Hugging Face's logo

vaibhav-ceew
/
onet-msmacroL6

Text Ranking
sentence-transformers
Safetensors
bert
cross-encoder
Generated from Trainer
dataset_size:17639
loss:BinaryCrossEntropyLoss
Eval Results (legacy)
text-embeddings-inference
Model card Files
xet
 Community
vaibhav-ceew commited on
Commit
68e2c2d
·
verified ·
1 Parent(s): c0aabad

Upload folder using huggingface_hub

Browse files
Files changed (8) hide show
  1. .gitattributes +1 -0
  2. README.md +838 -3
  3. config.json +36 -0
  4. model.safetensors +3 -0
  5. sentencepiece.bpe.model +3 -0
  6. special_tokens_map.json +51 -0
  7. tokenizer.json +3 -0
  8. tokenizer_config.json +56 -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 CHANGED
@@ -1,3 +1,838 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - sentence-transformers
4
+ - cross-encoder
5
+ - generated_from_trainer
6
+ - dataset_size:17639
7
+ - loss:BinaryCrossEntropyLoss
8
+ base_model: cross-encoder/msmarco-MiniLM-L6-en-de-v1
9
+ pipeline_tag: text-ranking
10
+ library_name: sentence-transformers
11
+ metrics:
12
+ - pearson
13
+ - spearman
14
+ model-index:
15
+ - name: CrossEncoder based on cross-encoder/msmarco-MiniLM-L6-en-de-v1
16
+ results:
17
+ - task:
18
+ type: cross-encoder-correlation
19
+ name: Cross Encoder Correlation
20
+ dataset:
21
+ name: onet validation
22
+ type: onet-validation
23
+ metrics:
24
+ - type: pearson
25
+ value: 0.8246902137614378
26
+ name: Pearson
27
+ - type: spearman
28
+ value: 0.8073346678301418
29
+ name: Spearman
30
+ - type: pearson
31
+ value: 0.8080619777425957
32
+ name: Pearson
33
+ - type: spearman
34
+ value: 0.7875635794780041
35
+ name: Spearman
36
+ ---
37
+
38
+ # CrossEncoder based on cross-encoder/msmarco-MiniLM-L6-en-de-v1
39
+
40
+ This is a [Cross Encoder](https://www.sbert.net/docs/cross_encoder/usage/usage.html) model finetuned from [cross-encoder/msmarco-MiniLM-L6-en-de-v1](https://huggingface.co/cross-encoder/msmarco-MiniLM-L6-en-de-v1) on the csv dataset 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.
41
+
42
+ ## Model Details
43
+
44
+ ### Model Description
45
+ - **Model Type:** Cross Encoder
46
+ - **Base model:** [cross-encoder/msmarco-MiniLM-L6-en-de-v1](https://huggingface.co/cross-encoder/msmarco-MiniLM-L6-en-de-v1) <!-- at revision 9eb610d90d409cfefb7422e13debd405f8465af6 -->
47
+ - **Maximum Sequence Length:** 512 tokens
48
+ - **Number of Output Labels:** 1 label
49
+ - **Training Dataset:**
50
+ - csv
51
+ <!-- - **Language:** Unknown -->
52
+ <!-- - **License:** Unknown -->
53
+
54
+ ### Model Sources
55
+
56
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
57
+ - **Documentation:** [Cross Encoder Documentation](https://www.sbert.net/docs/cross_encoder/usage/usage.html)
58
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
59
+ - **Hugging Face:** [Cross Encoders on Hugging Face](https://huggingface.co/models?library=sentence-transformers&other=cross-encoder)
60
+
61
+ ## Usage
62
+
63
+ ### Direct Usage (Sentence Transformers)
64
+
65
+ First install the Sentence Transformers library:
66
+
67
+ ```bash
68
+ pip install -U sentence-transformers
69
+ ```
70
+
71
+ Then you can load this model and run inference.
72
+ ```python
73
+ from sentence_transformers import CrossEncoder
74
+
75
+ # Download from the 🤗 Hub
76
+ model = CrossEncoder("cross_encoder_model_id")
77
+ # Get scores for pairs of texts
78
+ pairs = [
79
+ ['Chief Executives:Determine and formulate policies and provide overall direction of companies or private and public sector organizations within guidelines set up by a board of directors or similar governing body. Plan, direct, or coordinate operational activities at the highest level of management with the help of subordinate executives and staff managers.', "Direct or coordinate an organization's financial or budget activities to fund operations, maximize investments, or increase efficiency."],
80
+ ['Chief Executives:Determine and formulate policies and provide overall direction of companies or private and public sector organizations within guidelines set up by a board of directors or similar governing body. Plan, direct, or coordinate operational activities at the highest level of management with the help of subordinate executives and staff managers.', 'Confer with board members, organization officials, or staff members to discuss issues, coordinate activities, or resolve problems.'],
81
+ ['Chief Executives:Determine and formulate policies and provide overall direction of companies or private and public sector organizations within guidelines set up by a board of directors or similar governing body. Plan, direct, or coordinate operational activities at the highest level of management with the help of subordinate executives and staff managers.', 'Prepare budgets for approval, including those for funding or implementation of programs.'],
82
+ ['Chief Executives:Determine and formulate policies and provide overall direction of companies or private and public sector organizations within guidelines set up by a board of directors or similar governing body. Plan, direct, or coordinate operational activities at the highest level of management with the help of subordinate executives and staff managers.', 'Direct, plan, or implement policies, objectives, or activities of organizations or businesses to ensure continuing operations, to maximize returns on investments, or to increase productivity.'],
83
+ ['Chief Executives:Determine and formulate policies and provide overall direction of companies or private and public sector organizations within guidelines set up by a board of directors or similar governing body. Plan, direct, or coordinate operational activities at the highest level of management with the help of subordinate executives and staff managers.', 'Prepare or present reports concerning activities, expenses, budgets, government statutes or rulings, or other items affecting businesses or program services.'],
84
+ ]
85
+ scores = model.predict(pairs)
86
+ print(scores.shape)
87
+ # (5,)
88
+
89
+ # Or rank different texts based on similarity to a single text
90
+ ranks = model.rank(
91
+ 'Chief Executives:Determine and formulate policies and provide overall direction of companies or private and public sector organizations within guidelines set up by a board of directors or similar governing body. Plan, direct, or coordinate operational activities at the highest level of management with the help of subordinate executives and staff managers.',
92
+ [
93
+ "Direct or coordinate an organization's financial or budget activities to fund operations, maximize investments, or increase efficiency.",
94
+ 'Confer with board members, organization officials, or staff members to discuss issues, coordinate activities, or resolve problems.',
95
+ 'Prepare budgets for approval, including those for funding or implementation of programs.',
96
+ 'Direct, plan, or implement policies, objectives, or activities of organizations or businesses to ensure continuing operations, to maximize returns on investments, or to increase productivity.',
97
+ 'Prepare or present reports concerning activities, expenses, budgets, government statutes or rulings, or other items affecting businesses or program services.',
98
+ ]
99
+ )
100
+ # [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...]
