Initial upload of fine-tuned SBERT model on culinary recipes
Browse files- 1_Pooling/config.json +10 -0
- README.md +526 -0
- config.json +28 -0
- config_sentence_transformers.json +10 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- modules.json +20 -0
- sentence_bert_config.json +4 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +64 -0
- vocab.json +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 +1,526 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: []
|
| 3 |
+
library_name: sentence-transformers
|
| 4 |
+
tags:
|
| 5 |
+
- sentence-transformers
|
| 6 |
+
- sentence-similarity
|
| 7 |
+
- feature-extraction
|
| 8 |
+
- dataset_size:10K<n<100K
|
| 9 |
+
- loss:CosineSimilarityLoss
|
| 10 |
+
base_model: sentence-transformers/all-distilroberta-v1
|
| 11 |
+
metrics:
|
| 12 |
+
- pearson_cosine
|
| 13 |
+
- spearman_cosine
|
| 14 |
+
- pearson_manhattan
|
| 15 |
+
- spearman_manhattan
|
| 16 |
+
- pearson_euclidean
|
| 17 |
+
- spearman_euclidean
|
| 18 |
+
- pearson_dot
|
| 19 |
+
- spearman_dot
|
| 20 |
+
- pearson_max
|
| 21 |
+
- spearman_max
|
| 22 |
+
widget:
|
| 23 |
+
- source_sentence: 'Ingredients: 2 mangoes - peeled, seeded, and chopped, 3/4 cup
|
| 24 |
+
chopped onion, 3/4 cup chopped cilantro, 1/2 cup chopped fresh mint, 1 1/2 limes,
|
| 25 |
+
juiced, 1/2 teaspoon minced fresh ginger root (optional). Instructions: Stir mangoes,
|
| 26 |
+
onion, cilantro, mint, lime juice, and ginger in a bowl until evenly mixed.'
|
| 27 |
+
sentences:
|
| 28 |
+
- 'Ingredients: 2 mangoes - peeled, seeded, and chopped, 1 (8 ounce) can pineapple
|
| 29 |
+
tidbits, drained, 1/4 cup chopped fresh cilantro leaves, 2 tablespoons peeled
|
| 30 |
+
and finely chopped fresh ginger, 1/2 cup chopped red onion, 1/4 cup rice vinegar,
|
| 31 |
+
1 teaspoon crushed red pepper flakes, or to taste. Instructions: Combine mango,
|
| 32 |
+
pineapple, cilantro, ginger, red onion, vinegar, and red pepper flakes in a bowl,
|
| 33 |
+
and stir lightly to mix well.'
|
| 34 |
+
- 'Ingredients: 3 egg whites, 1 cup white sugar, 1/2 teaspoon distilled white vinegar,
|
| 35 |
+
1/2 teaspoon vanilla extract, 1 pinch salt, 2 cups semisweet chocolate chips.
|
| 36 |
+
Instructions: Preheat oven to 300 degrees F (150 degrees C). Grease baking sheets
|
| 37 |
+
or line them with parchment paper. In a medium bowl, whip egg whites to soft peaks.
|
| 38 |
+
Gradually add the sugar, vinegar and vanilla while whipping to stiff peaks. Fold
|
| 39 |
+
in chocolate chips. Drop by spoonfuls onto the prepared cookie sheets. Bake for
|
| 40 |
+
20 to 25 minutes in the preheated oven, until cookies are dry.'
|
| 41 |
+
- 'Ingredients: 1 (18.25 ounce) package yellow cake mix, 5 tablespoons instant lemon
|
| 42 |
+
pudding mix, 2 eggs, 1/4 cup butter, softened, 1/3 cup water, 1/8 cup applesauce.
|
| 43 |
+
Instructions: Preheat oven to 350 degrees F (175 degrees C). Grease and flour
|
| 44 |
+
a 9 inch springform pan. In a medium bowl, stir together the cake mix and instant
|
| 45 |
+
pudding. Add the eggs, butter, water and applesauce, mix with an electric mixer
|
| 46 |
+
until smooth. Pour batter into the prepared pan. Bake for 30 to 35 minutes in
|
| 47 |
+
the preheated oven, until a toothpick inserted comes out clean. Let cake cool
|
| 48 |
+
in the pan for 10 minutes before removing from pan to cool on a wire rack.'
|
| 49 |
+
- source_sentence: 'Ingredients: 1 (.25 ounce) package active dry yeast, 3 cups bread
|
| 50 |
+
flour, 1/4 cup dry milk powder, 1 tablespoon butter, softened, 1 teaspoon salt.
|
| 51 |
+
Instructions: Place ingredients in the pan of the bread machine in the order recommended
|
| 52 |
+
by the manufacturer. Select White Bread setting; press Start.'
|
| 53 |
+
sentences:
|
| 54 |
+
- 'Ingredients: 1 1/4 cups water, 2 tablespoons margarine, softened, 2 tablespoons
|
| 55 |
+
dry milk powder, 2 tablespoons brown sugar, 1 1/4 teaspoons salt, 3 cups bread
|
| 56 |
+
flour, 1/3 cup whole wheat flour, 1/4 cup cracked wheat, 1 1/4 teaspoons active
|
| 57 |
+
dry yeast. Instructions: Place ingredients in the pan of the bread machine in
|
| 58 |
+
the order recommended by the manufacturer. Select regular/light cycle; press Start.'
|
| 59 |
+
- 'Ingredients: 2 3/4 cups baking mix, 1/2 teaspoon crushed red pepper flakes, 3/4
|
| 60 |
+
teaspoon garlic powder, 1 cup milk, 1 cup shredded Cheddar cheese, 2 tablespoons
|
| 61 |
+
butter, melted. Instructions: Preheat oven to 425 degrees F (220 degrees C). Combine
|
| 62 |
+
biscuit mix, pepper, and 1/2 teaspoon garlic powder in a large bowl. With a fork,
|
| 63 |
+
stir in milk and cheese until mixture forms a soft dough. Drop by 1/4 cupfuls
|
| 64 |
+
onto greased cookie sheet. Combine butter and remaining 1/4 teaspoon garlic powder,
|
| 65 |
+
and brush on top of biscuits. Bake for 10 to 12 minutes, or until golden brown.'
