code>Wanawake wawili wanakumbatiana huku wakishikilia vifurushi vya kwenda.</code> | <code>Wanawake wawili wanashikilia vifurushi.</code> | <code>Wanaume hao wanapigana nje ya duka la vyakula vitamu.</code> |
|
| 496 |
+
| <code>Two young children in blue jerseys, one with the number 9 and one with the number 2 are standing on wooden steps in a bathroom and washing their hands in a sink.</code> | <code>Two kids in numbered jerseys wash their hands.</code> | <code>Two kids in jackets walk to school.</code> |
|
| 497 |
+
* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
|
| 498 |
+
```json
|
| 499 |
+
{
|
| 500 |
+
"loss": "MultipleNegativesRankingLoss",
|
| 501 |
+
"matryoshka_dims": [
|
| 502 |
+
768,
|
| 503 |
+
512,
|
| 504 |
+
256,
|
| 505 |
+
128,
|
| 506 |
+
64
|
| 507 |
+
],
|
| 508 |
+
"matryoshka_weights": [
|
| 509 |
+
1,
|
| 510 |
+
1,
|
| 511 |
+
1,
|
| 512 |
+
1,
|
| 513 |
+
1
|
| 514 |
+
],
|
| 515 |
+
"n_dims_per_step": -1
|
| 516 |
+
}
|
| 517 |
+
```
|
| 518 |
+
|
| 519 |
+
### Training Hyperparameters
|
| 520 |
+
#### Non-Default Hyperparameters
|
| 521 |
+
|
| 522 |
+
- `per_device_train_batch_size`: 24
|
| 523 |
+
- `per_device_eval_batch_size`: 24
|
| 524 |
+
- `learning_rate`: 2e-05
|
| 525 |
+
- `num_train_epochs`: 1
|
| 526 |
+
- `warmup_ratio`: 0.1
|
| 527 |
+
- `bf16`: True
|
| 528 |
+
- `batch_sampler`: no_duplicates
|
| 529 |
+
|
| 530 |
+
#### All Hyperparameters
|
| 531 |
+
<details><summary>Click to expand</summary>
|
| 532 |
+
|
| 533 |
+
- `overwrite_output_dir`: False
|
| 534 |
+
- `do_predict`: False
|
| 535 |
+
- `prediction_loss_only`: True
|
| 536 |
+
- `per_device_train_batch_size`: 24
|
| 537 |
+
- `per_device_eval_batch_size`: 24
|
| 538 |
+
- `per_gpu_train_batch_size`: None
|
| 539 |
+
- `per_gpu_eval_batch_size`: None
|
| 540 |
+
- `gradient_accumulation_steps`: 1
|
| 541 |
+
- `eval_accumulation_steps`: None
|
| 542 |
+
- `learning_rate`: 2e-05
|
| 543 |
+
- `weight_decay`: 0.0
|
| 544 |
+
- `adam_beta1`: 0.9
|
| 545 |
+
- `adam_beta2`: 0.999
|
| 546 |
+
- `adam_epsilon`: 1e-08
|
| 547 |
+
- `max_grad_norm`: 1.0
|
| 548 |
+
- `num_train_epochs`: 1
|
| 549 |
+
- `max_steps`: -1
|
| 550 |
+
- `lr_scheduler_type`: linear
|
| 551 |
+
- `lr_scheduler_kwargs`: {}
|
| 552 |
+
- `warmup_ratio`: 0.1
|
| 553 |
+
- `warmup_steps`: 0
|
| 554 |
+
- `log_level`: passive
|
| 555 |
+
- `log_level_replica`: warning
|
| 556 |
+
- `log_on_each_node`: True
|
| 557 |
+
- `logging_nan_inf_filter`: True
|
| 558 |
+
- `save_safetensors`: True
|
| 559 |
+
- `save_on_each_node`: False
|
| 560 |
+
- `save_only_model`: False
|
| 561 |
+
- `no_cuda`: False
|
| 562 |
+
- `use_cpu`: False
|
| 563 |
+
- `use_mps_device`: False
|
| 564 |
+
- `seed`: 42
|
| 565 |
+
- `data_seed`: None
|
| 566 |
+
- `jit_mode_eval`: False
|
| 567 |
+
- `use_ipex`: False
|
| 568 |
+
- `bf16`: True
|
| 569 |
+
- `fp16`: False
|
| 570 |
+
- `fp16_opt_level`: O1
|
| 571 |
+
- `half_precision_backend`: auto
|
| 572 |
+
- `bf16_full_eval`: False
|
| 573 |
+
- `fp16_full_eval`: False
|
| 574 |
+
- `tf32`: None
|
| 575 |
+
- `local_rank`: 0
|
| 576 |
+
- `ddp_backend`: None
|
| 577 |
+
- `tpu_num_cores`: None
|
| 578 |
+
- `tpu_metrics_debug`: False
|
| 579 |
+
- `debug`: []
|
| 580 |
+
