MohamedAshraf701 commited on
Commit
9b279ab
·
verified ·
1 Parent(s): 3ecf4e9

Upload fine-tuned model

Browse files
Files changed (2) hide show
  1. README.md +56 -70
  2. model.safetensors +1 -1
README.md CHANGED
@@ -13,47 +13,47 @@ widget:
13
  - source_sentence: Men
14
  sentences:
15
  - Casual
16
- - Summer
17
- - Cream
18
- - Timberland Men's Madbury Convertible Off White Pant
19
- - Apparel
20
- - Track Pants
21
- - Bottomwear
22
- - source_sentence: Women
23
  sentences:
24
- - Fall
25
- - Brown
26
  - Casual
27
  - Accessories
28
- - Allen Solly Woman Women Brown Pendant
29
- - Jewellery
30
- - Pendant
31
- - source_sentence: Men
32
  sentences:
33
- - Tshirts
34
- - White
35
  - Casual
36
- - Apparel
37
  - Summer
38
- - Scullers Men White Striped T-shirt
39
- - Topwear
40
- - source_sentence: Women
41
  sentences:
42
- - Handbags
43
  - Summer
44
  - Accessories
45
  - Brown
46
- - Casual
47
- - Lino Perros Women Brown Handbag
48
- - Bags
49
- - source_sentence: Boys
50
  sentences:
51
- - Grey
52
  - Apparel
53
  - Topwear
54
- - Gini and Jony Boys Around The World Grey T-shirt
55
  - Tshirts
56
- - Summer
57
  - Casual
58
  ---
59
 
