Hugging Face's logo

saracandu
/
stlenc

Feature Extraction
Transformers
Safetensors
stl_encoder
Generated from Trainer
custom_code
Model card Files
xet
Community
saracandu commited on
Commit
26909cc
·
verified ·
1 Parent(s): 84b831f

Training finale completato - main aggiornato

Browse files
Files changed (2) hide show
  1. README.md +531 -38
  2. model.safetensors +1 -1
README.md CHANGED
@@ -1,59 +1,552 @@
1
  ---
2
- language:
3
- - en
4
  library_name: transformers
5
- tags:
6
- - stl
7
- - formal-methods
8
- - signal-temporal-logic
9
- - encoder
10
- - pytorch
11
- - kernel-methods
12
  license: mit
13
  base_model: saracandu/stlenc
14
- model_type: stl_encoder
15
- pipeline_tag: feature-extraction
 
 
 
16
  ---
17
 
18
- # STL Encoder (Neural Backbone)
 
 
 
19
 
20
- This repository contains the neural encoder architecture for the **STLEnc** project. The model is designed to map **Signal Temporal Logic (STL)** formulae into a 1024-dimensional latent embedding space.
 
 
 
 
21
 
22
- ## Model Description
23
 
24
- This model is a neural approximation of the kernel-based framework introduced by **Gallo et al.** in [*"A Kernel-Based Approach to Signal Temporal Logic"* (2020)](https://arxiv.org/abs/2009.05484).
25
 
26
- In the original framework, STL formulae are embedded into a Reproducing Kernel Hilbert Space (RKHS) using a recursive kernel that accounts for the syntax and temporal intervals of the logic. Our approach replaces the traditional kernel-based projection with a **Transformer-based encoder**.
27
 
28
- By using a fixed **anchor set** of formulae (as suggested in kernel approximation methods), the Transformer is trained to learn a mapping that mimics the kernel's distance properties. This allows for:
29
- - **Scalability**: Faster computation compared to recursive kernel evaluations.
30
- - **Continuity**: A smooth latent space suitable for optimization and deep learning tasks.
31
 
32
- - **Architecture**: Custom Transformer Encoder (12 layers, 16 attention heads).
33
- - **Tokenizer**: Custom *longest-match* tokenizer optimized for STL symbols, temporal intervals, and numeric predicates.
34
- - **Output**: 1024-dimensional embeddings via `[CLS]` token pooling.
35
 
36
- ## Training Data
37
 
38
- The model is designed to be trained on the [saracandu/stl_formulae](https://huggingface.co/datasets/saracandu/stl_formulae) dataset, which contains a large-scale collection of STL expressions and their corresponding kernel-derived embeddings.
39
 