- `dataloader_drop_last`: False
|
| 581 |
+
- `dataloader_num_workers`: 0
|
| 582 |
+
- `dataloader_prefetch_factor`: None
|
| 583 |
+
- `past_index`: -1
|
| 584 |
+
- `disable_tqdm`: False
|
| 585 |
+
- `remove_unused_columns`: True
|
| 586 |
+
- `label_names`: None
|
| 587 |
+
- `load_best_model_at_end`: False
|
| 588 |
+
- `ignore_data_skip`: False
|
| 589 |
+
- `fsdp`: []
|
| 590 |
+
- `fsdp_min_num_params`: 0
|
| 591 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
| 592 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
| 593 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'gradient_accumulation_kwargs': None}
|
| 594 |
+
- `deepspeed`: None
|
| 595 |
+
- `label_smoothing_factor`: 0.0
|
| 596 |
+
- `optim`: adamw_torch
|
| 597 |
+
- `optim_args`: None
|
| 598 |
+
- `adafactor`: False
|
| 599 |
+
- `group_by_length`: False
|
| 600 |
+
- `length_column_name`: length
|
| 601 |
+
- `ddp_find_unused_parameters`: None
|
| 602 |
+
- `ddp_bucket_cap_mb`: None
|
| 603 |
+
- `ddp_broadcast_buffers`: False
|
| 604 |
+
- `dataloader_pin_memory`: True
|
| 605 |
+
- `dataloader_persistent_workers`: False
|
| 606 |
+
- `skip_memory_metrics`: True
|
| 607 |
+
- `use_legacy_prediction_loop`: False
|
| 608 |
+
- `push_to_hub`: False
|
| 609 |
+
- `resume_from_checkpoint`: None
|
| 610 |
+
- `hub_model_id`: None
|
| 611 |
+
- `hub_strategy`: every_save
|
| 612 |
+
- `hub_private_repo`: False
|
| 613 |
+
- `hub_always_push`: False
|
| 614 |
+
- `gradient_checkpointing`: False
|
| 615 |
+
- `gradient_checkpointing_kwargs`: None
|
| 616 |
+
- `include_inputs_for_metrics`: False
|
| 617 |
+
- `eval_do_concat_batches`: True
|
| 618 |
+
- `fp16_backend`: auto
|
| 619 |
+
- `push_to_hub_model_id`: None
|
| 620 |
+
- `push_to_hub_organization`: None
|
| 621 |
+
- `mp_parameters`:
|
| 622 |
+
- `auto_find_batch_size`: False
|
| 623 |
+
- `full_determinism`: False
|
| 624 |
+
- `torchdynamo`: None
|
| 625 |
+
- `ray_scope`: last
|
| 626 |
+
- `ddp_timeout`: 1800
|
| 627 |
+
- `torch_compile`: False
|
| 628 |
+
- `torch_compile_backend`: None
|
| 629 |
+
- `torch_compile_mode`: None
|
| 630 |
+
- `dispatch_batches`: None
|
| 631 |
+
- `split_batches`: None
|
| 632 |
+
- `include_tokens_per_second`: False
|
| 633 |
+
- `include_num_input_tokens_seen`: False
|
| 634 |
+
- `neftune_noise_alpha`: None
|
| 635 |
+
- `optim_target_modules`: None
|
| 636 |
+
- `batch_sampler`: no_duplicates
|
| 637 |
+
- `multi_dataset_batch_sampler`: proportional
|
| 638 |
+
|
| 639 |
+
</details>
|
| 640 |
+
|
| 641 |
+
### Training Logs
|
| 642 |
+
<details><summary>Click to expand</summary>
|
| 643 |
+
|
| 644 |
+
| Epoch | Step | Training Loss | sts-test-128_spearman_cosine | sts-test-256_spearman_cosine | sts-test-512_spearman_cosine | sts-test-64_spearman_cosine | sts-test-768_spearman_cosine |
|
| 645 |
+
|:------:|:-----:|:-------------:|:----------------------------:|:----------------------------:|:----------------------------:|:---------------------------:|:----------------------------:|
|
| 646 |
+
| 0.0043 | 100 | 10.0627 | - | - | - | - | - |
|
| 647 |
+
| 0.0086 | 200 | 8.2355 | - | - | - | - | - |
|
| 648 |
+
| 0.0129 | 300 | 6.7233 | - | - | - | - | - |
|
| 649 |
+
| 0.0172 | 400 | 6.5832 | - | - | - | - | - |
