Commit
•
b4ba8b3
1
Parent(s):
bbd7653
Add new SentenceTransformer model.
Browse files- README.md +106 -96
- model.safetensors +1 -1
README.md
CHANGED
|
@@ -6,7 +6,7 @@ tags:
|
|
| 6 |
- sentence-similarity
|
| 7 |
- feature-extraction
|
| 8 |
- generated_from_trainer
|
| 9 |
-
- dataset_size:
|
| 10 |
- loss:CoSENTLoss
|
| 11 |
base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
|
| 12 |
datasets: []
|
|
@@ -22,30 +22,30 @@ metrics:
|
|
| 22 |
- pearson_max
|
| 23 |
- spearman_max
|
| 24 |
widget:
|
| 25 |
-
- source_sentence:
|
| 26 |
sentences:
|
| 27 |
-
- order query
|
| 28 |
- faq query
|
| 29 |
-
-
|
| 30 |
-
-
|
|
|
|
| 31 |
sentences:
|
| 32 |
-
-
|
|
|
|
| 33 |
- feedback query
|
| 34 |
-
|
| 35 |
-
- source_sentence: 告诉我如何更改我的密码
|
| 36 |
sentences:
|
| 37 |
- support query
|
| 38 |
- product query
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
- faq query
|
| 40 |
-
- source_sentence:
|
| 41 |
sentences:
|
| 42 |
-
-
|
| 43 |
-
- service request
|
| 44 |
- account query
|
| 45 |
-
- source_sentence: Change the currency for my payment
|
| 46 |
-
sentences:
|
| 47 |
-
- product query
|
| 48 |
-
- payment query
|
| 49 |
- faq query
|
| 50 |
pipeline_tag: sentence-similarity
|
| 51 |
model-index:
|
|
@@ -59,34 +59,34 @@ model-index:
|
|
| 59 |
type: MiniLM-dev
|
| 60 |
metrics:
|
| 61 |
- type: pearson_cosine
|
| 62 |
-
value: 0.
|
| 63 |
name: Pearson Cosine
|
| 64 |
- type: spearman_cosine
|
| 65 |
-
value: 0.
|
| 66 |
name: Spearman Cosine
|
| 67 |
- type: pearson_manhattan
|
| 68 |
-
value: 0.
|
| 69 |
name: Pearson Manhattan
|
| 70 |
- type: spearman_manhattan
|
| 71 |
-
value: 0.
|
| 72 |
name: Spearman Manhattan
|
| 73 |
- type: pearson_euclidean
|
| 74 |
-
value: 0.
|
| 75 |
name: Pearson Euclidean
|
| 76 |
- type: spearman_euclidean
|
| 77 |
-
value: 0.
|
| 78 |
name: Spearman Euclidean
|
| 79 |
- type: pearson_dot
|
| 80 |
-
value: 0.
|
| 81 |
name: Pearson Dot
|
| 82 |
- type: spearman_dot
|
| 83 |
-
value: 0.
|
| 84 |
name: Spearman Dot
|
| 85 |
- type: pearson_max
|
| 86 |
-
value: 0.
|
| 87 |
name: Pearson Max
|
| 88 |
- type: spearman_max
|
| 89 |
-
value: 0.
|
| 90 |
name: Spearman Max
|
| 91 |
- task:
|
| 92 |
type: semantic-similarity
|
|
@@ -96,34 +96,34 @@ model-index:
|
|
| 96 |
type: MiniLM-test
|
| 97 |
metrics:
|
| 98 |
- type: pearson_cosine
|
| 99 |
-
value: 0.
|
| 100 |
name: Pearson Cosine
|
| 101 |
- type: spearman_cosine
|
| 102 |
-
value: 0.
|
| 103 |
name: Spearman Cosine
|
| 104 |
- type: pearson_manhattan
|
| 105 |
-
value: 0.
|
| 106 |
name: Pearson Manhattan
|
| 107 |
- type: spearman_manhattan
|
| 108 |
-
value: 0.
|
| 109 |
name: Spearman Manhattan
|
| 110 |
- type: pearson_euclidean
|
| 111 |
-
value: 0.