101
+ ```
102
+
103
+ <!--
104
+ ### Direct Usage (Transformers)
105
+
106
+ <details><summary>Click to see the direct usage in Transformers</summary>
107
+
108
+ </details>
109
+ -->
110
+
111
+ <!--
112
+ ### Downstream Usage (Sentence Transformers)
113
+
114
+ You can finetune this model on your own dataset.
115
+
116
+ <details><summary>Click to expand</summary>
117
+
118
+ </details>
119
+ -->
120
+
121
+ <!--
122
+ ### Out-of-Scope Use
123
+
124
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
125
+ -->
126
+
127
+ ## Evaluation
128
+
129
+ ### Metrics
130
+
131
+ #### Cross Encoder Correlation
132
+
133
+ * Dataset: `onet-validation`
134
+ * Evaluated with [<code>CrossEncoderCorrelationEvaluator</code>](https://sbert.net/docs/package_reference/cross_encoder/evaluation.html#sentence_transformers.cross_encoder.evaluation.CrossEncoderCorrelationEvaluator)
135
+
136
+ | Metric | Value |
137
+ |:-------------|:-----------|
138
+ | pearson | 0.8247 |
139
+ | **spearman** | **0.8073** |
140
+
141
+ #### Cross Encoder Correlation
142
+
143
+ * Dataset: `onet-validation`
144
+ * Evaluated with [<code>CrossEncoderCorrelationEvaluator</code>](https://sbert.net/docs/package_reference/cross_encoder/evaluation.html#sentence_transformers.cross_encoder.evaluation.CrossEncoderCorrelationEvaluator)
145
+
146
+ | Metric | Value |
147
+ |:-------------|:-----------|
148
+ | pearson | 0.8081 |
149
+ | **spearman** | **0.7876** |
150
+
151
+ <!--
152
+ ## Bias, Risks and Limitations
153
+
154
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
155
+ -->
156
+
157
+ <!--
158
+ ### Recommendations
159
+
160
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
161
+ -->
162
+
163
+ ## Training Details
164
+
165
+ ### Training Dataset
166
+
167
+ #### csv
168
+
169
+ * Dataset: csv
170
+ * Size: 17,639 training samples
171
+ * Columns: <code>query</code>, <code>task</code>, and <code>score</code>
172
+ * Approximate statistics based on the first 1000 samples:
173
+ | | query | task | score |
174
+ |:--------|:--------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------|:----------------------------------------------------------------|
175
+ | type | string | string | float |
176
+ | details | <ul><li>min: 105 characters</li><li>mean: 235.78 characters</li><li>max: 562 characters</li></ul> | <ul><li>min: 20 characters</li><li>mean: 103.24 characters</li><li>max: 317 characters</li></ul> | <ul><li>min: 0.42</li><li>mean: 0.8</li><li>max: 0.98</li></ul> |
177
+ * Samples:
178
+ | query | task | score |
179
+ |:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------|
180
+ | <code>Chief Executives:Determine and formulate policies and provide overall direction of companies or private and public sector organizations within guidelines set up by a board of directors or similar governing body. Plan, direct, or coordinate operational activities at the highest level of management with the help of subordinate executives and staff managers.</code> | <code>Direct or coordinate an organization's financial or budget activities to fund operations, maximize investments, or increase efficiency.</code> | <code>0.8242</code> |
181
+ | <code>Chief Executives:Determine and formulate policies and provide overall direction of companies or private and public sector organizations within guidelines set up by a board of directors or similar governing body. Plan, direct, or coordinate operational activities at the highest level of management with the help of subordinate executives and staff managers.</code> | <code>Confer with board members, organization officials, or staff members to discuss issues, coordinate activities, or resolve problems.</code> | <code>0.84055</code> |
182
+ | <code>Chief Executives:Determine and formulate policies and provide overall direction of companies or private and public sector organizations within guidelines set up by a board of directors or similar governing body. Plan, direct, or coordinate operational activities at the highest level of management with the help of subordinate executives and staff managers.</code> | <code>Prepare budgets for approval, including those for funding or implementation of programs.</code> | <code>0.89705</code> |
183
+ * Loss: [<code>BinaryCrossEntropyLoss</code>](https://sbert.net/docs/package_reference/cross_encoder/losses.html#binarycrossentropyloss) with these parameters:
184
+ ```json
185
+ {
186
+ "activation_fn": "torch.nn.modules.linear.Identity",
187
+ "pos_weight": null
188
+ }
189
+ ```
190
+
191
+ ### Evaluation Dataset
192
+
193
+ #### csv
194
+
195
+ * Dataset: csv
196
+ * Size: 1,764 evaluation samples
197
+ * Columns: <code>query</code>, <code>task</code>, and <code>score</code>
198
+ * Approximate statistics based on the first 1000 samples:
199
+ | | query | task | score |
200
+ |:--------|:--------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------|:----------------------------------------------------------------|
201
+ | type | string | string | float |
202
+ | details | <ul><li>min: 105 characters</li><li>mean: 235.78 characters</li><li>max: 562 characters</li></ul> | <ul><li>min: 20 characters</li><li>mean: 103.24 characters</li><li>max: 317 characters</li></ul> | <ul><li>min: 0.42</li><li>mean: 0.8</li><li>max: 0.98</li></ul> |
203
+ * Samples:
204
+ | query | task | score |
205
+ |:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------|
206
+ | <code>Chief Executives:Determine and formulate policies and provide overall direction of companies or private and public sector organizations within guidelines set up by a board of directors or similar governing body. Plan, direct, or coordinate operational activities at the highest level of management with the help of subordinate executives and staff managers.</code> | <code>Direct or coordinate an organization's financial or budget activities to fund operations, maximize investments, or increase efficiency.</code> | <code>0.8242</code> |
207
+ | <code>Chief Executives:Determine and formulate policies and provide overall direction of companies or private and public sector organizations within guidelines set up by a board of directors or similar governing body. Plan, direct, or coordinate operational activities at the highest level of management with the help of subordinate executives and staff managers.</code> | <code>Confer with board members, organization officials, or staff members to discuss issues, coordinate activities, or resolve problems.</code> | <code>0.84055</code> |
208
+ | <code>Chief Executives:Determine and formulate policies and provide overall direction of companies or private and public sector organizations within guidelines set up by a board of directors or similar governing body. Plan, direct, or coordinate operational activities at the highest level of management with the help of subordinate executives and staff managers.</code> | <code>Prepare budgets for approval, including those for funding or implementation of programs.</code> | <code>0.89705</code> |
209
+ * Loss: [<code>BinaryCrossEntropyLoss</code>](https://sbert.net/docs/package_reference/cross_encoder/losses.html#binarycrossentropyloss) with these parameters:
210
+ ```json
211
+ {
212
+ "activation_fn": "torch.nn.modules.linear.Identity",
213
+ "pos_weight": null
214
+ }
215
+ ```
216
+
217
+ ### Training Hyperparameters
218
+ #### Non-Default Hyperparameters
219
+
220
+ - `eval_strategy`: steps
221
+ - `num_train_epochs`: 4
222
+ - `warmup_ratio`: 0.1
223
+ - `bf16`: True
224
+
225
+ #### All Hyperparameters
226
+ <details><summary>Click to expand</summary>
227
+
228
+ - `overwrite_output_dir`: False
229
+ - `do_predict`: False
230
+ - `eval_strategy`: steps
231
+ - `prediction_loss_only`: True
232
+ - `per_device_train_batch_size`: 8
233
+ - `per_device_eval_batch_size`: 8
234
+ - `per_gpu_train_batch_size`: None
235
+ - `per_gpu_eval_batch_size`: None
236
+ - `gradient_accumulation_steps`: 1
237
+ - `eval_accumulation_steps`: None
238
+ - `torch_empty_cache_steps`: None
239
+ - `learning_rate`: 5e-05
240
+ - `weight_decay`: 0.0
241
+ - `adam_beta1`: 0.9
242
+ - `adam_beta2`: 0.999
243
+ - `adam_epsilon`: 1e-08
244
+ - `max_grad_norm`: 1.0
245
+ - `num_train_epochs`: 4
246
+ - `max_steps`: -1
247
+ - `lr_scheduler_type`: linear
248
+ - `lr_scheduler_kwargs`: {}
249
+ - `warmup_ratio`: 0.1
250
+ - `warmup_steps`: 0
251
+ - `log_level`: passive
252
+ - `log_level_replica`: warning
253
+ - `log_on_each_node`: True
254
+ - `logging_nan_inf_filter`: True
255
+ - `save_safetensors`: True
256
+ - `save_on_each_node`: False
257
+ - `save_only_model`: False
258
+ - `restore_callback_states_from_checkpoint`: False
259
+ - `no_cuda`: False
260
+ - `use_cpu`: False
261
+ - `use_mps_device`: False
262
+ - `seed`: 42
263
+ - `data_seed`: None
264
+ - `jit_mode_eval`: False
265
+ - `use_ipex`: False
266
+ - `bf16`: True
267
+ - `fp16`: False
268
+ - `fp16_opt_level`: O1
269
+ - `half_precision_backend`: auto
270
+ - `bf16_full_eval`: False
271
+ - `fp16_full_eval`: False
272
+ - `tf32`: None
273
+ - `local_rank`: 0
274
+ - `ddp_backend`: None
275
+ - `tpu_num_cores`: None
276
+ - `tpu_metrics_debug`: False
277
+ - `debug`: []
278
+ - `dataloader_drop_last`: False
279
+ - `dataloader_num_workers`: 0
280
+ - `dataloader_prefetch_factor`: None
281
+ - `past_index`: -1
282
+ - `disable_tqdm`: False
283
+ - `remove_unused_columns`: True
284
+ - `label_names`: None
285
+ - `load_best_model_at_end`: False
286
+ - `ignore_data_skip`: False
287
+ - `fsdp`: []
288
+ - `fsdp_min_num_params`: 0