|
| 66 |
+
- 'Ingredients: 4 skinless, boneless chicken breast halves, 1 cup lime juice, 3/4
|
| 67 |
+
cup lemon juice, 3/4 cup orange juice, 1/2 cup pineapple juice, 1/2 cup cherry
|
| 68 |
+
juice. Instructions: Preheat outdoor grill for medium high heat and lightly oil
|
| 69 |
+
grate; OR preheat oven to Grill/Broil. Place chicken on grill/grate. In a medium
|
| 70 |
+
bowl mix together the lime juice, lemon juice, orange juice, pineapple juice and
|
| 71 |
+
cherry juice. Pour mixture over chicken a little bit at a time; turn after 5 to
|
| 72 |
+
7 minutes and repeat. Cook until chicken is cooked through (juices run clear),
|
| 73 |
+
about 15 minutes.'
|
| 74 |
+
- source_sentence: 'Ingredients: 1 (4 pound) whole chicken, 1 1/2 cups prepared barbecue
|
| 75 |
+
sauce. Instructions: Put chicken, legs up, into slow cooker. Pour sauce over
|
| 76 |
+
and inside the chicken. Cover. Cook for 8 to 10 hours on low setting. It is
|
| 77 |
+
not a good idea to check it, as steam escapes and it takes quite awhile to reheat.'
|
| 78 |
+
sentences:
|
| 79 |
+
- 'Ingredients: 1 (3 pound) whole chicken, 1/2 cup soy sauce. Instructions: Place
|
| 80 |
+
chicken in a slow cooker and add soy sauce. Cook on Low until chicken is cooked
|
| 81 |
+
through, about 5 hours. An instant-read thermometer inserted into the thickest
|
| 82 |
+
part of the thigh, near the bone should read 165 degrees F (74 degrees C).'
|
| 83 |
+
- 'Ingredients: 1/2 cup margarine, softened, 2/3 cup milk, 2 eggs, 2 1/2 cups all-purpose
|
| 84 |
+
flour, 1 cup white sugar, 2 1/2 teaspoons baking powder, 1/2 teaspoon baking soda,
|
| 85 |
+
1 teaspoon salt, 2/3 cup mashed bananas, 1/2 cup chopped walnuts. Instructions:
|
| 86 |
+
Spray bread machine pan with vegetable oil spray. Premix ingredients in order
|
| 87 |
+
listed. Place mixture in bread machine pan. Select the Quick Bread/Cake cycle. Press
|
| 88 |
+
Start. Check after 1 minute to see if mixture is well blended. Cook until cake
|
| 89 |
+
cycle stops. Remove pan, and cool completely before removing bread from pan.'
|
| 90 |
+
- 'Ingredients: 7/8 cup water, 3/4 teaspoon cider vinegar, 1 1/2 cups bread flour,
|
| 91 |
+
1/2 cup rye flour, 1/4 cup oat bran, 1 tablespoon margarine, 1 1/2 tablespoons
|
| 92 |
+
white sugar, 1 teaspoon salt, 1 teaspoon caraway seed, 1 teaspoon dried minced
|
| 93 |
+
onion, 2 tablespoons unsweetened cocoa powder, 1 teaspoon active dry yeast. Instructions:
|
| 94 |
+
Place the ingredients in the pan of the bread machine in the order suggested by
|
| 95 |
+
the manufacturer. Select Normal setting, and then press Start.'
|
| 96 |
+
- source_sentence: 'Ingredients: 1 egg, 1 cup orange juice, 1/4 cup hot water, 1 tablespoon
|
| 97 |
+
margarine, 1/4 cup white sugar, 3 1/2 cups bread flour. Instructions: Place ingredients
|
| 98 |
+
into the pan of the bread machine in the order suggested by the manufacturer.
|
| 99 |
+
Select the White Bread or Basic cycle, and Start.'
|
| 100 |
+
sentences:
|
| 101 |
+
- 'Ingredients: 2 eggs, 2 tablespoons white sugar, 3 tablespoons all-purpose flour,
|
| 102 |
+
3/4 cup milk. Instructions: Place the eggs, sugar, flour and milk into the container
|
| 103 |
+
of a blender. Process until smooth on low speed. Heat a large skillet or griddle
|
| 104 |
+
over medium heat. Pour batter about 1/4 cup at a time (or more for larger pancakes).
|
| 105 |
+
Tilt pan to achieve a round shape. Heat until golden, then flip and brown on the
|
| 106 |
+
other side. Serve immediately with syrup, or fresh berries and whipped cream.'
|
| 107 |
+
- 'Ingredients: 2 large eggs, 1 tablespoon ground cinnamon, 1 tablespoon vanilla
|
| 108 |
+
extract, 1 cup maple syrup, 2 slices bread, 8 slices bacon. Instructions: Whisk
|
| 109 |
+
eggs, cinnamon, and vanilla extract together in a shallow bowl. Pour syrup into
|
| 110 |
+
a skillet over low heat. Dip bread into egg mixture, allowing excess liquid to
|
| 111 |
+
drip back into bowl. Wrap 4 slices bacon around each piece of bread. Dip bacon-wrapped
|
| 112 |
+
bread back into egg mixture. Cook 1 piece bacon-wrapped bread in the syrup at
|
| 113 |
+
a time until bacon is cooked to desired doneness, about 8 minutes per side.'
|
| 114 |
+
- 'Ingredients: 7 cups chopped new potatoes, 1 (8 ounce) container sour cream, 2
|
| 115 |
+
teaspoons chopped fresh dill weed, 1 teaspoon dried parsley. Instructions: Bring
|
| 116 |
+
a large pot of salted water to a boil. Add potatoes and cook until tender but
|
| 117 |
+
still firm, about 15 minutes. Drain, cool, peel and chill. Meanwhile, in a medium
|
| 118 |
+
bowl combine sour cream, dill, parsley, Dijon, salt and pepper. Pour dressing
|
| 119 |
+
over potatoes and toss gently. Chill before serving.'