|
| 112 |
name: Pearson Euclidean
|
| 113 |
- type: spearman_euclidean
|
| 114 |
-
value: 0.
|
| 115 |
name: Spearman Euclidean
|
| 116 |
- type: pearson_dot
|
| 117 |
-
value: 0.
|
| 118 |
name: Pearson Dot
|
| 119 |
- type: spearman_dot
|
| 120 |
-
value: 0.
|
| 121 |
name: Spearman Dot
|
| 122 |
- type: pearson_max
|
| 123 |
-
value: 0.
|
| 124 |
name: Pearson Max
|
| 125 |
- type: spearman_max
|
| 126 |
-
value: 0.
|
| 127 |
name: Spearman Max
|
| 128 |
---
|
| 129 |
|
|
@@ -176,9 +176,9 @@ from sentence_transformers import SentenceTransformer
|
|
| 176 |
model = SentenceTransformer("philipp-zettl/MiniLM-similarity-small")
|
| 177 |
# Run inference
|
| 178 |
sentences = [
|
| 179 |
-
'
|
| 180 |
-
'payment query',
|
| 181 |
'faq query',
|
|
|
|
| 182 |
]
|
| 183 |
embeddings = model.encode(sentences)
|
| 184 |
print(embeddings.shape)
|
|
@@ -224,16 +224,16 @@ You can finetune this model on your own dataset.
|
|
| 224 |
|
| 225 |
| Metric | Value |
|
| 226 |
|:--------------------|:-----------|
|
| 227 |
-
| pearson_cosine | 0.
|
| 228 |
-
| **spearman_cosine** | **0.
|
| 229 |
-
| pearson_manhattan | 0.
|
| 230 |
-
| spearman_manhattan | 0.
|
| 231 |
-
| pearson_euclidean | 0.
|
| 232 |
-
| spearman_euclidean | 0.
|
| 233 |
-
| pearson_dot | 0.
|
| 234 |
-
| spearman_dot | 0.
|
| 235 |
-
| pearson_max | 0.
|
| 236 |
-
| spearman_max | 0.
|
| 237 |
|
| 238 |
#### Semantic Similarity
|
| 239 |
* Dataset: `MiniLM-test`
|
|
@@ -241,16 +241,16 @@ You can finetune this model on your own dataset.
|
|
| 241 |
|
| 242 |
| Metric | Value |
|
| 243 |
|:--------------------|:-----------|
|
| 244 |
-
| pearson_cosine | 0.
|
| 245 |
-
| **spearman_cosine** | **0.
|
| 246 |
-
| pearson_manhattan | 0.
|
| 247 |
-
| spearman_manhattan | 0.
|
| 248 |
-
| pearson_euclidean | 0.
|
| 249 |
-
| spearman_euclidean | 0.
|
| 250 |
-
| pearson_dot | 0.
|
| 251 |
-
| spearman_dot | 0.
|
| 252 |
-
| pearson_max | 0.
|
| 253 |
-
| spearman_max | 0.
|
| 254 |
|
| 255 |
<!--
|
| 256 |
## Bias, Risks and Limitations
|
|
@@ -271,19 +271,19 @@ You can finetune this model on your own dataset.
|
|
| 271 |
#### Unnamed Dataset
|
| 272 |
|
| 273 |
|
| 274 |
-
* Size:
|
| 275 |
* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
|
| 276 |
* Approximate statistics based on the first 1000 samples:
|
| 277 |
-
| | sentence1
|
| 278 |
-
|
| 279 |
-
| type | string
|
| 280 |
-
| details | <ul><li>min: 6 tokens</li><li>mean: 10.
|
| 281 |
* Samples:
|
| 282 |
-
| sentence1
|
| 283 |
-
|
| 284 |
-
| <code>
|
| 285 |
-
| <code
|
| 286 |
-
| <code
|
| 287 |
* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
|
| 288 |
```json
|
| 289 |
{
|
|
@@ -297,19 +297,19 @@ You can finetune this model on your own dataset.