40
- ## Usage
41
 
42
- ```python
43
- from transformers import AutoModel, AutoTokenizer
44
- import torch
 
 
 
 
 
 
45
 
46
- repo_id = "saracandu/stlenc"
47
 
48
- # Load Tokenizer & Model
49
- tokenizer = AutoTokenizer.from_pretrained(repo_id, trust_remote_code=True)
50
- model = AutoModel.from_pretrained(repo_id, trust_remote_code=True)
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
51
 
52
- # Example: Encode an STL formula
53
- formula = "always[0, 10] (x > 0) and eventually[5, 20] (y < -1)"
54
- inputs = tokenizer(formula, return_tensors="pt")
55
 
56
- with torch.no_grad():
57
- embedding = model(**inputs)
58
 
59
- print(embedding.shape) # [1, 1024]
 
 
 
 
1
  ---
 
 
2
  library_name: transformers
 
 
 
 
 
 
 
3
  license: mit
4
  base_model: saracandu/stlenc
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: stlenc
9
+ results: []
10
  ---
11
 
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # stlenc
16
 
17
+ This model is a fine-tuned version of [saracandu/stlenc](https://huggingface.co/saracandu/stlenc) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.0125
20
+ - Mse Sync: 0.0125
21
+ - Cosine Similarity: 0.6938
22
 
23
+ ## Model description
24
 
25
+ More information needed
26
 
27
+ ## Intended uses & limitations
28
 
29
+ More information needed
 
 
30
 
31
+ ## Training and evaluation data
 
 
32
 
33
+ More information needed
34
 
35
+ ## Training procedure
36
 
37
+ ### Training hyperparameters
38
 
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 5e-05
41
+ - train_batch_size: 16
42
+ - eval_batch_size: 16
43
+ - seed: 42
44
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 10
47
+ - mixed_precision_training: Native AMP
48
 
49
+ ### Training results
50
 
51
+ | Training Loss | Epoch | Step | Validation Loss | Mse Sync | Cosine Similarity |
52
+ |:-------------:|:------:|:-----:|:---------------:|:--------:|:-----------------:|
53
+ | 0.0247 | 0.0203 | 100 | 0.0222 | 0.0222 | 0.4734 |
54
+ | 0.0247 | 0.0407 | 200 | 0.0205 | 0.0205 | 0.5004 |
55
+ | 0.0242 | 0.0610 | 300 | 0.0208 | 0.0208 | 0.4881 |
56
+ | 0.0258 | 0.0813 | 400 | 0.0202 | 0.0202 | 0.5144 |
57
+ | 0.0236 | 0.1016 | 500 | 0.0202 | 0.0202 | 0.5102 |
58
+ | 0.023 | 0.1220 | 600 | 0.0198 | 0.0198 | 0.5193 |
59
+ | 0.0228 | 0.1423 | 700 | 0.0210 | 0.0210 | 0.5076 |
60
+ | 0.0245 | 0.1626 | 800 | 0.0197 | 0.0197 | 0.5135 |
61
+ | 0.0229 | 0.1829 | 900 | 0.0200 | 0.0200 | 0.5133 |
62
+ | 0.0213 | 0.2033 | 1000 | 0.0200 | 0.0200 | 0.5050 |
63
+ | 0.0224 | 0.2236 | 1100 | 0.0196 | 0.0196 | 0.5187 |
64
+ | 0.0235 | 0.2439 | 1200 | 0.0198 | 0.0198 | 0.5165 |
65
+ | 0.0216 | 0.2642 | 1300 | 0.0195 | 0.0195 | 0.5210 |
66
+ | 0.0227 | 0.2846 | 1400 | 0.0201 | 0.0201 | 0.5162 |
67
+ | 0.0216 | 0.3049 | 1500 | 0.0191 | 0.0191 | 0.5348 |
68
+ | 0.0207 | 0.3252 | 1600 | 0.0196 | 0.0196 | 0.5202 |
69
+ | 0.0209 | 0.3455 | 1700 | 0.0193 | 0.0193 | 0.5231 |
70
+ | 0.0218 | 0.3659 | 1800 | 0.0193 | 0.0193 | 0.5317 |
71
+ | 0.0226 | 0.3862 | 1900 | 0.0193 | 0.0193 | 0.5275 |
72
+ | 0.0214 | 0.4065 | 2000 | 0.0194 | 0.0194 | 0.5242 |
73
+ | 0.0211 | 0.4268 | 2100 | 0.0192 | 0.0192 | 0.5301 |
74
+ | 0.021 | 0.4472 | 2200 | 0.0196 | 0.0196 | 0.5214 |
75
+ | 0.0215 | 0.4675 | 2300 | 0.0190 | 0.0190 | 0.5339 |
76
+ | 0.0205 | 0.4878 | 2400 | 0.0187 | 0.0187 | 0.5438 |
77
+ | 0.0207 | 0.5081 | 2500 | 0.0188 | 0.0188 | 0.5425 |
78
+ | 0.0207 | 0.5285 | 2600 | 0.0190 | 0.0190 | 0.5422 |
79
+ | 0.0203 | 0.5488 | 2700 | 0.0194 | 0.0194 | 0.5413 |
80
+ | 0.0214 | 0.5691 | 2800 | 0.0192 | 0.0192 | 0.5390 |
81
+ | 0.0202 | 0.5894 | 2900 | 0.0186 | 0.0186 | 0.5509 |
82
+ | 0.0196 | 0.6098 | 3000 | 0.0192 | 0.0192 | 0.5456 |
83
+ | 0.0201 | 0.6301 | 3100 | 0.0185 | 0.0185 | 0.5504 |
84
+ | 0.0203 | 0.6504 | 3200 | 0.0202 | 0.0202 | 0.5340 |
85
+ | 0.0194 | 0.6707 | 3300 | 0.0184 | 0.0184 | 0.5512 |
86
+ | 0.0205 | 0.6911 | 3400 | 0.0188 | 0.0188 | 0.5340 |
87
+ | 0.0201 | 0.7114 | 3500 | 0.0186 | 0.0186 | 0.5504 |
88
+ | 0.0206 | 0.7317 | 3600 | 0.0190 | 0.0190 | 0.5409 |
89
+ | 0.0194 | 0.7520 | 3700 | 0.0183 | 0.0183 | 0.5600 |
90
+ | 0.02 | 0.7724 | 3800 | 0.0187 | 0.0187 | 0.5567 |
91
+ | 0.0209 | 0.7927 | 3900 | 0.0185 | 0.0185 | 0.5464 |
92
+ | 0.0191 | 0.8130 | 4000 | 0.0185 | 0.0185 | 0.5530 |
93
+ | 0.0199 | 0.8333 | 4100 | 0.0186 | 0.0186 | 0.5472 |
94
+ | 0.0191 | 0.8537 | 4200 | 0.0182 | 0.0182 | 0.5595 |
95
+ | 0.0206 | 0.8740 | 4300 | 0.0191 | 0.0191 | 0.5430 |
96
+ | 0.0205 | 0.8943 | 4400 | 0.0182 | 0.0182 | 0.5597 |
97
+ | 0.0201 | 0.9146 | 4500 | 0.0185 | 0.0185 | 0.5521 |
98
+ | 0.0215 | 0.9350 | 4600 | 0.0188 | 0.0188 | 0.5417 |
