Hugging Face's logo

CALDISS-AAU
/
da-reported-speech-e5

Text Classification
setfit
Safetensors
sentence-transformers
Danish
Few-Shot
Transformers
Text-classification
generated_from_setfit_traine
Computational_humanities
SSH
Social-work
Model card Files Community
SirMappel commited on
Commit
7be0c1e
·
verified ·
1 Parent(s): 86cc441

Upload 13 files

Browse files
Files changed (14) hide show
  1. .gitattributes +1 -0
  2. rep_speech_model/1_Pooling/config.json +10 -0
  3. rep_speech_model/README.md +754 -0
  4. rep_speech_model/config.json +28 -0
  5. rep_speech_model/config_sentence_transformers.json +10 -0
  6. rep_speech_model/config_setfit.json +7 -0
  7. rep_speech_model/model.safetensors +3 -0
  8. rep_speech_model/model_head.pkl +3 -0
  9. rep_speech_model/modules.json +20 -0
  10. rep_speech_model/sentence_bert_config.json +4 -0
  11. rep_speech_model/special_tokens_map.json +51 -0
  12. rep_speech_model/tokenizer.json +3 -0
  13. rep_speech_model/tokenizer_config.json +61 -0
  14. training-results.md +540 -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
+ rep_speech_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
rep_speech_model/1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 1024,
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
+ }
rep_speech_model/README.md ADDED
@@ -0,0 +1,754 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: intfloat/multilingual-e5-large
3
+ library_name: setfit
4
+ metrics:
5
+ - accuracy
6
+ - precision
7
+ - recall
8
+ - f1
9
+ pipeline_tag: text-classification
10
+ tags:
11
+ - setfit
12
+ - sentence-transformers
13
+ - text-classification
14
+ - generated_from_setfit_trainer
15
+ widget:
16
+ - text: 'men det kan så åbne nogle nye
17
+
18
+
19
+ '
20
+ - text: 'som jeg siger, der jo en grund til at jeg har fået et
21
+
22
+ handicapskilt og sådan'
23
+ - text: 'meget, ellers har jeg overholdt alt.
24
+
25
+
26
+ '
27
+ - text: 'sige det er 15 timer, du får betalte timer, jamen det er også en start,
28
+
29
+ '
30
+ - text: og jo det er nok rigtigt, det er sådan, jeg skal gøre det
31
+ inference: true
32
+ model-index:
33
+ - name: SetFit with intfloat/multilingual-e5-large
34
+ results:
35
+ - task:
36
+ type: text-classification
37
+ name: Text Classification
38
+ dataset:
39
+ name: Unknown
40
+ type: unknown
41
+ split: test
42
+ metrics:
43
+ - type: accuracy
44
+ value: 0.9724770642201835
45
+ name: Accuracy
46
+ - type: precision
47
+ value: 0.9557522123893806
48
+ name: Precision
49
+ - type: recall
50
+ value: 0.9908256880733946
51
+ name: Recall
52
+ - type: f1
53
+ value: 0.972972972972973
54
+ name: F1
55
+ ---
56
+
57
+ # SetFit with intfloat/multilingual-e5-large
58
+
59
+ This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [intfloat/multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.
60
+
61
+ The model has been trained using an efficient few-shot learning technique that involves:
62
+
63
+ 1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
64
+ 2. Training a classification head with features from the fine-tuned Sentence Transformer.
65
+
66
+ ## Model Details
67
+
68
+ ### Model Description
69
+ - **Model Type:** SetFit
70
+ - **Sentence Transformer body:** [intfloat/multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large)
71
+ - **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
72
+ - **Maximum Sequence Length:** 512 tokens
73
+ - **Number of Classes:** 2 classes
74
+ <!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
75
+ <!-- - **Language:** Unknown -->
76
+ <!-- - **License:** Unknown -->
77
+
78
+ ### Model Sources
79
+
80
+ - **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
81
+ - **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
82
+ - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
83
+
84
+ ### Model Labels
85
+ | Label | Examples |
86
+ |:--------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
87
+ | reported speech | <ul><li>'der fortalte jeg dig alt det der om ret og pligt '</li><li>'Så havde vi de der snakke om, at du ligesom selv fik lov at styre dit\nNem-ID.'</li><li>'Amina sagde at min\ndumme mor havde ringet'</li></ul> |
88
+ | not reported speech | <ul><li>'sag. '</li><li>'du klage over ik Lykke?\n\n'</li><li>'S: nej. '</li></ul> |
89
+
90
+ ## Evaluation
91
+
92
+ ### Metrics
93
+ | Label | Accuracy | Precision | Recall | F1 |
94
+ |:--------|:---------|:----------|:-------|:-------|
95
+ | **all** | 0.9725 | 0.9558 | 0.9908 | 0.9730 |
96
+
97
+ ## Uses
98
+
99
+ ### Direct Use for Inference
100
+
101
+ First install the SetFit library:
102
+
103
+ ```bash
104
+ pip install setfit
105
+ ```
106
+
107
+ Then you can load this model and run inference.
108
+
109
+ ```python
110
+ from setfit import SetFitModel
111
+
112
+ # Download from the 🤗 Hub
113
+ model = SetFitModel.from_pretrained("setfit_model_id")
114
+ # Run inference
115
+ preds = model("men det kan så åbne nogle nye
116
+
117
+ ")
118
+ ```
119
+
120
+ <!--
121
+ ### Downstream Use
122
+
123
+ *List how someone could finetune this model on their own dataset.*
124
+ -->
125
+
126
+ <!--
127
+ ### Out-of-Scope Use
128
+
129
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
130
+ -->
131
+
132
+ <!--
133
+ ## Bias, Risks and Limitations
134
+
135
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
136
+ -->
137
+
138
+ <!--
139
+ ### Recommendations
140
+
141
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
142
+ -->
143
+
144
+ ## Training Details
145
+
146
+ ### Training Set Metrics
147
+ | Training set | Min | Median | Max |
148
+ |:-------------|:----|:--------|:----|
149
+ | Word count | 1 | 19.1755 | 196 |
150
+
151
+ | Label | Training Sample Count |
152
+ |:--------------------|:----------------------|
153
+ | not reported speech | 265 |
154
+ | reported speech | 265 |
155
+
156
+ ### Training Hyperparameters
157
+ - batch_size: (32, 32)
158
+ - num_epochs: (6, 6)
159
+ - max_steps: -1
160
+ - sampling_strategy: oversampling
161
+ - body_learning_rate: (1.0770502781075495e-06, 1.0770502781075495e-06)
162
+ - head_learning_rate: 0.01
163
+ - loss: CosineSimilarityLoss
164
+ - distance_metric: cosine_distance
165
+ - margin: 0.25
166
+ - end_to_end: False
167
+ - use_amp: False
168
+ - warmup_proportion: 0.1
169
+ - seed: 42
170
+ - eval_max_steps: -1
171
+ - load_best_model_at_end: True
172
+
173
+ ### Training Results
174
