Add new SentenceTransformer model.
Browse files- README.md +127 -127
- checkpoint-816/1_Pooling/config.json +10 -0
- checkpoint-816/README.md +589 -0
- checkpoint-816/added_tokens.json +3 -0
- checkpoint-816/config.json +33 -0
- checkpoint-816/config_sentence_transformers.json +10 -0
- checkpoint-816/model.safetensors +3 -0
- checkpoint-816/modules.json +14 -0
- checkpoint-816/optimizer.pt +3 -0
- checkpoint-816/rng_state.pth +3 -0
- checkpoint-816/scheduler.pt +3 -0
- checkpoint-816/sentence_bert_config.json +4 -0
- checkpoint-816/special_tokens_map.json +15 -0
- checkpoint-816/spm.model +3 -0
- checkpoint-816/tokenizer.json +0 -0
- checkpoint-816/tokenizer_config.json +65 -0
- checkpoint-816/trainer_state.json +633 -0
- checkpoint-816/training_args.bin +3 -0
- checkpoint-884/1_Pooling/config.json +10 -0
- checkpoint-884/README.md +590 -0
- checkpoint-884/added_tokens.json +3 -0
- checkpoint-884/config.json +33 -0
- checkpoint-884/config_sentence_transformers.json +10 -0
- checkpoint-884/model.safetensors +3 -0
- checkpoint-884/modules.json +14 -0
- checkpoint-884/optimizer.pt +3 -0
- checkpoint-884/rng_state.pth +3 -0
- checkpoint-884/scheduler.pt +3 -0
- checkpoint-884/sentence_bert_config.json +4 -0
- checkpoint-884/special_tokens_map.json +15 -0
- checkpoint-884/spm.model +3 -0
- checkpoint-884/tokenizer.json +0 -0
- checkpoint-884/tokenizer_config.json +65 -0
- checkpoint-884/trainer_state.json +683 -0
- checkpoint-884/training_args.bin +3 -0
- model.safetensors +1 -1
- runs/Sep03_22-46-20_default/events.out.tfevents.1725403583.default.1138.0 +3 -0
- runs/Sep04_17-30-25_default/events.out.tfevents.1725471030.default.394.0 +3 -0
- runs/Sep04_21-08-57_default/events.out.tfevents.1725484141.default.793.0 +3 -0
- runs/Sep11_17-50-24_default/events.out.tfevents.1726077038.default.828.0 +3 -0
- runs/Sep11_18-02-35_default/events.out.tfevents.1726077764.default.959.0 +3 -0
- runs/Sep11_18-05-21_default/events.out.tfevents.1726077928.default.1078.0 +3 -0
- runs/Sep11_23-48-08_default/events.out.tfevents.1726098512.default.5852.0 +3 -0
- runs/Sep12_00-21-44_default/events.out.tfevents.1726100510.default.6560.0 +3 -0
- runs/Sep12_00-34-34_default/events.out.tfevents.1726101282.default.6715.0 +3 -0
- tokenizer.model +3 -0
- tokenizer_config.json +14 -64
README.md
CHANGED
|
@@ -43,34 +43,34 @@ tags:
|
|
| 43 |
- sentence-similarity
|
| 44 |
- feature-extraction
|
| 45 |
- generated_from_trainer
|
| 46 |
-
- dataset_size:
|
| 47 |
- loss:CoSENTLoss
|
| 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 |
|
|
@@ -235,12 +235,12 @@ Then you can load this model and run inference.
|
|
| 235 |
from sentence_transformers import SentenceTransformer
|
| 236 |
|
| 237 |
# Download from the 🤗 Hub
|
| 238 |
-
model = SentenceTransformer("
|
| 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
|
|
@@ -341,19 +341,19 @@ You can finetune this model on your own dataset.
|
|
| 341 |
#### csv
|
| 342 |
|
| 343 |
* Dataset: csv
|
| 344 |
-
* Size:
|
| 345 |
* Columns: <code>text1</code>, <code>text2</code>, and <code>label</code>
|
| 346 |
-
* Approximate statistics based on the first
|
| 347 |
| | text1 | text2 | label |
|
| 348 |
|:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:------------------------------------------------|
|
| 349 |
| type | string | string | int |
|
| 350 |
-
| details | <ul><li>min: 4 tokens</li><li>mean:
|
| 351 |
* Samples:
|
| 352 |
-
| text1
|
| 353 |
-
|
| 354 |
-
| <code
|
| 355 |
-
| <code
|
| 356 |
-
| <code
|
| 357 |
* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
|
| 358 |
```json
|
| 359 |
{
|
|
@@ -367,19 +367,19 @@ You can finetune this model on your own dataset.
|
|
| 367 |
#### csv
|
| 368 |
|
| 369 |
* Dataset: csv
|
| 370 |
-
* Size:
|
| 371 |
* Columns: <code>text1</code>, <code>text2</code>, and <code>label</code>
|
| 372 |
-
* Approximate statistics based on the first
|
| 373 |
| | text1 | text2 | label |
|
| 374 |
|:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:------------------------------------------------|
|
| 375 |
| type | string | string | int |
|
| 376 |
-
| details | <ul><li>min: 4 tokens</li><li>mean: 8.
|
| 377 |
* Samples:
|
| 378 |
-
| text1
|
| 379 |
-
|
| 380 |
-
| <code
|
| 381 |
-
| <code
|
| 382 |
-
| <code
|
| 383 |
* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
|
| 384 |
```json
|
| 385 |
{
|
|
@@ -516,22 +516,22 @@ You can finetune this model on your own dataset.
|
|
| 516 |
</details>
|
| 517 |
|
| 518 |
### Training Logs
|
| 519 |
-
| Epoch
|
| 520 |
-
|
| 521 |
-
| None
|
| 522 |
-
| 1.
|
| 523 |
-
| 2.
|
| 524 |
-
| 3.
|
| 525 |
-
| 4.
|
| 526 |
-
| 5.
|
| 527 |
-
| 6.
|
| 528 |
-
| 7.
|
| 529 |
-
| 8.
|
| 530 |
-
| 9.
|
| 531 |
-
| 10.
|
| 532 |
-
| 11.
|
| 533 |
-
| 12.
|
| 534 |
-
|
|
| 535 |
|
| 536 |
|
| 537 |
### Framework Versions
|
|
|
|
| 43 |
- sentence-similarity
|
| 44 |
- feature-extraction
|
| 45 |
- generated_from_trainer
|
| 46 |
+
- dataset_size:680
|
| 47 |
- loss:CoSENTLoss
|
| 48 |
widget:
|
| 49 |
+
- source_sentence: 中を見てみよう
|
| 50 |
sentences:
|
| 51 |
+
- 外を調べよう
|
| 52 |
+
- リリアンはどんな魔法が使えるの？
|
| 53 |
+
- 花がぬいぐるみに変えられている
|
| 54 |
+
- source_sentence: キャンドル要らない
|
| 55 |
sentences:
|
| 56 |
+
- なんで猫が話せる？
|
| 57 |
+
- 自分でやれば？
|
| 58 |
+
- 中を見てみよう
|
| 59 |
+
- source_sentence: 信用できない
|
| 60 |
sentences:
|
| 61 |
+
- どっちでもいいよ
|
| 62 |
+
- 誰？
|
| 63 |
+
- 誰かが呪文で花をぬいぐるみに変えた
|
| 64 |
+
- source_sentence: 例えば？
|
| 65 |
sentences:
|
| 66 |
+
- 誰かがが魔法をかけた
|
| 67 |
+
- ジャック
|
| 68 |
+
- なんでしなきゃいけないの？
|
| 69 |
+
- source_sentence: 魔法を使える人
|
| 70 |
sentences:
|
| 71 |
+
- かっこいいね
|
| 72 |
+
- 物の姿を変えられる人
|
| 73 |
+
- 町って？
|
| 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: 0.9044117647058824
|
| 86 |
name: Cosine Accuracy
|
| 87 |
- type: cosine_accuracy_threshold
|
| 88 |
+
value: 0.5485918521881104
|
| 89 |
name: Cosine Accuracy Threshold
|
| 90 |
- type: cosine_f1
|
| 91 |
+
value: 0.912751677852349
|
| 92 |
name: Cosine F1
|
| 93 |
- type: cosine_f1_threshold
|
| 94 |
+
value: 0.47659817337989807
|
| 95 |
name: Cosine F1 Threshold
|
| 96 |
- type: cosine_precision
|
| 97 |
+
value: 0.918918918918919
|
| 98 |
name: Cosine Precision
|
| 99 |
- type: cosine_recall
|
| 100 |
+
value: 0.9066666666666666
|
| 101 |
name: Cosine Recall
|
| 102 |
- type: cosine_ap
|
| 103 |
+
value: 0.9088999169341241
|
| 104 |
name: Cosine Ap
|
| 105 |
- type: dot_accuracy
|
| 106 |
+
value: 0.9117647058823529
|
| 107 |
name: Dot Accuracy
|
| 108 |
- type: dot_accuracy_threshold
|
| 109 |
+
value: 293.22845458984375
|
| 110 |
name: Dot Accuracy Threshold
|
| 111 |
- type: dot_f1
|
| 112 |
+
value: 0.9166666666666666
|
| 113 |
name: Dot F1
|
| 114 |
- type: dot_f1_threshold
|
| 115 |
+
value: 293.22845458984375
|
| 116 |
name: Dot F1 Threshold
|
| 117 |
- type: dot_precision
|
| 118 |
+
value: 0.9565217391304348
|
| 119 |
name: Dot Precision
|
| 120 |
- type: dot_recall
|
| 121 |
+
value: 0.88
|
| 122 |
name: Dot Recall
|
| 123 |
- type: dot_ap
|
| 124 |
+
value: 0.9171086358892895
|
| 125 |
name: Dot Ap
|
| 126 |
- type: manhattan_accuracy
|
| 127 |
+
value: 0.9117647058823529
|
| 128 |
name: Manhattan Accuracy
|
| 129 |
- type: manhattan_accuracy_threshold
|
| 130 |
+
value: 524.0676879882812
|
| 131 |
name: Manhattan Accuracy Threshold
|
| 132 |
- type: manhattan_f1
|
| 133 |
+
value: 0.918918918918919
|
| 134 |
name: Manhattan F1
|
| 135 |
- type: manhattan_f1_threshold
|
| 136 |
+
value: 524.0676879882812
|
| 137 |
name: Manhattan F1 Threshold
|
| 138 |
- type: manhattan_precision
|
| 139 |
+
value: 0.9315068493150684
|
| 140 |
name: Manhattan Precision
|
| 141 |
- type: manhattan_recall
|
| 142 |
+
value: 0.9066666666666666
|
| 143 |
name: Manhattan Recall
|
| 144 |
- type: manhattan_ap
|
| 145 |
+
value: 0.9111567321590129
|
| 146 |
name: Manhattan Ap
|
| 147 |
- type: euclidean_accuracy
|
| 148 |
+
value: 0.9117647058823529
|
| 149 |
name: Euclidean Accuracy
|
| 150 |
- type: euclidean_accuracy_threshold
|
| 151 |
+
value: 23.82940673828125
|
| 152 |
name: Euclidean Accuracy Threshold
|
| 153 |
- type: euclidean_f1
|
| 154 |
+
value: 0.918918918918919
|
| 155 |
name: Euclidean F1
|
| 156 |
- type: euclidean_f1_threshold
|
| 157 |
+
value: 23.82940673828125
|
| 158 |
name: Euclidean F1 Threshold
|
| 159 |
- type: euclidean_precision
|
| 160 |
+
value: 0.9315068493150684
|
| 161 |
name: Euclidean Precision
|
| 162 |
- type: euclidean_recall
|
| 163 |
+
value: 0.9066666666666666
|
| 164 |
name: Euclidean Recall
|
| 165 |
- type: euclidean_ap
|
| 166 |
+
value: 0.9094221163568814
|
| 167 |
name: Euclidean Ap
|
| 168 |
- type: max_accuracy
|
| 169 |
+
value: 0.9117647058823529
|
| 170 |
name: Max Accuracy
|
| 171 |
- type: max_accuracy_threshold
|
| 172 |
+
value: 524.0676879882812
|
| 173 |
name: Max Accuracy Threshold
|
| 174 |
- type: max_f1
|
| 175 |
+
value: 0.918918918918919
|
| 176 |
name: Max F1
|
| 177 |
- type: max_f1_threshold
|
| 178 |
+
value: 524.0676879882812
|
| 179 |
name: Max F1 Threshold
|
| 180 |
- type: max_precision
|
| 181 |
+
value: 0.9565217391304348
|
| 182 |
name: Max Precision
|
| 183 |
- type: max_recall
|
| 184 |
+
value: 0.9066666666666666
|
| 185 |
name: Max Recall
|
| 186 |
- type: max_ap
|
| 187 |
+
value: 0.9171086358892895
|
| 188 |
name: Max Ap
|
| 189 |
---
|
| 190 |
|
|
|
|
| 235 |
from sentence_transformers import SentenceTransformer
|
| 236 |
|
| 237 |
# Download from the 🤗 Hub
|
| 238 |
+
model = SentenceTransformer("sentence_transformers_model_id")
|
| 239 |
# Run inference
|
| 240 |
sentences = [
|
| 241 |
+
'魔法を使える人',
|
| 242 |
+
'物の姿を変えられる人',
|
| 243 |
+
'かっこいいね',
|
| 244 |
]
|
| 245 |
embeddings = model.encode(sentences)
|
| 246 |
print(embeddings.shape)
|
|
|
|
| 286 |
|
| 287 |
| Metric | Value |
|
| 288 |
|:-----------------------------|:-----------|
|
| 289 |
+
| cosine_accuracy | 0.9044 |
|
| 290 |
+
| cosine_accuracy_threshold | 0.5486 |
|
| 291 |
+
| cosine_f1 | 0.9128 |
|
| 292 |
+
| cosine_f1_threshold | 0.4766 |
|
| 293 |
+
| cosine_precision | 0.9189 |
|
| 294 |
+
| cosine_recall | 0.9067 |
|
| 295 |
+
| cosine_ap | 0.9089 |
|
| 296 |
+
| dot_accuracy | 0.9118 |
|
| 297 |
+
| dot_accuracy_threshold | 293.2285 |
|
| 298 |
+
| dot_f1 | 0.9167 |
|
| 299 |
+
| dot_f1_threshold | 293.2285 |
|
| 300 |
+
| dot_precision | 0.9565 |
|
| 301 |
+
| dot_recall | 0.88 |
|
| 302 |
+
| dot_ap | 0.9171 |
|
| 303 |
+
| manhattan_accuracy | 0.9118 |
|
| 304 |
+
| manhattan_accuracy_threshold | 524.0677 |
|
| 305 |
+
| manhattan_f1 | 0.9189 |
|
| 306 |
+
| manhattan_f1_threshold | 524.0677 |
|
| 307 |
+
| manhattan_precision | 0.9315 |
|
| 308 |
+
| manhattan_recall | 0.9067 |
|
| 309 |
+
| manhattan_ap | 0.9112 |
|
| 310 |
+
| euclidean_accuracy | 0.9118 |
|
| 311 |
+
| euclidean_accuracy_threshold | 23.8294 |
|
| 312 |
+
| euclidean_f1 | 0.9189 |
|
| 313 |
+
| euclidean_f1_threshold | 23.8294 |
|
| 314 |
+
| euclidean_precision | 0.9315 |
|
| 315 |
+
| euclidean_recall | 0.9067 |
|
| 316 |
+
| euclidean_ap | 0.9094 |
|
| 317 |
+
| max_accuracy | 0.9118 |
|
| 318 |
+
| max_accuracy_threshold | 524.0677 |
|
| 319 |
+
| max_f1 | 0.9189 |
|
| 320 |
+
| max_f1_threshold | 524.0677 |
|
| 321 |
+
| max_precision | 0.9565 |
|
| 322 |
+
| max_recall | 0.9067 |
|
| 323 |
+
| **max_ap** | **0.9171** |
|
| 324 |
|
| 325 |
<!--
|
| 326 |
## Bias, Risks and Limitations
|
|
|
|
| 341 |
#### csv
|
| 342 |
|
| 343 |
* Dataset: csv
|
| 344 |
+
* Size: 680 training samples
|
| 345 |
* Columns: <code>text1</code>, <code>text2</code>, and <code>label</code>
|
| 346 |
+
* Approximate statistics based on the first 680 samples:
|
| 347 |
| | text1 | text2 | label |
|
| 348 |
|:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:------------------------------------------------|
|
| 349 |
| type | string | string | int |
|
| 350 |
+
| details | <ul><li>min: 4 tokens</li><li>mean: 8.29 tokens</li><li>max: 15 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 7.97 tokens</li><li>max: 14 tokens</li></ul> | <ul><li>0: ~40.44%</li><li>1: ~59.56%</li></ul> |
