Hugging Face's logo

HERIUN
/
wav2vec-bert-korean-dialect-recognition

Audio Classification
Transformers
Safetensors
wav2vec2-bert
Generated from Trainer
Inference Endpoints
Model card Files Community
HERIUN commited on
Commit
4cbb458
·
verified ·
1 Parent(s): b4e47ca

Model save

Browse files
Files changed (2) hide show
  1. README.md +235 -20
  2. model.safetensors +1 -1
README.md CHANGED
@@ -3,10 +3,12 @@ library_name: transformers
3
  license: mit
4
  base_model: facebook/w2v-bert-2.0
5
  tags:
6
- - audio-classification
7
  - generated_from_trainer
8
  metrics:
9
  - accuracy
 
 
 
10
  model-index:
11
  - name: wav2vec-bert-korean-dialect-recognition
12
  results: []
@@ -19,8 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.6935
23
- - Accuracy: 0.7453
 
 
 
24
 
25
  ## Model description
26
 
@@ -40,9 +45,13 @@ More information needed
40
 
41
  The following hyperparameters were used during training:
42
  - learning_rate: 5e-05
43
- - train_batch_size: 4
44
- - eval_batch_size: 4
45
  - seed: 42
 
 
 
 
46
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_steps: 500
@@ -51,23 +60,229 @@ The following hyperparameters were used during training:
51
 
52
  ### Training results
53
 
54
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
55
- |:-------------:|:-----:|:------:|:---------------:|:--------:|
56
- | 1.1772 | 1.0 | 32734 | 0.9692 | 0.6393 |
57
- | 1.1915 | 2.0 | 65468 | 0.8570 | 0.6765 |
58
- | 1.198 | 3.0 | 98202 | 0.7810 | 0.7097 |
59
- | 1.2072 | 4.0 | 130936 | 0.7748 | 0.7121 |
60
- | 1.2897 | 5.0 | 163670 | 0.7394 | 0.7252 |
61
- | 1.206 | 6.0 | 196404 | 0.7457 | 0.7196 |
62
- | 1.0204 | 7.0 | 229138 | 0.7299 | 0.7273 |
63
- | 1.1207 | 8.0 | 261872 | 0.7225 | 0.7330 |
64
- | 1.3417 | 9.0 | 294606 | 0.6936 | 0.7450 |
65
- | 1.1021 | 10.0 | 327340 | 0.7014 | 0.7415 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
66
 
67
 
68
  ### Framework versions
69
 
70
- - Transformers 4.47.1
71
- - Pytorch 2.5.1+cu124
72
- - Datasets 3.2.0
73
  - Tokenizers 0.21.0
 
3
  license: mit
4
  base_model: facebook/w2v-bert-2.0
5
  tags:
 
6
  - generated_from_trainer
7
  metrics:
8
  - accuracy
9
+ - precision
10
+ - recall
11
+ - f1
12
  model-index:
13
  - name: wav2vec-bert-korean-dialect-recognition
14
  results: []
 
21
 
22
  This model is a fine-tuned version of [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0) on an unknown dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 1.1634
25
+ - Accuracy: 0.5646
26
+ - Precision: 0.5686
27
+ - Recall: 0.5646
28
+ - F1: 0.5531
29
 
30
  ## Model description
31
 
 
45
 
46
  The following hyperparameters were used during training:
47
  - learning_rate: 5e-05
48
+ - train_batch_size: 8
49
+ - eval_batch_size: 16
50
  - seed: 42
51
+ - distributed_type: multi-GPU
52
+ - num_devices: 2
53
+ - total_train_batch_size: 16
54
+ - total_eval_batch_size: 32
55
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
56
  - lr_scheduler_type: linear
57
  - lr_scheduler_warmup_steps: 500
 
