Hugging Face's logo

Noddybear
/
akkadian-embed

Sentence Similarity
sentence-transformers
Safetensors
modernbert
feature-extraction
dense
Generated from Trainer
dataset_size:371366
loss:MatryoshkaLoss
loss:MultipleNegativesRankingLoss
Eval Results (legacy)
text-embeddings-inference
Model card Files
xet
 Community
Noddybear commited on
Commit
7b432c4
·
verified ·
1 Parent(s): 9d64e6a

Upload akkadian-embed (modernbert-embed-base fine-tuned)

Browse files
Files changed (10) hide show
  1. 1_Pooling/config.json +10 -0
  2. README.md +1193 -0
  3. config.json +45 -0
  4. config_sentence_transformers.json +14 -0
  5. model.safetensors +3 -0
  6. modules.json +20 -0
  7. sentence_bert_config.json +4 -0
  8. special_tokens_map.json +37 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +952 -0
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": true,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": false,
9
+ "include_prompt": true
10
+ }
README.md ADDED
@@ -0,0 +1,1193 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: nomic-ai/modernbert-embed-base
3
+ library_name: sentence-transformers
4
+ metrics:
5
+ - cosine_accuracy@1
6
+ - cosine_accuracy@3
7
+ - cosine_accuracy@5
8
+ - cosine_accuracy@10
9
+ - cosine_precision@1
10
+ - cosine_precision@3
11
+ - cosine_precision@5
12
+ - cosine_precision@10
13
+ - cosine_recall@1
14
+ - cosine_recall@3
15
+ - cosine_recall@5
16
+ - cosine_recall@10
17
+ - cosine_ndcg@10
18
+ - cosine_mrr@10
19
+ - cosine_map@100
20
+ model-index:
21
+ - name: SentenceTransformer based on nomic-ai/modernbert-embed-base
22
+ results:
23
+ - dataset:
24
+ name: akkadian ir
25
+ type: akkadian-ir
26
+ metrics:
27
+ - name: Cosine Accuracy@1
28
+ type: cosine_accuracy@1
29
+ value: 0.5072397032489128
30
+ - name: Cosine Accuracy@3
31
+ type: cosine_accuracy@3
32
+ value: 0.733231005372218
33
+ - name: Cosine Accuracy@5
34
+ type: cosine_accuracy@5
35
+ value: 0.7706830391404451
36
+ - name: Cosine Accuracy@10
37
+ type: cosine_accuracy@10
38
+ value: 0.8067536454336147
39
+ - name: Cosine Precision@1
40
+ type: cosine_precision@1
41
+ value: 0.5072397032489128
42
+ - name: Cosine Precision@3
43
+ type: cosine_precision@3
44
+ value: 0.24441033512407265
45
+ - name: Cosine Precision@5
46
+ type: cosine_precision@5
47
+ value: 0.15413660782808902
48
+ - name: Cosine Precision@10
49
+ type: cosine_precision@10
50
+ value: 0.08067536454336147
51
+ - name: Cosine Recall@1
52
+ type: cosine_recall@1
53
+ value: 0.5072397032489128
54
+ - name: Cosine Recall@3
55
+ type: cosine_recall@3
56
+ value: 0.733231005372218
57
+ - name: Cosine Recall@5
58
+ type: cosine_recall@5
59
+ value: 0.7706830391404451
60
+ - name: Cosine Recall@10
61
+ type: cosine_recall@10
62
+ value: 0.8067536454336147
63
+ - name: Cosine Ndcg@10
64
+ type: cosine_ndcg@10
65
+ value: 0.669848499932859
66
+ - name: Cosine Mrr@10
67
+ type: cosine_mrr@10
68
+ value: 0.6245717046945073
69
+ - name: Cosine Map@100
70
+ type: cosine_map@100
71
+ value: 0.6276029021828822
72
+ task:
73
+ name: Information Retrieval
74
+ type: information-retrieval
75
+ pipeline_tag: sentence-similarity
76
+ tags:
77
+ - sentence-transformers
78
+ - sentence-similarity
79
+ - feature-extraction
80
+ - dense
81
+ - generated_from_trainer
82
+ - dataset_size:371366
83
+ - loss:MatryoshkaLoss
84
+ - loss:MultipleNegativesRankingLoss
85
+ ---
86
+
87
+ # SentenceTransformer based on nomic-ai/modernbert-embed-base
88
+
89
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [nomic-ai/modernbert-embed-base](https://huggingface.co/nomic-ai/modernbert-embed-base). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
90
+
91
+ ## Model Details
92
+
93
+ ### Model Description
94
+ - **Model Type:** Sentence Transformer
95
+ - **Base model:** [nomic-ai/modernbert-embed-base](https://huggingface.co/nomic-ai/modernbert-embed-base) <!-- at revision d556a88e332558790b210f7bdbe87da2fa94a8d8 -->
96
+ - **Maximum Sequence Length:** 8192 tokens
97
+ - **Output Dimensionality:** 768 dimensions
98
+ - **Similarity Function:** Cosine Similarity
99
+ <!-- - **Training Dataset:** Unknown -->
100
+ <!-- - **Language:** Unknown -->
101
+ <!-- - **License:** Unknown -->
102
+
103
+ ### Model Sources
104
+
105
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
106
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/sentence-transformers)
107
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
108
+
109
+ ### Full Model Architecture
110
+
111
+ ```
112
+ SentenceTransformer(
113
+ (0): Transformer({'max_seq_length': 8192, 'do_lower_case': False, 'architecture': 'ModernBertModel'})
114
+ (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
115
+ (2): Normalize()
116
+ )
117
+ ```
118
+
119
+ ## Usage
120
+
121
+ ### Direct Usage (Sentence Transformers)
122
+
123
+ First install the Sentence Transformers library:
124
+
125
+ ```bash
126
+ pip install -U sentence-transformers
127
+ ```
128
+
129
+ Then you can load this model and run inference.
130
+ ```python
131
+ from sentence_transformers import SentenceTransformer
132
+
133
+ # Download from the 🤗 Hub
134
+ model = SentenceTransformer("sentence_transformers_model_id")
135
+ # Run inference
136
+ sentences = [
137
+ 'ma-a 12 GÍN i-dí-sú-in KI tù-ra-a i-lá-qé 5',
138
+ 'Indeed, Iddin-Suen will receive 12 shekels from Turaya.',
139
+ 'ina pa-ni-szu-nu i-za#-mu-ru ina _ugu_ szA ni-iq-bu-ni ma-a [x x x x x x] ki',
140
+ ]
141
+ embeddings = model.encode(sentences)
142
+ print(embeddings.shape)
143
+ # [3, 768]
144
+
145
+ # Get the similarity scores for the embeddings
146
+ similarities = model.similarity(embeddings, embeddings)
147
+ print(similarities)
148
+ # tensor([[ 1.0000, 0.6474, -0.1447],
149
+ # [ 0.6474, 1.0000, -0.0218],
150
+ # [-0.1447, -0.0218, 1.0000]])
151
+ ```
152
+
153
+ <!--
154
+ ### Direct Usage (Transformers)
155
+
156
+ <details><summary>Click to see the direct usage in Transformers</summary>
157
+
158
+ </details>
159
+ -->
160
+
161
+ <!--
162
+ ### Downstream Usage (Sentence Transformers)
163
+
164
+ You can finetune this model on your own dataset.
165
+
166
+ <details><summary>Click to expand</summary>
167
+
168
+ </details>
169
+ -->
170
+
171
+ <!--
172
+ ### Out-of-Scope Use
173
+
174
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
175
+ -->
176
+
177
+ ## Evaluation
178
+
179
+ ### Metrics
180
+
181
+ #### Information Retrieval
182
+
183
+ * Dataset: `akkadian-ir`
184
+ * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters:
185
+ ```json
186
+ {
187
+ "truncate_dim": 384
188
+ }
189
+ ```
190
+
191
+ | Metric | Value |
192
+ |:--------------------|:-----------|
193
+ | cosine_accuracy@1 | 0.5072 |
194
+ | cosine_accuracy@3 | 0.7332 |
195
+ | cosine_accuracy@5 | 0.7707 |
196
+ | cosine_accuracy@10 | 0.8068 |
197
+ | cosine_precision@1 | 0.5072 |
198
+ | cosine_precision@3 | 0.2444 |
199
+ | cosine_precision@5 | 0.1541 |
200
+ | cosine_precision@10 | 0.0807 |
201
+ | cosine_recall@1 | 0.5072 |
202
+ | cosine_recall@3 | 0.7332 |
203
+ | cosine_recall@5 | 0.7707 |
204
+ | cosine_recall@10 | 0.8068 |
205
+ | **cosine_ndcg@10** | **0.6698** |
206
+ | cosine_mrr@10 | 0.6246 |
207
+ | cosine_map@100 | 0.6276 |
208
+
209
+ <!--
210
+ ## Bias, Risks and Limitations
211
+
212
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
213
+ -->
214
+
215
+ <!--
216
+ ### Recommendations
217
+
218
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
219
+ -->
220
+
221
+ ## Training Details
222
+
223
+ ### Training Dataset
224
+
225
+ #### Unnamed Dataset
226
+
227
+ * Size: 371,366 training samples
228
+ * Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
229
+ * Approximate statistics based on the first 1000 samples:
230
+ | | anchor | positive | negative |
231
+ |:--------|:-----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
232
+ | type | string | string | string |
233