289
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
290
+ - `tp_size`: 0
291
+ - `fsdp_transformer_layer_cls_to_wrap`: None
292
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
293
+ - `deepspeed`: None
294
+ - `label_smoothing_factor`: 0.0
295
+ - `optim`: adamw_torch
296
+ - `optim_args`: None
297
+ - `adafactor`: False
298
+ - `group_by_length`: False
299
+ - `length_column_name`: length
300
+ - `ddp_find_unused_parameters`: None
301
+ - `ddp_bucket_cap_mb`: None
302
+ - `ddp_broadcast_buffers`: False
303
+ - `dataloader_pin_memory`: True
304
+ - `dataloader_persistent_workers`: False
305
+ - `skip_memory_metrics`: True
306
+ - `use_legacy_prediction_loop`: False
307
+ - `push_to_hub`: False
308
+ - `resume_from_checkpoint`: None
309
+ - `hub_model_id`: None
310
+ - `hub_strategy`: every_save
311
+ - `hub_private_repo`: None
312
+ - `hub_always_push`: False
313
+ - `gradient_checkpointing`: False
314
+ - `gradient_checkpointing_kwargs`: None
315
+ - `include_inputs_for_metrics`: False
316
+ - `include_for_metrics`: []
317
+ - `eval_do_concat_batches`: True
318
+ - `fp16_backend`: auto
319
+ - `push_to_hub_model_id`: None
320
+ - `push_to_hub_organization`: None
321
+ - `mp_parameters`:
322
+ - `auto_find_batch_size`: False
323
+ - `full_determinism`: False
324
+ - `torchdynamo`: None
325
+ - `ray_scope`: last
326
+ - `ddp_timeout`: 1800
327
+ - `torch_compile`: False
328
+ - `torch_compile_backend`: None
329
+ - `torch_compile_mode`: None
330
+ - `include_tokens_per_second`: False
331
+ - `include_num_input_tokens_seen`: False
332
+ - `neftune_noise_alpha`: None
333
+ - `optim_target_modules`: None
334
+ - `batch_eval_metrics`: False
335
+ - `eval_on_start`: False
336
+ - `use_liger_kernel`: False
337
+ - `eval_use_gather_object`: False
338
+ - `average_tokens_across_devices`: False
339
+ - `prompts`: None
340
+ - `batch_sampler`: batch_sampler
341
+ - `multi_dataset_batch_sampler`: proportional
342
+
343
+ </details>
344
+
345
+ ### Training Logs
346
+ <details><summary>Click to expand</summary>
347
+
348
+ | Epoch | Step | Training Loss | Validation Loss | onet-validation_spearman |
349
+ |:------:|:----:|:-------------:|:---------------:|:------------------------:|
350
+ | -1 | -1 | - | - | 0.0090 |
351
+ | 0.0091 | 20 | 1.2693 | - | - |
352
+ | 0.0181 | 40 | 1.3548 | - | - |
353
+ | 0.0272 | 60 | 1.0328 | - | - |
354
+ | 0.0363 | 80 | 0.9504 | 0.8379 | 0.0108 |
355
+ | 0.0454 | 100 | 0.9183 | - | - |
356
+ | 0.0544 | 120 | 0.697 | - | - |
357
+ | 0.0635 | 140 | 0.625 | - | - |
358
+ | 0.0726 | 160 | 0.5337 | 0.5489 | 0.0368 |
359
+ | 0.0816 | 180 | 0.5008 | - | - |
360
+ | 0.0907 | 200 | 0.4894 | - | - |
361
+ | 0.0998 | 220 | 0.5352 | - | - |
362
+ | 0.1088 | 240 | 0.4994 | 0.5040 | 0.0981 |
363
+ | 0.1179 | 260 | 0.4857 | - | - |
364
+ | 0.1270 | 280 | 0.5122 | - | - |
365
+ | 0.1361 | 300 | 0.517 | - | - |
366
+ | 0.1451 | 320 | 0.5156 | 0.4994 | 0.1470 |
367
+ | 0.1542 | 340 | 0.4859 | - | - |
368
+ | 0.1633 | 360 | 0.4842 | - | - |
369
+ | 0.1723 | 380 | 0.5138 | - | - |
370
+ | 0.1814 | 400 | 0.5142 | 0.5011 | 0.1403 |
371
+ | 0.1905 | 420 | 0.4948 | - | - |
372
+ | 0.1995 | 440 | 0.499 | - | - |
373
+ | 0.2086 | 460 | 0.4732 | - | - |
374
+ | 0.2177 | 480 | 0.5066 | 0.5007 | 0.1681 |
375
+ | 0.2268 | 500 | 0.5014 | - | - |
376
+ | 0.2358 | 520 | 0.4819 | - | - |
377
+ | 0.2449 | 540 | 0.4937 | - | - |
378
+ | 0.2540 | 560 | 0.5056 | 0.4974 | 0.2359 |
379
+ | 0.2630 | 580 | 0.4986 | - | - |
380
+ | 0.2721 | 600 | 0.5066 | - | - |
381
+ | 0.2812 | 620 | 0.4776 | - | - |
382
+ | 0.2902 | 640 | 0.4845 | 0.5024 | 0.2607 |
383
+ | 0.2993 | 660 | 0.4991 | - | - |
384
+ | 0.3084 | 680 | 0.5034 | - | - |
385
+ | 0.3175 | 700 | 0.4655 | - | - |
386
+ | 0.3265 | 720 | 0.5191 | 0.5107 | 0.2969 |
387
+ | 0.3356 | 740 | 0.509 | - | - |
388
+ | 0.3447 | 760 | 0.484 | - | - |
389
+ | 0.3537 | 780 | 0.5113 | - | - |
390
+ | 0.3628 | 800 | 0.4968 | 0.4966 | 0.3645 |
391
+ | 0.3719 | 820 | 0.4713 | - | - |
392
+ | 0.3810 | 840 | 0.507 | - | - |
393
+ | 0.3900 | 860 | 0.5041 | - | - |
394
+ | 0.3991 | 880 | 0.4868 | 0.4953 | 0.3896 |
395
+ | 0.4082 | 900 | 0.4985 | - | - |
396
+ | 0.4172 | 920 | 0.477 | - | - |
397
+ | 0.4263 | 940 | 0.4888 | - | - |
398
+ | 0.4354 | 960 | 0.4791 | 0.4916 | 0.4280 |
399
+ | 0.4444 | 980 | 0.4969 | - | - |
400
+ | 0.4535 | 1000 | 0.4757 | - | - |
401
+ | 0.4626 | 1020 | 0.4978 | - | - |
402
+ | 0.4717 | 1040 | 0.4998 | 0.4966 | 0.4299 |
403
+ | 0.4807 | 1060 | 0.5062 | - | - |
404
+ | 0.4898 | 1080 | 0.4876 | - | - |
405
+ | 0.4989 | 1100 | 0.4836 | - | - |
406
+ | 0.5079 | 1120 | 0.5034 | 0.4908 | 0.4404 |
407
+ | 0.5170 | 1140 | 0.4788 | - | - |
408
+ | 0.5261 | 1160 | 0.5037 | - | - |
409
+ | 0.5351 | 1180 | 0.467 | - | - |
410
