sub-version a: Hyper Tunning for "full stack", "back end" and "front end"
Browse files- README.md +164 -164
- model card.txt +7 -5
- model.safetensors +1 -1
README.md
CHANGED
|
@@ -4,35 +4,35 @@ tags:
|
|
| 4 |
- sentence-similarity
|
| 5 |
- feature-extraction
|
| 6 |
- generated_from_trainer
|
| 7 |
-
- dataset_size:
|
| 8 |
- loss:CosineSimilarityLoss
|
| 9 |
base_model: intfloat/multilingual-e5-small
|
| 10 |
widget:
|
| 11 |
-
- source_sentence:
|
| 12 |
sentences:
|
| 13 |
-
-
|
| 14 |
-
-
|
| 15 |
-
-
|
| 16 |
-
- source_sentence:
|
| 17 |
sentences:
|
| 18 |
-
-
|
| 19 |
-
-
|
| 20 |
-
-
|
| 21 |
-
- source_sentence:
|
| 22 |
sentences:
|
| 23 |
-
-
|
| 24 |
-
-
|
| 25 |
-
-
|
| 26 |
-
- source_sentence:
|
| 27 |
sentences:
|
| 28 |
-
-
|
| 29 |
-
-
|
| 30 |
-
-
|
| 31 |
-
- source_sentence:
|
| 32 |
sentences:
|
| 33 |
-
-
|
| 34 |
-
-
|
| 35 |
-
-
|
| 36 |
pipeline_tag: sentence-similarity
|
| 37 |
library_name: sentence-transformers
|
| 38 |
metrics:
|
|
@@ -49,10 +49,10 @@ model-index:
|
|
| 49 |
type: sts-dev
|
| 50 |
metrics:
|
| 51 |
- type: pearson_cosine
|
| 52 |
-
value: 0.
|
| 53 |
name: Pearson Cosine
|
| 54 |
- type: spearman_cosine
|
| 55 |
-
value: 0.
|
| 56 |
name: Spearman Cosine
|
| 57 |
- task:
|
| 58 |
type: semantic-similarity
|
|
@@ -62,10 +62,10 @@ model-index:
|
|
| 62 |
type: sts-test
|
| 63 |
metrics:
|
| 64 |
- type: pearson_cosine
|
| 65 |
-
value: 0.
|
| 66 |
name: Pearson Cosine
|
| 67 |
- type: spearman_cosine
|
| 68 |
-
value: 0.
|
| 69 |
name: Spearman Cosine
|
| 70 |
---
|
| 71 |
|
|
@@ -119,9 +119,9 @@ from sentence_transformers import SentenceTransformer
|
|
| 119 |
model = SentenceTransformer("sentence_transformers_model_id")
|
| 120 |
# Run inference
|
| 121 |
sentences = [
|
| 122 |
-
'
|
| 123 |
-
'
|
| 124 |
-
'
|
| 125 |
]
|
| 126 |
embeddings = model.encode(sentences)
|
| 127 |
print(embeddings.shape)
|
|
@@ -166,10 +166,10 @@ You can finetune this model on your own dataset.
|
|
| 166 |
* Datasets: `sts-dev` and `sts-test`
|
| 167 |
* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
|
| 168 |
|
| 169 |
-
| Metric | sts-dev | sts-test
|
| 170 |
-
|
| 171 |
-
| pearson_cosine | 0.
|
| 172 |
-
| **spearman_cosine** | **0.
|
| 173 |
|
| 174 |
<!--
|
| 175 |
## Bias, Risks and Limitations
|
|
@@ -189,19 +189,19 @@ You can finetune this model on your own dataset.
|
|
| 189 |
|
| 190 |
#### Unnamed Dataset
|
| 191 |
|
| 192 |
-
* Size:
|
| 193 |
* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
|
| 194 |
* Approximate statistics based on the first 1000 samples:
|
| 195 |
| | sentence1 | sentence2 | score |
|
| 196 |
|:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------|
|
| 197 |
| type | string | string | float |
|
| 198 |
-
| details | <ul><li>min: 3 tokens</li><li>mean:
|
| 199 |
* Samples:
|
| 200 |
-
| sentence1
|
| 201 |
-
|
| 202 |
-
| <code
|
| 203 |
-
| <code>
|
| 204 |
-
| <code>
|
| 205 |
* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
|
| 206 |
```json
|
| 207 |
{
|
|
@@ -213,19 +213,19 @@ You can finetune this model on your own dataset.
