Hugging Face's logo

CuongCao
/
oe-bge-reranker-large-ft-v2

Text Ranking
sentence-transformers
Safetensors
xlm-roberta
cross-encoder
reranker
Generated from Trainer
dataset_size:5400
loss:BinaryCrossEntropyLoss
Eval Results (legacy)
text-embeddings-inference
Model card Files
xet
 Community
CuongCao commited on
Commit
de2de5a
·
verified ·
1 Parent(s): 5e06d9d

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. .gitattributes +1 -0
  2. README.md +437 -0
  3. config.json +40 -0
  4. model.safetensors +3 -0
  5. tokenizer.json +3 -0
  6. tokenizer_config.json +16 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,437 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - sentence-transformers
4
+ - cross-encoder
5
+ - reranker
6
+ - generated_from_trainer
7
+ - dataset_size:5400
8
+ - loss:BinaryCrossEntropyLoss
9
+ base_model: BAAI/bge-reranker-large
10
+ pipeline_tag: text-ranking
11
+ library_name: sentence-transformers
12
+ metrics:
13
+ - map
14
+ - mrr@10
15
+ - ndcg@10
16
+ model-index:
17
+ - name: CrossEncoder based on BAAI/bge-reranker-large
18
+ results:
19
+ - task:
20
+ type: cross-encoder-reranking
21
+ name: Cross Encoder Reranking
22
+ dataset:
23
+ name: support rerank eval
24
+ type: support-rerank-eval
25
+ metrics:
26
+ - type: map
27
+ value: 0.9087
28
+ name: Map
29
+ - type: mrr@10
30
+ value: 0.9087
31
+ name: Mrr@10
32
+ - type: ndcg@10
33
+ value: 0.9315
34
+ name: Ndcg@10
35
+ ---
36
+
37
+ # CrossEncoder based on BAAI/bge-reranker-large
38
+
39
+ This is a [Cross Encoder](https://www.sbert.net/docs/cross_encoder/usage/usage.html) model finetuned from [BAAI/bge-reranker-large](https://huggingface.co/BAAI/bge-reranker-large) using the [sentence-transformers](https://www.SBERT.net) library. It computes scores for pairs of texts, which can be used for text reranking and semantic search.
40
+
41
+ ## Model Details
42
+
43
+ ### Model Description
44
+ - **Model Type:** Cross Encoder
45
+ - **Base model:** [BAAI/bge-reranker-large](https://huggingface.co/BAAI/bge-reranker-large) <!-- at revision 55611d7bca2a7133960a6d3b71e083071bbfc312 -->
46
+ - **Maximum Sequence Length:** 512 tokens
47
+ - **Number of Output Labels:** 1 label
48
+ <!-- - **Training Dataset:** Unknown -->
49
+ <!-- - **Language:** Unknown -->
50
+ <!-- - **License:** Unknown -->
51
+
52
+ ### Model Sources
53
+
54
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
55
+ - **Documentation:** [Cross Encoder Documentation](https://www.sbert.net/docs/cross_encoder/usage/usage.html)
56
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/sentence-transformers)
57
+ - **Hugging Face:** [Cross Encoders on Hugging Face](https://huggingface.co/models?library=sentence-transformers&other=cross-encoder)
58
+
59
+ ## Usage
60
+
61
+ ### Direct Usage (Sentence Transformers)
62
+
63
+ First install the Sentence Transformers library:
64
+
65
+ ```bash
66
+ pip install -U sentence-transformers
67
+ ```
68
+
69
+ Then you can load this model and run inference.