+ | 0.5442 | 1200 | 0.4785 | 0.4942 | 0.4701 |
411
+ | 0.5533 | 1220 | 0.502 | - | - |
412
+ | 0.5624 | 1240 | 0.5223 | - | - |
413
+ | 0.5714 | 1260 | 0.4755 | - | - |
414
+ | 0.5805 | 1280 | 0.4826 | 0.4888 | 0.4685 |
415
+ | 0.5896 | 1300 | 0.493 | - | - |
416
+ | 0.5986 | 1320 | 0.4935 | - | - |
417
+ | 0.6077 | 1340 | 0.4851 | - | - |
418
+ | 0.6168 | 1360 | 0.4884 | 0.4908 | 0.5028 |
419
+ | 0.6259 | 1380 | 0.4966 | - | - |
420
+ | 0.6349 | 1400 | 0.4769 | - | - |
421
+ | 0.6440 | 1420 | 0.4965 | - | - |
422
+ | 0.6531 | 1440 | 0.492 | 0.4869 | 0.5234 |
423
+ | 0.6621 | 1460 | 0.487 | - | - |
424
+ | 0.6712 | 1480 | 0.5045 | - | - |
425
+ | 0.6803 | 1500 | 0.4638 | - | - |
426
+ | 0.6893 | 1520 | 0.4622 | 0.4874 | 0.5281 |
427
+ | 0.6984 | 1540 | 0.468 | - | - |
428
+ | 0.7075 | 1560 | 0.4627 | - | - |
429
+ | 0.7166 | 1580 | 0.4892 | - | - |
430
+ | 0.7256 | 1600 | 0.5044 | 0.4885 | 0.5219 |
431
+ | 0.7347 | 1620 | 0.4941 | - | - |
432
+ | 0.7438 | 1640 | 0.4857 | - | - |
433
+ | 0.7528 | 1660 | 0.497 | - | - |
434
+ | 0.7619 | 1680 | 0.5007 | 0.4925 | 0.5146 |
435
+ | 0.7710 | 1700 | 0.5038 | - | - |
436
+ | 0.7800 | 1720 | 0.4702 | - | - |
437
+ | 0.7891 | 1740 | 0.4754 | - | - |
438
+ | 0.7982 | 1760 | 0.4852 | 0.4874 | 0.5402 |
439
+ | 0.8073 | 1780 | 0.4858 | - | - |
440
+ | 0.8163 | 1800 | 0.493 | - | - |
441
+ | 0.8254 | 1820 | 0.4802 | - | - |
442
+ | 0.8345 | 1840 | 0.4905 | 0.4865 | 0.5370 |
443
+ | 0.8435 | 1860 | 0.5 | - | - |
444
+ | 0.8526 | 1880 | 0.4888 | - | - |
445
+ | 0.8617 | 1900 | 0.4764 | - | - |
446
+ | 0.8707 | 1920 | 0.4647 | 0.4885 | 0.5100 |
447
+ | 0.8798 | 1940 | 0.4714 | - | - |
448
+ | 0.8889 | 1960 | 0.497 | - | - |
449
+ | 0.8980 | 1980 | 0.4878 | - | - |
450
+ | 0.9070 | 2000 | 0.4906 | 0.4855 | 0.5633 |
451
+ | 0.9161 | 2020 | 0.5018 | - | - |
452
+ | 0.9252 | 2040 | 0.4998 | - | - |
453
+ | 0.9342 | 2060 | 0.4619 | - | - |
454
+ | 0.9433 | 2080 | 0.4722 | 0.4855 | 0.5575 |
455
+ | 0.9524 | 2100 | 0.487 | - | - |
456
+ | 0.9615 | 2120 | 0.4798 | - | - |
457
+ | 0.9705 | 2140 | 0.46 | - | - |
458
+ | 0.9796 | 2160 | 0.4683 | 0.4844 | 0.5710 |
459
+ | 0.9887 | 2180 | 0.5026 | - | - |
460
+ | 0.9977 | 2200 | 0.4905 | - | - |
461
+ | 1.0068 | 2220 | 0.5008 | - | - |
462
+ | 1.0159 | 2240 | 0.4918 | 0.4832 | 0.5951 |
463
+ | 1.0249 | 2260 | 0.4809 | - | - |
464
+ | 1.0340 | 2280 | 0.4964 | - | - |
465
+ | 1.0431 | 2300 | 0.4562 | - | - |
466
+ | 1.0522 | 2320 | 0.4529 | 0.4862 | 0.5884 |
467
+ | 1.0612 | 2340 | 0.4689 | - | - |
468
+ | 1.0703 | 2360 | 0.4811 | - | - |
469
+ | 1.0794 | 2380 | 0.4822 | - | - |
470
+ | 1.0884 | 2400 | 0.4944 | 0.4832 | 0.5892 |
471
+ | 1.0975 | 2420 | 0.5001 | - | - |
472
+ | 1.1066 | 2440 | 0.4912 | - | - |
473
+ | 1.1156 | 2460 | 0.4826 | - | - |
474
+ | 1.1247 | 2480 | 0.47 | 0.4834 | 0.5988 |
475
+ | 1.1338 | 2500 | 0.4818 | - | - |
476
+ | 1.1429 | 2520 | 0.4648 | - | - |
477
+ | 1.1519 | 2540 | 0.4687 | - | - |
478
+ | 1.1610 | 2560 | 0.4737 | 0.4837 | 0.5984 |
479
+ | 1.1701 | 2580 | 0.4789 | - | - |
480
+ | 1.1791 | 2600 | 0.4876 | - | - |
481
+ | 1.1882 | 2620 | 0.4952 | - | - |
482
+ | 1.1973 | 2640 | 0.4861 | 0.4823 | 0.5981 |
483
+ | 1.2063 | 2660 | 0.4758 | - | - |
484
+ | 1.2154 | 2680 | 0.4927 | - | - |
485
+ | 1.2245 | 2700 | 0.4897 | - | - |
486
+ | 1.2336 | 2720 | 0.4785 | 0.4835 | 0.6037 |
487
+ | 1.2426 | 2740 | 0.5027 | - | - |
488
+ | 1.2517 | 2760 | 0.4776 | - | - |
489
+ | 1.2608 | 2780 | 0.445 | - | - |
490
+ | 1.2698 | 2800 | 0.4675 | 0.4844 | 0.6264 |
491
+ | 1.2789 | 2820 | 0.4646 | - | - |
492
+ | 1.2880 | 2840 | 0.4822 | - | - |
493
+ | 1.2971 | 2860 | 0.4669 | - | - |
494
+ | 1.3061 | 2880 | 0.4817 | 0.4823 | 0.6375 |
495
+ | 1.3152 | 2900 | 0.4759 | - | - |
496
+ | 1.3243 | 2920 | 0.4876 | - | - |
497
+ | 1.3333 | 2940 | 0.4689 | - | - |
498
+ | 1.3424 | 2960 | 0.4751 | 0.4807 | 0.6520 |
499
+ | 1.3515 | 2980 | 0.4872 | - | - |
500
+ | 1.3605 | 3000 | 0.4543 | - | - |
501
+ | 1.3696 | 3020 | 0.4687 | - | - |
502
+ | 1.3787 | 3040 | 0.4759 | 0.4819 | 0.6136 |
503
+ | 1.3878 | 3060 | 0.4827 | - | - |
504
+ | 1.3968 | 3080 | 0.4876 | - | - |
505
+ | 1.4059 | 3100 | 0.4791 | - | - |
506
+ | 1.4150 | 3120 | 0.4887 | 0.4818 | 0.6314 |
507
+ | 1.4240 | 3140 | 0.4863 | - | - |
508
+ | 1.4331 | 3160 | 0.4864 | - | - |
509
+ | 1.4422 | 3180 | 0.4824 | - | - |
510
+ | 1.4512 | 3200 | 0.4974 | 0.4829 | 0.6645 |
511
+ | 1.4603 | 3220 | 0.4554 | - | - |
512
+ | 1.4694 | 3240 | 0.484 | - | - |
513
+ | 1.4785 | 3260 | 0.4735 | - | - |
514
+ | 1.4875 | 3280 | 0.504 | 0.4832 | 0.6617 |
515
+ | 1.4966 | 3300 | 0.4758 | - | - |
516
+ | 1.5057 | 3320 | 0.4711 | - | - |
517
+ | 1.5147 | 3340 | 0.486 | - | - |
518
+ | 1.5238 | 3360 | 0.4751 | 0.4815 | 0.6502 |
519
+ | 1.5329 | 3380 | 0.4761 | - | - |