|
| 351 |
* Samples:
|
| 352 |
+
| text1 | text2 | label |
|
| 353 |
+
|:----------------------------|:----------------------------|:---------------|
|
| 354 |
+
| <code>いらない</code> | <code>うんよろしく</code> | <code>0</code> |
|
| 355 |
+
| <code>足元よりも更に深くってどこ？</code> | <code>足元よりも更に深くってなに？</code> | <code>1</code> |
|
| 356 |
+
| <code>他にはないの？</code> | <code>どう思う？</code> | <code>0</code> |
|
| 357 |
* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
|
| 358 |
```json
|
| 359 |
{
|
|
|
|
| 367 |
#### csv
|
| 368 |
|
| 369 |
* Dataset: csv
|
| 370 |
+
* Size: 680 evaluation samples
|
| 371 |
* Columns: <code>text1</code>, <code>text2</code>, and <code>label</code>
|
| 372 |
+
* Approximate statistics based on the first 680 samples:
|
| 373 |
| | text1 | text2 | label |
|
| 374 |
|:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:------------------------------------------------|
|
| 375 |
| type | string | string | int |
|
| 376 |
+
| details | <ul><li>min: 4 tokens</li><li>mean: 8.32 tokens</li><li>max: 15 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 8.16 tokens</li><li>max: 14 tokens</li></ul> | <ul><li>0: ~44.85%</li><li>1: ~55.15%</li></ul> |
|
| 377 |
* Samples:
|
| 378 |
+
| text1 | text2 | label |
|
| 379 |
+
|:-------------------------|:-------------------------|:---------------|
|
| 380 |
+
| <code>井戸から水をくんでいた</code> | <code>井戸を使っていた</code> | <code>1</code> |
|
| 381 |
+
| <code>夕飯は何だったの？</code> | <code>チキンヌードル食べた？</code> | <code>0</code> |
|
| 382 |
+
| <code>水を井戸からくんでいた</code> | <code>夜ごはんの前</code> | <code>0</code> |
|
| 383 |
* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
|
| 384 |
```json
|
| 385 |
{
|
|
|
|
| 516 |
</details>
|
| 517 |
|
| 518 |
### Training Logs
|
| 519 |
+
| Epoch | Step | Training Loss | loss | custom-arc-semantics-data-jp_max_ap |
|
| 520 |
+
|:-----:|:----:|:-------------:|:------:|:-----------------------------------:|
|
| 521 |
+
| None | 0 | - | - | 0.8596 |
|
| 522 |
+
| 1.0 | 68 | 2.6802 | 1.7807 | 0.8872 |
|
| 523 |
+
| 2.0 | 136 | 1.4014 | 1.7683 | 0.8945 |
|
| 524 |
+
| 3.0 | 204 | 0.7937 | 1.9877 | 0.9039 |
|
| 525 |
+
| 4.0 | 272 | 0.5443 | 1.9106 | 0.9075 |
|
| 526 |
+
| 5.0 | 340 | 0.4225 | 1.9418 | 0.9109 |
|
| 527 |
+
| 6.0 | 408 | 0.3347 | 2.0123 | 0.9107 |
|
| 528 |
+
| 7.0 | 476 | 0.3425 | 2.0387 | 0.9094 |
|
| 529 |
+
| 8.0 | 544 | 0.2427 | 1.9878 | 0.9103 |
|
| 530 |
+
| 9.0 | 612 | 0.2412 | 2.0424 | 0.9178 |
|
| 531 |
+
| 10.0 | 680 | 0.1623 | 2.0273 | 0.9188 |
|
| 532 |
+
| 11.0 | 748 | 0.1909 | 2.0955 | 0.9220 |
|
| 533 |
+
| 12.0 | 816 | 0.1507 | 2.2124 | 0.9157 |
|
| 534 |
+
| 13.0 | 884 | 0.1406 | 2.2126 | 0.9171 |
|
| 535 |
|
| 536 |
|
| 537 |
### Framework Versions
|
checkpoint-816/1_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 |
+
}
|
checkpoint-816/README.md
ADDED
|
@@ -0,0 +1,589 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: colorfulscoop/sbert-base-ja
|
| 3 |
+
library_name: sentence-transformers
|
| 4 |
+
metrics:
|
| 5 |
+
- cosine_accuracy
|
| 6 |
+
- cosine_accuracy_threshold
|
| 7 |
+
- cosine_f1
|
| 8 |
+
- cosine_f1_threshold
|
| 9 |
+
- cosine_precision
|
| 10 |
+
- cosine_recall
|
| 11 |
+
- cosine_ap
|
| 12 |
+
- dot_accuracy
|
| 13 |
+
- dot_accuracy_threshold
|
| 14 |
+
- dot_f1
|
| 15 |
+
- dot_f1_threshold
|
| 16 |
+
- dot_precision
|
| 17 |
+
- dot_recall
|
| 18 |
+
- dot_ap
|
| 19 |
+
- manhattan_accuracy
|
| 20 |
+
- manhattan_accuracy_threshold
|
| 21 |
+
- manhattan_f1
|
| 22 |
+
- manhattan_f1_threshold
|
| 23 |
+
- manhattan_precision
|
| 24 |
+
- manhattan_recall
|
| 25 |
+
- manhattan_ap
|
| 26 |
+
- euclidean_accuracy
|
| 27 |
+
- euclidean_accuracy_threshold
|
| 28 |
+
- euclidean_f1
|
| 29 |
+
- euclidean_f1_threshold
|
| 30 |
+
- euclidean_precision
|
| 31 |
+
- euclidean_recall
|
| 32 |
+
- euclidean_ap
|
| 33 |
+
- max_accuracy
|
| 34 |
+
- max_accuracy_threshold
|
| 35 |
+
- max_f1
|
| 36 |
+
- max_f1_threshold
|
| 37 |
+
- max_precision
|
| 38 |
+
- max_recall
|
| 39 |
+
- max_ap
|
| 40 |
+
pipeline_tag: sentence-similarity
|
| 41 |
+
tags:
|
| 42 |
+
- sentence-transformers
|
| 43 |
+
- sentence-similarity
|
| 44 |
+
- feature-extraction
|
| 45 |
+
- generated_from_trainer
|
| 46 |
+
- dataset_size:680
|
| 47 |
+
- loss:CoSENTLoss
|
| 48 |
+
widget:
|
| 49 |
+
- source_sentence: 中を見てみよう
|
| 50 |
+
sentences:
|
| 51 |
+
- 外を調べよう
|
| 52 |
+
- リリアンはどんな魔法が使えるの？
|
| 53 |
+
- 花がぬいぐるみに変えられている
|
| 54 |
+
- source_sentence: キャンドル要らない
|
| 55 |
+
sentences:
|
| 56 |
+
- なんで猫が話せる？
|
| 57 |
+
- 自分でやれば？
|
| 58 |
+
- 中を見てみよう
|
| 59 |
+
- source_sentence: 信用できない
|
| 60 |
+
sentences:
|
| 61 |
+
- どっちでもいいよ
|
| 62 |
+
- 誰？
|
| 63 |
+
- 誰かが呪文で花をぬいぐるみに変えた
|
| 64 |
+
- source_sentence: 例えば？
|
| 65 |
+
sentences:
|
| 66 |
+
- 誰かがが魔法をかけた
|
| 67 |
+
- ジャック
|
| 68 |
+
- なんでしなきゃいけないの？
|
| 69 |
+
- source_sentence: 魔法を使える人
|
| 70 |
+
sentences:
|
| 71 |
+
- かっこいいね
|
| 72 |
+
- 物の姿を変えられる人
|
| 73 |
+
- 町って？
|
| 74 |
+
model-index:
|
| 75 |
+
- name: SentenceTransformer based on colorfulscoop/sbert-base-ja
|
| 76 |
+
results:
|
| 77 |
+
- task:
|
| 78 |
+
type: binary-classification
|
| 79 |
+
name: Binary Classification
|
| 80 |
+
dataset:
|
| 81 |
+
name: custom arc semantics data jp
|
| 82 |
+
type: custom-arc-semantics-data-jp
|
| 83 |
+
metrics:
|
| 84 |
+
- type: cosine_accuracy
|
| 85 |
+
value: 0.9044117647058824
|
| 86 |
+
name: Cosine Accuracy
|
| 87 |
+
- type: cosine_accuracy_threshold
|
| 88 |
+
value: 0.5501536726951599
|
| 89 |
+
name: Cosine Accuracy Threshold
|
| 90 |
+
- type: cosine_f1
|
| 91 |
+
value: 0.912751677852349
|
| 92 |
+
name: Cosine F1
|
| 93 |
+
- type: cosine_f1_threshold
|
| 94 |
+
value: 0.4790937304496765
|
| 95 |
+
name: Cosine F1 Threshold
|
| 96 |
+
- type: cosine_precision
|
| 97 |
+
value: 0.918918918918919
|
| 98 |
+
name: Cosine Precision
|
| 99 |
+
- type: cosine_recall
|
| 100 |
+
value: 0.9066666666666666
|
| 101 |
+
name: Cosine Recall
|
| 102 |
+
- type: cosine_ap
|
| 103 |
+
value: 0.9084179566135925
|
| 104 |
+
name: Cosine Ap
|
| 105 |
+
- type: dot_accuracy
|
| 106 |
+
value: 0.9117647058823529
|
| 107 |
+
name: Dot Accuracy
|
| 108 |
+
- type: dot_accuracy_threshold
|
| 109 |
+
value: 294.13421630859375
|
| 110 |
+
name: Dot Accuracy Threshold
|
| 111 |
+
- type: dot_f1
|
| 112 |
+
value: 0.9166666666666666
|
| 113 |
+
name: Dot F1
|
| 114 |
+
- type: dot_f1_threshold
|
| 115 |
+
value: 294.13421630859375
|
| 116 |
+
name: Dot F1 Threshold
|
| 117 |
+
- type: dot_precision
|
| 118 |
+
value: 0.9565217391304348
|
| 119 |
+
name: Dot Precision
|
| 120 |
+
- type: dot_recall
|
| 121 |
+
value: 0.88
|
| 122 |
+
name: Dot Recall
|
| 123 |
+
- type: dot_ap
|
| 124 |
+
value: 0.915716305189008
|
| 125 |
+
name: Dot Ap
|
| 126 |
+
- type: manhattan_accuracy
|
| 127 |
+
value: 0.9044117647058824
|
| 128 |
+
name: Manhattan Accuracy
|
| 129 |
+
- type: manhattan_accuracy_threshold
|
| 130 |
+
value: 482.6566162109375
|
| 131 |
+
name: Manhattan Accuracy Threshold
|
| 132 |
+
- type: manhattan_f1
|
| 133 |
+
value: 0.913907284768212
|
| 134 |
+
name: Manhattan F1
|
| 135 |
+
- type: manhattan_f1_threshold
|
| 136 |
+
value: 532.9744262695312
|
| 137 |
+
name: Manhattan F1 Threshold
|
| 138 |
+
- type: manhattan_precision
|
| 139 |
+
value: 0.9078947368421053
|
| 140 |
+
name: Manhattan Precision
|
| 141 |
+
- type: manhattan_recall
|
| 142 |
+
value: 0.92
|
| 143 |
+
name: Manhattan Recall
|
| 144 |
+
- type: manhattan_ap
|
| 145 |
+
value: 0.9104676924615509
|
| 146 |
+
name: Manhattan Ap
|
| 147 |
+
- type: euclidean_accuracy
|
| 148 |
+
value: 0.9117647058823529
|
| 149 |
+
name: Euclidean Accuracy
|
| 150 |
+
- type: euclidean_accuracy_threshold
|
| 151 |
+
value: 23.818954467773438
|
| 152 |
+
name: Euclidean Accuracy Threshold
|
| 153 |
+
- type: euclidean_f1
|
| 154 |
+
value: 0.918918918918919
|
| 155 |
+
name: Euclidean F1
|
| 156 |
+
- type: euclidean_f1_threshold
|
| 157 |
+
value: 23.818954467773438
|
| 158 |
+
name: Euclidean F1 Threshold
|
| 159 |
+
- type: euclidean_precision
|
| 160 |
+
value: 0.9315068493150684
|
| 161 |
+
name: Euclidean Precision
|
| 162 |
+
- type: euclidean_recall
|
| 163 |
+
value: 0.9066666666666666
|
| 164 |
+
name: Euclidean Recall
|
| 165 |
+
- type: euclidean_ap
|
| 166 |
+
value: 0.9093211275077335
|
| 167 |
+
name: Euclidean Ap
|
| 168 |
+
- type: max_accuracy
|
| 169 |
+
value: 0.9117647058823529
|
| 170 |
+
name: Max Accuracy
|
| 171 |
+
- type: max_accuracy_threshold
|
| 172 |
+
value: 482.6566162109375
|
| 173 |
+
name: Max Accuracy Threshold
|
| 174 |
+
- type: max_f1
|
| 175 |
+
value: 0.918918918918919
|
| 176 |
+
name: Max F1
|
| 177 |
+
- type: max_f1_threshold
|
| 178 |
+
value: 532.9744262695312
|
| 179 |
+
name: Max F1 Threshold
|
| 180 |
+
- type: max_precision
|
| 181 |
+
value: 0.9565217391304348
|
| 182 |
+
name: Max Precision
|
| 183 |
+
- type: max_recall
|
| 184 |
+
value: 0.92
|
| 185 |
+
name: Max Recall
|
| 186 |
+
- type: max_ap
|
| 187 |
+
value: 0.915716305189008
|
| 188 |
+
name: Max Ap
|
| 189 |
+
---
|
| 190 |
+
|
| 191 |
+
# SentenceTransformer based on colorfulscoop/sbert-base-ja
|
| 192 |
+
|
| 193 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [colorfulscoop/sbert-base-ja](https://huggingface.co/colorfulscoop/sbert-base-ja) on the csv dataset. 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.
|
| 194 |
+
|
| 195 |
+
## Model Details
|
| 196 |
+
|
| 197 |
+
### Model Description
|
| 198 |
+
- **Model Type:** Sentence Transformer
|
| 199 |
+
- **Base model:** [colorfulscoop/sbert-base-ja](https://huggingface.co/colorfulscoop/sbert-base-ja) <!-- at revision ecb8a98cd5176719ff7ab0d770a27420118732cf -->
|
| 200 |
+
- **Maximum Sequence Length:** 512 tokens
|
| 201 |
+
- **Output Dimensionality:** 768 tokens
|
| 202 |
+
- **Similarity Function:** Cosine Similarity
|
| 203 |
+
- **Training Dataset:**
|
| 204 |
+
- csv
|
| 205 |
+
<!-- - **Language:** Unknown -->
|
| 206 |
+
<!-- - **License:** Unknown -->
|
| 207 |
+
|
| 208 |
+
### Model Sources
|
| 209 |
+
|
| 210 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
| 211 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
| 212 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
| 213 |
+
|
| 214 |
+
### Full Model Architecture
|
| 215 |
+
|
| 216 |
+
```
|
| 217 |
+
SentenceTransformer(
|
| 218 |
+
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
|
| 219 |
+
(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})
|
| 220 |
+
)
|
| 221 |
+
```
|
| 222 |
+
|
| 223 |
+
## Usage
|
| 224 |
+
|
| 225 |
+
### Direct Usage (Sentence Transformers)
|
| 226 |
+
|
| 227 |
+
First install the Sentence Transformers library:
|
| 228 |
+
|
| 229 |
+
```bash
|
| 230 |
+
pip install -U sentence-transformers
|
| 231 |
+
```
|
| 232 |
+
|
| 233 |
+
Then you can load this model and run inference.
|
| 234 |
+
```python
|
| 235 |
+
from sentence_transformers import SentenceTransformer
|
| 236 |
+
|
| 237 |
+
# Download from the 🤗 Hub
|
| 238 |
+
model = SentenceTransformer("sentence_transformers_model_id")
|
| 239 |
+
# Run inference
|
| 240 |
+
sentences = [
|
| 241 |
+
'魔法を使える人',
|
| 242 |
+
'物の姿を変えられる人',
|
| 243 |
+
'かっこいいね',
|
| 244 |
+
]
|
| 245 |
+
embeddings = model.encode(sentences)
|
| 246 |
+
print(embeddings.shape)
|
| 247 |
+
# [3, 768]
|
| 248 |
+
|
| 249 |
+
# Get the similarity scores for the embeddings
|
| 250 |
+
similarities = model.similarity(embeddings, embeddings)
|
| 251 |
+
print(similarities.shape)
|
| 252 |
+
# [3, 3]
|
| 253 |
+
```
|
| 254 |
+
|
| 255 |
+
<!--
|
| 256 |
+
### Direct Usage (Transformers)
|
| 257 |
+
|
| 258 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
| 259 |
+
|
| 260 |
+
</details>
|
| 261 |
+
-->
|
| 262 |
+
|
| 263 |
+
<!--
|
| 264 |
+
### Downstream Usage (Sentence Transformers)
|
| 265 |
+
|
| 266 |
+
You can finetune this model on your own dataset.