|
|
| 213 |
|
| 214 |
#### Unnamed Dataset
|
| 215 |
|
| 216 |
-
* Size: 113,
|
| 217 |
* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
|
| 218 |
* Approximate statistics based on the first 1000 samples:
|
| 219 |
| | sentence1 | sentence2 | score |
|
| 220 |
|:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------|
|
| 221 |
| type | string | string | float |
|
| 222 |
-
| details | <ul><li>min:
|
| 223 |
* Samples:
|
| 224 |
-
| sentence1
|
| 225 |
-
|
| 226 |
-
| <code>
|
| 227 |
-
| <code>
|
| 228 |
-
| <code>
|
| 229 |
* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
|
| 230 |
```json
|
| 231 |
{
|
|
@@ -369,124 +369,124 @@ You can finetune this model on your own dataset.
|
|
| 369 |
|
| 370 |
| Epoch | Step | Training Loss | Validation Loss | sts-dev_spearman_cosine | sts-test_spearman_cosine |
|
| 371 |
|:------:|:-----:|:-------------:|:---------------:|:-----------------------:|:------------------------:|
|
| 372 |
-
| 0.0352 | 500 | 0.
|
| 373 |
-
| 0.
|
| 374 |
-
| 0.
|
| 375 |
-
| 0.1407 | 2000 | 0.
|
| 376 |
-
| 0.
|
| 377 |
-
| 0.
|
| 378 |
-
| 0.
|
| 379 |
-
| 0.
|
| 380 |
-
| 0.
|
| 381 |
-
| 0.
|
| 382 |
-
| 0.
|
| 383 |
-
| 0.
|
| 384 |
-
| 0.
|
| 385 |
-
| 0.
|
| 386 |
-
| 0.
|
| 387 |
-
| 0.
|
| 388 |
-
| 0.
|
| 389 |
-
| 0.
|
| 390 |
-
| 0.
|
| 391 |
-
| 0.
|
| 392 |
-
| 0.
|
| 393 |
-
| 0.
|
| 394 |
-
| 0.
|
| 395 |
-
| 0.
|
| 396 |
-
| 0.
|
| 397 |
-
| 0.
|
| 398 |
-
| 0.
|
| 399 |
-
| 0.
|
| 400 |
-
| 1.0 |
|
| 401 |
-
| 1.
|
| 402 |
-
| 1.
|
| 403 |
-
| 1.
|
| 404 |
-
| 1.
|
| 405 |
-
| 1.
|
| 406 |
-
| 1.
|
| 407 |
-
| 1.
|
| 408 |
-
| 1.
|
| 409 |
-
| 1.
|
| 410 |
-
| 1.
|
| 411 |
-
| 1.
|
| 412 |
-
| 1.
|
| 413 |
-
| 1.
|
| 414 |
-
| 1.
|
| 415 |
-
| 1.
|
| 416 |
-
| 1.
|
| 417 |
-
| 1.
|
| 418 |
-
| 1.
|
| 419 |
-
| 1.
|
| 420 |
-
| 1.
|
| 421 |
-
| 1.
|
| 422 |
-
| 1.
|
| 423 |
-
| 1.
|
| 424 |
-
| 1.
|
| 425 |
-
| 1.
|
| 426 |
-
| 1.
|
| 427 |
-
| 1.
|
| 428 |
-
| 1.
|
| 429 |
-
| 2.0 |
|
| 430 |
-
| 2.
|
| 431 |
-
| 2.
|
| 432 |
-
| 2.
|
| 433 |
-
| 2.
|
| 434 |
-
| 2.
|
| 435 |
-
| 2.
|
| 436 |
-
| 2.
|
| 437 |
-
| 2.
|
| 438 |
-
| 2.
|
| 439 |
-
| 2.
|
| 440 |
-
| 2.
|
| 441 |
-
| 2.
|
| 442 |
-
| 2.
|
| 443 |
-
| 2.
|
| 444 |
-
| 2.
|
| 445 |
-
| 2.
|
| 446 |
-
| 2.
|
| 447 |
-
| 2.
|
| 448 |
-
| 2.
|
| 449 |
-
| 2.