|
| 120 |
+
- source_sentence: 'Ingredients: 1 head cabbage, cored and shredded, 1/8 cup olive
|
| 121 |
+
oil. Instructions: Place the shredded cabbage in a large bowl, and drizzle olive
|
| 122 |
+
oil over it. Toss until evenly coated. Season with garlic powder, lemon juice
|
| 123 |
+
and cilantro, and stir to blend in all of the flavors.'
|
| 124 |
+
sentences:
|
| 125 |
+
- 'Ingredients: 1/2 cup canola oil, 1/4 cup red wine vinegar, 1 tablespoon soy sauce,
|
| 126 |
+
6 tablespoons white sugar, 1 (8 ounce) package shredded cabbage. Instructions:
|
| 127 |
+
Mix canola oil, red wine vinegar, soy sauce, and sugar in a large bowl, mixing
|
| 128 |
+
until sugar has dissolved. Toss cabbage, green onions, almonds, and sunflower
|
| 129 |
+
seed kernels into the dressing. Cover bowl and refrigerate at least 1 hour before
|
| 130 |
+
serving; slaw tastes better when chilled overnight.'
|
| 131 |
+
- 'Ingredients: 1/4 cup instant cocoa powder, 1 cup shredded coconut, 1/3 cup raisins,
|
| 132 |
+
1/2 cup cornflakes cereal, 1/4 cup chopped walnuts, 1 teaspoon sherry, 2 cups
|
| 133 |
+
vanilla wafer crumbs, 1/4 cup sweetened condensed milk, 3 (1 ounce) squares unsweetened
|
| 134 |
+
chocolate. Instructions: Lightly butter a 7 or 8 inch square pan. Put all ingredients
|
| 135 |
+
(except chocolate squares) into mixing bowl: mix well together. Press into pan;
|
| 136 |
+
smooth surface. Melt chocolate in double broiler; spread evenly over top of mixture. Score
|
| 137 |
+
with fork. Refrigerate until firm. Cut into small bars.'
|
| 138 |
+
- 'Ingredients: 1 3/4 cups all-purpose flour, 1 tablespoon baking powder, 1/2 teaspoon
|
| 139 |
+
salt, 3/4 cup white sugar, 1/2 cup lowfat cream cheese, 2 eggs, 3/4 cup mashed
|
| 140 |
+
bananas, 1/4 cup brewed chai tea. Instructions: In a medium bowl mix together
|
| 141 |
+
flour, baking powder, and salt. In a separate bowl mix sugar, cream cheese, and
|
| 142 |
+
eggs until light and fluffy. Mix mashed bananas and Chai into cream cheese mixture.
|
| 143 |
+
Add flour mixture and mix until smooth. Pour mixture into a greased 9x5 inch loaf
|
| 144 |
+
pan. Bake in a preheated 350 degree F(175 degrees C) oven for 60 minutes. Cool
|
| 145 |
+
on rack. Remove from pan after 10 minutes.'
|
| 146 |
+
pipeline_tag: sentence-similarity
|
| 147 |
+
model-index:
|
| 148 |
+
- name: SentenceTransformer based on sentence-transformers/all-distilroberta-v1
|
| 149 |
+
results:
|
| 150 |
+
- task:
|
| 151 |
+
type: semantic-similarity
|
| 152 |
+
name: Semantic Similarity
|
| 153 |
+
dataset:
|
| 154 |
+
name: val evaluator
|
| 155 |
+
type: val-evaluator
|
| 156 |
+
metrics:
|
| 157 |
+
- type: pearson_cosine
|
| 158 |
+
value: 0.9427502034315512
|
| 159 |
+
name: Pearson Cosine
|
| 160 |
+
- type: spearman_cosine
|
| 161 |
+
value: 0.9450402775914729
|
| 162 |
+
name: Spearman Cosine
|
| 163 |
+
- type: pearson_manhattan
|
| 164 |
+
value: 0.9339570316757035
|
| 165 |
+
name: Pearson Manhattan
|
| 166 |
+
- type: spearman_manhattan
|
| 167 |
+
value: 0.9423095584878247
|
| 168 |
+
name: Spearman Manhattan
|
| 169 |
+
- type: pearson_euclidean
|
| 170 |
+
value: 0.9368025558795947
|
| 171 |
+
name: Pearson Euclidean
|
| 172 |
+
- type: spearman_euclidean
|
| 173 |
+
value: 0.9450402775914729
|
| 174 |
+
name: Spearman Euclidean
|
| 175 |
+
- type: pearson_dot
|
| 176 |
+
value: 0.9427502030632885
|
| 177 |
+
name: Pearson Dot
|
| 178 |
+
- type: spearman_dot
|
| 179 |
+
value: 0.9450402775914729
|
| 180 |
+
name: Spearman Dot
|
| 181 |
+
- type: pearson_max
|
| 182 |
+
value: 0.9427502034315512
|
| 183 |
+
name: Pearson Max
|
| 184 |
+
- type: spearman_max
|
| 185 |
+
value: 0.9450402775914729
|
| 186 |
+
name: Spearman Max
|
| 187 |
+
---
|
| 188 |
+
|
| 189 |
+
# SentenceTransformer based on sentence-transformers/all-distilroberta-v1
|
| 190 |
+
|
| 191 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-distilroberta-v1](https://huggingface.co/sentence-transformers/all-distilroberta-v1). 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.