+ | Epoch | Step | Training Loss | Validation Loss |
175
+ |:-------:|:---------:|:-------------:|:---------------:|
176
+ | 0.0002 | 1 | 0.3495 | - |
177
+ | 0.0113 | 50 | 0.3524 | - |
178
+ | 0.0227 | 100 | 0.3496 | - |
179
+ | 0.0340 | 150 | 0.3464 | - |
180
+ | 0.0454 | 200 | 0.3419 | - |
181
+ | 0.0567 | 250 | 0.328 | - |
182
+ | 0.0681 | 300 | 0.3166 | - |
183
+ | 0.0794 | 350 | 0.3012 | - |
184
+ | 0.0908 | 400 | 0.277 | - |
185
+ | 0.1021 | 450 | 0.259 | - |
186
+ | 0.1135 | 500 | 0.2568 | - |
187
+ | 0.1248 | 550 | 0.2483 | - |
188
+ | 0.1362 | 600 | 0.2457 | - |
189
+ | 0.1475 | 650 | 0.2263 | - |
190
+ | 0.1589 | 700 | 0.2361 | - |
191
+ | 0.1702 | 750 | 0.2108 | - |
192
+ | 0.1816 | 800 | 0.2025 | - |
193
+ | 0.1929 | 850 | 0.1881 | - |
194
+ | 0.2043 | 900 | 0.1559 | - |
195
+ | 0.2156 | 950 | 0.1055 | - |
196
+ | 0.2270 | 1000 | 0.0693 | - |
197
+ | 0.2383 | 1050 | 0.0332 | - |
198
+ | 0.2497 | 1100 | 0.0287 | - |
199
+ | 0.2610 | 1150 | 0.0185 | - |
200
+ | 0.2724 | 1200 | 0.0421 | - |
201
+ | 0.2837 | 1250 | 0.0087 | - |
202
+ | 0.2951 | 1300 | 0.0233 | - |
203
+ | 0.3064 | 1350 | 0.0083 | - |
204
+ | 0.3177 | 1400 | 0.0043 | - |
205
+ | 0.3291 | 1450 | 0.0037 | - |
206
+ | 0.3404 | 1500 | 0.0033 | - |
207
+ | 0.3518 | 1550 | 0.0019 | - |
208
+ | 0.3631 | 1600 | 0.0016 | - |
209
+ | 0.3745 | 1650 | 0.0012 | - |
210
+ | 0.3858 | 1700 | 0.002 | - |
211
+ | 0.3972 | 1750 | 0.0014 | - |
212
+ | 0.4085 | 1800 | 0.0012 | - |
213
+ | 0.4199 | 1850 | 0.001 | - |
214
+ | 0.4312 | 1900 | 0.001 | - |
215
+ | 0.4426 | 1950 | 0.0037 | - |
216
+ | 0.4539 | 2000 | 0.0006 | - |
217
+ | 0.4653 | 2050 | 0.0009 | - |
218
+ | 0.4766 | 2100 | 0.001 | - |
219
+ | 0.4880 | 2150 | 0.0006 | - |
220
+ | 0.4993 | 2200 | 0.0007 | - |
221
+ | 0.5107 | 2250 | 0.0005 | - |
222
+ | 0.5220 | 2300 | 0.001 | - |
223
+ | 0.5334 | 2350 | 0.0006 | - |
224
+ | 0.5447 | 2400 | 0.0004 | - |
225
+ | 0.5561 | 2450 | 0.0003 | - |
226
+ | 0.5674 | 2500 | 0.0004 | - |
227
+ | 0.5788 | 2550 | 0.0005 | - |
228
+ | 0.5901 | 2600 | 0.0003 | - |
229
+ | 0.6015 | 2650 | 0.0003 | - |
230
+ | 0.6128 | 2700 | 0.0003 | - |
231
+ | 0.6241 | 2750 | 0.0003 | - |
232
+ | 0.6355 | 2800 | 0.0004 | - |
233
+ | 0.6468 | 2850 | 0.0003 | - |
234
+ | 0.6582 | 2900 | 0.0002 | - |
235
+ | 0.6695 | 2950 | 0.0003 | - |
236
+ | 0.6809 | 3000 | 0.0003 | - |
237
+ | 0.6922 | 3050 | 0.0003 | - |
238
+ | 0.7036 | 3100 | 0.0003 | - |
239
+ | 0.7149 | 3150 | 0.0002 | - |
240
+ | 0.7263 | 3200 | 0.0003 | - |
241
+ | 0.7376 | 3250 | 0.0001 | - |
242
+ | 0.7490 | 3300 | 0.0002 | - |
243
+ | 0.7603 | 3350 | 0.0002 | - |
244
+ | 0.7717 | 3400 | 0.0002 | - |
245
+ | 0.7830 | 3450 | 0.0002 | - |
246
+ | 0.7944 | 3500 | 0.0002 | - |
247
+ | 0.8057 | 3550 | 0.0002 | - |
248
+ | 0.8171 | 3600 | 0.0002 | - |
249
+ | 0.8284 | 3650 | 0.0002 | - |
250
+ | 0.8398 | 3700 | 0.0003 | - |
251
+ | 0.8511 | 3750 | 0.0002 | - |
252
+ | 0.8625 | 3800 | 0.0002 | - |
253
+ | 0.8738 | 3850 | 0.0002 | - |
254
+ | 0.8852 | 3900 | 0.0002 | - |
255
+ | 0.8965 | 3950 | 0.0002 | - |
256
+ | 0.9079 | 4000 | 0.0001 | - |
257
+ | 0.9192 | 4050 | 0.0002 | - |
258
+ | 0.9305 | 4100 | 0.0002 | - |
259
+ | 0.9419 | 4150 | 0.0001 | - |
260
+ | 0.9532 | 4200 | 0.0001 | - |
261
+ | 0.9646 | 4250 | 0.0001 | - |
262
+ | 0.9759 | 4300 | 0.0001 | - |
263
+ | 0.9873 | 4350 | 0.0002 | - |
264
+ | 0.9986 | 4400 | 0.0002 | - |
265
+ | 1.0 | 4406 | - | 0.0601 |
266
+ | 1.0100 | 4450 | 0.0001 | - |
267
+ | 1.0213 | 4500 | 0.0001 | - |
268
+ | 1.0327 | 4550 | 0.0001 | - |
269
+ | 1.0440 | 4600 | 0.0001 | - |
270
+ | 1.0554 | 4650 | 0.0001 | - |
271
+ | 1.0667 | 4700 | 0.0001 | - |
272
+ | 1.0781 | 4750 | 0.0001 | - |
273
+ | 1.0894 | 4800 | 0.0001 | - |
274
+ | 1.1008 | 4850 | 0.0001 | - |
275
+ | 1.1121 | 4900 | 0.0001 | - |
276
+ | 1.1235 | 4950 | 0.0001 | - |
277
+ | 1.1348 | 5000 | 0.0001 | - |
278
+ | 1.1462 | 5050 | 0.0002 | - |
279
+ | 1.1575 | 5100 | 0.0001 | - |
280
+ | 1.1689 | 5150 | 0.0001 | - |
281
+ | 1.1802 | 5200 | 0.0001 | - |
282
+ | 1.1916 | 5250 | 0.0001 | - |
283
+ | 1.2029 | 5300 | 0.0001 | - |
284
+ | 1.2143 | 5350 | 0.0001 | - |
285
+ | 1.2256 | 5400 | 0.0001 | - |
286
+ | 1.2369 | 5450 | 0.0001 | - |
287
+ | 1.2483 | 5500 | 0.0001 | - |
288
+ | 1.2596 | 5550 | 0.0001 | - |
289
+ | 1.2710 | 5600 | 0.0001 | - |
290
+ | 1.2823 | 5650 | 0.0001 | - |
291
+ | 1.2937 | 5700 | 0.0001 | - |
292
+ | 1.3050 | 5750 | 0.0001 | - |
293
+ | 1.3164 | 5800 | 0.0001 | - |
294
+ | 1.3277 | 5850 | 0.0001 | - |
295
+ | 1.3391 | 5900 | 0.0001 | - |
296
+ | 1.3504 | 5950 | 0.0001 | - |
297
+ | 1.3618 | 6000 | 0.0001 | - |
298
+ | 1.3731 | 6050 | 0.0001 | - |
299
+ | 1.3845 | 6100 | 0.0001 | - |
300
+ | 1.3958 | 6150 | 0.0001 | - |
301
+ | 1.4072 | 6200 | 0.0001 | - |
302
+ | 1.4185 | 6250 | 0.0001 | - |
303
+ | 1.4299 | 6300 | 0.0001 | - |
304
+ | 1.4412 | 6350 | 0.0001 | - |
305
+ | 1.4526 | 6400 | 0.0001 | - |
306
+ | 1.4639 | 6450 | 0.0 | - |
307
+ | 1.4753 | 6500 | 0.0001 | - |
308
+ | 1.4866 | 6550 | 0.0011 | - |
309
+ | 1.4980 | 6600 | 0.0001 | - |
310
+ | 1.5093 | 6650 | 0.0001 | - |
311
+ | 1.5207 | 6700 | 0.0 | - |
312
+ | 1.5320 | 6750 | 0.0 | - |
313
+ | 1.5433 | 6800 | 0.0001 | - |
314
+ | 1.5547 | 6850 | 0.0001 | - |
315
+ | 1.5660 | 6900 | 0.0001 | - |
316
+ | 1.5774 | 6950 | 0.0001 | - |
317
+ | 1.5887 | 7000 | 0.0001 | - |
318
+ | 1.6001 | 7050 | 0.0001 | - |
319
+ | 1.6114 | 7100 | 0.0001 | - |
320
+ | 1.6228 | 7150 | 0.0 | - |
321
+ | 1.6341 | 7200 | 0.0 | - |
322
+ | 1.6455 | 7250 | 0.0001 | - |
323
+ | 1.6568 | 7300 | 0.0001 | - |
324
+ | 1.6682 | 7350 | 0.0001 | - |
325
+ | 1.6795 | 7400 | 0.0001 | - |
326
+ | 1.6909 | 7450 | 0.0 | - |
327
+ | 1.7022 | 7500 | 0.0001 | - |
328
+ | 1.7136 | 7550 | 0.0001 | - |
329
+ | 1.7249 | 7600 | 0.0001 | - |
330
+ | 1.7363 | 7650 | 0.0 | - |
331
+ | 1.7476 | 7700 | 0.0 | - |
332
+ | 1.7590 | 7750 | 0.0 | - |
333
+ | 1.7703 | 7800 | 0.0001 | - |
334
+ | 1.7817 | 7850 | 0.0 | - |
335
+ | 1.7930 | 7900 | 0.0 | - |
336
+ | 1.8044 | 7950 | 0.0 | - |
337
+ | 1.8157 | 8000 | 0.0001 | - |
338
+ | 1.8271 | 8050 | 0.0 | - |
339
+ | 1.8384 | 8100 | 0.0 | - |
340
+ | 1.8498 | 8150 | 0.0001 | - |
341
+ | 1.8611 | 8200 | 0.0 | - |
342
+ | 1.8724 | 8250 | 0.0001 | - |
343
+ | 1.8838 | 8300 | 0.0 | - |
344
+ | 1.8951 | 8350 | 0.0001 | - |
345
+ | 1.9065 | 8400 | 0.0001 | - |
346
+ | 1.9178 | 8450 | 0.0001 | - |
347
+ | 1.9292 | 8500 | 0.0 | - |
