Add new SentenceTransformer model.
Browse files
README.md
CHANGED
|
@@ -46,31 +46,31 @@ tags:
|
|
| 46 |
- dataset_size:680
|
| 47 |
- loss:ContrastiveLoss
|
| 48 |
widget:
|
| 49 |
-
- source_sentence:
|
| 50 |
sentences:
|
| 51 |
-
-
|
| 52 |
-
-
|
| 53 |
-
-
|
| 54 |
-
- source_sentence:
|
| 55 |
sentences:
|
| 56 |
-
-
|
| 57 |
-
-
|
| 58 |
-
-
|
| 59 |
-
- source_sentence:
|
| 60 |
sentences:
|
| 61 |
-
-
|
| 62 |
-
-
|
| 63 |
-
-
|
| 64 |
-
- source_sentence:
|
| 65 |
sentences:
|
| 66 |
-
-
|
| 67 |
-
-
|
| 68 |
-
-
|
| 69 |
-
- source_sentence:
|
| 70 |
sentences:
|
| 71 |
-
-
|
| 72 |
-
-
|
| 73 |
-
-
|
| 74 |
model-index:
|
| 75 |
- name: SentenceTransformer based on colorfulscoop/sbert-base-ja
|
| 76 |
results:
|
|
@@ -82,109 +82,109 @@ model-index:
|
|
| 82 |
type: custom-arc-semantics-data-jp
|
| 83 |
metrics:
|
| 84 |
- type: cosine_accuracy
|
| 85 |
-
value: 0.
|
| 86 |
name: Cosine Accuracy
|
| 87 |
- type: cosine_accuracy_threshold
|
| 88 |
-
value: 0.
|
| 89 |
name: Cosine Accuracy Threshold
|
| 90 |
- type: cosine_f1
|
| 91 |
-
value: 0.
|
| 92 |
name: Cosine F1
|
| 93 |
- type: cosine_f1_threshold
|
| 94 |
-
value: 0.
|
| 95 |
name: Cosine F1 Threshold
|
| 96 |
- type: cosine_precision
|
| 97 |
-
value: 0.
|
| 98 |
name: Cosine Precision
|
| 99 |
- type: cosine_recall
|
| 100 |
-
value: 0.
|
| 101 |
name: Cosine Recall
|
| 102 |
- type: cosine_ap
|
| 103 |
-
value: 0.
|
| 104 |
name: Cosine Ap
|
| 105 |
- type: dot_accuracy
|
| 106 |
-
value: 0.
|
| 107 |
name: Dot Accuracy
|
| 108 |
- type: dot_accuracy_threshold
|
| 109 |
-
value:
|
| 110 |
name: Dot Accuracy Threshold
|
| 111 |
- type: dot_f1
|
| 112 |
-
value: 0.
|
| 113 |
name: Dot F1
|
| 114 |
- type: dot_f1_threshold
|
| 115 |
-
value:
|
| 116 |
name: Dot F1 Threshold
|
| 117 |
- type: dot_precision
|
| 118 |
-
value: 0.
|
| 119 |
name: Dot Precision
|
| 120 |
- type: dot_recall
|
| 121 |
-
value: 0.
|
| 122 |
name: Dot Recall
|
| 123 |
- type: dot_ap
|
| 124 |
-
value: 0.
|
| 125 |
name: Dot Ap
|
| 126 |
- type: manhattan_accuracy
|
| 127 |
-
value: 0.
|
| 128 |
name: Manhattan Accuracy
|
| 129 |
- type: manhattan_accuracy_threshold
|
| 130 |
-
value:
|
| 131 |
name: Manhattan Accuracy Threshold
|
| 132 |
- type: manhattan_f1
|
| 133 |
-
value: 0.
|
| 134 |
name: Manhattan F1
|
| 135 |
- type: manhattan_f1_threshold
|
| 136 |
-
value:
|
| 137 |
name: Manhattan F1 Threshold
|
| 138 |
- type: manhattan_precision
|
| 139 |
-
value: 0.
|
| 140 |
name: Manhattan Precision
|
| 141 |
- type: manhattan_recall
|
| 142 |
-
value: 0.
|
| 143 |
name: Manhattan Recall
|
| 144 |
- type: manhattan_ap
|
| 145 |
-
value: 0.