|
| 192 |
+
|
| 193 |
+
## Model Details
|
| 194 |
+
|
| 195 |
+
### Model Description
|
| 196 |
+
- **Model Type:** Sentence Transformer
|
| 197 |
+
- **Base model:** [sentence-transformers/all-distilroberta-v1](https://huggingface.co/sentence-transformers/all-distilroberta-v1) <!-- at revision 14e2a3f3090548596d23882845152a951333c0e3 -->
|
| 198 |
+
- **Maximum Sequence Length:** 512 tokens
|
| 199 |
+
- **Output Dimensionality:** 768 tokens
|
| 200 |
+
- **Similarity Function:** Cosine Similarity
|
| 201 |
+
<!-- - **Training Dataset:** Unknown -->
|
| 202 |
+
<!-- - **Language:** Unknown -->
|
| 203 |
+
<!-- - **License:** Unknown -->
|
| 204 |
+
|
| 205 |
+
### Model Sources
|
| 206 |
+
|
| 207 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
| 208 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
| 209 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
| 210 |
+
|
| 211 |
+
### Full Model Architecture
|
| 212 |
+
|
| 213 |
+
```
|
| 214 |
+
SentenceTransformer(
|
| 215 |
+
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: RobertaModel
|
| 216 |
+
(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})
|
| 217 |
+
(2): Normalize()
|
| 218 |
+
)
|
| 219 |
+
```
|
| 220 |
+
|
| 221 |
+
## Usage
|
| 222 |
+
|
| 223 |
+
### Direct Usage (Sentence Transformers)
|
| 224 |
+
|
| 225 |
+
First install the Sentence Transformers library:
|
| 226 |
+
|
| 227 |
+
```bash
|
| 228 |
+
pip install -U sentence-transformers
|
| 229 |
+
```
|
| 230 |
+
|
| 231 |
+
Then you can load this model and run inference.
|
| 232 |
+
```python
|
| 233 |
+
from sentence_transformers import SentenceTransformer
|
| 234 |
+
|
| 235 |
+
# Download from the 🤗 Hub
|
| 236 |
+
model = SentenceTransformer("sentence_transformers_model_id")
|
| 237 |
+
# Run inference
|
| 238 |
+
sentences = [
|
| 239 |
+
'Ingredients: 1 head cabbage, cored and shredded, 1/8 cup olive oil. Instructions: Place the shredded cabbage in a large bowl, and drizzle olive oil over it. Toss until evenly coated. Season with garlic powder, lemon juice and cilantro, and stir to blend in all of the flavors.',
|
| 240 |
+
'Ingredients: 1/2 cup canola oil, 1/4 cup red wine vinegar, 1 tablespoon soy sauce, 6 tablespoons white sugar, 1 (8 ounce) package shredded cabbage. Instructions: Mix canola oil, red wine vinegar, soy sauce, and sugar in a large bowl, mixing until sugar has dissolved. Toss cabbage, green onions, almonds, and sunflower seed kernels into the dressing. Cover bowl and refrigerate at least 1 hour before serving; slaw tastes better when chilled overnight.',
|
| 241 |
+
'Ingredients: 1/4 cup instant cocoa powder, 1 cup shredded coconut, 1/3 cup raisins, 1/2 cup cornflakes cereal, 1/4 cup chopped walnuts, 1 teaspoon sherry, 2 cups vanilla wafer crumbs, 1/4 cup sweetened condensed milk, 3 (1 ounce) squares unsweetened chocolate. Instructions: Lightly butter a 7 or 8 inch square pan. Put all ingredients (except chocolate squares) into mixing bowl: mix well together. Press into pan; smooth surface. Melt chocolate in double broiler; spread evenly over top of mixture. Score with fork. Refrigerate until firm. Cut into small bars.',
|
| 242 |
+
]
|
| 243 |
+
embeddings = model.encode(sentences)
|
| 244 |
+
print(embeddings.shape)
|
| 245 |
+
# [3, 768]
|
| 246 |
+
|
| 247 |
+
# Get the similarity scores for the embeddings
|
| 248 |
+
similarities = model.similarity(embeddings, embeddings)
|
| 249 |
+
print(similarities.shape)
|
| 250 |
+
# [3, 3]
|
| 251 |
+
```
|
| 252 |
+
|
| 253 |
+
<!--
|
| 254 |
+
### Direct Usage (Transformers)
|
| 255 |
+
|
| 256 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
| 257 |
+
|
| 258 |
+
</details>
|
| 259 |
+
-->
|
| 260 |
+
|
| 261 |
+
<!--
|
| 262 |
+
### Downstream Usage (Sentence Transformers)
|
| 263 |
+
|
| 264 |
+
You can finetune this model on your own dataset.
|
| 265 |
+
|
| 266 |
+
<details><summary>Click to expand</summary>
|
| 267 |
+
|
| 268 |
+
</details>
|
| 269 |
+
-->
|
| 270 |
+
|
| 271 |
+
<!--
|
| 272 |
+
### Out-of-Scope Use
|
| 273 |
+
|
| 274 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
| 275 |
+
-->
|
| 276 |
+
|
| 277 |
+
## Evaluation
|
| 278 |
+
|
| 279 |
+
### Metrics
|
| 280 |
+
|
| 281 |
+
#### Semantic Similarity
|
| 282 |
+
* Dataset: `val-evaluator`
|
| 283 |
+
* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
|
| 284 |
+
|
| 285 |
+
| Metric | Value |
|
| 286 |
+
|:-------------------|:----------|
|
| 287 |
+
| pearson_cosine | 0.9428 |
|
| 288 |
+
| spearman_cosine | 0.945 |
|
| 289 |
+
| pearson_manhattan | 0.934 |
|
| 290 |
+
| spearman_manhattan | 0.9423 |
|
| 291 |
+
| pearson_euclidean | 0.9368 |
|
| 292 |
+
| spearman_euclidean | 0.945 |
|
| 293 |
+
| pearson_dot | 0.9428 |
|
| 294 |
+
| spearman_dot | 0.945 |
|
| 295 |
+
| pearson_max | 0.9428 |
|
| 296 |
+
| **spearman_max** | **0.945** |
|
| 297 |
+
|
| 298 |
+
<!--
|
| 299 |
+
## Bias, Risks and Limitations
|
| 300 |
+
|
| 301 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