+ | details | <ul><li>min: 3 tokens</li><li>mean: 38.93 tokens</li><li>max: 606 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 52.63 tokens</li><li>max: 1105 tokens</li></ul> | <ul><li>min: 2 tokens</li><li>mean: 23.5 tokens</li><li>max: 335 tokens</li></ul> |
234
+ * Samples:
235
+ | anchor | positive | negative |
236
+ |:-------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------|
237
+ | <code>kà-sí-im (kāsu)</code> | <code>m. & f.; pl. f. "cup, bowl" [GAL; MB on (DUG.)GÚ.ZI] freq. of metal; for oil, wine; MB, NA as measure of capacity</code> | <code>If in Nisannu Month I, for his house ....</code> |
238
+ | <code>SIG5 ša-bu-ra-am i-ṣé-er i-dí-a-šur DUMU dan-a-šur PUZUR4.IŠTAR a-hi-šu ù i-ku-pí-a DUMU a-šur-i-mì-tí iš-ma-a-šur i-šu</code> | <code>Idī-Aššur s. Dān-Aššur, brother of Puzur-Ištar, and Ikuppiya s. Aššur-imitt owe Išme-Aššur 14 talents broken refined copper.</code> | <code>DUMU {1}-ba-da-a.a</code> |
239
+ | <code>mì-šu ṣú-ha-ru-ša ša-lim-a-šur ù a-li-ku a-dí šé-ni-šu i-li-ku-ni-ma té-er-ta-ak-nu-ma lá i-li-kà-ni</code> | <code>Why is it that Šalim-Aššur's servants and other travellers have come here twice, but no message from you has arrived?</code> | <code>servant Ina-šar-Bel-allak</code> |
240
+ * Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
241
+ ```json
242
+ {
243
+ "loss": "MultipleNegativesRankingLoss",
244
+ "matryoshka_dims": [
245
+ 768,
246
+ 512,
247
+ 384,
248
+ 256,
249
+ 128
250
+ ],
251
+ "matryoshka_weights": [
252
+ 1,
253
+ 1,
254
+ 1,
255
+ 1,
256
+ 1
257
+ ],
258
+ "n_dims_per_step": -1
259
+ }
260
+ ```
261
+
262
+ ### Training Hyperparameters
263
+ #### Non-Default Hyperparameters
264
+
265
+ - `eval_strategy`: steps
266
+ - `per_device_train_batch_size`: 32
267
+ - `learning_rate`: 2e-05
268
+ - `lr_scheduler_type`: cosine
269
+ - `warmup_ratio`: 0.1
270
+ - `fp16`: True
271
+ - `load_best_model_at_end`: True
272
+
273
+ #### All Hyperparameters
274
+ <details><summary>Click to expand</summary>
275
+
276
+ - `overwrite_output_dir`: False
277
+ - `do_predict`: False
278
+ - `eval_strategy`: steps
279
+ - `prediction_loss_only`: True
280
+ - `per_device_train_batch_size`: 32
281
+ - `per_device_eval_batch_size`: 8
282
+ - `per_gpu_train_batch_size`: None
283
+ - `per_gpu_eval_batch_size`: None
284
+ - `gradient_accumulation_steps`: 1
285
+ - `eval_accumulation_steps`: None
286
+ - `torch_empty_cache_steps`: None
287
+ - `learning_rate`: 2e-05
288
+ - `weight_decay`: 0.0
289
+ - `adam_beta1`: 0.9
290
+ - `adam_beta2`: 0.999
291
+ - `adam_epsilon`: 1e-08
292
+ - `max_grad_norm`: 1.0
293
+ - `num_train_epochs`: 3
294
+ - `max_steps`: -1
295
+ - `lr_scheduler_type`: cosine
296
+ - `lr_scheduler_kwargs`: None
297
+ - `warmup_ratio`: 0.1
298
+ - `warmup_steps`: 0
299
+ - `log_level`: passive
300
+ - `log_level_replica`: warning
301
+ - `log_on_each_node`: True
302
+ - `logging_nan_inf_filter`: True
303
+ - `save_safetensors`: True
304
+ - `save_on_each_node`: False
305
+ - `save_only_model`: False
306
+ - `restore_callback_states_from_checkpoint`: False
307
+ - `no_cuda`: False
308
+ - `use_cpu`: False
309
+ - `use_mps_device`: False
310
+ - `seed`: 42
311
+ - `data_seed`: None
312
+ - `jit_mode_eval`: False
313
+ - `bf16`: False
314
+ - `fp16`: True
315
+ - `fp16_opt_level`: O1
316
+ - `half_precision_backend`: auto
317
+ - `bf16_full_eval`: False
318
+ - `fp16_full_eval`: False
319
+ - `tf32`: None
320
+ - `local_rank`: 0
321
+ - `ddp_backend`: None
322
+ - `tpu_num_cores`: None
323
+ - `tpu_metrics_debug`: False
324
+ - `debug`: []
325
+ - `dataloader_drop_last`: False
326
+ - `dataloader_num_workers`: 0
327
+ - `dataloader_prefetch_factor`: None
328
+ - `past_index`: -1
329
+ - `disable_tqdm`: False
330
+ - `remove_unused_columns`: True
331
+ - `label_names`: None
332
+ - `load_best_model_at_end`: True
333
+ - `ignore_data_skip`: False
334
+ - `fsdp`: []
335
+ - `fsdp_min_num_params`: 0
336
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
337
+ - `fsdp_transformer_layer_cls_to_wrap`: None
338
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
339
+ - `parallelism_config`: None
340
+ - `deepspeed`: None
341
+ - `label_smoothing_factor`: 0.0
342
+ - `optim`: adamw_torch_fused
343
+ - `optim_args`: None
344
+ - `adafactor`: False
345
+ - `group_by_length`: False
346
+ - `length_column_name`: length
347
+ - `project`: huggingface
348
+ - `trackio_space_id`: trackio
349
+ - `ddp_find_unused_parameters`: None
350
+ - `ddp_bucket_cap_mb`: None
351
+ - `ddp_broadcast_buffers`: False
352
+ - `dataloader_pin_memory`: True
353
+ - `dataloader_persistent_workers`: False
354
+ - `skip_memory_metrics`: True
355
+ - `use_legacy_prediction_loop`: False
356
+ - `push_to_hub`: False
357
+ - `resume_from_checkpoint`: None
358
+ - `hub_model_id`: None
359
+ - `hub_strategy`: every_save
360
+ - `hub_private_repo`: None
361
+ - `hub_always_push`: False
362
+ - `hub_revision`: None
363
+ - `gradient_checkpointing`: False
364
+ - `gradient_checkpointing_kwargs`: None
365
+ - `include_inputs_for_metrics`: False
366
+ - `include_for_metrics`: []
367
+ - `eval_do_concat_batches`: True
368
+ - `fp16_backend`: auto
369
+ - `push_to_hub_model_id`: None
370
+ - `push_to_hub_organization`: None
371
+ - `mp_parameters`:
372
+ - `auto_find_batch_size`: False
373
+ - `full_determinism`: False
374
+ - `torchdynamo`: None
375
+ - `ray_scope`: last
376
+ - `ddp_timeout`: 1800
377
+ - `torch_compile`: False
378
+ - `torch_compile_backend`: None
379
+ - `torch_compile_mode`: None
380
+ - `include_tokens_per_second`: False
381
+ - `include_num_input_tokens_seen`: no
382
+ - `neftune_noise_alpha`: None
383
+ - `optim_target_modules`: None
384
+ - `batch_eval_metrics`: False
385
+ - `eval_on_start`: False
386
+ - `use_liger_kernel`: False
387
+ - `liger_kernel_config`: None
388
+ - `eval_use_gather_object`: False
389
+ - `average_tokens_across_devices`: True
390
+ - `prompts`: None
391
+ - `batch_sampler`: batch_sampler
392
+ - `multi_dataset_batch_sampler`: proportional
393
+ - `router_mapping`: {}
394
+ - `learning_rate_mapping`: {}
395
+
396
+ </details>
397
+
398
+ ### Training Logs
399
+ <details><summary>Click to expand</summary>
400
+
401
+ | Epoch | Step | Training Loss | akkadian-ir_cosine_ndcg@10 |
402
+ |:------:|:-----:|:-------------:|:--------------------------:|
403
+ | 0.0043 | 50 | 24.2917 | - |
404
+ | 0.0086 | 100 | 22.3808 | - |
405
+ | 0.0129 | 150 | 19.4952 | - |
406
+ | 0.0172 | 200 | 16.7314 | - |
407
+ | 0.0215 | 250 | 14.4493 | - |
408
+ | 0.0258 | 300 | 12.8579 | - |
409
+ | 0.0302 | 350 | 11.6765 | - |
410
+ | 0.0345 | 400 | 11.056 | - |
411
+ | 0.0388 | 450 | 10.3627 | - |
412
+ | 0.0431 | 500 | 9.5568 | - |
413
+ | 0.0474 | 550 | 9.1752 | - |
414
+ | 0.0517 | 600 | 8.7544 | - |
415
+ | 0.0560 | 650 | 8.7637 | - |
416
+ | 0.0603 | 700 | 8.3496 | - |
417
+ | 0.0646 | 750 | 8.0293 | - |
418
+ | 0.0689 | 800 | 7.5629 | - |
419
+ | 0.0732 | 850 | 7.682 | - |
420
+ | 0.0775 | 900 | 7.2793 | - |
421
+ | 0.0819 | 950 | 7.2354 | - |
422
+ | 0.0862 | 1000 | 7.0245 | - |
423
+ | 0.0905 | 1050 | 6.7 | - |
424
+ | 0.0948 | 1100 | 6.8599 | - |
425
+ | 0.0991 | 1150 | 6.1292 | - |
426
+ | 0.0999 | 1160 | - | 0.1951 |
427
+ | 0.1034 | 1200 | 6.0634 | - |
428
+ | 0.1077 | 1250 | 5.9424 | - |
429
+ | 0.1120 | 1300 | 6.3258 | - |
430
+ | 0.1163 | 1350 | 5.8804 | - |
431
+ | 0.1206 | 1400 | 5.9022 | - |
432
+ | 0.1249 | 1450 | 5.7101 | - |
433
+ | 0.1292 | 1500 | 5.6781 | - |
434
+ | 0.1336 | 1550 | 5.603 | - |
435
+ | 0.1379 | 1600 | 5.4788 | - |
436
+ | 0.1422 | 1650 | 5.5066 | - |
437
+ | 0.1465 | 1700 | 5.6286 | - |
438
+ | 0.1508 | 1750 | 5.2864 | - |
439
+ | 0.1551 | 1800 | 5.399 | - |
440
+ | 0.1594 | 1850 | 5.1604 | - |
441
+ | 0.1637 | 1900 | 5.264 | - |
442
+ | 0.1680 | 1950 | 5.3405 | - |
443
+ | 0.1723 | 2000 | 5.0218 | - |
444
+ | 0.1766 | 2050 | 5.2333 | - |
445
+ | 0.1809 | 2100 | 4.9349 | - |
446
+ | 0.1852 | 2150 | 4.6845 | - |
447
+ | 0.1896 | 2200 | 5.1475 | - |
448
+ | 0.1939 | 2250 | 4.5305 | - |
449
+ | 0.1982 | 2300 | 4.6658 | - |
450