|
|
| 297 |
#### Unnamed Dataset
|
| 298 |
|
| 299 |
|
| 300 |
-
* Size:
|
| 301 |
* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
|
| 302 |
* Approximate statistics based on the first 1000 samples:
|
| 303 |
| | sentence1 | sentence2 | score |
|
| 304 |
|:--------|:----------------------------------------------------------------------------------|:--------------------------------------------------------------------------------|:---------------------------------------------------------------|
|
| 305 |
| type | string | string | float |
|
| 306 |
-
| details | <ul><li>min: 6 tokens</li><li>mean: 10.
|
| 307 |
* Samples:
|
| 308 |
-
| sentence1
|
| 309 |
-
|
| 310 |
-
| <code
|
| 311 |
-
| <code>
|
| 312 |
-
| <code>
|
| 313 |
* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
|
| 314 |
```json
|
| 315 |
{
|
|
@@ -445,28 +445,38 @@ You can finetune this model on your own dataset.
|
|
| 445 |
### Training Logs
|
| 446 |
| Epoch | Step | Training Loss | loss | MiniLM-dev_spearman_cosine | MiniLM-test_spearman_cosine |
|
| 447 |
|:------:|:----:|:-------------:|:------:|:--------------------------:|:---------------------------:|
|
| 448 |
-
| 0.
|
| 449 |
-
| 0.
|
| 450 |
-
| 0.
|
| 451 |
-
| 0.
|
| 452 |
-
| 0.
|
| 453 |
-
| 0.
|
| 454 |
-
| 0.
|
| 455 |
-
| 0.
|
| 456 |
-
| 0.
|
| 457 |
-
| 0.
|
| 458 |
-
|
|
| 459 |
-
|
|
| 460 |
-
|
|
| 461 |
-
|
|
| 462 |
-
|
|
| 463 |
-
| 1.
|
| 464 |
-
| 1.
|
| 465 |
-
| 1.
|
| 466 |
-
| 1.
|
| 467 |
-
| 1.
|
| 468 |
-
| 1.
|
| 469 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 470 |
|
| 471 |
|
| 472 |
### Framework Versions
|
|
|
|
| 6 |
- sentence-similarity
|
| 7 |
- feature-extraction
|
| 8 |
- generated_from_trainer
|
| 9 |
+
- dataset_size:1267
|
| 10 |
- loss:CoSENTLoss
|
| 11 |
base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
|
| 12 |
datasets: []
|
|
|
|
| 22 |
- pearson_max
|
| 23 |
- spearman_max
|
| 24 |
widget:
|
| 25 |
+
- source_sentence: Give me suggestions for a high-quality DSLR camera
|
| 26 |
sentences:
|
|
|
|
| 27 |
- faq query
|
| 28 |
+
- subscription query
|
| 29 |
+
- faq query
|
| 30 |
+
- source_sentence: Aidez-moi à configurer une nouvelle adresse e-mail
|
| 31 |
sentences:
|
| 32 |
+
- order query
|
| 33 |
+
- faq query
|
| 34 |
- feedback query
|
| 35 |
+
- source_sentence: Как я могу изменить адрес доставки?