| 302 |
+
-->
|
| 303 |
+
|
| 304 |
+
<!--
|
| 305 |
+
### Recommendations
|
| 306 |
+
|
| 307 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
| 308 |
+
-->
|
| 309 |
+
|
| 310 |
+
## Training Details
|
| 311 |
+
|
| 312 |
+
### Training Dataset
|
| 313 |
+
|
| 314 |
+
#### Unnamed Dataset
|
| 315 |
+
|
| 316 |
+
|
| 317 |
+
* Size: 28,937 training samples
|
| 318 |
+
* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code>
|
| 319 |
+
* Approximate statistics based on the first 1000 samples:
|
| 320 |
+
| | sentence_0 | sentence_1 | label |
|
| 321 |
+
|:--------|:------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|:-----------------------------------------------------------------|
|
| 322 |
+
| type | string | string | float |
|
| 323 |
+
| details | <ul><li>min: 57 tokens</li><li>mean: 230.8 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 44 tokens</li><li>mean: 235.93 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 0.02</li><li>mean: 0.48</li><li>max: 1.44</li></ul> |
|
| 324 |
+
* Samples:
|
| 325 |
+
| sentence_0 | sentence_1 | label |
|
| 326 |
+
|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------|
|
| 327 |
+
| <code>Ingredients: 2 cups milk, 2 (.25 ounce) packages active dry yeast, 1/2 cup warm water, 1/3 cup white sugar, 1/3 cup vegetable oil, 1 tablespoon baking powder, 2 teaspoons salt, 1 egg, 7 cups all-purpose flour, 1 cup packed brown sugar, 1/2 cup butter, 2 tablespoons light corn syrup, 1 cup pecan halves, 1/4 cup butter, softened, 1/2 cup white sugar, 1 1/2 tablespoons ground cinnamon. Instructions: Warm the milk in a small saucepan until it bubbles, then remove from heat. Let cool until lukewarm. In a small bowl, dissolve yeast in warm water. Let stand until creamy, about 10 minutes. In a large bowl, combine yeast mixture, milk, sugar, oil, baking powder, salt, egg and 3 cups flour. Beat until smooth. Stir in the remaining flour, 1/2 cup at a time, beating well after each addition. When the dough has pulled together, turn it out onto a lightly floured surface and knead until smooth and elastic, about 8 minutes. Lightly oil a large bowl, place the dough in the bowl and turn to coat with oil. Cover with a damp cloth and let rise in a warm place until doubled in volume, about 1 hour. Heat brown sugar and 1/2 cup butter until melted. Remove from heat; stir in corn syrup. Divide mixture between two 9x13 inch baking pans. Sprinkle 1/2 cup pecans in each pan. When dough has doubled in size, punch down and turn out onto a lightly floured surface. Roll out into a large rectangle and spread with butter. Sprinkle with sugar and cinnamon. Starting with the long side, roll up the rectangle into a log, and slice into 1 inch wide rolls. Place the rolls slightly apart in pans. Wrap pans with aluminum foil and refrigerate at least 12 hours but no longer than 48. Remove rolls from refrigerator and let stand in a warm place until doubled in size, about 30 minutes. Meanwhile, preheat oven to 350 degrees F (175 degrees C). Bake uncovered in preheated oven until golden 30 to 35 minutes. Immediately invert pan on heatproof serving plate. Wait for 1 or 2 minutes before removing pan, so that caramel drizzles over rolls.</code> | <code>Ingredients: 1/2 cup boiling water, 3/4 cup cold milk, 1 teaspoon white sugar, 1 1/2 teaspoons active dry yeast, 1 egg, beaten, 2 tablespoons butter, melted and cooled. Instructions: In a large bowl, stir together the water, milk, and sugar. Sprinkle the yeast over the top, and let stand for 5 minutes to dissolve. Stir the egg and butter into the yeast mixture, then stir in the salt, nutmeg, and 2 cups of the flour. Mix until everything is well blended. Mix in remaining flour, 1/2 cup at a time until the dough pulls away from the side of the bowl. Turn out onto a floured surface, and knead for 10 minutes (no cheating!). Place dough into a greased bowl, and let rise until doubled in size. Divide the dough into 8 balls, and let rest for another 20 minutes. Roll each ball out to 8 to 10 inches in diameter. Heat a cast-iron skillet over medium-high heat. Fry each of the pieces of bread fro 30 to 60 seconds on each side, or until light to medium brown spots appear. Keep covered with a damp cloth, or store in a plastic bag until serving.</code> | <code>0.7624140157295458</code> |
|
| 328 |
+