+ | 0.1999 | 2320 | - | 0.2463 |
451
+ | 0.2025 | 2350 | 4.618 | - |
452
+ | 0.2068 | 2400 | 4.6903 | - |
453
+ | 0.2111 | 2450 | 4.4551 | - |
454
+ | 0.2154 | 2500 | 4.7722 | - |
455
+ | 0.2197 | 2550 | 4.3916 | - |
456
+ | 0.2240 | 2600 | 4.1282 | - |
457
+ | 0.2283 | 2650 | 4.3277 | - |
458
+ | 0.2326 | 2700 | 4.6267 | - |
459
+ | 0.2369 | 2750 | 4.3596 | - |
460
+ | 0.2413 | 2800 | 4.3899 | - |
461
+ | 0.2456 | 2850 | 4.2 | - |
462
+ | 0.2499 | 2900 | 4.1903 | - |
463
+ | 0.2542 | 2950 | 4.1434 | - |
464
+ | 0.2585 | 3000 | 4.2724 | - |
465
+ | 0.2628 | 3050 | 4.244 | - |
466
+ | 0.2671 | 3100 | 4.1991 | - |
467
+ | 0.2714 | 3150 | 4.0842 | - |
468
+ | 0.2757 | 3200 | 3.9193 | - |
469
+ | 0.2800 | 3250 | 3.8654 | - |
470
+ | 0.2843 | 3300 | 3.9076 | - |
471
+ | 0.2886 | 3350 | 3.4862 | - |
472
+ | 0.2930 | 3400 | 3.7306 | - |
473
+ | 0.2973 | 3450 | 3.8205 | - |
474
+ | 0.2998 | 3480 | - | 0.2908 |
475
+ | 0.3016 | 3500 | 4.0037 | - |
476
+ | 0.3059 | 3550 | 3.5835 | - |
477
+ | 0.3102 | 3600 | 3.7554 | - |
478
+ | 0.3145 | 3650 | 3.4443 | - |
479
+ | 0.3188 | 3700 | 3.8453 | - |
480
+ | 0.3231 | 3750 | 3.5481 | - |
481
+ | 0.3274 | 3800 | 3.6546 | - |
482
+ | 0.3317 | 3850 | 3.4082 | - |
483
+ | 0.3360 | 3900 | 3.2601 | - |
484
+ | 0.3403 | 3950 | 3.5107 | - |
485
+ | 0.3446 | 4000 | 3.1638 | - |
486
+ | 0.3490 | 4050 | 3.3906 | - |
487
+ | 0.3533 | 4100 | 3.5139 | - |
488
+ | 0.3576 | 4150 | 3.2548 | - |
489
+ | 0.3619 | 4200 | 3.392 | - |
490
+ | 0.3662 | 4250 | 3.292 | - |
491
+ | 0.3705 | 4300 | 3.0331 | - |
492
+ | 0.3748 | 4350 | 2.8747 | - |
493
+ | 0.3791 | 4400 | 3.193 | - |
494
+ | 0.3834 | 4450 | 3.1662 | - |
495
+ | 0.3877 | 4500 | 2.9548 | - |
496
+ | 0.3920 | 4550 | 3.1211 | - |
497
+ | 0.3963 | 4600 | 2.9486 | - |
498
+ | 0.3998 | 4640 | - | 0.3222 |
499
+ | 0.4007 | 4650 | 3.0281 | - |
500
+ | 0.4050 | 4700 | 2.9552 | - |
501
+ | 0.4093 | 4750 | 2.6024 | - |
502
+ | 0.4136 | 4800 | 2.8493 | - |
503
+ | 0.4179 | 4850 | 2.7818 | - |
504
+ | 0.4222 | 4900 | 2.8218 | - |
505
+ | 0.4265 | 4950 | 2.5303 | - |
506
+ | 0.4308 | 5000 | 2.5312 | - |
507
+ | 0.4351 | 5050 | 2.8386 | - |
508
+ | 0.4394 | 5100 | 2.6784 | - |
509
+ | 0.4437 | 5150 | 2.7933 | - |
510
+ | 0.4480 | 5200 | 2.6402 | - |
511
+ | 0.4524 | 5250 | 2.7994 | - |
512
+ | 0.4567 | 5300 | 2.8292 | - |
513
+ | 0.4610 | 5350 | 2.6279 | - |
514
+ | 0.4653 | 5400 | 2.4097 | - |
515
+ | 0.4696 | 5450 | 2.7501 | - |
516
+ | 0.4739 | 5500 | 2.3796 | - |
517
+ | 0.4782 | 5550 | 2.6051 | - |
518
+ | 0.4825 | 5600 | 2.6986 | - |
519
+ | 0.4868 | 5650 | 2.4088 | - |
520
+ | 0.4911 | 5700 | 2.5498 | - |
521
+ | 0.4954 | 5750 | 2.3827 | - |
522
+ | 0.4997 | 5800 | 2.5159 | 0.3500 |
523
+ | 0.5040 | 5850 | 2.4432 | - |
524
+ | 0.5084 | 5900 | 2.1923 | - |
525
+ | 0.5127 | 5950 | 2.4678 | - |
526
+ | 0.5170 | 6000 | 2.228 | - |
527
+ | 0.5213 | 6050 | 2.2555 | - |
528
+ | 0.5256 | 6100 | 2.4221 | - |
529
+ | 0.5299 | 6150 | 2.3692 | - |
530
+ | 0.5342 | 6200 | 2.5304 | - |
531
+ | 0.5385 | 6250 | 2.2569 | - |
532
+ | 0.5428 | 6300 | 2.0883 | - |
533
+ | 0.5471 | 6350 | 2.2691 | - |
534
+ | 0.5514 | 6400 | 2.2558 | - |
535
+ | 0.5557 | 6450 | 2.2126 | - |
536
+ | 0.5601 | 6500 | 2.1121 | - |
537
+ | 0.5644 | 6550 | 2.12 | - |
538
+ | 0.5687 | 6600 | 2.2115 | - |
539
+ | 0.5730 | 6650 | 1.9303 | - |
540
+ | 0.5773 | 6700 | 1.9711 | - |
541
+ | 0.5816 | 6750 | 2.1382 | - |
542
+ | 0.5859 | 6800 | 1.9612 | - |
543
+ | 0.5902 | 6850 | 1.9234 | - |
544
+ | 0.5945 | 6900 | 2.1105 | - |
545
+ | 0.5988 | 6950 | 1.9214 | - |
546
+ | 0.5997 | 6960 | - | 0.3794 |
547
+ | 0.6031 | 7000 | 1.8454 | - |
548
+ | 0.6074 | 7050 | 2.127 | - |
549
+ | 0.6118 | 7100 | 2.0367 | - |
550
+ | 0.6161 | 7150 | 2.0193 | - |
551
+ | 0.6204 | 7200 | 1.8004 | - |
552
+ | 0.6247 | 7250 | 2.0138 | - |
553
+ | 0.6290 | 7300 | 1.789 | - |
554
+ | 0.6333 | 7350 | 1.9486 | - |
555
+ | 0.6376 | 7400 | 1.9889 | - |
556
+ | 0.6419 | 7450 | 2.0563 | - |
557
+ | 0.6462 | 7500 | 1.9492 | - |
558
+ | 0.6505 | 7550 | 1.8981 | - |
559
+ | 0.6548 | 7600 | 1.8442 | - |
560
+ | 0.6591 | 7650 | 1.852 | - |
561
+ | 0.6634 | 7700 | 1.7902 | - |
562
+ | 0.6678 | 7750 | 1.6871 | - |
563
+ | 0.6721 | 7800 | 1.698 | - |
564
+ | 0.6764 | 7850 | 1.5765 | - |
565
+ | 0.6807 | 7900 | 1.8773 | - |
566
+ | 0.6850 | 7950 | 1.7695 | - |
567
+ | 0.6893 | 8000 | 1.621 | - |
568
+ | 0.6936 | 8050 | 1.492 | - |
569
+ | 0.6979 | 8100 | 1.6412 | - |
570
+ | 0.6996 | 8120 | - | 0.4046 |
571
+ | 0.7022 | 8150 | 1.7606 | - |
572
+ | 0.7065 | 8200 | 1.5547 | - |
573
+ | 0.7108 | 8250 | 1.7866 | - |
574
+ | 0.7151 | 8300 | 1.531 | - |
575
+ | 0.7195 | 8350 | 1.7266 | - |
576
+ | 0.7238 | 8400 | 1.4949 | - |
577
+ | 0.7281 | 8450 | 1.9541 | - |
578
+ | 0.7324 | 8500 | 1.6818 | - |
579
+ | 0.7367 | 8550 | 1.4678 | - |
580
+ | 0.7410 | 8600 | 1.8328 | - |
581
+ | 0.7453 | 8650 | 1.5184 | - |
582
+ | 0.7496 | 8700 | 1.6247 | - |
583
+ | 0.7539 | 8750 | 1.5787 | - |
584
+ | 0.7582 | 8800 | 1.6704 | - |
585
+ | 0.7625 | 8850 | 1.5755 | - |
586
+ | 0.7668 | 8900 | 1.6273 | - |
587
+ | 0.7712 | 8950 | 1.614 | - |
588
+ | 0.7755 | 9000 | 1.5335 | - |
589
+ | 0.7798 | 9050 | 1.461 | - |
590
+ | 0.7841 | 9100 | 1.5011 | - |
591
+ | 0.7884 | 9150 | 1.6853 | - |
592
+ | 0.7927 | 9200 | 1.4713 | - |
593
+ | 0.7970 | 9250 | 1.504 | - |
594
+ | 0.7996 | 9280 | - | 0.4436 |
595
+ | 0.8013 | 9300 | 1.5662 | - |
596
+ | 0.8056 | 9350 | 1.3562 | - |
597
+ | 0.8099 | 9400 | 1.4698 | - |
598
+ | 0.8142 | 9450 | 1.5387 | - |
599
+ | 0.8185 | 9500 | 1.3739 | - |
600
+ | 0.8229 | 9550 | 1.4344 | - |
601
+ | 0.8272 | 9600 | 1.5813 | - |
602
+ | 0.8315 | 9650 | 1.5476 | - |
603
+ | 0.8358 | 9700 | 1.4192 | - |
604
+ | 0.8401 | 9750 | 1.5959 | - |
605
+ | 0.8444 | 9800 | 1.463 | - |
606
+ | 0.8487 | 9850 | 1.5049 | - |
607
+ | 0.8530 | 9900 | 1.5464 | - |
608
+ | 0.8573 | 9950 | 1.5782 | - |
609
+ | 0.8616 | 10000 | 1.4452 | - |
610
+ | 0.8659 | 10050 | 1.3905 | - |
611
+ | 0.8702 | 10100 | 1.5898 | - |
612
+ | 0.8745 | 10150 | 1.3744 | - |
613
+ | 0.8789 | 10200 | 1.2622 | - |
614
+ | 0.8832 | 10250 | 1.1547 | - |
615
+ | 0.8875 | 10300 | 1.3283 | - |
616
+ | 0.8918 | 10350 | 1.4365 | - |
617
+ | 0.8961 | 10400 | 1.5452 | - |
618
+ | 0.8995 | 10440 | - | 0.4659 |
619
+ | 0.9004 | 10450 | 1.3644 | - |
620
+ | 0.9047 | 10500 | 1.4959 | - |
621
+ | 0.9090 | 10550 | 1.4951 | - |
622
+ | 0.9133 | 10600 | 1.3366 | - |
623
+ | 0.9176 | 10650 | 1.5537 | - |
624
+ | 0.9219 | 10700 | 1.2168 | - |
625
+ | 0.9262 | 10750 | 1.2671 | - |
626
+ | 0.9306 | 10800 | 1.2388 | - |
627
+ | 0.9349 | 10850 | 1.4667 | - |
628
+ | 0.9392 | 10900 | 1.2911 | - |
629
+ | 0.9435 | 10950 | 1.2547 | - |
630
+ | 0.9478 | 11000 | 1.4643 | - |
631
+ | 0.9521 | 11050 | 1.4337 | - |
632
+ | 0.9564 | 11100 | 1.2031 | - |
633
+ | 0.9607 | 11150 | 1.3594 | - |
634
+ | 0.9650 | 11200 | 1.3133 | - |
635
+ | 0.9693 | 11250 | 1.2628 | - |
636
+ | 0.9736 | 11300 | 1.116 | - |
637
+ | 0.9779 | 11350 | 1.2652 | - |
638
+ | 0.9823 | 11400 | 1.2119 | - |
639
+ | 0.9866 | 11450 | 1.1888 | - |
640
+ | 0.9909 | 11500 | 1.2845 | - |
641
+ | 0.9952 | 11550 | 1.399 | - |
642
+ | 0.9995 | 11600 | 1.0896 | 0.4985 |
643
+ | 1.0038 | 11650 | 1.1697 | - |
644
+ | 1.0081 | 11700 | 1.189 | - |
645
+ | 1.0124 | 11750 | 1.2988 | - |
646
+ | 1.0167 | 11800 | 1.178 | - |
647
+ | 1.0210 | 11850 | 1.4166 | - |
648
+ | 1.0253 | 11900 | 1.1385 | - |
649
+ | 1.0296 | 11950 | 1.1459 | - |
650
+ | 1.0339 | 12000 | 1.2123 | - |
651
+ | 1.0383 | 12050 | 1.0782 | - |
652
+ | 1.0426 | 12100 | 1.2136 | - |
653
+ | 1.0469 | 12150 | 1.2298 | - |
654
+ | 1.0512 | 12200 | 1.2266 | - |
655
+ | 1.0555 | 12250 | 1.1184 | - |
656
+ | 1.0598 | 12300 | 1.1255 | - |
657
+ | 1.0641 | 12350 | 1.2786 | - |
658
+ | 1.0684 | 12400 | 1.2258 | - |
659
+ | 1.0727 | 12450 | 1.2677 | - |
660
+ | 1.0770 | 12500 | 1.1009 | - |
661
+ | 1.0813 | 12550 | 1.3069 | - |
662
+ | 1.0856 | 12600 | 1.1574 | - |
663
+ | 1.0900 | 12650 | 1.232 | - |
664