|
| 450 |
-
| 2.
|
| 451 |
-
| 2.
|
| 452 |
-
| 2.
|
| 453 |
-
| 2.
|
| 454 |
-
| 2.
|
| 455 |
-
| 2.
|
| 456 |
-
| 2.
|
| 457 |
-
| 2.
|
| 458 |
-
| 2.
|
| 459 |
-
| 3.0 |
|
| 460 |
-
| 3.
|
| 461 |
-
| 3.
|
| 462 |
-
| 3.
|
| 463 |
-
| 3.
|
| 464 |
-
| 3.
|
| 465 |
-
| 3.
|
| 466 |
-
| 3.
|
| 467 |
-
| 3.
|
| 468 |
-
| 3.
|
| 469 |
-
| 3.
|
| 470 |
-
| 3.
|
| 471 |
-
| 3.
|
| 472 |
-
| 3.
|
| 473 |
-
| 3.
|
| 474 |
-
| 3.
|
| 475 |
-
| 3.
|
| 476 |
-
| 3.
|
| 477 |
-
| 3.
|
| 478 |
-
| 3.
|
| 479 |
-
| 3.
|
| 480 |
-
| 3.
|
| 481 |
-
| 3.
|
| 482 |
-
| 3.
|
| 483 |
-
| 3.
|
| 484 |
-
| 3.
|
| 485 |
-
| 3.
|
| 486 |
-
| 3.
|
| 487 |
-
| 3.
|
| 488 |
-
| 4.0 |
|
| 489 |
-
| -1 | -1 | - | - | - | 0.
|
| 490 |
|
| 491 |
</details>
|
| 492 |
|
|
|
|
| 4 |
- sentence-similarity
|
| 5 |
- feature-extraction
|
| 6 |
- generated_from_trainer
|
| 7 |
+
- dataset_size:910013
|
| 8 |
- loss:CosineSimilarityLoss
|
| 9 |
base_model: intfloat/multilingual-e5-small
|
| 10 |
widget:
|
| 11 |
+
- source_sentence: business healing
|
| 12 |
sentences:
|
| 13 |
+
- modify ict system capacity
|
| 14 |
+
- objetividade, inovadora,estudiosa,pesquisadora e organizada
|
| 15 |
+
- business consulting
|
| 16 |
+
- source_sentence: architecture acoustics
|
| 17 |
sentences:
|
| 18 |
+
- disicpline leader
|
| 19 |
+
- 生产工艺开发及优化
|
| 20 |
+
- data analysis
|
| 21 |
+
- source_sentence: arbitru natatie
|
| 22 |
sentences:
|
| 23 |
+
- criação cinematográfica
|
| 24 |
+
- quarterly distribution
|
| 25 |
+
- улучшение путешествий клиентов с помощью дополненной реальности
|
| 26 |
+
- source_sentence: configuración de software antivirus
|
| 27 |
sentences:
|
| 28 |
+
- protocol & coordination
|
| 29 |
+
- laurea magistrale biologia
|
| 30 |
+
- deploy anti-virus software
|
| 31 |
+
- source_sentence: child maltreatment counselling
|
| 32 |
sentences:
|
| 33 |
+
- book covers, flyers, posters, banners
|
| 34 |
+
- tool and die making
|
| 35 |
+
- cmc
|
| 36 |
pipeline_tag: sentence-similarity
|
| 37 |
library_name: sentence-transformers
|
| 38 |
metrics:
|
|
|
|
| 49 |
type: sts-dev
|
| 50 |
metrics:
|
| 51 |
- type: pearson_cosine
|
| 52 |
+
value: 0.9579653395486292
|
| 53 |
name: Pearson Cosine
|
| 54 |
- type: spearman_cosine
|
| 55 |
+
value: 0.8788941637037295
|
| 56 |
name: Spearman Cosine
|
| 57 |
- task:
|
| 58 |
type: semantic-similarity
|
|
|
|
| 62 |
type: sts-test
|
| 63 |
metrics:
|
| 64 |
- type: pearson_cosine
|
| 65 |
+
value: 0.9579215714676803
|
| 66 |
name: Pearson Cosine
|
| 67 |
- type: spearman_cosine
|
| 68 |
+
value: 0.8795799743051839
|
| 69 |
name: Spearman Cosine
|
| 70 |
---
|
| 71 |
|
|
|
|
| 119 |
model = SentenceTransformer("sentence_transformers_model_id")
|
| 120 |
# Run inference
|
| 121 |
sentences = [
|
| 122 |
+