70
+ ```python
71
+ from sentence_transformers import CrossEncoder
72
+
73
+ # Download from the 🤗 Hub
74
+ model = CrossEncoder("cross_encoder_model_id")
75
+ # Get scores for pairs of texts
76
+ pairs = [
77
+ ['Hi, is there a way to show an image once the personalization toggle is on?', "Hi there, This is Hazel from Tepo Support team. I hope your day is going great! Yes, you can ultilize our conditional settings to show an image based on the toggle's selection, as demonstrated on our demo product [here](https://tepo.app/products/conditional-logic) <3 For step-by-step instructions on how to set up conditional settings on your end, please check out our [guide](https://support.tepo.app/en/article/set-up-conditional-logic-1sp9tac/). If you prefer watching than reading, feel free to take a look at our tutorial video [here](https://www.youtube.com/watch?v=7voAaJ2lzkc)"],
78
+ ['Hi, is there a way to show an image once the personalization toggle is on?', "Hello there, I apologize for getting back to you a bit later, as we've been away during non-working hours. I hope your weekend went great! For your information, we have a feature to change the product image based on the option's selection. I have enabled this feature for your store, so feel free to follow our step-by-step instructions [here](https://support.tepo.app/en/article/change-product-images-based-on-selected-options-1831rew/) to set up this feature for your store. Please let me know if you encounter any difficulties. I am more than happy to help!"],
79
+ ['Hi, is there a way to show an image once the personalization toggle is on?', "Hello, Thank you for contacting Tepo Support team! I hope you're having a wonderful day! To enlarge the size of the image swatches, you can refer to our guide [here](https://support.tepo.app/en/article/customize-style-for-app-options-using-css-26kmin/) for step-by-step instructions. This will allow you to make the necessary adjustments on your end. Feel free to give it a try, and if you encounter any difficulties or if coding isn't your forte, please don't hesitate to share the product URL with me. I'll be more than happy to assist further!"],
80
+ ['Hi, is there a way to show an image once the personalization toggle is on?', 'Good day~ This is Robin from Tepo Support team! I hope your day has been amazing so far! To make sure I’m on the same page, when you say getting the older version of the option set, are you referring to undoing some changes after you’ve already hit save? If I’ve misunderstood anything, please don’t hesitate to correct me. I want to make sure I assist you as best as I can!'],
81
+ ['Hi, is there a way to show an image once the personalization toggle is on?', "> Hello there, > This is Hazel from Tepo Support team. I hope your day is going great! > Thanks for sharing your concern with us. Regarding the packing slip, we do have a step-by-step instruction [here](https://support.tepo.app/en/article/how-to-show-options-in-shopify-packing-slip-1dyay7y/) that you can follow more easily on your end. Feel free to give it a try on your end to show Tepo options in your packing slip In Shopify, a courier slip is also known as a packing slip. I've seen that Hazel has sent you the instruction to add the code into the packing slip template to show the TEPO options already. May I ask if you give it a try on your end yet?"],
82
+ ]
83
+ scores = model.predict(pairs)
84
+ print(scores.shape)
85
+ # (5,)
86
+
87
+ # Or rank different texts based on similarity to a single text
88
+ ranks = model.rank(
89
+ 'Hi, is there a way to show an image once the personalization toggle is on?',
90
+ [
91