|
| 267 |
+
|
| 268 |
+
<details><summary>Click to expand</summary>
|
| 269 |
+
|
| 270 |
+
</details>
|
| 271 |
+
-->
|
| 272 |
+
|
| 273 |
+
<!--
|
| 274 |
+
### Out-of-Scope Use
|
| 275 |
+
|
| 276 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
| 277 |
+
-->
|
| 278 |
+
|
| 279 |
+
## Evaluation
|
| 280 |
+
|
| 281 |
+
### Metrics
|
| 282 |
+
|
| 283 |
+
#### Binary Classification
|
| 284 |
+
* Dataset: `custom-arc-semantics-data-jp`
|
| 285 |
+
* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
|
| 286 |
+
|
| 287 |
+
| Metric | Value |
|
| 288 |
+
|:-----------------------------|:-----------|
|
| 289 |
+
| cosine_accuracy | 0.9044 |
|
| 290 |
+
| cosine_accuracy_threshold | 0.5502 |
|
| 291 |
+
| cosine_f1 | 0.9128 |
|
| 292 |
+
| cosine_f1_threshold | 0.4791 |
|
| 293 |
+
| cosine_precision | 0.9189 |
|
| 294 |
+
| cosine_recall | 0.9067 |
|
| 295 |
+
| cosine_ap | 0.9084 |
|
| 296 |
+
| dot_accuracy | 0.9118 |
|
| 297 |
+
| dot_accuracy_threshold | 294.1342 |
|
| 298 |
+
| dot_f1 | 0.9167 |
|
| 299 |
+
| dot_f1_threshold | 294.1342 |
|
| 300 |
+
| dot_precision | 0.9565 |
|
| 301 |
+
| dot_recall | 0.88 |
|
| 302 |
+
| dot_ap | 0.9157 |
|
| 303 |
+
| manhattan_accuracy | 0.9044 |
|
| 304 |
+
| manhattan_accuracy_threshold | 482.6566 |
|
| 305 |
+
| manhattan_f1 | 0.9139 |
|
| 306 |
+
| manhattan_f1_threshold | 532.9744 |
|
| 307 |
+
| manhattan_precision | 0.9079 |
|
| 308 |
+
| manhattan_recall | 0.92 |
|
| 309 |
+
| manhattan_ap | 0.9105 |
|
| 310 |
+
| euclidean_accuracy | 0.9118 |
|
| 311 |
+
| euclidean_accuracy_threshold | 23.819 |
|
| 312 |
+
| euclidean_f1 | 0.9189 |
|
| 313 |
+
| euclidean_f1_threshold | 23.819 |
|
| 314 |
+
| euclidean_precision | 0.9315 |
|
| 315 |
+
| euclidean_recall | 0.9067 |
|
| 316 |
+
| euclidean_ap | 0.9093 |
|
| 317 |
+
| max_accuracy | 0.9118 |
|
| 318 |
+
| max_accuracy_threshold | 482.6566 |
|
| 319 |
+
| max_f1 | 0.9189 |
|
| 320 |
+
| max_f1_threshold | 532.9744 |
|
| 321 |
+
| max_precision | 0.9565 |
|
| 322 |
+
| max_recall | 0.92 |
|
| 323 |
+
| **max_ap** | **0.9157** |
|
| 324 |
+
|
| 325 |
+
<!--
|
| 326 |
+
## Bias, Risks and Limitations
|
| 327 |
+
|
| 328 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
| 329 |
+
-->
|
| 330 |
+
|
| 331 |
+
<!--
|
| 332 |
+
### Recommendations
|
| 333 |
+
|
| 334 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
| 335 |
+
-->
|
| 336 |
+
|
| 337 |
+
## Training Details
|
| 338 |
+
|
| 339 |
+
### Training Dataset
|
| 340 |
+
|
| 341 |
+
#### csv
|
| 342 |
+
|
| 343 |
+
* Dataset: csv
|
| 344 |
+
* Size: 680 training samples
|
| 345 |
+
* Columns: <code>text1</code>, <code>text2</code>, and <code>label</code>
|
| 346 |
+
* Approximate statistics based on the first 680 samples:
|
| 347 |
+
| | text1 | text2 | label |
|
| 348 |
+
|:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:------------------------------------------------|
|
| 349 |
+
| type | string | string | int |
|
| 350 |
+
| details | <ul><li>min: 4 tokens</li><li>mean: 8.29 tokens</li><li>max: 15 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 7.97 tokens</li><li>max: 14 tokens</li></ul> | <ul><li>0: ~40.44%</li><li>1: ~59.56%</li></ul> |
|
| 351 |
+
* Samples:
|
| 352 |
+
| text1 | text2 | label |
|
| 353 |
+
|:----------------------------|:----------------------------|:---------------|
|
| 354 |
+
| <code>いらない</code> | <code>うんよろしく</code> | <code>0</code> |
|
| 355 |
+
| <code>足元よりも更に深くってどこ？</code> | <code>足元よりも更に深くってなに？</code> | <code>1</code> |
|
| 356 |
+
| <code>他にはないの？</code> | <code>どう思う？</code> | <code>0</code> |
|
| 357 |
+
* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
|
| 358 |
+
```json
|
| 359 |
+
{
|
| 360 |
+
"scale": 20.0,
|
| 361 |
+
"similarity_fct": "pairwise_cos_sim"
|
| 362 |
+
}
|
| 363 |
+
```
|
| 364 |
+
|
| 365 |
+
### Evaluation Dataset
|
| 366 |
+
|
| 367 |
+
#### csv
|
| 368 |
+
|
| 369 |
+
* Dataset: csv
|
| 370 |
+
* Size: 680 evaluation samples
|
| 371 |
+
* Columns: <code>text1</code>, <code>text2</code>, and <code>label</code>
|
| 372 |
+
* Approximate statistics based on the first 680 samples:
|
| 373 |
+
| | text1 | text2 | label |
|
| 374 |
+
|:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:------------------------------------------------|
|
| 375 |
+
| type | string | string | int |
|
| 376 |
+
| details | <ul><li>min: 4 tokens</li><li>mean: 8.32 tokens</li><li>max: 15 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 8.16 tokens</li><li>max: 14 tokens</li></ul> | <ul><li>0: ~44.85%</li><li>1: ~55.15%</li></ul> |
|
| 377 |
+
* Samples:
|
| 378 |
+
| text1 | text2 | label |
|
| 379 |
+
|:-------------------------|:-------------------------|:---------------|
|
| 380 |
+
| <code>井戸から水をくんでいた</code> | <code>井戸を使っていた</code> | <code>1</code> |
|
| 381 |
+
| <code>夕飯は何だったの？</code> | <code>チキンヌードル食べた？</code> | <code>0</code> |
|
| 382 |
+
| <code>水を井戸からくんでいた</code> | <code>夜ごはんの前</code> | <code>0</code> |
|
| 383 |
+
* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
|
| 384 |
+
```json
|
| 385 |
+
{
|
| 386 |
+
"scale": 20.0,
|
| 387 |
+
"similarity_fct": "pairwise_cos_sim"
|
| 388 |
+
}
|
| 389 |
+
```
|
| 390 |
+
|
| 391 |
+
### Training Hyperparameters
|
| 392 |
+
#### Non-Default Hyperparameters
|
| 393 |
+
|
| 394 |
+
- `eval_strategy`: epoch
|
| 395 |
+
- `learning_rate`: 2e-05
|
| 396 |
+
- `num_train_epochs`: 13
|
| 397 |
+
- `warmup_ratio`: 0.1
|
| 398 |
+
- `fp16`: True
|
| 399 |
+
- `batch_sampler`: no_duplicates
|
| 400 |
+
|
| 401 |
+
#### All Hyperparameters
|
| 402 |
+
<details><summary>Click to expand</summary>
|
| 403 |
+
|
| 404 |
+
- `overwrite_output_dir`: False
|
| 405 |
+
- `do_predict`: False
|
| 406 |
+
- `eval_strategy`: epoch
|
| 407 |
+
- `prediction_loss_only`: True
|
| 408 |
+
- `per_device_train_batch_size`: 8
|
| 409 |
+
- `per_device_eval_batch_size`: 8
|
| 410 |
+
- `per_gpu_train_batch_size`: None
|
| 411 |
+
- `per_gpu_eval_batch_size`: None
|
| 412 |
+
- `gradient_accumulation_steps`: 1
|
| 413 |
+
- `eval_accumulation_steps`: None
|
| 414 |
+
- `torch_empty_cache_steps`: None
|
| 415 |
+
- `learning_rate`: 2e-05
|
| 416 |
+
- `weight_decay`: 0.0
|
| 417 |
+
- `adam_beta1`: 0.9
|
| 418 |
+
- `adam_beta2`: 0.999
|
| 419 |
+
- `adam_epsilon`: 1e-08
|
| 420 |
+
- `max_grad_norm`: 1.0
|
| 421 |
+
- `num_train_epochs`: 13
|
| 422 |
+
- `max_steps`: -1
|
| 423 |
+
- `lr_scheduler_type`: linear
|
| 424 |
+
- `lr_scheduler_kwargs`: {}
|
| 425 |
+
- `warmup_ratio`: 0.1
|
| 426 |
+
- `warmup_steps`: 0
|
| 427 |
+
- `log_level`: passive
|
| 428 |
+
- `log_level_replica`: warning
|
| 429 |
+
- `log_on_each_node`: True
|
| 430 |
+
- `logging_nan_inf_filter`: True
|
| 431 |
+
- `save_safetensors`: True
|
| 432 |
+
- `save_on_each_node`: False
|
| 433 |
+
- `save_only_model`: False
|
| 434 |
+
- `restore_callback_states_from_checkpoint`: False
|
| 435 |
+
- `no_cuda`: False
|
| 436 |
+
- `use_cpu`: False
|
| 437 |
+
- `use_mps_device`: False
|
| 438 |
+
- `seed`: 42
|
| 439 |
+
- `data_seed`: None
|
| 440 |
+
- `jit_mode_eval`: False
|
| 441 |
+
- `use_ipex`: False
|
| 442 |
+
- `bf16`: False
|
| 443 |
+
- `fp16`: True
|
| 444 |
+
- `fp16_opt_level`: O1
|
| 445 |
+
- `half_precision_backend`: auto
|
| 446 |
+
- `bf16_full_eval`: False
|
| 447 |
+
- `fp16_full_eval`: False
|
| 448 |
+
- `tf32`: None
|
| 449 |
+
- `local_rank`: 0
|
| 450 |
+
- `ddp_backend`: None
|
| 451 |
+
- `tpu_num_cores`: None
|
| 452 |
+
- `tpu_metrics_debug`: False
|
| 453 |
+
- `debug`: []
|
| 454 |
+
- `dataloader_drop_last`: False
|
| 455 |
+
- `dataloader_num_workers`: 0
|
| 456 |
+
- `dataloader_prefetch_factor`: None
|
| 457 |
+
- `past_index`: -1
|
| 458 |
+
- `disable_tqdm`: False
|
| 459 |
+
- `remove_unused_columns`: True
|
| 460 |
+
- `label_names`: None
|
| 461 |
+
- `load_best_model_at_end`: False
|
| 462 |
+
- `ignore_data_skip`: False
|
| 463 |
+
- `fsdp`: []
|
| 464 |
+
- `fsdp_min_num_params`: 0
|
| 465 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
| 466 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
| 467 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
| 468 |
+
- `deepspeed`: None
|
| 469 |
+
- `label_smoothing_factor`: 0.0
|
| 470 |
+
- `optim`: adamw_torch
|
| 471 |
+
- `optim_args`: None
|
| 472 |
+
- `adafactor`: False
|
| 473 |
+
- `group_by_length`: False
|
| 474 |
+
- `length_column_name`: length
|
| 475 |
+
- `ddp_find_unused_parameters`: None
|
| 476 |
+
- `ddp_bucket_cap_mb`: None
|
| 477 |
+
- `ddp_broadcast_buffers`: False
|
| 478 |
+
- `dataloader_pin_memory`: True
|
| 479 |
+
- `dataloader_persistent_workers`: False
|
| 480 |
+
- `skip_memory_metrics`: True
|
| 481 |
+
- `use_legacy_prediction_loop`: False
|
| 482 |
+
- `push_to_hub`: False
|
| 483 |
+
- `resume_from_checkpoint`: None
|
| 484 |
+
- `hub_model_id`: None
|
| 485 |
+
- `hub_strategy`: every_save
|
| 486 |
+
- `hub_private_repo`: False
|
| 487 |
+
- `hub_always_push`: False
|
| 488 |
+
- `gradient_checkpointing`: False
|
| 489 |
+
- `gradient_checkpointing_kwargs`: None
|
| 490 |
+
- `include_inputs_for_metrics`: False
|
| 491 |
+
- `eval_do_concat_batches`: True
|
| 492 |
+
- `fp16_backend`: auto
|
| 493 |
+
- `push_to_hub_model_id`: None
|
| 494 |
+
- `push_to_hub_organization`: None
|
| 495 |
+
- `mp_parameters`:
|
| 496 |
+
- `auto_find_batch_size`: False
|
| 497 |
+
- `full_determinism`: False
|
| 498 |
+
- `torchdynamo`: None
|
| 499 |
+
- `ray_scope`: last
|
| 500 |
+
- `ddp_timeout`: 1800
|
| 501 |
+
- `torch_compile`: False
|
| 502 |
+
- `torch_compile_backend`: None
|
| 503 |
+
- `torch_compile_mode`: None
|
| 504 |
+
- `dispatch_batches`: None
|
| 505 |
+
- `split_batches`: None
|
| 506 |
+
- `include_tokens_per_second`: False
|
| 507 |
+
- `include_num_input_tokens_seen`: False
|
| 508 |
+
- `neftune_noise_alpha`: None
|
| 509 |
+
- `optim_target_modules`: None
|
| 510 |
+
- `batch_eval_metrics`: False
|
| 511 |
+
- `eval_on_start`: False
|
| 512 |
+
- `eval_use_gather_object`: False
|
| 513 |
+
- `batch_sampler`: no_duplicates
|
| 514 |
+
- `multi_dataset_batch_sampler`: proportional
|
| 515 |
+
|
| 516 |
+
</details>
|
| 517 |
+
|
| 518 |
+
### Training Logs
|
| 519 |
+
| Epoch | Step | Training Loss | loss | custom-arc-semantics-data-jp_max_ap |
|
| 520 |
+
|:-----:|:----:|:-------------:|:------:|:-----------------------------------:|
|
| 521 |
+
| None | 0 | - | - | 0.8596 |
|
| 522 |
+
| 1.0 | 68 | 2.6802 | 1.7807 | 0.8872 |
|
| 523 |
+
| 2.0 | 136 | 1.4014 | 1.7683 | 0.8945 |
|
| 524 |
+
| 3.0 | 204 | 0.7937 | 1.9877 | 0.9039 |
|
| 525 |
+
| 4.0 | 272 | 0.5443 | 1.9106 | 0.9075 |
|
| 526 |
+
| 5.0 | 340 | 0.4225 | 1.9418 | 0.9109 |
|
| 527 |
+
| 6.0 | 408 | 0.3347 | 2.0123 | 0.9107 |
|
| 528 |
+
| 7.0 | 476 | 0.3425 | 2.0387 | 0.9094 |
|
| 529 |
+
| 8.0 | 544 | 0.2427 | 1.9878 | 0.9103 |
|
| 530 |
+
| 9.0 | 612 | 0.2412 | 2.0424 | 0.9178 |
|
| 531 |
+
| 10.0 | 680 | 0.1623 | 2.0273 | 0.9188 |
|
| 532 |
+
| 11.0 | 748 | 0.1909 | 2.0955 | 0.9220 |
|
| 533 |
+
| 12.0 | 816 | 0.1507 | 2.2124 | 0.9157 |
|
| 534 |
+
|
| 535 |
+
|
| 536 |
+
### Framework Versions
|
| 537 |
+
- Python: 3.10.14
|
| 538 |
+
- Sentence Transformers: 3.1.0
|
| 539 |
+
- Transformers: 4.44.2
|
| 540 |
+
- PyTorch: 2.4.1+cu121
|
| 541 |
+
- Accelerate: 0.34.2
|
| 542 |
+
- Datasets: 2.20.0
|
| 543 |
+
- Tokenizers: 0.19.1
|
| 544 |
+
|
| 545 |
+
## Citation
|
| 546 |
+
|
| 547 |
+
### BibTeX
|
| 548 |
+
|
| 549 |
+
#### Sentence Transformers
|
| 550 |
+
```bibtex
|
| 551 |
+
@inproceedings{reimers-2019-sentence-bert,
|
| 552 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
| 553 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
| 554 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
| 555 |
+
month = "11",
|
| 556 |
+
year = "2019",
|
| 557 |
+
publisher = "Association for Computational Linguistics",
|
| 558 |
+
url = "https://arxiv.org/abs/1908.10084",
|
| 559 |
+
}
|
| 560 |
+
```
|
| 561 |
+
|
| 562 |
+
#### CoSENTLoss
|
| 563 |
+
```bibtex
|
| 564 |
+
@online{kexuefm-8847,
|
| 565 |
+
title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
|
| 566 |
+
author={Su Jianlin},
|
| 567 |
+
year={2022},
|
| 568 |
+
month={Jan},
|
| 569 |
+
url={https://kexue.fm/archives/8847},
|
| 570 |
+
}
|
| 571 |
+
```
|
| 572 |
+
|
| 573 |
+
<!--
|
| 574 |
+
## Glossary
|
| 575 |
+
|
| 576 |
+
*Clearly define terms in order to be accessible across audiences.*
|
| 577 |
+
-->
|
| 578 |
+
|
| 579 |
+
<!--
|
| 580 |
+
## Model Card Authors
|
| 581 |
+
|
| 582 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
| 583 |
+
-->
|
| 584 |
+
|
| 585 |
+
<!--
|
| 586 |
+
## Model Card Contact
|
| 587 |
+
|
| 588 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
| 589 |
+
-->
|
checkpoint-816/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 32000
|
| 3 |
+
}
|
checkpoint-816/config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "colorfulscoop/sbert-base-ja",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertModel"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 2,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"cls_token_id": 2,
|
| 10 |
+
"eos_token_id": 3,
|
| 11 |
+
"gradient_checkpointing": false,
|
| 12 |
+
"hidden_act": "gelu",
|
| 13 |
+
"hidden_dropout_prob": 0.1,
|
| 14 |
+
"hidden_size": 768,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 3072,
|
| 17 |
+
"layer_norm_eps": 1e-12,
|
| 18 |
+
"mask_token_id": 4,
|
| 19 |
+
"max_position_embeddings": 512,
|
| 20 |
+
"model_type": "bert",
|
| 21 |
+
"num_attention_heads": 12,
|
| 22 |
+
"num_hidden_layers": 12,
|
| 23 |
+
"pad_token_id": 0,
|
| 24 |
+
"position_embedding_type": "absolute",
|
| 25 |
+
"sep_token_id": 3,
|
| 26 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.44.2",
|
| 29 |
+
"type_vocab_size": 2,
|
| 30 |
+
"unk_token_id": 1,
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 32000
|
| 33 |
+
}
|
checkpoint-816/config_sentence_transformers.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"__version__": {
|
| 3 |
+
"sentence_transformers": "3.1.0",
|
| 4 |
+
"transformers": "4.44.2",
|
| 5 |
+
"pytorch": "2.4.1+cu121"
|
| 6 |
+
},
|
| 7 |
+
"prompts": {},
|
| 8 |
+
"default_prompt_name": null,
|
| 9 |
+
"similarity_fn_name": null
|
| 10 |
+
}
|
checkpoint-816/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b39d988a62cf3328c005ebecdda07f0df50a10d199b1f8812f8ce2729238961
|
| 3 |
+
size 442491744
|
checkpoint-816/modules.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
]
|
checkpoint-816/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13cda44a810c660a8f509a2dd6d1695114c4b0f55ee02b394a52aca420e66684
|
| 3 |
+
size 880373306
|
checkpoint-816/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23f1a25ebc26b1fcdc98956b5af5bc23a09d13a4dc85b2e06beec26dd1f847f8
|
| 3 |
+
size 13990
|
checkpoint-816/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1469853985d8479d14e56985ee2e4845f271b406135d192db2351f4fb4f0ed07
|
| 3 |
+
size 1064
|
checkpoint-816/sentence_bert_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"max_seq_length": 512,
|
| 3 |
+
"do_lower_case": false
|
| 4 |
+
}
|
checkpoint-816/special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "[SEP]",
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"pad_token": "<pad>",
|
| 7 |
+
"sep_token": "[SEP]",
|
| 8 |
+
"unk_token": {
|
| 9 |
+
"content": "<unk>",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": true,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
}
|
| 15 |
+
}
|
checkpoint-816/spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6467857b4b0c77ded9bac7ad2fb5c16eb64e17e417ce46624dacac2bbb404fc
|
| 3 |
+
size 802713
|
checkpoint-816/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-816/tokenizer_config.json
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<pad>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<unk>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": true,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": false
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": false
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": false
|
| 42 |
+
},
|
| 43 |
+
"32000": {
|
| 44 |
+
"content": "[PAD]",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": true,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": false
|
| 50 |
+
}
|
| 51 |
+
},
|
| 52 |
+
"bos_token": "[CLS]",
|
| 53 |
+
"clean_up_tokenization_spaces": true,
|
| 54 |
+
"cls_token": "[CLS]",
|
| 55 |
+
"do_lower_case": false,
|
| 56 |
+
"eos_token": "[SEP]",
|
| 57 |
+
"mask_token": "[MASK]",
|
| 58 |
+
"model_max_length": 512,
|
| 59 |
+
"pad_token": "<pad>",
|
| 60 |
+
"sep_token": "[SEP]",
|
| 61 |
+
"sp_model_kwargs": {},
|
| 62 |
+
"split_by_punct": false,
|
| 63 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 64 |
+
"unk_token": "<unk>"
|
| 65 |
+
}
|
checkpoint-816/trainer_state.json
ADDED
|
@@ -0,0 +1,633 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 12.0,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 816,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"grad_norm": 37.9459228515625,
|
| 14 |
+
"learning_rate": 1.5280898876404495e-05,
|
| 15 |
+
"loss": 2.6802,
|
| 16 |
+
"step": 68
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.8529411764705882,
|
| 21 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.7407679557800293,
|
| 22 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.8861687056931384,
|
| 23 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.863013698630137,
|
| 24 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.7407679557800293,
|
| 25 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.8873239436619719,
|
| 26 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.84,
|
| 27 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.8529411764705882,
|
| 28 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 413.34197998046875,
|
| 29 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.887218522968793,
|
| 30 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.8648648648648648,
|
| 31 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 413.34197998046875,
|
| 32 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.8767123287671232,
|
| 33 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.8533333333333334,
|
| 34 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.8602941176470589,
|
| 35 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 17.441856384277344,
|
| 36 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.8855166425710176,
|
| 37 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.87248322147651,
|
| 38 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 17.441856384277344,
|
| 39 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.8783783783783784,
|
| 40 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.8666666666666667,
|
| 41 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.8602941176470589,
|
| 42 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 382.9211730957031,
|
| 43 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.8854876210985647,
|
| 44 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.8741721854304636,
|
| 45 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 386.8717956542969,
|
| 46 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.868421052631579,
|
| 47 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.88,
|
| 48 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.8602941176470589,
|
| 49 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 413.34197998046875,
|
| 50 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.887218522968793,
|
| 51 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.8741721854304636,
|
| 52 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 413.34197998046875,
|
| 53 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.8873239436619719,
|
| 54 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.88,
|
| 55 |
+
"eval_loss": 1.7807204723358154,
|
| 56 |
+
"eval_runtime": 14.8133,
|
| 57 |
+
"eval_samples_per_second": 9.181,
|
| 58 |
+
"eval_steps_per_second": 1.148,
|
| 59 |
+
"step": 68
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 2.0,
|
| 63 |
+
"grad_norm": 101.59432983398438,
|
| 64 |
+
"learning_rate": 1.8817610062893082e-05,
|
| 65 |
+
"loss": 1.4014,
|
| 66 |
+
"step": 136
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 2.0,
|
| 70 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.8676470588235294,
|
| 71 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.656826376914978,
|
| 72 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.894049495028942,
|
| 73 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.8783783783783784,
|
| 74 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.656826376914978,
|
| 75 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.8904109589041096,
|
| 76 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.8666666666666667,
|
| 77 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.8602941176470589,
|
| 78 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 367.9239501953125,
|
| 79 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.8915744113817081,
|
| 80 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.87248322147651,
|
| 81 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 363.2611999511719,
|
| 82 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.8783783783783784,
|
| 83 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.8666666666666667,
|
| 84 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.8602941176470589,
|
| 85 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 19.78958511352539,
|