'child maltreatment counselling',
|
| 123 |
+
'cmc',
|
| 124 |
+
'book covers, flyers, posters, banners',
|
| 125 |
]
|
| 126 |
embeddings = model.encode(sentences)
|
| 127 |
print(embeddings.shape)
|
|
|
|
| 166 |
* Datasets: `sts-dev` and `sts-test`
|
| 167 |
* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
|
| 168 |
|
| 169 |
+
| Metric | sts-dev | sts-test |
|
| 170 |
+
|:--------------------|:-----------|:-----------|
|
| 171 |
+
| pearson_cosine | 0.958 | 0.9579 |
|
| 172 |
+
| **spearman_cosine** | **0.8789** | **0.8796** |
|
| 173 |
|
| 174 |
<!--
|
| 175 |
## Bias, Risks and Limitations
|
|
|
|
| 189 |
|
| 190 |
#### Unnamed Dataset
|
| 191 |
|
| 192 |
+
* Size: 910,013 training samples
|
| 193 |
* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
|
| 194 |
* Approximate statistics based on the first 1000 samples:
|
| 195 |
| | sentence1 | sentence2 | score |
|
| 196 |
|:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------|
|
| 197 |
| type | string | string | float |
|
| 198 |
+
| details | <ul><li>min: 3 tokens</li><li>mean: 8.91 tokens</li><li>max: 30 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 8.83 tokens</li><li>max: 30 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.52</li><li>max: 1.0</li></ul> |
|
| 199 |
* Samples:
|
| 200 |
+
| sentence1 | sentence2 | score |
|
| 201 |
+
|:----------------------------------------------------------------------------------------------|:--------------------------------------------------|:------------------|
|
| 202 |
+
| <code>edición de fotografias, fondos</code> | <code>material selection and cognition</code> | <code>0.0</code> |
|
| 203 |
+
| <code>professional alarm installer,service tech.,customer service relations,sales,cctv</code> | <code>quantity surveying & reading charts</code> | <code>0.1</code> |
|
| 204 |
+
| <code>diagnostico ecografico</code> | <code>waste identification system downtime</code> | <code>0.19</code> |
|
| 205 |
* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
|
| 206 |
```json
|
| 207 |
{
|
|
|
|
| 213 |
|
| 214 |
#### Unnamed Dataset
|
| 215 |
|
| 216 |
+
* Size: 113,751 evaluation samples
|
| 217 |
* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
|
| 218 |
* Approximate statistics based on the first 1000 samples:
|
| 219 |
| | sentence1 | sentence2 | score |
|
| 220 |
|:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------|
|
| 221 |
| type | string | string | float |
|
| 222 |
+
| details | <ul><li>min: 4 tokens</li><li>mean: 8.89 tokens</li><li>max: 30 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 8.96 tokens</li><li>max: 30 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.54</li><li>max: 1.0</li></ul> |
|
| 223 |
* Samples:
|
| 224 |
+
| sentence1 | sentence2 | score |
|
| 225 |
+