| <code>Ingredients: 4 cups bread flour, or more as needed, 1/3 cup white sugar, 1 teaspoon salt, 1 (.25 ounce) package rapid-rise yeast, 1/3 cup unsalted butter, melted, 1 1/2 cups hot tap water, 1 large egg, 1 teaspoon oil, or as needed, 1/2 cup brown sugar, or as needed, 1/2 cup chopped pecans, or as needed, 2 tablespoons ground cinnamon, or as needed, 1/2 cup unsalted butter, melted, or as needed, 1 1/2 cups confectioners' sugar, 1/4 cup unsalted butter, softened. Instructions: Sift 2 cups flour, sugar, and salt for dough together into the bowl of a stand mixer fitted with the paddle attachment. Stir in yeast. Add butter and blend at low speed until combined. Add hot water (the hottest it comes from your tap) all at once with the mixer running. Mix in egg until fully incorporated. Add remaining 2 cups flour and mix briefly until dough is soft and flour is incorporated. Change to the dough hook and knead dough for 10 minutes. If dough does not knead, you may need to add a little bit more flour carefully while the mixer is running. Once the dough climbs up the dough hook you have the right consistency. Make dough into a ball. Oil a bowl. Place the dough into the bowl and turn to coat with oil. Cover with a cloth and let sit until doubled in size, 1 to 2 hours. Cover your countertop with flour and roll dough out to a large rectangle, roughly 18x24 inches. Sprinkle brown sugar, pecans, and cinnamon on the dough, then pour melted butter over top. Roll the dough up from the longer side and cut into twelve 2-inch pieces. Place the pieces in a baking pan or on a baking stone. Cover with a cloth and let rise until doubled in size, about 45 minutes. Keep a close eye on the rolls; if they start to fall or look deflated at all, bake them immediately. Preheat the oven to 375 degrees F (190 degrees C). Bake the rolls in the preheated oven until golden brown, 6 to 10 minutes. Meanwhile, combine confectioners' sugar, butter, cream cheese, vanilla, and salt in a large bowl; beat with an electric mixer until no lumps of cream cheese remain. Whip for 2 to 3 more minutes on medium speed. Spread icing on warm rolls and serve.</code> | <code>Ingredients: 1 cup all-purpose flour, 1 cup rolled oats, 1 cup packed brown sugar, 1 teaspoon baking soda, 1/4 teaspoon salt, 1/2 cup butter, 2 eggs, 1 cup packed brown sugar, 1/2 teaspoon almond extract, 1 tablespoon all-purpose flour, 1 teaspoon baking powder, 1/2 teaspoon salt, 1 cup flaked coconut, 1 cup maraschino cherries, drained and juice reserved, 1/2 cup chopped pecans, 6 tablespoons butter, softened, 4 cups confectioners' sugar, 2 teaspoons vanilla extract. Instructions: Preheat oven to 350 degrees F (175 degrees C). In a medium bowl, stir together 1 cup flour, oats, 1 cup brown sugar, baking soda and 1/4 teaspoon salt. Rub in the 1/2 cup of butter until crumbly. Press into the bottom of a 9x13 inch baking pan. Bake for 10 minutes in the preheated oven. Remove and cool. Make the filling while the crust is baking. In a medium bowl, beat eggs, almond extract, 1 cup of brown sugar, 1 tablespoon of flour, baking powder and 1/2 teaspoon of salt until smooth. Stir in the coconut, cherries and pecans. Spread over the pre-baked crust. Bake for 25 minutes in the preheated oven, until light brown. Let cool before icing. To make the icing, mix together the remaining 6 tablespoons butter, confectioners' sugar and vanilla until smooth. Gradually add the reserved cherry juice until the desired consistency is reached. Drizzle over cooled bars before cutting into squares.</code> | <code>0.7566587642301353</code> |
|
| 329 |
+
| <code>Ingredients: 1/2 cup butter, 1 7/8 cups white sugar, 4 egg yolks, 1 cup all-purpose flour, 1 cup unsweetened cocoa powder, 1 1/3 tablespoons baking powder, 1/2 teaspoon salt, 4 egg whites, 1 cup milk, 2 teaspoons vanilla extract, 2 cups semisweet chocolate chips, 3/4 cup sour cream, 1 teaspoon vanilla extract, 1 pinch salt. Instructions: Preheat oven to 325 degrees F (165 degrees C). Grease and flour three 9 inch round cake pans. In a large bowl, cream together the butter and sugar. Beat in the egg yolks, one at a time. Stir in 2 teaspoons vanilla. Combine the flour, cocoa, baking powder and salt, stir into the creamed mixture alternately with the milk. In a large clean glass or metal bowl, whip egg whites until soft peaks form. Fold 1/3 of whites into batter to lighten it, then quickly fold in remaining whites until no streaks remain. Divide batter into the 3 prepared pans. Bake for 20 to 25 minutes in the preheated oven, until a toothpick inserted into the center of the cake comes out clean. Cool in pans on a wire rack. To make the frosting: Melt the chocolate chips in the top of a double boiler, stirring occasionally until smooth. Remove from heat and stir in the sour cream, 1 teaspoon vanilla and pinch of salt. Frosting can be used warm to fill and frost the 3 layers.</code> | <code>Ingredients: 1/2 cup butter, 2 cups all-purpose flour, 1 cup white sugar, 1/2 cup packed brown sugar, 2 eggs, 1 teaspoon baking powder, 1 teaspoon baking soda, 1 cup sour cream, 1 teaspoon vanilla extract, 1 teaspoon ground cinnamon, 1/4 cup brown sugar, 4 tablespoons milk, 1 cup confectioners' sugar, 1/4 ounce candy sprinkles (optional). Instructions: In a large bowl, blend together butter or margarine, white sugar, 1/2 cup brown sugar, sour cream, eggs, and vanilla. Add to these ingredients the flour, baking powder, and soda. Blend until smooth. To Make Filling: Combine cinnamon and 1/4 cup brown sugar. Grease and flour a large Bundt pan. Pour 1/2 of the batter into the prepared pan. Sprinkle the cinnamon sugar mix on top of the batter in the pan, and cover with the remaining batter. Bake at 350 degrees F (175 degrees C) for 45 to 50 minutes. Cool. Make a thick glaze by mixing together confectioners' sugar with 2 to 3 tablespoons milk until smooth. Pour over cooled cake, and add sprinkles if desired.</code> | <code>0.8263426596124509</code> |