+ "Hi there, This is Hazel from Tepo Support team. I hope your day is going great! Yes, you can ultilize our conditional settings to show an image based on the toggle's selection, as demonstrated on our demo product [here](https://tepo.app/products/conditional-logic) <3 For step-by-step instructions on how to set up conditional settings on your end, please check out our [guide](https://support.tepo.app/en/article/set-up-conditional-logic-1sp9tac/). If you prefer watching than reading, feel free to take a look at our tutorial video [here](https://www.youtube.com/watch?v=7voAaJ2lzkc)",
92
+ "Hello there, I apologize for getting back to you a bit later, as we've been away during non-working hours. I hope your weekend went great! For your information, we have a feature to change the product image based on the option's selection. I have enabled this feature for your store, so feel free to follow our step-by-step instructions [here](https://support.tepo.app/en/article/change-product-images-based-on-selected-options-1831rew/) to set up this feature for your store. Please let me know if you encounter any difficulties. I am more than happy to help!",
93
+ "Hello, Thank you for contacting Tepo Support team! I hope you're having a wonderful day! To enlarge the size of the image swatches, you can refer to our guide [here](https://support.tepo.app/en/article/customize-style-for-app-options-using-css-26kmin/) for step-by-step instructions. This will allow you to make the necessary adjustments on your end. Feel free to give it a try, and if you encounter any difficulties or if coding isn't your forte, please don't hesitate to share the product URL with me. I'll be more than happy to assist further!",
94
+ 'Good day~ This is Robin from Tepo Support team! I hope your day has been amazing so far! To make sure I’m on the same page, when you say getting the older version of the option set, are you referring to undoing some changes after you’ve already hit save? If I’ve misunderstood anything, please don’t hesitate to correct me. I want to make sure I assist you as best as I can!',
95
+ "> Hello there, > This is Hazel from Tepo Support team. I hope your day is going great! > Thanks for sharing your concern with us. Regarding the packing slip, we do have a step-by-step instruction [here](https://support.tepo.app/en/article/how-to-show-options-in-shopify-packing-slip-1dyay7y/) that you can follow more easily on your end. Feel free to give it a try on your end to show Tepo options in your packing slip In Shopify, a courier slip is also known as a packing slip. I've seen that Hazel has sent you the instruction to add the code into the packing slip template to show the TEPO options already. May I ask if you give it a try on your end yet?",
96
+ ]
97
+ )
98
+ # [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...]
99
+ ```
100
+
101
+ <!--
102
+ ### Direct Usage (Transformers)
103
+
104
+ <details><summary>Click to see the direct usage in Transformers</summary>
105
+
106
+ </details>
107
+ -->
108
+
109
+ <!--
110
+ ### Downstream Usage (Sentence Transformers)
111
+
112
+ You can finetune this model on your own dataset.
113
+
114
+ <details><summary>Click to expand</summary>
115
+
116
+ </details>
117
+ -->
118
+
119
+ <!--
120
+ ### Out-of-Scope Use
121
+
122
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
123
+ -->
124
+
125
+ ## Evaluation
126
+
127
+ ### Metrics
128
+
129
+ #### Cross Encoder Reranking
130
+
131
+ * Dataset: `support-rerank-eval`
132
+ * Evaluated with [<code>CrossEncoderRerankingEvaluator</code>](https://sbert.net/docs/package_reference/cross_encoder/evaluation.html#sentence_transformers.cross_encoder.evaluation.CrossEncoderRerankingEvaluator) with these parameters:
133
+ ```json
134
+ {
135
+ "at_k": 10,
136
+ "always_rerank_positives": false
137
+ }
138
+ ```
139
+
140
+ | Metric | Value |
141
+ |:------------|:---------------------|
142
+ | map | 0.9087 (-0.0913) |
143
+ | mrr@10 | 0.9087 (-0.0913) |
144
+ | **ndcg@10** | **0.9315 (-0.0685)** |
145
+
146
+ <!--
147
+ ## Bias, Risks and Limitations
148
+
149
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
150
+ -->
151
+
152
+ <!--
153
+ ### Recommendations
154
+
155
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
156
+ -->
157
+
158
+ ## Training Details
159
+
160
+ ### Training Dataset
161
+
162
+ #### Unnamed Dataset
163
+
164
+ * Size: 5,400 training samples
165
+ * Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
166
+ * Approximate statistics based on the first 1000 samples:
167
+ | | sentence1 | sentence2 | label |
168
+ |:--------|:--------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------|:---------------------------------------------------------------|
169
+ | type | string | string | float |
170
+ | details | <ul><li>min: 28 characters</li><li>mean: 218.29 characters</li><li>max: 1961 characters</li></ul> | <ul><li>min: 141 characters</li><li>mean: 643.39 characters</li><li>max: 3722 characters</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.17</li><li>max: 1.0</li></ul> |
171
+ * Samples:
172
+ | sentence1 | sentence2 | label |
173
+ |:----------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------|
174
+ | <code>Hi, is there a way to show an image once the personalization toggle is on?</code> | <code>Hi there, This is Hazel from Tepo Support team. I hope your day is going great! Yes, you can ultilize our conditional settings to show an image based on the toggle's selection, as demonstrated on our demo product [here](https://tepo.app/products/conditional-logic) <3 For step-by-step instructions on how to set up conditional settings on your end, please check out our [guide](https://support.tepo.app/en/article/set-up-conditional-logic-1sp9tac/). If you prefer watching than reading, feel free to take a look at our tutorial video [here](https://www.youtube.com/watch?v=7voAaJ2lzkc)</code> | <code>1.0</code> |
175
+ | <code>Hi, is there a way to show an image once the personalization toggle is on?</code> | <code>Hello there, I apologize for getting back to you a bit later, as we've been away during non-working hours. I hope your weekend went great! For your information, we have a feature to change the product image based on the option's selection. I have enabled this feature for your store, so feel free to follow our step-by-step instructions [here](https://support.tepo.app/en/article/change-product-images-based-on-selected-options-1831rew/) to set up this feature for your store. Please let me know if you encounter any difficulties. I am more than happy to help!</code> | <code>0.0</code> |
176
+ | <code>Hi, is there a way to show an image once the personalization toggle is on?</code> | <code>Hello, Thank you for contacting Tepo Support team! I hope you're having a wonderful day! To enlarge the size of the image swatches, you can refer to our guide [here](https://support.tepo.app/en/article/customize-style-for-app-options-using-css-26kmin/) for step-by-step instructions. This will allow you to make the necessary adjustments on your end. Feel free to give it a try, and if you encounter any difficulties or if coding isn't your forte, please don't hesitate to share the product URL with me. I'll be more than happy to assist further!</code> | <code>0.0</code> |
177
+ * Loss: [<code>BinaryCrossEntropyLoss</code>](https://sbert.net/docs/package_reference/cross_encoder/losses.html#binarycrossentropyloss) with these parameters:
178
+ ```json
179
+ {
180
+ "activation_fn": "torch.nn.modules.linear.Identity",
181
+ "pos_weight": 5
182
+ }
183
+ ```
184
+
185
+ ### Training Hyperparameters
186
+ #### Non-Default Hyperparameters
187
+
188
+ - `eval_strategy`: steps
189
+ - `per_device_train_batch_size`: 1
190
+ - `gradient_accumulation_steps`: 32
191
+ - `learning_rate`: 1e-05
192
+ - `num_train_epochs`: 5
193
+ - `warmup_ratio`: 0.2
194
+ - `warmup_steps`: 0.2
195
+ - `seed`: 67
196
+ - `fp16`: True
197
+ - `load_best_model_at_end`: True
198
+
199
+ #### All Hyperparameters
200
+ <details><summary>Click to expand</summary>
201
+
202
+ - `do_predict`: False
203
+ - `eval_strategy`: steps
204
+ - `prediction_loss_only`: True
205
+ - `per_device_train_batch_size`: 1
206
+ - `per_device_eval_batch_size`: 8
207
+ - `gradient_accumulation_steps`: 32
208
+ - `eval_accumulation_steps`: None
209
+ - `torch_empty_cache_steps`: None
210
+ - `learning_rate`: 1e-05
211
+ - `weight_decay`: 0.0
212
+ - `adam_beta1`: 0.9
213
+ - `adam_beta2`: 0.999
214
+ - `adam_epsilon`: 1e-08
215
+ - `max_grad_norm`: 1.0
216
+ - `num_train_epochs`: 5
217
+ - `max_steps`: -1
218
+ - `lr_scheduler_type`: linear
219
+ - `lr_scheduler_kwargs`: None
220
+ - `warmup_ratio`: 0.2
221
+ - `warmup_steps`: 0.2
222
+ - `log_level`: passive
223
+ - `log_level_replica`: warning
224
+ - `log_on_each_node`: True
225
+ - `logging_nan_inf_filter`: True
226
+ - `enable_jit_checkpoint`: False
227
+ - `save_on_each_node`: False
228
+ - `save_only_model`: False
229
+ - `restore_callback_states_from_checkpoint`: False
230
+ - `use_cpu`: False
231
+ - `seed`: 67
232
+ - `data_seed`: None
233
+ - `bf16`: False
234
+ - `fp16`: True
235
+ - `bf16_full_eval`: False
236
+ - `fp16_full_eval`: False
237
+ - `tf32`: None
238
+ - `local_rank`: -1
239
+ - `ddp_backend`: None
240
+ - `debug`: []
241
+ - `dataloader_drop_last`: False
242
+ - `dataloader_num_workers`: 0
243
+ - `dataloader_prefetch_factor`: None
244
+ - `disable_tqdm`: True
245
+ - `remove_unused_columns`: True
246
+ - `label_names`: None
247
+ - `load_best_model_at_end`: True
248
+ - `ignore_data_skip`: False
249
+ - `fsdp`: []
250
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
251
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
252
+ - `parallelism_config`: None
253
+ - `deepspeed`: None
254
+ - `label_smoothing_factor`: 0.0
255
+ - `optim`: adamw_torch_fused
256
+ - `optim_args`: None
257
+ - `group_by_length`: False
258
+ - `length_column_name`: length
259
+ - `project`: huggingface
260
+ - `trackio_space_id`: trackio
261
+ - `ddp_find_unused_parameters`: None
262
+ - `ddp_bucket_cap_mb`: None
263
+ - `ddp_broadcast_buffers`: False
264
+ - `dataloader_pin_memory`: True
265
+ - `dataloader_persistent_workers`: False
266
+ - `skip_memory_metrics`: True
267
+ - `push_to_hub`: False
268
+ - `resume_from_checkpoint`: None
269
+ - `hub_model_id`: None
270
+ - `hub_strategy`: every_save
271
+ - `hub_private_repo`: None
272
+ - `hub_always_push`: False
273
+ - `hub_revision`: None
274
+ - `gradient_checkpointing`: False
275
+ - `gradient_checkpointing_kwargs`: None
276
+ - `include_for_metrics`: []
277
+ - `eval_do_concat_batches`: True
278
+ - `auto_find_batch_size`: False
279
+ - `full_determinism`: False
280
+ - `ddp_timeout`: 1800
281
+ - `torch_compile`: False
282
+ - `torch_compile_backend`: None
283
+ - `torch_compile_mode`: None
284
+ - `include_num_input_tokens_seen`: no
285
+ - `neftune_noise_alpha`: None
286
+ - `optim_target_modules`: None
287
+ - `batch_eval_metrics`: False
288
+ - `eval_on_start`: False
289
+ - `use_liger_kernel`: False
290
+ - `liger_kernel_config`: None
291
+ - `eval_use_gather_object`: False
