Add new SentenceTransformer model.
Browse files- README.md +117 -177
- config.json +1 -1
- model.safetensors +1 -1
README.md
CHANGED
|
@@ -5,67 +5,36 @@ tags:
|
|
| 5 |
- sentence-transformers
|
| 6 |
- sentence-similarity
|
| 7 |
- feature-extraction
|
| 8 |
-
- dataset_size:
|
| 9 |
- loss:CachedGISTEmbedLoss
|
| 10 |
base_model: nomic-ai/nomic-embed-text-v1.5
|
| 11 |
-
metrics:
|
| 12 |
-
- cosine_accuracy
|
| 13 |
-
- dot_accuracy
|
| 14 |
-
- manhattan_accuracy
|
| 15 |
-
- euclidean_accuracy
|
| 16 |
-
- max_accuracy
|
| 17 |
widget:
|
| 18 |
-
- source_sentence:
|
| 19 |
sentences:
|
| 20 |
-
-
|
| 21 |
-
-
|
| 22 |
-
-
|
| 23 |
-
- source_sentence:
|
| 24 |
sentences:
|
| 25 |
-
-
|
| 26 |
-
-
|
| 27 |
-
-
|
| 28 |
-
- source_sentence:
|
| 29 |
sentences:
|
| 30 |
-
-
|
| 31 |
-
-
|
| 32 |
-
-
|
| 33 |
-
- source_sentence:
|
| 34 |
sentences:
|
| 35 |
-
-
|
| 36 |
-
-
|
| 37 |
-
-
|
| 38 |
-
- source_sentence:
|
| 39 |
sentences:
|
| 40 |
-
-
|
| 41 |
-
-
|
| 42 |
-
-
|
| 43 |
pipeline_tag: sentence-similarity
|
| 44 |
-
model-index:
|
| 45 |
-
- name: SentenceTransformer based on nomic-ai/nomic-embed-text-v1.5
|
| 46 |
-
results:
|
| 47 |
-
- task:
|
| 48 |
-
type: triplet
|
| 49 |
-
name: Triplet
|
| 50 |
-
dataset:
|
| 51 |
-
name: esci dev
|
| 52 |
-
type: esci-dev
|
| 53 |
-
metrics:
|
| 54 |
-
- type: cosine_accuracy
|
| 55 |
-
value: 0.6414052697616061
|
| 56 |
-
name: Cosine Accuracy
|
| 57 |
-
- type: dot_accuracy
|
| 58 |
-
value: 0.36637390213299875
|
| 59 |
-
name: Dot Accuracy
|
| 60 |
-
- type: manhattan_accuracy
|
| 61 |
-
value: 0.6404015056461732
|
| 62 |
-
name: Manhattan Accuracy
|
| 63 |
-
- type: euclidean_accuracy
|
| 64 |
-
value: 0.6406524466750314
|
| 65 |
-
name: Euclidean Accuracy
|
| 66 |
-
- type: max_accuracy
|
| 67 |
-
value: 0.6414052697616061
|
| 68 |
-
name: Max Accuracy
|
| 69 |
---
|
| 70 |
|
| 71 |
# SentenceTransformer based on nomic-ai/nomic-embed-text-v1.5
|
|
@@ -117,9 +86,9 @@ from sentence_transformers import SentenceTransformer
|
|
| 117 |
model = SentenceTransformer("sentence_transformers_model_id")
|
| 118 |
# Run inference
|
| 119 |
sentences = [
|
| 120 |
-
'
|
| 121 |
-
'
|
| 122 |
-
'
|
| 123 |
]
|
| 124 |
embeddings = model.encode(sentences)
|
| 125 |
print(embeddings.shape)
|
|
@@ -155,22 +124,6 @@ You can finetune this model on your own dataset.