99
+ | 0.02 | 0.9553 | 4700 | 0.0186 | 0.0186 | 0.5534 |
100
+ | 0.0208 | 0.9756 | 4800 | 0.0187 | 0.0187 | 0.5475 |
101
+ | 0.0194 | 0.9959 | 4900 | 0.0183 | 0.0183 | 0.5611 |
102
+ | 0.0187 | 1.0163 | 5000 | 0.0191 | 0.0191 | 0.5489 |
103
+ | 0.0203 | 1.0366 | 5100 | 0.0194 | 0.0194 | 0.5413 |
104
+ | 0.0192 | 1.0569 | 5200 | 0.0185 | 0.0185 | 0.5580 |
105
+ | 0.02 | 1.0772 | 5300 | 0.0196 | 0.0196 | 0.5371 |
106
+ | 0.0198 | 1.0976 | 5400 | 0.0182 | 0.0182 | 0.5592 |
107
+ | 0.0198 | 1.1179 | 5500 | 0.0182 | 0.0182 | 0.5592 |
108
+ | 0.0191 | 1.1382 | 5600 | 0.0185 | 0.0185 | 0.5529 |
109
+ | 0.0191 | 1.1585 | 5700 | 0.0182 | 0.0182 | 0.5608 |
110
+ | 0.0195 | 1.1789 | 5800 | 0.0181 | 0.0181 | 0.5604 |
111
+ | 0.0198 | 1.1992 | 5900 | 0.0183 | 0.0183 | 0.5586 |
112
+ | 0.0193 | 1.2195 | 6000 | 0.0185 | 0.0185 | 0.5537 |
113
+ | 0.0205 | 1.2398 | 6100 | 0.0182 | 0.0182 | 0.5658 |
114
+ | 0.0195 | 1.2602 | 6200 | 0.0180 | 0.0180 | 0.5636 |
115
+ | 0.0197 | 1.2805 | 6300 | 0.0180 | 0.0180 | 0.5680 |
116
+ | 0.0205 | 1.3008 | 6400 | 0.0182 | 0.0182 | 0.5605 |
117
+ | 0.0198 | 1.3211 | 6500 | 0.0185 | 0.0185 | 0.5548 |
118
+ | 0.02 | 1.3415 | 6600 | 0.0183 | 0.0183 | 0.5558 |
119
+ | 0.0196 | 1.3618 | 6700 | 0.0180 | 0.0180 | 0.5626 |
120
+ | 0.0199 | 1.3821 | 6800 | 0.0184 | 0.0184 | 0.5552 |
121
+ | 0.0194 | 1.4024 | 6900 | 0.0185 | 0.0185 | 0.5627 |
122
+ | 0.019 | 1.4228 | 7000 | 0.0180 | 0.0180 | 0.5654 |
123
+ | 0.0191 | 1.4431 | 7100 | 0.0180 | 0.0180 | 0.5646 |
124
+ | 0.0202 | 1.4634 | 7200 | 0.0183 | 0.0183 | 0.5625 |
125
+ | 0.0192 | 1.4837 | 7300 | 0.0187 | 0.0187 | 0.5589 |
126
+ | 0.0202 | 1.5041 | 7400 | 0.0180 | 0.0180 | 0.5597 |
127
+ | 0.02 | 1.5244 | 7500 | 0.0183 | 0.0183 | 0.5602 |
128
+ | 0.0201 | 1.5447 | 7600 | 0.0178 | 0.0178 | 0.5695 |
129
+ | 0.0192 | 1.5650 | 7700 | 0.0178 | 0.0178 | 0.5697 |
130
+ | 0.0179 | 1.5854 | 7800 | 0.0178 | 0.0178 | 0.5688 |
131
+ | 0.0177 | 1.6057 | 7900 | 0.0181 | 0.0181 | 0.5636 |
132
+ | 0.0192 | 1.6260 | 8000 | 0.0179 | 0.0179 | 0.5680 |
133
+ | 0.0195 | 1.6463 | 8100 | 0.0180 | 0.0180 | 0.5637 |
134
+ | 0.0185 | 1.6667 | 8200 | 0.0179 | 0.0179 | 0.5609 |
135
+ | 0.0191 | 1.6870 | 8300 | 0.0177 | 0.0177 | 0.5723 |
136
+ | 0.0185 | 1.7073 | 8400 | 0.0176 | 0.0176 | 0.5735 |
137
+ | 0.019 | 1.7276 | 8500 | 0.0178 | 0.0178 | 0.5695 |
138
+ | 0.0187 | 1.7480 | 8600 | 0.0175 | 0.0175 | 0.5768 |
139
+ | 0.0168 | 1.7683 | 8700 | 0.0173 | 0.0173 | 0.5776 |
140
+ | 0.0168 | 1.7886 | 8800 | 0.0169 | 0.0169 | 0.5865 |
141
+ | 0.0178 | 1.8089 | 8900 | 0.0170 | 0.0170 | 0.5886 |
142
+ | 0.0175 | 1.8293 | 9000 | 0.0171 | 0.0171 | 0.5932 |
143
+ | 0.0175 | 1.8496 | 9100 | 0.0175 | 0.0175 | 0.5744 |
144
+ | 0.0169 | 1.8699 | 9200 | 0.0168 | 0.0168 | 0.5952 |
145
+ | 0.0183 | 1.8902 | 9300 | 0.0166 | 0.0166 | 0.6016 |
146
+ | 0.0162 | 1.9106 | 9400 | 0.0164 | 0.0164 | 0.6034 |
147
+ | 0.0167 | 1.9309 | 9500 | 0.0163 | 0.0163 | 0.6039 |
148
+ | 0.0167 | 1.9512 | 9600 | 0.0166 | 0.0166 | 0.6031 |
149
+ | 0.0166 | 1.9715 | 9700 | 0.0163 | 0.0163 | 0.6064 |
150
+ | 0.0169 | 1.9919 | 9800 | 0.0165 | 0.0165 | 0.6034 |
151
+ | 0.0162 | 2.0122 | 9900 | 0.0161 | 0.0161 | 0.6103 |
152
+ | 0.016 | 2.0325 | 10000 | 0.0167 | 0.0167 | 0.6069 |
153
+ | 0.0152 | 2.0528 | 10100 | 0.0163 | 0.0163 | 0.6030 |
154
+ | 0.016 | 2.0732 | 10200 | 0.0158 | 0.0158 | 0.6184 |
155
+ | 0.0161 | 2.0935 | 10300 | 0.0160 | 0.0160 | 0.6165 |
156
+ | 0.0167 | 2.1138 | 10400 | 0.0156 | 0.0156 | 0.6176 |
157
+ | 0.0155 | 2.1341 | 10500 | 0.0158 | 0.0158 | 0.6212 |
158
+ | 0.0144 | 2.1545 | 10600 | 0.0156 | 0.0156 | 0.6219 |
159
+ | 0.0145 | 2.1748 | 10700 | 0.0160 | 0.0160 | 0.6131 |
160
+ | 0.0158 | 2.1951 | 10800 | 0.0161 | 0.0161 | 0.6085 |
161
+ | 0.0159 | 2.2154 | 10900 | 0.0156 | 0.0156 | 0.6200 |
162
+ | 0.0143 | 2.2358 | 11000 | 0.0156 | 0.0156 | 0.6192 |
163
+ | 0.0158 | 2.2561 | 11100 | 0.0158 | 0.0158 | 0.6173 |
164
+ | 0.015 | 2.2764 | 11200 | 0.0157 | 0.0157 | 0.6234 |
165
+ | 0.0156 | 2.2967 | 11300 | 0.0153 | 0.0153 | 0.6251 |
166
+ | 0.0143 | 2.3171 | 11400 | 0.0155 | 0.0155 | 0.6215 |
167
+ | 0.0159 | 2.3374 | 11500 | 0.0159 | 0.0159 | 0.6101 |
168
+ | 0.0155 | 2.3577 | 11600 | 0.0155 | 0.0155 | 0.6292 |
169
+ | 0.0145 | 2.3780 | 11700 | 0.0153 | 0.0153 | 0.6271 |
170
+ | 0.014 | 2.3984 | 11800 | 0.0152 | 0.0152 | 0.6296 |
171
+ | 0.0154 | 2.4187 | 11900 | 0.0151 | 0.0151 | 0.6282 |
172
+ | 0.0155 | 2.4390 | 12000 | 0.0154 | 0.0154 | 0.6190 |
173
+ | 0.0151 | 2.4593 | 12100 | 0.0158 | 0.0158 | 0.6152 |
174
+ | 0.0156 | 2.4797 | 12200 | 0.0152 | 0.0152 | 0.6301 |