| 86 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.8925974243856872,
|
| 87 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.8819875776397516,
|
| 88 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 20.95208740234375,
|
| 89 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.8255813953488372,
|
| 90 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.9466666666666667,
|
| 91 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.875,
|
| 92 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 456.61602783203125,
|
| 93 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.8944639878933996,
|
| 94 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.8930817610062893,
|
| 95 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 456.61602783203125,
|
| 96 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.8452380952380952,
|
| 97 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.9466666666666667,
|
| 98 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.875,
|
| 99 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 456.61602783203125,
|
| 100 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.8944639878933996,
|
| 101 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.8930817610062893,
|
| 102 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 456.61602783203125,
|
| 103 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.8904109589041096,
|
| 104 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.9466666666666667,
|
| 105 |
+
"eval_loss": 1.7683357000350952,
|
| 106 |
+
"eval_runtime": 13.9834,
|
| 107 |
+
"eval_samples_per_second": 9.726,
|
| 108 |
+
"eval_steps_per_second": 1.216,
|
| 109 |
+
"step": 136
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 3.0,
|
| 113 |
+
"grad_norm": 102.5489730834961,
|
| 114 |
+
"learning_rate": 1.7106918238993714e-05,
|
| 115 |
+
"loss": 0.7937,
|
| 116 |
+
"step": 204
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 3.0,
|
| 120 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.8897058823529411,
|
| 121 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.5597226619720459,
|
| 122 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.9038906301326961,
|
| 123 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.9006622516556291,
|
| 124 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.5076813697814941,
|
| 125 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.8947368421052632,
|
| 126 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.9066666666666666,
|
| 127 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.8823529411764706,
|
| 128 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 314.1024475097656,
|
| 129 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.9012158574599884,
|
| 130 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.8904109589041095,
|
| 131 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 295.25762939453125,
|
| 132 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.9154929577464789,
|
| 133 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.8666666666666667,
|
| 134 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.8970588235294118,
|
| 135 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 22.511234283447266,
|
| 136 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.9033993255493061,
|
| 137 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.9054054054054055,
|
| 138 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 22.511234283447266,
|
| 139 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.9178082191780822,
|
| 140 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.8933333333333333,
|
| 141 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.8897058823529411,
|
| 142 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 480.63677978515625,
|
| 143 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.9033851155012284,
|
| 144 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.8993288590604026,
|
| 145 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 502.66156005859375,
|
| 146 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.9054054054054054,
|
| 147 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.8933333333333333,
|
| 148 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.8970588235294118,
|
| 149 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 480.63677978515625,
|
| 150 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.9038906301326961,
|
| 151 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.9054054054054055,
|
| 152 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 502.66156005859375,
|
| 153 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.9178082191780822,
|
| 154 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.9066666666666666,
|
| 155 |
+
"eval_loss": 1.9876813888549805,
|
| 156 |
+
"eval_runtime": 15.0797,
|
| 157 |
+
"eval_samples_per_second": 9.019,
|
| 158 |
+
"eval_steps_per_second": 1.127,
|
| 159 |
+
"step": 204
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 4.0,
|
| 163 |
+
"grad_norm": 54.64971160888672,
|
| 164 |
+
"learning_rate": 1.539622641509434e-05,
|
| 165 |
+
"loss": 0.5443,
|
| 166 |
+
"step": 272
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 4.0,
|
| 170 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.9117647058823529,
|
| 171 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.5411365032196045,
|
| 172 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.9075251070302803,
|
| 173 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.918918918918919,
|
| 174 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.5411365032196045,
|
| 175 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.9315068493150684,
|
| 176 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.9066666666666666,
|
| 177 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.8897058823529411,
|
| 178 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 311.26678466796875,
|
| 179 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.9040853015076152,
|
| 180 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.9006622516556291,
|
| 181 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 285.96728515625,
|
| 182 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.8947368421052632,
|
| 183 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.9066666666666666,
|
| 184 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.9117647058823529,
|
| 185 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 22.630477905273438,
|
| 186 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.906411643380887,
|
| 187 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.918918918918919,
|
| 188 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 22.630477905273438,
|
| 189 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.9315068493150684,
|
| 190 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.9066666666666666,
|
| 191 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.9117647058823529,
|
| 192 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 495.93194580078125,
|
| 193 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.9068108312799359,
|
| 194 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.918918918918919,
|
| 195 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 495.93194580078125,
|
| 196 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.9315068493150684,
|
| 197 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.9066666666666666,
|
| 198 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.9117647058823529,
|
| 199 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 495.93194580078125,
|
| 200 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.9075251070302803,
|
| 201 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.918918918918919,
|
| 202 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 495.93194580078125,
|
| 203 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.9315068493150684,
|
| 204 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.9066666666666666,
|
| 205 |
+
"eval_loss": 1.910571813583374,
|
| 206 |
+
"eval_runtime": 14.3178,
|
| 207 |
+
"eval_samples_per_second": 9.499,
|
| 208 |
+
"eval_steps_per_second": 1.187,
|
| 209 |
+
"step": 272
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 5.0,
|
| 213 |
+
"grad_norm": 7.771420955657959,
|
| 214 |
+
"learning_rate": 1.368553459119497e-05,
|
| 215 |
+
"loss": 0.4225,
|
| 216 |
+
"step": 340
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 5.0,
|
| 220 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.9117647058823529,
|
| 221 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.5279971361160278,
|
| 222 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.9104573720737034,
|
| 223 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.918918918918919,
|
| 224 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.5279971361160278,
|
| 225 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.9315068493150684,
|
| 226 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.9066666666666666,
|
| 227 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.9044117647058824,
|
| 228 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 319.6995849609375,
|
| 229 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.907606464463115,
|
| 230 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.9115646258503401,
|
| 231 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 290.19317626953125,
|
| 232 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.9305555555555556,
|
| 233 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.8933333333333333,
|
| 234 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.9117647058823529,
|
| 235 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 22.626989364624023,
|
| 236 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.9092245976210003,
|
| 237 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.918918918918919,
|
| 238 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 22.626989364624023,
|
| 239 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.9315068493150684,
|
| 240 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.9066666666666666,
|
| 241 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.9117647058823529,
|
| 242 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 494.6650390625,
|
| 243 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.9108555121538641,
|
| 244 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.92,
|
| 245 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 514.7510986328125,
|
| 246 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.92,
|
| 247 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.92,
|
| 248 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.9117647058823529,
|
| 249 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 494.6650390625,
|
| 250 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.9108555121538641,
|
| 251 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.92,
|
| 252 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 514.7510986328125,
|
| 253 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.9315068493150684,
|
| 254 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.92,
|
| 255 |
+
"eval_loss": 1.9418467283248901,
|
| 256 |
+
"eval_runtime": 14.4159,
|
| 257 |
+
"eval_samples_per_second": 9.434,
|
| 258 |
+
"eval_steps_per_second": 1.179,
|
| 259 |
+
"step": 340
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 6.0,
|
| 263 |
+
"grad_norm": 0.8858943581581116,
|
| 264 |
+
"learning_rate": 1.1974842767295597e-05,
|
| 265 |
+
"loss": 0.3347,
|
| 266 |
+
"step": 408
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 6.0,
|
| 270 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.9117647058823529,
|
| 271 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.5068449974060059,
|
| 272 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.9088529074244793,
|
| 273 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.918918918918919,
|
| 274 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.5068449974060059,
|
| 275 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.9315068493150684,
|
| 276 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.9066666666666666,
|
| 277 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.8970588235294118,
|
| 278 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 322.01324462890625,
|
| 279 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.9107273300403762,
|
| 280 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.9054054054054055,
|
| 281 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 276.34893798828125,
|
| 282 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.9178082191780822,
|
| 283 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.8933333333333333,
|
| 284 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.9117647058823529,
|
| 285 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 23.167011260986328,
|
| 286 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.9088745561179659,
|
| 287 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.918918918918919,
|
| 288 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 23.167011260986328,
|
| 289 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.9315068493150684,
|
| 290 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.9066666666666666,
|
| 291 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.9117647058823529,
|
| 292 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 506.7710266113281,
|
| 293 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.9092068556819233,
|
| 294 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.918918918918919,
|
| 295 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 506.7710266113281,
|
| 296 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.9315068493150684,
|
| 297 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.9066666666666666,
|
| 298 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.9117647058823529,
|
| 299 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 506.7710266113281,
|
| 300 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.9107273300403762,
|
| 301 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.918918918918919,
|
| 302 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 506.7710266113281,
|
| 303 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.9315068493150684,
|
| 304 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.9066666666666666,
|
| 305 |
+
"eval_loss": 2.012265920639038,
|
| 306 |
+
"eval_runtime": 13.9077,
|
| 307 |
+
"eval_samples_per_second": 9.779,
|
| 308 |
+
"eval_steps_per_second": 1.222,
|
| 309 |
+
"step": 408
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 7.0,
|
| 313 |
+
"grad_norm": 0.24478188157081604,
|
| 314 |
+
"learning_rate": 1.0264150943396227e-05,
|
| 315 |
+
"loss": 0.3425,
|
| 316 |
+
"step": 476
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 7.0,
|
| 320 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.9044117647058824,
|
| 321 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.5215883255004883,
|
| 322 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.9081430244026829,
|
| 323 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.912751677852349,
|
| 324 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.5215883255004883,
|
| 325 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.918918918918919,
|
| 326 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.9066666666666666,
|
| 327 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.9044117647058824,
|
| 328 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 313.0162353515625,
|
| 329 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.9094090969210814,
|
| 330 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.9090909090909091,
|
| 331 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 313.0162353515625,
|
| 332 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.9558823529411765,
|
| 333 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.8666666666666667,
|
| 334 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.9044117647058824,
|
| 335 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 23.342838287353516,
|
| 336 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.907981722850528,
|
| 337 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.912751677852349,
|
| 338 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 23.342838287353516,
|
| 339 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.918918918918919,
|
| 340 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.9066666666666666,
|
| 341 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.9044117647058824,
|
| 342 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 511.61737060546875,
|
| 343 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.9085688725632555,
|
| 344 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.912751677852349,
|
| 345 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 511.61737060546875,
|
| 346 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.918918918918919,
|
| 347 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.9066666666666666,
|
| 348 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.9044117647058824,
|
| 349 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 511.61737060546875,
|
| 350 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.9094090969210814,
|
| 351 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.912751677852349,
|
| 352 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 511.61737060546875,
|
| 353 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.9558823529411765,
|
| 354 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.9066666666666666,
|
| 355 |
+
"eval_loss": 2.038686752319336,
|
| 356 |
+
"eval_runtime": 14.7627,
|
| 357 |
+
"eval_samples_per_second": 9.212,
|
| 358 |
+
"eval_steps_per_second": 1.152,
|
| 359 |
+
"step": 476
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 8.0,
|
| 363 |
+
"grad_norm": 0.09618318825960159,
|
| 364 |
+
"learning_rate": 8.553459119496857e-06,
|
| 365 |
+
"loss": 0.2427,
|
| 366 |
+
"step": 544
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 8.0,
|
| 370 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.9044117647058824,
|
| 371 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.5501157641410828,
|
| 372 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.9086817589029806,
|
| 373 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.912751677852349,
|
| 374 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.5119773149490356,
|
| 375 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.918918918918919,
|
| 376 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.9066666666666666,
|
| 377 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.9117647058823529,
|
| 378 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 294.31005859375,
|
| 379 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.9096226292878296,
|
| 380 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.9166666666666666,
|
| 381 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 294.31005859375,
|
| 382 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.9565217391304348,
|
| 383 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.88,
|
| 384 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.9117647058823529,
|
| 385 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 23.28342056274414,
|
| 386 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.9089227316320502,
|
| 387 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.918918918918919,
|
| 388 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 23.28342056274414,
|
| 389 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.9315068493150684,
|
| 390 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.9066666666666666,
|
| 391 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.9117647058823529,
|
| 392 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 509.5169677734375,
|
| 393 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.9102569832574411,
|
| 394 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.918918918918919,
|
| 395 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 509.5169677734375,
|
| 396 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.9315068493150684,
|
| 397 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.9066666666666666,
|
| 398 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.9117647058823529,
|
| 399 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 509.5169677734375,
|
| 400 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.9102569832574411,
|
| 401 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.918918918918919,
|
| 402 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 509.5169677734375,
|
| 403 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.9565217391304348,
|
| 404 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.9066666666666666,
|
| 405 |
+
"eval_loss": 1.9878324270248413,
|
| 406 |
+
"eval_runtime": 13.7764,
|
| 407 |
+
"eval_samples_per_second": 9.872,
|
| 408 |
+
"eval_steps_per_second": 1.234,
|
| 409 |
+
"step": 544
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 9.0,
|
| 413 |
+
"grad_norm": 0.046123113483190536,
|
| 414 |
+
"learning_rate": 6.842767295597485e-06,
|
| 415 |
+
"loss": 0.2412,
|
| 416 |
+
"step": 612
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 9.0,
|
| 420 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.9044117647058824,
|