348
+ | 1.9405 | 8550 | 0.0 | - |
349
+ | 1.9519 | 8600 | 0.0 | - |
350
+ | 1.9632 | 8650 | 0.0 | - |
351
+ | 1.9746 | 8700 | 0.0 | - |
352
+ | 1.9859 | 8750 | 0.0 | - |
353
+ | 1.9973 | 8800 | 0.0 | - |
354
+ | 2.0 | 8812 | - | 0.0549 |
355
+ | 2.0086 | 8850 | 0.0 | - |
356
+ | 2.0200 | 8900 | 0.0 | - |
357
+ | 2.0313 | 8950 | 0.0 | - |
358
+ | 2.0427 | 9000 | 0.0 | - |
359
+ | 2.0540 | 9050 | 0.0 | - |
360
+ | 2.0654 | 9100 | 0.0 | - |
361
+ | 2.0767 | 9150 | 0.0 | - |
362
+ | 2.0881 | 9200 | 0.0 | - |
363
+ | 2.0994 | 9250 | 0.0 | - |
364
+ | 2.1108 | 9300 | 0.0 | - |
365
+ | 2.1221 | 9350 | 0.0 | - |
366
+ | 2.1335 | 9400 | 0.0001 | - |
367
+ | 2.1448 | 9450 | 0.0 | - |
368
+ | 2.1562 | 9500 | 0.0 | - |
369
+ | 2.1675 | 9550 | 0.0 | - |
370
+ | 2.1788 | 9600 | 0.0 | - |
371
+ | 2.1902 | 9650 | 0.0 | - |
372
+ | 2.2015 | 9700 | 0.0 | - |
373
+ | 2.2129 | 9750 | 0.0 | - |
374
+ | 2.2242 | 9800 | 0.0 | - |
375
+ | 2.2356 | 9850 | 0.0 | - |
376
+ | 2.2469 | 9900 | 0.0 | - |
377
+ | 2.2583 | 9950 | 0.0 | - |
378
+ | 2.2696 | 10000 | 0.0 | - |
379
+ | 2.2810 | 10050 | 0.0 | - |
380
+ | 2.2923 | 10100 | 0.0 | - |
381
+ | 2.3037 | 10150 | 0.0 | - |
382
+ | 2.3150 | 10200 | 0.0 | - |
383
+ | 2.3264 | 10250 | 0.0 | - |
384
+ | 2.3377 | 10300 | 0.0 | - |
385
+ | 2.3491 | 10350 | 0.0 | - |
386
+ | 2.3604 | 10400 | 0.0 | - |
387
+ | 2.3718 | 10450 | 0.0001 | - |
388
+ | 2.3831 | 10500 | 0.0 | - |
389
+ | 2.3945 | 10550 | 0.0 | - |
390
+ | 2.4058 | 10600 | 0.0 | - |
391
+ | 2.4172 | 10650 | 0.0 | - |
392
+ | 2.4285 | 10700 | 0.0 | - |
393
+ | 2.4399 | 10750 | 0.0 | - |
394
+ | 2.4512 | 10800 | 0.0 | - |
395
+ | 2.4626 | 10850 | 0.0 | - |
396
+ | 2.4739 | 10900 | 0.0 | - |
397
+ | 2.4852 | 10950 | 0.0 | - |
398
+ | 2.4966 | 11000 | 0.0 | - |
399
+ | 2.5079 | 11050 | 0.0 | - |
400
+ | 2.5193 | 11100 | 0.0 | - |
401
+ | 2.5306 | 11150 | 0.0 | - |
402
+ | 2.5420 | 11200 | 0.0 | - |
403
+ | 2.5533 | 11250 | 0.0 | - |
404
+ | 2.5647 | 11300 | 0.0 | - |
405
+ | 2.5760 | 11350 | 0.0 | - |
406
+ | 2.5874 | 11400 | 0.0 | - |
407
+ | 2.5987 | 11450 | 0.0 | - |
408
+ | 2.6101 | 11500 | 0.0 | - |
409
+ | 2.6214 | 11550 | 0.0 | - |
410
+ | 2.6328 | 11600 | 0.0 | - |
411
+ | 2.6441 | 11650 | 0.0 | - |
412
+ | 2.6555 | 11700 | 0.0 | - |
413
+ | 2.6668 | 11750 | 0.0 | - |
414
+ | 2.6782 | 11800 | 0.0 | - |
415
+ | 2.6895 | 11850 | 0.0 | - |
416
+ | 2.7009 | 11900 | 0.0 | - |
417
+ | 2.7122 | 11950 | 0.0 | - |
418
+ | 2.7236 | 12000 | 0.0 | - |
419
+ | 2.7349 | 12050 | 0.0 | - |
420
+ | 2.7463 | 12100 | 0.0 | - |
421
+ | 2.7576 | 12150 | 0.0 | - |
422
+ | 2.7690 | 12200 | 0.0 | - |
423
+ | 2.7803 | 12250 | 0.0 | - |
424
+ | 2.7916 | 12300 | 0.0 | - |
425
+ | 2.8030 | 12350 | 0.0 | - |
426
+ | 2.8143 | 12400 | 0.0 | - |
427
+ | 2.8257 | 12450 | 0.0 | - |
428
+ | 2.8370 | 12500 | 0.0 | - |
429
+ | 2.8484 | 12550 | 0.0 | - |
430
+ | 2.8597 | 12600 | 0.0 | - |
431
+ | 2.8711 | 12650 | 0.0 | - |
432
+ | 2.8824 | 12700 | 0.0 | - |
433
+ | 2.8938 | 12750 | 0.0 | - |
434
+ | 2.9051 | 12800 | 0.0 | - |
435
+ | 2.9165 | 12850 | 0.0 | - |
436
+ | 2.9278 | 12900 | 0.0 | - |
437
+ | 2.9392 | 12950 | 0.0 | - |
438
+ | 2.9505 | 13000 | 0.0 | - |
439
+ | 2.9619 | 13050 | 0.0 | - |
440
+ | 2.9732 | 13100 | 0.0 | - |
441
+ | 2.9846 | 13150 | 0.0 | - |
442
+ | 2.9959 | 13200 | 0.0 | - |
443
+ | 3.0 | 13218 | - | 0.0469 |
444
+ | 3.0073 | 13250 | 0.0 | - |
445
+ | 3.0186 | 13300 | 0.0 | - |
446
+ | 3.0300 | 13350 | 0.0 | - |
447
+ | 3.0413 | 13400 | 0.0 | - |
448
+ | 3.0527 | 13450 | 0.0 | - |
449
+ | 3.0640 | 13500 | 0.0 | - |
450
+ | 3.0754 | 13550 | 0.0 | - |
451
+ | 3.0867 | 13600 | 0.0 | - |
452
+ | 3.0980 | 13650 | 0.0 | - |
453
+ | 3.1094 | 13700 | 0.0 | - |
454
+ | 3.1207 | 13750 | 0.0 | - |
455
+ | 3.1321 | 13800 | 0.0 | - |
456
+ | 3.1434 | 13850 | 0.0 | - |
457
+ | 3.1548 | 13900 | 0.0 | - |
458
+ | 3.1661 | 13950 | 0.0 | - |
459
+ | 3.1775 | 14000 | 0.0 | - |
460
+ | 3.1888 | 14050 | 0.0 | - |
461
+ | 3.2002 | 14100 | 0.0 | - |
462
+ | 3.2115 | 14150 | 0.0 | - |
463
+ | 3.2229 | 14200 | 0.0 | - |
464
+ | 3.2342 | 14250 | 0.0 | - |
465
+ | 3.2456 | 14300 | 0.0 | - |
466
+ | 3.2569 | 14350 | 0.0 | - |
467
+ | 3.2683 | 14400 | 0.0 | - |
468
+ | 3.2796 | 14450 | 0.0 | - |
469
+ | 3.2910 | 14500 | 0.0 | - |
470
+ | 3.3023 | 14550 | 0.0 | - |
471
+ | 3.3137 | 14600 | 0.0 | - |
472
+ | 3.3250 | 14650 | 0.0 | - |
473
+ | 3.3364 | 14700 | 0.0 | - |
474
+ | 3.3477 | 14750 | 0.0 | - |
475
+ | 3.3591 | 14800 | 0.0 | - |
476
+ | 3.3704 | 14850 | 0.0 | - |
477
+ | 3.3818 | 14900 | 0.0 | - |
478
+ | 3.3931 | 14950 | 0.0 | - |
479
+ | 3.4044 | 15000 | 0.0 | - |
480
+ | 3.4158 | 15050 | 0.0 | - |
481
+ | 3.4271 | 15100 | 0.0 | - |
482
+ | 3.4385 | 15150 | 0.0 | - |
483
+ | 3.4498 | 15200 | 0.0 | - |
484
+ | 3.4612 | 15250 | 0.0 | - |
485
+ | 3.4725 | 15300 | 0.0 | - |
486
+ | 3.4839 | 15350 | 0.0 | - |
487
+ | 3.4952 | 15400 | 0.0 | - |
488
+ | 3.5066 | 15450 | 0.0 | - |
489
+ | 3.5179 | 15500 | 0.0 | - |
490
+ | 3.5293 | 15550 | 0.0 | - |
491
+ | 3.5406 | 15600 | 0.0 | - |
492
+ | 3.5520 | 15650 | 0.0 | - |
493
+ | 3.5633 | 15700 | 0.0 | - |
494
+ | 3.5747 | 15750 | 0.0 | - |
495
+ | 3.5860 | 15800 | 0.0 | - |
496
+ | 3.5974 | 15850 | 0.0 | - |
497
+ | 3.6087 | 15900 | 0.0 | - |
498
+ | 3.6201 | 15950 | 0.0 | - |
499
+ | 3.6314 | 16000 | 0.0 | - |
500
+ | 3.6428 | 16050 | 0.0 | - |
501
+ | 3.6541 | 16100 | 0.0 | - |
502
+ | 3.6655 | 16150 | 0.0 | - |
503
+ | 3.6768 | 16200 | 0.0 | - |
504
+ | 3.6882 | 16250 | 0.0 | - |
505
+ | 3.6995 | 16300 | 0.0 | - |
506
+ | 3.7108 | 16350 | 0.0 | - |
507
+ | 3.7222 | 16400 | 0.0 | - |
508
+ | 3.7335 | 16450 | 0.0 | - |
509
+ | 3.7449 | 16500 | 0.0 | - |
510
+ | 3.7562 | 16550 | 0.0 | - |
511
+ | 3.7676 | 16600 | 0.0 | - |
512
+ | 3.7789 | 16650 | 0.0 | - |
513
+ | 3.7903 | 16700 | 0.0 | - |
514
+ | 3.8016 | 16750 | 0.0 | - |
515
+ | 3.8130 | 16800 | 0.0 | - |
516
+ | 3.8243 | 16850 | 0.0 | - |
517
+ | 3.8357 | 16900 | 0.0 | - |
518
+ | 3.8470 | 16950 | 0.0 | - |
519
+ | 3.8584 | 17000 | 0.0 | - |
520
+ | 3.8697 | 17050 | 0.0 | - |
521
+ | 3.8811 | 17100 | 0.0 | - |
522
+ | 3.8924 | 17150 | 0.0 | - |
523
+ | 3.9038 | 17200 | 0.0 | - |
524
+ | 3.9151 | 17250 | 0.0 | - |
525
+ | 3.9265 | 17300 | 0.0 | - |
526
+ | 3.9378 | 17350 | 0.0 | - |
527
+ | 3.9492 | 17400 | 0.0 | - |
528
+ | 3.9605 | 17450 | 0.0 | - |
529
+ | 3.9719 | 17500 | 0.0 | - |
530
+ | 3.9832 | 17550 | 0.0 | - |