60
 
61
  ### Training results
62
 
63
+ | Training Loss | Epoch | Step | Accuracy | F1 | Validation Loss | Precision | Recall |
64
+ |:-------------:|:------:|:------:|:--------:|:------:|:---------------:|:---------:|:------:|
65
+ | 1.757 | 0.0356 | 1000 | 0.1934 | 0.1444 | 1.8080 | 0.3630 | 0.1934 |
66
+ | 1.7207 | 0.0711 | 2000 | 0.1858 | 0.1167 | 1.8231 | 0.4510 | 0.1858 |
67
+ | 1.7191 | 0.1067 | 3000 | 0.2319 | 0.1956 | 1.7802 | 0.3031 | 0.2319 |
68
+ | 1.6801 | 0.1422 | 4000 | 0.2710 | 0.2483 | 1.7571 | 0.3163 | 0.2710 |
69
+ | 1.6729 | 0.1778 | 5000 | 0.316 | 0.3071 | 1.7127 | 0.3274 | 0.316 |
70
+ | 1.6273 | 0.2133 | 6000 | 0.2663 | 0.2278 | 1.7038 | 0.3393 | 0.2663 |
71
+ | 1.638 | 0.2489 | 7000 | 0.3340 | 0.2975 | 1.6556 | 0.3365 | 0.3340 |
72
+ | 1.6088 | 0.2844 | 8000 | 0.3467 | 0.3030 | 1.6232 | 0.3529 | 0.3467 |
73
+ | 1.6045 | 0.32 | 9000 | 0.3678 | 0.3467 | 1.6154 | 0.3719 | 0.3678 |
74
+ | 1.5529 | 0.3889 | 10000 | 0.3898 | 0.3557 | 1.5715 | 0.3820 | 0.3898 |
75
+ | 1.5729 | 0.4278 | 11000 | 0.3882 | 0.3649 | 1.5619 | 0.4034 | 0.3882 |
76
+ | 1.5647 | 0.4667 | 12000 | 0.4043 | 0.3773 | 1.5250 | 0.4066 | 0.4043 |
77
+ | 1.5344 | 0.5056 | 13000 | 0.4231 | 0.3957 | 1.5101 | 0.4251 | 0.4231 |
78
+ | 1.558 | 0.5445 | 14000 | 0.4288 | 0.4052 | 1.4953 | 0.4249 | 0.4288 |
79
+ | 1.5119 | 0.5834 | 15000 | 0.4318 | 0.4108 | 1.4901 | 0.4326 | 0.4318 |
80
+ | 1.53 | 0.6223 | 16000 | 0.4374 | 0.4203 | 1.4725 | 0.4316 | 0.4374 |
81
+ | 1.5029 | 0.6611 | 17000 | 0.4375 | 0.4130 | 1.4610 | 0.4317 | 0.4375 |
82
+ | 1.5406 | 0.7000 | 18000 | 0.4470 | 0.4341 | 1.4421 | 0.4589 | 0.4470 |
83
+ | 1.4774 | 0.7389 | 19000 | 0.4537 | 0.4282 | 1.4335 | 0.4697 | 0.4537 |
84
+ | 1.5911 | 0.7778 | 20000 | 0.4617 | 0.4440 | 1.4154 | 0.4506 | 0.4617 |
85
+ | 1.5075 | 0.8167 | 21000 | 0.4367 | 0.4043 | 1.4382 | 0.4717 | 0.4367 |
86
+ | 1.4361 | 0.8556 | 22000 | 0.4542 | 0.4433 | 1.4165 | 0.4565 | 0.4542 |
87
+ | 1.5074 | 0.8945 | 23000 | 0.4397 | 0.4216 | 1.4402 | 0.4570 | 0.4397 |
88
+ | 1.5422 | 0.9334 | 24000 | 0.4324 | 0.4164 | 1.4387 | 0.4636 | 0.4324 |
89
+ | 1.504 | 0.9723 | 25000 | 0.4691 | 0.4573 | 1.3951 | 0.4829 | 0.4691 |
90
+ | 1.589 | 1.0112 | 26000 | 0.4568 | 0.4396 | 1.4080 | 0.4792 | 0.4568 |
91
+ | 1.5463 | 1.0501 | 27000 | 0.4763 | 0.4612 | 1.3758 | 0.4912 | 0.4763 |
92
+ | 1.5442 | 1.0889 | 28000 | 0.4810 | 0.4603 | 1.3749 | 0.5010 | 0.4810 |
93
+ | 1.5678 | 1.1278 | 29000 | 0.4821 | 0.4679 | 1.3573 | 0.4898 | 0.4821 |
94
+ | 1.4957 | 1.1667 | 30000 | 0.4773 | 0.4531 | 1.3754 | 0.4864 | 0.4773 |