520
+ | 1.5420 | 3400 | 0.467 | - | - |
521
+ | 1.5510 | 3420 | 0.4706 | - | - |
522
+ | 1.5601 | 3440 | 0.4894 | 0.4798 | 0.6549 |
523
+ | 1.5692 | 3460 | 0.4795 | - | - |
524
+ | 1.5782 | 3480 | 0.4922 | - | - |
525
+ | 1.5873 | 3500 | 0.4763 | - | - |
526
+ | 1.5964 | 3520 | 0.4801 | 0.4804 | 0.6608 |
527
+ | 1.6054 | 3540 | 0.4692 | - | - |
528
+ | 1.6145 | 3560 | 0.4886 | - | - |
529
+ | 1.6236 | 3580 | 0.4758 | - | - |
530
+ | 1.6327 | 3600 | 0.456 | 0.4801 | 0.6651 |
531
+ | 1.6417 | 3620 | 0.496 | - | - |
532
+ | 1.6508 | 3640 | 0.5179 | - | - |
533
+ | 1.6599 | 3660 | 0.4729 | - | - |
534
+ | 1.6689 | 3680 | 0.4612 | 0.4785 | 0.6767 |
535
+ | 1.6780 | 3700 | 0.4628 | - | - |
536
+ | 1.6871 | 3720 | 0.4516 | - | - |
537
+ | 1.6961 | 3740 | 0.4773 | - | - |
538
+ | 1.7052 | 3760 | 0.4732 | 0.4781 | 0.6798 |
539
+ | 1.7143 | 3780 | 0.5025 | - | - |
540
+ | 1.7234 | 3800 | 0.4843 | - | - |
541
+ | 1.7324 | 3820 | 0.4799 | - | - |
542
+ | 1.7415 | 3840 | 0.4753 | 0.4781 | 0.6837 |
543
+ | 1.7506 | 3860 | 0.4568 | - | - |
544
+ | 1.7596 | 3880 | 0.4782 | - | - |
545
+ | 1.7687 | 3900 | 0.4855 | - | - |
546
+ | 1.7778 | 3920 | 0.4699 | 0.4791 | 0.6913 |
547
+ | 1.7868 | 3940 | 0.48 | - | - |
548
+ | 1.7959 | 3960 | 0.4743 | - | - |
549
+ | 1.8050 | 3980 | 0.453 | - | - |
550
+ | 1.8141 | 4000 | 0.4755 | 0.4816 | 0.6937 |
551
+ | 1.8231 | 4020 | 0.4419 | - | - |
552
+ | 1.8322 | 4040 | 0.4724 | - | - |
553
+ | 1.8413 | 4060 | 0.4892 | - | - |
554
+ | 1.8503 | 4080 | 0.4779 | 0.4829 | 0.6903 |
555
+ | 1.8594 | 4100 | 0.4748 | - | - |
556
+ | 1.8685 | 4120 | 0.4909 | - | - |
557
+ | 1.8776 | 4140 | 0.5026 | - | - |
558
+ | 1.8866 | 4160 | 0.4668 | 0.4795 | 0.7060 |
559
+ | 1.8957 | 4180 | 0.47 | - | - |
560
+ | 1.9048 | 4200 | 0.4977 | - | - |
561
+ | 1.9138 | 4220 | 0.4644 | - | - |
562
+ | 1.9229 | 4240 | 0.4745 | 0.4777 | 0.7053 |
563
+ | 1.9320 | 4260 | 0.455 | - | - |
564
+ | 1.9410 | 4280 | 0.4864 | - | - |
565
+ | 1.9501 | 4300 | 0.4987 | - | - |
566
+ | 1.9592 | 4320 | 0.4716 | 0.4770 | 0.6948 |
567
+ | 1.9683 | 4340 | 0.4877 | - | - |
568
+ | 1.9773 | 4360 | 0.4741 | - | - |
569
+ | 1.9864 | 4380 | 0.4969 | - | - |
570
+ | 1.9955 | 4400 | 0.4733 | 0.4767 | 0.7052 |
571
+ | 2.0045 | 4420 | 0.4842 | - | - |
572
+ | 2.0136 | 4440 | 0.48 | - | - |
573
+ | 2.0227 | 4460 | 0.4985 | - | - |
574
+ | 2.0317 | 4480 | 0.483 | 0.4760 | 0.7110 |
575
+ | 2.0408 | 4500 | 0.482 | - | - |
576
+ | 2.0499 | 4520 | 0.4687 | - | - |
577
+ | 2.0590 | 4540 | 0.4595 | - | - |
578
+ | 2.0680 | 4560 | 0.4699 | 0.4764 | 0.7095 |
579
+ | 2.0771 | 4580 | 0.4426 | - | - |
580
+ | 2.0862 | 4600 | 0.4691 | - | - |
581
+ | 2.0952 | 4620 | 0.4568 | - | - |
582
+ | 2.1043 | 4640 | 0.4716 | 0.4774 | 0.7124 |
583
+ | 2.1134 | 4660 | 0.4696 | - | - |
584
+ | 2.1224 | 4680 | 0.4737 | - | - |
585
+ | 2.1315 | 4700 | 0.4925 | - | - |
586
+ | 2.1406 | 4720 | 0.4708 | 0.4754 | 0.7274 |
587
+ | 2.1497 | 4740 | 0.4531 | - | - |
588
+ | 2.1587 | 4760 | 0.473 | - | - |
589
+ | 2.1678 | 4780 | 0.4824 | - | - |
590
+ | 2.1769 | 4800 | 0.4573 | 0.4760 | 0.7291 |
591
+ | 2.1859 | 4820 | 0.4774 | - | - |
592
+ | 2.1950 | 4840 | 0.4776 | - | - |
593
+ | 2.2041 | 4860 | 0.4764 | - | - |
594
+ | 2.2132 | 4880 | 0.4893 | 0.4749 | 0.7352 |
595
+ | 2.2222 | 4900 | 0.4793 | - | - |
596
+ | 2.2313 | 4920 | 0.4473 | - | - |
597
+ | 2.2404 | 4940 | 0.4851 | - | - |
598
+ | 2.2494 | 4960 | 0.4787 | 0.4757 | 0.7261 |
599
+ | 2.2585 | 4980 | 0.4676 | - | - |
600
+ | 2.2676 | 5000 | 0.4621 | - | - |
601
+ | 2.2766 | 5020 | 0.4714 | - | - |
602
+ | 2.2857 | 5040 | 0.4758 | 0.4762 | 0.7230 |
603
+ | 2.2948 | 5060 | 0.4754 | - | - |
604
+ | 2.3039 | 5080 | 0.4305 | - | - |
605
+ | 2.3129 | 5100 | 0.4752 | - | - |
606
+ | 2.3220 | 5120 | 0.4606 | 0.4759 | 0.7355 |
607
+ | 2.3311 | 5140 | 0.4936 | - | - |
608
+ | 2.3401 | 5160 | 0.4456 | - | - |
609
+ | 2.3492 | 5180 | 0.489 | - | - |
610
+ | 2.3583 | 5200 | 0.4633 | 0.4779 | 0.7319 |
611
+ | 2.3673 | 5220 | 0.4909 | - | - |
612
+ | 2.3764 | 5240 | 0.4601 | - | - |
613
+ | 2.3855 | 5260 | 0.476 | - | - |
614
+ | 2.3946 | 5280 | 0.4793 | 0.4739 | 0.7454 |
615
+ | 2.4036 | 5300 | 0.4618 | - | - |
616
+ | 2.4127 | 5320 | 0.4668 | - | - |
617
+ | 2.4218 | 5340 | 0.4621 | - | - |
618
+ | 2.4308 | 5360 | 0.4732 | 0.4749 | 0.7412 |
619
+ | 2.4399 | 5380 | 0.4683 | - | - |
620
+ | 2.4490 | 5400 | 0.4902 | - | - |
621
+ | 2.4580 | 5420 | 0.4629 | - | - |
622
+ | 2.4671 | 5440 | 0.4917 | 0.4748 | 0.7353 |
623
+ | 2.4762 | 5460 | 0.4783 | - | - |
624
+ | 2.4853 | 5480 | 0.4865 | - | - |
625
+ | 2.4943 | 5500 | 0.4838 | - | - |
626
+ | 2.5034 | 5520 | 0.4486 | 0.4759 | 0.7376 |
627
+ | 2.5125 | 5540 | 0.4705 | - | - |
628
+ | 2.5215 | 5560 | 0.4713 | - | - |
629
+ | 2.5306 | 5580 | 0.5 | - | - |
630