531
+ | 3.9946 | 17600 | 0.0 | - |
532
+ | 4.0 | 17624 | - | 0.0404 |
533
+ | 4.0059 | 17650 | 0.0 | - |
534
+ | 4.0172 | 17700 | 0.0 | - |
535
+ | 4.0286 | 17750 | 0.0 | - |
536
+ | 4.0399 | 17800 | 0.0 | - |
537
+ | 4.0513 | 17850 | 0.0 | - |
538
+ | 4.0626 | 17900 | 0.0 | - |
539
+ | 4.0740 | 17950 | 0.0 | - |
540
+ | 4.0853 | 18000 | 0.0 | - |
541
+ | 4.0967 | 18050 | 0.0 | - |
542
+ | 4.1080 | 18100 | 0.0 | - |
543
+ | 4.1194 | 18150 | 0.0 | - |
544
+ | 4.1307 | 18200 | 0.0 | - |
545
+ | 4.1421 | 18250 | 0.0 | - |
546
+ | 4.1534 | 18300 | 0.0 | - |
547
+ | 4.1648 | 18350 | 0.0 | - |
548
+ | 4.1761 | 18400 | 0.0 | - |
549
+ | 4.1875 | 18450 | 0.0 | - |
550
+ | 4.1988 | 18500 | 0.0 | - |
551
+ | 4.2102 | 18550 | 0.0 | - |
552
+ | 4.2215 | 18600 | 0.0 | - |
553
+ | 4.2329 | 18650 | 0.0 | - |
554
+ | 4.2442 | 18700 | 0.0 | - |
555
+ | 4.2556 | 18750 | 0.0 | - |
556
+ | 4.2669 | 18800 | 0.0 | - |
557
+ | 4.2783 | 18850 | 0.0 | - |
558
+ | 4.2896 | 18900 | 0.0 | - |
559
+ | 4.3010 | 18950 | 0.0 | - |
560
+ | 4.3123 | 19000 | 0.0 | - |
561
+ | 4.3236 | 19050 | 0.0 | - |
562
+ | 4.3350 | 19100 | 0.0 | - |
563
+ | 4.3463 | 19150 | 0.0 | - |
564
+ | 4.3577 | 19200 | 0.0 | - |
565
+ | 4.3690 | 19250 | 0.0 | - |
566
+ | 4.3804 | 19300 | 0.0 | - |
567
+ | 4.3917 | 19350 | 0.0 | - |
568
+ | 4.4031 | 19400 | 0.0 | - |
569
+ | 4.4144 | 19450 | 0.0 | - |
570
+ | 4.4258 | 19500 | 0.0 | - |
571
+ | 4.4371 | 19550 | 0.0 | - |
572
+ | 4.4485 | 19600 | 0.0 | - |
573
+ | 4.4598 | 19650 | 0.0 | - |
574
+ | 4.4712 | 19700 | 0.0 | - |
575
+ | 4.4825 | 19750 | 0.0 | - |
576
+ | 4.4939 | 19800 | 0.0 | - |
577
+ | 4.5052 | 19850 | 0.0 | - |
578
+ | 4.5166 | 19900 | 0.0 | - |
579
+ | 4.5279 | 19950 | 0.0 | - |
580
+ | 4.5393 | 20000 | 0.0 | - |
581
+ | 4.5506 | 20050 | 0.0 | - |
582
+ | 4.5620 | 20100 | 0.0 | - |
583
+ | 4.5733 | 20150 | 0.0 | - |
584
+ | 4.5847 | 20200 | 0.0 | - |
585
+ | 4.5960 | 20250 | 0.0 | - |
586
+ | 4.6074 | 20300 | 0.0 | - |
587
+ | 4.6187 | 20350 | 0.0 | - |
588
+ | 4.6300 | 20400 | 0.0 | - |
589
+ | 4.6414 | 20450 | 0.0 | - |
590
+ | 4.6527 | 20500 | 0.0 | - |
591
+ | 4.6641 | 20550 | 0.0 | - |
592
+ | 4.6754 | 20600 | 0.0 | - |
593
+ | 4.6868 | 20650 | 0.0 | - |
594
+ | 4.6981 | 20700 | 0.0 | - |
595
+ | 4.7095 | 20750 | 0.0 | - |
596
+ | 4.7208 | 20800 | 0.0 | - |
597
+ | 4.7322 | 20850 | 0.0 | - |
598
+ | 4.7435 | 20900 | 0.0 | - |
599
+ | 4.7549 | 20950 | 0.0 | - |
600
+ | 4.7662 | 21000 | 0.0 | - |
601
+ | 4.7776 | 21050 | 0.0 | - |
602
+ | 4.7889 | 21100 | 0.0 | - |
603
+ | 4.8003 | 21150 | 0.0 | - |
604
+ | 4.8116 | 21200 | 0.0 | - |
605
+ | 4.8230 | 21250 | 0.0 | - |
606
+ | 4.8343 | 21300 | 0.0 | - |
607
+ | 4.8457 | 21350 | 0.0 | - |
608
+ | 4.8570 | 21400 | 0.0 | - |
609
+ | 4.8684 | 21450 | 0.0 | - |
610
+ | 4.8797 | 21500 | 0.0 | - |
611
+ | 4.8911 | 21550 | 0.0 | - |
612
+ | 4.9024 | 21600 | 0.0 | - |
613
+ | 4.9138 | 21650 | 0.0 | - |
614
+ | 4.9251 | 21700 | 0.0 | - |
615
+ | 4.9365 | 21750 | 0.0 | - |
616
+ | 4.9478 | 21800 | 0.0 | - |
617
+ | 4.9591 | 21850 | 0.0 | - |
618
+ | 4.9705 | 21900 | 0.0 | - |
619
+ | 4.9818 | 21950 | 0.0 | - |
620
+ | 4.9932 | 22000 | 0.0 | - |
621
+ | **5.0** | **22030** | **-** | **0.038** |
622
+ | 5.0045 | 22050 | 0.0 | - |
623
+ | 5.0159 | 22100 | 0.0 | - |
624
+ | 5.0272 | 22150 | 0.0 | - |
625
+ | 5.0386 | 22200 | 0.0 | - |
626
+ | 5.0499 | 22250 | 0.0 | - |
627
+ | 5.0613 | 22300 | 0.0 | - |
628
+ | 5.0726 | 22350 | 0.0 | - |
629
+ | 5.0840 | 22400 | 0.0 | - |
630
+ | 5.0953 | 22450 | 0.0 | - |
631
+ | 5.1067 | 22500 | 0.0 | - |
632
+ | 5.1180 | 22550 | 0.0 | - |
633
+ | 5.1294 | 22600 | 0.0 | - |
634
+ | 5.1407 | 22650 | 0.0 | - |
635
+ | 5.1521 | 22700 | 0.0 | - |
636
+ | 5.1634 | 22750 | 0.0 | - |
637
+ | 5.1748 | 22800 | 0.0 | - |
638
+ | 5.1861 | 22850 | 0.0 | - |
639
+ | 5.1975 | 22900 | 0.0 | - |
640
+ | 5.2088 | 22950 | 0.0 | - |
641
+ | 5.2202 | 23000 | 0.0 | - |
642
+ | 5.2315 | 23050 | 0.0 | - |
643
+ | 5.2429 | 23100 | 0.0 | - |
644
+ | 5.2542 | 23150 | 0.0 | - |
645
+ | 5.2655 | 23200 | 0.0 | - |
646
+ | 5.2769 | 23250 | 0.0 | - |
647
+ | 5.2882 | 23300 | 0.0 | - |
648
+ | 5.2996 | 23350 | 0.0 | - |
649
+ | 5.3109 | 23400 | 0.0 | - |
650
+ | 5.3223 | 23450 | 0.0 | - |
651
+ | 5.3336 | 23500 | 0.0 | - |
652
+ | 5.3450 | 23550 | 0.0 | - |
653
+ | 5.3563 | 23600 | 0.0 | - |
654
+ | 5.3677 | 23650 | 0.0 | - |
655
+ | 5.3790 | 23700 | 0.0 | - |
656
+ | 5.3904 | 23750 | 0.0 | - |
657
+ | 5.4017 | 23800 | 0.0 | - |
658
+ | 5.4131 | 23850 | 0.0 | - |
659
+ | 5.4244 | 23900 | 0.0 | - |
660
+ | 5.4358 | 23950 | 0.0 | - |
661
+ | 5.4471 | 24000 | 0.0 | - |
662
+ | 5.4585 | 24050 | 0.0 | - |
663
+ | 5.4698 | 24100 | 0.0 | - |
664
+ | 5.4812 | 24150 | 0.0 | - |
665
+ | 5.4925 | 24200 | 0.0 | - |
666
+ | 5.5039 | 24250 | 0.0 | - |
667
+ | 5.5152 | 24300 | 0.0 | - |
668
+ | 5.5266 | 24350 | 0.0 | - |
669
+ | 5.5379 | 24400 | 0.0 | - |
670
+ | 5.5493 | 24450 | 0.0 | - |
671
+ | 5.5606 | 24500 | 0.0 | - |
672
+ | 5.5719 | 24550 | 0.0 | - |
673
+ | 5.5833 | 24600 | 0.0 | - |
674
+ | 5.5946 | 24650 | 0.0 | - |
675
+ | 5.6060 | 24700 | 0.0 | - |
676
+ | 5.6173 | 24750 | 0.0 | - |
677
+ | 5.6287 | 24800 | 0.0 | - |
678
+ | 5.6400 | 24850 | 0.0 | - |
679
+ | 5.6514 | 24900 | 0.0 | - |
680
+ | 5.6627 | 24950 | 0.0 | - |
681
+ | 5.6741 | 25000 | 0.0 | - |
682
+ | 5.6854 | 25050 | 0.0 | - |
683
+ | 5.6968 | 25100 | 0.0 | - |
684
+ | 5.7081 | 25150 | 0.0 | - |
685
+ | 5.7195 | 25200 | 0.0 | - |
686
+ | 5.7308 | 25250 | 0.0 | - |
687
+ | 5.7422 | 25300 | 0.0 | - |
688
+ | 5.7535 | 25350 | 0.0 | - |
689
+ | 5.7649 | 25400 | 0.0 | - |
690
+ | 5.7762 | 25450 | 0.0 | - |
691
+ | 5.7876 | 25500 | 0.0 | - |
692
+ | 5.7989 | 25550 | 0.0 | - |
693
+ | 5.8103 | 25600 | 0.0 | - |
694
+ | 5.8216 | 25650 | 0.0 | - |
695
+ | 5.8330 | 25700 | 0.0 | - |
696
+ | 5.8443 | 25750 | 0.0 | - |
697
+ | 5.8557 | 25800 | 0.0 | - |
698
+ | 5.8670 | 25850 | 0.0 | - |
699
+ | 5.8783 | 25900 | 0.0 | - |
700
+ | 5.8897 | 25950 | 0.0 | - |
701
+ | 5.9010 | 26000 | 0.0 | - |
702
+ | 5.9124 | 26050 | 0.0 | - |
703
+ | 5.9237 | 26100 | 0.0 | - |
704
+ | 5.9351 | 26150 | 0.0 | - |
705
+ | 5.9464 | 26200 | 0.0 | - |
706
+ | 5.9578 | 26250 | 0.0 | - |
707
+ | 5.9691 | 26300 | 0.0 | - |
708
+ | 5.9805 | 26350 | 0.0 | - |
709
+ | 5.9918 | 26400 | 0.0 | - |
710
+ | 6.0 | 26436 | - | 0.0382 |
711
+
712
+ * The bold row denotes the saved checkpoint.