|
| 650 |
+
| 0.0215 | 500 | 6.7512 | - | - | - | - | - |
|
| 651 |
+
| 0.0258 | 600 | 6.7634 | - | - | - | - | - |
|
| 652 |
+
| 0.0301 | 700 | 6.5592 | - | - | - | - | - |
|
| 653 |
+
| 0.0344 | 800 | 5.0689 | - | - | - | - | - |
|
| 654 |
+
| 0.0387 | 900 | 4.7079 | - | - | - | - | - |
|
| 655 |
+
| 0.0430 | 1000 | 4.6359 | - | - | - | - | - |
|
| 656 |
+
| 0.0473 | 1100 | 4.4513 | - | - | - | - | - |
|
| 657 |
+
| 0.0516 | 1200 | 4.2328 | - | - | - | - | - |
|
| 658 |
+
| 0.0559 | 1300 | 3.7454 | - | - | - | - | - |
|
| 659 |
+
| 0.0602 | 1400 | 3.9198 | - | - | - | - | - |
|
| 660 |
+
| 0.0645 | 1500 | 4.0727 | - | - | - | - | - |
|
| 661 |
+
| 0.0688 | 1600 | 3.8923 | - | - | - | - | - |
|
| 662 |
+
| 0.0731 | 1700 | 3.8137 | - | - | - | - | - |
|
| 663 |
+
| 0.0774 | 1800 | 4.1512 | - | - | - | - | - |
|
| 664 |
+
| 0.0817 | 1900 | 4.1304 | - | - | - | - | - |
|
| 665 |
+
| 0.0860 | 2000 | 4.0195 | - | - | - | - | - |
|
| 666 |
+
| 0.0903 | 2100 | 3.6836 | - | - | - | - | - |
|
| 667 |
+
| 0.0946 | 2200 | 2.9968 | - | - | - | - | - |
|
| 668 |
+
| 0.0990 | 2300 | 2.8909 | - | - | - | - | - |
|
| 669 |
+
| 0.1033 | 2400 | 3.0884 | - | - | - | - | - |
|
| 670 |
+
| 0.1076 | 2500 | 3.3081 | - | - | - | - | - |
|
| 671 |
+
| 0.1119 | 2600 | 3.6266 | - | - | - | - | - |
|
| 672 |
+
| 0.1162 | 2700 | 4.3754 | - | - | - | - | - |
|
| 673 |
+
| 0.1205 | 2800 | 4.0218 | - | - | - | - | - |
|
| 674 |
+
| 0.1248 | 2900 | 3.7167 | - | - | - | - | - |
|
| 675 |
+
| 0.1291 | 3000 | 3.4815 | - | - | - | - | - |
|
| 676 |
+
| 0.1334 | 3100 | 3.6446 | - | - | - | - | - |
|
| 677 |
+
| 0.1377 | 3200 | 3.44 | - | - | - | - | - |
|
| 678 |
+
| 0.1420 | 3300 | 3.6725 | - | - | - | - | - |
|
| 679 |
+
| 0.1463 | 3400 | 3.4699 | - | - | - | - | - |
|
| 680 |
+
| 0.1506 | 3500 | 3.076 | - | - | - | - | - |
|
| 681 |
+
| 0.1549 | 3600 | 3.1179 | - | - | - | - | - |
|
| 682 |
+
| 0.1592 | 3700 | 3.1704 | - | - | - | - | - |
|
| 683 |
+
| 0.1635 | 3800 | 3.4614 | - | - | - | - | - |
|
| 684 |
+
| 0.1678 | 3900 | 4.1157 | - | - | - | - | - |
|
| 685 |
+
| 0.1721 | 4000 | 4.1584 | - | - | - | - | - |
|
| 686 |
+
| 0.1764 | 4100 | 4.5602 | - | - | - | - | - |
|
| 687 |
+
| 0.1807 | 4200 | 3.6875 | - | - | - | - | - |
|
| 688 |
+
| 0.1850 | 4300 | 4.1521 | - | - | - | - | - |
|
| 689 |
+
| 0.1893 | 4400 | 3.5475 | - | - | - | - | - |
|
| 690 |
+
| 0.1936 | 4500 | 3.4036 | - | - | - | - | - |
|
| 691 |
+
| 0.1979 | 4600 | 3.0564 | - | - | - | - | - |
|
| 692 |
+
| 0.2022 | 4700 | 3.7761 | - | - | - | - | - |
|
| 693 |
+
| 0.2065 | 4800 | 3.6857 | - | - | - | - | - |
|
| 694 |
+
| 0.2108 | 4900 | 3.3534 | - | - | - | - | - |
|
| 695 |
+
| 0.2151 | 5000 | 4.1137 | - | - | - | - | - |
|
| 696 |
+
| 0.2194 | 5100 | 3.5239 | - | - | - | - | - |
|
| 697 |
+
| 0.2237 | 5200 | 4.1297 | - | - | - | - | - |
|
| 698 |
+
| 0.2280 | 5300 | 3.5339 | - | - | - | - | - |
|
| 699 |
+
| 0.2323 | 5400 | 3.9294 | - | - | - | - | - |
|
| 700 |
+
| 0.2366 | 5500 | 3.717 | - | - | - | - | - |
|
| 701 |
+
| 0.2409 | 5600 | 3.3346 | - | - | - | - | - |
|
| 702 |
+
| 0.2452 | 5700 | 4.0495 | - | - | - | - | - |
|
| 703 |
+
| 0.2495 | 5800 | 3.7869 | - | - | - | - | - |
|
| 704 |
+
| 0.2538 | 5900 | 3.9533 | - | - | - | - | - |