95
+ | 1.4619 | 1.2056 | 31000 | 0.4583 | 0.4333 | 1.4045 | 0.4852 | 0.4583 |
96
+ | 1.5267 | 1.2445 | 32000 | 0.4830 | 0.4659 | 1.3626 | 0.4797 | 0.4830 |
97
+ | 1.4861 | 1.2834 | 33000 | 0.4753 | 0.4560 | 1.3709 | 0.4818 | 0.4753 |
98
+ | 1.532 | 1.3223 | 34000 | 0.4689 | 0.4318 | 1.3816 | 0.4647 | 0.4689 |
99
+ | 1.5705 | 1.3612 | 35000 | 0.4840 | 0.4597 | 1.3663 | 0.4826 | 0.4840 |
100
+ | 1.4912 | 1.4001 | 36000 | 0.4854 | 0.4635 | 1.3536 | 0.4973 | 0.4854 |
101
+ | 1.4966 | 1.4390 | 37000 | 0.4909 | 0.4702 | 1.3497 | 0.4884 | 0.4909 |
102
+ | 1.4327 | 1.4779 | 38000 | 0.4800 | 0.4685 | 1.3592 | 0.4885 | 0.4800 |
103
+ | 1.5454 | 1.5167 | 39000 | 0.5042 | 0.4773 | 1.3186 | 0.5126 | 0.5042 |
104
+ | 1.4842 | 1.5556 | 40000 | 0.5018 | 0.4860 | 1.3254 | 0.5038 | 0.5018 |
105
+ | 1.4606 | 1.5945 | 41000 | 0.4928 | 0.4627 | 1.3411 | 0.5006 | 0.4928 |
106
+ | 1.4117 | 1.6334 | 42000 | 0.5009 | 0.4915 | 1.3106 | 0.5220 | 0.5009 |
107
+ | 1.4794 | 1.6723 | 43000 | 0.5002 | 0.4821 | 1.3182 | 0.5228 | 0.5002 |
108
+ | 1.5223 | 1.7112 | 44000 | 0.5027 | 0.4897 | 1.3102 | 0.5135 | 0.5027 |
109
+ | 1.5187 | 1.7501 | 45000 | 0.5134 | 0.4991 | 1.2922 | 0.5090 | 0.5134 |
110
+ | 1.6064 | 1.7890 | 46000 | 0.5105 | 0.4938 | 1.2987 | 0.5039 | 0.5105 |
111
+ | 1.5322 | 1.8279 | 47000 | 0.5081 | 0.4831 | 1.3015 | 0.4997 | 0.5081 |
112
+ | 1.4831 | 1.8668 | 48000 | 0.4918 | 0.4704 | 1.3280 | 0.5077 | 0.4918 |
113
+ | 1.4726 | 1.9057 | 49000 | 0.5011 | 0.4822 | 1.3042 | 0.5145 | 0.5011 |
114
+ | 1.5298 | 1.9445 | 50000 | 0.5162 | 0.5028 | 1.2816 | 0.5206 | 0.5162 |
115
+ | 1.559 | 1.9834 | 51000 | 0.5133 | 0.4969 | 1.2905 | 0.5131 | 0.5133 |
116
+ | 1.5835 | 2.0223 | 52000 | 0.5198 | 0.5097 | 1.2741 | 0.5248 | 0.5198 |
117
+ | 1.5087 | 2.0612 | 53000 | 0.5125 | 0.5040 | 1.2828 | 0.5206 | 0.5125 |
118
+ | 1.4915 | 2.1001 | 54000 | 0.5115 | 0.4952 | 1.2897 | 0.5185 | 0.5115 |
119
+ | 1.482 | 2.1390 | 55000 | 0.5138 | 0.5024 | 1.2792 | 0.5219 | 0.5138 |
120
+ | 1.5485 | 2.1779 | 56000 | 0.5181 | 0.5036 | 1.2789 | 0.5282 | 0.5181 |
121
+ | 1.5636 | 2.2168 | 57000 | 0.5151 | 0.5005 | 1.2838 | 0.5257 | 0.5151 |
122
+ | 1.4106 | 2.2557 | 58000 | 0.5132 | 0.4920 | 1.2850 | 0.5161 | 0.5132 |
123
+ | 1.4449 | 2.2946 | 59000 | 0.503 | 0.4772 | 1.3000 | 0.5147 | 0.503 |
124
+ | 1.4786 | 2.3335 | 60000 | 0.5203 | 0.5043 | 1.2671 | 0.5432 | 0.5203 |
125
+ | 1.4684 | 2.3723 | 61000 | 0.5206 | 0.5091 | 1.2671 | 0.5356 | 0.5206 |
126
+ | 1.4268 | 2.4112 | 62000 | 0.5223 | 0.5089 | 1.2658 | 0.5269 | 0.5223 |
127