| 421 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.5531296730041504,
|
| 422 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.9088232956862466,
|
| 423 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.912751677852349,
|
| 424 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.49595877528190613,
|
| 425 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.918918918918919,
|
| 426 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.9066666666666666,
|
| 427 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.9117647058823529,
|
| 428 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 295.7380676269531,
|
| 429 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.9178358242971421,
|
| 430 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.9166666666666666,
|
| 431 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 295.7380676269531,
|
| 432 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.9565217391304348,
|
| 433 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.88,
|
| 434 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.9117647058823529,
|
| 435 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 23.565818786621094,
|
| 436 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.9092338106583002,
|
| 437 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.918918918918919,
|
| 438 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 23.565818786621094,
|
| 439 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.9315068493150684,
|
| 440 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.9066666666666666,
|
| 441 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.9117647058823529,
|
| 442 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 515.80322265625,
|
| 443 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.9102278723159124,
|
| 444 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.918918918918919,
|
| 445 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 515.80322265625,
|
| 446 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.9315068493150684,
|
| 447 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.9066666666666666,
|
| 448 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.9117647058823529,
|
| 449 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 515.80322265625,
|
| 450 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.9178358242971421,
|
| 451 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.918918918918919,
|
| 452 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 515.80322265625,
|
| 453 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.9565217391304348,
|
| 454 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.9066666666666666,
|
| 455 |
+
"eval_loss": 2.0423502922058105,
|
| 456 |
+
"eval_runtime": 18.8817,
|
| 457 |
+
"eval_samples_per_second": 7.203,
|
| 458 |
+
"eval_steps_per_second": 0.9,
|
| 459 |
+
"step": 612
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 10.0,
|
| 463 |
+
"grad_norm": 0.029908249154686928,
|
| 464 |
+
"learning_rate": 5.1320754716981136e-06,
|
| 465 |
+
"loss": 0.1623,
|
| 466 |
+
"step": 680
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 10.0,
|
| 470 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.9044117647058824,
|
| 471 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.5516438484191895,
|
| 472 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.9085774598037802,
|
| 473 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.9103448275862068,
|
| 474 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.519783079624176,
|
| 475 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.9428571428571428,
|
| 476 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.88,
|
| 477 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.9117647058823529,
|
| 478 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 294.6772766113281,
|
| 479 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.918847565389113,
|
| 480 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.9166666666666666,
|
| 481 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 294.6772766113281,
|
| 482 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.9565217391304348,
|
| 483 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.88,
|
| 484 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.9044117647058824,
|
| 485 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 21.938934326171875,
|
| 486 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.9089511554768472,
|
| 487 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.912751677852349,
|
| 488 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 23.713035583496094,
|
| 489 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.918918918918919,
|
| 490 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.9066666666666666,
|
| 491 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.9044117647058824,
|
| 492 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 482.1662292480469,
|
| 493 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.910254731797207,
|
| 494 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.912751677852349,
|
| 495 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 524.188232421875,
|
| 496 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.918918918918919,
|
| 497 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.9066666666666666,
|
| 498 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.9117647058823529,
|
| 499 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 482.1662292480469,
|
| 500 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.918847565389113,
|
| 501 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.9166666666666666,
|
| 502 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 524.188232421875,
|
| 503 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.9565217391304348,
|
| 504 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.9066666666666666,
|
| 505 |
+
"eval_loss": 2.0273122787475586,
|
| 506 |
+
"eval_runtime": 20.5658,
|
| 507 |
+
"eval_samples_per_second": 6.613,
|
| 508 |
+
"eval_steps_per_second": 0.827,
|
| 509 |
+
"step": 680
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 11.0,
|
| 513 |
+
"grad_norm": 0.007907501421868801,
|
| 514 |
+
"learning_rate": 3.4213836477987424e-06,
|
| 515 |
+
"loss": 0.1909,
|
| 516 |
+
"step": 748
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 11.0,
|
| 520 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.9044117647058824,
|
| 521 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.550028383731842,
|
| 522 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.9090819039672458,
|
| 523 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.912751677852349,
|
| 524 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.48157936334609985,
|
| 525 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.918918918918919,
|
| 526 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.9066666666666666,
|
| 527 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.9117647058823529,
|
| 528 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 293.80010986328125,
|
| 529 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.9219827879602106,
|
| 530 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.9166666666666666,
|
| 531 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 293.80010986328125,
|
| 532 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.9565217391304348,
|
| 533 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.88,
|
| 534 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.9117647058823529,
|
| 535 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 23.849559783935547,
|
| 536 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.90922024992935,
|
| 537 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.918918918918919,
|
| 538 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 23.849559783935547,
|
| 539 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.9315068493150684,
|
| 540 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.9066666666666666,
|
| 541 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.9044117647058824,
|
| 542 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 482.9535827636719,
|
| 543 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.910689468531078,
|
| 544 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.912751677852349,
|
| 545 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 527.540771484375,
|
| 546 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.918918918918919,
|
| 547 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.9066666666666666,
|
| 548 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.9117647058823529,
|
| 549 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 482.9535827636719,
|
| 550 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.9219827879602106,
|
| 551 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.918918918918919,
|
| 552 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 527.540771484375,
|
| 553 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.9565217391304348,
|
| 554 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.9066666666666666,
|
| 555 |
+
"eval_loss": 2.0955376625061035,
|
| 556 |
+
"eval_runtime": 20.4117,
|
| 557 |
+
"eval_samples_per_second": 6.663,
|
| 558 |
+
"eval_steps_per_second": 0.833,
|
| 559 |
+
"step": 748
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 12.0,
|
| 563 |
+
"grad_norm": 0.3338662087917328,
|
| 564 |
+
"learning_rate": 1.7106918238993712e-06,
|
| 565 |
+
"loss": 0.1507,
|
| 566 |
+
"step": 816
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 12.0,
|
| 570 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.9044117647058824,
|
| 571 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.5501536726951599,
|
| 572 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.9084179566135925,
|
| 573 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.912751677852349,
|
| 574 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.4790937304496765,
|
| 575 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.918918918918919,
|
| 576 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.9066666666666666,
|
| 577 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.9117647058823529,
|
| 578 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 294.13421630859375,
|
| 579 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.915716305189008,
|
| 580 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.9166666666666666,
|
| 581 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 294.13421630859375,
|
| 582 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.9565217391304348,
|
| 583 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.88,
|
| 584 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.9117647058823529,
|
| 585 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 23.818954467773438,
|
| 586 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.9093211275077335,
|
| 587 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.918918918918919,
|
| 588 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 23.818954467773438,
|
| 589 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.9315068493150684,
|
| 590 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.9066666666666666,
|
| 591 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.9044117647058824,
|
| 592 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 482.6566162109375,
|
| 593 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.9104676924615509,
|
| 594 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.913907284768212,
|
| 595 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 532.9744262695312,
|
| 596 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.9078947368421053,
|
| 597 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.92,
|
| 598 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.9117647058823529,
|
| 599 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 482.6566162109375,
|
| 600 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.915716305189008,
|
| 601 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.918918918918919,
|
| 602 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 532.9744262695312,
|
| 603 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.9565217391304348,
|
| 604 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.92,
|
| 605 |
+
"eval_loss": 2.2124059200286865,
|
| 606 |
+
"eval_runtime": 20.6137,
|
| 607 |
+
"eval_samples_per_second": 6.598,
|
| 608 |
+
"eval_steps_per_second": 0.825,
|
| 609 |
+
"step": 816
|
| 610 |
+
}
|
| 611 |
+
],
|
| 612 |
+
"logging_steps": 500,
|
| 613 |
+
"max_steps": 884,
|
| 614 |
+
"num_input_tokens_seen": 0,
|
| 615 |
+
"num_train_epochs": 13,
|
| 616 |
+
"save_steps": 100,
|
| 617 |
+
"stateful_callbacks": {
|
| 618 |
+
"TrainerControl": {
|
| 619 |
+
"args": {
|
| 620 |
+
"should_epoch_stop": false,
|
| 621 |
+
"should_evaluate": false,
|
| 622 |
+
"should_log": false,
|
| 623 |
+
"should_save": true,
|
| 624 |
+
"should_training_stop": false
|
| 625 |
+
},
|
| 626 |
+
"attributes": {}
|
| 627 |
+
}
|
| 628 |
+
},
|
| 629 |
+
"total_flos": 0.0,
|
| 630 |
+
"train_batch_size": 8,
|
| 631 |
+
"trial_name": null,
|
| 632 |
+
"trial_params": null
|
| 633 |
+
}
|
checkpoint-816/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb4f571730ddebdbfd409aa41c36173377c8d33a0e18444875f0d792c4278e37
|
| 3 |
+
size 5432
|
checkpoint-884/1_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 |
+
}
|
checkpoint-884/README.md
ADDED
|
@@ -0,0 +1,590 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: colorfulscoop/sbert-base-ja
|
| 3 |
+
library_name: sentence-transformers
|
| 4 |
+
metrics:
|
| 5 |
+
- cosine_accuracy
|
| 6 |
+
- cosine_accuracy_threshold
|
| 7 |
+
- cosine_f1
|
| 8 |
+
- cosine_f1_threshold
|
| 9 |
+
- cosine_precision
|
| 10 |
+
- cosine_recall
|
| 11 |
+
- cosine_ap
|
| 12 |
+
- dot_accuracy
|
| 13 |
+
- dot_accuracy_threshold
|
| 14 |
+
- dot_f1
|
| 15 |
+
- dot_f1_threshold
|
| 16 |
+
- dot_precision
|
| 17 |
+
- dot_recall
|
| 18 |
+
- dot_ap
|
| 19 |
+
- manhattan_accuracy
|
| 20 |
+
- manhattan_accuracy_threshold
|
| 21 |
+
- manhattan_f1
|
| 22 |
+
- manhattan_f1_threshold
|
| 23 |
+
- manhattan_precision
|
| 24 |
+
- manhattan_recall
|
| 25 |
+
- manhattan_ap
|
| 26 |
+
- euclidean_accuracy
|
| 27 |
+
- euclidean_accuracy_threshold
|
| 28 |
+
- euclidean_f1
|
| 29 |
+
- euclidean_f1_threshold
|
| 30 |
+
- euclidean_precision
|
| 31 |
+
- euclidean_recall
|
| 32 |
+
- euclidean_ap
|
| 33 |
+
- max_accuracy
|
| 34 |
+
- max_accuracy_threshold
|
| 35 |
+
- max_f1
|
| 36 |
+
- max_f1_threshold
|
| 37 |
+
- max_precision
|
| 38 |
+
- max_recall
|
| 39 |
+
- max_ap
|
| 40 |
+
pipeline_tag: sentence-similarity
|
| 41 |
+
tags:
|
| 42 |
+
- sentence-transformers
|
| 43 |
+
- sentence-similarity
|
| 44 |
+
- feature-extraction
|
| 45 |
+
- generated_from_trainer
|
| 46 |
+
- dataset_size:680
|
| 47 |
+
- loss:CoSENTLoss
|
| 48 |
+
widget:
|
| 49 |
+
- source_sentence: 中を見てみよう
|
| 50 |
+
sentences:
|
| 51 |
+
- 外を調べよう
|
| 52 |
+
- リリアンはどんな魔法が使えるの？
|
| 53 |
+
- 花がぬいぐるみに変えられている
|
| 54 |
+
- source_sentence: キャンドル要らない
|
| 55 |
+
sentences:
|
| 56 |
+
- なんで猫が話せる？
|
| 57 |
+
- 自分でやれば？
|
| 58 |
+
- 中を見てみよう
|
| 59 |
+
- source_sentence: 信用できない
|
| 60 |
+
sentences:
|
| 61 |
+
- どっちでもいいよ
|
| 62 |
+
- 誰？
|
| 63 |
+
- 誰かが呪文で花をぬいぐるみに変えた
|
| 64 |
+
- source_sentence: 例えば？
|
| 65 |
+
sentences:
|
| 66 |
+
- 誰かがが魔法をかけた
|
| 67 |
+
- ジャック
|
| 68 |
+
- なんでしなきゃいけないの？
|
| 69 |
+
- source_sentence: 魔法を使える人
|
| 70 |
+
sentences:
|
| 71 |
+
- かっこいいね
|
| 72 |
+
- 物の姿を変えられる人
|
| 73 |
+
- 町って？
|
| 74 |
+
model-index:
|
| 75 |
+
- name: SentenceTransformer based on colorfulscoop/sbert-base-ja
|
| 76 |
+
results:
|
| 77 |
+
- task:
|
| 78 |
+
type: binary-classification
|
| 79 |
+
name: Binary Classification
|
| 80 |
+
dataset:
|
| 81 |
+
name: custom arc semantics data jp
|
| 82 |
+
type: custom-arc-semantics-data-jp
|
| 83 |
+
metrics:
|
| 84 |
+
- type: cosine_accuracy
|
| 85 |
+
value: 0.9044117647058824
|
| 86 |
+
name: Cosine Accuracy
|
| 87 |
+
- type: cosine_accuracy_threshold
|
| 88 |
+
value: 0.5485918521881104
|
| 89 |
+
name: Cosine Accuracy Threshold
|
| 90 |
+
- type: cosine_f1
|
| 91 |
+
value: 0.912751677852349
|
| 92 |
+
name: Cosine F1
|
| 93 |
+
- type: cosine_f1_threshold
|
| 94 |
+
value: 0.47659817337989807
|
| 95 |
+
name: Cosine F1 Threshold
|
| 96 |
+
- type: cosine_precision
|
| 97 |
+
value: 0.918918918918919
|
| 98 |
+
name: Cosine Precision
|
| 99 |
+
- type: cosine_recall
|
| 100 |
+
value: 0.9066666666666666
|
| 101 |
+
name: Cosine Recall
|
| 102 |
+
- type: cosine_ap
|
| 103 |
+
value: 0.9088999169341241
|
| 104 |
+
name: Cosine Ap
|
| 105 |
+
- type: dot_accuracy
|
| 106 |
+
value: 0.9117647058823529
|
| 107 |
+
name: Dot Accuracy
|
| 108 |
+
- type: dot_accuracy_threshold
|
| 109 |
+
value: 293.22845458984375
|
| 110 |
+
name: Dot Accuracy Threshold
|
| 111 |
+
- type: dot_f1
|
| 112 |
+
value: 0.9166666666666666
|
| 113 |
+
name: Dot F1
|
| 114 |
+
- type: dot_f1_threshold
|
| 115 |
+
value: 293.22845458984375
|
| 116 |
+
name: Dot F1 Threshold
|
| 117 |
+
- type: dot_precision
|
| 118 |
+
value: 0.9565217391304348
|
| 119 |
+
name: Dot Precision
|
| 120 |
+
- type: dot_recall
|
| 121 |
+
value: 0.88
|
| 122 |
+
name: Dot Recall
|
| 123 |
+
- type: dot_ap
|
| 124 |
+
value: 0.9171086358892895
|
| 125 |
+
name: Dot Ap
|
| 126 |
+
- type: manhattan_accuracy
|
| 127 |
+
value: 0.9117647058823529
|
| 128 |
+
name: Manhattan Accuracy
|
| 129 |
+
- type: manhattan_accuracy_threshold
|
| 130 |
+
value: 524.0676879882812
|
| 131 |
+
name: Manhattan Accuracy Threshold
|
| 132 |
+
- type: manhattan_f1
|
| 133 |
+
value: 0.918918918918919
|
| 134 |
+
name: Manhattan F1
|
| 135 |
+
- type: manhattan_f1_threshold
|
| 136 |
+
value: 524.0676879882812
|
| 137 |
+
name: Manhattan F1 Threshold
|
| 138 |
+
- type: manhattan_precision
|
| 139 |
+
value: 0.9315068493150684
|
| 140 |
+
name: Manhattan Precision
|
| 141 |
+
- type: manhattan_recall
|
| 142 |
+
value: 0.9066666666666666
|
| 143 |
+
name: Manhattan Recall
|
| 144 |
+
- type: manhattan_ap
|
| 145 |
+
value: 0.9111567321590129
|
| 146 |
+
name: Manhattan Ap
|
| 147 |
+
- type: euclidean_accuracy
|
| 148 |
+
value: 0.9117647058823529
|
| 149 |
+
name: Euclidean Accuracy
|
| 150 |
+
- type: euclidean_accuracy_threshold
|
| 151 |
+
value: 23.82940673828125
|
| 152 |
+
name: Euclidean Accuracy Threshold
|
| 153 |
+
- type: euclidean_f1
|
| 154 |
+
value: 0.918918918918919
|
| 155 |
+
name: Euclidean F1
|
| 156 |
+
- type: euclidean_f1_threshold
|
| 157 |
+
value: 23.82940673828125
|
| 158 |
+
name: Euclidean F1 Threshold
|
| 159 |
+
- type: euclidean_precision
|
| 160 |
+
value: 0.9315068493150684
|
| 161 |
+
name: Euclidean Precision
|
| 162 |
+
- type: euclidean_recall
|
| 163 |
+
value: 0.9066666666666666
|
| 164 |
+
name: Euclidean Recall
|
| 165 |
+
- type: euclidean_ap
|
| 166 |
+
value: 0.9094221163568814
|
| 167 |
+
name: Euclidean Ap
|
| 168 |
+
- type: max_accuracy
|
| 169 |
+
value: 0.9117647058823529
|
| 170 |
+
name: Max Accuracy
|
| 171 |
+
- type: max_accuracy_threshold
|
| 172 |
+
value: 524.0676879882812
|
| 173 |
+
name: Max Accuracy Threshold
|
| 174 |
+
- type: max_f1
|
| 175 |
+
value: 0.918918918918919
|
| 176 |
+
name: Max F1
|
| 177 |
+
- type: max_f1_threshold
|
| 178 |
+
value: 524.0676879882812
|
| 179 |
+
name: Max F1 Threshold
|
| 180 |
+
- type: max_precision
|
| 181 |
+
value: 0.9565217391304348
|
| 182 |
+
name: Max Precision
|
| 183 |
+
- type: max_recall
|
| 184 |
+
value: 0.9066666666666666
|
| 185 |
+
name: Max Recall
|
| 186 |
+
- type: max_ap
|
| 187 |
+
value: 0.9171086358892895
|
| 188 |
+
name: Max Ap
|
| 189 |
+
---
|
| 190 |
+
|
| 191 |
+
# SentenceTransformer based on colorfulscoop/sbert-base-ja
|
| 192 |
+
|
| 193 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [colorfulscoop/sbert-base-ja](https://huggingface.co/colorfulscoop/sbert-base-ja) on the csv dataset. 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.
|
| 194 |
+
|
| 195 |
+
## Model Details
|
| 196 |
+
|
| 197 |
+
### Model Description
|
| 198 |
+
- **Model Type:** Sentence Transformer
|
| 199 |
+
- **Base model:** [colorfulscoop/sbert-base-ja](https://huggingface.co/colorfulscoop/sbert-base-ja) <!-- at revision ecb8a98cd5176719ff7ab0d770a27420118732cf -->
|
| 200 |
+
- **Maximum Sequence Length:** 512 tokens
|
| 201 |
+
- **Output Dimensionality:** 768 tokens
|
| 202 |
+
- **Similarity Function:** Cosine Similarity
|
| 203 |
+
- **Training Dataset:**
|
| 204 |
+
- csv
|
| 205 |
+
<!-- - **Language:** Unknown -->
|
| 206 |
+
<!-- - **License:** Unknown -->
|
| 207 |
+
|
| 208 |
+
### Model Sources
|
| 209 |
+
|
| 210 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
| 211 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
| 212 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
| 213 |
+
|
| 214 |
+
### Full Model Architecture
|
| 215 |
+
|
| 216 |
+
```
|
| 217 |
+
SentenceTransformer(
|
| 218 |
+
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
|
| 219 |
+
(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})
|
| 220 |
+
)
|
| 221 |
+
```
|
| 222 |
+
|
| 223 |
+
## Usage
|
| 224 |
+
|
| 225 |
+
### Direct Usage (Sentence Transformers)
|
| 226 |
+
|
| 227 |
+
First install the Sentence Transformers library:
|
| 228 |
+
|
| 229 |
+
```bash
|
| 230 |
+
pip install -U sentence-transformers
|
| 231 |
+
```
|
| 232 |
+
|
| 233 |
+
Then you can load this model and run inference.