|
|
|
|
| 36 |
sentences:
|
| 37 |
- support query
|
| 38 |
- product query
|
| 39 |
+
- product query
|
| 40 |
+
- source_sentence: ساعدني في حذف الملفات الغير مرغوب فيها من هاتفي
|
| 41 |
+
sentences:
|
| 42 |
+
- technical support query
|
| 43 |
+
- product recommendation
|
| 44 |
- faq query
|
| 45 |
+
- source_sentence: Envoyez-moi la politique de garantie de ce produit
|
| 46 |
sentences:
|
| 47 |
+
- faq query
|
|
|
|
| 48 |
- account query
|
|
|
|
|
|
|
|
|
|
|
|
|
| 49 |
- faq query
|
| 50 |
pipeline_tag: sentence-similarity
|
| 51 |
model-index:
|
|
|
|
| 59 |
type: MiniLM-dev
|
| 60 |
metrics:
|
| 61 |
- type: pearson_cosine
|
| 62 |
+
value: 0.6538226572138826
|
| 63 |
name: Pearson Cosine
|
| 64 |
- type: spearman_cosine
|
| 65 |
+
value: 0.6336766646599241
|
| 66 |
name: Spearman Cosine
|
| 67 |
- type: pearson_manhattan
|
| 68 |
+
value: 0.5799895241429639
|
| 69 |
name: Pearson Manhattan
|
| 70 |
- type: spearman_manhattan
|
| 71 |
+
value: 0.5525776786782183
|
| 72 |
name: Spearman Manhattan
|
| 73 |
- type: pearson_euclidean
|
| 74 |
+
value: 0.5732001104236694
|
| 75 |
name: Pearson Euclidean
|
| 76 |
- type: spearman_euclidean
|
| 77 |
+
value: 0.5394971970682657
|
| 78 |
name: Spearman Euclidean
|
| 79 |
- type: pearson_dot
|
| 80 |
+
value: 0.6359725423136287
|
| 81 |
name: Pearson Dot
|
| 82 |
- type: spearman_dot
|
| 83 |
+
value: 0.6237936341101822
|
| 84 |
name: Spearman Dot
|
| 85 |
- type: pearson_max
|
| 86 |
+
value: 0.6538226572138826
|
| 87 |
name: Pearson Max
|
| 88 |
- type: spearman_max
|
| 89 |
+
value: 0.6336766646599241
|
| 90 |
name: Spearman Max
|
| 91 |
- task:
|
| 92 |
type: semantic-similarity
|
|
|
|
| 96 |
type: MiniLM-test
|
| 97 |
metrics:
|
| 98 |
- type: pearson_cosine
|
| 99 |
+
value: 0.6682368113711722
|
| 100 |
name: Pearson Cosine
|
| 101 |
- type: spearman_cosine
|
| 102 |
+
value: 0.6222011918428743
|
| 103 |
name: Spearman Cosine
|
| 104 |
- type: pearson_manhattan
|
| 105 |
+
value: 0.5714617063306076
|
| 106 |
name: Pearson Manhattan
|
| 107 |
- type: spearman_manhattan
|
| 108 |
+
value: 0.5481366191719228
|
| 109 |
name: Spearman Manhattan
|
| 110 |
- type: pearson_euclidean
|
| 111 |
+
value: 0.5726946277850402
|
| 112 |
name: Pearson Euclidean
|
| 113 |
- type: spearman_euclidean
|
| 114 |
+
value: 0.549312247309557
|
| 115 |
name: Spearman Euclidean
|
| 116 |
- type: pearson_dot
|
| 117 |
+
value: 0.6396412507506479
|
| 118 |
name: Pearson Dot
|
| 119 |
- type: spearman_dot
|
| 120 |
+
value: 0.6107388175009413
|
| 121 |
name: Spearman Dot
|
| 122 |
- type: pearson_max
|
| 123 |
+
value: 0.6682368113711722
|
| 124 |
name: Pearson Max
|
| 125 |
- type: spearman_max
|
| 126 |
+
value: 0.6222011918428743
|
| 127 |
name: Spearman Max
|
| 128 |
---
|
| 129 |
|
|
|
|
| 176 |
model = SentenceTransformer("philipp-zettl/MiniLM-similarity-small")
|
| 177 |
# Run inference
|
| 178 |
sentences = [
|
| 179 |
+
'Envoyez-moi la politique de garantie de ce produit',
|
|
|
|
| 180 |
'faq query',
|
| 181 |
+
'account query',
|
| 182 |
]
|
| 183 |
embeddings = model.encode(sentences)
|
| 184 |
print(embeddings.shape)
|
|
|
|
| 224 |
|
| 225 |
| Metric | Value |
|
| 226 |