+ | 1.4774 | 2.4501 | 63000 | 0.5296 | 0.5181 | 1.2524 | 0.5371 | 0.5296 |
128
+ | 1.4325 | 2.4890 | 64000 | 0.5202 | 0.5059 | 1.2673 | 0.5250 | 0.5202 |
129
+ | 1.5087 | 2.5279 | 65000 | 0.4971 | 0.4755 | 1.3084 | 0.5250 | 0.4971 |
130
+ | 1.4453 | 2.5668 | 66000 | 0.5123 | 0.5017 | 1.2858 | 0.5276 | 0.5123 |
131
+ | 1.476 | 2.6057 | 67000 | 0.5233 | 0.5089 | 1.2626 | 0.5223 | 0.5233 |
132
+ | 1.4795 | 2.6446 | 68000 | 0.5159 | 0.4972 | 1.2777 | 0.5278 | 0.5159 |
133
+ | 1.4468 | 2.6835 | 69000 | 0.5299 | 0.5126 | 1.2504 | 0.5283 | 0.5299 |
134
+ | 1.4137 | 2.7224 | 70000 | 0.5290 | 0.5176 | 1.2511 | 0.5377 | 0.5289 |
135
+ | 1.5105 | 2.7612 | 71000 | 0.5383 | 0.5298 | 1.2342 | 0.5430 | 0.5383 |
136
+ | 1.4906 | 2.8001 | 72000 | 0.5271 | 0.5137 | 1.2550 | 0.5295 | 0.5271 |
137
+ | 1.4464 | 2.8390 | 73000 | 0.5273 | 0.5118 | 1.2512 | 0.5384 | 0.5273 |
138
+ | 1.6306 | 2.8779 | 74000 | 0.5300 | 0.5160 | 1.2466 | 0.5320 | 0.5300 |
139
+ | 1.4965 | 2.9168 | 75000 | 0.5222 | 0.5078 | 1.2595 | 0.5358 | 0.5222 |
140
+ | 1.4079 | 2.9557 | 76000 | 0.5227 | 0.5092 | 1.2536 | 0.5231 | 0.5227 |
141
+ | 1.448 | 2.9946 | 77000 | 0.5230 | 0.4991 | 1.2700 | 0.5295 | 0.5230 |
142
+ | 1.6561 | 3.0335 | 78000 | 0.5348 | 0.5200 | 1.2381 | 0.5237 | 0.5348 |
143
+ | 1.5103 | 3.0724 | 79000 | 0.5334 | 0.5216 | 1.2393 | 0.5451 | 0.5334 |
144
+ | 1.5148 | 3.1113 | 80000 | 0.5307 | 0.5091 | 1.2489 | 0.5474 | 0.5307 |
145
+ | 1.4129 | 3.1502 | 81000 | 0.5379 | 0.5238 | 1.2319 | 0.5292 | 0.5379 |
146
+ | 1.6654 | 3.1890 | 82000 | 0.5335 | 0.5165 | 1.2415 | 0.5372 | 0.5335 |
147
+ | 1.4226 | 3.2279 | 83000 | 0.5336 | 0.5210 | 1.2343 | 0.5478 | 0.5336 |
148
+ | 1.3913 | 3.2668 | 84000 | 0.5381 | 0.5251 | 1.2317 | 0.5344 | 0.5381 |
149
+ | 1.4628 | 3.3057 | 85000 | 0.5240 | 0.5142 | 1.2496 | 0.5327 | 0.5240 |
150
+ | 1.3775 | 3.3446 | 86000 | 0.5305 | 0.5159 | 1.2400 | 0.5383 | 0.5305 |
151
+ | 1.4292 | 3.3835 | 87000 | 0.5140 | 0.4945 | 1.2727 | 0.5329 | 0.5140 |
152
+ | 1.5157 | 3.4224 | 88000 | 0.5243 | 0.5146 | 1.2419 | 0.5502 | 0.5243 |
153
+ | 1.4581 | 3.4613 | 89000 | 0.5318 | 0.5245 | 1.2296 | 0.5524 | 0.5318 |
154
+ | 1.3873 | 3.5002 | 90000 | 0.5314 | 0.5211 | 1.2380 | 0.5436 | 0.5314 |
155
+ | 1.425 | 3.5391 | 91000 | 0.5371 | 0.5242 | 1.2300 | 0.5420 | 0.5371 |
156
+ | 1.4202 | 3.5780 | 92000 | 0.5430 | 0.5282 | 1.2211 | 0.5475 | 0.5430 |
157
+ | 1.4748 | 3.6168 | 93000 | 0.5407 | 0.5273 | 1.2256 | 0.5422 | 0.5407 |
158
+ | 1.4289 | 3.6557 | 94000 | 0.5351 | 0.5230 | 1.2293 | 0.5426 | 0.5351 |
159