|
| 234 |
+
```python
|
| 235 |
+
from sentence_transformers import SentenceTransformer
|
| 236 |
+
|
| 237 |
+
# Download from the 🤗 Hub
|
| 238 |
+
model = SentenceTransformer("sentence_transformers_model_id")
|
| 239 |
+
# Run inference
|
| 240 |
+
sentences = [
|
| 241 |
+
'魔法を使える人',
|
| 242 |
+
'物の姿を変えられる人',
|
| 243 |
+
'かっこいいね',
|
| 244 |
+
]
|
| 245 |
+
embeddings = model.encode(sentences)
|
| 246 |
+
print(embeddings.shape)
|
| 247 |
+
# [3, 768]
|
| 248 |
+
|
| 249 |
+
# Get the similarity scores for the embeddings
|
| 250 |
+
similarities = model.similarity(embeddings, embeddings)
|
| 251 |
+
print(similarities.shape)
|
| 252 |
+
# [3, 3]
|
| 253 |
+
```
|
| 254 |
+
|
| 255 |
+
<!--
|
| 256 |
+
### Direct Usage (Transformers)
|
| 257 |
+
|
| 258 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
| 259 |
+
|
| 260 |
+
</details>
|
| 261 |
+
-->
|
| 262 |
+
|
| 263 |
+
<!--
|
| 264 |
+
### Downstream Usage (Sentence Transformers)
|
| 265 |
+
|
| 266 |
+
You can finetune this model on your own dataset.
|
| 267 |
+
|
| 268 |
+
<details><summary>Click to expand</summary>
|
| 269 |
+
|
| 270 |
+
</details>
|
| 271 |
+
-->
|
| 272 |
+
|
| 273 |
+
<!--
|
| 274 |
+
### Out-of-Scope Use
|
| 275 |
+
|
| 276 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
| 277 |
+
-->
|
| 278 |
+
|
| 279 |
+
## Evaluation
|
| 280 |
+
|
| 281 |
+
### Metrics
|
| 282 |
+
|
| 283 |
+
#### Binary Classification
|
| 284 |
+
* Dataset: `custom-arc-semantics-data-jp`
|
| 285 |
+
* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
|
| 286 |
+
|
| 287 |
+
| Metric | Value |
|
| 288 |
+
|:-----------------------------|:-----------|
|
| 289 |
+
| cosine_accuracy | 0.9044 |
|
| 290 |
+
| cosine_accuracy_threshold | 0.5486 |
|
| 291 |
+
| cosine_f1 | 0.9128 |
|
| 292 |
+
| cosine_f1_threshold | 0.4766 |
|
| 293 |
+
| cosine_precision | 0.9189 |
|
| 294 |
+
| cosine_recall | 0.9067 |
|
| 295 |
+
| cosine_ap | 0.9089 |
|
| 296 |
+
| dot_accuracy | 0.9118 |
|
| 297 |
+
| dot_accuracy_threshold | 293.2285 |
|
| 298 |
+
| dot_f1 | 0.9167 |
|
| 299 |
+
| dot_f1_threshold | 293.2285 |
|
| 300 |
+
| dot_precision | 0.9565 |
|
| 301 |
+
| dot_recall | 0.88 |
|
| 302 |
+
| dot_ap | 0.9171 |
|
| 303 |
+
| manhattan_accuracy | 0.9118 |
|
| 304 |
+
| manhattan_accuracy_threshold | 524.0677 |
|
| 305 |
+
| manhattan_f1 | 0.9189 |
|
| 306 |
+
| manhattan_f1_threshold | 524.0677 |
|
| 307 |
+
| manhattan_precision | 0.9315 |
|
| 308 |
+
| manhattan_recall | 0.9067 |
|
| 309 |
+
| manhattan_ap | 0.9112 |
|
| 310 |
+
| euclidean_accuracy | 0.9118 |
|
| 311 |
+
| euclidean_accuracy_threshold | 23.8294 |
|
| 312 |
+
| euclidean_f1 | 0.9189 |
|
| 313 |
+
| euclidean_f1_threshold | 23.8294 |
|
| 314 |
+
| euclidean_precision | 0.9315 |
|
| 315 |
+
| euclidean_recall | 0.9067 |
|
| 316 |
+
| euclidean_ap | 0.9094 |
|
| 317 |
+
| max_accuracy | 0.9118 |
|
| 318 |
+
| max_accuracy_threshold | 524.0677 |
|
| 319 |
+
| max_f1 | 0.9189 |
|
| 320 |
+
| max_f1_threshold | 524.0677 |
|
| 321 |
+
| max_precision | 0.9565 |
|
| 322 |
+
| max_recall | 0.9067 |
|
| 323 |
+
| **max_ap** | **0.9171** |
|
| 324 |
+
|
| 325 |
+
<!--
|
| 326 |
+
## Bias, Risks and Limitations
|
| 327 |
+
|
| 328 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
| 329 |
+
-->
|
| 330 |
+
|
| 331 |
+
<!--
|
| 332 |
+
### Recommendations
|
| 333 |
+
|
| 334 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
| 335 |
+
-->
|
| 336 |
+
|
| 337 |
+
## Training Details
|
| 338 |
+
|
| 339 |
+
### Training Dataset
|
| 340 |
+
|
| 341 |
+
#### csv
|
| 342 |
+
|
| 343 |
+
* Dataset: csv
|
| 344 |
+
* Size: 680 training samples
|
| 345 |
+
* Columns: <code>text1</code>, <code>text2</code>, and <code>label</code>
|
| 346 |
+
* Approximate statistics based on the first 680 samples:
|
| 347 |
+
| | text1 | text2 | label |
|
| 348 |
+
|:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:------------------------------------------------|
|
| 349 |
+
| type | string | string | int |
|
| 350 |
+
| details | <ul><li>min: 4 tokens</li><li>mean: 8.29 tokens</li><li>max: 15 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 7.97 tokens</li><li>max: 14 tokens</li></ul> | <ul><li>0: ~40.44%</li><li>1: ~59.56%</li></ul> |
|
| 351 |
+
* Samples:
|
| 352 |
+
| text1 | text2 | label |
|
| 353 |
+
|:----------------------------|:----------------------------|:---------------|
|
| 354 |
+
| <code>いらない</code> | <code>うんよろしく</code> | <code>0</code> |
|
| 355 |
+
| <code>足元よりも更に深くってどこ？</code> | <code>足元よりも更に深くってなに？</code> | <code>1</code> |
|
| 356 |
+
| <code>他にはないの？</code> | <code>どう思う？</code> | <code>0</code> |
|
| 357 |
+
* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
|
| 358 |
+
```json
|
| 359 |
+
{
|
| 360 |
+
"scale": 20.0,
|
| 361 |
+
"similarity_fct": "pairwise_cos_sim"
|
| 362 |
+
}
|
| 363 |
+
```
|
| 364 |
+
|
| 365 |
+
### Evaluation Dataset
|
| 366 |
+
|
| 367 |
+
#### csv
|
| 368 |
+
|
| 369 |
+
* Dataset: csv
|
| 370 |
+
* Size: 680 evaluation samples
|
| 371 |
+
* Columns: <code>text1</code>, <code>text2</code>, and <code>label</code>
|
| 372 |
+
* Approximate statistics based on the first 680 samples:
|
| 373 |
+
| | text1 | text2 | label |
|
| 374 |
+
|:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:------------------------------------------------|
|
| 375 |
+
| type | string | string | int |
|
| 376 |
+
| details | <ul><li>min: 4 tokens</li><li>mean: 8.32 tokens</li><li>max: 15 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 8.16 tokens</li><li>max: 14 tokens</li></ul> | <ul><li>0: ~44.85%</li><li>1: ~55.15%</li></ul> |
|
| 377 |
+
* Samples:
|
| 378 |
+
| text1 | text2 | label |
|
| 379 |
+
|:-------------------------|:-------------------------|:---------------|
|
| 380 |
+
| <code>井戸から水をくんでいた</code> | <code>井戸を使っていた</code> | <code>1</code> |
|
| 381 |
+
| <code>夕飯は何だったの？</code> | <code>チキンヌードル食べた？</code> | <code>0</code> |
|
| 382 |
+
| <code>水を井戸からくんでいた</code> | <code>夜ごはんの前</code> | <code>0</code> |
|
| 383 |
+
* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
|
| 384 |
+
```json
|
| 385 |
+
{
|
| 386 |
+
"scale": 20.0,
|
| 387 |
+
"similarity_fct": "pairwise_cos_sim"
|
| 388 |
+
}
|
| 389 |
+
```
|
| 390 |
+
|
| 391 |
+
### Training Hyperparameters
|
| 392 |
+
#### Non-Default Hyperparameters
|
| 393 |
+
|
| 394 |
+
- `eval_strategy`: epoch
|
| 395 |
+
- `learning_rate`: 2e-05
|
| 396 |
+
- `num_train_epochs`: 13
|
| 397 |
+
- `warmup_ratio`: 0.1
|
| 398 |
+
- `fp16`: True
|
| 399 |
+
- `batch_sampler`: no_duplicates
|
| 400 |
+
|
| 401 |
+
#### All Hyperparameters
|
| 402 |
+
<details><summary>Click to expand</summary>
|
| 403 |
+
|
| 404 |
+
- `overwrite_output_dir`: False
|
| 405 |
+
- `do_predict`: False
|
| 406 |
+
- `eval_strategy`: epoch
|
| 407 |
+
- `prediction_loss_only`: True
|
| 408 |
+
- `per_device_train_batch_size`: 8
|
| 409 |
+
- `per_device_eval_batch_size`: 8
|
| 410 |
+
- `per_gpu_train_batch_size`: None
|
| 411 |
+
- `per_gpu_eval_batch_size`: None
|
| 412 |
+
- `gradient_accumulation_steps`: 1
|
| 413 |
+
- `eval_accumulation_steps`: None
|
| 414 |
+
- `torch_empty_cache_steps`: None
|
| 415 |
+
- `learning_rate`: 2e-05
|
| 416 |
+
- `weight_decay`: 0.0
|
| 417 |
+
- `adam_beta1`: 0.9
|
| 418 |
+
- `adam_beta2`: 0.999
|
| 419 |
+
- `adam_epsilon`: 1e-08
|
| 420 |
+
- `max_grad_norm`: 1.0
|
| 421 |
+
- `num_train_epochs`: 13
|
| 422 |
+
- `max_steps`: -1
|
| 423 |
+
- `lr_scheduler_type`: linear
|
| 424 |
+
- `lr_scheduler_kwargs`: {}
|
| 425 |
+
- `warmup_ratio`: 0.1
|
| 426 |
+
- `warmup_steps`: 0
|
| 427 |
+
- `log_level`: passive
|
| 428 |
+
- `log_level_replica`: warning
|
| 429 |
+
- `log_on_each_node`: True
|
| 430 |
+
- `logging_nan_inf_filter`: True
|
| 431 |
+
- `save_safetensors`: True
|
| 432 |
+
- `save_on_each_node`: False
|
| 433 |
+
- `save_only_model`: False
|
| 434 |
+
- `restore_callback_states_from_checkpoint`: False
|
| 435 |
+
- `no_cuda`: False
|
| 436 |
+
- `use_cpu`: False
|
| 437 |
+
- `use_mps_device`: False
|
| 438 |
+
- `seed`: 42
|
| 439 |
+
- `data_seed`: None
|
| 440 |
+
- `jit_mode_eval`: False
|
| 441 |
+
- `use_ipex`: False
|
| 442 |
+
- `bf16`: False
|
| 443 |
+
- `fp16`: True
|
| 444 |
+
- `fp16_opt_level`: O1
|
| 445 |
+
- `half_precision_backend`: auto
|
| 446 |
+
- `bf16_full_eval`: False
|
| 447 |
+
- `fp16_full_eval`: False
|
| 448 |
+
- `tf32`: None
|
| 449 |
+
- `local_rank`: 0
|
| 450 |
+
- `ddp_backend`: None
|
| 451 |
+
- `tpu_num_cores`: None
|
| 452 |
+
- `tpu_metrics_debug`: False
|
| 453 |
+
- `debug`: []
|
| 454 |
+
- `dataloader_drop_last`: False
|
| 455 |
+
- `dataloader_num_workers`: 0
|
| 456 |
+
- `dataloader_prefetch_factor`: None
|
| 457 |
+
- `past_index`: -1
|
| 458 |
+
- `disable_tqdm`: False
|
| 459 |
+
- `remove_unused_columns`: True
|
| 460 |
+
- `label_names`: None
|
| 461 |
+
- `load_best_model_at_end`: False
|
| 462 |
+
- `ignore_data_skip`: False
|
| 463 |
+
- `fsdp`: []
|
| 464 |
+
- `fsdp_min_num_params`: 0
|
| 465 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
| 466 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
| 467 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
| 468 |
+
- `deepspeed`: None
|
| 469 |
+
- `label_smoothing_factor`: 0.0
|
| 470 |
+
- `optim`: adamw_torch
|
| 471 |
+
- `optim_args`: None
|
| 472 |
+
- `adafactor`: False
|
| 473 |
+
- `group_by_length`: False
|
| 474 |
+
- `length_column_name`: length
|
| 475 |
+
- `ddp_find_unused_parameters`: None
|
| 476 |
+
- `ddp_bucket_cap_mb`: None
|
| 477 |
+
- `ddp_broadcast_buffers`: False
|
| 478 |
+
- `dataloader_pin_memory`: True
|
| 479 |
+
- `dataloader_persistent_workers`: False
|
| 480 |
+
- `skip_memory_metrics`: True
|
| 481 |
+
- `use_legacy_prediction_loop`: False
|
| 482 |
+
- `push_to_hub`: False
|
| 483 |
+
- `resume_from_checkpoint`: None
|
| 484 |
+
- `hub_model_id`: None
|
| 485 |
+
- `hub_strategy`: every_save
|
| 486 |
+
- `hub_private_repo`: False
|
| 487 |
+
- `hub_always_push`: False
|
| 488 |
+
- `gradient_checkpointing`: False
|
| 489 |
+
- `gradient_checkpointing_kwargs`: None
|
| 490 |
+
- `include_inputs_for_metrics`: False
|
| 491 |
+
- `eval_do_concat_batches`: True
|
| 492 |
+
- `fp16_backend`: auto
|
| 493 |
+
- `push_to_hub_model_id`: None
|
| 494 |
+
- `push_to_hub_organization`: None
|
| 495 |
+
- `mp_parameters`:
|
| 496 |
+
- `auto_find_batch_size`: False
|
| 497 |
+
- `full_determinism`: False
|
| 498 |
+
- `torchdynamo`: None
|
| 499 |
+
- `ray_scope`: last
|
| 500 |
+
- `ddp_timeout`: 1800
|
| 501 |
+
- `torch_compile`: False
|
| 502 |
+
- `torch_compile_backend`: None
|
| 503 |
+
- `torch_compile_mode`: None
|
| 504 |
+
- `dispatch_batches`: None
|
| 505 |
+
- `split_batches`: None
|
| 506 |
+
- `include_tokens_per_second`: False
|
| 507 |
+
- `include_num_input_tokens_seen`: False
|
| 508 |
+
- `neftune_noise_alpha`: None
|
| 509 |
+
- `optim_target_modules`: None
|
| 510 |
+
- `batch_eval_metrics`: False
|
| 511 |
+
- `eval_on_start`: False
|
| 512 |
+
- `eval_use_gather_object`: False
|
| 513 |
+
- `batch_sampler`: no_duplicates
|
| 514 |
+
- `multi_dataset_batch_sampler`: proportional
|
| 515 |
+
|
| 516 |
+
</details>
|
| 517 |
+
|
| 518 |
+
### Training Logs
|
| 519 |
+
| Epoch | Step | Training Loss | loss | custom-arc-semantics-data-jp_max_ap |
|
| 520 |
+
|:-----:|:----:|:-------------:|:------:|:-----------------------------------:|
|
| 521 |
+
| None | 0 | - | - | 0.8596 |
|
| 522 |
+
| 1.0 | 68 | 2.6802 | 1.7807 | 0.8872 |
|
| 523 |
+
| 2.0 | 136 | 1.4014 | 1.7683 | 0.8945 |
|
| 524 |
+
| 3.0 | 204 | 0.7937 | 1.9877 | 0.9039 |
|
| 525 |
+
| 4.0 | 272 | 0.5443 | 1.9106 | 0.9075 |
|
| 526 |
+
| 5.0 | 340 | 0.4225 | 1.9418 | 0.9109 |
|
| 527 |
+
| 6.0 | 408 | 0.3347 | 2.0123 | 0.9107 |
|
| 528 |
+
| 7.0 | 476 | 0.3425 | 2.0387 | 0.9094 |
|
| 529 |
+
| 8.0 | 544 | 0.2427 | 1.9878 | 0.9103 |
|
| 530 |
+
| 9.0 | 612 | 0.2412 | 2.0424 | 0.9178 |
|
| 531 |
+
| 10.0 | 680 | 0.1623 | 2.0273 | 0.9188 |
|
| 532 |
+
| 11.0 | 748 | 0.1909 | 2.0955 | 0.9220 |
|
| 533 |
+
| 12.0 | 816 | 0.1507 | 2.2124 | 0.9157 |
|
| 534 |
+
| 13.0 | 884 | 0.1406 | 2.2126 | 0.9171 |
|
| 535 |
+
|
| 536 |
+
|
| 537 |
+
### Framework Versions
|
| 538 |
+
- Python: 3.10.14
|
| 539 |
+
- Sentence Transformers: 3.1.0
|
| 540 |
+
- Transformers: 4.44.2
|
| 541 |
+
- PyTorch: 2.4.1+cu121
|
| 542 |
+
- Accelerate: 0.34.2
|
| 543 |
+
- Datasets: 2.20.0
|
| 544 |
+
- Tokenizers: 0.19.1
|
| 545 |
+
|
| 546 |
+
## Citation
|
| 547 |
+
|
| 548 |
+
### BibTeX
|
| 549 |
+
|
| 550 |
+
#### Sentence Transformers
|
| 551 |
+
```bibtex
|
| 552 |
+
@inproceedings{reimers-2019-sentence-bert,
|
| 553 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
| 554 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
| 555 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
| 556 |
+
month = "11",
|
| 557 |
+
year = "2019",
|
| 558 |
+
publisher = "Association for Computational Linguistics",
|
| 559 |
+
url = "https://arxiv.org/abs/1908.10084",
|
| 560 |
+
}
|
| 561 |
+
```
|
| 562 |
+
|
| 563 |
+
#### CoSENTLoss
|
| 564 |
+
```bibtex
|
| 565 |
+
@online{kexuefm-8847,
|
| 566 |
+
title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
|
| 567 |
+
author={Su Jianlin},
|
| 568 |
+
year={2022},
|
| 569 |
+
month={Jan},
|
| 570 |
+
url={https://kexue.fm/archives/8847},
|
| 571 |
+
}
|
| 572 |
+
```
|
| 573 |
+
|
| 574 |
+
<!--
|
| 575 |
+
## Glossary
|
| 576 |
+
|
| 577 |
+
*Clearly define terms in order to be accessible across audiences.*
|
| 578 |
+
-->
|
| 579 |
+
|
| 580 |
+
<!--
|
| 581 |
+
## Model Card Authors
|
| 582 |
+
|
| 583 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
| 584 |
+
-->
|
| 585 |
+
|
| 586 |
+
<!--
|
| 587 |
+
## Model Card Contact
|
| 588 |
+
|
| 589 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
| 590 |
+
-->
|
checkpoint-884/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 32000
|
| 3 |
+
}
|
checkpoint-884/config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "colorfulscoop/sbert-base-ja",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertModel"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 2,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"cls_token_id": 2,
|
| 10 |
+
"eos_token_id": 3,
|
| 11 |
+
"gradient_checkpointing": false,
|
| 12 |
+
"hidden_act": "gelu",
|
| 13 |
+
"hidden_dropout_prob": 0.1,
|
| 14 |
+
"hidden_size": 768,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 3072,
|
| 17 |
+
"layer_norm_eps": 1e-12,
|
| 18 |
+
"mask_token_id": 4,
|
| 19 |
+
"max_position_embeddings": 512,
|
| 20 |
+
"model_type": "bert",
|
| 21 |
+
"num_attention_heads": 12,
|
| 22 |
+
"num_hidden_layers": 12,
|
| 23 |
+
"pad_token_id": 0,
|
| 24 |
+
"position_embedding_type": "absolute",
|
| 25 |
+
"sep_token_id": 3,
|
| 26 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.44.2",
|
| 29 |
+
"type_vocab_size": 2,
|
| 30 |
+
"unk_token_id": 1,
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 32000
|
| 33 |
+
}
|
checkpoint-884/config_sentence_transformers.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"__version__": {
|
| 3 |
+
"sentence_transformers": "3.1.0",
|
| 4 |
+
"transformers": "4.44.2",
|
| 5 |
+
"pytorch": "2.4.1+cu121"
|
| 6 |
+
},
|
| 7 |
+
"prompts": {},
|
| 8 |
+
"default_prompt_name": null,
|
| 9 |
+
"similarity_fn_name": null
|
| 10 |
+
}
|
checkpoint-884/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ea971648a5f2a8763054e8e39824b1f5acc795ea1e4e11c3565210e0f89f56c
|
| 3 |
+
size 442491744
|
checkpoint-884/modules.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
]
|
checkpoint-884/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0d46a15c28464cd9937ebba27b97d8e74d87d66ef07628f0b7444366fa0c673
|
| 3 |
+
size 880373306
|
checkpoint-884/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:acb7f3930feaeca11a54945463fe298db1ad6a0449ea14aa24e77a866f871390
|
| 3 |
+
size 13990
|
checkpoint-884/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:472e7088b090d418cf1a50a3ea1f58423524f7b2af2e0abb5273be0d15b293f0
|
| 3 |
+
size 1064
|
checkpoint-884/sentence_bert_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"max_seq_length": 512,
|
| 3 |
+
"do_lower_case": false
|
| 4 |
+
}
|
checkpoint-884/special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "[SEP]",
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"pad_token": "<pad>",
|
| 7 |
+
"sep_token": "[SEP]",
|
| 8 |
+
"unk_token": {
|
| 9 |
+
"content": "<unk>",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": true,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
}
|
| 15 |
+
}
|
checkpoint-884/spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6467857b4b0c77ded9bac7ad2fb5c16eb64e17e417ce46624dacac2bbb404fc
|
| 3 |
+
size 802713
|
checkpoint-884/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-884/tokenizer_config.json
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<pad>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<unk>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": true,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": false
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": false
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": false
|
| 42 |
+
},
|
| 43 |
+
"32000": {
|
| 44 |
+
"content": "[PAD]",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": true,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": false
|
| 50 |
+
}
|
| 51 |
+
},
|
| 52 |
+
"bos_token": "[CLS]",
|
| 53 |
+
"clean_up_tokenization_spaces": true,
|
| 54 |
+
"cls_token": "[CLS]",
|
| 55 |
+
"do_lower_case": false,
|
| 56 |
+
"eos_token": "[SEP]",
|
| 57 |
+
"mask_token": "[MASK]",
|
| 58 |
+
"model_max_length": 512,
|
| 59 |
+
"pad_token": "<pad>",
|
| 60 |
+
"sep_token": "[SEP]",
|
| 61 |
+
"sp_model_kwargs": {},
|
| 62 |
+
"split_by_punct": false,
|
| 63 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 64 |
+
"unk_token": "<unk>"
|
| 65 |
+
}
|
checkpoint-884/trainer_state.json
ADDED
|
@@ -0,0 +1,683 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 13.0,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 884,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"grad_norm": 37.9459228515625,
|
| 14 |
+
"learning_rate": 1.5280898876404495e-05,
|
| 15 |
+
"loss": 2.6802,
|
| 16 |
+
"step": 68
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.8529411764705882,
|
| 21 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.7407679557800293,
|
| 22 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.8861687056931384,
|
| 23 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.863013698630137,
|
| 24 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.7407679557800293,
|
| 25 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.8873239436619719,
|
| 26 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.84,
|
| 27 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.8529411764705882,
|
| 28 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 413.34197998046875,
|
| 29 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.887218522968793,
|
| 30 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.8648648648648648,
|
| 31 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 413.34197998046875,
|
| 32 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.8767123287671232,
|
| 33 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.8533333333333334,
|
| 34 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.8602941176470589,
|
| 35 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 17.441856384277344,
|
| 36 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.8855166425710176,
|
| 37 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.87248322147651,
|
| 38 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 17.441856384277344,
|
| 39 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.8783783783783784,
|
| 40 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.8666666666666667,
|
| 41 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.8602941176470589,
|
| 42 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 382.9211730957031,
|
| 43 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.8854876210985647,
|
| 44 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.8741721854304636,
|
| 45 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 386.8717956542969,
|
| 46 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.868421052631579,
|
| 47 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.88,
|
| 48 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.8602941176470589,
|
| 49 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 413.34197998046875,
|
| 50 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.887218522968793,
|
| 51 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.8741721854304636,
|
| 52 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 413.34197998046875,
|
| 53 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.8873239436619719,
|
| 54 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.88,
|
| 55 |
+
"eval_loss": 1.7807204723358154,
|
| 56 |
+
"eval_runtime": 14.8133,
|
| 57 |
+
"eval_samples_per_second": 9.181,
|
| 58 |
+
"eval_steps_per_second": 1.148,
|
| 59 |
+
"step": 68
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 2.0,
|
| 63 |
+
"grad_norm": 101.59432983398438,
|
| 64 |
+
"learning_rate": 1.8817610062893082e-05,
|
| 65 |
+
"loss": 1.4014,
|
| 66 |
+
"step": 136
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 2.0,
|
| 70 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.8676470588235294,
|
| 71 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.656826376914978,
|
| 72 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.894049495028942,
|
| 73 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.8783783783783784,
|
| 74 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.656826376914978,