|:--------------------|:-----------|
|
| 227 |
+
| pearson_cosine | 0.6538 |
|
| 228 |
+
| **spearman_cosine** | **0.6337** |
|
| 229 |
+
| pearson_manhattan | 0.58 |
|
| 230 |
+
| spearman_manhattan | 0.5526 |
|
| 231 |
+
| pearson_euclidean | 0.5732 |
|
| 232 |
+
| spearman_euclidean | 0.5395 |
|
| 233 |
+
| pearson_dot | 0.636 |
|
| 234 |
+
| spearman_dot | 0.6238 |
|
| 235 |
+
| pearson_max | 0.6538 |
|
| 236 |
+
| spearman_max | 0.6337 |
|
| 237 |
|
| 238 |
#### Semantic Similarity
|
| 239 |
* Dataset: `MiniLM-test`
|
|
|
|
| 241 |
|
| 242 |
| Metric | Value |
|
| 243 |
|:--------------------|:-----------|
|
| 244 |
+
| pearson_cosine | 0.6682 |
|
| 245 |
+
| **spearman_cosine** | **0.6222** |
|
| 246 |
+
| pearson_manhattan | 0.5715 |
|
| 247 |
+
| spearman_manhattan | 0.5481 |
|
| 248 |
+
| pearson_euclidean | 0.5727 |
|
| 249 |
+
| spearman_euclidean | 0.5493 |
|
| 250 |
+
| pearson_dot | 0.6396 |
|
| 251 |
+
| spearman_dot | 0.6107 |
|
| 252 |
+
| pearson_max | 0.6682 |
|
| 253 |
+
| spearman_max | 0.6222 |
|
| 254 |
|
| 255 |
<!--
|
| 256 |
## Bias, Risks and Limitations
|
|
|
|
| 271 |
#### Unnamed Dataset
|
| 272 |
|
| 273 |
|
| 274 |
+
* Size: 1,267 training samples
|
| 275 |
* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
|
| 276 |
* Approximate statistics based on the first 1000 samples:
|
| 277 |
+
| | sentence1 | sentence2 | score |
|
| 278 |
+
|:--------|:----------------------------------------------------------------------------------|:--------------------------------------------------------------------------------|:---------------------------------------------------------------|
|
| 279 |
+
| type | string | string | float |
|
| 280 |
+
| details | <ul><li>min: 6 tokens</li><li>mean: 10.77 tokens</li><li>max: 18 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 5.31 tokens</li><li>max: 6 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.67</li><li>max: 1.0</li></ul> |
|
| 281 |
* Samples:
|
| 282 |
+
| sentence1 | sentence2 | score |
|
| 283 |
+
|:--------------------------------------------------------------|:---------------------------|:-----------------|
|
| 284 |
+
| <code>Get information on the next art exhibition</code> | <code>product query</code> | <code>0.0</code> |
|
| 285 |
+
| <code>Show me how to update my profile</code> | <code>product query</code> | <code>0.0</code> |
|
| 286 |
+
| <code>Покажите мне доступные варианты полетов в Турцию</code> | <code>faq query</code> | <code>0.0</code> |
|
| 287 |
* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
|
| 288 |
```json
|
| 289 |
{
|
|
|
|
| 297 |
#### Unnamed Dataset
|
| 298 |
|
| 299 |
|
| 300 |
+
* Size: 159 evaluation samples
|
| 301 |
* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
|
| 302 |
* Approximate statistics based on the first 1000 samples:
|
| 303 |
| | sentence1 | sentence2 | score |
|
| 304 |
|:--------|:----------------------------------------------------------------------------------|:--------------------------------------------------------------------------------|:---------------------------------------------------------------|
|
| 305 |
| type | string | string | float |
|
| 306 |
+