+ | 1.4312 | 3.6946 | 95000 | 0.5405 | 0.5314 | 1.2180 | 0.5483 | 0.5405 |
160
+ | 1.4342 | 3.7335 | 96000 | 0.5256 | 0.5085 | 1.2435 | 0.5420 | 0.5256 |
161
+ | 1.8241 | 3.7724 | 97000 | 0.5335 | 0.5138 | 1.2389 | 0.5384 | 0.5335 |
162
+ | 1.4589 | 3.8113 | 98000 | 0.5222 | 0.5070 | 1.2484 | 0.5458 | 0.5222 |
163
+ | 1.4884 | 3.8502 | 99000 | 0.5231 | 0.4996 | 1.2610 | 0.5311 | 0.5231 |
164
+ | 1.5725 | 3.8891 | 100000 | 0.5468 | 0.5383 | 1.2074 | 0.5456 | 0.5468 |
165
+ | 1.4603 | 3.9280 | 101000 | 0.5409 | 0.5261 | 1.2154 | 0.5471 | 0.5409 |
166
+ | 1.4581 | 3.9669 | 102000 | 0.5365 | 0.5221 | 1.2234 | 0.5352 | 0.5365 |
167
+ | 1.5738 | 4.0058 | 103000 | 0.5339 | 0.5205 | 1.2247 | 0.5445 | 0.5339 |
168
+ | 1.593 | 4.0446 | 104000 | 0.5210 | 0.5067 | 1.2527 | 0.5370 | 0.5210 |
169
+ | 1.4523 | 4.0835 | 105000 | 0.5456 | 0.5261 | 1.2102 | 0.5411 | 0.5456 |
170
+ | 1.5537 | 4.1224 | 106000 | 0.5341 | 0.5155 | 1.2337 | 0.5334 | 0.5341 |
171
+ | 1.4931 | 4.1613 | 107000 | 0.5437 | 0.5336 | 1.2114 | 0.5461 | 0.5437 |
172
+ | 1.4286 | 4.2002 | 108000 | 0.5153 | 0.4956 | 1.2611 | 0.5458 | 0.5153 |
173
+ | 1.3667 | 4.2391 | 109000 | 0.5439 | 0.5301 | 1.2108 | 0.5463 | 0.5439 |
174
+ | 1.4723 | 4.2780 | 110000 | 0.5312 | 0.5213 | 1.2269 | 0.5497 | 0.5312 |
175
+ | 1.3852 | 4.3169 | 111000 | 0.5452 | 0.5290 | 1.2128 | 0.5488 | 0.5452 |
176
+ | 1.489 | 4.3558 | 112000 | 0.5419 | 0.5310 | 1.2094 | 0.5471 | 0.5419 |
177
+ | 1.4598 | 4.3947 | 113000 | 0.5356 | 0.5246 | 1.2183 | 0.5418 | 0.5356 |
178
+ | 1.5491 | 4.4336 | 114000 | 0.5438 | 0.5372 | 1.2062 | 0.5535 | 0.5438 |
179
+ | 1.3628 | 4.4724 | 115000 | 0.5381 | 0.5281 | 1.2204 | 0.5430 | 0.5381 |
180
+ | 1.5225 | 4.5113 | 116000 | 0.5362 | 0.5289 | 1.2174 | 0.5573 | 0.5362 |
181
+ | 1.4036 | 4.5502 | 117000 | 0.5440 | 0.5316 | 1.2084 | 0.5547 | 0.5440 |
182
+ | 1.4956 | 4.5891 | 118000 | 0.5319 | 0.5173 | 1.2280 | 0.5358 | 0.5318 |
183
+ | 1.3991 | 4.6280 | 119000 | 0.5453 | 0.5338 | 1.2046 | 0.5494 | 0.5453 |
184
+ | 1.5407 | 4.6669 | 120000 | 0.5428 | 0.5289 | 1.2093 | 0.5503 | 0.5428 |
185
+ | 1.5033 | 4.7058 | 121000 | 0.5403 | 0.5237 | 1.2122 | 0.5630 | 0.5403 |
186
+ | 1.5966 | 4.7447 | 122000 | 0.5536 | 0.5462 | 1.1886 | 0.5590 | 0.5536 |
187
+ | 1.637 | 2.3918 | 123000 | 0.5389 | 0.5157 | 1.2282 | 0.5438 | 0.5389 |
188
+ | 1.5217 | 2.4113 | 124000 | 0.5488 | 0.5427 | 1.2010 | 0.5442 | 0.5488 |
189
+ | 1.6031 | 2.4307 | 125000 | 0.5400 | 0.5277 | 1.2237 | 0.5371 | 0.5400 |
190
+ | 1.4542 | 2.4502 | 126000 | 0.5434 | 0.5308 | 1.2101 | 0.5586 | 0.5434 |
191