713
+ ### Framework Versions
714
+ - Python: 3.12.3
715
+ - SetFit: 1.0.3
716
+ - Sentence Transformers: 3.0.1
717
+ - Transformers: 4.39.0
718
+ - PyTorch: 2.4.1+cu121
719
+ - Datasets: 2.21.0
720
+ - Tokenizers: 0.15.2
721
+
722
+ ## Citation
723
+
724
+ ### BibTeX
725
+ ```bibtex
726
+ @article{https://doi.org/10.48550/arxiv.2209.11055,
727
+ doi = {10.48550/ARXIV.2209.11055},
728
+ url = {https://arxiv.org/abs/2209.11055},
729
+ author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
730
+ keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
731
+ title = {Efficient Few-Shot Learning Without Prompts},
732
+ publisher = {arXiv},
733
+ year = {2022},
734
+ copyright = {Creative Commons Attribution 4.0 International}
735
+ }
736
+ ```
737
+
738
+ <!--
739
+ ## Glossary
740
+
741
+ *Clearly define terms in order to be accessible across audiences.*
742
+ -->
743
+
744
+ <!--
745
+ ## Model Card Authors
746
+
747
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
748
+ -->
749
+
750
+ <!--
751
+ ## Model Card Contact
752
+
753
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
754
+ -->
rep_speech_model/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "checkpoints/step_22030",
3
+ "architectures": [
4
+ "XLMRobertaModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 4096,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "xlm-roberta",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 24,
20
+ "output_past": true,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.39.0",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 250002
28
+ }
rep_speech_model/config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.0.1",
4
+ "transformers": "4.39.0",
5
+ "pytorch": "2.4.1+cu121"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null,
9
+ "similarity_fn_name": null
10
+ }
rep_speech_model/config_setfit.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "normalize_embeddings": false,
3
+ "labels": [
4
+ "not reported speech",
5
+ "reported speech"
6
+ ]
7
+ }
rep_speech_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0868c324e4d4e293fb536bce44b9dd512b832d348c8f05c3d1a1133ccac34f5
3
+ size 2239607176
rep_speech_model/model_head.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a41b2e0d6572265716d1fb8346393cd1058b16f8c792792922e8faa213b00f02
3
+ size 9199
rep_speech_model/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
+ ]
rep_speech_model/sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 512,
3
+ "do_lower_case": false
4
+ }
rep_speech_model/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": true,
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
+ }
rep_speech_model/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1cc44ad7faaeec47241864835473fd5403f2da94673f3f764a77ebcb0a803ec
3
+ size 17083009
rep_speech_model/tokenizer_config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "max_length": 512,
50
+ "model_max_length": 512,
51
+ "pad_to_multiple_of": null,
52
+ "pad_token": "<pad>",
53
+ "pad_token_type_id": 0,
54
+ "padding_side": "right",
55
+ "sep_token": "</s>",
56
+ "stride": 0,
57
+ "tokenizer_class": "XLMRobertaTokenizer",
58
+ "truncation_side": "right",
59
+ "truncation_strategy": "longest_first",
60
+ "unk_token": "<unk>"
61
+ }
training-results.md ADDED
@@ -0,0 +1,540 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ### Training Results
2
+ | Epoch | Step | Training Loss | Validation Loss |
3
+ |:-------:|:---------:|:-------------:|:---------------:|
4
+ | 0.0002 | 1 | 0.3495 | - |
5
+ | 0.0113 | 50 | 0.3524 | - |
6
+ | 0.0227 | 100 | 0.3496 | - |
7
+ | 0.0340 | 150 | 0.3464 | - |
8
+ | 0.0454 | 200 | 0.3419 | - |
9
+ | 0.0567 | 250 | 0.328 | - |
10
+ | 0.0681 | 300 | 0.3166 | - |
11
+ | 0.0794 | 350 | 0.3012 | - |
12
+ | 0.0908 | 400 | 0.277 | - |
13
+ | 0.1021 | 450 | 0.259 | - |
14
+ | 0.1135 | 500 | 0.2568 | - |
15
+ | 0.1248 | 550 | 0.2483 | - |
16
+ | 0.1362 | 600 | 0.2457 | - |
17
+ | 0.1475 | 650 | 0.2263 | - |
18
+ | 0.1589 | 700 | 0.2361 | - |
19
+ | 0.1702 | 750 | 0.2108 | - |
20
+ | 0.1816 | 800 | 0.2025 | - |
21
+ | 0.1929 | 850 | 0.1881 | - |
22
+ | 0.2043 | 900 | 0.1559 | - |
23
+ | 0.2156 | 950 | 0.1055 | - |
24
+ | 0.2270 | 1000 | 0.0693 | - |
25
+ | 0.2383 | 1050 | 0.0332 | - |
26
+ | 0.2497 | 1100 | 0.0287 | - |
27
+ | 0.2610 | 1150 | 0.0185 | - |
28
+ | 0.2724 | 1200 | 0.0421 | - |
29
+ | 0.2837 | 1250 | 0.0087 | - |
30
+ | 0.2951 | 1300 | 0.0233 | - |
31
+ | 0.3064 | 1350 | 0.0083 | - |
32
+ | 0.3177 | 1400 | 0.0043 | - |
33
+ | 0.3291 | 1450 | 0.0037 | - |
34
+ | 0.3404 | 1500 | 0.0033 | - |
35
+ | 0.3518 | 1550 | 0.0019 | - |
36
+ | 0.3631 | 1600 | 0.0016 | - |
37
+ | 0.3745 | 1650 | 0.0012 | - |
38
+ | 0.3858 | 1700 | 0.002 | - |
39
+ | 0.3972 | 1750 | 0.0014 | - |
40
+ | 0.4085 | 1800 | 0.0012 | - |
41
+ | 0.4199 | 1850 | 0.001 | - |
42
+ | 0.4312 | 1900 | 0.001 | - |
43
+ | 0.4426 | 1950 | 0.0037 | - |
44
+ | 0.4539 | 2000 | 0.0006 | - |
45
+ | 0.4653 | 2050 | 0.0009 | - |
46
+ | 0.4766 | 2100 | 0.001 | - |
47
+ | 0.4880 | 2150 | 0.0006 | - |
48
+ | 0.4993 | 2200 | 0.0007 | - |
49
+ | 0.5107 | 2250 | 0.0005 | - |
50
+ | 0.5220 | 2300 | 0.001 | - |
51
+ | 0.5334 | 2350 | 0.0006 | - |
52
+ | 0.5447 | 2400 | 0.0004 | - |
53
+ | 0.5561 | 2450 | 0.0003 | - |
54
+ | 0.5674 | 2500 | 0.0004 | - |
55
+ | 0.5788 | 2550 | 0.0005 | - |
56
+ | 0.5901 | 2600 | 0.0003 | - |
57
+ | 0.6015 | 2650 | 0.0003 | - |
58
+ | 0.6128 | 2700 | 0.0003 | - |
59
+ | 0.6241 | 2750 | 0.0003 | - |
60
+ | 0.6355 | 2800 | 0.0004 | - |
61
+ | 0.6468 | 2850 | 0.0003 | - |
62
+ | 0.6582 | 2900 | 0.0002 | - |
63
+ | 0.6695 | 2950 | 0.0003 | - |