@@ -107,7 +107,7 @@ from sentence_transformers import SentenceTransformer
107
  model = SentenceTransformer("sentence_transformers_model_id")
108
  # Run inference
109
  sentences = [
110
- 'Boys',
111
  'Apparel',
112
  'Topwear',
113
  ]
@@ -167,16 +167,16 @@ You can finetune this model on your own dataset.
167
  * Size: 44,072 training samples
168
  * Columns: <code>sentence_0</code>, <code>sentence_1</code>, <code>sentence_2</code>, <code>sentence_3</code>, <code>sentence_4</code>, <code>sentence_5</code>, <code>sentence_6</code>, and <code>sentence_7</code>
169
  * Approximate statistics based on the first 1000 samples:
170
- | | sentence_0 | sentence_1 | sentence_2 | sentence_3 | sentence_4 | sentence_5 | sentence_6 | sentence_7 |
171
- |:--------|:--------------------------------------------------------------------------------|:--------------------------------------------------------------------------------|:--------------------------------------------------------------------------------|:-------------------------------------------------------------------------------|:--------------------------------------------------------------------------------|:-------------------------------------------------------------------------------|:-------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
172
- | type | string | string | string | string | string | string | string | string |
173
- | details | <ul><li>min: 3 tokens</li><li>mean: 3.11 tokens</li><li>max: 5 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 3.27 tokens</li><li>max: 4 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 3.62 tokens</li><li>max: 7 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 3.9 tokens</li><li>max: 7 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 3.07 tokens</li><li>max: 5 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 3.0 tokens</li><li>max: 3 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 3.0 tokens</li><li>max: 4 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 10.12 tokens</li><li>max: 24 tokens</li></ul> |
174
  * Samples:
175
- | sentence_0 | sentence_1 | sentence_2 | sentence_3 | sentence_4 | sentence_5 | sentence_6 | sentence_7 |
176
- |:------------------|:---------------------|:---------------------|:---------------------|:-------------------|:--------------------|:--------------------|:----------------------------------------------------|
177
- | <code>Boys</code> | <code>Apparel</code> | <code>Topwear</code> | <code>Tshirts</code> | <code>Blue</code> | <code>Summer</code> | <code>Casual</code> | <code>Mr.Men Boys A Lot Of Work Blue T-shirt</code> |
178
- | <code>Men</code> | <code>Apparel</code> | <code>Topwear</code> | <code>Shirts</code> | <code>Blue</code> | <code>Fall</code> | <code>Casual</code> | <code>Locomotive Men Check Blue Shirt</code> |
179
- | <code>Men</code> | <code>Apparel</code> | <code>Topwear</code> | <code>Shirts</code> | <code>Black</code> | <code>Fall</code> | <code>Formal</code> | <code>Arrow Men Stripes Black Shirts</code> |
180
  * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
181
  ```json
182
  {
@@ -188,8 +188,8 @@ You can finetune this model on your own dataset.
188
  ### Training Hyperparameters
189
  #### Non-Default Hyperparameters
190
 
191
- - `per_device_train_batch_size`: 64
192
- - `per_device_eval_batch_size`: 64
193
  - `num_train_epochs`: 20
194
  - `multi_dataset_batch_sampler`: round_robin
195
 
@@ -200,8 +200,8 @@ You can finetune this model on your own dataset.
200
  - `do_predict`: False
201
  - `eval_strategy`: no
202
  - `prediction_loss_only`: True
203
- - `per_device_train_batch_size`: 64
204
- - `per_device_eval_batch_size`: 64
205
  - `per_gpu_train_batch_size`: None
206
  - `per_gpu_eval_batch_size`: None
207
  - `gradient_accumulation_steps`: 1
@@ -312,35 +312,21 @@ You can finetune this model on your own dataset.
312
  </details>
313
 
314
  ### Training Logs
315
- | Epoch | Step | Training Loss |
316
- |:-------:|:-----:|:-------------:|
317
- | 0.7257 | 500 | 4.593 |
318
- | 1.4514 | 1000 | 4.1126 |
319
- | 2.1771 | 1500 | 4.1057 |
320
- | 2.9028 | 2000 | 4.1028 |
321
- | 3.6284 | 2500 | 4.1026 |
322
- | 4.3541 | 3000 | 4.1014 |
323
- | 5.0798 | 3500 | 4.1015 |
324
- | 5.8055 | 4000 | 4.1019 |
325
- | 6.5312 | 4500 | 4.1001 |
326
- | 7.2569 | 5000 | 4.1009 |
327
- | 7.9826 | 5500 | 4.1001 |
328
- | 8.7083 | 6000 | 4.0995 |
329
- | 9.4340 | 6500 | 4.099 |
330
- | 10.1597 | 7000 | 4.0995 |
331
- | 10.8853 | 7500 | 4.0995 |
332
- | 11.6110 | 8000 | 4.1004 |
333
- | 12.3367 | 8500 | 4.099 |
334
- | 13.0624 | 9000 | 4.0997 |
335
- | 13.7881 | 9500 | 4.0994 |
336
- | 14.5138 | 10000 | 4.0994 |
337
- | 15.2395 | 10500 | 4.0992 |
338
- | 15.9652 | 11000 | 4.0993 |
339
- | 16.6909 | 11500 | 4.0986 |
340
- | 17.4165 | 12000 | 4.0973 |
341
- | 18.1422 | 12500 | 4.0993 |
342
- | 18.8679 | 13000 | 4.0984 |
343
- | 19.5936 | 13500 | 4.0992 |
344
 
345
 
346
  ### Framework Versions
 
13
  - source_sentence: Men
14
  sentences:
15
  - Casual
16
+ - Spring
17
+ - Navy Blue
18
+ - Carlton London Men Navy Blue Shoes
19
+ - Footwear
20
+ - Casual Shoes
21
+ - Shoes
22
+ - source_sentence: Men
23
  sentences:
24
+ - Winter
25
+ - Black
26
  - Casual
27
  - Accessories
28
+ - United Colors of Benetton Men Black Sunglasses
29
+ - Eyewear
30
+ - Sunglasses
31
+ - source_sentence: Women
32
  sentences:
33
+ - Casual Shoes
34
+ - Purple
35
  - Casual
36
+ - Footwear
37
  - Summer
38
+ - ADIDAS Neo Women Renewal Purple Shoes
39
+ - Shoes
40
+ - source_sentence: Men
41
  sentences:
42
+ - Wallets
43
  - Summer
44
  - Accessories
45
  - Brown
46
+ - Formal
47
+ - Peter England Men Statements Brown Wallet
48
+ - Wallets
49
+ - source_sentence: Men
50
  sentences:
51
+ - Yellow
52
  - Apparel
53
  - Topwear
54
+ - Peter England Men Stripes Yellow Polo T-Shirt
55
  - Tshirts
56
+ - Fall
57
  - Casual
58
  ---
59
 
 
107
  model = SentenceTransformer("sentence_transformers_model_id")
108
  # Run inference
109
  sentences = [
110
+ 'Men',
111
  'Apparel',
112
  'Topwear',
113
  ]
 
167
  * Size: 44,072 training samples
168
  * Columns: <code>sentence_0</code>, <code>sentence_1</code>, <code>sentence_2</code>, <code>sentence_3</code>, <code>sentence_4</code>, <code>sentence_5</code>, <code>sentence_6</code>, and <code>sentence_7</code>
169
  * Approximate statistics based on the first 1000 samples:
170
+ | | sentence_0 | sentence_1 | sentence_2 | sentence_3 | sentence_4 | sentence_5 | sentence_6 | sentence_7 |
171
+ |:--------|:-------------------------------------------------------------------------------|:--------------------------------------------------------------------------------|:--------------------------------------------------------------------------------|:-------------------------------------------------------------------------------|:--------------------------------------------------------------------------------|:-------------------------------------------------------------------------------|:-------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
172
+ | type | string | string | string | string | string | string | string | string |
173
+ | details | <ul><li>min: 3 tokens</li><li>mean: 3.1 tokens</li><li>max: 5 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 3.26 tokens</li><li>max: 4 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 3.62 tokens</li><li>max: 7 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 3.9 tokens</li><li>max: 7 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 3.08 tokens</li><li>max: 5 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 3.0 tokens</li><li>max: 3 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 3.0 tokens</li><li>max: 3 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 10.13 tokens</li><li>max: 28 tokens</li></ul> |
174
  * Samples:
175
+ | sentence_0 | sentence_1 | sentence_2 | sentence_3 | sentence_4 | sentence_5 | sentence_6 | sentence_7 |
176
+ |:-------------------|:-------------------------|:-------------------|:--------------------------|:-------------------|:--------------------|:--------------------|:------------------------------------------------------|
177
+ | <code>Women</code> | <code>Footwear</code> | <code>Shoes</code> | <code>Heels</code> | <code>Gold</code> | <code>Summer</code> | <code>Casual</code> | <code>Enroute Women Gold Flats</code> |
178
+ | <code>Men</code> | <code>Accessories</code> | <code>Belts</code> | <code>Belts</code> | <code>Black</code> | <code>Fall</code> | <code>Casual</code> | <code>Wrangler Textured Men Black Belts</code> |
179
+ | <code>Men</code> | <code>Footwear</code> | <code>Shoes</code> | <code>Sports Shoes</code> | <code>Grey</code> | <code>Fall</code> | <code>Sports</code> | <code>Nike Men Air Max+ 2011 Grey Sports Shoes</code> |
180
  * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
181
  ```json
182
  {
 