+ | 1.5071 | 2.4696 | 127000 | 0.5429 | 0.5279 | 1.2116 | 0.5501 | 0.5429 |
192
+ | 1.5437 | 2.4891 | 128000 | 0.5383 | 0.5256 | 1.2150 | 0.5487 | 0.5383 |
193
+ | 1.4489 | 2.5085 | 129000 | 0.5129 | 0.5063 | 1.2566 | 0.5528 | 0.5129 |
194
+ | 1.5495 | 2.5280 | 130000 | 0.5532 | 0.5427 | 1.1922 | 0.5581 | 0.5532 |
195
+ | 1.4348 | 2.5474 | 131000 | 0.5432 | 0.5375 | 1.2032 | 0.5510 | 0.5432 |
196
+ | 1.4554 | 2.5668 | 132000 | 0.5383 | 0.5252 | 1.2144 | 0.5638 | 0.5383 |
197
+ | 1.4183 | 2.5863 | 133000 | 0.5335 | 0.5256 | 1.2202 | 0.5482 | 0.5335 |
198
+ | 1.4754 | 2.6057 | 134000 | 0.5470 | 0.5437 | 1.1988 | 0.5537 | 0.5470 |
199
+ | 1.5864 | 2.6252 | 135000 | 0.5426 | 0.5348 | 1.2015 | 0.5414 | 0.5426 |
200
+ | 1.3715 | 2.6446 | 136000 | 0.5287 | 0.5136 | 1.2306 | 0.5495 | 0.5287 |
201
+ | 1.3886 | 2.6641 | 137000 | 0.5445 | 0.5323 | 1.2043 | 0.5478 | 0.5445 |
202
+ | 1.4509 | 2.6835 | 138000 | 0.5438 | 0.5276 | 1.2045 | 0.5602 | 0.5438 |
203
+ | 1.4868 | 2.7030 | 139000 | 0.5233 | 0.5097 | 1.2468 | 0.5385 | 0.5233 |
204
+ | 1.4345 | 2.7224 | 140000 | 0.5456 | 0.5312 | 1.2123 | 0.5404 | 0.5456 |
205
+ | 1.3935 | 2.7419 | 141000 | 0.5441 | 0.5321 | 1.2061 | 0.5428 | 0.5441 |
206
+ | 1.5243 | 2.7613 | 142000 | 0.5530 | 0.5402 | 1.1959 | 0.5437 | 0.5530 |
207
+ | 1.5884 | 2.8196 | 145000 | 0.5519 | 0.5430 | 1.1936 | 0.5581 | 0.5519 |
208
+ | 1.4449 | 2.9169 | 150000 | 0.5288 | 0.5164 | 1.2338 | 0.5527 | 0.5288 |
209
+ | 1.4557 | 3.0141 | 155000 | 0.5561 | 0.5428 | 1.1910 | 0.5568 | 0.5561 |
210
+ | 1.6852 | 3.1113 | 160000 | 0.5564 | 0.5497 | 1.1852 | 0.5597 | 0.5564 |
211
+ | 1.4623 | 3.2086 | 165000 | 0.5598 | 0.5557 | 1.1777 | 0.5623 | 0.5598 |
212
+ | 1.4993 | 3.3058 | 170000 | 1.2342 | 0.5299 | 0.5362 | 0.5299 | 0.5146 |
213
+ | 1.466 | 3.4030 | 175000 | 1.1878 | 0.5499 | 0.5656 | 0.5499 | 0.5471 |
214
+ | 1.409 | 3.5002 | 180000 | 1.2197 | 0.5333 | 0.5568 | 0.5333 | 0.5278 |
215
+ | 1.4949 | 3.5975 | 185000 | 1.1775 | 0.5617 | 0.5611 | 0.5618 | 0.5408 |
216
+ | 1.4764 | 3.6947 | 190000 | 1.2087 | 0.5430 | 0.5455 | 0.5430 | 0.5266 |
217
+ | 1.4751 | 3.7919 | 195000 | 1.2000 | 0.5462 | 0.5690 | 0.5462 | 0.5353 |
218
+ | 1.5135 | 3.8892 | 200000 | 1.2028 | 0.5468 | 0.5500 | 0.5468 | 0.5348 |
219
+ | 1.3999 | 3.9864 | 205000 | 1.1762 | 0.5622 | 0.5630 | 0.5622 | 0.5517 |
220
+ | 1.4685 | 4.0836 | 210000 | 1.1819 | 0.5550 | 0.5632 | 0.5550 | 0.5405 |
221
+ | 1.4338 | 4.1808 | 215000 | 1.1992 | 0.5498 | 0.5569 | 0.5498 | 0.5354 |
222
+ | 1.6445 | 4.2781 | 220000 | 1.2039 | 0.5424 | 0.5603 | 0.5424 | 0.5297 |