292
+ - `average_tokens_across_devices`: True
293
+ - `use_cache`: False
294
+ - `prompts`: None
295
+ - `batch_sampler`: batch_sampler
296
+ - `multi_dataset_batch_sampler`: proportional
297
+ - `router_mapping`: {}
298
+ - `learning_rate_mapping`: {}
299
+
300
+ </details>
301
+
302
+ ### Training Logs
303
+ | Epoch | Step | Training Loss | support-rerank-eval_ndcg@10 |
304
+ |:----------:|:-------:|:-------------:|:---------------------------:|
305
+ | -1 | -1 | - | 0.8413 (-0.1587) |
306
+ | 0.0119 | 1 | 1.3864 | - |
307
+ | 0.0593 | 5 | 2.2658 | - |
308
+ | 0.1185 | 10 | 1.5262 | - |
309
+ | 0.1778 | 15 | 1.5737 | - |
310
+ | 0.2370 | 20 | 1.3171 | - |
311
+ | 0.2963 | 25 | 1.0806 | - |
312
+ | 0.3556 | 30 | 1.0587 | - |
313
+ | 0.4148 | 35 | 0.8149 | - |
314
+ | 0.4741 | 40 | 0.8706 | - |
315
+ | 0.5333 | 45 | 1.1330 | - |
316
+ | 0.5926 | 50 | 1.1210 | - |
317
+ | 0.6519 | 55 | 0.7105 | - |
318
+ | 0.7111 | 60 | 0.8596 | - |
319
+ | 0.7704 | 65 | 0.8416 | - |
320
+ | 0.8296 | 70 | 0.6543 | - |
321
+ | 0.8889 | 75 | 0.7784 | - |
322
+ | 0.9481 | 80 | 0.5754 | - |
323
+ | 1.0 | 85 | 0.7647 | - |
324
+ | 1.0593 | 90 | 0.5856 | - |
325
+ | 1.1185 | 95 | 0.5812 | - |
326
+ | 1.1778 | 100 | 0.5459 | 0.8906 (-0.1094) |
327
+ | 1.2370 | 105 | 0.5259 | - |
328
+ | 1.2963 | 110 | 0.6609 | - |
329
+ | 1.3556 | 115 | 0.5932 | - |
330
+ | 1.4148 | 120 | 0.5482 | - |
331
+ | 1.4741 | 125 | 0.7539 | - |
332
+ | 1.5333 | 130 | 0.6486 | - |
333
+ | 1.5926 | 135 | 0.6475 | - |
334
+ | 1.6519 | 140 | 0.5627 | - |
335
+ | 1.7111 | 145 | 0.6848 | - |
336
+ | 1.7704 | 150 | 0.6890 | - |
337
+ | 1.8296 | 155 | 0.5712 | - |
338
+ | 1.8889 | 160 | 0.5949 | - |
339
+ | 1.9481 | 165 | 0.7066 | - |
340
+ | 2.0 | 170 | 0.7013 | - |
341
+ | 2.0593 | 175 | 0.3729 | - |
342
+ | 2.1185 | 180 | 0.4327 | - |
343
+ | 2.1778 | 185 | 0.3703 | - |
344
+ | 2.2370 | 190 | 0.4843 | - |
345
+ | 2.2963 | 195 | 0.3460 | - |
346
+ | 2.3556 | 200 | 0.3679 | 0.9241 (-0.0759) |
347
+ | 2.4148 | 205 | 0.4412 | - |
348
+ | 2.4741 | 210 | 0.5300 | - |
349
+ | 2.5333 | 215 | 0.4922 | - |
350
+ | 2.5926 | 220 | 0.4407 | - |
351
+ | 2.6519 | 225 | 0.3835 | - |
352
+ | 2.7111 | 230 | 0.4581 | - |
353
+ | 2.7704 | 235 | 0.4687 | - |
354
+ | 2.8296 | 240 | 0.3968 | - |
355
+ | 2.8889 | 245 | 0.3373 | - |
356
+ | 2.9481 | 250 | 0.3882 | - |
357
+ | 3.0 | 255 | 0.5394 | - |
358
+ | 3.0593 | 260 | 0.3229 | - |
359
+ | 3.1185 | 265 | 0.2746 | - |
360
+ | 3.1778 | 270 | 0.4415 | - |
361
+ | 3.2370 | 275 | 0.2434 | - |
362
+ | 3.2963 | 280 | 0.3033 | - |
363
+ | 3.3556 | 285 | 0.3377 | - |
364
+ | 3.4148 | 290 | 0.3316 | - |
365
+ | 3.4741 | 295 | 0.2425 | - |
366
+ | 3.5333 | 300 | 0.3449 | 0.9141 (-0.0859) |
367
+ | 3.5926 | 305 | 0.2569 | - |
368
+ | 3.6519 | 310 | 0.3693 | - |
369
+ | 3.7111 | 315 | 0.2660 | - |
370
+ | 3.7704 | 320 | 0.3553 | - |
371
+ | 3.8296 | 325 | 0.3099 | - |
372
+ | 3.8889 | 330 | 0.2923 | - |
373
+ | 3.9481 | 335 | 0.3726 | - |
374
+ | 4.0 | 340 | 0.5681 | - |
375
+ | 4.0593 | 345 | 0.1964 | - |
376
+ | 4.1185 | 350 | 0.2471 | - |
377
+ | 4.1778 | 355 | 0.3227 | - |
378
+ | 4.2370 | 360 | 0.2911 | - |
379
+ | 4.2963 | 365 | 0.2578 | - |
380
+ | 4.3556 | 370 | 0.2402 | - |
381
+ | 4.4148 | 375 | 0.2367 | - |
382
+ | 4.4741 | 380 | 0.1998 | - |
383
+ | 4.5333 | 385 | 0.2359 | - |
384
+ | 4.5926 | 390 | 0.2177 | - |
385
+ | 4.6519 | 395 | 0.1999 | - |
386
+ | **4.7111** | **400** | **0.2293** | **0.9315 (-0.0685)** |
387
+ | 4.7704 | 405 | 0.2748 | - |
388
+ | 4.8296 | 410 | 0.2312 | - |
389
+ | 4.8889 | 415 | 0.3013 | - |
390
+ | 4.9481 | 420 | 0.1602 | - |
391
+ | 5.0 | 425 | 0.3283 | - |
392
+
393
+ * The bold row denotes the saved checkpoint.