64
+ | 0.6809 | 3000 | 0.0003 | - |
65
+ | 0.6922 | 3050 | 0.0003 | - |
66
+ | 0.7036 | 3100 | 0.0003 | - |
67
+ | 0.7149 | 3150 | 0.0002 | - |
68
+ | 0.7263 | 3200 | 0.0003 | - |
69
+ | 0.7376 | 3250 | 0.0001 | - |
70
+ | 0.7490 | 3300 | 0.0002 | - |
71
+ | 0.7603 | 3350 | 0.0002 | - |
72
+ | 0.7717 | 3400 | 0.0002 | - |
73
+ | 0.7830 | 3450 | 0.0002 | - |
74
+ | 0.7944 | 3500 | 0.0002 | - |
75
+ | 0.8057 | 3550 | 0.0002 | - |
76
+ | 0.8171 | 3600 | 0.0002 | - |
77
+ | 0.8284 | 3650 | 0.0002 | - |
78
+ | 0.8398 | 3700 | 0.0003 | - |
79
+ | 0.8511 | 3750 | 0.0002 | - |
80
+ | 0.8625 | 3800 | 0.0002 | - |
81
+ | 0.8738 | 3850 | 0.0002 | - |
82
+ | 0.8852 | 3900 | 0.0002 | - |
83
+ | 0.8965 | 3950 | 0.0002 | - |
84
+ | 0.9079 | 4000 | 0.0001 | - |
85
+ | 0.9192 | 4050 | 0.0002 | - |
86
+ | 0.9305 | 4100 | 0.0002 | - |
87
+ | 0.9419 | 4150 | 0.0001 | - |
88
+ | 0.9532 | 4200 | 0.0001 | - |
89
+ | 0.9646 | 4250 | 0.0001 | - |
90
+ | 0.9759 | 4300 | 0.0001 | - |
91
+ | 0.9873 | 4350 | 0.0002 | - |
92
+ | 0.9986 | 4400 | 0.0002 | - |
93
+ | 1.0 | 4406 | - | 0.0601 |
94
+ | 1.0100 | 4450 | 0.0001 | - |
95
+ | 1.0213 | 4500 | 0.0001 | - |
96
+ | 1.0327 | 4550 | 0.0001 | - |
97
+ | 1.0440 | 4600 | 0.0001 | - |
98
+ | 1.0554 | 4650 | 0.0001 | - |
99
+ | 1.0667 | 4700 | 0.0001 | - |
100
+ | 1.0781 | 4750 | 0.0001 | - |
101
+ | 1.0894 | 4800 | 0.0001 | - |
102
+ | 1.1008 | 4850 | 0.0001 | - |
103
+ | 1.1121 | 4900 | 0.0001 | - |
104
+ | 1.1235 | 4950 | 0.0001 | - |
105
+ | 1.1348 | 5000 | 0.0001 | - |
106
+ | 1.1462 | 5050 | 0.0002 | - |
107
+ | 1.1575 | 5100 | 0.0001 | - |
108
+ | 1.1689 | 5150 | 0.0001 | - |
109
+ | 1.1802 | 5200 | 0.0001 | - |
110
+ | 1.1916 | 5250 | 0.0001 | - |
111
+ | 1.2029 | 5300 | 0.0001 | - |
112
+ | 1.2143 | 5350 | 0.0001 | - |
113
+ | 1.2256 | 5400 | 0.0001 | - |
114
+ | 1.2369 | 5450 | 0.0001 | - |
115
+ | 1.2483 | 5500 | 0.0001 | - |
116
+ | 1.2596 | 5550 | 0.0001 | - |
117
+ | 1.2710 | 5600 | 0.0001 | - |
118
+ | 1.2823 | 5650 | 0.0001 | - |
119
+ | 1.2937 | 5700 | 0.0001 | - |
120
+ | 1.3050 | 5750 | 0.0001 | - |
121
+ | 1.3164 | 5800 | 0.0001 | - |
122
+ | 1.3277 | 5850 | 0.0001 | - |
123
+ | 1.3391 | 5900 | 0.0001 | - |
124
+ | 1.3504 | 5950 | 0.0001 | - |
125
+ | 1.3618 | 6000 | 0.0001 | - |
126
+ | 1.3731 | 6050 | 0.0001 | - |
127
+ | 1.3845 | 6100 | 0.0001 | - |
128
+ | 1.3958 | 6150 | 0.0001 | - |
129
+ | 1.4072 | 6200 | 0.0001 | - |
130
+ | 1.4185 | 6250 | 0.0001 | - |
131
+ | 1.4299 | 6300 | 0.0001 | - |
132
+ | 1.4412 | 6350 | 0.0001 | - |
133
+ | 1.4526 | 6400 | 0.0001 | - |
134
+ | 1.4639 | 6450 | 0.0 | - |
135
+ | 1.4753 | 6500 | 0.0001 | - |
136
+ | 1.4866 | 6550 | 0.0011 | - |
137
+ | 1.4980 | 6600 | 0.0001 | - |
138
+ | 1.5093 | 6650 | 0.0001 | - |
139
+ | 1.5207 | 6700 | 0.0 | - |
140
+ | 1.5320 | 6750 | 0.0 | - |
141
+ | 1.5433 | 6800 | 0.0001 | - |
142
+ | 1.5547 | 6850 | 0.0001 | - |
143
+ | 1.5660 | 6900 | 0.0001 | - |
144
+ | 1.5774 | 6950 | 0.0001 | - |
145
+ | 1.5887 | 7000 | 0.0001 | - |
146
+ | 1.6001 | 7050 | 0.0001 | - |
147
+ | 1.6114 | 7100 | 0.0001 | - |
148
+ | 1.6228 | 7150 | 0.0 | - |
149
+ | 1.6341 | 7200 | 0.0 | - |
150
+ | 1.6455 | 7250 | 0.0001 | - |
151
+ | 1.6568 | 7300 | 0.0001 | - |
152
+ | 1.6682 | 7350 | 0.0001 | - |
153
+ | 1.6795 | 7400 | 0.0001 | - |
154
+ | 1.6909 | 7450 | 0.0 | - |
155
+ | 1.7022 | 7500 | 0.0001 | - |
156
+ | 1.7136 | 7550 | 0.0001 | - |
157
+ | 1.7249 | 7600 | 0.0001 | - |
158
+ | 1.7363 | 7650 | 0.0 | - |
159
+ | 1.7476 | 7700 | 0.0 | - |
160
+ | 1.7590 | 7750 | 0.0 | - |
161
+ | 1.7703 | 7800 | 0.0001 | - |
162
+ | 1.7817 | 7850 | 0.0 | - |
163
+ | 1.7930 | 7900 | 0.0 | - |
164
+ | 1.8044 | 7950 | 0.0 | - |
165
+ | 1.8157 | 8000 | 0.0001 | - |
166
+ | 1.8271 | 8050 | 0.0 | - |
167
+ | 1.8384 | 8100 | 0.0 | - |
168
+ | 1.8498 | 8150 | 0.0001 | - |
169
+ | 1.8611 | 8200 | 0.0 | - |
170
+ | 1.8724 | 8250 | 0.0001 | - |
171
+ | 1.8838 | 8300 | 0.0 | - |
172
+ | 1.8951 | 8350 | 0.0001 | - |
173
+ | 1.9065 | 8400 | 0.0001 | - |
174
+ | 1.9178 | 8450 | 0.0001 | - |
175
+ | 1.9292 | 8500 | 0.0 | - |
176
+ | 1.9405 | 8550 | 0.0 | - |
177
+ | 1.9519 | 8600 | 0.0 | - |
178
+ | 1.9632 | 8650 | 0.0 | - |
179
+ | 1.9746 | 8700 | 0.0 | - |
180
+ | 1.9859 | 8750 | 0.0 | - |
181
+ | 1.9973 | 8800 | 0.0 | - |
182
+ | 2.0 | 8812 | - | 0.0549 |
183
+ | 2.0086 | 8850 | 0.0 | - |
184
+ | 2.0200 | 8900 | 0.0 | - |
185
+ | 2.0313 | 8950 | 0.0 | - |
186
+ | 2.0427 | 9000 | 0.0 | - |
187
+ | 2.0540 | 9050 | 0.0 | - |
188
+ | 2.0654 | 9100 | 0.0 | - |
189
+ | 2.0767 | 9150 | 0.0 | - |
190
+ | 2.0881 | 9200 | 0.0 | - |
191
+ | 2.0994 | 9250 | 0.0 | - |
192
+ | 2.1108 | 9300 | 0.0 | - |
193
+ | 2.1221 | 9350 | 0.0 | - |
194
+ | 2.1335 | 9400 | 0.0001 | - |
195
+ | 2.1448 | 9450 | 0.0 | - |
196
+ | 2.1562 | 9500 | 0.0 | - |
197
+ | 2.1675 | 9550 | 0.0 | - |
198
+ | 2.1788 | 9600 | 0.0 | - |
199
+ | 2.1902 | 9650 | 0.0 | - |
200
+ | 2.2015 | 9700 | 0.0 | - |
201
+ | 2.2129 | 9750 | 0.0 | - |
202
+ | 2.2242 | 9800 | 0.0 | - |
203
+ | 2.2356 | 9850 | 0.0 | - |
204
+ | 2.2469 | 9900 | 0.0 | - |
205
+ | 2.2583 | 9950 | 0.0 | - |
206
+ | 2.2696 | 10000 | 0.0 | - |
207
+ | 2.2810 | 10050 | 0.0 | - |
208
+ | 2.2923 | 10100 | 0.0 | - |
209
+ | 2.3037 | 10150 | 0.0 | - |
210
+ | 2.3150 | 10200 | 0.0 | - |
211
+ | 2.3264 | 10250 | 0.0 | - |
212
+ | 2.3377 | 10300 | 0.0 | - |
213
+ | 2.3491 | 10350 | 0.0 | - |
214
+ | 2.3604 | 10400 | 0.0 | - |
215
+ | 2.3718 | 10450 | 0.0001 | - |
216
+ | 2.3831 | 10500 | 0.0 | - |
217
+ | 2.3945 | 10550 | 0.0 | - |
218
+ | 2.4058 | 10600 | 0.0 | - |
219
+ | 2.4172 | 10650 | 0.0 | - |
220
+ | 2.4285 | 10700 | 0.0 | - |