175
+ | 0.0148 | 2.5 | 12300 | 0.0150 | 0.0150 | 0.6332 |
176
+ | 0.0148 | 2.5203 | 12400 | 0.0149 | 0.0149 | 0.6326 |
177
+ | 0.0161 | 2.5407 | 12500 | 0.0154 | 0.0154 | 0.6279 |
178
+ | 0.0143 | 2.5610 | 12600 | 0.0148 | 0.0148 | 0.6392 |
179
+ | 0.0143 | 2.5813 | 12700 | 0.0151 | 0.0151 | 0.6325 |
180
+ | 0.0141 | 2.6016 | 12800 | 0.0154 | 0.0154 | 0.6281 |
181
+ | 0.0148 | 2.6220 | 12900 | 0.0149 | 0.0149 | 0.6323 |
182
+ | 0.016 | 2.6423 | 13000 | 0.0155 | 0.0155 | 0.6230 |
183
+ | 0.0154 | 2.6626 | 13100 | 0.0156 | 0.0156 | 0.6211 |
184
+ | 0.0147 | 2.6829 | 13200 | 0.0151 | 0.0151 | 0.6320 |
185
+ | 0.0152 | 2.7033 | 13300 | 0.0153 | 0.0153 | 0.6253 |
186
+ | 0.0153 | 2.7236 | 13400 | 0.0155 | 0.0155 | 0.6275 |
187
+ | 0.0153 | 2.7439 | 13500 | 0.0147 | 0.0147 | 0.6431 |
188
+ | 0.0148 | 2.7642 | 13600 | 0.0154 | 0.0154 | 0.6322 |
189
+ | 0.0134 | 2.7846 | 13700 | 0.0153 | 0.0153 | 0.6272 |
190
+ | 0.0165 | 2.8049 | 13800 | 0.0149 | 0.0149 | 0.6357 |
191
+ | 0.014 | 2.8252 | 13900 | 0.0150 | 0.0150 | 0.6340 |
192
+ | 0.014 | 2.8455 | 14000 | 0.0149 | 0.0149 | 0.6318 |
193
+ | 0.0145 | 2.8659 | 14100 | 0.0151 | 0.0151 | 0.6353 |
194
+ | 0.0139 | 2.8862 | 14200 | 0.0149 | 0.0149 | 0.6367 |
195
+ | 0.0155 | 2.9065 | 14300 | 0.0151 | 0.0151 | 0.6354 |
196
+ | 0.015 | 2.9268 | 14400 | 0.0146 | 0.0146 | 0.6405 |
197
+ | 0.0145 | 2.9472 | 14500 | 0.0149 | 0.0149 | 0.6368 |
198
+ | 0.0142 | 2.9675 | 14600 | 0.0150 | 0.0150 | 0.6296 |
199
+ | 0.015 | 2.9878 | 14700 | 0.0147 | 0.0147 | 0.6433 |
200
+ | 0.0155 | 3.0081 | 14800 | 0.0147 | 0.0147 | 0.6400 |
201
+ | 0.0147 | 3.0285 | 14900 | 0.0146 | 0.0146 | 0.6363 |
202
+ | 0.0127 | 3.0488 | 15000 | 0.0147 | 0.0147 | 0.6406 |
203
+ | 0.0132 | 3.0691 | 15100 | 0.0146 | 0.0146 | 0.6417 |
204
+ | 0.014 | 3.0894 | 15200 | 0.0146 | 0.0146 | 0.6375 |
205
+ | 0.0139 | 3.1098 | 15300 | 0.0146 | 0.0146 | 0.6435 |
206
+ | 0.0152 | 3.1301 | 15400 | 0.0149 | 0.0149 | 0.6333 |
207
+ | 0.0145 | 3.1504 | 15500 | 0.0146 | 0.0146 | 0.6417 |
208
+ | 0.0136 | 3.1707 | 15600 | 0.0145 | 0.0145 | 0.6467 |
209
+ | 0.0143 | 3.1911 | 15700 | 0.0149 | 0.0149 | 0.6386 |
210
+ | 0.014 | 3.2114 | 15800 | 0.0147 | 0.0147 | 0.6458 |
211
+ | 0.0142 | 3.2317 | 15900 | 0.0143 | 0.0143 | 0.6479 |
212
+ | 0.0137 | 3.2520 | 16000 | 0.0148 | 0.0148 | 0.6387 |
213
+ | 0.0135 | 3.2724 | 16100 | 0.0147 | 0.0147 | 0.6394 |
214
+ | 0.0151 | 3.2927 | 16200 | 0.0144 | 0.0144 | 0.6465 |
215
+ | 0.0154 | 3.3130 | 16300 | 0.0142 | 0.0142 | 0.6553 |
216
+ | 0.0139 | 3.3333 | 16400 | 0.0149 | 0.0149 | 0.6360 |
217
+ | 0.0137 | 3.3537 | 16500 | 0.0145 | 0.0145 | 0.6458 |
218
+ | 0.0141 | 3.3740 | 16600 | 0.0145 | 0.0145 | 0.6468 |
219
+ | 0.0139 | 3.3943 | 16700 | 0.0148 | 0.0148 | 0.6402 |
220
+ | 0.0132 | 3.4146 | 16800 | 0.0149 | 0.0149 | 0.6424 |
221
+ | 0.0133 | 3.4350 | 16900 | 0.0147 | 0.0147 | 0.6423 |
222
+ | 0.0137 | 3.4553 | 17000 | 0.0143 | 0.0143 | 0.6493 |
223
+ | 0.0142 | 3.4756 | 17100 | 0.0146 | 0.0146 | 0.6462 |
224
+ | 0.0138 | 3.4959 | 17200 | 0.0143 | 0.0143 | 0.6470 |
225
+ | 0.0149 | 3.5163 | 17300 | 0.0145 | 0.0145 | 0.6511 |
226
+ | 0.0148 | 3.5366 | 17400 | 0.0145 | 0.0145 | 0.6469 |
227
+ | 0.0138 | 3.5569 | 17500 | 0.0144 | 0.0144 | 0.6437 |
228
+ | 0.0136 | 3.5772 | 17600 | 0.0143 | 0.0143 | 0.6526 |
229
+ | 0.0139 | 3.5976 | 17700 | 0.0143 | 0.0143 | 0.6494 |
230
+ | 0.0126 | 3.6179 | 17800 | 0.0143 | 0.0143 | 0.6523 |
231
+ | 0.0127 | 3.6382 | 17900 | 0.0144 | 0.0144 | 0.6456 |
232
+ | 0.0133 | 3.6585 | 18000 | 0.0143 | 0.0143 | 0.6499 |
233
+ | 0.0141 | 3.6789 | 18100 | 0.0142 | 0.0142 | 0.6527 |
234
+ | 0.0124 | 3.6992 | 18200 | 0.0146 | 0.0146 | 0.6429 |
235
+ | 0.0139 | 3.7195 | 18300 | 0.0142 | 0.0142 | 0.6493 |
236
+ | 0.0141 | 3.7398 | 18400 | 0.0142 | 0.0142 | 0.6512 |
237
+ | 0.0132 | 3.7602 | 18500 | 0.0143 | 0.0143 | 0.6490 |
238
+ | 0.0141 | 3.7805 | 18600 | 0.0144 | 0.0144 | 0.6432 |
239
+ | 0.0131 | 3.8008 | 18700 | 0.0142 | 0.0142 | 0.6519 |
240
+ | 0.0135 | 3.8211 | 18800 | 0.0147 | 0.0147 | 0.6442 |
241
+ | 0.0149 | 3.8415 | 18900 | 0.0147 | 0.0147 | 0.6422 |
242
+ | 0.0141 | 3.8618 | 19000 | 0.0142 | 0.0142 | 0.6547 |
243
+ | 0.0132 | 3.8821 | 19100 | 0.0143 | 0.0143 | 0.6489 |
244
+ | 0.0141 | 3.9024 | 19200 | 0.0143 | 0.0143 | 0.6494 |
245
+ | 0.0123 | 3.9228 | 19300 | 0.0140 | 0.0140 | 0.6559 |
246
+ | 0.0139 | 3.9431 | 19400 | 0.0142 | 0.0142 | 0.6535 |
247
+ | 0.0138 | 3.9634 | 19500 | 0.0144 | 0.0144 | 0.6457 |
248
+ | 0.0131 | 3.9837 | 19600 | 0.0142 | 0.0142 | 0.6477 |
249
+ | 0.0128 | 4.0041 | 19700 | 0.0145 | 0.0145 | 0.6453 |
250