|
| 146 |
name: Manhattan Ap
|
| 147 |
- type: euclidean_accuracy
|
| 148 |
-
value: 0.
|
| 149 |
name: Euclidean Accuracy
|
| 150 |
- type: euclidean_accuracy_threshold
|
| 151 |
-
value:
|
| 152 |
name: Euclidean Accuracy Threshold
|
| 153 |
- type: euclidean_f1
|
| 154 |
-
value: 0.
|
| 155 |
name: Euclidean F1
|
| 156 |
- type: euclidean_f1_threshold
|
| 157 |
-
value:
|
| 158 |
name: Euclidean F1 Threshold
|
| 159 |
- type: euclidean_precision
|
| 160 |
-
value: 0.
|
| 161 |
name: Euclidean Precision
|
| 162 |
- type: euclidean_recall
|
| 163 |
-
value: 0.
|
| 164 |
name: Euclidean Recall
|
| 165 |
- type: euclidean_ap
|
| 166 |
-
value: 0.
|
| 167 |
name: Euclidean Ap
|
| 168 |
- type: max_accuracy
|
| 169 |
-
value: 0.
|
| 170 |
name: Max Accuracy
|
| 171 |
- type: max_accuracy_threshold
|
| 172 |
-
value:
|
| 173 |
name: Max Accuracy Threshold
|
| 174 |
- type: max_f1
|
| 175 |
-
value: 0.
|
| 176 |
name: Max F1
|
| 177 |
- type: max_f1_threshold
|
| 178 |
-
value:
|
| 179 |
name: Max F1 Threshold
|
| 180 |
- type: max_precision
|
| 181 |
-
value: 0.
|
| 182 |
name: Max Precision
|
| 183 |
- type: max_recall
|
| 184 |
-
value: 0.
|
| 185 |
name: Max Recall
|
| 186 |
- type: max_ap
|
| 187 |
-
value: 0.
|
| 188 |
name: Max Ap
|
| 189 |
---
|
| 190 |
|
|
@@ -238,9 +238,9 @@ from sentence_transformers import SentenceTransformer
|
|
| 238 |
model = SentenceTransformer("sentence_transformers_model_id")
|
| 239 |
# Run inference
|
| 240 |
sentences = [
|
| 241 |
-
'
|
| 242 |
-
'
|
| 243 |
-
'
|
| 244 |
]
|
| 245 |
embeddings = model.encode(sentences)
|
| 246 |
print(embeddings.shape)
|
|
@@ -286,41 +286,41 @@ You can finetune this model on your own dataset.
|
|
| 286 |
|
| 287 |
| Metric | Value |
|
| 288 |
|:-----------------------------|:-----------|
|
| 289 |
-
| cosine_accuracy | 0.
|
| 290 |
-
| cosine_accuracy_threshold | 0.
|
| 291 |
-
| cosine_f1 | 0.
|
| 292 |
-
| cosine_f1_threshold | 0.
|
| 293 |
-
| cosine_precision | 0.
|
| 294 |
-
| cosine_recall | 0.
|
| 295 |
-
| cosine_ap | 0.
|
| 296 |
-
| dot_accuracy | 0.
|
| 297 |
-
| dot_accuracy_threshold |
|
| 298 |
-
| dot_f1 | 0.
|
| 299 |
-
| dot_f1_threshold |
|
| 300 |
-
| dot_precision | 0.
|
| 301 |
-
| dot_recall | 0.
|
| 302 |
-
| dot_ap | 0.
|
| 303 |
-
| manhattan_accuracy | 0.
|
| 304 |
-
| manhattan_accuracy_threshold |
|
| 305 |
-
| manhattan_f1 | 0.
|
| 306 |
-
| manhattan_f1_threshold |
|
| 307 |
-
| manhattan_precision | 0.
|
| 308 |
-
| manhattan_recall | 0.
|
| 309 |
-
| manhattan_ap | 0.
|
| 310 |
-
| euclidean_accuracy | 0.
|
| 311 |
-
| euclidean_accuracy_threshold |
|
| 312 |
-
| euclidean_f1 | 0.
|
| 313 |
-
| euclidean_f1_threshold |
|
| 314 |
-
| euclidean_precision | 0.
|
| 315 |
-
| euclidean_recall | 0.