+ | 1.0943 | 12700 | 1.3349 | - |
665
+ | 1.0986 | 12750 | 1.0868 | - |
666
+ | 1.0994 | 12760 | - | 0.5223 |
667
+ | 1.1029 | 12800 | 1.1968 | - |
668
+ | 1.1072 | 12850 | 1.1317 | - |
669
+ | 1.1115 | 12900 | 1.0791 | - |
670
+ | 1.1158 | 12950 | 1.1399 | - |
671
+ | 1.1201 | 13000 | 1.1907 | - |
672
+ | 1.1244 | 13050 | 1.322 | - |
673
+ | 1.1287 | 13100 | 1.2167 | - |
674
+ | 1.1330 | 13150 | 1.1696 | - |
675
+ | 1.1373 | 13200 | 1.2748 | - |
676
+ | 1.1417 | 13250 | 1.2751 | - |
677
+ | 1.1460 | 13300 | 1.2965 | - |
678
+ | 1.1503 | 13350 | 1.1097 | - |
679
+ | 1.1546 | 13400 | 1.3141 | - |
680
+ | 1.1589 | 13450 | 1.2249 | - |
681
+ | 1.1632 | 13500 | 1.4477 | - |
682
+ | 1.1675 | 13550 | 1.1688 | - |
683
+ | 1.1718 | 13600 | 1.2521 | - |
684
+ | 1.1761 | 13650 | 1.0834 | - |
685
+ | 1.1804 | 13700 | 1.2089 | - |
686
+ | 1.1847 | 13750 | 1.0982 | - |
687
+ | 1.1890 | 13800 | 1.2871 | - |
688
+ | 1.1933 | 13850 | 1.053 | - |
689
+ | 1.1977 | 13900 | 1.1601 | - |
690
+ | 1.1994 | 13920 | - | 0.5383 |
691
+ | 1.2020 | 13950 | 1.2559 | - |
692
+ | 1.2063 | 14000 | 1.076 | - |
693
+ | 1.2106 | 14050 | 1.2375 | - |
694
+ | 1.2149 | 14100 | 1.1363 | - |
695
+ | 1.2192 | 14150 | 1.1253 | - |
696
+ | 1.2235 | 14200 | 1.0961 | - |
697
+ | 1.2278 | 14250 | 1.1226 | - |
698
+ | 1.2321 | 14300 | 1.0251 | - |
699
+ | 1.2364 | 14350 | 1.087 | - |
700
+ | 1.2407 | 14400 | 1.1262 | - |
701
+ | 1.2450 | 14450 | 1.2847 | - |
702
+ | 1.2494 | 14500 | 1.1392 | - |
703
+ | 1.2537 | 14550 | 1.2119 | - |
704
+ | 1.2580 | 14600 | 1.0831 | - |
705
+ | 1.2623 | 14650 | 1.1392 | - |
706
+ | 1.2666 | 14700 | 1.2348 | - |
707
+ | 1.2709 | 14750 | 1.1431 | - |
708
+ | 1.2752 | 14800 | 1.1248 | - |
709
+ | 1.2795 | 14850 | 1.1533 | - |
710
+ | 1.2838 | 14900 | 1.134 | - |
711
+ | 1.2881 | 14950 | 1.1922 | - |
712
+ | 1.2924 | 15000 | 1.2331 | - |
713
+ | 1.2967 | 15050 | 1.1185 | - |
714
+ | 1.2993 | 15080 | - | 0.5594 |
715
+ | 1.3011 | 15100 | 1.3496 | - |
716
+ | 1.3054 | 15150 | 1.0629 | - |
717
+ | 1.3097 | 15200 | 1.2785 | - |
718
+ | 1.3140 | 15250 | 1.2427 | - |
719
+ | 1.3183 | 15300 | 1.2051 | - |
720
+ | 1.3226 | 15350 | 0.9325 | - |
721
+ | 1.3269 | 15400 | 1.0465 | - |
722
+ | 1.3312 | 15450 | 1.1105 | - |
723
+ | 1.3355 | 15500 | 1.1853 | - |
724
+ | 1.3398 | 15550 | 1.1192 | - |
725
+ | 1.3441 | 15600 | 1.0018 | - |
726
+ | 1.3484 | 15650 | 1.1357 | - |
727
+ | 1.3527 | 15700 | 1.2298 | - |
728
+ | 1.3571 | 15750 | 1.0783 | - |
729
+ | 1.3614 | 15800 | 1.271 | - |
730
+ | 1.3657 | 15850 | 1.1724 | - |
731
+ | 1.3700 | 15900 | 1.273 | - |
732
+ | 1.3743 | 15950 | 1.2049 | - |
733
+ | 1.3786 | 16000 | 0.9902 | - |
734
+ | 1.3829 | 16050 | 1.1044 | - |
735
+ | 1.3872 | 16100 | 1.1175 | - |
736
+ | 1.3915 | 16150 | 1.0599 | - |
737
+ | 1.3958 | 16200 | 1.1392 | - |
738
+ | 1.3993 | 16240 | - | 0.5806 |
739
+ | 1.4001 | 16250 | 1.1629 | - |
740
+ | 1.4044 | 16300 | 1.1323 | - |
741
+ | 1.4088 | 16350 | 1.2096 | - |
742
+ | 1.4131 | 16400 | 0.9091 | - |
743
+ | 1.4174 | 16450 | 1.1328 | - |
744
+ | 1.4217 | 16500 | 1.1584 | - |
745
+ | 1.4260 | 16550 | 1.2615 | - |
746
+ | 1.4303 | 16600 | 1.1547 | - |
747
+ | 1.4346 | 16650 | 1.0805 | - |
748
+ | 1.4389 | 16700 | 1.2107 | - |
749
+ | 1.4432 | 16750 | 1.1184 | - |
750
+ | 1.4475 | 16800 | 1.0953 | - |
751
+ | 1.4518 | 16850 | 1.2088 | - |
752
+ | 1.4561 | 16900 | 1.0663 | - |
753
+ | 1.4605 | 16950 | 1.0531 | - |
754
+ | 1.4648 | 17000 | 1.0374 | - |
755
+ | 1.4691 | 17050 | 1.1432 | - |
756
+ | 1.4734 | 17100 | 1.0345 | - |
757
+ | 1.4777 | 17150 | 1.0081 | - |
758
+ | 1.4820 | 17200 | 1.0979 | - |
759
+ | 1.4863 | 17250 | 1.0554 | - |
760
+ | 1.4906 | 17300 | 1.1095 | - |
761
+ | 1.4949 | 17350 | 1.1157 | - |
762
+ | 1.4992 | 17400 | 1.0901 | 0.5940 |
763
+ | 1.5035 | 17450 | 1.2183 | - |
764
+ | 1.5078 | 17500 | 1.1127 | - |
765
+ | 1.5121 | 17550 | 0.9928 | - |
766
+ | 1.5165 | 17600 | 1.0612 | - |
767
+ | 1.5208 | 17650 | 1.2894 | - |
768
+ | 1.5251 | 17700 | 1.0407 | - |
769
+ | 1.5294 | 17750 | 1.0467 | - |
770
+ | 1.5337 | 17800 | 1.1305 | - |
771
+ | 1.5380 | 17850 | 1.2103 | - |
772
+ | 1.5423 | 17900 | 1.0317 | - |
773
+ | 1.5466 | 17950 | 0.8727 | - |
774
+ | 1.5509 | 18000 | 1.0039 | - |
775
+ | 1.5552 | 18050 | 1.1078 | - |
776
+ | 1.5595 | 18100 | 0.8985 | - |
777
+ | 1.5638 | 18150 | 1.073 | - |
778
+ | 1.5682 | 18200 | 1.1185 | - |
779
+ | 1.5725 | 18250 | 1.1867 | - |
780
+ | 1.5768 | 18300 | 1.0053 | - |
781
+ | 1.5811 | 18350 | 1.0772 | - |
782
+ | 1.5854 | 18400 | 1.1199 | - |
783
+ | 1.5897 | 18450 | 1.1933 | - |
784
+ | 1.5940 | 18500 | 1.1376 | - |
785
+ | 1.5983 | 18550 | 1.0323 | - |
786
+ | 1.5992 | 18560 | - | 0.6092 |
787
+ | 1.6026 | 18600 | 1.1533 | - |
788
+ | 1.6069 | 18650 | 1.1542 | - |
789
+ | 1.6112 | 18700 | 0.8537 | - |
790
+ | 1.6155 | 18750 | 1.2019 | - |
791
+ | 1.6199 | 18800 | 0.9037 | - |
792
+ | 1.6242 | 18850 | 1.1072 | - |
793
+ | 1.6285 | 18900 | 0.9368 | - |
794
+ | 1.6328 | 18950 | 0.8755 | - |
795
+ | 1.6371 | 19000 | 1.0589 | - |
796
+ | 1.6414 | 19050 | 1.2077 | - |
797
+ | 1.6457 | 19100 | 1.0273 | - |
798
+ | 1.6500 | 19150 | 0.9574 | - |
799
+ | 1.6543 | 19200 | 0.9654 | - |
800
+ | 1.6586 | 19250 | 0.9936 | - |
801
+ | 1.6629 | 19300 | 0.936 | - |
802
+ | 1.6672 | 19350 | 1.1334 | - |
803
+ | 1.6715 | 19400 | 1.1132 | - |
804
+ | 1.6759 | 19450 | 0.9652 | - |
805
+ | 1.6802 | 19500 | 0.9999 | - |
806
+ | 1.6845 | 19550 | 1.0588 | - |
807
+ | 1.6888 | 19600 | 0.8735 | - |
808
+ | 1.6931 | 19650 | 1.0931 | - |
809
+ | 1.6974 | 19700 | 0.9329 | - |
810
+ | 1.6991 | 19720 | - | 0.6159 |
811
+ | 1.7017 | 19750 | 1.0249 | - |
812
+ | 1.7060 | 19800 | 0.9529 | - |
813
+ | 1.7103 | 19850 | 1.0974 | - |
814
+ | 1.7146 | 19900 | 1.156 | - |
815
+ | 1.7189 | 19950 | 1.2541 | - |
816
+ | 1.7232 | 20000 | 1.1157 | - |
817
+ | 1.7276 | 20050 | 0.9739 | - |
818
+ | 1.7319 | 20100 | 0.8053 | - |
819
+ | 1.7362 | 20150 | 0.9672 | - |
820
+ | 1.7405 | 20200 | 0.9638 | - |
821
+ | 1.7448 | 20250 | 1.0336 | - |
822
+ | 1.7491 | 20300 | 1.0707 | - |
823
+ | 1.7534 | 20350 | 1.1464 | - |
824
+ | 1.7577 | 20400 | 0.9545 | - |
825
+ | 1.7620 | 20450 | 1.0381 | - |
826
+ | 1.7663 | 20500 | 1.217 | - |
827
+ | 1.7706 | 20550 | 1.1779 | - |
828
+ | 1.7749 | 20600 | 0.8474 | - |
829
+ | 1.7793 | 20650 | 1.062 | - |
830
+ | 1.7836 | 20700 | 0.8884 | - |
831
+ | 1.7879 | 20750 | 1.1615 | - |
832
+ | 1.7922 | 20800 | 1.0987 | - |
833
+ | 1.7965 | 20850 | 1.126 | - |
834
+ | 1.7991 | 20880 | - | 0.6320 |
835
+ | 1.8008 | 20900 | 1.0833 | - |
836
+ | 1.8051 | 20950 | 1.049 | - |
837
+ | 1.8094 | 21000 | 1.0177 | - |
838
+ | 1.8137 | 21050 | 1.1588 | - |
839
+ | 1.8180 | 21100 | 0.9397 | - |
840
+ | 1.8223 | 21150 | 0.9947 | - |
841
+ | 1.8266 | 21200 | 1.0446 | - |
842
+ | 1.8309 | 21250 | 1.1826 | - |
843
+ | 1.8353 | 21300 | 0.9498 | - |
844
+ | 1.8396 | 21350 | 1.3614 | - |
845
+ | 1.8439 | 21400 | 1.1025 | - |
846
+ | 1.8482 | 21450 | 1.028 | - |
847
+ | 1.8525 | 21500 | 1.0175 | - |
848
+ | 1.8568 | 21550 | 0.8465 | - |
849
+ | 1.8611 | 21600 | 0.9803 | - |
850
+ | 1.8654 | 21650 | 0.8592 | - |
851
+ | 1.8697 | 21700 | 0.9792 | - |
852
+ | 1.8740 | 21750 | 1.0933 | - |
853
+ | 1.8783 | 21800 | 0.8312 | - |
854
+ | 1.8826 | 21850 | 1.0615 | - |
855
+ | 1.8870 | 21900 | 1.0027 | - |
856
+ | 1.8913 | 21950 | 1.1034 | - |
857
+ | 1.8956 | 22000 | 1.0831 | - |
858
+ | 1.8990 | 22040 | - | 0.6385 |
859
+ | 1.8999 | 22050 | 0.9895 | - |
860
+ | 1.9042 | 22100 | 1.1019 | - |
861
+ | 1.9085 | 22150 | 1.1036 | - |
862
+ | 1.9128 | 22200 | 0.9039 | - |
863
+ | 1.9171 | 22250 | 1.0744 | - |
864
+ | 1.9214 | 22300 | 1.1484 | - |
865
+ | 1.9257 | 22350 | 1.0977 | - |
866
+ | 1.9300 | 22400 | 1.091 | - |
867
+ | 1.9343 | 22450 | 0.8213 | - |
868
+ | 1.9387 | 22500 | 1.0402 | - |
869
+ | 1.9430 | 22550 | 1.1233 | - |
870
+ | 1.9473 | 22600 | 1.0408 | - |
871
+ | 1.9516 | 22650 | 1.1515 | - |
872
+ | 1.9559 | 22700 | 1.1289 | - |
873
+ | 1.9602 | 22750 | 0.8997 | - |