188
  ### Training Hyperparameters
189
  #### Non-Default Hyperparameters
190
 
191
+ - `per_device_train_batch_size`: 128
192
+ - `per_device_eval_batch_size`: 128
193
  - `num_train_epochs`: 20
194
  - `multi_dataset_batch_sampler`: round_robin
195
 
 
200
  - `do_predict`: False
201
  - `eval_strategy`: no
202
  - `prediction_loss_only`: True
203
+ - `per_device_train_batch_size`: 128
204
+ - `per_device_eval_batch_size`: 128
205
  - `per_gpu_train_batch_size`: None
206
  - `per_gpu_eval_batch_size`: None
207
  - `gradient_accumulation_steps`: 1
 
312
  </details>
313
 
314
  ### Training Logs
315
+ | Epoch | Step | Training Loss |
316
+ |:-------:|:----:|:-------------:|
317
+ | 1.4493 | 500 | 5.1318 |
318
+ | 2.8986 | 1000 | 4.7978 |
319
+ | 4.3478 | 1500 | 4.7906 |
320
+ | 5.7971 | 2000 | 4.7948 |
321
+ | 7.2464 | 2500 | 4.7897 |
322
+ | 8.6957 | 3000 | 4.7936 |
323
+ | 10.1449 | 3500 | 4.789 |
324
+ | 11.5942 | 4000 | 4.7916 |
325
+ | 13.0435 | 4500 | 4.7887 |
326
+ | 14.4928 | 5000 | 4.7903 |
327
+ | 15.9420 | 5500 | 4.791 |
328
+ | 17.3913 | 6000 | 4.788 |
329
+ | 18.8406 | 6500 | 4.7909 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
330
 
331
 
332
  ### Framework Versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da4f911198a75f628278b25b6f2e9d7caa8d1465a0e6ac55c62e817b0382626d
3
  size 90864192
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30aa5b9f40abb7cb565642e6975afb531fb5aa3e3ce70e32fb7a2a7304bf8e6c
3
  size 90864192