|
|
| 155 |
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
| 156 |
-->
|
| 157 |
|
| 158 |
-
## Evaluation
|
| 159 |
-
|
| 160 |
-
### Metrics
|
| 161 |
-
|
| 162 |
-
#### Triplet
|
| 163 |
-
* Dataset: `esci-dev`
|
| 164 |
-
* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
|
| 165 |
-
|
| 166 |
-
| Metric | Value |
|
| 167 |
-
|:-------------------|:-----------|
|
| 168 |
-
| cosine_accuracy | 0.6414 |
|
| 169 |
-
| dot_accuracy | 0.3664 |
|
| 170 |
-
| manhattan_accuracy | 0.6404 |
|
| 171 |
-
| euclidean_accuracy | 0.6407 |
|
| 172 |
-
| **max_accuracy** | **0.6414** |
|
| 173 |
-
|
| 174 |
<!--
|
| 175 |
## Bias, Risks and Limitations
|
| 176 |
|
|
@@ -190,46 +143,19 @@ You can finetune this model on your own dataset.
|
|
| 190 |
#### Unnamed Dataset
|
| 191 |
|
| 192 |
|
| 193 |
-
* Size:
|
| 194 |
-
* Columns: <code>
|
| 195 |
-
* Approximate statistics based on the first 1000 samples:
|
| 196 |
-
| | query | pos | neg |
|
| 197 |
-
|:--------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
|
| 198 |
-
| type | string | string | string |
|
| 199 |
-
| details | <ul><li>min: 3 tokens</li><li>mean: 7.42 tokens</li><li>max: 30 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 29.27 tokens</li><li>max: 87 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 29.8 tokens</li><li>max: 82 tokens</li></ul> |
|
| 200 |
-
* Samples:
|
| 201 |
-
| query | pos | neg |
|
| 202 |
-
|:--------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
| 203 |
-
| <code>1 3/4 inch tooled belt strap without belt buckle</code> | <code>BS3501 Solid Brass Leaf Belt Buckle Fits 1-3/4"(45mm) Wide Belt</code> | <code>Nocona Men's Hired Brown Floral Eagle, 40</code> |
|
| 204 |
-
| <code>7edge phone case peacock</code> | <code>Galaxy S7 Edge Case for Girls Women Clear with Flowers Design Shockproof Protective Cell Phone Cases for Samsung Galaxy S7 Edge 5.5 Inch Cute Floral Pattern Print Flexible Slim Fit Bumper Rubber Cover</code> | <code>Galaxy S7 Case, Galaxy S7 Phone Case with HD Screen Protector for Girls Women, Gritup Cute Clear Gradient Glitter Liquid TPU Slim Phone Case for Samsung Galaxy S7 Teal/Purple</code> |
|
| 205 |
-
| <code>girls white shoes</code> | <code>adidas Women's Coast Star Shoes, ftwr White/Silver Met./ core Black, 6 M US</code> | <code>Converse Optical White M7650 - HI TOP Size 6 M US Women / 4 M US Men</code> |
|
| 206 |
-
* Loss: [<code>CachedGISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cachedgistembedloss) with these parameters:
|
| 207 |
-
```json
|
| 208 |
-
{'guide': SentenceTransformer(
|
| 209 |
-
(0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: BertModel
|
| 210 |
-
(1): Pooling({'word_embedding_dimension': 384, '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})
|
| 211 |
-
(2): Normalize()
|
| 212 |
-
), 'temperature': 0.01}
|
| 213 |
-
```
|
| 214 |
-
|
| 215 |
-
### Evaluation Dataset
|
| 216 |
-
|
| 217 |
-
#### Unnamed Dataset
|
| 218 |
-
|
| 219 |
-
|
| 220 |
-
* Size: 3,985 evaluation samples
|
| 221 |
-
* Columns: <code>query</code>, <code>pos</code>, and <code>neg</code>
|
| 222 |
* Approximate statistics based on the first 1000 samples:
|
| 223 |
-
| |
|
| 224 |
-
|
| 225 |
-
| type | string
|
| 226 |
-
| details | <ul><li>min:
|
| 227 |
* Samples:
|
| 228 |
-
|
|
| 229 |
-
|
| 230 |
-
| <code>
|
| 231 |
-
| <code>
|
| 232 |
-
| <code>
|
| 233 |
* Loss: [<code>CachedGISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cachedgistembedloss) with these parameters:
|
| 234 |
```json
|
| 235 |
{'guide': SentenceTransformer(
|
|
@@ -242,9 +168,10 @@ You can finetune this model on your own dataset.