874
+ | 1.9645 | 22800 | 0.9587 | - |
875
+ | 1.9688 | 22850 | 0.9716 | - |
876
+ | 1.9731 | 22900 | 0.9622 | - |
877
+ | 1.9774 | 22950 | 1.0119 | - |
878
+ | 1.9817 | 23000 | 1.0433 | - |
879
+ | 1.9860 | 23050 | 1.1165 | - |
880
+ | 1.9903 | 23100 | 0.9443 | - |
881
+ | 1.9947 | 23150 | 1.0661 | - |
882
+ | 1.9990 | 23200 | 1.0166 | 0.6490 |
883
+ | 2.0033 | 23250 | 0.982 | - |
884
+ | 2.0076 | 23300 | 1.1731 | - |
885
+ | 2.0119 | 23350 | 1.0112 | - |
886
+ | 2.0162 | 23400 | 1.0373 | - |
887
+ | 2.0205 | 23450 | 0.8866 | - |
888
+ | 2.0248 | 23500 | 0.9581 | - |
889
+ | 2.0291 | 23550 | 1.2335 | - |
890
+ | 2.0334 | 23600 | 0.9536 | - |
891
+ | 2.0377 | 23650 | 0.9767 | - |
892
+ | 2.0420 | 23700 | 1.0382 | - |
893
+ | 2.0464 | 23750 | 1.1288 | - |
894
+ | 2.0507 | 23800 | 0.8292 | - |
895
+ | 2.0550 | 23850 | 1.1083 | - |
896
+ | 2.0593 | 23900 | 0.9252 | - |
897
+ | 2.0636 | 23950 | 1.1108 | - |
898
+ | 2.0679 | 24000 | 1.1602 | - |
899
+ | 2.0722 | 24050 | 0.9616 | - |
900
+ | 2.0765 | 24100 | 1.0108 | - |
901
+ | 2.0808 | 24150 | 1.0974 | - |
902
+ | 2.0851 | 24200 | 0.9542 | - |
903
+ | 2.0894 | 24250 | 0.9269 | - |
904
+ | 2.0937 | 24300 | 1.0494 | - |
905
+ | 2.0981 | 24350 | 1.074 | - |
906
+ | 2.0989 | 24360 | - | 0.6508 |
907
+ | 2.1024 | 24400 | 0.8881 | - |
908
+ | 2.1067 | 24450 | 1.0372 | - |
909
+ | 2.1110 | 24500 | 1.0833 | - |
910
+ | 2.1153 | 24550 | 1.1226 | - |
911
+ | 2.1196 | 24600 | 1.1199 | - |
912
+ | 2.1239 | 24650 | 0.9263 | - |
913
+ | 2.1282 | 24700 | 0.9799 | - |
914
+ | 2.1325 | 24750 | 0.9388 | - |
915
+ | 2.1368 | 24800 | 1.1606 | - |
916
+ | 2.1411 | 24850 | 0.998 | - |
917
+ | 2.1454 | 24900 | 1.1349 | - |
918
+ | 2.1498 | 24950 | 1.1257 | - |
919
+ | 2.1541 | 25000 | 0.9132 | - |
920
+ | 2.1584 | 25050 | 1.068 | - |
921
+ | 2.1627 | 25100 | 0.9177 | - |
922
+ | 2.1670 | 25150 | 1.0174 | - |
923
+ | 2.1713 | 25200 | 1.1028 | - |
924
+ | 2.1756 | 25250 | 0.9742 | - |
925
+ | 2.1799 | 25300 | 0.9095 | - |
926
+ | 2.1842 | 25350 | 0.9706 | - |
927
+ | 2.1885 | 25400 | 1.1514 | - |
928
+ | 2.1928 | 25450 | 1.1459 | - |
929
+ | 2.1971 | 25500 | 1.2085 | - |
930
+ | 2.1989 | 25520 | - | 0.6582 |
931
+ | 2.2014 | 25550 | 0.9208 | - |
932
+ | 2.2058 | 25600 | 1.1146 | - |
933
+ | 2.2101 | 25650 | 1.003 | - |
934
+ | 2.2144 | 25700 | 0.9197 | - |
935
+ | 2.2187 | 25750 | 1.029 | - |
936
+ | 2.2230 | 25800 | 1.1035 | - |
937
+ | 2.2273 | 25850 | 1.0754 | - |
938
+ | 2.2316 | 25900 | 1.1675 | - |
939
+ | 2.2359 | 25950 | 0.9714 | - |
940
+ | 2.2402 | 26000 | 1.116 | - |
941
+ | 2.2445 | 26050 | 1.0347 | - |
942
+ | 2.2488 | 26100 | 1.027 | - |
943
+ | 2.2531 | 26150 | 0.9373 | - |
944
+ | 2.2575 | 26200 | 1.1202 | - |
945
+ | 2.2618 | 26250 | 0.8809 | - |
946
+ | 2.2661 | 26300 | 1.0182 | - |
947
+ | 2.2704 | 26350 | 1.0033 | - |
948
+ | 2.2747 | 26400 | 0.9937 | - |
949
+ | 2.2790 | 26450 | 1.0004 | - |
950
+ | 2.2833 | 26500 | 1.0014 | - |
951
+ | 2.2876 | 26550 | 1.2473 | - |
952
+ | 2.2919 | 26600 | 1.0909 | - |
953
+ | 2.2962 | 26650 | 1.1588 | - |
954
+ | 2.2988 | 26680 | - | 0.6620 |
955
+ | 2.3005 | 26700 | 0.9797 | - |
956
+ | 2.3048 | 26750 | 1.1163 | - |
957
+ | 2.3092 | 26800 | 1.1619 | - |
958
+ | 2.3135 | 26850 | 0.9237 | - |
959
+ | 2.3178 | 26900 | 0.9336 | - |
960
+ | 2.3221 | 26950 | 1.0761 | - |
961
+ | 2.3264 | 27000 | 1.0624 | - |
962
+ | 2.3307 | 27050 | 0.9467 | - |
963
+ | 2.3350 | 27100 | 1.2416 | - |
964
+ | 2.3393 | 27150 | 0.8832 | - |
965
+ | 2.3436 | 27200 | 1.0419 | - |
966
+ | 2.3479 | 27250 | 0.8805 | - |
967
+ | 2.3522 | 27300 | 1.063 | - |
968
+ | 2.3565 | 27350 | 1.0 | - |
969
+ | 2.3608 | 27400 | 0.9411 | - |
970
+ | 2.3652 | 27450 | 1.2561 | - |
971
+ | 2.3695 | 27500 | 1.0111 | - |
972
+ | 2.3738 | 27550 | 0.9595 | - |
973
+ | 2.3781 | 27600 | 0.8381 | - |
974
+ | 2.3824 | 27650 | 1.0234 | - |
975
+ | 2.3867 | 27700 | 0.8935 | - |
976
+ | 2.3910 | 27750 | 0.8965 | - |
977
+ | 2.3953 | 27800 | 1.0653 | - |
978
+ | 2.3988 | 27840 | - | 0.6641 |
979
+ | 2.3996 | 27850 | 1.0907 | - |
980
+ | 2.4039 | 27900 | 1.0517 | - |
981
+ | 2.4082 | 27950 | 0.9392 | - |
982
+ | 2.4125 | 28000 | 0.9978 | - |
983
+ | 2.4169 | 28050 | 1.0318 | - |
984
+ | 2.4212 | 28100 | 0.9021 | - |
985
+ | 2.4255 | 28150 | 0.9216 | - |
986
+ | 2.4298 | 28200 | 1.0857 | - |
987
+ | 2.4341 | 28250 | 0.9689 | - |
988
+ | 2.4384 | 28300 | 1.0085 | - |
989
+ | 2.4427 | 28350 | 1.0434 | - |
990
+ | 2.4470 | 28400 | 1.1309 | - |
991
+ | 2.4513 | 28450 | 0.9319 | - |
992
+ | 2.4556 | 28500 | 0.9562 | - |
993
+ | 2.4599 | 28550 | 0.9197 | - |
994
+ | 2.4642 | 28600 | 1.2111 | - |
995
+ | 2.4686 | 28650 | 1.0983 | - |
996
+ | 2.4729 | 28700 | 0.9562 | - |
997
+ | 2.4772 | 28750 | 0.9327 | - |
998
+ | 2.4815 | 28800 | 0.9716 | - |
999
+ | 2.4858 | 28850 | 1.0202 | - |
1000
+ | 2.4901 | 28900 | 1.1367 | - |
1001
+ | 2.4944 | 28950 | 0.9014 | - |
1002
+ | 2.4987 | 29000 | 1.1313 | 0.6672 |
1003
+ | 2.5030 | 29050 | 1.148 | - |
1004
+ | 2.5073 | 29100 | 0.799 | - |
1005
+ | 2.5116 | 29150 | 1.0012 | - |
1006
+ | 2.5159 | 29200 | 0.7844 | - |
1007
+ | 2.5202 | 29250 | 1.1639 | - |
1008
+ | 2.5246 | 29300 | 0.9905 | - |
1009
+ | 2.5289 | 29350 | 1.0579 | - |
1010
+ | 2.5332 | 29400 | 0.9329 | - |
1011
+ | 2.5375 | 29450 | 0.9496 | - |
1012
+ | 2.5418 | 29500 | 0.9521 | - |
1013
+ | 2.5461 | 29550 | 0.8535 | - |
1014
+ | 2.5504 | 29600 | 1.019 | - |
1015
+ | 2.5547 | 29650 | 1.1031 | - |
1016
+ | 2.5590 | 29700 | 1.0894 | - |
1017
+ | 2.5633 | 29750 | 1.0078 | - |
1018
+ | 2.5676 | 29800 | 0.8403 | - |
1019
+ | 2.5719 | 29850 | 0.916 | - |
1020
+ | 2.5763 | 29900 | 1.2096 | - |
1021
+ | 2.5806 | 29950 | 0.9969 | - |
1022
+ | 2.5849 | 30000 | 1.1598 | - |
1023
+ | 2.5892 | 30050 | 0.8849 | - |
1024
+ | 2.5935 | 30100 | 1.0619 | - |
1025
+ | 2.5978 | 30150 | 0.9554 | - |
1026
+ | 2.5987 | 30160 | - | 0.6693 |
1027
+ | 2.6021 | 30200 | 1.1025 | - |
1028
+ | 2.6064 | 30250 | 1.1252 | - |
1029
+ | 2.6107 | 30300 | 0.8108 | - |
1030
+ | 2.6150 | 30350 | 0.927 | - |
1031
+ | 2.6193 | 30400 | 1.1574 | - |
1032
+ | 2.6236 | 30450 | 1.0098 | - |
1033
+ | 2.6280 | 30500 | 0.8702 | - |
1034
+ | 2.6323 | 30550 | 0.9672 | - |
1035
+ | 2.6366 | 30600 | 0.9361 | - |
1036
+ | 2.6409 | 30650 | 0.9801 | - |
1037
+ | 2.6452 | 30700 | 1.114 | - |
1038
+ | 2.6495 | 30750 | 0.8666 | - |
1039
+ | 2.6538 | 30800 | 0.9648 | - |
1040
+ | 2.6581 | 30850 | 0.9423 | - |
1041
+ | 2.6624 | 30900 | 1.059 | - |
1042
+ | 2.6667 | 30950 | 0.9149 | - |
1043
+ | 2.6710 | 31000 | 0.8954 | - |
1044
+ | 2.6753 | 31050 | 0.8769 | - |
1045
+ | 2.6796 | 31100 | 0.8124 | - |
1046
+ | 2.6840 | 31150 | 1.151 | - |
1047
+ | 2.6883 | 31200 | 1.0145 | - |
1048
+ | 2.6926 | 31250 | 0.9653 | - |
1049
+ | 2.6969 | 31300 | 1.136 | - |
1050
+ | 2.6986 | 31320 | - | 0.6693 |
1051
+ | 2.7012 | 31350 | 0.9122 | - |
1052
+ | 2.7055 | 31400 | 1.0161 | - |
1053
+ | 2.7098 | 31450 | 1.0152 | - |
1054
+ | 2.7141 | 31500 | 1.1181 | - |
1055
+ | 2.7184 | 31550 | 0.8969 | - |
1056
+ | 2.7227 | 31600 | 1.2101 | - |
1057
+ | 2.7270 | 31650 | 1.0958 | - |
1058
+ | 2.7313 | 31700 | 0.9548 | - |
1059
+ | 2.7357 | 31750 | 0.9755 | - |
1060
+ | 2.7400 | 31800 | 0.9796 | - |
1061
+ | 2.7443 | 31850 | 1.0564 | - |
1062
+ | 2.7486 | 31900 | 0.9581 | - |
1063
+ | 2.7529 | 31950 | 0.8607 | - |
1064
+ | 2.7572 | 32000 | 0.8933 | - |
1065
+ | 2.7615 | 32050 | 0.9828 | - |
1066
+ | 2.7658 | 32100 | 1.1992 | - |
1067
+ | 2.7701 | 32150 | 1.0162 | - |
1068
+ | 2.7744 | 32200 | 0.8406 | - |
1069
+ | 2.7787 | 32250 | 0.7896 | - |
1070
+ | 2.7830 | 32300 | 1.0311 | - |
1071
+ | 2.7874 | 32350 | 1.0507 | - |
1072
+ | 2.7917 | 32400 | 1.136 | - |
1073
+ | 2.7960 | 32450 | 1.0504 | - |
1074
+ | 2.7986 | 32480 | - | 0.6697 |
1075
+ | 2.8003 | 32500 | 0.9271 | - |
1076
+ | 2.8046 | 32550 | 1.0412 | - |
1077
+ | 2.8089 | 32600 | 0.8542 | - |
1078
+ | 2.8132 | 32650 | 1.1015 | - |
1079
+ | 2.8175 | 32700 | 0.9957 | - |
1080
+ | 2.8218 | 32750 | 1.0845 | - |
1081