|
| 75 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.8904109589041096,
|
| 76 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.8666666666666667,
|
| 77 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.8602941176470589,
|
| 78 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 367.9239501953125,
|
| 79 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.8915744113817081,
|
| 80 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.87248322147651,
|
| 81 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 363.2611999511719,
|
| 82 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.8783783783783784,
|
| 83 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.8666666666666667,
|
| 84 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.8602941176470589,
|
| 85 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 19.78958511352539,
|
| 86 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.8925974243856872,
|
| 87 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.8819875776397516,
|
| 88 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 20.95208740234375,
|
| 89 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.8255813953488372,
|
| 90 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.9466666666666667,
|
| 91 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.875,
|
| 92 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 456.61602783203125,
|
| 93 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.8944639878933996,
|
| 94 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.8930817610062893,
|
| 95 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 456.61602783203125,
|
| 96 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.8452380952380952,
|
| 97 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.9466666666666667,
|
| 98 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.875,
|
| 99 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 456.61602783203125,
|
| 100 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.8944639878933996,
|
| 101 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.8930817610062893,
|
| 102 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 456.61602783203125,
|
| 103 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.8904109589041096,
|
| 104 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.9466666666666667,
|
| 105 |
+
"eval_loss": 1.7683357000350952,
|
| 106 |
+
"eval_runtime": 13.9834,
|
| 107 |
+
"eval_samples_per_second": 9.726,
|
| 108 |
+
"eval_steps_per_second": 1.216,
|
| 109 |
+
"step": 136
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 3.0,
|
| 113 |
+
"grad_norm": 102.5489730834961,
|
| 114 |
+
"learning_rate": 1.7106918238993714e-05,
|
| 115 |
+
"loss": 0.7937,
|
| 116 |
+
"step": 204
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 3.0,
|
| 120 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.8897058823529411,
|
| 121 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.5597226619720459,
|
| 122 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.9038906301326961,
|
| 123 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.9006622516556291,
|
| 124 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.5076813697814941,
|
| 125 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.8947368421052632,
|
| 126 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.9066666666666666,
|
| 127 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.8823529411764706,
|
| 128 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 314.1024475097656,
|
| 129 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.9012158574599884,
|
| 130 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.8904109589041095,
|
| 131 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 295.25762939453125,
|
| 132 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.9154929577464789,
|
| 133 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.8666666666666667,
|
| 134 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.8970588235294118,
|
| 135 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 22.511234283447266,
|
| 136 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.9033993255493061,
|
| 137 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.9054054054054055,
|
| 138 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 22.511234283447266,
|
| 139 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.9178082191780822,
|
| 140 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.8933333333333333,
|
| 141 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.8897058823529411,
|
| 142 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 480.63677978515625,
|
| 143 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.9033851155012284,
|
| 144 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.8993288590604026,
|
| 145 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 502.66156005859375,
|
| 146 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.9054054054054054,
|
| 147 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.8933333333333333,
|
| 148 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.8970588235294118,
|
| 149 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 480.63677978515625,
|
| 150 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.9038906301326961,
|
| 151 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.9054054054054055,
|
| 152 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 502.66156005859375,
|
| 153 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.9178082191780822,
|
| 154 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.9066666666666666,
|
| 155 |
+
"eval_loss": 1.9876813888549805,
|
| 156 |
+
"eval_runtime": 15.0797,
|
| 157 |
+
"eval_samples_per_second": 9.019,
|
| 158 |
+
"eval_steps_per_second": 1.127,
|
| 159 |
+
"step": 204
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 4.0,
|
| 163 |
+
"grad_norm": 54.64971160888672,
|
| 164 |
+
"learning_rate": 1.539622641509434e-05,
|
| 165 |
+
"loss": 0.5443,
|
| 166 |
+
"step": 272
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 4.0,
|
| 170 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.9117647058823529,
|
| 171 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.5411365032196045,
|
| 172 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.9075251070302803,
|
| 173 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.918918918918919,
|
| 174 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.5411365032196045,
|
| 175 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.9315068493150684,
|
| 176 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.9066666666666666,
|
| 177 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.8897058823529411,
|
| 178 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 311.26678466796875,
|
| 179 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.9040853015076152,
|
| 180 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.9006622516556291,
|
| 181 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 285.96728515625,
|
| 182 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.8947368421052632,
|
| 183 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.9066666666666666,
|
| 184 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.9117647058823529,
|
| 185 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 22.630477905273438,
|
| 186 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.906411643380887,
|
| 187 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.918918918918919,
|
| 188 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 22.630477905273438,
|
| 189 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.9315068493150684,
|
| 190 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.9066666666666666,
|
| 191 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.9117647058823529,
|
| 192 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 495.93194580078125,
|
| 193 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.9068108312799359,
|
| 194 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.918918918918919,
|
| 195 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 495.93194580078125,
|
| 196 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.9315068493150684,
|
| 197 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.9066666666666666,
|
| 198 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.9117647058823529,
|
| 199 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 495.93194580078125,
|
| 200 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.9075251070302803,
|
| 201 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.918918918918919,
|
| 202 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 495.93194580078125,
|
| 203 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.9315068493150684,
|
| 204 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.9066666666666666,
|
| 205 |
+
"eval_loss": 1.910571813583374,
|
| 206 |
+
"eval_runtime": 14.3178,
|
| 207 |
+
"eval_samples_per_second": 9.499,
|
| 208 |
+
"eval_steps_per_second": 1.187,
|
| 209 |
+
"step": 272
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 5.0,
|
| 213 |
+
"grad_norm": 7.771420955657959,
|
| 214 |
+
"learning_rate": 1.368553459119497e-05,
|
| 215 |
+
"loss": 0.4225,
|
| 216 |
+
"step": 340
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 5.0,
|
| 220 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.9117647058823529,
|
| 221 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.5279971361160278,
|
| 222 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.9104573720737034,
|
| 223 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.918918918918919,
|
| 224 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.5279971361160278,
|
| 225 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.9315068493150684,
|
| 226 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.9066666666666666,
|
| 227 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.9044117647058824,
|
| 228 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 319.6995849609375,
|
| 229 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.907606464463115,
|
| 230 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.9115646258503401,
|
| 231 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 290.19317626953125,
|
| 232 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.9305555555555556,
|
| 233 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.8933333333333333,
|
| 234 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.9117647058823529,
|
| 235 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 22.626989364624023,
|
| 236 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.9092245976210003,
|
| 237 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.918918918918919,
|
| 238 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 22.626989364624023,
|
| 239 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.9315068493150684,
|
| 240 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.9066666666666666,
|
| 241 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.9117647058823529,
|
| 242 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 494.6650390625,
|
| 243 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.9108555121538641,
|
| 244 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.92,
|
| 245 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 514.7510986328125,
|
| 246 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.92,
|
| 247 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.92,
|
| 248 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.9117647058823529,
|
| 249 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 494.6650390625,
|
| 250 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.9108555121538641,
|
| 251 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.92,
|
| 252 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 514.7510986328125,
|
| 253 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.9315068493150684,
|
| 254 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.92,
|
| 255 |
+
"eval_loss": 1.9418467283248901,
|
| 256 |
+
"eval_runtime": 14.4159,
|
| 257 |
+
"eval_samples_per_second": 9.434,
|
| 258 |
+
"eval_steps_per_second": 1.179,
|
| 259 |
+
"step": 340
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 6.0,
|
| 263 |
+
"grad_norm": 0.8858943581581116,
|
| 264 |
+
"learning_rate": 1.1974842767295597e-05,
|
| 265 |
+
"loss": 0.3347,
|
| 266 |
+
"step": 408
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 6.0,
|
| 270 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.9117647058823529,
|
| 271 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.5068449974060059,
|
| 272 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.9088529074244793,
|
| 273 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.918918918918919,
|
| 274 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.5068449974060059,
|
| 275 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.9315068493150684,
|
| 276 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.9066666666666666,
|
| 277 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.8970588235294118,
|
| 278 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 322.01324462890625,
|
| 279 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.9107273300403762,
|
| 280 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.9054054054054055,
|
| 281 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 276.34893798828125,
|
| 282 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.9178082191780822,
|
| 283 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.8933333333333333,
|
| 284 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.9117647058823529,
|
| 285 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 23.167011260986328,
|
| 286 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.9088745561179659,
|
| 287 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.918918918918919,
|
| 288 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 23.167011260986328,
|
| 289 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.9315068493150684,
|
| 290 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.9066666666666666,
|
| 291 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.9117647058823529,
|
| 292 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 506.7710266113281,
|
| 293 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.9092068556819233,
|
| 294 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.918918918918919,
|
| 295 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 506.7710266113281,
|
| 296 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.9315068493150684,
|
| 297 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.9066666666666666,
|
| 298 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.9117647058823529,
|
| 299 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 506.7710266113281,
|
| 300 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.9107273300403762,
|
| 301 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.918918918918919,
|
| 302 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 506.7710266113281,
|
| 303 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.9315068493150684,
|
| 304 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.9066666666666666,
|
| 305 |
+
"eval_loss": 2.012265920639038,
|
| 306 |
+
"eval_runtime": 13.9077,
|
| 307 |
+
"eval_samples_per_second": 9.779,
|
| 308 |
+
"eval_steps_per_second": 1.222,
|
| 309 |
+
"step": 408
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 7.0,
|
| 313 |
+
"grad_norm": 0.24478188157081604,
|
| 314 |
+
"learning_rate": 1.0264150943396227e-05,
|
| 315 |
+
"loss": 0.3425,
|
| 316 |
+
"step": 476
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 7.0,
|
| 320 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.9044117647058824,
|
| 321 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.5215883255004883,
|
| 322 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.9081430244026829,
|
| 323 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.912751677852349,
|
| 324 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.5215883255004883,
|
| 325 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.918918918918919,
|
| 326 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.9066666666666666,
|
| 327 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.9044117647058824,
|
| 328 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 313.0162353515625,
|
| 329 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.9094090969210814,
|
| 330 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.9090909090909091,
|
| 331 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 313.0162353515625,
|
| 332 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.9558823529411765,
|
| 333 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.8666666666666667,
|
| 334 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.9044117647058824,
|
| 335 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 23.342838287353516,
|
| 336 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.907981722850528,
|
| 337 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.912751677852349,
|
| 338 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 23.342838287353516,
|
| 339 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.918918918918919,
|
| 340 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.9066666666666666,
|
| 341 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.9044117647058824,
|
| 342 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 511.61737060546875,
|
| 343 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.9085688725632555,
|
| 344 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.912751677852349,
|
| 345 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 511.61737060546875,
|
| 346 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.918918918918919,
|
| 347 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.9066666666666666,
|
| 348 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.9044117647058824,
|
| 349 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 511.61737060546875,
|
| 350 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.9094090969210814,
|
| 351 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.912751677852349,
|
| 352 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 511.61737060546875,
|
| 353 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.9558823529411765,
|
| 354 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.9066666666666666,
|
| 355 |
+
"eval_loss": 2.038686752319336,
|
| 356 |
+
"eval_runtime": 14.7627,
|
| 357 |
+
"eval_samples_per_second": 9.212,
|
| 358 |
+
"eval_steps_per_second": 1.152,
|
| 359 |
+
"step": 476
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 8.0,
|
| 363 |
+
"grad_norm": 0.09618318825960159,
|
| 364 |
+
"learning_rate": 8.553459119496857e-06,
|
| 365 |
+
"loss": 0.2427,
|
| 366 |
+
"step": 544
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 8.0,
|
| 370 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.9044117647058824,
|
| 371 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.5501157641410828,
|
| 372 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.9086817589029806,
|
| 373 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.912751677852349,
|
| 374 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.5119773149490356,
|
| 375 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.918918918918919,
|
| 376 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.9066666666666666,
|
| 377 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.9117647058823529,
|
| 378 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 294.31005859375,
|
| 379 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.9096226292878296,
|
| 380 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.9166666666666666,
|
| 381 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 294.31005859375,
|
| 382 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.9565217391304348,
|
| 383 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.88,
|
| 384 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.9117647058823529,
|
| 385 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 23.28342056274414,
|
| 386 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.9089227316320502,
|
| 387 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.918918918918919,
|
| 388 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 23.28342056274414,
|
| 389 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.9315068493150684,
|
| 390 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.9066666666666666,
|
| 391 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.9117647058823529,
|
| 392 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 509.5169677734375,
|
| 393 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.9102569832574411,
|
| 394 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.918918918918919,
|
| 395 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 509.5169677734375,
|
| 396 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.9315068493150684,
|
| 397 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.9066666666666666,
|
| 398 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.9117647058823529,
|
| 399 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 509.5169677734375,
|
| 400 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.9102569832574411,
|
| 401 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.918918918918919,
|
| 402 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 509.5169677734375,