+ | 2.5397 | 5600 | 0.4645 | 0.4753 | 0.7415 |
631
+ | 2.5488 | 5620 | 0.4655 | - | - |
632
+ | 2.5578 | 5640 | 0.4646 | - | - |
633
+ | 2.5669 | 5660 | 0.4608 | - | - |
634
+ | 2.5760 | 5680 | 0.4752 | 0.4741 | 0.7406 |
635
+ | 2.5850 | 5700 | 0.4608 | - | - |
636
+ | 2.5941 | 5720 | 0.46 | - | - |
637
+ | 2.6032 | 5740 | 0.4603 | - | - |
638
+ | 2.6122 | 5760 | 0.4686 | 0.4734 | 0.7438 |
639
+ | 2.6213 | 5780 | 0.4542 | - | - |
640
+ | 2.6304 | 5800 | 0.4718 | - | - |
641
+ | 2.6395 | 5820 | 0.4615 | - | - |
642
+ | 2.6485 | 5840 | 0.4749 | 0.4729 | 0.7552 |
643
+ | 2.6576 | 5860 | 0.4951 | - | - |
644
+ | 2.6667 | 5880 | 0.4944 | - | - |
645
+ | 2.6757 | 5900 | 0.459 | - | - |
646
+ | 2.6848 | 5920 | 0.4593 | 0.4743 | 0.7567 |
647
+ | 2.6939 | 5940 | 0.474 | - | - |
648
+ | 2.7029 | 5960 | 0.4555 | - | - |
649
+ | 2.7120 | 5980 | 0.465 | - | - |
650
+ | 2.7211 | 6000 | 0.4583 | 0.4730 | 0.7560 |
651
+ | 2.7302 | 6020 | 0.4528 | - | - |
652
+ | 2.7392 | 6040 | 0.4375 | - | - |
653
+ | 2.7483 | 6060 | 0.4838 | - | - |
654
+ | 2.7574 | 6080 | 0.4995 | 0.4729 | 0.7552 |
655
+ | 2.7664 | 6100 | 0.4687 | - | - |
656
+ | 2.7755 | 6120 | 0.4615 | - | - |
657
+ | 2.7846 | 6140 | 0.4619 | - | - |
658
+ | 2.7937 | 6160 | 0.4726 | 0.4734 | 0.7589 |
659
+ | 2.8027 | 6180 | 0.4699 | - | - |
660
+ | 2.8118 | 6200 | 0.4772 | - | - |
661
+ | 2.8209 | 6220 | 0.469 | - | - |
662
+ | 2.8299 | 6240 | 0.4592 | 0.4728 | 0.7640 |
663
+ | 2.8390 | 6260 | 0.4599 | - | - |
664
+ | 2.8481 | 6280 | 0.4642 | - | - |
665
+ | 2.8571 | 6300 | 0.4658 | - | - |
666
+ | 2.8662 | 6320 | 0.4786 | 0.4724 | 0.7655 |
667
+ | 2.8753 | 6340 | 0.4537 | - | - |
668
+ | 2.8844 | 6360 | 0.4984 | - | - |
669
+ | 2.8934 | 6380 | 0.4816 | - | - |
670
+ | 2.9025 | 6400 | 0.4598 | 0.4726 | 0.7649 |
671
+ | 2.9116 | 6420 | 0.4775 | - | - |
672
+ | 2.9206 | 6440 | 0.4802 | - | - |
673
+ | 2.9297 | 6460 | 0.4556 | - | - |
674
+ | 2.9388 | 6480 | 0.4787 | 0.4744 | 0.7737 |
675
+ | 2.9478 | 6500 | 0.4835 | - | - |
676
+ | 2.9569 | 6520 | 0.4638 | - | - |
677
+ | 2.9660 | 6540 | 0.4912 | - | - |
678
+ | 2.9751 | 6560 | 0.4727 | 0.4718 | 0.7725 |
679
+ | 2.9841 | 6580 | 0.4637 | - | - |
680
+ | 2.9932 | 6600 | 0.4934 | - | - |
681
+ | 3.0023 | 6620 | 0.4632 | - | - |
682
+ | 3.0113 | 6640 | 0.4772 | 0.4720 | 0.7786 |
683
+ | 3.0204 | 6660 | 0.4565 | - | - |
684
+ | 3.0295 | 6680 | 0.4433 | - | - |
685
+ | 3.0385 | 6700 | 0.4642 | - | - |
686
+ | 3.0476 | 6720 | 0.4603 | 0.4737 | 0.7768 |
687
+ | 3.0567 | 6740 | 0.466 | - | - |
688
+ | 3.0658 | 6760 | 0.4509 | - | - |
689
+ | 3.0748 | 6780 | 0.4455 | - | - |
690
+ | 3.0839 | 6800 | 0.4808 | 0.4718 | 0.7777 |
691
+ | 3.0930 | 6820 | 0.4836 | - | - |
692
+ | 3.1020 | 6840 | 0.4823 | - | - |
693
+ | 3.1111 | 6860 | 0.469 | - | - |
694
+ | 3.1202 | 6880 | 0.4654 | 0.4715 | 0.7777 |
695
+ | 3.1293 | 6900 | 0.4705 | - | - |
696
+ | 3.1383 | 6920 | 0.4869 | - | - |
697
+ | 3.1474 | 6940 | 0.4964 | - | - |
698
+ | 3.1565 | 6960 | 0.4346 | 0.4729 | 0.7823 |
699
+ | 3.1655 | 6980 | 0.478 | - | - |
700
+ | 3.1746 | 7000 | 0.4691 | - | - |
701
+ | 3.1837 | 7020 | 0.45 | - | - |
702
+ | 3.1927 | 7040 | 0.4821 | 0.4715 | 0.7868 |
703
+ | 3.2018 | 7060 | 0.4652 | - | - |
704
+ | 3.2109 | 7080 | 0.4654 | - | - |
705
+ | 3.2200 | 7100 | 0.4561 | - | - |
706
+ | 3.2290 | 7120 | 0.4657 | 0.4713 | 0.7860 |
707
+ | 3.2381 | 7140 | 0.4431 | - | - |
708
+ | 3.2472 | 7160 | 0.448 | - | - |
709
+ | 3.2562 | 7180 | 0.478 | - | - |
710
+ | 3.2653 | 7200 | 0.4574 | 0.4707 | 0.7913 |
711
+ | 3.2744 | 7220 | 0.4589 | - | - |
712
+ | 3.2834 | 7240 | 0.4759 | - | - |
713
+ | 3.2925 | 7260 | 0.4703 | - | - |
714
+ | 3.3016 | 7280 | 0.4683 | 0.4712 | 0.7943 |
715
+ | 3.3107 | 7300 | 0.4576 | - | - |
716
+ | 3.3197 | 7320 | 0.4517 | - | - |
717
+ | 3.3288 | 7340 | 0.4498 | - | - |
718
+ | 3.3379 | 7360 | 0.4782 | 0.4705 | 0.7961 |
719
+ | 3.3469 | 7380 | 0.476 | - | - |
720
+ | 3.3560 | 7400 | 0.4642 | - | - |
721
+ | 3.3651 | 7420 | 0.4923 | - | - |
722
+ | 3.3741 | 7440 | 0.4637 | 0.4706 | 0.7949 |
723
+ | 3.3832 | 7460 | 0.4512 | - | - |
724
+ | 3.3923 | 7480 | 0.4392 | - | - |
725
+ | 3.4014 | 7500 | 0.486 | - | - |
726
+ | 3.4104 | 7520 | 0.4632 | 0.4709 | 0.7950 |
727
+ | 3.4195 | 7540 | 0.4816 | - | - |
728
+ | 3.4286 | 7560 | 0.46 | - | - |
729
+ | 3.4376 | 7580 | 0.473 | - | - |
730
+ | 3.4467 | 7600 | 0.4618 | 0.4708 | 0.7953 |
731
+ | 3.4558 | 7620 | 0.4584 | - | - |
732
+ | 3.4649 | 7640 | 0.46 | - | - |
733
+ | 3.4739 | 7660 | 0.4655 | - | - |
734
+ | 3.4830 | 7680 | 0.4461 | 0.4713 | 0.7981 |
735
+ | 3.4921 | 7700 | 0.4521 | - | - |
736
+ | 3.5011 | 7720 | 0.4802 | - | - |
737
+ | 3.5102 | 7740 | 0.464 | - | - |
738
+ | 3.5193 | 7760 | 0.481 | 0.4699 | 0.7991 |
739
+ | 3.5283 | 7780 | 0.4719 | - | - |
740