|
| 705 |
+
| 0.2581 | 6000 | 4.1135 | - | - | - | - | - |
|
| 706 |
+
| 0.2624 | 6100 | 3.6655 | - | - | - | - | - |
|
| 707 |
+
| 0.2667 | 6200 | 3.9111 | - | - | - | - | - |
|
| 708 |
+
| 0.2710 | 6300 | 3.8582 | - | - | - | - | - |
|
| 709 |
+
| 0.2753 | 6400 | 3.7712 | - | - | - | - | - |
|
| 710 |
+
| 0.2796 | 6500 | 3.6536 | - | - | - | - | - |
|
| 711 |
+
| 0.2839 | 6600 | 3.4516 | - | - | - | - | - |
|
| 712 |
+
| 0.2882 | 6700 | 3.7151 | - | - | - | - | - |
|
| 713 |
+
| 0.2925 | 6800 | 3.7659 | - | - | - | - | - |
|
| 714 |
+
| 0.2969 | 6900 | 3.3159 | - | - | - | - | - |
|
| 715 |
+
| 0.3012 | 7000 | 3.5753 | - | - | - | - | - |
|
| 716 |
+
| 0.3055 | 7100 | 4.2095 | - | - | - | - | - |
|
| 717 |
+
| 0.3098 | 7200 | 3.718 | - | - | - | - | - |
|
| 718 |
+
| 0.3141 | 7300 | 4.0709 | - | - | - | - | - |
|
| 719 |
+
| 0.3184 | 7400 | 3.8079 | - | - | - | - | - |
|
| 720 |
+
| 0.3227 | 7500 | 3.3735 | - | - | - | - | - |
|
| 721 |
+
| 0.3270 | 7600 | 3.7303 | - | - | - | - | - |
|
| 722 |
+
| 0.3313 | 7700 | 3.2693 | - | - | - | - | - |
|
| 723 |
+
| 0.3356 | 7800 | 3.6564 | - | - | - | - | - |
|
| 724 |
+
| 0.3399 | 7900 | 3.6702 | - | - | - | - | - |
|
| 725 |
+
| 0.3442 | 8000 | 3.7274 | - | - | - | - | - |
|
| 726 |
+
| 0.3485 | 8100 | 3.8536 | - | - | - | - | - |
|
| 727 |
+
| 0.3528 | 8200 | 3.9516 | - | - | - | - | - |
|
| 728 |
+
| 0.3571 | 8300 | 3.7351 | - | - | - | - | - |
|
| 729 |
+
| 0.3614 | 8400 | 3.649 | - | - | - | - | - |
|
| 730 |
+
| 0.3657 | 8500 | 3.5913 | - | - | - | - | - |
|
| 731 |
+
| 0.3700 | 8600 | 3.7733 | - | - | - | - | - |
|
| 732 |
+
| 0.3743 | 8700 | 3.6359 | - | - | - | - | - |
|
| 733 |
+
| 0.3786 | 8800 | 4.2983 | - | - | - | - | - |
|
| 734 |
+
| 0.3829 | 8900 | 3.6692 | - | - | - | - | - |
|
| 735 |
+
| 0.3872 | 9000 | 3.7309 | - | - | - | - | - |
|
| 736 |
+
| 0.3915 | 9100 | 3.8886 | - | - | - | - | - |
|
| 737 |
+
| 0.3958 | 9200 | 3.8999 | - | - | - | - | - |
|
| 738 |
+
| 0.4001 | 9300 | 3.5528 | - | - | - | - | - |
|
| 739 |
+
| 0.4044 | 9400 | 3.6309 | - | - | - | - | - |
|
| 740 |
+
| 0.4087 | 9500 | 4.2475 | - | - | - | - | - |
|
| 741 |
+
| 0.4130 | 9600 | 3.793 | - | - | - | - | - |
|
| 742 |
+
| 0.4173 | 9700 | 3.6575 | - | - | - | - | - |
|
| 743 |
+
| 0.4216 | 9800 | 3.84 | - | - | - | - | - |
|
| 744 |
+
| 0.4259 | 9900 | 3.3721 | - | - | - | - | - |
|
| 745 |
+
| 0.4302 | 10000 | 4.3743 | - | - | - | - | - |
|
| 746 |
+
| 0.4345 | 10100 | 3.5054 | - | - | - | - | - |
|
| 747 |
+
| 0.4388 | 10200 | 3.54 | - | - | - | - | - |
|
| 748 |
+
| 0.4431 | 10300 | 3.6197 | - | - | - | - | - |
|
| 749 |
+
| 0.4474 | 10400 | 3.7567 | - | - | - | - | - |
|
| 750 |
+
| 0.4517 | 10500 | 3.9814 | - | - | - | - | - |
|
| 751 |
+
| 0.4560 | 10600 | 3.6277 | - | - | - | - | - |
|
| 752 |
+
| 0.4603 | 10700 | 3.5071 | - | - | - | - | - |
|
| 753 |
+
| 0.4646 | 10800 | 3.8348 | - | - | - | - | - |
|
| 754 |
+
| 0.4689 | 10900 | 3.8674 | - | - | - | - | - |
|
| 755 |
+
| 0.4732 | 11000 | 3.0325 | - | - | - | - | - |
|
| 756 |
+
| 0.4775 | 11100 | 3.7262 | - | - | - | - | - |
|
| 757 |
+
| 0.4818 | 11200 | 3.6921 | - | - | - | - | - |
|
| 758 |
+
| 0.4861 | 11300 | 3.4946 | - | - | - | - | - |
|
| 759 |
+
| 0.4904 | 11400 | 3.7541 | - | - | - | - | - |