|
| 316 |
-
| euclidean_ap | 0.
|
| 317 |
-
| max_accuracy | 0.
|
| 318 |
-
| max_accuracy_threshold |
|
| 319 |
-
| max_f1 | 0.
|
| 320 |
-
| max_f1_threshold |
|
| 321 |
-
| max_precision | 0.
|
| 322 |
-
| max_recall | 0.
|
| 323 |
-
| **max_ap** | **0.
|
| 324 |
|
| 325 |
<!--
|
| 326 |
## Bias, Risks and Limitations
|
|
@@ -347,13 +347,13 @@ You can finetune this model on your own dataset.
|
|
| 347 |
| | text1 | text2 | label |
|
| 348 |
|:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:------------------------------------------------|
|
| 349 |
| type | string | string | int |
|
| 350 |
-
| details | <ul><li>min: 4 tokens</li><li>mean: 8.
|
| 351 |
* Samples:
|
| 352 |
-
| text1 | text2
|
| 353 |
-
|
| 354 |
-
| <code
|
| 355 |
-
| <code
|
| 356 |
-
| <code
|
| 357 |
* Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters:
|
| 358 |
```json
|
| 359 |
{
|
|
@@ -371,16 +371,16 @@ You can finetune this model on your own dataset.
|
|
| 371 |
* Size: 680 evaluation samples
|
| 372 |
* Columns: <code>text1</code>, <code>text2</code>, and <code>label</code>
|
| 373 |
* Approximate statistics based on the first 680 samples:
|
| 374 |
-
| | text1
|
| 375 |
-
|
| 376 |
-
| type | string
|
| 377 |
-
| details | <ul><li>min: 4 tokens</li><li>mean: 8.
|
| 378 |
* Samples:
|
| 379 |
-
| text1
|
| 380 |
-
|
| 381 |
-
| <code
|
| 382 |
-
| <code
|
| 383 |
-
| <code
|
| 384 |
* Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters:
|
| 385 |
```json
|
| 386 |
{
|
|
@@ -520,12 +520,12 @@ You can finetune this model on your own dataset.
|
|
| 520 |
### Training Logs
|
| 521 |
| Epoch | Step | Training Loss | loss | custom-arc-semantics-data-jp_max_ap |
|
| 522 |
|:------:|:----:|:-------------:|:------:|:-----------------------------------:|
|
| 523 |
-
| None | 0 | - | - | 0.
|
| 524 |
-
| 1.0147 | 69 | 0.
|
| 525 |
-
| 2.0147 | 138 | 0.
|
| 526 |
-
| 3.0147 | 207 | 0.
|
| 527 |
-
| 4.0147 | 276 | 0.
|
| 528 |
-
| 4.9412 | 340 | 0.
|
| 529 |
|
| 530 |
|
| 531 |
### Framework Versions
|
|
|
|
| 46 |
- dataset_size:680
|
| 47 |
- loss:ContrastiveLoss
|
| 48 |
widget:
|
| 49 |
+
- source_sentence: 木材の山の中にスカーフはある？
|
| 50 |
sentences:
|
| 51 |
+
- 巻き割をした？
|
| 52 |
+
- どっちが欲しい？
|
| 53 |
+
- おすすめは？
|
| 54 |
+
- source_sentence: ' 君は猫なの？'
|
| 55 |
sentences:
|
| 56 |
+
- どこ探すんだっけ？
|
| 57 |
+
- 足元よりも更に深くってなに？
|
| 58 |
+
- キミって猫？
|
| 59 |
+
- source_sentence: 欲しくない
|
| 60 |
sentences:
|
| 61 |
+
- 物体を変化できる人
|
| 62 |
+
- どっちも欲しくない
|
| 63 |
+
- スカーフがキャンプファイヤーで燃えてる
|
| 64 |
+
- source_sentence: 外を見てみよう
|
| 65 |
sentences:
|
| 66 |
+
- 誰かが魔法の呪文で花をぬいぐるみに変えた
|
| 67 |
+
- キミって猫？
|
| 68 |
+
- 長老
|
| 69 |
+
- source_sentence: 他には選べないの？
|
| 70 |
sentences:
|
| 71 |
+
- お鍋から匂いがしたから
|
| 72 |
+
- どっちがおすすめ？
|
| 73 |
+
- なにするんだっけ？
|
| 74 |
model-index:
|
| 75 |
- name: SentenceTransformer based on colorfulscoop/sbert-base-ja
|
| 76 |
results:
|
|
|
|
| 82 |