+ | 2.8261 | 32800 | 1.1226 | - |
1082
+ | 2.8304 | 32850 | 1.0235 | - |
1083
+ | 2.8347 | 32900 | 0.996 | - |
1084
+ | 2.8390 | 32950 | 1.0855 | - |
1085
+ | 2.8434 | 33000 | 1.2322 | - |
1086
+ | 2.8477 | 33050 | 0.999 | - |
1087
+ | 2.8520 | 33100 | 1.04 | - |
1088
+ | 2.8563 | 33150 | 1.1466 | - |
1089
+ | 2.8606 | 33200 | 0.9061 | - |
1090
+ | 2.8649 | 33250 | 1.0011 | - |
1091
+ | 2.8692 | 33300 | 1.0205 | - |
1092
+ | 2.8735 | 33350 | 1.0136 | - |
1093
+ | 2.8778 | 33400 | 0.8956 | - |
1094
+ | 2.8821 | 33450 | 0.9722 | - |
1095
+ | 2.8864 | 33500 | 0.8962 | - |
1096
+ | 2.8907 | 33550 | 0.9545 | - |
1097
+ | 2.8951 | 33600 | 0.8474 | - |
1098
+ | 2.8985 | 33640 | - | 0.6700 |
1099
+ | 2.8994 | 33650 | 0.782 | - |
1100
+ | 2.9037 | 33700 | 0.9551 | - |
1101
+ | 2.9080 | 33750 | 1.0217 | - |
1102
+ | 2.9123 | 33800 | 0.8188 | - |
1103
+ | 2.9166 | 33850 | 1.0652 | - |
1104
+ | 2.9209 | 33900 | 1.1314 | - |
1105
+ | 2.9252 | 33950 | 0.9487 | - |
1106
+ | 2.9295 | 34000 | 0.9906 | - |
1107
+ | 2.9338 | 34050 | 1.1317 | - |
1108
+ | 2.9381 | 34100 | 0.9139 | - |
1109
+ | 2.9424 | 34150 | 0.9394 | - |
1110
+ | 2.9468 | 34200 | 0.9904 | - |
1111
+ | 2.9511 | 34250 | 1.0758 | - |
1112
+ | 2.9554 | 34300 | 0.9388 | - |
1113
+ | 2.9597 | 34350 | 0.9417 | - |
1114
+ | 2.9640 | 34400 | 0.9871 | - |
1115
+ | 2.9683 | 34450 | 1.0431 | - |
1116
+ | 2.9726 | 34500 | 1.0538 | - |
1117
+ | 2.9769 | 34550 | 1.078 | - |
1118
+ | 2.9812 | 34600 | 1.0972 | - |
1119
+ | 2.9855 | 34650 | 1.0294 | - |
1120
+ | 2.9898 | 34700 | 1.0387 | - |
1121
+ | 2.9941 | 34750 | 0.8923 | - |
1122
+ | 2.9984 | 34800 | 1.0937 | 0.6698 |
1123
+
1124
+ </details>
1125
+
1126
+ ### Framework Versions
1127
+ - Python: 3.12.3
1128
+ - Sentence Transformers: 5.3.0
1129
+ - Transformers: 4.57.6
1130
+ - PyTorch: 2.9.1+cu128
1131
+ - Accelerate: 1.13.0
1132
+ - Datasets: 4.6.1
1133
+ - Tokenizers: 0.22.2
1134
+
1135
+ ## Citation
1136
+
1137
+ ### BibTeX
1138
+
1139
+ #### Sentence Transformers
1140
+ ```bibtex
1141
+ @inproceedings{reimers-2019-sentence-bert,
1142
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
1143
+ author = "Reimers, Nils and Gurevych, Iryna",
1144
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
1145
+ month = "11",
1146
+ year = "2019",
1147
+ publisher = "Association for Computational Linguistics",
1148
+ url = "https://arxiv.org/abs/1908.10084",
1149
+ }
1150
+ ```
1151
+
1152
+ #### MatryoshkaLoss
1153
+ ```bibtex
1154
+ @misc{kusupati2024matryoshka,
1155
+ title={Matryoshka Representation Learning},
1156
+ author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
1157
+ year={2024},
1158
+ eprint={2205.13147},
1159
+ archivePrefix={arXiv},
1160
+ primaryClass={cs.LG}
1161
+ }
1162
+ ```
1163
+
1164
+ #### MultipleNegativesRankingLoss
1165
+ ```bibtex
1166
+ @misc{oord2019representationlearningcontrastivepredictive,
1167
+ title={Representation Learning with Contrastive Predictive Coding},
1168
+ author={Aaron van den Oord and Yazhe Li and Oriol Vinyals},
1169
+ year={2019},
1170
+ eprint={1807.03748},
1171
+ archivePrefix={arXiv},
1172
+ primaryClass={cs.LG},
1173
+ url={https://arxiv.org/abs/1807.03748},
1174
+ }
1175
+ ```
1176
+
1177
+ <!--
1178
+ ## Glossary
1179
+
1180
+ *Clearly define terms in order to be accessible across audiences.*
1181
+ -->
1182
+
1183
+ <!--
1184
+ ## Model Card Authors
1185
+
1186
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
1187
+ -->
1188
+
1189
+ <!--
1190
+ ## Model Card Contact
1191
+
1192
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
1193
+ -->
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertModel"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 50281,
8
+ "classifier_activation": "gelu",
9
+ "classifier_bias": false,
10
+ "classifier_dropout": 0.0,
11
+ "classifier_pooling": "mean",
12
+ "cls_token_id": 50281,
13
+ "decoder_bias": true,
14
+ "deterministic_flash_attn": false,
15
+ "dtype": "float32",
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": 50282,
18
+ "global_attn_every_n_layers": 3,
19
+ "global_rope_theta": 160000.0,
20
+ "gradient_checkpointing": false,
21
+ "hidden_activation": "gelu",
22
+ "hidden_size": 768,
23
+ "initializer_cutoff_factor": 2.0,
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 1152,
26
+ "layer_norm_eps": 1e-05,
27
+ "local_attention": 128,
28
+ "local_rope_theta": 10000.0,
29
+ "max_position_embeddings": 8192,
30
+ "mlp_bias": false,
31
+ "mlp_dropout": 0.0,
32
+ "model_type": "modernbert",
33
+ "norm_bias": false,
34
+ "norm_eps": 1e-05,
35
+ "num_attention_heads": 12,
36
+ "num_hidden_layers": 22,
37
+ "pad_token_id": 50283,
38
+ "position_embedding_type": "absolute",
39
+ "repad_logits_with_grad": false,
40
+ "sep_token_id": 50282,
41
+ "sparse_pred_ignore_index": -100,
42
+ "sparse_prediction": false,
43
+ "transformers_version": "4.57.6",
44
+ "vocab_size": 50368
45
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "5.3.0",
4
+ "transformers": "4.57.6",
5
+ "pytorch": "2.9.1+cu128"
6
+ },
7
+ "prompts": {
8
+ "query": "",
9
+ "document": ""
10
+ },
11
+ "default_prompt_name": null,
12
+ "similarity_fn_name": "cosine",
13
+ "model_type": "SentenceTransformer"
14
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbaa849f9b3b286921cbce2e4dbfdbf6a75399b14eb5176c008dda5207373393
3
+ size 596070136
modules.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ },
14
+ {
15
+ "idx": 2,
16
+ "name": "2",
17
+ "path": "2_Normalize",
18
+ "type": "sentence_transformers.models.Normalize"
19
+ }
20
+ ]
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 8192,
3
+ "do_lower_case": false
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,952 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "|||IP_ADDRESS|||",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "1": {
12
+ "content": "<|padding|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "50254": {
20
+ "content": " ",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "50255": {
28
+ "content": " ",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "50256": {
36
+ "content": " ",
37
+ "lstrip": false,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": false
42
+ },
43
+ "50257": {
44
+ "content": " ",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "50258": {
52
+ "content": " ",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "50259": {
60
+ "content": " ",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "50260": {
68
+ "content": " ",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "50261": {
76
+ "content": " ",
77
+ "lstrip": false,
78
+ "normalized": true,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "50262": {
84
+ "content": " ",
85
+ "lstrip": false,
86
+ "normalized": true,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "50263": {
92
+ "content": " ",
93
+ "lstrip": false,
94
+ "normalized": true,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "50264": {
100
+ "content": " ",
101
+ "lstrip": false,
102
+ "normalized": true,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "50265": {
108
+ "content": " ",
109
+ "lstrip": false,
110
+ "normalized": true,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "50266": {
116
+ "content": " ",
117
+ "lstrip": false,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "50267": {
124
+ "content": " ",
125
+ "lstrip": false,
126
+ "normalized": true,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "50268": {
132
+ "content": " ",
133
+ "lstrip": false,
134
+ "normalized": true,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "50269": {
140
+ "content": " ",
141
+ "lstrip": false,
142
+ "normalized": true,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "50270": {
148
+ "content": " ",
149
+ "lstrip": false,
150
+ "normalized": true,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "50271": {
156
+ "content": " ",
157
+ "lstrip": false,
158
+ "normalized": true,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "50272": {
164