|
|
| 242 |
### Training Hyperparameters
|
| 243 |
#### Non-Default Hyperparameters
|
| 244 |
|
| 245 |
-
- `
|
| 246 |
-
- `
|
| 247 |
-
- `
|
|
|
|
| 248 |
- `warmup_ratio`: 0.1
|
| 249 |
- `fp16`: True
|
| 250 |
- `batch_sampler`: no_duplicates
|
|
@@ -255,21 +182,21 @@ You can finetune this model on your own dataset.
|
|
| 255 |
- `overwrite_output_dir`: False
|
| 256 |
- `do_predict`: False
|
| 257 |
- `prediction_loss_only`: True
|
| 258 |
-
- `per_device_train_batch_size`:
|
| 259 |
-
- `per_device_eval_batch_size`:
|
| 260 |
- `per_gpu_train_batch_size`: None
|
| 261 |
- `per_gpu_eval_batch_size`: None
|
| 262 |
-
- `gradient_accumulation_steps`:
|
| 263 |
- `eval_accumulation_steps`: None
|
| 264 |
-
- `learning_rate`:
|
| 265 |
- `weight_decay`: 0.0
|
| 266 |
- `adam_beta1`: 0.9
|
| 267 |
- `adam_beta2`: 0.999
|
| 268 |
- `adam_epsilon`: 1e-08
|
| 269 |
- `max_grad_norm`: 1.0
|
| 270 |
-
- `num_train_epochs`:
|
| 271 |
- `max_steps`: -1
|
| 272 |
-
- `lr_scheduler_type`:
|
| 273 |
- `lr_scheduler_kwargs`: {}
|
| 274 |
- `warmup_ratio`: 0.1
|
| 275 |
- `warmup_steps`: 0
|
|
@@ -359,65 +286,78 @@ You can finetune this model on your own dataset.
|
|
| 359 |
</details>
|
| 360 |
|
| 361 |
### Training Logs
|
| 362 |
-
| Epoch | Step | Training Loss |
|
| 363 |
-
|
| 364 |
-
| 0
|
| 365 |
-
| 0.
|
| 366 |
-
| 0.
|
| 367 |
-
| 0.
|
| 368 |
-
| 0.
|
| 369 |
-
| 0.
|
| 370 |
-
|
|
| 371 |
-
|
|
| 372 |
-
|
|
| 373 |
-
|
|
| 374 |
-
|
|
| 375 |
-
|
|
| 376 |
-
|
|
| 377 |
-
|
|
| 378 |
-
|
|
| 379 |
-
|
|
| 380 |
-
|
|
| 381 |
-
|
|
| 382 |
-
|
|
| 383 |
-
|
|
| 384 |
-
|
|
| 385 |
-
|
|
| 386 |
-
|
|
| 387 |
-
|
|
| 388 |
-
|
|
| 389 |
-
|
|
| 390 |
-
|
|
| 391 |
-
|
|
| 392 |
-
|
|
| 393 |
-
|
|
| 394 |
-
|
|
| 395 |
-
|
|
| 396 |
-
|
|
| 397 |
-
|
|
| 398 |
-
|
|
| 399 |
-
|
|
| 400 |
-
|
|
| 401 |
-
|
|
| 402 |
-
|
|
| 403 |
-
|
|
| 404 |
-
|
|
| 405 |
-
|
|
| 406 |
-
|
|
| 407 |
-
|
|
| 408 |
-
|
|
| 409 |
-
|
|
| 410 |
-
|
|
| 411 |
-
|
|
| 412 |
-
|
|
| 413 |
-
|
|
| 414 |
-
|
|
| 415 |
-
|
|
| 416 |
-
|
|
| 417 |
-
|
|
| 418 |
-
|
|
| 419 |
-
|
|
| 420 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 421 |
|
| 422 |
|
| 423 |
### Framework Versions
|
|
|
|
| 5 |
- sentence-transformers
|
| 6 |
- sentence-similarity
|
| 7 |
- feature-extraction
|
| 8 |
+
- dataset_size:1M<n<10M
|
| 9 |
- loss:CachedGISTEmbedLoss
|
| 10 |
base_model: nomic-ai/nomic-embed-text-v1.5
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
widget:
|
| 12 |
+
- source_sentence: 'search_query: 楢崎壮太'
|
| 13 |
sentences:
|
| 14 |
+
- 'search_query: 野崎萌香'
|
| 15 |
+
- 'search_query: ps4 slim 1tb'
|
| 16 |
+
- 'search_query: toy story 4 on dvd'
|
| 17 |
+
- source_sentence: 'search_query: テプラ'