|
| 330 |
+
* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
|
| 331 |
+
```json
|
| 332 |
+
{
|
| 333 |
+
"loss_fct": "torch.nn.modules.loss.MSELoss"
|
| 334 |
+
}
|
| 335 |
+
```
|
| 336 |
+
|
| 337 |
+
### Training Hyperparameters
|
| 338 |
+
#### Non-Default Hyperparameters
|
| 339 |
+
|
| 340 |
+
- `eval_strategy`: steps
|
| 341 |
+
- `per_device_train_batch_size`: 16
|
| 342 |
+
- `per_device_eval_batch_size`: 16
|
| 343 |
+
- `num_train_epochs`: 1
|
| 344 |
+
- `multi_dataset_batch_sampler`: round_robin
|
| 345 |
+
|
| 346 |
+
#### All Hyperparameters
|
| 347 |
+
<details><summary>Click to expand</summary>
|
| 348 |
+
|
| 349 |
+
- `overwrite_output_dir`: False
|
| 350 |
+
- `do_predict`: False
|
| 351 |
+
- `eval_strategy`: steps
|
| 352 |
+
- `prediction_loss_only`: True
|
| 353 |
+
- `per_device_train_batch_size`: 16
|
| 354 |
+
- `per_device_eval_batch_size`: 16
|
| 355 |
+
- `per_gpu_train_batch_size`: None
|
| 356 |
+
- `per_gpu_eval_batch_size`: None
|
| 357 |
+
- `gradient_accumulation_steps`: 1
|
| 358 |
+
- `eval_accumulation_steps`: None
|
| 359 |
+
- `learning_rate`: 5e-05
|
| 360 |
+
- `weight_decay`: 0.0
|
| 361 |
+
- `adam_beta1`: 0.9
|
| 362 |
+
- `adam_beta2`: 0.999
|
| 363 |
+
- `adam_epsilon`: 1e-08
|
| 364 |
+
- `max_grad_norm`: 1
|
| 365 |
+
- `num_train_epochs`: 1
|
| 366 |
+
- `max_steps`: -1
|
| 367 |
+
- `lr_scheduler_type`: linear
|
| 368 |
+
- `lr_scheduler_kwargs`: {}
|
| 369 |
+
- `warmup_ratio`: 0.0
|
| 370 |
+
- `warmup_steps`: 0
|
| 371 |
+
- `log_level`: passive
|
| 372 |
+
- `log_level_replica`: warning
|
| 373 |
+
- `log_on_each_node`: True
|
| 374 |
+
- `logging_nan_inf_filter`: True
|
| 375 |
+
- `save_safetensors`: True
|
| 376 |
+
- `save_on_each_node`: False
|
| 377 |
+
- `save_only_model`: False
|
| 378 |
+
- `restore_callback_states_from_checkpoint`: False
|
| 379 |
+
- `no_cuda`: False
|
| 380 |
+
- `use_cpu`: False
|
| 381 |
+
- `use_mps_device`: False
|
| 382 |
+
- `seed`: 42
|
| 383 |
+
- `data_seed`: None
|
| 384 |
+
- `jit_mode_eval`: False
|
| 385 |
+
- `use_ipex`: False
|
| 386 |
+
- `bf16`: False
|
| 387 |
+
- `fp16`: False
|
| 388 |
+
- `fp16_opt_level`: O1
|
| 389 |
+
- `half_precision_backend`: auto
|
| 390 |
+
- `bf16_full_eval`: False
|
| 391 |
+
- `fp16_full_eval`: False
|
| 392 |
+
- `tf32`: None
|
| 393 |
+
- `local_rank`: 0
|
| 394 |
+
- `ddp_backend`: None
|
| 395 |
+
- `tpu_num_cores`: None
|
| 396 |
+
- `tpu_metrics_debug`: False
|
| 397 |
+
- `debug`: []
|
| 398 |
+
- `dataloader_drop_last`: False
|
| 399 |
+
- `dataloader_num_workers`: 0
|
| 400 |
+
- `dataloader_prefetch_factor`: None
|
| 401 |
+
- `past_index`: -1
|
| 402 |
+
- `disable_tqdm`: False
|
| 403 |
+
- `remove_unused_columns`: True
|
| 404 |
+
- `label_names`: None
|
| 405 |
+
- `load_best_model_at_end`: False
|
| 406 |
+
- `ignore_data_skip`: False
|
| 407 |
+
- `fsdp`: []
|
| 408 |
+
- `fsdp_min_num_params`: 0
|
| 409 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
| 410 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
| 411 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
| 412 |
+
- `deepspeed`: None
|
| 413 |
+
- `label_smoothing_factor`: 0.0
|
| 414 |
+
- `optim`: adamw_torch
|
| 415 |
+
- `optim_args`: None
|
| 416 |
+
- `adafactor`: False
|
| 417 |
+
- `group_by_length`: False
|
| 418 |
+
- `length_column_name`: length
|
| 419 |
+
- `ddp_find_unused_parameters`: None
|
| 420 |
+
- `ddp_bucket_cap_mb`: None
|
| 421 |
+
- `ddp_broadcast_buffers`: False
|
| 422 |
+
- `dataloader_pin_memory`: True
|
| 423 |
+
- `dataloader_persistent_workers`: False
|
| 424 |
+
- `skip_memory_metrics`: True
|
| 425 |
+
- `use_legacy_prediction_loop`: False
|
| 426 |
+
- `push_to_hub`: False
|
| 427 |
+
- `resume_from_checkpoint`: None
|
| 428 |
+
- `hub_model_id`: None
|
| 429 |
+
- `hub_strategy`: every_save
|
| 430 |
+
- `hub_private_repo`: False
|
| 431 |
+
- `hub_always_push`: False
|
| 432 |
+
- `gradient_checkpointing`: False
|
| 433 |
+
- `gradient_checkpointing_kwargs`: None
|
| 434 |
+
- `include_inputs_for_metrics`: False
|
| 435 |
+
- `eval_do_concat_batches`: True
|
| 436 |
+
- `fp16_backend`: auto
|
| 437 |
+
- `push_to_hub_model_id`: None
|
| 438 |
+
- `push_to_hub_organization`: None
|
| 439 |
+
- `mp_parameters`:
|
| 440 |
+
- `auto_find_batch_size`: False
|
| 441 |
+
- `full_determinism`: False
|
| 442 |
+
- `torchdynamo`: None
|
| 443 |
+
- `ray_scope`: last
|
| 444 |
+
- `ddp_timeout`: 1800
|
| 445 |
+
- `torch_compile`: False
|
| 446 |
+
- `torch_compile_backend`: None
|
| 447 |
+
- `torch_compile_mode`: None