+ | 0.0128 | 4.0244 | 19800 | 0.0142 | 0.0142 | 0.6516 |
251
+ | 0.0127 | 4.0447 | 19900 | 0.0141 | 0.0141 | 0.6517 |
252
+ | 0.0137 | 4.0650 | 20000 | 0.0147 | 0.0147 | 0.6458 |
253
+ | 0.0137 | 4.0854 | 20100 | 0.0142 | 0.0142 | 0.6535 |
254
+ | 0.013 | 4.1057 | 20200 | 0.0146 | 0.0146 | 0.6506 |
255
+ | 0.0134 | 4.1260 | 20300 | 0.0149 | 0.0149 | 0.6443 |
256
+ | 0.0135 | 4.1463 | 20400 | 0.0145 | 0.0145 | 0.6495 |
257
+ | 0.0139 | 4.1667 | 20500 | 0.0140 | 0.0140 | 0.6597 |
258
+ | 0.014 | 4.1870 | 20600 | 0.0147 | 0.0147 | 0.6421 |
259
+ | 0.0135 | 4.2073 | 20700 | 0.0145 | 0.0145 | 0.6438 |
260
+ | 0.0127 | 4.2276 | 20800 | 0.0143 | 0.0143 | 0.6502 |
261
+ | 0.0124 | 4.2480 | 20900 | 0.0141 | 0.0141 | 0.6558 |
262
+ | 0.0139 | 4.2683 | 21000 | 0.0143 | 0.0143 | 0.6509 |
263
+ | 0.013 | 4.2886 | 21100 | 0.0141 | 0.0141 | 0.6591 |
264
+ | 0.0129 | 4.3089 | 21200 | 0.0143 | 0.0143 | 0.6497 |
265
+ | 0.0122 | 4.3293 | 21300 | 0.0148 | 0.0148 | 0.6440 |
266
+ | 0.0135 | 4.3496 | 21400 | 0.0142 | 0.0142 | 0.6550 |
267
+ | 0.0117 | 4.3699 | 21500 | 0.0142 | 0.0142 | 0.6516 |
268
+ | 0.0105 | 4.3902 | 21600 | 0.0146 | 0.0146 | 0.6420 |
269
+ | 0.0142 | 4.4106 | 21700 | 0.0146 | 0.0146 | 0.6451 |
270
+ | 0.0132 | 4.4309 | 21800 | 0.0143 | 0.0143 | 0.6504 |
271
+ | 0.0134 | 4.4512 | 21900 | 0.0139 | 0.0139 | 0.6580 |
272
+ | 0.0107 | 4.4715 | 22000 | 0.0147 | 0.0147 | 0.6431 |
273
+ | 0.0133 | 4.4919 | 22100 | 0.0142 | 0.0142 | 0.6533 |
274
+ | 0.0124 | 4.5122 | 22200 | 0.0141 | 0.0141 | 0.6564 |
275
+ | 0.011 | 4.5325 | 22300 | 0.0139 | 0.0139 | 0.6608 |
276
+ | 0.011 | 4.5528 | 22400 | 0.0141 | 0.0141 | 0.6551 |
277
+ | 0.0131 | 4.5732 | 22500 | 0.0144 | 0.0144 | 0.6532 |
278
+ | 0.0112 | 4.5935 | 22600 | 0.0143 | 0.0143 | 0.6521 |
279
+ | 0.0116 | 4.6138 | 22700 | 0.0140 | 0.0140 | 0.6558 |
280
+ | 0.01 | 4.6341 | 22800 | 0.0143 | 0.0143 | 0.6469 |
281
+ | 0.0112 | 4.6545 | 22900 | 0.0141 | 0.0141 | 0.6540 |
282
+ | 0.0115 | 4.6748 | 23000 | 0.0140 | 0.0140 | 0.6519 |
283
+ | 0.0107 | 4.6951 | 23100 | 0.0141 | 0.0141 | 0.6545 |
284
+ | 0.011 | 4.7154 | 23200 | 0.0141 | 0.0141 | 0.6525 |
285
+ | 0.0119 | 4.7358 | 23300 | 0.0139 | 0.0139 | 0.6609 |
286
+ | 0.013 | 4.7561 | 23400 | 0.0138 | 0.0138 | 0.6587 |
287
+ | 0.0107 | 4.7764 | 23500 | 0.0136 | 0.0136 | 0.6665 |
288
+ | 0.0111 | 4.7967 | 23600 | 0.0136 | 0.0136 | 0.6634 |
289
+ | 0.0111 | 4.8171 | 23700 | 0.0140 | 0.0140 | 0.6565 |
290
+ | 0.0106 | 4.8374 | 23800 | 0.0139 | 0.0139 | 0.6587 |
291
+ | 0.0114 | 4.8577 | 23900 | 0.0140 | 0.0140 | 0.6575 |
292
+ | 0.011 | 4.8780 | 24000 | 0.0142 | 0.0142 | 0.6575 |
293
+ | 0.0115 | 4.8984 | 24100 | 0.0139 | 0.0139 | 0.6612 |
294
+ | 0.012 | 4.9187 | 24200 | 0.0136 | 0.0136 | 0.6683 |
295
+ | 0.0123 | 4.9390 | 24300 | 0.0137 | 0.0137 | 0.6659 |
296
+ | 0.0118 | 4.9593 | 24400 | 0.0144 | 0.0144 | 0.6548 |
297
+ | 0.01 | 4.9797 | 24500 | 0.0140 | 0.0140 | 0.6594 |
298
+ | 0.0112 | 5.0 | 24600 | 0.0136 | 0.0136 | 0.6662 |
299
+ | 0.0108 | 5.0203 | 24700 | 0.0140 | 0.0140 | 0.6605 |
300
+ | 0.0103 | 5.0407 | 24800 | 0.0138 | 0.0138 | 0.6636 |
301
+ | 0.0124 | 5.0610 | 24900 | 0.0137 | 0.0137 | 0.6645 |
302
+ | 0.0116 | 5.0813 | 25000 | 0.0141 | 0.0141 | 0.6558 |
303
+ | 0.009 | 5.1016 | 25100 | 0.0138 | 0.0138 | 0.6637 |
304
+ | 0.0111 | 5.1220 | 25200 | 0.0140 | 0.0140 | 0.6594 |
305
+ | 0.0119 | 5.1423 | 25300 | 0.0139 | 0.0139 | 0.6584 |
306
+ | 0.011 | 5.1626 | 25400 | 0.0138 | 0.0138 | 0.6649 |
307
+ | 0.0111 | 5.1829 | 25500 | 0.0137 | 0.0137 | 0.6660 |
308
+ | 0.0115 | 5.2033 | 25600 | 0.0138 | 0.0138 | 0.6654 |
309
+ | 0.0113 | 5.2236 | 25700 | 0.0138 | 0.0138 | 0.6615 |
310
+ | 0.01 | 5.2439 | 25800 | 0.0142 | 0.0142 | 0.6558 |
311
+ | 0.0114 | 5.2642 | 25900 | 0.0137 | 0.0137 | 0.6656 |
312
+ | 0.0097 | 5.2846 | 26000 | 0.0138 | 0.0138 | 0.6620 |
313
+ | 0.0094 | 5.3049 | 26100 | 0.0136 | 0.0136 | 0.6663 |
314
+ | 0.0111 | 5.3252 | 26200 | 0.0137 | 0.0137 | 0.6638 |
315
+ | 0.0114 | 5.3455 | 26300 | 0.0142 | 0.0142 | 0.6554 |
316
+ | 0.0107 | 5.3659 | 26400 | 0.0137 | 0.0137 | 0.6619 |
317
+ | 0.0115 | 5.3862 | 26500 | 0.0137 | 0.0137 | 0.6645 |
318
+ | 0.0112 | 5.4065 | 26600 | 0.0134 | 0.0134 | 0.6712 |
319
+ | 0.0106 | 5.4268 | 26700 | 0.0134 | 0.0134 | 0.6691 |
320
+ | 0.011 | 5.4472 | 26800 | 0.0134 | 0.0134 | 0.6713 |
321
+ | 0.0116 | 5.4675 | 26900 | 0.0136 | 0.0136 | 0.6682 |
322
+ | 0.0111 | 5.4878 | 27000 | 0.0134 | 0.0134 | 0.6695 |
323
+ | 0.0111 | 5.5081 | 27100 | 0.0136 | 0.0136 | 0.6686 |
324
+ | 0.0106 | 5.5285 | 27200 | 0.0135 | 0.0135 | 0.6719 |
325
+ | 0.011 | 5.5488 | 27300 | 0.0138 | 0.0138 | 0.6628 |