type: custom-arc-semantics-data-jp
|
| 83 |
metrics:
|
| 84 |
- type: cosine_accuracy
|
| 85 |
+
value: 0.8235294117647058
|
| 86 |
name: Cosine Accuracy
|
| 87 |
- type: cosine_accuracy_threshold
|
| 88 |
+
value: 0.6800776720046997
|
| 89 |
name: Cosine Accuracy Threshold
|
| 90 |
- type: cosine_f1
|
| 91 |
+
value: 0.8571428571428572
|
| 92 |
name: Cosine F1
|
| 93 |
- type: cosine_f1_threshold
|
| 94 |
+
value: 0.6610503196716309
|
| 95 |
name: Cosine F1 Threshold
|
| 96 |
- type: cosine_precision
|
| 97 |
+
value: 0.7912087912087912
|
| 98 |
name: Cosine Precision
|
| 99 |
- type: cosine_recall
|
| 100 |
+
value: 0.935064935064935
|
| 101 |
name: Cosine Recall
|
| 102 |
- type: cosine_ap
|
| 103 |
+
value: 0.8465974769503343
|
| 104 |
name: Cosine Ap
|
| 105 |
- type: dot_accuracy
|
| 106 |
+
value: 0.8161764705882353
|
| 107 |
name: Dot Accuracy
|
| 108 |
- type: dot_accuracy_threshold
|
| 109 |
+
value: 441.6131591796875
|
| 110 |
name: Dot Accuracy Threshold
|
| 111 |
- type: dot_f1
|
| 112 |
+
value: 0.8520710059171598
|
| 113 |
name: Dot F1
|
| 114 |
- type: dot_f1_threshold
|
| 115 |
+
value: 379.92266845703125
|
| 116 |
name: Dot F1 Threshold
|
| 117 |
- type: dot_precision
|
| 118 |
+
value: 0.782608695652174
|
| 119 |
name: Dot Precision
|
| 120 |
- type: dot_recall
|
| 121 |
+
value: 0.935064935064935
|
| 122 |
name: Dot Recall
|
| 123 |
- type: dot_ap
|
| 124 |
+
value: 0.8509292792079832
|
| 125 |
name: Dot Ap
|
| 126 |
- type: manhattan_accuracy
|
| 127 |
+
value: 0.8308823529411765
|
| 128 |
name: Manhattan Accuracy
|
| 129 |
- type: manhattan_accuracy_threshold
|
| 130 |
+
value: 420.1961975097656
|
| 131 |
name: Manhattan Accuracy Threshold
|
| 132 |
- type: manhattan_f1
|
| 133 |
+
value: 0.8622754491017963
|
| 134 |
name: Manhattan F1
|
| 135 |
- type: manhattan_f1_threshold
|
| 136 |
+
value: 430.6374206542969
|
| 137 |
name: Manhattan F1 Threshold
|
| 138 |
- type: manhattan_precision
|
| 139 |
+
value: 0.8
|
| 140 |
name: Manhattan Precision
|
| 141 |
- type: manhattan_recall
|
| 142 |
+
value: 0.935064935064935
|
| 143 |
name: Manhattan Recall
|
| 144 |
- type: manhattan_ap
|
| 145 |
+
value: 0.848438229073751
|
| 146 |
name: Manhattan Ap
|
| 147 |
- type: euclidean_accuracy
|
| 148 |
+
value: 0.8308823529411765
|
| 149 |
name: Euclidean Accuracy
|
| 150 |
- type: euclidean_accuracy_threshold
|
| 151 |
+
value: 18.93894386291504
|
| 152 |
name: Euclidean Accuracy Threshold
|
| 153 |
- type: euclidean_f1
|
| 154 |
+
value: 0.8588957055214723
|
| 155 |
name: Euclidean F1
|
| 156 |
- type: euclidean_f1_threshold
|
| 157 |
+
value: 18.93894386291504
|
| 158 |
name: Euclidean F1 Threshold
|
| 159 |
- type: euclidean_precision
|
| 160 |
+
value: 0.813953488372093
|
| 161 |
name: Euclidean Precision
|
| 162 |
- type: euclidean_recall
|
| 163 |
+
value: 0.9090909090909091
|
| 164 |
name: Euclidean Recall
|
| 165 |
- type: euclidean_ap