+ "content": " ",
165
+ "lstrip": false,
166
+ "normalized": true,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "50273": {
172
+ "content": " ",
173
+ "lstrip": false,
174
+ "normalized": true,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "50274": {
180
+ "content": " ",
181
+ "lstrip": false,
182
+ "normalized": true,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "50275": {
188
+ "content": " ",
189
+ "lstrip": false,
190
+ "normalized": true,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "50276": {
196
+ "content": " ",
197
+ "lstrip": false,
198
+ "normalized": true,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "50277": {
204
+ "content": "|||EMAIL_ADDRESS|||",
205
+ "lstrip": false,
206
+ "normalized": true,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "50278": {
212
+ "content": "|||PHONE_NUMBER|||",
213
+ "lstrip": false,
214
+ "normalized": true,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "50279": {
220
+ "content": "<|endoftext|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "50280": {
228
+ "content": "[UNK]",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "50281": {
236
+ "content": "[CLS]",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "50282": {
244
+ "content": "[SEP]",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "50283": {
252
+ "content": "[PAD]",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "50284": {
260
+ "content": "[MASK]",
261
+ "lstrip": true,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "50285": {
268
+ "content": "[unused0]",
269
+ "lstrip": false,
270
+ "normalized": true,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "50286": {
276
+ "content": "[unused1]",
277
+ "lstrip": false,
278
+ "normalized": true,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "50287": {
284
+ "content": "[unused2]",
285
+ "lstrip": false,
286
+ "normalized": true,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": false
290
+ },
291
+ "50288": {
292
+ "content": "[unused3]",
293
+ "lstrip": false,
294
+ "normalized": true,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": false
298
+ },
299
+ "50289": {
300
+ "content": "[unused4]",
301
+ "lstrip": false,
302
+ "normalized": true,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": false
306
+ },
307
+ "50290": {
308
+ "content": "[unused5]",
309
+ "lstrip": false,
310
+ "normalized": true,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": false
314
+ },
315
+ "50291": {
316
+ "content": "[unused6]",
317
+ "lstrip": false,
318
+ "normalized": true,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": false
322
+ },
323
+ "50292": {
324
+ "content": "[unused7]",
325
+ "lstrip": false,
326
+ "normalized": true,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": false
330
+ },
331
+ "50293": {
332
+ "content": "[unused8]",
333
+ "lstrip": false,
334
+ "normalized": true,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": false
338
+ },
339
+ "50294": {
340
+ "content": "[unused9]",
341
+ "lstrip": false,
342
+ "normalized": true,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": false
346
+ },
347
+ "50295": {
348
+ "content": "[unused10]",
349
+ "lstrip": false,
350
+ "normalized": true,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": false
354
+ },
355
+ "50296": {
356
+ "content": "[unused11]",
357
+ "lstrip": false,
358
+ "normalized": true,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": false
362
+ },
363
+ "50297": {
364
+ "content": "[unused12]",
365
+ "lstrip": false,
366
+ "normalized": true,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": false
370
+ },
371
+ "50298": {
372
+ "content": "[unused13]",
373
+ "lstrip": false,
374
+ "normalized": true,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": false
378
+ },
379
+ "50299": {
380
+ "content": "[unused14]",
381
+ "lstrip": false,
382
+ "normalized": true,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": false
386
+ },
387
+ "50300": {
388
+ "content": "[unused15]",
389
+ "lstrip": false,
390
+ "normalized": true,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": false
394
+ },
395
+ "50301": {
396
+ "content": "[unused16]",
397
+ "lstrip": false,
398
+ "normalized": true,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": false
402
+ },
403
+ "50302": {
404
+ "content": "[unused17]",
405
+ "lstrip": false,
406
+ "normalized": true,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": false
410
+ },
411
+ "50303": {
412
+ "content": "[unused18]",
413
+ "lstrip": false,
414
+ "normalized": true,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": false
418
+ },
419
+ "50304": {
420
+ "content": "[unused19]",
421
+ "lstrip": false,
422
+ "normalized": true,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": false
426
+ },
427
+ "50305": {
428
+ "content": "[unused20]",
429
+ "lstrip": false,
430
+ "normalized": true,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": false
434
+ },
435
+ "50306": {
436
+ "content": "[unused21]",
437
+ "lstrip": false,
438
+ "normalized": true,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": false
442
+ },
443
+ "50307": {
444
+ "content": "[unused22]",
445
+ "lstrip": false,
446
+ "normalized": true,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": false
450
+ },
451
+ "50308": {
452
+ "content": "[unused23]",
453
+ "lstrip": false,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": false
458
+ },
459
+ "50309": {
460
+ "content": "[unused24]",
461
+ "lstrip": false,
462
+ "normalized": true,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": false
466
+ },
467
+ "50310": {
468
+ "content": "[unused25]",
469
+ "lstrip": false,
470
+ "normalized": true,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": false
474
+ },
475
+ "50311": {
476
+ "content": "[unused26]",
477
+ "lstrip": false,
478
+ "normalized": true,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": false
482
+ },
483
+ "50312": {
484
+ "content": "[unused27]",
485
+ "lstrip": false,
486
+ "normalized": true,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": false
490
+ },
491
+ "50313": {
492
+ "content": "[unused28]",
493
+ "lstrip": false,
494
+ "normalized": true,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": false
498
+ },
499
+ "50314": {
500
+ "content": "[unused29]",
501
+ "lstrip": false,
502
+ "normalized": true,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": false
506
+ },
507
+ "50315": {
508
+ "content": "[unused30]",
509
+ "lstrip": false,
510
+ "normalized": true,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": false
514
+ },
515
+ "50316": {
516
+ "content": "[unused31]",
517
+ "lstrip": false,
518
+ "normalized": true,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": false
522
+ },
523
+ "50317": {
524
+ "content": "[unused32]",
525
+ "lstrip": false,
526
+ "normalized": true,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": false
530
+ },
531
+ "50318": {
532
+ "content": "[unused33]",
533
+ "lstrip": false,
534
+ "normalized": true,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": false
538
+ },
539
+ "50319": {
540
+ "content": "[unused34]",
541
+ "lstrip": false,
542
+ "normalized": true,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": false
546
+ },
547
+ "50320": {
548
+ "content": "[unused35]",
549
+ "lstrip": false,
550
+ "normalized": true,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": false
554
+ },
555
+ "50321": {
556
+ "content": "[unused36]",
557
+ "lstrip": false,
558
+ "normalized": true,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": false
562
+ },
563
+ "50322": {
564
+ "content": "[unused37]",
565
+ "lstrip": false,
566
+ "normalized": true,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": false
570
+ },
571
+ "50323": {
572
+ "content": "[unused38]",
573
+ "lstrip": false,
574
+ "normalized": true,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": false
578
+ },
579
+ "50324": {