326
+ | 0.0094 | 5.5691 | 27400 | 0.0135 | 0.0135 | 0.6687 |
327
+ | 0.0102 | 5.5894 | 27500 | 0.0138 | 0.0138 | 0.6641 |
328
+ | 0.0104 | 5.6098 | 27600 | 0.0135 | 0.0135 | 0.6703 |
329
+ | 0.01 | 5.6301 | 27700 | 0.0136 | 0.0136 | 0.6708 |
330
+ | 0.0104 | 5.6504 | 27800 | 0.0136 | 0.0136 | 0.6688 |
331
+ | 0.0102 | 5.6707 | 27900 | 0.0136 | 0.0136 | 0.6682 |
332
+ | 0.0108 | 5.6911 | 28000 | 0.0138 | 0.0138 | 0.6614 |
333
+ | 0.0108 | 5.7114 | 28100 | 0.0135 | 0.0135 | 0.6716 |
334
+ | 0.0103 | 5.7317 | 28200 | 0.0137 | 0.0137 | 0.6650 |
335
+ | 0.0105 | 5.7520 | 28300 | 0.0136 | 0.0136 | 0.6679 |
336
+ | 0.0108 | 5.7724 | 28400 | 0.0135 | 0.0135 | 0.6693 |
337
+ | 0.0102 | 5.7927 | 28500 | 0.0133 | 0.0133 | 0.6745 |
338
+ | 0.0111 | 5.8130 | 28600 | 0.0133 | 0.0133 | 0.6745 |
339
+ | 0.0102 | 5.8333 | 28700 | 0.0134 | 0.0134 | 0.6703 |
340
+ | 0.0087 | 5.8537 | 28800 | 0.0137 | 0.0137 | 0.6660 |
341
+ | 0.0114 | 5.8740 | 28900 | 0.0136 | 0.0136 | 0.6686 |
342
+ | 0.0114 | 5.8943 | 29000 | 0.0134 | 0.0134 | 0.6739 |
343
+ | 0.0098 | 5.9146 | 29100 | 0.0134 | 0.0134 | 0.6724 |
344
+ | 0.0097 | 5.9350 | 29200 | 0.0132 | 0.0132 | 0.6767 |
345
+ | 0.0108 | 5.9553 | 29300 | 0.0131 | 0.0131 | 0.6803 |
346
+ | 0.0106 | 5.9756 | 29400 | 0.0132 | 0.0132 | 0.6775 |
347
+ | 0.0112 | 5.9959 | 29500 | 0.0133 | 0.0133 | 0.6763 |
348
+ | 0.0096 | 6.0163 | 29600 | 0.0134 | 0.0134 | 0.6706 |
349
+ | 0.0105 | 6.0366 | 29700 | 0.0141 | 0.0141 | 0.6561 |
350
+ | 0.0115 | 6.0569 | 29800 | 0.0132 | 0.0132 | 0.6745 |
351
+ | 0.01 | 6.0772 | 29900 | 0.0132 | 0.0132 | 0.6782 |
352
+ | 0.0114 | 6.0976 | 30000 | 0.0133 | 0.0133 | 0.6737 |
353
+ | 0.0116 | 6.1179 | 30100 | 0.0132 | 0.0132 | 0.6771 |
354
+ | 0.0095 | 6.1382 | 30200 | 0.0135 | 0.0135 | 0.6688 |
355
+ | 0.01 | 6.1585 | 30300 | 0.0134 | 0.0134 | 0.6682 |
356
+ | 0.01 | 6.1789 | 30400 | 0.0132 | 0.0132 | 0.6756 |
357
+ | 0.0106 | 6.1992 | 30500 | 0.0134 | 0.0134 | 0.6726 |
358
+ | 0.0092 | 6.2195 | 30600 | 0.0131 | 0.0131 | 0.6755 |
359
+ | 0.0117 | 6.2398 | 30700 | 0.0133 | 0.0133 | 0.6723 |
360
+ | 0.0098 | 6.2602 | 30800 | 0.0131 | 0.0131 | 0.6748 |
361
+ | 0.0103 | 6.2805 | 30900 | 0.0132 | 0.0132 | 0.6757 |
362
+ | 0.0097 | 6.3008 | 31000 | 0.0135 | 0.0135 | 0.6682 |
363
+ | 0.0103 | 6.3211 | 31100 | 0.0134 | 0.0134 | 0.6726 |
364
+ | 0.0101 | 6.3415 | 31200 | 0.0134 | 0.0134 | 0.6712 |
365
+ | 0.0107 | 6.3618 | 31300 | 0.0132 | 0.0132 | 0.6773 |
366
+ | 0.01 | 6.3821 | 31400 | 0.0133 | 0.0133 | 0.6740 |
367
+ | 0.0097 | 6.4024 | 31500 | 0.0136 | 0.0136 | 0.6704 |
368
+ | 0.0108 | 6.4228 | 31600 | 0.0132 | 0.0132 | 0.6764 |
369
+ | 0.0104 | 6.4431 | 31700 | 0.0131 | 0.0131 | 0.6784 |
370
+ | 0.0123 | 6.4634 | 31800 | 0.0133 | 0.0133 | 0.6725 |
371
+ | 0.0097 | 6.4837 | 31900 | 0.0134 | 0.0134 | 0.6703 |
372
+ | 0.0097 | 6.5041 | 32000 | 0.0133 | 0.0133 | 0.6725 |
373
+ | 0.009 | 6.5244 | 32100 | 0.0130 | 0.0130 | 0.6829 |
374
+ | 0.0116 | 6.5447 | 32200 | 0.0133 | 0.0133 | 0.6731 |
375
+ | 0.0099 | 6.5650 | 32300 | 0.0132 | 0.0132 | 0.6760 |
376
+ | 0.0108 | 6.5854 | 32400 | 0.0133 | 0.0133 | 0.6754 |
377
+ | 0.0103 | 6.6057 | 32500 | 0.0136 | 0.0136 | 0.6701 |
378
+ | 0.0092 | 6.6260 | 32600 | 0.0132 | 0.0132 | 0.6782 |
379
+ | 0.0105 | 6.6463 | 32700 | 0.0130 | 0.0130 | 0.6814 |
380
+ | 0.011 | 6.6667 | 32800 | 0.0133 | 0.0133 | 0.6734 |
381
+ | 0.0102 | 6.6870 | 32900 | 0.0132 | 0.0132 | 0.6750 |
382
+ | 0.0103 | 6.7073 | 33000 | 0.0132 | 0.0132 | 0.6766 |
383
+ | 0.0112 | 6.7276 | 33100 | 0.0131 | 0.0131 | 0.6788 |
384
+ | 0.0089 | 6.7480 | 33200 | 0.0131 | 0.0131 | 0.6773 |
385
+ | 0.0103 | 6.7683 | 33300 | 0.0131 | 0.0131 | 0.6752 |
386
+ | 0.0109 | 6.7886 | 33400 | 0.0133 | 0.0133 | 0.6761 |
387
+ | 0.0078 | 6.8089 | 33500 | 0.0131 | 0.0131 | 0.6778 |
388
+ | 0.011 | 6.8293 | 33600 | 0.0130 | 0.0130 | 0.6823 |
389
+ | 0.0085 | 6.8496 | 33700 | 0.0129 | 0.0129 | 0.6815 |
390
+ | 0.009 | 6.8699 | 33800 | 0.0131 | 0.0131 | 0.6770 |
391
+ | 0.0093 | 6.8902 | 33900 | 0.0131 | 0.0131 | 0.6769 |
392
+ | 0.01 | 6.9106 | 34000 | 0.0132 | 0.0132 | 0.6750 |
393
+ | 0.0097 | 6.9309 | 34100 | 0.0131 | 0.0131 | 0.6791 |
394
+ | 0.0107 | 6.9512 | 34200 | 0.0130 | 0.0130 | 0.6824 |
395
+ | 0.0099 | 6.9715 | 34300 | 0.0130 | 0.0130 | 0.6815 |
396
+ | 0.0095 | 6.9919 | 34400 | 0.0130 | 0.0130 | 0.6822 |
397
+ | 0.01 | 7.0122 | 34500 | 0.0129 | 0.0129 | 0.6827 |
398
+ | 0.0097 | 7.0325 | 34600 | 0.0131 | 0.0131 | 0.6801 |
399
+ | 0.0099 | 7.0528 | 34700 | 0.0129 | 0.0129 | 0.6843 |
400
+ | 0.0085 | 7.0732 | 34800 | 0.0132 | 0.0132 | 0.6774 |
401