|:----------------------------------------------------------|:-------------------------|:------------------|
|
| 226 |
+
| <code>a2 dutch</code> | <code>a2 dutch</code> | <code>0.98</code> |
|
| 227 |
+
| <code>design of mine dumps</code> | <code>设计矿山废料堆</code> | <code>1.0</code> |
|
| 228 |
+
| <code>create soil and plant improvement programmes</code> | <code>创建土壤和植物改良计划</code> | <code>1.0</code> |
|
| 229 |
* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
|
| 230 |
```json
|
| 231 |
{
|
|
|
|
| 369 |
|
| 370 |
| Epoch | Step | Training Loss | Validation Loss | sts-dev_spearman_cosine | sts-test_spearman_cosine |
|
| 371 |
|:------:|:-----:|:-------------:|:---------------:|:-----------------------:|:------------------------:|
|
| 372 |
+
| 0.0352 | 500 | 0.1991 | - | - | - |
|
| 373 |
+
| 0.0703 | 1000 | 0.0513 | - | - | - |
|
| 374 |
+
| 0.1055 | 1500 | 0.0362 | - | - | - |
|
| 375 |
+
| 0.1407 | 2000 | 0.0331 | - | - | - |
|
| 376 |
+
| 0.1758 | 2500 | 0.0305 | - | - | - |
|
| 377 |
+
| 0.2110 | 3000 | 0.029 | - | - | - |
|
| 378 |
+
| 0.2461 | 3500 | 0.0273 | - | - | - |
|
| 379 |
+
| 0.2813 | 4000 | 0.0268 | - | - | - |
|
| 380 |
+
| 0.3165 | 4500 | 0.0255 | - | - | - |
|
| 381 |
+
| 0.3516 | 5000 | 0.0245 | - | - | - |
|
| 382 |
+
| 0.3868 | 5500 | 0.0238 | - | - | - |
|
| 383 |
+
| 0.4220 | 6000 | 0.0236 | - | - | - |
|
| 384 |
+
| 0.4571 | 6500 | 0.0233 | - | - | - |
|
| 385 |
+
| 0.4923 | 7000 | 0.0222 | - | - | - |
|
| 386 |
+
| 0.5275 | 7500 | 0.0225 | - | - | - |
|
| 387 |
+
| 0.5626 | 8000 | 0.0219 | - | - | - |
|
| 388 |
+
| 0.5978 | 8500 | 0.0212 | - | - | - |
|
| 389 |
+
| 0.6330 | 9000 | 0.0215 | - | - | - |
|
| 390 |
+
| 0.6681 | 9500 | 0.0207 | - | - | - |
|
| 391 |
+
| 0.7033 | 10000 | 0.0204 | - | - | - |
|
| 392 |
+
| 0.7384 | 10500 | 0.0203 | - | - | - |
|
| 393 |
+
| 0.7736 | 11000 | 0.0203 | - | - | - |
|
| 394 |
+
| 0.8088 | 11500 | 0.0202 | - | - | - |
|
| 395 |
+
| 0.8439 | 12000 | 0.0202 | - | - | - |
|
| 396 |
+
| 0.8791 | 12500 | 0.0196 | - | - | - |
|
| 397 |
+
| 0.9143 | 13000 | 0.0193 | - | - | - |
|
| 398 |
+
| 0.9494 | 13500 | 0.0193 | - | - | - |
|
| 399 |
+
| 0.9846 | 14000 | 0.0193 | - | - | - |
|
| 400 |
+
| 1.0 | 14219 | - | 0.0170 | 0.8694 | - |
|
| 401 |
+
| 1.0198 | 14500 | 0.0188 | - | - | - |
|
| 402 |
+
| 1.0549 | 15000 | 0.0178 | - | - | - |
|
| 403 |
+
| 1.0901 | 15500 | 0.0179 | - | - | - |
|
| 404 |
+
| 1.1253 | 16000 | 0.0178 | - | - | - |
|
| 405 |
+
| 1.1604 | 16500 | 0.0178 | - | - | - |
|
| 406 |
+
| 1.1956 | 17000 | 0.0172 | - | - | - |
|
| 407 |
+
| 1.2307 | 17500 | 0.0172 | - | - | - |
|
| 408 |
+
| 1.2659 | 18000 | 0.0175 | - | - | - |
|
| 409 |
+
| 1.3011 | 18500 | 0.0178 | - | - | - |
|
| 410 |
+
| 1.3362 | 19000 | 0.0174 | - | - | - |
|
| 411 |
+
| 1.3714 | 19500 | 0.0175 | - | - | - |