|
| 166 |
+
value: 0.8470258990606743
|
| 167 |
name: Euclidean Ap
|
| 168 |
- type: max_accuracy
|
| 169 |
+
value: 0.8308823529411765
|
| 170 |
name: Max Accuracy
|
| 171 |
- type: max_accuracy_threshold
|
| 172 |
+
value: 441.6131591796875
|
| 173 |
name: Max Accuracy Threshold
|
| 174 |
- type: max_f1
|
| 175 |
+
value: 0.8622754491017963
|
| 176 |
name: Max F1
|
| 177 |
- type: max_f1_threshold
|
| 178 |
+
value: 430.6374206542969
|
| 179 |
name: Max F1 Threshold
|
| 180 |
- type: max_precision
|
| 181 |
+
value: 0.813953488372093
|
| 182 |
name: Max Precision
|
| 183 |
- type: max_recall
|
| 184 |
+
value: 0.935064935064935
|
| 185 |
name: Max Recall
|
| 186 |
- type: max_ap
|
| 187 |
+
value: 0.8509292792079832
|
| 188 |
name: Max Ap
|
| 189 |
---
|
| 190 |
|
|
|
|
| 238 |
model = SentenceTransformer("sentence_transformers_model_id")
|
| 239 |
# Run inference
|
| 240 |
sentences = [
|
| 241 |
+
'他には選べないの？',
|
| 242 |
+
'どっちがおすすめ？',
|
| 243 |
+
'お鍋から匂いがしたから',
|
| 244 |
]
|
| 245 |
embeddings = model.encode(sentences)
|
| 246 |
print(embeddings.shape)
|
|
|
|
| 286 |
|
| 287 |
| Metric | Value |
|
| 288 |
|:-----------------------------|:-----------|
|
| 289 |
+
| cosine_accuracy | 0.8235 |
|
| 290 |
+
| cosine_accuracy_threshold | 0.6801 |
|
| 291 |
+
| cosine_f1 | 0.8571 |
|
| 292 |
+
| cosine_f1_threshold | 0.6611 |
|
| 293 |
+
| cosine_precision | 0.7912 |
|
| 294 |
+
| cosine_recall | 0.9351 |
|
| 295 |
+
| cosine_ap | 0.8466 |
|
| 296 |
+
| dot_accuracy | 0.8162 |
|
| 297 |
+
| dot_accuracy_threshold | 441.6132 |
|
| 298 |
+
| dot_f1 | 0.8521 |
|
| 299 |
+
| dot_f1_threshold | 379.9227 |
|
| 300 |
+
| dot_precision | 0.7826 |
|
| 301 |
+
| dot_recall | 0.9351 |
|
| 302 |
+
| dot_ap | 0.8509 |
|
| 303 |
+
| manhattan_accuracy | 0.8309 |
|
| 304 |
+
| manhattan_accuracy_threshold | 420.1962 |
|
| 305 |
+
| manhattan_f1 | 0.8623 |
|
| 306 |
+
| manhattan_f1_threshold | 430.6374 |
|
| 307 |
+
| manhattan_precision | 0.8 |
|
| 308 |
+
| manhattan_recall | 0.9351 |
|
| 309 |
+
| manhattan_ap | 0.8484 |
|
| 310 |
+
| euclidean_accuracy | 0.8309 |
|
| 311 |
+
| euclidean_accuracy_threshold | 18.9389 |
|
| 312 |
+
| euclidean_f1 | 0.8589 |
|
| 313 |
+
| euclidean_f1_threshold | 18.9389 |
|
| 314 |
+
| euclidean_precision | 0.814 |
|
| 315 |
+
| euclidean_recall | 0.9091 |
|
| 316 |
+
| euclidean_ap | 0.847 |
|
| 317 |
+
| max_accuracy | 0.8309 |
|
| 318 |
+
| max_accuracy_threshold | 441.6132 |
|
| 319 |
+
| max_f1 | 0.8623 |
|
| 320 |
+
| max_f1_threshold | 430.6374 |
|
| 321 |
+
| max_precision | 0.814 |
|
| 322 |
+
| max_recall | 0.9351 |
|
| 323 |
+
| **max_ap** | **0.8509** |
|
| 324 |
|
| 325 |
<!--
|
| 326 |
## Bias, Risks and Limitations
|
|
|
|
| 347 |
| | text1 | text2 | label |
|
| 348 |
|:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:------------------------------------------------|
|
| 349 |