221
+ | 2.4399 | 10750 | 0.0 | - |
222
+ | 2.4512 | 10800 | 0.0 | - |
223
+ | 2.4626 | 10850 | 0.0 | - |
224
+ | 2.4739 | 10900 | 0.0 | - |
225
+ | 2.4852 | 10950 | 0.0 | - |
226
+ | 2.4966 | 11000 | 0.0 | - |
227
+ | 2.5079 | 11050 | 0.0 | - |
228
+ | 2.5193 | 11100 | 0.0 | - |
229
+ | 2.5306 | 11150 | 0.0 | - |
230
+ | 2.5420 | 11200 | 0.0 | - |
231
+ | 2.5533 | 11250 | 0.0 | - |
232
+ | 2.5647 | 11300 | 0.0 | - |
233
+ | 2.5760 | 11350 | 0.0 | - |
234
+ | 2.5874 | 11400 | 0.0 | - |
235
+ | 2.5987 | 11450 | 0.0 | - |
236
+ | 2.6101 | 11500 | 0.0 | - |
237
+ | 2.6214 | 11550 | 0.0 | - |
238
+ | 2.6328 | 11600 | 0.0 | - |
239
+ | 2.6441 | 11650 | 0.0 | - |
240
+ | 2.6555 | 11700 | 0.0 | - |
241
+ | 2.6668 | 11750 | 0.0 | - |
242
+ | 2.6782 | 11800 | 0.0 | - |
243
+ | 2.6895 | 11850 | 0.0 | - |
244
+ | 2.7009 | 11900 | 0.0 | - |
245
+ | 2.7122 | 11950 | 0.0 | - |
246
+ | 2.7236 | 12000 | 0.0 | - |
247
+ | 2.7349 | 12050 | 0.0 | - |
248
+ | 2.7463 | 12100 | 0.0 | - |
249
+ | 2.7576 | 12150 | 0.0 | - |
250
+ | 2.7690 | 12200 | 0.0 | - |
251
+ | 2.7803 | 12250 | 0.0 | - |
252
+ | 2.7916 | 12300 | 0.0 | - |
253
+ | 2.8030 | 12350 | 0.0 | - |
254
+ | 2.8143 | 12400 | 0.0 | - |
255
+ | 2.8257 | 12450 | 0.0 | - |
256
+ | 2.8370 | 12500 | 0.0 | - |
257
+ | 2.8484 | 12550 | 0.0 | - |
258
+ | 2.8597 | 12600 | 0.0 | - |
259
+ | 2.8711 | 12650 | 0.0 | - |
260
+ | 2.8824 | 12700 | 0.0 | - |
261
+ | 2.8938 | 12750 | 0.0 | - |
262
+ | 2.9051 | 12800 | 0.0 | - |
263
+ | 2.9165 | 12850 | 0.0 | - |
264
+ | 2.9278 | 12900 | 0.0 | - |
265
+ | 2.9392 | 12950 | 0.0 | - |
266
+ | 2.9505 | 13000 | 0.0 | - |
267
+ | 2.9619 | 13050 | 0.0 | - |
268
+ | 2.9732 | 13100 | 0.0 | - |
269
+ | 2.9846 | 13150 | 0.0 | - |
270
+ | 2.9959 | 13200 | 0.0 | - |
271
+ | 3.0 | 13218 | - | 0.0469 |
272
+ | 3.0073 | 13250 | 0.0 | - |
273
+ | 3.0186 | 13300 | 0.0 | - |
274
+ | 3.0300 | 13350 | 0.0 | - |
275
+ | 3.0413 | 13400 | 0.0 | - |
276
+ | 3.0527 | 13450 | 0.0 | - |
277
+ | 3.0640 | 13500 | 0.0 | - |
278
+ | 3.0754 | 13550 | 0.0 | - |
279
+ | 3.0867 | 13600 | 0.0 | - |
280
+ | 3.0980 | 13650 | 0.0 | - |
281
+ | 3.1094 | 13700 | 0.0 | - |
282
+ | 3.1207 | 13750 | 0.0 | - |
283
+ | 3.1321 | 13800 | 0.0 | - |
284
+ | 3.1434 | 13850 | 0.0 | - |
285
+ | 3.1548 | 13900 | 0.0 | - |
286
+ | 3.1661 | 13950 | 0.0 | - |
287
+ | 3.1775 | 14000 | 0.0 | - |
288
+ | 3.1888 | 14050 | 0.0 | - |
289
+ | 3.2002 | 14100 | 0.0 | - |
290
+ | 3.2115 | 14150 | 0.0 | - |
291
+ | 3.2229 | 14200 | 0.0 | - |
292
+ | 3.2342 | 14250 | 0.0 | - |
293
+ | 3.2456 | 14300 | 0.0 | - |
294
+ | 3.2569 | 14350 | 0.0 | - |
295
+ | 3.2683 | 14400 | 0.0 | - |
296
+ | 3.2796 | 14450 | 0.0 | - |
297
+ | 3.2910 | 14500 | 0.0 | - |
298
+ | 3.3023 | 14550 | 0.0 | - |
299
+ | 3.3137 | 14600 | 0.0 | - |
300
+ | 3.3250 | 14650 | 0.0 | - |
301
+ | 3.3364 | 14700 | 0.0 | - |
302
+ | 3.3477 | 14750 | 0.0 | - |
303
+ | 3.3591 | 14800 | 0.0 | - |
304
+ | 3.3704 | 14850 | 0.0 | - |
305
+ | 3.3818 | 14900 | 0.0 | - |
306
+ | 3.3931 | 14950 | 0.0 | - |
307
+ | 3.4044 | 15000 | 0.0 | - |
308
+ | 3.4158 | 15050 | 0.0 | - |
309
+ | 3.4271 | 15100 | 0.0 | - |
310
+ | 3.4385 | 15150 | 0.0 | - |
311
+ | 3.4498 | 15200 | 0.0 | - |
312
+ | 3.4612 | 15250 | 0.0 | - |
313
+ | 3.4725 | 15300 | 0.0 | - |
314
+ | 3.4839 | 15350 | 0.0 | - |
315
+ | 3.4952 | 15400 | 0.0 | - |
316
+ | 3.5066 | 15450 | 0.0 | - |
317
+ | 3.5179 | 15500 | 0.0 | - |
318
+ | 3.5293 | 15550 | 0.0 | - |
319
+ | 3.5406 | 15600 | 0.0 | - |
320
+ | 3.5520 | 15650 | 0.0 | - |
321
+ | 3.5633 | 15700 | 0.0 | - |
322
+ | 3.5747 | 15750 | 0.0 | - |
323
+ | 3.5860 | 15800 | 0.0 | - |
324
+ | 3.5974 | 15850 | 0.0 | - |
325
+ | 3.6087 | 15900 | 0.0 | - |
326
+ | 3.6201 | 15950 | 0.0 | - |
327
+ | 3.6314 | 16000 | 0.0 | - |
328
+ | 3.6428 | 16050 | 0.0 | - |
329
+ | 3.6541 | 16100 | 0.0 | - |
330
+ | 3.6655 | 16150 | 0.0 | - |
331
+ | 3.6768 | 16200 | 0.0 | - |
332
+ | 3.6882 | 16250 | 0.0 | - |
333
+ | 3.6995 | 16300 | 0.0 | - |
334
+ | 3.7108 | 16350 | 0.0 | - |
335
+ | 3.7222 | 16400 | 0.0 | - |
336
+ | 3.7335 | 16450 | 0.0 | - |
337
+ | 3.7449 | 16500 | 0.0 | - |
338
+ | 3.7562 | 16550 | 0.0 | - |
339
+ | 3.7676 | 16600 | 0.0 | - |
340
+ | 3.7789 | 16650 | 0.0 | - |
341
+ | 3.7903 | 16700 | 0.0 | - |
342
+ | 3.8016 | 16750 | 0.0 | - |
343
+ | 3.8130 | 16800 | 0.0 | - |
344
+ | 3.8243 | 16850 | 0.0 | - |
345
+ | 3.8357 | 16900 | 0.0 | - |
346
+ | 3.8470 | 16950 | 0.0 | - |
347
+ | 3.8584 | 17000 | 0.0 | - |
348
+ | 3.8697 | 17050 | 0.0 | - |
349
+ | 3.8811 | 17100 | 0.0 | - |
350
+ | 3.8924 | 17150 | 0.0 | - |
351
+ | 3.9038 | 17200 | 0.0 | - |
352
+ | 3.9151 | 17250 | 0.0 | - |
353
+ | 3.9265 | 17300 | 0.0 | - |
354
+ | 3.9378 | 17350 | 0.0 | - |
355
+ | 3.9492 | 17400 | 0.0 | - |
356
+ | 3.9605 | 17450 | 0.0 | - |
357
+ | 3.9719 | 17500 | 0.0 | - |
358
+ | 3.9832 | 17550 | 0.0 | - |
359
+ | 3.9946 | 17600 | 0.0 | - |
360
+ | 4.0 | 17624 | - | 0.0404 |
361
+ | 4.0059 | 17650 | 0.0 | - |
362
+ | 4.0172 | 17700 | 0.0 | - |
363
+ | 4.0286 | 17750 | 0.0 | - |
364
+ | 4.0399 | 17800 | 0.0 | - |
365
+ | 4.0513 | 17850 | 0.0 | - |
366
+ | 4.0626 | 17900 | 0.0 | - |
367
+ | 4.0740 | 17950 | 0.0 | - |
368
+ | 4.0853 | 18000 | 0.0 | - |
369
+ | 4.0967 | 18050 | 0.0 | - |
370
+ | 4.1080 | 18100 | 0.0 | - |
371
+ | 4.1194 | 18150 | 0.0 | - |
372
+ | 4.1307 | 18200 | 0.0 | - |
373
+ | 4.1421 | 18250 | 0.0 | - |
374
+ | 4.1534 | 18300 | 0.0 | - |
375
+ | 4.1648 | 18350 | 0.0 | - |
376
+ | 4.1761 | 18400 | 0.0 | - |
377
+ | 4.1875 | 18450 | 0.0 | - |
378
+ | 4.1988 | 18500 | 0.0 | - |
379
+ | 4.2102 | 18550 | 0.0 | - |
380
+ | 4.2215 | 18600 | 0.0 | - |