|
| 412 |
+
| 1.4066 | 20000 | 0.0171 | - | - | - |
|
| 413 |
+
| 1.4417 | 20500 | 0.0175 | - | - | - |
|
| 414 |
+
| 1.4769 | 21000 | 0.0173 | - | - | - |
|
| 415 |
+
| 1.5121 | 21500 | 0.0171 | - | - | - |
|
| 416 |
+
| 1.5472 | 22000 | 0.0174 | - | - | - |
|
| 417 |
+
| 1.5824 | 22500 | 0.0172 | - | - | - |
|
| 418 |
+
| 1.6176 | 23000 | 0.0168 | - | - | - |
|
| 419 |
+
| 1.6527 | 23500 | 0.0165 | - | - | - |
|
| 420 |
+
| 1.6879 | 24000 | 0.0169 | - | - | - |
|
| 421 |
+
| 1.7230 | 24500 | 0.0169 | - | - | - |
|
| 422 |
+
| 1.7582 | 25000 | 0.0171 | - | - | - |
|
| 423 |
+
| 1.7934 | 25500 | 0.0165 | - | - | - |
|
| 424 |
+
| 1.8285 | 26000 | 0.0165 | - | - | - |
|
| 425 |
+
| 1.8637 | 26500 | 0.0165 | - | - | - |
|
| 426 |
+
| 1.8989 | 27000 | 0.0165 | - | - | - |
|
| 427 |
+
| 1.9340 | 27500 | 0.0164 | - | - | - |
|
| 428 |
+
| 1.9692 | 28000 | 0.0164 | - | - | - |
|
| 429 |
+
| 2.0 | 28438 | - | 0.0153 | 0.8751 | - |
|
| 430 |
+
| 2.0044 | 28500 | 0.0162 | - | - | - |
|
| 431 |
+
| 2.0395 | 29000 | 0.0156 | - | - | - |
|
| 432 |
+
| 2.0747 | 29500 | 0.0154 | - | - | - |
|
| 433 |
+
| 2.1099 | 30000 | 0.0157 | - | - | - |
|
| 434 |
+
| 2.1450 | 30500 | 0.016 | - | - | - |
|
| 435 |
+
| 2.1802 | 31000 | 0.015 | - | - | - |
|
| 436 |
+
| 2.2153 | 31500 | 0.0155 | - | - | - |
|
| 437 |
+
| 2.2505 | 32000 | 0.0154 | - | - | - |
|
| 438 |
+
| 2.2857 | 32500 | 0.0152 | - | - | - |
|
| 439 |
+
| 2.3208 | 33000 | 0.0152 | - | - | - |
|
| 440 |
+
| 2.3560 | 33500 | 0.0152 | - | - | - |
|
| 441 |
+
| 2.3912 | 34000 | 0.0154 | - | - | - |
|
| 442 |
+
| 2.4263 | 34500 | 0.0153 | - | - | - |
|
| 443 |
+
| 2.4615 | 35000 | 0.0154 | - | - | - |
|
| 444 |
+
| 2.4967 | 35500 | 0.015 | - | - | - |
|
| 445 |
+
| 2.5318 | 36000 | 0.0153 | - | - | - |
|
| 446 |
+
| 2.5670 | 36500 | 0.0149 | - | - | - |
|
| 447 |
+
| 2.6022 | 37000 | 0.015 | - | - | - |
|
| 448 |
+
| 2.6373 | 37500 | 0.0152 | - | - | - |
|
| 449 |
+
| 2.6725 | 38000 | 0.0152 | - | - | - |
|
| 450 |
+
| 2.7076 | 38500 | 0.015 | - | - | - |
|
| 451 |
+
| 2.7428 | 39000 | 0.0151 | - | - | - |
|
| 452 |
+
| 2.7780 | 39500 | 0.0155 | - | - | - |
|
| 453 |
+
| 2.8131 | 40000 | 0.0148 | - | - | - |
|
| 454 |
+
| 2.8483 | 40500 | 0.0149 | - | - | - |
|
| 455 |
+
| 2.8835 | 41000 | 0.0147 | - | - | - |
|
| 456 |
+
| 2.9186 | 41500 | 0.015 | - | - | - |
|
| 457 |
+
| 2.9538 | 42000 | 0.0148 | - | - | - |
|
| 458 |
+
| 2.9890 | 42500 | 0.0146 | - | - | - |
|
| 459 |
+
| 3.0 | 42657 | - | 0.0146 | 0.8775 | - |
|
| 460 |
+
| 3.0241 | 43000 | 0.0142 | - | - | - |
|
| 461 |
+
| 3.0593 | 43500 | 0.0144 | - | - | - |
|
| 462 |
+
| 3.0945 | 44000 | 0.0146 | - | - | - |
|
| 463 |
+
| 3.1296 | 44500 | 0.0142 | - | - | - |
|
| 464 |
+
| 3.1648 | 45000 | 0.0144 | - | - | - |
|
| 465 |
+