|
| 760 |
+
| 0.4948 | 11500 | 3.6751 | - | - | - | - | - |
|
| 761 |
+
| 0.4991 | 11600 | 3.8765 | - | - | - | - | - |
|
| 762 |
+
| 0.5034 | 11700 | 3.5058 | - | - | - | - | - |
|
| 763 |
+
| 0.5077 | 11800 | 3.5135 | - | - | - | - | - |
|
| 764 |
+
| 0.5120 | 11900 | 3.8052 | - | - | - | - | - |
|
| 765 |
+
| 0.5163 | 12000 | 3.3015 | - | - | - | - | - |
|
| 766 |
+
| 0.5206 | 12100 | 3.5389 | - | - | - | - | - |
|
| 767 |
+
| 0.5249 | 12200 | 3.5226 | - | - | - | - | - |
|
| 768 |
+
| 0.5292 | 12300 | 3.6715 | - | - | - | - | - |
|
| 769 |
+
| 0.5335 | 12400 | 3.2256 | - | - | - | - | - |
|
| 770 |
+
| 0.5378 | 12500 | 3.3447 | - | - | - | - | - |
|
| 771 |
+
| 0.5421 | 12600 | 3.6315 | - | - | - | - | - |
|
| 772 |
+
| 0.5464 | 12700 | 3.8674 | - | - | - | - | - |
|
| 773 |
+
| 0.5507 | 12800 | 3.4066 | - | - | - | - | - |
|
| 774 |
+
| 0.5550 | 12900 | 3.7356 | - | - | - | - | - |
|
| 775 |
+
| 0.5593 | 13000 | 3.5742 | - | - | - | - | - |
|
| 776 |
+
| 0.5636 | 13100 | 3.7676 | - | - | - | - | - |
|
| 777 |
+
| 0.5679 | 13200 | 3.7907 | - | - | - | - | - |
|
| 778 |
+
| 0.5722 | 13300 | 3.8089 | - | - | - | - | - |
|
| 779 |
+
| 0.5765 | 13400 | 3.4742 | - | - | - | - | - |
|
| 780 |
+
| 0.5808 | 13500 | 3.6536 | - | - | - | - | - |
|
| 781 |
+
| 0.5851 | 13600 | 3.7736 | - | - | - | - | - |
|
| 782 |
+
| 0.5894 | 13700 | 3.9072 | - | - | - | - | - |
|
| 783 |
+
| 0.5937 | 13800 | 3.7386 | - | - | - | - | - |
|
| 784 |
+
| 0.5980 | 13900 | 3.3387 | - | - | - | - | - |
|
| 785 |
+
| 0.6023 | 14000 | 3.5509 | - | - | - | - | - |
|
| 786 |
+
| 0.6066 | 14100 | 3.7056 | - | - | - | - | - |
|
| 787 |
+
| 0.6109 | 14200 | 3.7283 | - | - | - | - | - |
|
| 788 |
+
| 0.6152 | 14300 | 3.7301 | - | - | - | - | - |
|
| 789 |
+
| 0.6195 | 14400 | 3.8027 | - | - | - | - | - |
|
| 790 |
+
| 0.6238 | 14500 | 3.5606 | - | - | - | - | - |
|
| 791 |
+
| 0.6281 | 14600 | 3.9467 | - | - | - | - | - |
|
| 792 |
+
| 0.6324 | 14700 | 3.3394 | - | - | - | - | - |
|
| 793 |
+
| 0.6367 | 14800 | 4.1254 | - | - | - | - | - |
|
| 794 |
+
| 0.6410 | 14900 | 3.7121 | - | - | - | - | - |
|
| 795 |
+
| 0.6453 | 15000 | 3.9167 | - | - | - | - | - |
|
| 796 |
+
| 0.6496 | 15100 | 3.8084 | - | - | - | - | - |
|
| 797 |
+
| 0.6539 | 15200 | 3.7794 | - | - | - | - | - |
|
| 798 |
+
| 0.6582 | 15300 | 3.7664 | - | - | - | - | - |
|
| 799 |
+
| 0.6625 | 15400 | 3.4378 | - | - | - | - | - |
|
| 800 |
+
| 0.6668 | 15500 | 3.6632 | - | - | - | - | - |
|
| 801 |
+
| 0.6711 | 15600 | 3.8493 | - | - | - | - | - |
|
| 802 |
+
| 0.6754 | 15700 | 4.1475 | - | - | - | - | - |
|
| 803 |
+
| 0.6797 | 15800 | 3.5782 | - | - | - | - | - |
|
| 804 |
+
| 0.6840 | 15900 | 3.4341 | - | - | - | - | - |
|
| 805 |
+
| 0.6883 | 16000 | 3.3295 | - | - | - | - | - |
|
| 806 |
+
| 0.6927 | 16100 | 3.8165 | - | - | - | - | - |
|
| 807 |
+
| 0.6970 | 16200 | 3.9702 | - | - | - | - | - |
|
| 808 |
+
| 0.7013 | 16300 | 3.6555 | - | - | - | - | - |
|
| 809 |
+
| 0.7056 | 16400 | 3.6946 | - | - | - | - | - |
|
| 810 |
+
| 0.7099 | 16500 | 3.8027 | - | - | - | - | - |
|
| 811 |
+
| 0.7142 | 16600 | 3.4523 | - | - | - | - | - |
|
| 812 |
+
| 0.7185 | 16700 | 3.461 | - | - | - | - | - |
|
| 813 |
+
| 0.7228 | 16800 | 3.4403 | - | - | - | - | - |