|
| 18 |
sentences:
|
| 19 |
+
- 'search_query: 携帯デコシール'
|
| 20 |
+
- 'search_query: womens boots'
|
| 21 |
+
- 'search_query: nfl gift'
|
| 22 |
+
- source_sentence: 'search_query: 扇子 布'
|
| 23 |
sentences:
|
| 24 |
+
- 'search_query: 天気の子'
|
| 25 |
+
- 'search_query: 登山ぐつ メンズ 紐なし'
|
| 26 |
+
- 'search_query: 10gbe switch'
|
| 27 |
+
- source_sentence: 'search_query: リング棒'
|
| 28 |
sentences:
|
| 29 |
+
- 'search_query: ライトショアジギング'
|
| 30 |
+
- 'search_query: auvハンガーすべらない'
|
| 31 |
+
- 'search_query: plastic drum lid'
|
| 32 |
+
- source_sentence: 'search_query: 聖 龍人'
|
| 33 |
sentences:
|
| 34 |
+
- 'search_query: 越前かに職人甲羅組'
|
| 35 |
+
- 'search_query: tea tree oil'
|
| 36 |
+
- 'search_query: lift storage bed'
|
| 37 |
pipeline_tag: sentence-similarity
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 38 |
---
|
| 39 |
|
| 40 |
# SentenceTransformer based on nomic-ai/nomic-embed-text-v1.5
|
|
|
|
| 86 |
model = SentenceTransformer("sentence_transformers_model_id")
|
| 87 |
# Run inference
|
| 88 |
sentences = [
|
| 89 |
+
'search_query: 聖 龍人',
|
| 90 |
+
'search_query: 越前かに職人甲羅組',
|
| 91 |
+
'search_query: tea tree oil',
|
| 92 |
]
|
| 93 |
embeddings = model.encode(sentences)
|
| 94 |
print(embeddings.shape)
|
|
|
|
| 124 |
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
| 125 |
-->
|
| 126 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 127 |
<!--
|
| 128 |
## Bias, Risks and Limitations
|
| 129 |
|
|
|
|
| 143 |
#### Unnamed Dataset
|
| 144 |
|
| 145 |
|
| 146 |
+
* Size: 1,767,572 training samples
|
| 147 |
+
* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 148 |
* Approximate statistics based on the first 1000 samples:
|
| 149 |
+
| | anchor | positive | negative |
|
| 150 |
+
|:--------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
|
| 151 |
+
| type | string | string | string |
|
| 152 |
+
| details | <ul><li>min: 7 tokens</li><li>mean: 12.26 tokens</li><li>max: 59 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 31.93 tokens</li><li>max: 140 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 34.3 tokens</li><li>max: 157 tokens</li></ul> |
|
| 153 |
* Samples:
|
| 154 |
+
| anchor | positive | negative |
|
| 155 |
+
|:---------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------|
|
| 156 |
+
| <code>search_query: plus tops for women</code> | <code>search_document:Just My Size Women's Plus-Size Graphic Short Sleeve V-Neck T-Shirt, White-Y07188, 5X, JUST MY SIZE, White-y07188</code> | <code>search_document:Calvin Klein Women's Regular Modern Cotton Bralette, Nymph's Thigh, S, Calvin Klein, Nymph's Thigh</code> |
|
| 157 |
+