| type | string | string | int |
|
| 350 |
+
| details | <ul><li>min: 4 tokens</li><li>mean: 8.31 tokens</li><li>max: 15 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 8.03 tokens</li><li>max: 14 tokens</li></ul> | <ul><li>0: ~40.81%</li><li>1: ~59.19%</li></ul> |
|
| 351 |
* Samples:
|
| 352 |
+
| text1 | text2 | label |
|
| 353 |
+
|:-------------------------|:-------------------------------|:---------------|
|
| 354 |
+
| <code>姿かたちを変える魔法</code> | <code>物の姿を変えられる魔法</code> | <code>1</code> |
|
| 355 |
+
| <code>青いオーブを見かけた？</code> | <code>青いオーブがどこにあるか知ってる？</code> | <code>1</code> |
|
| 356 |
+
| <code>猫のぬいぐるみを見たよ</code> | <code>猫のぬいぐるみを失くさなかった？</code> | <code>1</code> |
|
| 357 |
* Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters:
|
| 358 |
```json
|
| 359 |
{
|
|
|
|
| 371 |
* Size: 680 evaluation samples
|
| 372 |
* Columns: <code>text1</code>, <code>text2</code>, and <code>label</code>
|
| 373 |
* Approximate statistics based on the first 680 samples:
|
| 374 |
+
| | text1 | text2 | label |
|
| 375 |
+
|:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:------------------------------------------------|
|
| 376 |
+
| type | string | string | int |
|
| 377 |
+
| details | <ul><li>min: 4 tokens</li><li>mean: 8.24 tokens</li><li>max: 15 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 7.88 tokens</li><li>max: 14 tokens</li></ul> | <ul><li>0: ~43.38%</li><li>1: ~56.62%</li></ul> |
|
| 378 |
* Samples:
|
| 379 |
+
| text1 | text2 | label |
|
| 380 |
+
|:------------------------|:-------------------------|:---------------|
|
| 381 |
+
| <code>調子はどう？</code> | <code>最近どう？</code> | <code>1</code> |
|
| 382 |
+
| <code>なにも要らない</code> | <code>家の中</code> | <code>0</code> |
|
| 383 |
+
| <code>昨日は何を作ったの？</code> | <code>ビーフシチュー食べた？</code> | <code>0</code> |
|
| 384 |
* Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters:
|
| 385 |
```json
|
| 386 |
{
|
|
|
|
| 520 |
### Training Logs
|
| 521 |
| Epoch | Step | Training Loss | loss | custom-arc-semantics-data-jp_max_ap |
|
| 522 |
|:------:|:----:|:-------------:|:------:|:-----------------------------------:|
|
| 523 |
+
| None | 0 | - | - | 0.7957 |
|
| 524 |
+
| 1.0147 | 69 | 0.0205 | 0.0199 | 0.8294 |
|
| 525 |
+
| 2.0147 | 138 | 0.0148 | 0.0180 | 0.8410 |
|
| 526 |
+
| 3.0147 | 207 | 0.0118 | 0.0173 | 0.8455 |
|
| 527 |
+
| 4.0147 | 276 | 0.0104 | 0.0170 | 0.8489 |
|
| 528 |
+
| 4.9412 | 340 | 0.0098 | 0.0168 | 0.8509 |
|
| 529 |
|
| 530 |
|
| 531 |
### Framework Versions
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 442491744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df532cbf8c515730b079cb46df0f8397bd0412de5a0619608c49d03caf8e7902
|
| 3 |
size 442491744
|
runs/Sep12_19-08-06_default/events.out.tfevents.1726168095.default.1847.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32eddd6cc79cf3f51591dc64c1ddf3bba17c026db5c91ff0bfdf16cb3f7d029c
|
| 3 |
+
size 22423
|