|
| 403 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.9565217391304348,
|
| 404 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.9066666666666666,
|
| 405 |
+
"eval_loss": 1.9878324270248413,
|
| 406 |
+
"eval_runtime": 13.7764,
|
| 407 |
+
"eval_samples_per_second": 9.872,
|
| 408 |
+
"eval_steps_per_second": 1.234,
|
| 409 |
+
"step": 544
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 9.0,
|
| 413 |
+
"grad_norm": 0.046123113483190536,
|
| 414 |
+
"learning_rate": 6.842767295597485e-06,
|
| 415 |
+
"loss": 0.2412,
|
| 416 |
+
"step": 612
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 9.0,
|
| 420 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.9044117647058824,
|
| 421 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.5531296730041504,
|
| 422 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.9088232956862466,
|
| 423 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.912751677852349,
|
| 424 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.49595877528190613,
|
| 425 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.918918918918919,
|
| 426 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.9066666666666666,
|
| 427 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.9117647058823529,
|
| 428 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 295.7380676269531,
|
| 429 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.9178358242971421,
|
| 430 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.9166666666666666,
|
| 431 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 295.7380676269531,
|
| 432 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.9565217391304348,
|
| 433 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.88,
|
| 434 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.9117647058823529,
|
| 435 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 23.565818786621094,
|
| 436 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.9092338106583002,
|
| 437 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.918918918918919,
|
| 438 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 23.565818786621094,
|
| 439 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.9315068493150684,
|
| 440 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.9066666666666666,
|
| 441 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.9117647058823529,
|
| 442 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 515.80322265625,
|
| 443 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.9102278723159124,
|
| 444 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.918918918918919,
|
| 445 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 515.80322265625,
|
| 446 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.9315068493150684,
|
| 447 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.9066666666666666,
|
| 448 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.9117647058823529,
|
| 449 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 515.80322265625,
|
| 450 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.9178358242971421,
|
| 451 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.918918918918919,
|
| 452 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 515.80322265625,
|
| 453 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.9565217391304348,
|
| 454 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.9066666666666666,
|
| 455 |
+
"eval_loss": 2.0423502922058105,
|
| 456 |
+
"eval_runtime": 18.8817,
|
| 457 |
+
"eval_samples_per_second": 7.203,
|
| 458 |
+
"eval_steps_per_second": 0.9,
|
| 459 |
+
"step": 612
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 10.0,
|
| 463 |
+
"grad_norm": 0.029908249154686928,
|
| 464 |
+
"learning_rate": 5.1320754716981136e-06,
|
| 465 |
+
"loss": 0.1623,
|
| 466 |
+
"step": 680
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 10.0,
|
| 470 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.9044117647058824,
|
| 471 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.5516438484191895,
|
| 472 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.9085774598037802,
|
| 473 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.9103448275862068,
|
| 474 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.519783079624176,
|
| 475 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.9428571428571428,
|
| 476 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.88,
|
| 477 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.9117647058823529,
|
| 478 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 294.6772766113281,
|
| 479 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.918847565389113,
|
| 480 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.9166666666666666,
|
| 481 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 294.6772766113281,
|
| 482 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.9565217391304348,
|
| 483 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.88,
|
| 484 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.9044117647058824,
|
| 485 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 21.938934326171875,
|
| 486 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.9089511554768472,
|
| 487 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.912751677852349,
|
| 488 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 23.713035583496094,
|
| 489 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.918918918918919,
|
| 490 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.9066666666666666,
|
| 491 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.9044117647058824,
|
| 492 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 482.1662292480469,
|
| 493 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.910254731797207,
|
| 494 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.912751677852349,
|
| 495 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 524.188232421875,
|
| 496 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.918918918918919,
|
| 497 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.9066666666666666,
|
| 498 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.9117647058823529,
|
| 499 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 482.1662292480469,
|
| 500 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.918847565389113,
|
| 501 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.9166666666666666,
|
| 502 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 524.188232421875,
|
| 503 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.9565217391304348,
|
| 504 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.9066666666666666,
|
| 505 |
+
"eval_loss": 2.0273122787475586,
|
| 506 |
+
"eval_runtime": 20.5658,
|
| 507 |
+
"eval_samples_per_second": 6.613,
|
| 508 |
+
"eval_steps_per_second": 0.827,
|
| 509 |
+
"step": 680
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 11.0,
|
| 513 |
+
"grad_norm": 0.007907501421868801,
|
| 514 |
+
"learning_rate": 3.4213836477987424e-06,
|
| 515 |
+
"loss": 0.1909,
|
| 516 |
+
"step": 748
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 11.0,
|
| 520 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.9044117647058824,
|
| 521 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.550028383731842,
|
| 522 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.9090819039672458,
|
| 523 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.912751677852349,
|
| 524 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.48157936334609985,
|
| 525 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.918918918918919,
|
| 526 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.9066666666666666,
|
| 527 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.9117647058823529,
|
| 528 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 293.80010986328125,
|
| 529 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.9219827879602106,
|
| 530 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.9166666666666666,
|
| 531 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 293.80010986328125,
|
| 532 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.9565217391304348,
|
| 533 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.88,
|
| 534 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.9117647058823529,
|
| 535 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 23.849559783935547,
|
| 536 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.90922024992935,
|
| 537 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.918918918918919,
|
| 538 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 23.849559783935547,
|
| 539 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.9315068493150684,
|
| 540 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.9066666666666666,
|
| 541 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.9044117647058824,
|
| 542 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 482.9535827636719,
|
| 543 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.910689468531078,
|
| 544 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.912751677852349,
|
| 545 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 527.540771484375,
|
| 546 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.918918918918919,
|
| 547 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.9066666666666666,
|
| 548 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.9117647058823529,
|
| 549 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 482.9535827636719,
|
| 550 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.9219827879602106,
|
| 551 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.918918918918919,
|
| 552 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 527.540771484375,
|
| 553 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.9565217391304348,
|
| 554 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.9066666666666666,
|
| 555 |
+
"eval_loss": 2.0955376625061035,
|
| 556 |
+
"eval_runtime": 20.4117,
|
| 557 |
+
"eval_samples_per_second": 6.663,
|
| 558 |
+
"eval_steps_per_second": 0.833,
|
| 559 |
+
"step": 748
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 12.0,
|
| 563 |
+
"grad_norm": 0.3338662087917328,
|
| 564 |
+
"learning_rate": 1.7106918238993712e-06,
|
| 565 |
+
"loss": 0.1507,
|
| 566 |
+
"step": 816
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 12.0,
|
| 570 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.9044117647058824,
|
| 571 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.5501536726951599,
|
| 572 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.9084179566135925,
|
| 573 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.912751677852349,
|
| 574 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.4790937304496765,
|
| 575 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.918918918918919,
|
| 576 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.9066666666666666,
|
| 577 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.9117647058823529,
|
| 578 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 294.13421630859375,
|
| 579 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.915716305189008,
|
| 580 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.9166666666666666,
|
| 581 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 294.13421630859375,
|
| 582 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.9565217391304348,
|
| 583 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.88,
|
| 584 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.9117647058823529,
|
| 585 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 23.818954467773438,
|
| 586 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.9093211275077335,
|
| 587 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.918918918918919,
|
| 588 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 23.818954467773438,
|
| 589 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.9315068493150684,
|
| 590 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.9066666666666666,
|
| 591 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.9044117647058824,
|
| 592 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 482.6566162109375,
|
| 593 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.9104676924615509,
|
| 594 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.913907284768212,
|
| 595 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 532.9744262695312,
|
| 596 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.9078947368421053,
|
| 597 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.92,
|
| 598 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.9117647058823529,
|
| 599 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 482.6566162109375,
|
| 600 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.915716305189008,
|
| 601 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.918918918918919,
|
| 602 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 532.9744262695312,
|
| 603 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.9565217391304348,
|
| 604 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.92,
|
| 605 |
+
"eval_loss": 2.2124059200286865,
|
| 606 |
+
"eval_runtime": 20.6137,
|
| 607 |
+
"eval_samples_per_second": 6.598,
|
| 608 |
+
"eval_steps_per_second": 0.825,
|
| 609 |
+
"step": 816
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 13.0,
|
| 613 |
+
"grad_norm": 0.01023839507251978,
|
| 614 |
+
"learning_rate": 0.0,
|
| 615 |
+
"loss": 0.1406,
|
| 616 |
+
"step": 884
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 13.0,
|
| 620 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.9044117647058824,
|
| 621 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.5485918521881104,
|
| 622 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.9088999169341241,
|
| 623 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.912751677852349,
|
| 624 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.47659817337989807,
|
| 625 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.918918918918919,
|
| 626 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.9066666666666666,
|
| 627 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.9117647058823529,
|
| 628 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 293.22845458984375,
|
| 629 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.9171086358892895,
|
| 630 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.9166666666666666,
|
| 631 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 293.22845458984375,
|
| 632 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.9565217391304348,
|
| 633 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.88,
|
| 634 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.9117647058823529,
|
| 635 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 23.82940673828125,
|
| 636 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.9094221163568814,
|
| 637 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.918918918918919,
|
| 638 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 23.82940673828125,
|
| 639 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.9315068493150684,
|
| 640 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.9066666666666666,
|
| 641 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.9117647058823529,
|
| 642 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 524.0676879882812,
|
| 643 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.9111567321590129,
|
| 644 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.918918918918919,
|
| 645 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 524.0676879882812,
|
| 646 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.9315068493150684,
|
| 647 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.9066666666666666,
|
| 648 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.9117647058823529,
|
| 649 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 524.0676879882812,
|
| 650 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.9171086358892895,
|
| 651 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.918918918918919,
|
| 652 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 524.0676879882812,
|
| 653 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.9565217391304348,
|
| 654 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.9066666666666666,
|
| 655 |
+
"eval_loss": 2.2125871181488037,
|
| 656 |
+
"eval_runtime": 20.4613,
|
| 657 |
+
"eval_samples_per_second": 6.647,
|
| 658 |
+
"eval_steps_per_second": 0.831,
|
| 659 |
+
"step": 884
|
| 660 |
+
}
|
| 661 |
+
],
|
| 662 |
+
"logging_steps": 500,
|
| 663 |
+
"max_steps": 884,
|
| 664 |
+
"num_input_tokens_seen": 0,
|
| 665 |
+
"num_train_epochs": 13,
|
| 666 |
+
"save_steps": 100,
|
| 667 |
+
"stateful_callbacks": {
|
| 668 |
+
"TrainerControl": {
|
| 669 |
+
"args": {
|
| 670 |
+
"should_epoch_stop": false,
|
| 671 |
+
"should_evaluate": false,
|
| 672 |
+
"should_log": false,
|
| 673 |
+
"should_save": true,
|
| 674 |
+
"should_training_stop": true
|
| 675 |
+
},
|
| 676 |
+
"attributes": {}
|
| 677 |
+
}
|
| 678 |
+
},
|
| 679 |
+
"total_flos": 0.0,
|
| 680 |
+
"train_batch_size": 8,
|
| 681 |
+
"trial_name": null,
|
| 682 |
+
"trial_params": null
|
| 683 |
+
}
|
checkpoint-884/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb4f571730ddebdbfd409aa41c36173377c8d33a0e18444875f0d792c4278e37
|
| 3 |
+
size 5432
|
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 sha256:6ea971648a5f2a8763054e8e39824b1f5acc795ea1e4e11c3565210e0f89f56c
|
| 3 |
size 442491744
|
runs/Sep03_22-46-20_default/events.out.tfevents.1725403583.default.1138.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb8fd5bfc896f65a3d434039684a6cabfaddb87865aa16c2b2d8090cac014f6f
|
| 3 |
+
size 49331
|
runs/Sep04_17-30-25_default/events.out.tfevents.1725471030.default.394.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46d31cb7eb223ba8dc96326c2462b6eef63d993f82bd3fbc703df4590623056d
|
| 3 |
+
size 35129
|
runs/Sep04_21-08-57_default/events.out.tfevents.1725484141.default.793.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85bf0744933646bd101ae62fb2710a14a3b11e7fc0d0f26abbda6ff31e213948
|
| 3 |
+
size 49463
|
runs/Sep11_17-50-24_default/events.out.tfevents.1726077038.default.828.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d9830d26f5e7833d13cb1631f7af76dd8bfd56db34468f72bb2301fb046d8cba
|
| 3 |
+
size 25624
|
runs/Sep11_18-02-35_default/events.out.tfevents.1726077764.default.959.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7514d733eb7e908dde3f2aa6f1950bc7038fe646195029a27f454b5854ef6347
|
| 3 |
+
size 4184
|
runs/Sep11_18-05-21_default/events.out.tfevents.1726077928.default.1078.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f5639a4eda642b609a41df68e6a6b5bb880730593b76c8a871b949b91bd5a0b5
|
| 3 |
+
size 50916
|
runs/Sep11_23-48-08_default/events.out.tfevents.1726098512.default.5852.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38a5c6822acc517b03e1f08527ee0bad0e8f50e86d9bbcf3e82141840d2633b0
|
| 3 |
+
size 4278
|
runs/Sep12_00-21-44_default/events.out.tfevents.1726100510.default.6560.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12e163434007f9913a647fafb29bb7d6b8c4945795162667798c8c263ed84815
|
| 3 |
+
size 15289
|
runs/Sep12_00-34-34_default/events.out.tfevents.1726101282.default.6715.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5661cb6e830be489024cb91ad77b592057ebd50e5239353a37af89bbb476e611
|
| 3 |
+
size 50960
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6467857b4b0c77ded9bac7ad2fb5c16eb64e17e417ce46624dacac2bbb404fc
|
| 3 |
+
size 802713
|
tokenizer_config.json
CHANGED
|
@@ -1,65 +1,15 @@
|
|
| 1 |
{
|
| 2 |
-
|
| 3 |
-
"
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
"
|
| 12 |
-
|
| 13 |
-
|
| 14 |
-
|
| 15 |
-
|
| 16 |
-
"single_word": false,
|
| 17 |
-
"special": true
|
| 18 |
-
},
|
| 19 |
-
"2": {
|
| 20 |
-
"content": "[CLS]",
|
| 21 |
-
"lstrip": false,
|
| 22 |
-
"normalized": false,
|
| 23 |
-
"rstrip": false,
|
| 24 |
-
"single_word": false,
|
| 25 |
-
"special": false
|
| 26 |
-
},
|
| 27 |
-
"3": {
|
| 28 |
-
"content": "[SEP]",
|
| 29 |
-
"lstrip": false,
|
| 30 |
-
"normalized": false,
|
| 31 |
-
"rstrip": false,
|
| 32 |
-
"single_word": false,
|
| 33 |
-
"special": false
|
| 34 |
-
},
|
| 35 |
-
"4": {
|
| 36 |
-
"content": "[MASK]",
|
| 37 |
-
"lstrip": false,
|
| 38 |
-
"normalized": false,
|
| 39 |
-
"rstrip": false,
|
| 40 |
-
"single_word": false,
|
| 41 |
-
"special": false
|
| 42 |
-
},
|
| 43 |
-
"32000": {
|
| 44 |
-
"content": "[PAD]",
|
| 45 |
-
"lstrip": false,
|
| 46 |
-
"normalized": true,
|
| 47 |
-
"rstrip": false,
|
| 48 |
-
"single_word": false,
|
| 49 |
-
"special": false
|
| 50 |
-
}
|
| 51 |
-
},
|
| 52 |
-
"bos_token": "[CLS]",
|
| 53 |
-
"clean_up_tokenization_spaces": true,
|
| 54 |
-
"cls_token": "[CLS]",
|
| 55 |
-
"do_lower_case": false,
|
| 56 |
-
"eos_token": "[SEP]",
|
| 57 |
-
"mask_token": "[MASK]",
|
| 58 |
-
"model_max_length": 512,
|
| 59 |
-
"pad_token": "<pad>",
|
| 60 |
-
"sep_token": "[SEP]",
|
| 61 |
-
"sp_model_kwargs": {},
|
| 62 |
-
"split_by_punct": false,
|
| 63 |
-
"tokenizer_class": "DebertaV2Tokenizer",
|
| 64 |
-
"unk_token": "<unk>"
|
| 65 |
-
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"clean_up_tokenization_spaces": true,
|
| 4 |
+
"cls_token": "[CLS]",
|
| 5 |
+
"do_lower_case": false,
|
| 6 |
+
"eos_token": "[SEP]",
|
| 7 |
+
"mask_token": "[MASK]",
|
| 8 |
+
"model_max_length": 512,
|
| 9 |
+
"pad_token": "<pad>",
|
| 10 |
+
"sep_token": "[SEP]",
|
| 11 |
+
"sp_model_kwargs": {},
|
| 12 |
+
"split_by_punct": false,
|
| 13 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|