| <code>search_query: mens black wallet trifold</code> | <code>search_document:Stealth Mode Trifold RFID Blocking Leather Wallet for Men (Black), Stealth Mode, Black</code> | <code>search_document:RFID Trifold Canvas Outdoor Sports Wallet for Kids - Front Pocket Wallet with Magic Sticker (Black), AI-DEE, Black</code> |
|
| 158 |
+
| <code>search_query: ipad pro reacondicionado 12,9</code> | <code>search_document:Apple iPad Pro (12.9 Pouces, Wi-FI, 64Go) 2018 - Gray (Renewed), Apple, Gris Espacial</code> | <code>search_document:Apple iPad Pro 3rd Generation (11-Inch, Wi-FI Only 64GB) - Space Gray (Renewed), Apple, Gris Espacial</code> |
|
| 159 |
* Loss: [<code>CachedGISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cachedgistembedloss) with these parameters:
|
| 160 |
```json
|
| 161 |
{'guide': SentenceTransformer(
|
|
|
|
| 168 |
### Training Hyperparameters
|
| 169 |
#### Non-Default Hyperparameters
|
| 170 |
|
| 171 |
+
- `per_device_eval_batch_size`: 2
|
| 172 |
+
- `gradient_accumulation_steps`: 2
|
| 173 |
+
- `learning_rate`: 1e-05
|
| 174 |
+
- `lr_scheduler_type`: cosine_with_restarts
|
| 175 |
- `warmup_ratio`: 0.1
|
| 176 |
- `fp16`: True
|
| 177 |
- `batch_sampler`: no_duplicates
|
|
|
|
| 182 |
- `overwrite_output_dir`: False
|
| 183 |
- `do_predict`: False
|
| 184 |
- `prediction_loss_only`: True
|
| 185 |
+
- `per_device_train_batch_size`: 8
|
| 186 |
+
- `per_device_eval_batch_size`: 2
|
| 187 |
- `per_gpu_train_batch_size`: None
|
| 188 |
- `per_gpu_eval_batch_size`: None
|
| 189 |
+
- `gradient_accumulation_steps`: 2
|
| 190 |
- `eval_accumulation_steps`: None
|
| 191 |
+
- `learning_rate`: 1e-05
|
| 192 |
- `weight_decay`: 0.0
|
| 193 |
- `adam_beta1`: 0.9
|
| 194 |
- `adam_beta2`: 0.999
|
| 195 |
- `adam_epsilon`: 1e-08
|
| 196 |
- `max_grad_norm`: 1.0
|
| 197 |
+
- `num_train_epochs`: 3
|
| 198 |
- `max_steps`: -1
|
| 199 |
+
- `lr_scheduler_type`: cosine_with_restarts
|
| 200 |
- `lr_scheduler_kwargs`: {}
|
| 201 |
- `warmup_ratio`: 0.1
|
| 202 |
- `warmup_steps`: 0
|
|
|
|
| 286 |
</details>
|
| 287 |
|
| 288 |
### Training Logs
|
| 289 |
+
| Epoch | Step | Training Loss |
|
| 290 |
+
|:------:|:----:|:-------------:|
|
| 291 |
+
| 0.0009 | 100 | 3.7009 |
|
| 292 |
+
| 0.0018 | 200 | 3.3796 |
|
| 293 |
+
| 0.0027 | 300 | 2.8348 |
|
| 294 |
+
| 0.0036 | 400 | 2.1803 |
|
| 295 |
+
| 0.0045 | 500 | 1.8272 |
|
| 296 |
+
| 0.0054 | 600 | 1.4715 |
|
| 297 |
+
| 0.0063 | 700 | 1.0056 |
|
| 298 |
+
| 0.0072 | 800 | 0.7984 |
|
| 299 |
+
| 0.0081 | 900 | 0.6925 |
|
| 300 |
+
| 0.0091 | 1000 | 0.6552 |
|
| 301 |
+
| 0.0100 | 1100 | 0.6054 |
|
| 302 |
+
| 0.0109 | 1200 | 0.5874 |
|
| 303 |
+
| 0.0118 | 1300 | 0.5641 |
|
| 304 |
+
| 0.0127 | 1400 | 0.528 |
|
| 305 |
+
| 0.0136 | 1500 | 0.5285 |
|
| 306 |
+
| 0.0145 | 1600 | 0.5032 |
|
| 307 |
+