394
+
395
+ ### Framework Versions
396
+ - Python: 3.12.12
397
+ - Sentence Transformers: 5.2.3
398
+ - Transformers: 5.0.0
399
+ - PyTorch: 2.10.0+cu128
400
+ - Accelerate: 1.12.0
401
+ - Datasets: 4.8.3
402
+ - Tokenizers: 0.22.2
403
+
404
+ ## Citation
405
+
406
+ ### BibTeX
407
+
408
+ #### Sentence Transformers
409
+ ```bibtex
410
+ @inproceedings{reimers-2019-sentence-bert,
411
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
412
+ author = "Reimers, Nils and Gurevych, Iryna",
413
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
414
+ month = "11",
415
+ year = "2019",
416
+ publisher = "Association for Computational Linguistics",
417
+ url = "https://arxiv.org/abs/1908.10084",
418
+ }
419
+ ```
420
+
421
+ <!--
422
+ ## Glossary
423
+
424
+ *Clearly define terms in order to be accessible across audiences.*
425
+ -->
426
+
427
+ <!--
428
+ ## Model Card Authors
429
+
430
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
431
+ -->
432
+
433
+ <!--
434
+ ## Model Card Contact
435
+
436
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
437
+ -->
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "dtype": "float32",
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 1024,
14
+ "id2label": {
15
+ "0": "LABEL_0"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 4096,
19
+ "is_decoder": false,
20
+ "label2id": {
21
+ "LABEL_0": 0
22
+ },
23
+ "layer_norm_eps": 1e-05,
24
+ "max_position_embeddings": 514,
25
+ "model_type": "xlm-roberta",
26
+ "num_attention_heads": 16,
27
+ "num_hidden_layers": 24,
28
+ "output_past": true,
29
+ "pad_token_id": 1,
30
+ "position_embedding_type": "absolute",
31
+ "sentence_transformers": {
32
+ "activation_fn": "torch.nn.modules.activation.Sigmoid",
33
+ "version": "5.2.3"
34
+ },
35
+ "tie_word_embeddings": true,
36
+ "transformers_version": "5.0.0",
37
+ "type_vocab_size": 1,
38
+ "use_cache": false,
39
+ "vocab_size": 250002
40
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:001ea1602477c265b6b88a46241accc307929d077a4eb61141967c0a7ddd9c8a
3
+ size 2239614524
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:370910e804ee5949718cd949e92ce47a6b816751b71b5569a2eedddc83eac50d
3
+ size 16781737
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<s>",
5
+ "clean_up_tokenization_spaces": true,
6
+ "cls_token": "<s>",
7
+ "eos_token": "</s>",
8
+ "is_local": false,
9
+ "mask_token": "<mask>",
10
+ "model_max_length": 512,
11
+ "pad_token": "<pad>",
12
+ "sep_token": "</s>",
13
+ "sp_model_kwargs": {},
14
+ "tokenizer_class": "XLMRobertaTokenizer",
15
+ "unk_token": "<unk>"
16
+ }