| details | <ul><li>min: 6 tokens</li><li>mean: 10.65 tokens</li><li>max: 17 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 5.35 tokens</li><li>max: 6 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.67</li><li>max: 1.0</li></ul> |
|
| 307 |
* Samples:
|
| 308 |
+
| sentence1 | sentence2 | score |
|
| 309 |
+
|:---------------------------------------------------------------|:---------------------------|:-----------------|
|
| 310 |
+
| <code>Sende mir die Bestellbestätigung per E-Mail</code> | <code>order query</code> | <code>0.0</code> |
|
| 311 |
+
| <code>How do I add a new payment method?</code> | <code>faq query</code> | <code>1.0</code> |
|
| 312 |
+
| <code>No puedo conectar mi impresora, ¿puedes ayudarme?</code> | <code>support query</code> | <code>1.0</code> |
|
| 313 |
* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
|
| 314 |
```json
|
| 315 |
{
|
|
|
|
| 445 |
### Training Logs
|
| 446 |
| Epoch | Step | Training Loss | loss | MiniLM-dev_spearman_cosine | MiniLM-test_spearman_cosine |
|
| 447 |
|:------:|:----:|:-------------:|:------:|:--------------------------:|:---------------------------:|
|
| 448 |
+
| 0.0629 | 10 | 6.2479 | 2.5890 | 0.1448 | - |
|
| 449 |
+
| 0.1258 | 20 | 4.3549 | 2.2787 | 0.1965 | - |
|
| 450 |
+
| 0.1887 | 30 | 3.5969 | 2.0104 | 0.2599 | - |
|
| 451 |
+
| 0.2516 | 40 | 2.4979 | 1.7269 | 0.3357 | - |
|
| 452 |
+
| 0.3145 | 50 | 2.5551 | 1.5747 | 0.4439 | - |
|
| 453 |
+
| 0.3774 | 60 | 3.1446 | 1.4892 | 0.4750 | - |
|
| 454 |
+
| 0.4403 | 70 | 2.1353 | 1.5305 | 0.4662 | - |
|
| 455 |
+
| 0.5031 | 80 | 2.9341 | 1.3718 | 0.4848 | - |
|
| 456 |
+
| 0.5660 | 90 | 2.8709 | 1.2469 | 0.5316 | - |
|
| 457 |
+
| 0.6289 | 100 | 2.1367 | 1.2558 | 0.5436 | - |
|
| 458 |
+
| 0.6918 | 110 | 2.2735 | 1.2939 | 0.5392 | - |
|
| 459 |
+
| 0.7547 | 120 | 2.8646 | 1.1206 | 0.5616 | - |
|
| 460 |
+
| 0.8176 | 130 | 3.3204 | 1.0213 | 0.5662 | - |
|
| 461 |
+
| 0.8805 | 140 | 0.8989 | 0.9866 | 0.5738 | - |
|
| 462 |
+
| 0.9434 | 150 | 0.0057 | 0.9961 | 0.5674 | - |
|
| 463 |
+
| 1.0063 | 160 | 0.0019 | 1.0111 | 0.5674 | - |
|
| 464 |
+
| 1.0692 | 170 | 0.4617 | 1.0275 | 0.5747 | - |
|
| 465 |
+
| 1.1321 | 180 | 0.0083 | 1.0746 | 0.5732 | - |
|
| 466 |
+
| 1.1950 | 190 | 0.5048 | 1.0968 | 0.5753 | - |
|
| 467 |
+
| 1.2579 | 200 | 0.0002 | 1.0840 | 0.5738 | - |
|
| 468 |
+
| 1.3208 | 210 | 0.07 | 1.0364 | 0.5753 | - |
|
| 469 |
+
| 1.3836 | 220 | 0.0 | 0.9952 | 0.5750 | - |
|
| 470 |
+
| 1.4465 | 230 | 0.0 | 0.9922 | 0.5744 | - |
|
| 471 |
+
| 1.5094 | 240 | 0.0 | 0.9923 | 0.5726 | - |
|
| 472 |
+
| 1.0126 | 250 | 0.229 | 0.9930 | 0.5729 | - |
|
| 473 |
+
| 1.0755 | 260 | 2.2061 | 0.9435 | 0.5880 | - |
|
| 474 |
+
| 1.1384 | 270 | 2.7711 | 0.8892 | 0.6078 | - |
|
| 475 |
+
| 1.2013 | 280 | 0.7528 | 0.8886 | 0.6148 | - |
|
| 476 |
+
| 1.2642 | 290 | 0.386 | 0.8927 | 0.6162 | - |
|
| 477 |
+
| 1.3270 | 300 | 0.8902 | 0.8710 | 0.6267 | - |
|
| 478 |
+
| 1.3899 | 310 | 0.9534 | 0.8429 | 0.6337 | - |
|
| 479 |
+
| 1.4403 | 318 | - | - | - | 0.6222 |
|
| 480 |
|
| 481 |
|
| 482 |
### Framework Versions
|
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:a480f8a3b0abde34feef318b982835792b5781f388c0cbeb144e8d54ef77f2a3
|
| 3 |
size 470637416
|