223
+ | 1.4788 | 4.3753 | 225000 | 1.1930 | 0.5549 | 0.5525 | 0.5549 | 0.5458 |
224
+ | 1.3937 | 4.4725 | 230000 | 1.1762 | 0.5571 | 0.5552 | 0.5571 | 0.5509 |
225
+ | 1.3932 | 4.5698 | 235000 | 1.2016 | 0.5471 | 0.5523 | 0.5471 | 0.5338 |
226
+ | 1.5177 | 4.6670 | 240000 | 1.1786 | 0.5577 | 0.5666 | 0.5577 | 0.5449 |
227
+ | 1.5508 | 4.7642 | 245000 | 1.1772 | 0.5540 | 0.5826 | 0.5540 | 0.5521 |
228
+ | 1.4184 | 4.8614 | 250000 | 1.1773 | 0.5581 | 0.5682 | 0.5581 | 0.5455 |
229
+ | 1.5349 | 4.9587 | 255000 | 1.1828 | 0.5581 | 0.5663 | 0.5581 | 0.5440 |
230
+ | 1.4414 | 5.0559 | 260000 | 1.1804 | 0.5536 | 0.5699 | 0.5536 | 0.5437 |
231
+ | 1.4374 | 5.1531 | 265000 | 1.1910 | 0.5525 | 0.5576 | 0.5525 | 0.5356 |
232
+ | 1.4101 | 5.2504 | 270000 | 1.1854 | 0.5548 | 0.5648 | 0.5548 | 0.5427 |
233
+ | 1.6934 | 5.3476 | 275000 | 1.2125 | 0.5399 | 0.5599 | 0.5399 | 0.5184 |
234
+ | 1.4133 | 5.4448 | 280000 | 1.1745 | 0.5591 | 0.5694 | 0.5591 | 0.5487 |
235
+ | 1.5981 | 5.5421 | 285000 | 1.2078 | 0.5391 | 0.5644 | 0.5391 | 0.5317 |
236
+ | 1.4194 | 5.6393 | 290000 | 1.1834 | 0.5507 | 0.5654 | 0.5507 | 0.5414 |
237
+ | 1.5619 | 5.7365 | 295000 | 1.1951 | 0.5485 | 0.5685 | 0.5485 | 0.5356 |
238
+ | 1.4517 | 5.8337 | 300000 | 1.1835 | 0.5570 | 0.5696 | 0.5570 | 0.5360 |
239
+ | 1.5457 | 5.9310 | 305000 | 1.1635 | 0.5617 | 0.5738 | 0.5618 | 0.5530 |
240
+ | 1.4769 | 6.0282 | 310000 | 1.1636 | 0.5633 | 0.5670 | 0.5633 | 0.5565 |
241
+ | 1.3975 | 6.1254 | 315000 | 1.1785 | 0.5596 | 0.5684 | 0.5596 | 0.5443 |
242
+ | 1.6069 | 6.2227 | 320000 | 1.1685 | 0.5634 | 0.5632 | 0.5634 | 0.5541 |
243
+ | 1.3608 | 6.3199 | 325000 | 1.1589 | 0.5673 | 0.5600 | 0.5673 | 0.5581 |
244
+ | 1.5021 | 6.4171 | 330000 | 1.1799 | 0.5576 | 0.5561 | 0.5576 | 0.5435 |
245
+ | 1.6022 | 6.5143 | 335000 | 1.1722 | 0.5617 | 0.5579 | 0.5617 | 0.5504 |
246
+ | 1.5354 | 6.6116 | 340000 | 1.1631 | 0.5644 | 0.5668 | 0.5644 | 0.5541 |
247
+ | 1.4264 | 6.7088 | 345000 | 1.1693 | 0.5626 | 0.5640 | 0.5626 | 0.5484 |
248
+ | 1.5207 | 6.8060 | 350000 | 1.1781 | 0.5583 | 0.5668 | 0.5583 | 0.5401 |
249
+ | 1.441 | 6.9033 | 355000 | 1.1746 | 0.5581 | 0.5666 | 0.5581 | 0.5496 |
250
+ | 1.33 | 7.0005 | 360000 | 1.1605 | 0.5677 | 0.5721 | 0.5677 | 0.5574 |
251
+ | 1.5886 | 7.0977 | 365000 | 1.1649 | 0.5657 | 0.5711 | 0.5657 | 0.5523 |
252
+ | 1.5005 | 7.1949 | 370000 | 1.1872 | 0.5523 | 0.5644 | 0.5523 | 0.5384 |
253
+ | 1.4685 | 7.2922 | 375000 | 1.1735 | 0.5607 | 0.5671 | 0.5607 | 0.5451 |
254
+ | 1.373 | 7.3894 | 380000 | 1.1597 | 0.5652 | 0.5726 | 0.5652 | 0.5557 |