580
+ "content": "[unused39]",
581
+ "lstrip": false,
582
+ "normalized": true,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": false
586
+ },
587
+ "50325": {
588
+ "content": "[unused40]",
589
+ "lstrip": false,
590
+ "normalized": true,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": false
594
+ },
595
+ "50326": {
596
+ "content": "[unused41]",
597
+ "lstrip": false,
598
+ "normalized": true,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": false
602
+ },
603
+ "50327": {
604
+ "content": "[unused42]",
605
+ "lstrip": false,
606
+ "normalized": true,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": false
610
+ },
611
+ "50328": {
612
+ "content": "[unused43]",
613
+ "lstrip": false,
614
+ "normalized": true,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": false
618
+ },
619
+ "50329": {
620
+ "content": "[unused44]",
621
+ "lstrip": false,
622
+ "normalized": true,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": false
626
+ },
627
+ "50330": {
628
+ "content": "[unused45]",
629
+ "lstrip": false,
630
+ "normalized": true,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": false
634
+ },
635
+ "50331": {
636
+ "content": "[unused46]",
637
+ "lstrip": false,
638
+ "normalized": true,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": false
642
+ },
643
+ "50332": {
644
+ "content": "[unused47]",
645
+ "lstrip": false,
646
+ "normalized": true,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": false
650
+ },
651
+ "50333": {
652
+ "content": "[unused48]",
653
+ "lstrip": false,
654
+ "normalized": true,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": false
658
+ },
659
+ "50334": {
660
+ "content": "[unused49]",
661
+ "lstrip": false,
662
+ "normalized": true,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": false
666
+ },
667
+ "50335": {
668
+ "content": "[unused50]",
669
+ "lstrip": false,
670
+ "normalized": true,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": false
674
+ },
675
+ "50336": {
676
+ "content": "[unused51]",
677
+ "lstrip": false,
678
+ "normalized": true,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": false
682
+ },
683
+ "50337": {
684
+ "content": "[unused52]",
685
+ "lstrip": false,
686
+ "normalized": true,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": false
690
+ },
691
+ "50338": {
692
+ "content": "[unused53]",
693
+ "lstrip": false,
694
+ "normalized": true,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": false
698
+ },
699
+ "50339": {
700
+ "content": "[unused54]",
701
+ "lstrip": false,
702
+ "normalized": true,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": false
706
+ },
707
+ "50340": {
708
+ "content": "[unused55]",
709
+ "lstrip": false,
710
+ "normalized": true,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": false
714
+ },
715
+ "50341": {
716
+ "content": "[unused56]",
717
+ "lstrip": false,
718
+ "normalized": true,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": false
722
+ },
723
+ "50342": {
724
+ "content": "[unused57]",
725
+ "lstrip": false,
726
+ "normalized": true,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": false
730
+ },
731
+ "50343": {
732
+ "content": "[unused58]",
733
+ "lstrip": false,
734
+ "normalized": true,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": false
738
+ },
739
+ "50344": {
740
+ "content": "[unused59]",
741
+ "lstrip": false,
742
+ "normalized": true,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": false
746
+ },
747
+ "50345": {
748
+ "content": "[unused60]",
749
+ "lstrip": false,
750
+ "normalized": true,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": false
754
+ },
755
+ "50346": {
756
+ "content": "[unused61]",
757
+ "lstrip": false,
758
+ "normalized": true,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": false
762
+ },
763
+ "50347": {
764
+ "content": "[unused62]",
765
+ "lstrip": false,
766
+ "normalized": true,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": false
770
+ },
771
+ "50348": {
772
+ "content": "[unused63]",
773
+ "lstrip": false,
774
+ "normalized": true,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": false
778
+ },
779
+ "50349": {
780
+ "content": "[unused64]",
781
+ "lstrip": false,
782
+ "normalized": true,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": false
786
+ },
787
+ "50350": {
788
+ "content": "[unused65]",
789
+ "lstrip": false,
790
+ "normalized": true,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": false
794
+ },
795
+ "50351": {
796
+ "content": "[unused66]",
797
+ "lstrip": false,
798
+ "normalized": true,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": false
802
+ },
803
+ "50352": {
804
+ "content": "[unused67]",
805
+ "lstrip": false,
806
+ "normalized": true,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": false
810
+ },
811
+ "50353": {
812
+ "content": "[unused68]",
813
+ "lstrip": false,
814
+ "normalized": true,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": false
818
+ },
819
+ "50354": {
820
+ "content": "[unused69]",
821
+ "lstrip": false,
822
+ "normalized": true,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": false
826
+ },
827
+ "50355": {
828
+ "content": "[unused70]",
829
+ "lstrip": false,
830
+ "normalized": true,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": false
834
+ },
835
+ "50356": {
836
+ "content": "[unused71]",
837
+ "lstrip": false,
838
+ "normalized": true,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": false
842
+ },
843
+ "50357": {
844
+ "content": "[unused72]",
845
+ "lstrip": false,
846
+ "normalized": true,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": false
850
+ },
851
+ "50358": {
852
+ "content": "[unused73]",
853
+ "lstrip": false,
854
+ "normalized": true,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": false
858
+ },
859
+ "50359": {
860
+ "content": "[unused74]",
861
+ "lstrip": false,
862
+ "normalized": true,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": false
866
+ },
867
+ "50360": {
868
+ "content": "[unused75]",
869
+ "lstrip": false,
870
+ "normalized": true,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": false
874
+ },
875
+ "50361": {
876
+ "content": "[unused76]",
877
+ "lstrip": false,
878
+ "normalized": true,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": false
882
+ },
883
+ "50362": {
884
+ "content": "[unused77]",
885
+ "lstrip": false,
886
+ "normalized": true,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": false
890
+ },
891
+ "50363": {
892
+ "content": "[unused78]",
893
+ "lstrip": false,
894
+ "normalized": true,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": false
898
+ },
899
+ "50364": {
900
+ "content": "[unused79]",
901
+ "lstrip": false,
902
+ "normalized": true,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": false
906
+ },
907
+ "50365": {
908
+ "content": "[unused80]",
909
+ "lstrip": false,
910
+ "normalized": true,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": false
914
+ },
915
+ "50366": {
916
+ "content": "[unused81]",
917
+ "lstrip": false,
918
+ "normalized": true,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": false
922
+ },
923
+ "50367": {
924
+ "content": "[unused82]",
925
+ "lstrip": false,
926
+ "normalized": true,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": false
930
+ }
931
+ },
932
+ "clean_up_tokenization_spaces": true,
933
+ "cls_token": "[CLS]",
934
+ "extra_special_tokens": {},
935
+ "mask_token": "[MASK]",
936
+ "max_length": 8192,
937
+ "model_input_names": [
938
+ "input_ids",
939
+ "attention_mask"
940
+ ],
941
+ "model_max_length": 8192,
942
+ "pad_to_multiple_of": null,
943
+ "pad_token": "[PAD]",
944
+ "pad_token_type_id": 0,
945
+ "padding_side": "right",
946
+ "sep_token": "[SEP]",
947
+ "stride": 0,
948
+ "tokenizer_class": "PreTrainedTokenizerFast",
949
+ "truncation_side": "right",
950
+ "truncation_strategy": "longest_first",
951
+ "unk_token": "[UNK]"
952
+ }