+ | 0.0098 | 7.0935 | 34900 | 0.0131 | 0.0131 | 0.6780 |
402
+ | 0.0103 | 7.1138 | 35000 | 0.0130 | 0.0130 | 0.6811 |
403
+ | 0.0104 | 7.1341 | 35100 | 0.0127 | 0.0127 | 0.6857 |
404
+ | 0.0094 | 7.1545 | 35200 | 0.0130 | 0.0130 | 0.6812 |
405
+ | 0.0104 | 7.1748 | 35300 | 0.0132 | 0.0132 | 0.6768 |
406
+ | 0.0092 | 7.1951 | 35400 | 0.0130 | 0.0130 | 0.6819 |
407
+ | 0.0099 | 7.2154 | 35500 | 0.0130 | 0.0130 | 0.6810 |
408
+ | 0.0103 | 7.2358 | 35600 | 0.0132 | 0.0132 | 0.6791 |
409
+ | 0.0103 | 7.2561 | 35700 | 0.0135 | 0.0135 | 0.6734 |
410
+ | 0.0081 | 7.2764 | 35800 | 0.0133 | 0.0133 | 0.6753 |
411
+ | 0.0079 | 7.2967 | 35900 | 0.0131 | 0.0131 | 0.6788 |
412
+ | 0.009 | 7.3171 | 36000 | 0.0130 | 0.0130 | 0.6826 |
413
+ | 0.0096 | 7.3374 | 36100 | 0.0130 | 0.0130 | 0.6829 |
414
+ | 0.0103 | 7.3577 | 36200 | 0.0132 | 0.0132 | 0.6821 |
415
+ | 0.0098 | 7.3780 | 36300 | 0.0130 | 0.0130 | 0.6821 |
416
+ | 0.0102 | 7.3984 | 36400 | 0.0130 | 0.0130 | 0.6830 |
417
+ | 0.0093 | 7.4187 | 36500 | 0.0133 | 0.0133 | 0.6756 |
418
+ | 0.0107 | 7.4390 | 36600 | 0.0131 | 0.0131 | 0.6801 |
419
+ | 0.01 | 7.4593 | 36700 | 0.0128 | 0.0128 | 0.6862 |
420
+ | 0.0101 | 7.4797 | 36800 | 0.0132 | 0.0132 | 0.6817 |
421
+ | 0.0088 | 7.5 | 36900 | 0.0130 | 0.0130 | 0.6823 |
422
+ | 0.0097 | 7.5203 | 37000 | 0.0130 | 0.0130 | 0.6828 |
423
+ | 0.0087 | 7.5407 | 37100 | 0.0129 | 0.0129 | 0.6859 |
424
+ | 0.008 | 7.5610 | 37200 | 0.0129 | 0.0129 | 0.6848 |
425
+ | 0.0096 | 7.5813 | 37300 | 0.0128 | 0.0128 | 0.6869 |
426
+ | 0.0092 | 7.6016 | 37400 | 0.0128 | 0.0128 | 0.6856 |
427
+ | 0.0101 | 7.6220 | 37500 | 0.0130 | 0.0130 | 0.6827 |
428
+ | 0.0102 | 7.6423 | 37600 | 0.0130 | 0.0130 | 0.6792 |
429
+ | 0.0097 | 7.6626 | 37700 | 0.0129 | 0.0129 | 0.6806 |
430
+ | 0.0106 | 7.6829 | 37800 | 0.0128 | 0.0128 | 0.6852 |
431
+ | 0.0087 | 7.7033 | 37900 | 0.0129 | 0.0129 | 0.6847 |
432
+ | 0.0091 | 7.7236 | 38000 | 0.0129 | 0.0129 | 0.6851 |
433
+ | 0.0099 | 7.7439 | 38100 | 0.0128 | 0.0128 | 0.6845 |
434
+ | 0.0094 | 7.7642 | 38200 | 0.0128 | 0.0128 | 0.6857 |
435
+ | 0.0097 | 7.7846 | 38300 | 0.0128 | 0.0128 | 0.6858 |
436
+ | 0.0108 | 7.8049 | 38400 | 0.0127 | 0.0127 | 0.6855 |
437
+ | 0.011 | 7.8252 | 38500 | 0.0128 | 0.0128 | 0.6836 |
438
+ | 0.0088 | 7.8455 | 38600 | 0.0129 | 0.0129 | 0.6826 |
439
+ | 0.0093 | 7.8659 | 38700 | 0.0131 | 0.0131 | 0.6796 |
440
+ | 0.0096 | 7.8862 | 38800 | 0.0129 | 0.0129 | 0.6830 |
441
+ | 0.0089 | 7.9065 | 38900 | 0.0128 | 0.0128 | 0.6855 |
442
+ | 0.0088 | 7.9268 | 39000 | 0.0128 | 0.0128 | 0.6879 |
443
+ | 0.0088 | 7.9472 | 39100 | 0.0127 | 0.0127 | 0.6897 |
444
+ | 0.0088 | 7.9675 | 39200 | 0.0129 | 0.0129 | 0.6840 |
445
+ | 0.0102 | 7.9878 | 39300 | 0.0127 | 0.0127 | 0.6878 |
446
+ | 0.008 | 8.0081 | 39400 | 0.0128 | 0.0128 | 0.6867 |
447
+ | 0.0106 | 8.0285 | 39500 | 0.0130 | 0.0130 | 0.6817 |
448
+ | 0.0089 | 8.0488 | 39600 | 0.0129 | 0.0129 | 0.6838 |
449
+ | 0.0084 | 8.0691 | 39700 | 0.0129 | 0.0129 | 0.6847 |
450
+ | 0.0089 | 8.0894 | 39800 | 0.0128 | 0.0128 | 0.6860 |
451
+ | 0.0095 | 8.1098 | 39900 | 0.0128 | 0.0128 | 0.6851 |
452
+ | 0.0085 | 8.1301 | 40000 | 0.0127 | 0.0127 | 0.6872 |
453
+ | 0.0084 | 8.1504 | 40100 | 0.0129 | 0.0129 | 0.6840 |
454
+ | 0.0084 | 8.1707 | 40200 | 0.0130 | 0.0130 | 0.6804 |
455
+ | 0.0082 | 8.1911 | 40300 | 0.0128 | 0.0128 | 0.6870 |
456
+ | 0.0082 | 8.2114 | 40400 | 0.0127 | 0.0127 | 0.6871 |
457
+ | 0.0114 | 8.2317 | 40500 | 0.0126 | 0.0126 | 0.6900 |
458
+ | 0.0101 | 8.2520 | 40600 | 0.0129 | 0.0129 | 0.6853 |
459
+ | 0.0099 | 8.2724 | 40700 | 0.0127 | 0.0127 | 0.6861 |
460
+ | 0.0087 | 8.2927 | 40800 | 0.0128 | 0.0128 | 0.6850 |
461
+ | 0.0081 | 8.3130 | 40900 | 0.0127 | 0.0127 | 0.6867 |
462
+ | 0.0086 | 8.3333 | 41000 | 0.0127 | 0.0127 | 0.6880 |
463
+ | 0.0095 | 8.3537 | 41100 | 0.0128 | 0.0128 | 0.6867 |
464
+ | 0.0082 | 8.3740 | 41200 | 0.0128 | 0.0128 | 0.6875 |
465
+ | 0.0075 | 8.3943 | 41300 | 0.0128 | 0.0128 | 0.6879 |
466
+ | 0.0095 | 8.4146 | 41400 | 0.0127 | 0.0127 | 0.6882 |
467
+ | 0.0091 | 8.4350 | 41500 | 0.0127 | 0.0127 | 0.6886 |
468
+ | 0.0098 | 8.4553 | 41600 | 0.0128 | 0.0128 | 0.6874 |
469
+ | 0.0099 | 8.4756 | 41700 | 0.0126 | 0.0126 | 0.6907 |
470
+ | 0.0094 | 8.4959 | 41800 | 0.0129 | 0.0129 | 0.6854 |
471
+ | 0.0097 | 8.5163 | 41900 | 0.0127 | 0.0127 | 0.6888 |
472
+ | 0.0104 | 8.5366 | 42000 | 0.0130 | 0.0130 | 0.6856 |
473
+ | 0.0085 | 8.5569 | 42100 | 0.0129 | 0.0129 | 0.6863 |
474
+ | 0.0083 | 8.5772 | 42200 | 0.0129 | 0.0129 | 0.6858 |
475
+ | 0.0085 | 8.5976 | 42300 | 0.0127 | 0.0127 | 0.6897 |
476
+ | 0.0091 | 8.6179 | 42400 | 0.0127 | 0.0127 | 0.6905 |