255
+ | 1.5504 | 7.4866 | 385000 | 1.1803 | 0.5518 | 0.5732 | 0.5518 | 0.5413 |
256
+ | 1.4173 | 7.5839 | 390000 | 1.1709 | 0.5601 | 0.5660 | 0.5601 | 0.5455 |
257
+ | 1.4251 | 7.6811 | 395000 | 1.1607 | 0.5674 | 0.5710 | 0.5674 | 0.5574 |
258
+ | 1.6129 | 7.7783 | 400000 | 1.1831 | 0.5530 | 0.5610 | 0.5530 | 0.5418 |
259
+ | 1.4331 | 7.8755 | 405000 | 1.1715 | 0.5626 | 0.5645 | 0.5626 | 0.5488 |
260
+ | 1.5966 | 7.9728 | 410000 | 1.1825 | 0.5592 | 0.5623 | 0.5592 | 0.5411 |
261
+ | 1.3413 | 8.0700 | 415000 | 1.1705 | 0.5585 | 0.5687 | 0.5585 | 0.5486 |
262
+ | 1.3785 | 8.1672 | 420000 | 1.1576 | 0.5692 | 0.5656 | 0.5692 | 0.5568 |
263
+ | 1.5491 | 8.2645 | 425000 | 1.1627 | 0.5665 | 0.5671 | 0.5665 | 0.5515 |
264
+ | 1.3878 | 8.3617 | 430000 | 1.1688 | 0.5607 | 0.5712 | 0.5607 | 0.5497 |
265
+ | 1.415 | 8.4589 | 435000 | 1.1801 | 0.5546 | 0.5650 | 0.5546 | 0.5423 |
266
+ | 1.3973 | 8.5561 | 440000 | 1.1650 | 0.5612 | 0.5712 | 0.5612 | 0.5538 |
267
+ | 1.3801 | 8.6534 | 445000 | 1.1671 | 0.5655 | 0.5665 | 0.5655 | 0.5525 |
268
+ | 1.4631 | 8.7506 | 450000 | 1.1839 | 0.5552 | 0.5631 | 0.5552 | 0.5414 |
269
+ | 1.4076 | 8.8478 | 455000 | 1.1725 | 0.5604 | 0.5668 | 0.5604 | 0.5452 |
270
+ | 1.6888 | 8.9451 | 460000 | 1.1622 | 0.5642 | 0.5732 | 0.5642 | 0.5533 |
271
+ | 1.4282 | 9.0423 | 465000 | 1.1566 | 0.5682 | 0.5726 | 0.5682 | 0.5579 |
272
+ | 1.4833 | 9.1395 | 470000 | 1.1658 | 0.5635 | 0.5725 | 0.5635 | 0.5526 |
273
+ | 1.5365 | 9.2368 | 475000 | 1.1589 | 0.5684 | 0.5687 | 0.5684 | 0.5567 |
274
+ | 1.3789 | 9.3340 | 480000 | 1.1688 | 0.5616 | 0.5678 | 0.5616 | 0.5489 |
275
+ | 1.3586 | 9.4312 | 485000 | 1.1796 | 0.5547 | 0.5646 | 0.5547 | 0.5427 |
276
+ | 1.4582 | 9.5284 | 490000 | 1.1725 | 0.5606 | 0.5635 | 0.5606 | 0.5485 |
277
+ | 1.439 | 9.6257 | 495000 | 1.1643 | 0.5649 | 0.5700 | 0.5650 | 0.5534 |
278
+ | 1.4671 | 9.7229 | 500000 | 1.1688 | 0.5617 | 0.5667 | 0.5617 | 0.5495 |
279
+ | 1.4149 | 9.8201 | 505000 | 1.1640 | 0.5652 | 0.5662 | 0.5652 | 0.5535 |
280
+ | 1.5227 | 9.9174 | 510000 | 1.1634 | 0.5646 | 0.5686 | 0.5646 | 0.5531 |
281
 
282
 
283
  ### Framework versions
284
 
285
+ - Transformers 4.48.0
286
+ - Pytorch 2.2.1+cu121
287
+ - Datasets 2.18.0
288
  - Tokenizers 0.21.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71c71d866a2567bda696d6c6bd7808616c5c80d618670c4725ddb6a3434940d6
3
  size 2325242152
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3ed71ece74b42689987110bd97434fe0d39af685b58be1ac725f8995bd7b4dc
3
  size 2325242152