|
| 814 |
+
| 0.7271 | 16900 | 3.6398 | - | - | - | - | - |
|
| 815 |
+
| 0.7314 | 17000 | 3.8443 | - | - | - | - | - |
|
| 816 |
+
| 0.7357 | 17100 | 3.6012 | - | - | - | - | - |
|
| 817 |
+
| 0.7400 | 17200 | 3.6645 | - | - | - | - | - |
|
| 818 |
+
| 0.7443 | 17300 | 3.4899 | - | - | - | - | - |
|
| 819 |
+
| 0.7486 | 17400 | 3.7186 | - | - | - | - | - |
|
| 820 |
+
| 0.7529 | 17500 | 3.6199 | - | - | - | - | - |
|
| 821 |
+
| 0.7572 | 17600 | 4.4274 | - | - | - | - | - |
|
| 822 |
+
| 0.7615 | 17700 | 4.0262 | - | - | - | - | - |
|
| 823 |
+
| 0.7658 | 17800 | 3.9325 | - | - | - | - | - |
|
| 824 |
+
| 0.7701 | 17900 | 3.6338 | - | - | - | - | - |
|
| 825 |
+
| 0.7744 | 18000 | 3.6136 | - | - | - | - | - |
|
| 826 |
+
| 0.7787 | 18100 | 3.4514 | - | - | - | - | - |
|
| 827 |
+
| 0.7830 | 18200 | 3.4427 | - | - | - | - | - |
|
| 828 |
+
| 0.7873 | 18300 | 3.3601 | - | - | - | - | - |
|
| 829 |
+
| 0.7916 | 18400 | 3.313 | - | - | - | - | - |
|
| 830 |
+
| 0.7959 | 18500 | 3.4062 | - | - | - | - | - |
|
| 831 |
+
| 0.8002 | 18600 | 3.098 | - | - | - | - | - |
|
| 832 |
+
| 0.8045 | 18700 | 3.183 | - | - | - | - | - |
|
| 833 |
+
| 0.8088 | 18800 | 3.1482 | - | - | - | - | - |
|
| 834 |
+
| 0.8131 | 18900 | 3.0122 | - | - | - | - | - |
|
| 835 |
+
| 0.8174 | 19000 | 3.0828 | - | - | - | - | - |
|
| 836 |
+
| 0.8217 | 19100 | 3.063 | - | - | - | - | - |
|
| 837 |
+
| 0.8260 | 19200 | 2.9688 | - | - | - | - | - |
|
| 838 |
+
| 0.8303 | 19300 | 3.0425 | - | - | - | - | - |
|
| 839 |
+
| 0.8346 | 19400 | 3.2018 | - | - | - | - | - |
|
| 840 |
+
| 0.8389 | 19500 | 2.9111 | - | - | - | - | - |
|
| 841 |
+
| 0.8432 | 19600 | 2.9516 | - | - | - | - | - |
|
| 842 |
+
| 0.8475 | 19700 | 2.9115 | - | - | - | - | - |
|
| 843 |
+
| 0.8518 | 19800 | 2.9323 | - | - | - | - | - |
|
| 844 |
+
| 0.8561 | 19900 | 2.8753 | - | - | - | - | - |
|
| 845 |
+
| 0.8604 | 20000 | 2.8344 | - | - | - | - | - |
|
| 846 |
+
| 0.8647 | 20100 | 2.7665 | - | - | - | - | - |
|
| 847 |
+
| 0.8690 | 20200 | 2.7732 | - | - | - | - | - |
|
| 848 |
+
| 0.8733 | 20300 | 2.8622 | - | - | - | - | - |
|
| 849 |
+
| 0.8776 | 20400 | 2.8749 | - | - | - | - | - |
|
| 850 |
+
| 0.8819 | 20500 | 2.8534 | - | - | - | - | - |
|
| 851 |
+
| 0.8863 | 20600 | 2.9254 | - | - | - | - | - |
|
| 852 |
+
| 0.8906 | 20700 | 2.7366 | - | - | - | - | - |
|
| 853 |
+
| 0.8949 | 20800 | 2.7287 | - | - | - | - | - |
|
| 854 |
+
| 0.8992 | 20900 | 2.9469 | - | - | - | - | - |
|
| 855 |
+
| 0.9035 | 21000 | 2.9052 | - | - | - | - | - |
|
| 856 |
+
| 0.9078 | 21100 | 2.7256 | - | - | - | - | - |
|
| 857 |
+
| 0.9121 | 21200 | 2.8469 | - | - | - | - | - |
|
| 858 |
+
| 0.9164 | 21300 | 2.6626 | - | - | - | - | - |
|
| 859 |
+
| 0.9207 | 21400 | 2.6796 | - | - | - | - | - |
|
| 860 |
+
| 0.9250 | 21500 | 2.6927 | - | - | - | - | - |
|
| 861 |
+
| 0.9293 | 21600 | 2.7125 | - | - | - | - | - |
|
| 862 |
+
| 0.9336 | 21700 | 2.6734 | - | - | - | - | - |
|
| 863 |
+
| 0.9379 | 21800 | 2.7199 | - | - | - | - | - |
|
| 864 |
+
| 0.9422 | 21900 | 2.6635 | - | - | - | - | - |
|
| 865 |
+
| 0.9465 | 22000 | 2.5218 | - | - | - | - | - |
|
| 866 |
+
| 0.9508 | 22100 | 2.7595 | - | - | - | - | - |
|
| 867 |
+
| 0.9551 | 22200 | 2.6821 | - | - | - | - | - |