477
+ | 0.0092 | 8.6382 | 42500 | 0.0126 | 0.0126 | 0.6903 |
478
+ | 0.0097 | 8.6585 | 42600 | 0.0126 | 0.0126 | 0.6901 |
479
+ | 0.0091 | 8.6789 | 42700 | 0.0127 | 0.0127 | 0.6880 |
480
+ | 0.008 | 8.6992 | 42800 | 0.0128 | 0.0128 | 0.6856 |
481
+ | 0.0093 | 8.7195 | 42900 | 0.0128 | 0.0128 | 0.6870 |
482
+ | 0.0096 | 8.7398 | 43000 | 0.0129 | 0.0129 | 0.6853 |
483
+ | 0.0102 | 8.7602 | 43100 | 0.0126 | 0.0126 | 0.6887 |
484
+ | 0.0097 | 8.7805 | 43200 | 0.0127 | 0.0127 | 0.6880 |
485
+ | 0.0092 | 8.8008 | 43300 | 0.0127 | 0.0127 | 0.6885 |
486
+ | 0.0089 | 8.8211 | 43400 | 0.0128 | 0.0128 | 0.6881 |
487
+ | 0.0083 | 8.8415 | 43500 | 0.0127 | 0.0127 | 0.6888 |
488
+ | 0.0089 | 8.8618 | 43600 | 0.0127 | 0.0127 | 0.6887 |
489
+ | 0.0094 | 8.8821 | 43700 | 0.0127 | 0.0127 | 0.6888 |
490
+ | 0.0085 | 8.9024 | 43800 | 0.0127 | 0.0127 | 0.6885 |
491
+ | 0.0108 | 8.9228 | 43900 | 0.0126 | 0.0126 | 0.6907 |
492
+ | 0.0095 | 8.9431 | 44000 | 0.0127 | 0.0127 | 0.6896 |
493
+ | 0.0082 | 8.9634 | 44100 | 0.0126 | 0.0126 | 0.6904 |
494
+ | 0.0089 | 8.9837 | 44200 | 0.0126 | 0.0126 | 0.6913 |
495
+ | 0.0093 | 9.0041 | 44300 | 0.0126 | 0.0126 | 0.6898 |
496
+ | 0.0091 | 9.0244 | 44400 | 0.0126 | 0.0126 | 0.6908 |
497
+ | 0.0091 | 9.0447 | 44500 | 0.0127 | 0.0127 | 0.6896 |
498
+ | 0.0083 | 9.0650 | 44600 | 0.0126 | 0.0126 | 0.6898 |
499
+ | 0.009 | 9.0854 | 44700 | 0.0126 | 0.0126 | 0.6910 |
500
+ | 0.0097 | 9.1057 | 44800 | 0.0126 | 0.0126 | 0.6908 |
501
+ | 0.0072 | 9.1260 | 44900 | 0.0127 | 0.0127 | 0.6877 |
502
+ | 0.0082 | 9.1463 | 45000 | 0.0127 | 0.0127 | 0.6885 |
503
+ | 0.0078 | 9.1667 | 45100 | 0.0127 | 0.0127 | 0.6881 |
504
+ | 0.0088 | 9.1870 | 45200 | 0.0125 | 0.0125 | 0.6914 |
505
+ | 0.0077 | 9.2073 | 45300 | 0.0127 | 0.0127 | 0.6879 |
506
+ | 0.009 | 9.2276 | 45400 | 0.0126 | 0.0126 | 0.6887 |
507
+ | 0.0088 | 9.2480 | 45500 | 0.0127 | 0.0127 | 0.6885 |
508
+ | 0.0089 | 9.2683 | 45600 | 0.0126 | 0.0126 | 0.6915 |
509
+ | 0.0074 | 9.2886 | 45700 | 0.0126 | 0.0126 | 0.6903 |
510
+ | 0.0085 | 9.3089 | 45800 | 0.0126 | 0.0126 | 0.6904 |
511
+ | 0.0091 | 9.3293 | 45900 | 0.0127 | 0.0127 | 0.6892 |
512
+ | 0.0088 | 9.3496 | 46000 | 0.0125 | 0.0125 | 0.6918 |
513
+ | 0.0094 | 9.3699 | 46100 | 0.0127 | 0.0127 | 0.6899 |
514
+ | 0.0098 | 9.3902 | 46200 | 0.0125 | 0.0125 | 0.6931 |
515
+ | 0.0087 | 9.4106 | 46300 | 0.0126 | 0.0126 | 0.6916 |
516
+ | 0.0086 | 9.4309 | 46400 | 0.0126 | 0.0126 | 0.6915 |
517
+ | 0.0084 | 9.4512 | 46500 | 0.0125 | 0.0125 | 0.6931 |
518
+ | 0.0092 | 9.4715 | 46600 | 0.0126 | 0.0126 | 0.6907 |
519
+ | 0.0087 | 9.4919 | 46700 | 0.0125 | 0.0125 | 0.6935 |
520
+ | 0.0085 | 9.5122 | 46800 | 0.0125 | 0.0125 | 0.6938 |
521
+ | 0.0083 | 9.5325 | 46900 | 0.0125 | 0.0125 | 0.6933 |
522
+ | 0.0091 | 9.5528 | 47000 | 0.0126 | 0.0126 | 0.6920 |
523
+ | 0.0082 | 9.5732 | 47100 | 0.0126 | 0.0126 | 0.6912 |
524
+ | 0.0091 | 9.5935 | 47200 | 0.0126 | 0.0126 | 0.6918 |
525
+ | 0.0092 | 9.6138 | 47300 | 0.0126 | 0.0126 | 0.6920 |
526
+ | 0.0086 | 9.6341 | 47400 | 0.0125 | 0.0125 | 0.6930 |
527
+ | 0.0087 | 9.6545 | 47500 | 0.0125 | 0.0125 | 0.6931 |
528
+ | 0.009 | 9.6748 | 47600 | 0.0126 | 0.0126 | 0.6932 |
529
+ | 0.0085 | 9.6951 | 47700 | 0.0125 | 0.0125 | 0.6941 |
530
+ | 0.0093 | 9.7154 | 47800 | 0.0125 | 0.0125 | 0.6930 |
531
+ | 0.009 | 9.7358 | 47900 | 0.0125 | 0.0125 | 0.6930 |
532
+ | 0.0092 | 9.7561 | 48000 | 0.0125 | 0.0125 | 0.6936 |
533
+ | 0.0093 | 9.7764 | 48100 | 0.0125 | 0.0125 | 0.6937 |
534
+ | 0.0101 | 9.7967 | 48200 | 0.0125 | 0.0125 | 0.6935 |
535
+ | 0.0089 | 9.8171 | 48300 | 0.0125 | 0.0125 | 0.6946 |
536
+ | 0.0087 | 9.8374 | 48400 | 0.0125 | 0.0125 | 0.6948 |
537
+ | 0.008 | 9.8577 | 48500 | 0.0125 | 0.0125 | 0.6943 |
538
+ | 0.0089 | 9.8780 | 48600 | 0.0125 | 0.0125 | 0.6944 |
539
+ | 0.0074 | 9.8984 | 48700 | 0.0125 | 0.0125 | 0.6937 |
540
+ | 0.009 | 9.9187 | 48800 | 0.0125 | 0.0125 | 0.6931 |
541
+ | 0.0077 | 9.9390 | 48900 | 0.0125 | 0.0125 | 0.6934 |
542
+ | 0.0078 | 9.9593 | 49000 | 0.0125 | 0.0125 | 0.6937 |
543
+ | 0.0086 | 9.9797 | 49100 | 0.0125 | 0.0125 | 0.6938 |
544
+ | 0.0074 | 10.0 | 49200 | 0.0125 | 0.0125 | 0.6938 |
545
 
 
 
 
546
 
547
+ ### Framework versions
 
548
 
549
+ - Transformers 4.57.3
550
+ - Pytorch 2.9.1+cu128
551
+ - Datasets 4.4.2
552
+ - Tokenizers 0.22.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7126f0f10f71c70c2cc266f497689c7f1ee1b8dbd1f992d4f6513fc2f31e0da6
3
  size 611073224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:776d40ba17a65efc60e14946afc8d537d10a55759277d714380f593d8c55e8d6
3
  size 611073224