| 0.0154 | 1700 | 0.5238 |
|
| 308 |
+
| 0.0163 | 1800 | 0.4565 |
|
| 309 |
+
| 0.0172 | 1900 | 0.4739 |
|
| 310 |
+
| 0.0181 | 2000 | 0.4614 |
|
| 311 |
+
| 0.0190 | 2100 | 0.4334 |
|
| 312 |
+
| 0.0199 | 2200 | 0.4217 |
|
| 313 |
+
| 0.0208 | 2300 | 0.3931 |
|
| 314 |
+
| 0.0217 | 2400 | 0.4102 |
|
| 315 |
+
| 0.0226 | 2500 | 0.3936 |
|
| 316 |
+
| 0.0235 | 2600 | 0.415 |
|
| 317 |
+
| 0.0244 | 2700 | 0.4462 |
|
| 318 |
+
| 0.0253 | 2800 | 0.3886 |
|
| 319 |
+
| 0.0263 | 2900 | 0.3887 |
|
| 320 |
+
| 0.0272 | 3000 | 0.3629 |
|
| 321 |
+
| 0.0281 | 3100 | 0.37 |
|
| 322 |
+
| 0.0290 | 3200 | 0.3861 |
|
| 323 |
+
| 0.0299 | 3300 | 0.3813 |
|
| 324 |
+
| 0.0308 | 3400 | 0.3348 |
|
| 325 |
+
| 0.0317 | 3500 | 0.3566 |
|
| 326 |
+
| 0.0326 | 3600 | 0.3674 |
|
| 327 |
+
| 0.0335 | 3700 | 0.3421 |
|
| 328 |
+
| 0.0344 | 3800 | 0.3225 |
|
| 329 |
+
| 0.0353 | 3900 | 0.406 |
|
| 330 |
+
| 0.0362 | 4000 | 0.3975 |
|
| 331 |
+
| 0.0371 | 4100 | 0.368 |
|
| 332 |
+
| 0.0380 | 4200 | 0.3481 |
|
| 333 |
+
| 0.0389 | 4300 | 0.3405 |
|
| 334 |
+
| 0.0398 | 4400 | 0.3529 |
|
| 335 |
+
| 0.0407 | 4500 | 0.3968 |
|
| 336 |
+
| 0.0416 | 4600 | 0.3634 |
|
| 337 |
+
| 0.0425 | 4700 | 0.3518 |
|
| 338 |
+
| 0.0434 | 4800 | 0.383 |
|
| 339 |
+
| 0.0444 | 4900 | 0.3261 |
|
| 340 |
+
| 0.0453 | 5000 | 0.323 |
|
| 341 |
+
| 0.0462 | 5100 | 0.3372 |
|
| 342 |
+
| 0.0471 | 5200 | 0.358 |
|
| 343 |
+
| 0.0480 | 5300 | 0.3207 |
|
| 344 |
+
| 0.0489 | 5400 | 0.341 |
|
| 345 |
+
| 0.0498 | 5500 | 0.3146 |
|
| 346 |
+
| 0.0507 | 5600 | 0.3065 |
|
| 347 |
+
| 0.0516 | 5700 | 0.3597 |
|
| 348 |
+
| 0.0525 | 5800 | 0.3352 |
|
| 349 |
+
| 0.0534 | 5900 | 0.3212 |
|
| 350 |
+
| 0.0543 | 6000 | 0.316 |
|
| 351 |
+
| 0.0552 | 6100 | 0.3405 |
|
| 352 |
+
| 0.0561 | 6200 | 0.3416 |
|
| 353 |
+
| 0.0570 | 6300 | 0.3124 |
|
| 354 |
+
| 0.0579 | 6400 | 0.3146 |
|
| 355 |
+
| 0.0588 | 6500 | 0.3043 |
|
| 356 |
+
| 0.0597 | 6600 | 0.3687 |
|
| 357 |
+
| 0.0606 | 6700 | 0.3359 |
|
| 358 |
+
| 0.0616 | 6800 | 0.3414 |
|
| 359 |
+
| 0.0625 | 6900 | 0.3161 |
|
| 360 |
+
| 0.0634 | 7000 | 0.3266 |
|
| 361 |
|
| 362 |
|
| 363 |
### Framework Versions
|
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "models/nomic-embed-text-esci/checkpoint-
|
| 3 |
"activation_function": "swiglu",
|
| 4 |
"architectures": [
|
| 5 |
"NomicBertModel"
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "models/nomic-embed-text-esci/checkpoint-7000",
|
| 3 |
"activation_function": "swiglu",
|
| 4 |
"architectures": [
|
| 5 |
"NomicBertModel"
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 546938168
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d84393e7281f9fa1749b614ba8833b120c31a65d73fe00f693417d03f68231c
|
| 3 |
size 546938168
|