|
| 868 |
+
| 0.9594 | 22300 | 2.6578 | - | - | - | - | - |
|
| 869 |
+
| 0.9637 | 22400 | 2.568 | - | - | - | - | - |
|
| 870 |
+
| 0.9680 | 22500 | 2.5527 | - | - | - | - | - |
|
| 871 |
+
| 0.9723 | 22600 | 2.6857 | - | - | - | - | - |
|
| 872 |
+
| 0.9766 | 22700 | 2.6637 | - | - | - | - | - |
|
| 873 |
+
| 0.9809 | 22800 | 2.6311 | - | - | - | - | - |
|
| 874 |
+
| 0.9852 | 22900 | 2.4635 | - | - | - | - | - |
|
| 875 |
+
| 0.9895 | 23000 | 2.6239 | - | - | - | - | - |
|
| 876 |
+
| 0.9938 | 23100 | 2.6873 | - | - | - | - | - |
|
| 877 |
+
| 0.9981 | 23200 | 2.5138 | - | - | - | - | - |
|
| 878 |
+
| 1.0 | 23244 | - | 0.6670 | 0.6815 | 0.6859 | 0.6524 | 0.6872 |
|
| 879 |
+
|
| 880 |
+
</details>
|
| 881 |
+
|
| 882 |
+
### Framework Versions
|
| 883 |
+
- Python: 3.11.9
|
| 884 |
+
- Sentence Transformers: 3.0.1
|
| 885 |
+
- Transformers: 4.40.1
|
| 886 |
+
- PyTorch: 2.3.0+cu121
|
| 887 |
+
- Accelerate: 0.29.3
|
| 888 |
+
- Datasets: 2.19.0
|
| 889 |
+
- Tokenizers: 0.19.1
|
| 890 |
+
|
| 891 |
+
## Citation
|
| 892 |
+
|
| 893 |
+
### BibTeX
|
| 894 |
+
|
| 895 |
+
#### Sentence Transformers
|
| 896 |
+
```bibtex
|
| 897 |
+
@inproceedings{reimers-2019-sentence-bert,
|
| 898 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
| 899 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
| 900 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
| 901 |
+
month = "11",
|
| 902 |
+
year = "2019",
|
| 903 |
+
publisher = "Association for Computational Linguistics",
|
| 904 |
+
url = "https://arxiv.org/abs/1908.10084",
|
| 905 |
+
}
|
| 906 |
+
```
|
| 907 |
+
|
| 908 |
+
#### MatryoshkaLoss
|
| 909 |
+
```bibtex
|
| 910 |
+
@misc{kusupati2024matryoshka,
|
| 911 |
+
title={Matryoshka Representation Learning},
|
| 912 |
+
author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
|
| 913 |
+
year={2024},
|
| 914 |
+
eprint={2205.13147},
|
| 915 |
+
archivePrefix={arXiv},
|
| 916 |
+
primaryClass={cs.LG}
|
| 917 |
+
}
|
| 918 |
+
```
|
| 919 |
+
|
| 920 |
+
#### MultipleNegativesRankingLoss
|
| 921 |
+
```bibtex
|
| 922 |
+
@misc{henderson2017efficient,
|
| 923 |
+
title={Efficient Natural Language Response Suggestion for Smart Reply},
|
| 924 |
+
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},
|
| 925 |
+
year={2017},
|
| 926 |
+
eprint={1705.00652},
|
| 927 |
+
archivePrefix={arXiv},
|
| 928 |
+
primaryClass={cs.CL}
|
| 929 |
+
}
|
| 930 |
+
```
|
| 931 |
+
|
| 932 |
+
<!--
|
| 933 |
+
## Glossary
|
| 934 |
+
|
| 935 |
+
*Clearly define terms in order to be accessible across audiences.*
|
| 936 |
+
-->
|
| 937 |
+
|
| 938 |
+
<!--
|
| 939 |
+
## Model Card Authors
|
| 940 |
+
|
| 941 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
| 942 |
+
-->
|
| 943 |
+
|
| 944 |
+
<!--
|
| 945 |
+
## Model Card Contact
|
| 946 |
+
|
| 947 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
| 948 |
+
-->
|
config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "nomic-ai/nomic-embed-text-v1.5",
|
| 3 |
+
"activation_function": "swiglu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"NomicBertModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.0,
|
| 8 |
+
"auto_map": {
|
| 9 |
+
"AutoConfig": "nomic-ai/nomic-bert-2048--configuration_hf_nomic_bert.NomicBertConfig",