|
| 448 |
+
- `dispatch_batches`: None
|
| 449 |
+
- `split_batches`: None
|
| 450 |
+
- `include_tokens_per_second`: False
|
| 451 |
+
- `include_num_input_tokens_seen`: False
|
| 452 |
+
- `neftune_noise_alpha`: None
|
| 453 |
+
- `optim_target_modules`: None
|
| 454 |
+
- `batch_eval_metrics`: False
|
| 455 |
+
- `batch_sampler`: batch_sampler
|
| 456 |
+
- `multi_dataset_batch_sampler`: round_robin
|
| 457 |
+
|
| 458 |
+
</details>
|
| 459 |
+
|
| 460 |
+
### Training Logs
|
| 461 |
+
| Epoch | Step | Training Loss | val-evaluator_spearman_max |
|
| 462 |
+
|:------:|:----:|:-------------:|:--------------------------:|
|
| 463 |
+
| 0.0553 | 100 | - | 0.8950 |
|
| 464 |
+
| 0.1106 | 200 | - | 0.9175 |
|
| 465 |
+
| 0.1658 | 300 | - | 0.9211 |
|
| 466 |
+
| 0.2211 | 400 | - | 0.9221 |
|
| 467 |
+
| 0.2764 | 500 | 0.0093 | 0.9239 |
|
| 468 |
+
| 0.3317 | 600 | - | 0.9308 |
|
| 469 |
+
| 0.3870 | 700 | - | 0.9340 |
|
| 470 |
+
| 0.4422 | 800 | - | 0.9324 |
|
| 471 |
+
| 0.4975 | 900 | - | 0.9338 |
|
| 472 |
+
| 0.5528 | 1000 | 0.0063 | 0.9376 |
|
| 473 |
+
| 0.6081 | 1100 | - | 0.9379 |
|
| 474 |
+
| 0.6633 | 1200 | - | 0.9420 |
|
| 475 |
+
| 0.7186 | 1300 | - | 0.9419 |
|
| 476 |
+
| 0.7739 | 1400 | - | 0.9420 |
|
| 477 |
+
| 0.8292 | 1500 | 0.0057 | 0.9441 |
|
| 478 |
+
| 0.8845 | 1600 | - | 0.9446 |
|
| 479 |
+
| 0.9397 | 1700 | - | 0.9446 |
|
| 480 |
+
| 0.9950 | 1800 | - | 0.9450 |
|
| 481 |
+
| 1.0 | 1809 | - | 0.9450 |
|
| 482 |
+
|
| 483 |
+
|
| 484 |
+
### Framework Versions
|
| 485 |
+
- Python: 3.10.12
|
| 486 |
+
- Sentence Transformers: 3.0.0
|
| 487 |
+
- Transformers: 4.41.1
|
| 488 |
+
- PyTorch: 2.3.0+cu121
|
| 489 |
+
- Accelerate: 0.30.1
|
| 490 |
+
- Datasets: 2.19.1
|
| 491 |
+
- Tokenizers: 0.19.1
|
| 492 |
+
|
| 493 |
+
## Citation
|
| 494 |
+
|
| 495 |
+
### BibTeX
|
| 496 |
+
|
| 497 |
+
#### Sentence Transformers
|
| 498 |
+
```bibtex
|
| 499 |
+
@inproceedings{reimers-2019-sentence-bert,
|
| 500 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
| 501 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
| 502 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
| 503 |
+
month = "11",
|
| 504 |
+
year = "2019",
|
| 505 |
+
publisher = "Association for Computational Linguistics",
|
| 506 |
+
url = "https://arxiv.org/abs/1908.10084",
|
| 507 |
+
}
|
| 508 |
+
```
|
| 509 |
+
|
| 510 |
+
<!--
|
| 511 |
+
## Glossary
|
| 512 |
+
|
| 513 |
+
*Clearly define terms in order to be accessible across audiences.*
|
| 514 |
+
-->
|
| 515 |
+
|
| 516 |
+
<!--
|
| 517 |
+
## Model Card Authors
|
| 518 |
+
|
| 519 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
| 520 |
+
-->
|
| 521 |
+
|
| 522 |
+
<!--
|
| 523 |
+
## Model Card Contact
|
| 524 |
+
|
| 525 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
| 526 |
+
-->
|
config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "fine_tuned_sbert_recipes",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaModel"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"layer_norm_eps": 1e-05,
|
| 17 |
+
"max_position_embeddings": 514,
|
| 18 |
+
"model_type": "roberta",
|
| 19 |
+
"num_attention_heads": 12,
|
| 20 |
+
"num_hidden_layers": 6,
|
| 21 |
+
"pad_token_id": 1,
|
| 22 |
+
"position_embedding_type": "absolute",
|
| 23 |
+
"torch_dtype": "float32",
|
| 24 |
+
"transformers_version": "4.41.2",
|
| 25 |
+
"type_vocab_size": 1,
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 50265
|
| 28 |
+
}
|
config_sentence_transformers.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"__version__": {
|
| 3 |
+
"sentence_transformers": "2.0.0",
|
| 4 |
+
"transformers": "4.6.1",
|
| 5 |
+
"pytorch": "1.8.1"
|
| 6 |
+
},
|
| 7 |
+
"prompts": {},
|
| 8 |
+
"default_prompt_name": null,
|
| 9 |
+
"similarity_fn_name": null
|
| 10 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c49fe7d0131504fdd9af69584dc60e9d83fed96ae515e92f3d1cc66f1718f0a
|
| 3 |
+
size 328485128
|
modules.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
{
|
| 15 |
+
"idx": 2,
|
| 16 |
+
"name": "2",
|
| 17 |
+
"path": "2_Normalize",
|
| 18 |
+
"type": "sentence_transformers.models.Normalize"
|
| 19 |
+
}
|
| 20 |
+
]
|
sentence_bert_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"max_seq_length": 512,
|
| 3 |
+
"do_lower_case": false
|
| 4 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": true,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"mask_token": "<mask>",
|
| 51 |
+
"max_length": 128,
|
| 52 |
+
"model_max_length": 512,
|
| 53 |
+
"pad_to_multiple_of": null,
|
| 54 |
+
"pad_token": "<pad>",
|
| 55 |
+
"pad_token_type_id": 0,
|
| 56 |
+
"padding_side": "right",
|
| 57 |
+
"sep_token": "</s>",
|
| 58 |
+
"stride": 0,
|
| 59 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 60 |
+
"trim_offsets": true,
|
| 61 |
+
"truncation_side": "right",
|
| 62 |
+
"truncation_strategy": "longest_first",
|
| 63 |
+
"unk_token": "<unk>"
|
| 64 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|