+ | 3.5374 | 7800 | 0.4615 | - | - |
741
+ | 3.5465 | 7820 | 0.458 | - | - |
742
+ | 3.5556 | 7840 | 0.4659 | 0.4700 | 0.7996 |
743
+ | 3.5646 | 7860 | 0.4688 | - | - |
744
+ | 3.5737 | 7880 | 0.457 | - | - |
745
+ | 3.5828 | 7900 | 0.4821 | - | - |
746
+ | 3.5918 | 7920 | 0.4567 | 0.4707 | 0.8018 |
747
+ | 3.6009 | 7940 | 0.4722 | - | - |
748
+ | 3.6100 | 7960 | 0.4785 | - | - |
749
+ | 3.6190 | 7980 | 0.4904 | - | - |
750
+ | 3.6281 | 8000 | 0.483 | 0.4698 | 0.8012 |
751
+ | 3.6372 | 8020 | 0.4756 | - | - |
752
+ | 3.6463 | 8040 | 0.4689 | - | - |
753
+ | 3.6553 | 8060 | 0.4774 | - | - |
754
+ | 3.6644 | 8080 | 0.4638 | 0.4707 | 0.8015 |
755
+ | 3.6735 | 8100 | 0.4648 | - | - |
756
+ | 3.6825 | 8120 | 0.478 | - | - |
757
+ | 3.6916 | 8140 | 0.4839 | - | - |
758
+ | 3.7007 | 8160 | 0.4623 | 0.4696 | 0.8036 |
759
+ | 3.7098 | 8180 | 0.4558 | - | - |
760
+ | 3.7188 | 8200 | 0.4575 | - | - |
761
+ | 3.7279 | 8220 | 0.4628 | - | - |
762
+ | 3.7370 | 8240 | 0.4552 | 0.4702 | 0.8042 |
763
+ | 3.7460 | 8260 | 0.4655 | - | - |
764
+ | 3.7551 | 8280 | 0.4687 | - | - |
765
+ | 3.7642 | 8300 | 0.4549 | - | - |
766
+ | 3.7732 | 8320 | 0.4522 | 0.4700 | 0.8052 |
767
+ | 3.7823 | 8340 | 0.4424 | - | - |
768
+ | 3.7914 | 8360 | 0.4612 | - | - |
769
+ | 3.8005 | 8380 | 0.4606 | - | - |
770
+ | 3.8095 | 8400 | 0.4553 | 0.4695 | 0.8058 |
771
+ | 3.8186 | 8420 | 0.4661 | - | - |
772
+ | 3.8277 | 8440 | 0.4811 | - | - |
773
+ | 3.8367 | 8460 | 0.4661 | - | - |
774
+ | 3.8458 | 8480 | 0.4805 | 0.4695 | 0.8065 |
775
+ | 3.8549 | 8500 | 0.4761 | - | - |
776
+ | 3.8639 | 8520 | 0.4778 | - | - |
777
+ | 3.8730 | 8540 | 0.4566 | - | - |
778
+ | 3.8821 | 8560 | 0.4359 | 0.4695 | 0.8067 |
779
+ | 3.8912 | 8580 | 0.47 | - | - |
780
+ | 3.9002 | 8600 | 0.4851 | - | - |
781
+ | 3.9093 | 8620 | 0.4609 | - | - |
782
+ | 3.9184 | 8640 | 0.4675 | 0.4695 | 0.8068 |
783
+ | 3.9274 | 8660 | 0.4628 | - | - |
784
+ | 3.9365 | 8680 | 0.4604 | - | - |
785
+ | 3.9456 | 8700 | 0.4829 | - | - |
786
+ | 3.9546 | 8720 | 0.462 | 0.4695 | 0.8071 |
787
+ | 3.9637 | 8740 | 0.4554 | - | - |
788
+ | 3.9728 | 8760 | 0.4674 | - | - |
789
+ | 3.9819 | 8780 | 0.4721 | - | - |
790
+ | 3.9909 | 8800 | 0.4534 | 0.4695 | 0.8073 |
791
+ | 4.0 | 8820 | 0.4667 | - | - |
792
+ | -1 | -1 | - | - | 0.7876 |
793
+
794
+ </details>
795
+
796
+ ### Framework Versions
797
+ - Python: 3.11.12
798
+ - Sentence Transformers: 4.1.0
799
+ - Transformers: 4.51.3
800
+ - PyTorch: 2.6.0+cu124
801
+ - Accelerate: 1.5.2
802
+ - Datasets: 3.5.0
803
+ - Tokenizers: 0.21.1
804
+
805
+ ## Citation
806
+
807
+ ### BibTeX
808
+
809
+ #### Sentence Transformers
810
+ ```bibtex
811
+ @inproceedings{reimers-2019-sentence-bert,
812
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
813
+ author = "Reimers, Nils and Gurevych, Iryna",
814
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
815
+ month = "11",
816
+ year = "2019",
817
+ publisher = "Association for Computational Linguistics",
818
+ url = "https://arxiv.org/abs/1908.10084",
819
+ }
820
+ ```
821
+
822
+ <!--
823
+ ## Glossary
824
+
825
+ *Clearly define terms in order to be accessible across audiences.*
826
+ -->
827
+
828
+ <!--
829
+ ## Model Card Authors
830
+
831
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
832
+ -->
833
+
834
+ <!--
835
+ ## Model Card Contact
836
+
837
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
838
+ -->
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 384,
11
+ "id2label": {
12
+ "0": "LABEL_0"
13
+ },
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 1536,
16
+ "label2id": {
17
+ "LABEL_0": 0
18
+ },
19
+ "layer_norm_eps": 1e-12,
20
+ "max_position_embeddings": 512,
21
+ "model_type": "bert",
22
+ "num_attention_heads": 12,
23
+ "num_hidden_layers": 6,
24
+ "pad_token_id": 0,
25
+ "position_embedding_type": "absolute",
26
+ "sentence_transformers": {
27
+ "activation_fn": "torch.nn.modules.linear.Identity",
28
+ "version": "4.1.0"
29
+ },
30
+ "tokenizer_class": "XLMRobertaTokenizer",
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.51.3",
33
+ "type_vocab_size": 2,
34
+ "use_cache": true,
35
+ "vocab_size": 250037
36
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e566fb374ff0d00ffe682019c1eb66e335ad0b4fd0f3591c22c2f0ef3cc7479
3
+ size 428041660
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef04f2b385d1514f500e779207ace0f53e30895ce37563179e29f4022d28ca38
3
+ size 17083053
tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": false,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "extra_special_tokens": {},
49
+ "mask_token": "<mask>",
50
+ "model_max_length": 512,
51
+ "pad_token": "<pad>",
52
+ "sep_token": "</s>",
53
+ "sp_model_kwargs": {},
54
+ "tokenizer_class": "XLMRobertaTokenizer",
55
+ "unk_token": "<unk>"
56
+ }