| 3.1999 | 45500 | 0.0141 | - | - | - |
|
| 466 |
+
| 3.2351 | 46000 | 0.0142 | - | - | - |
|
| 467 |
+
| 3.2703 | 46500 | 0.0142 | - | - | - |
|
| 468 |
+
| 3.3054 | 47000 | 0.0142 | - | - | - |
|
| 469 |
+
| 3.3406 | 47500 | 0.0145 | - | - | - |
|
| 470 |
+
| 3.3758 | 48000 | 0.0142 | - | - | - |
|
| 471 |
+
| 3.4109 | 48500 | 0.0143 | - | - | - |
|
| 472 |
+
| 3.4461 | 49000 | 0.0145 | - | - | - |
|
| 473 |
+
| 3.4813 | 49500 | 0.0142 | - | - | - |
|
| 474 |
+
| 3.5164 | 50000 | 0.014 | - | - | - |
|
| 475 |
+
| 3.5516 | 50500 | 0.0141 | - | - | - |
|
| 476 |
+
| 3.5868 | 51000 | 0.0144 | - | - | - |
|
| 477 |
+
| 3.6219 | 51500 | 0.0143 | - | - | - |
|
| 478 |
+
| 3.6571 | 52000 | 0.0143 | - | - | - |
|
| 479 |
+
| 3.6922 | 52500 | 0.0142 | - | - | - |
|
| 480 |
+
| 3.7274 | 53000 | 0.014 | - | - | - |
|
| 481 |
+
| 3.7626 | 53500 | 0.0142 | - | - | - |
|
| 482 |
+
| 3.7977 | 54000 | 0.0141 | - | - | - |
|
| 483 |
+
| 3.8329 | 54500 | 0.0141 | - | - | - |
|
| 484 |
+
| 3.8681 | 55000 | 0.014 | - | - | - |
|
| 485 |
+
| 3.9032 | 55500 | 0.0143 | - | - | - |
|
| 486 |
+
| 3.9384 | 56000 | 0.0142 | - | - | - |
|
| 487 |
+
| 3.9736 | 56500 | 0.0141 | - | - | - |
|
| 488 |
+
| 4.0 | 56876 | - | 0.0146 | 0.8789 | - |
|
| 489 |
+
| -1 | -1 | - | - | - | 0.8796 |
|
| 490 |
|
| 491 |
</details>
|
| 492 |
|
model card.txt
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
Training dataset:
|
| 2 |
-
File:
|
| 3 |
Origin: gpt_dataset_acronyms, gpt_dataset_related, gpt_dataset_translations, gpt_dataset_generator, gpt_dataset_variant_generator
|
| 4 |
Characteristics: LOWER CASE
|
| 5 |
Length: 1.136.837 rows
|
|
@@ -16,7 +16,9 @@ Training Data:
|
|
| 16 |
|
| 17 |
Training Results:
|
| 18 |
Epoch Training Loss Validation Loss Sts-dev Pearson Cosine Sts-dev Spearman Cosine
|
| 19 |
-
1 0.
|
| 20 |
-
2 0.
|
| 21 |
-
3 0.014600 0.
|
| 22 |
-
4 0.
|
|
|
|
|
|
|
|
|
| 1 |
Training dataset:
|
| 2 |
+
File: skills_matching_training_v1a
|
| 3 |
Origin: gpt_dataset_acronyms, gpt_dataset_related, gpt_dataset_translations, gpt_dataset_generator, gpt_dataset_variant_generator
|
| 4 |
Characteristics: LOWER CASE
|
| 5 |
Length: 1.136.837 rows
|
|
|
|
| 16 |
|
| 17 |
Training Results:
|
| 18 |
Epoch Training Loss Validation Loss Sts-dev Pearson Cosine Sts-dev Spearman Cosine
|
| 19 |
+
1 0.019300 0.016977 0.950964 0.869359
|
| 20 |
+
2 0.016400 0.015263 0.956199 0.875054
|
| 21 |
+
3 0.014600 0.014600 0.957986 0.877506
|
| 22 |
+
4 0.014100 0.014555 0.957965 0.878894
|
| 23 |
+
|
| 24 |
+
sub-version a: Hyper Tunning for "full stack", "back end" and "front end"
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 470637416
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:24e15e17ede2ec440a7e13f9c5776b7196cd822cc120edf133e0a70afbd60a38
|
| 3 |
size 470637416
|