381
+ | 4.2329 | 18650 | 0.0 | - |
382
+ | 4.2442 | 18700 | 0.0 | - |
383
+ | 4.2556 | 18750 | 0.0 | - |
384
+ | 4.2669 | 18800 | 0.0 | - |
385
+ | 4.2783 | 18850 | 0.0 | - |
386
+ | 4.2896 | 18900 | 0.0 | - |
387
+ | 4.3010 | 18950 | 0.0 | - |
388
+ | 4.3123 | 19000 | 0.0 | - |
389
+ | 4.3236 | 19050 | 0.0 | - |
390
+ | 4.3350 | 19100 | 0.0 | - |
391
+ | 4.3463 | 19150 | 0.0 | - |
392
+ | 4.3577 | 19200 | 0.0 | - |
393
+ | 4.3690 | 19250 | 0.0 | - |
394
+ | 4.3804 | 19300 | 0.0 | - |
395
+ | 4.3917 | 19350 | 0.0 | - |
396
+ | 4.4031 | 19400 | 0.0 | - |
397
+ | 4.4144 | 19450 | 0.0 | - |
398
+ | 4.4258 | 19500 | 0.0 | - |
399
+ | 4.4371 | 19550 | 0.0 | - |
400
+ | 4.4485 | 19600 | 0.0 | - |
401
+ | 4.4598 | 19650 | 0.0 | - |
402
+ | 4.4712 | 19700 | 0.0 | - |
403
+ | 4.4825 | 19750 | 0.0 | - |
404
+ | 4.4939 | 19800 | 0.0 | - |
405
+ | 4.5052 | 19850 | 0.0 | - |
406
+ | 4.5166 | 19900 | 0.0 | - |
407
+ | 4.5279 | 19950 | 0.0 | - |
408
+ | 4.5393 | 20000 | 0.0 | - |
409
+ | 4.5506 | 20050 | 0.0 | - |
410
+ | 4.5620 | 20100 | 0.0 | - |
411
+ | 4.5733 | 20150 | 0.0 | - |
412
+ | 4.5847 | 20200 | 0.0 | - |
413
+ | 4.5960 | 20250 | 0.0 | - |
414
+ | 4.6074 | 20300 | 0.0 | - |
415
+ | 4.6187 | 20350 | 0.0 | - |
416
+ | 4.6300 | 20400 | 0.0 | - |
417
+ | 4.6414 | 20450 | 0.0 | - |
418
+ | 4.6527 | 20500 | 0.0 | - |
419
+ | 4.6641 | 20550 | 0.0 | - |
420
+ | 4.6754 | 20600 | 0.0 | - |
421
+ | 4.6868 | 20650 | 0.0 | - |
422
+ | 4.6981 | 20700 | 0.0 | - |
423
+ | 4.7095 | 20750 | 0.0 | - |
424
+ | 4.7208 | 20800 | 0.0 | - |
425
+ | 4.7322 | 20850 | 0.0 | - |
426
+ | 4.7435 | 20900 | 0.0 | - |
427
+ | 4.7549 | 20950 | 0.0 | - |
428
+ | 4.7662 | 21000 | 0.0 | - |
429
+ | 4.7776 | 21050 | 0.0 | - |
430
+ | 4.7889 | 21100 | 0.0 | - |
431
+ | 4.8003 | 21150 | 0.0 | - |
432
+ | 4.8116 | 21200 | 0.0 | - |
433
+ | 4.8230 | 21250 | 0.0 | - |
434
+ | 4.8343 | 21300 | 0.0 | - |
435
+ | 4.8457 | 21350 | 0.0 | - |
436
+ | 4.8570 | 21400 | 0.0 | - |
437
+ | 4.8684 | 21450 | 0.0 | - |
438
+ | 4.8797 | 21500 | 0.0 | - |
439
+ | 4.8911 | 21550 | 0.0 | - |
440
+ | 4.9024 | 21600 | 0.0 | - |
441
+ | 4.9138 | 21650 | 0.0 | - |
442
+ | 4.9251 | 21700 | 0.0 | - |
443
+ | 4.9365 | 21750 | 0.0 | - |
444
+ | 4.9478 | 21800 | 0.0 | - |
445
+ | 4.9591 | 21850 | 0.0 | - |
446
+ | 4.9705 | 21900 | 0.0 | - |
447
+ | 4.9818 | 21950 | 0.0 | - |
448
+ | 4.9932 | 22000 | 0.0 | - |
449
+ | **5.0** | **22030** | **-** | **0.038** |
450
+ | 5.0045 | 22050 | 0.0 | - |
451
+ | 5.0159 | 22100 | 0.0 | - |
452
+ | 5.0272 | 22150 | 0.0 | - |
453
+ | 5.0386 | 22200 | 0.0 | - |
454
+ | 5.0499 | 22250 | 0.0 | - |
455
+ | 5.0613 | 22300 | 0.0 | - |
456
+ | 5.0726 | 22350 | 0.0 | - |
457
+ | 5.0840 | 22400 | 0.0 | - |
458
+ | 5.0953 | 22450 | 0.0 | - |
459
+ | 5.1067 | 22500 | 0.0 | - |
460
+ | 5.1180 | 22550 | 0.0 | - |
461
+ | 5.1294 | 22600 | 0.0 | - |
462
+ | 5.1407 | 22650 | 0.0 | - |
463
+ | 5.1521 | 22700 | 0.0 | - |
464
+ | 5.1634 | 22750 | 0.0 | - |
465
+ | 5.1748 | 22800 | 0.0 | - |
466
+ | 5.1861 | 22850 | 0.0 | - |
467
+ | 5.1975 | 22900 | 0.0 | - |
468
+ | 5.2088 | 22950 | 0.0 | - |
469
+ | 5.2202 | 23000 | 0.0 | - |
470
+ | 5.2315 | 23050 | 0.0 | - |
471
+ | 5.2429 | 23100 | 0.0 | - |
472
+ | 5.2542 | 23150 | 0.0 | - |
473
+ | 5.2655 | 23200 | 0.0 | - |
474
+ | 5.2769 | 23250 | 0.0 | - |
475
+ | 5.2882 | 23300 | 0.0 | - |
476
+ | 5.2996 | 23350 | 0.0 | - |
477
+ | 5.3109 | 23400 | 0.0 | - |
478
+ | 5.3223 | 23450 | 0.0 | - |
479
+ | 5.3336 | 23500 | 0.0 | - |
480
+ | 5.3450 | 23550 | 0.0 | - |
481
+ | 5.3563 | 23600 | 0.0 | - |
482
+ | 5.3677 | 23650 | 0.0 | - |
483
+ | 5.3790 | 23700 | 0.0 | - |
484
+ | 5.3904 | 23750 | 0.0 | - |
485
+ | 5.4017 | 23800 | 0.0 | - |
486
+ | 5.4131 | 23850 | 0.0 | - |
487
+ | 5.4244 | 23900 | 0.0 | - |
488
+ | 5.4358 | 23950 | 0.0 | - |
489
+ | 5.4471 | 24000 | 0.0 | - |
490
+ | 5.4585 | 24050 | 0.0 | - |
491
+ | 5.4698 | 24100 | 0.0 | - |
492
+ | 5.4812 | 24150 | 0.0 | - |
493
+ | 5.4925 | 24200 | 0.0 | - |
494
+ | 5.5039 | 24250 | 0.0 | - |
495
+ | 5.5152 | 24300 | 0.0 | - |
496
+ | 5.5266 | 24350 | 0.0 | - |
497
+ | 5.5379 | 24400 | 0.0 | - |
498
+ | 5.5493 | 24450 | 0.0 | - |
499
+ | 5.5606 | 24500 | 0.0 | - |
500
+ | 5.5719 | 24550 | 0.0 | - |
501
+ | 5.5833 | 24600 | 0.0 | - |
502
+ | 5.5946 | 24650 | 0.0 | - |
503
+ | 5.6060 | 24700 | 0.0 | - |
504
+ | 5.6173 | 24750 | 0.0 | - |
505
+ | 5.6287 | 24800 | 0.0 | - |
506
+ | 5.6400 | 24850 | 0.0 | - |
507
+ | 5.6514 | 24900 | 0.0 | - |
508
+ | 5.6627 | 24950 | 0.0 | - |
509
+ | 5.6741 | 25000 | 0.0 | - |
510
+ | 5.6854 | 25050 | 0.0 | - |
511
+ | 5.6968 | 25100 | 0.0 | - |
512
+ | 5.7081 | 25150 | 0.0 | - |
513
+ | 5.7195 | 25200 | 0.0 | - |
514
+ | 5.7308 | 25250 | 0.0 | - |
515
+ | 5.7422 | 25300 | 0.0 | - |
516
+ | 5.7535 | 25350 | 0.0 | - |
517
+ | 5.7649 | 25400 | 0.0 | - |
518
+ | 5.7762 | 25450 | 0.0 | - |
519
+ | 5.7876 | 25500 | 0.0 | - |
520
+ | 5.7989 | 25550 | 0.0 | - |
521
+ | 5.8103 | 25600 | 0.0 | - |
522
+ | 5.8216 | 25650 | 0.0 | - |
523
+ | 5.8330 | 25700 | 0.0 | - |
524
+ | 5.8443 | 25750 | 0.0 | - |
525
+ | 5.8557 | 25800 | 0.0 | - |
526
+ | 5.8670 | 25850 | 0.0 | - |
527
+ | 5.8783 | 25900 | 0.0 | - |
528
+ | 5.8897 | 25950 | 0.0 | - |
529
+ | 5.9010 | 26000 | 0.0 | - |
530
+ | 5.9124 | 26050 | 0.0 | - |
531
+ | 5.9237 | 26100 | 0.0 | - |
532
+ | 5.9351 | 26150 | 0.0 | - |
533
+ | 5.9464 | 26200 | 0.0 | - |
534
+ | 5.9578 | 26250 | 0.0 | - |
535
+ | 5.9691 | 26300 | 0.0 | - |
536
+ | 5.9805 | 26350 | 0.0 | - |
537
+ | 5.9918 | 26400 | 0.0 | - |
538
+ | 6.0 | 26436 | - | 0.0382 |
539
+
540
+ * The bold row denotes the saved checkpoint.