|
| 10 |
+
"AutoModel": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertModel",
|
| 11 |
+
"AutoModelForMaskedLM": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForPreTraining"
|
| 12 |
+
},
|
| 13 |
+
"bos_token_id": null,
|
| 14 |
+
"causal": false,
|
| 15 |
+
"dense_seq_output": true,
|
| 16 |
+
"embd_pdrop": 0.0,
|
| 17 |
+
"eos_token_id": null,
|
| 18 |
+
"fused_bias_fc": true,
|
| 19 |
+
"fused_dropout_add_ln": true,
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"layer_norm_epsilon": 1e-12,
|
| 22 |
+
"max_trained_positions": 2048,
|
| 23 |
+
"mlp_fc1_bias": false,
|
| 24 |
+
"mlp_fc2_bias": false,
|
| 25 |
+
"model_type": "nomic_bert",
|
| 26 |
+
"n_embd": 768,
|
| 27 |
+
"n_head": 12,
|
| 28 |
+
"n_inner": 3072,
|
| 29 |
+
"n_layer": 12,
|
| 30 |
+
"n_positions": 8192,
|
| 31 |
+
"pad_vocab_size_multiple": 64,
|
| 32 |
+
"parallel_block": false,
|
| 33 |
+
"parallel_block_tied_norm": false,
|
| 34 |
+
"prenorm": false,
|
| 35 |
+
"qkv_proj_bias": false,
|
| 36 |
+
"reorder_and_upcast_attn": false,
|
| 37 |
+
"resid_pdrop": 0.0,
|
| 38 |
+
"rotary_emb_base": 1000,
|
| 39 |
+
"rotary_emb_fraction": 1.0,
|
| 40 |
+
"rotary_emb_interleaved": false,
|
| 41 |
+
"rotary_emb_scale_base": null,
|
| 42 |
+
"rotary_scaling_factor": null,
|
| 43 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 44 |
+
"scale_attn_weights": true,
|
| 45 |
+
"summary_activation": null,
|
| 46 |
+
"summary_first_dropout": 0.0,
|
| 47 |
+
"summary_proj_to_labels": true,
|
| 48 |
+
"summary_type": "cls_index",
|
| 49 |
+
"summary_use_proj": true,
|
| 50 |
+
"torch_dtype": "float32",
|
| 51 |
+
"transformers_version": "4.40.1",
|
| 52 |
+
"type_vocab_size": 2,
|
| 53 |
+
"use_cache": true,
|
| 54 |
+
"use_flash_attn": true,
|
| 55 |
+
"use_rms_norm": false,
|
| 56 |
+
"use_xentropy": true,
|
| 57 |
+
"vocab_size": 30528
|
| 58 |
+
}
|
config_sentence_transformers.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"__version__": {
|
| 3 |
+
"sentence_transformers": "3.0.1",
|
| 4 |
+
"transformers": "4.40.1",
|
| 5 |
+
"pytorch": "2.3.0+cu121"
|
| 6 |
+
},
|
| 7 |
+
"prompts": {},
|
| 8 |
+
"default_prompt_name": null,
|
| 9 |
+
"similarity_fn_name": null
|
| 10 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f364eab736622029e58b114f30517fc96b8cee8629453678c9036f44de6e88e
|
| 3 |
+
size 546938168
|
modules.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"idx": 0,
|
| 4 |
+
"name": "0",
|
| 5 |
+
"path": "",
|
| 6 |
+
"type": "sentence_transformers.models.Transformer"
|
| 7 |
+
},
|
| 8 |
+
{
|
| 9 |
+
"idx": 1,
|
| 10 |
+
"name": "1",
|
| 11 |
+
"path": "1_Pooling",
|
| 12 |
+
"type": "sentence_transformers.models.Pooling"
|
| 13 |
+
}
|
| 14 |
+
]
|
sentence_bert_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"max_seq_length": 8192,
|
| 3 |
+
"do_lower_case": false
|
| 4 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"mask_token": "[MASK]",
|
| 48 |
+
"model_max_length": 8192,
|
| 49 |
+
"pad_token": "[PAD]",
|
| 50 |
+
"sep_token": "[SEP]",
|
| 51 |
+
"strip_accents": null,
|
| 52 |
+
"tokenize_chinese_chars": true,
|
| 53 |
+
"tokenizer_class": "BertTokenizer",
|
| 54 |
+
"unk_token": "[UNK]"
|
| 55 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|