Hugging Face's logo

QuanHoangNgoc
/
lock_s2t-small-uit-vimd_192355

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Vietnamese
speech_to_text
speech-to-text
vietnamese
uit-vimd
Generated from Trainer
Eval Results
Model card Files Metrics Community
QuanHoangNgoc commited on
Commit
d681f68
·
verified ·
1 Parent(s): 47c73aa

End of training

Browse files
Files changed (3) hide show
  1. README.md +498 -0
  2. generation_config.json +10 -0
  3. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,498 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ language:
4
+ - vi
5
+ base_model: s2t-small-librispeech-asr
6
+ tags:
7
+ - speech-to-text
8
+ - vietnamese
9
+ - uit-vimd
10
+ - generated_from_trainer
11
+ datasets:
12
+ - uit-vimd
13
+ metrics:
14
+ - wer
15
+ model-index:
16
+ - name: s2t-small-uit-vimd-finetuned
17
+ results:
18
+ - task:
19
+ name: Automatic Speech Recognition
20
+ type: automatic-speech-recognition
21
+ dataset:
22
+ name: UIT-ViMD
23
+ type: uit-vimd
24
+ metrics:
25
+ - name: Wer
26
+ type: wer
27
+ value: 0.662090007627765
28
+ ---
29
+
30
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
31
+ should probably proofread and complete it, then remove this comment. -->
32
+
33
+ # s2t-small-uit-vimd-finetuned
34
+
35
+ This model is a fine-tuned version of [s2t-small-librispeech-asr](https://huggingface.co/s2t-small-librispeech-asr) on the UIT-ViMD dataset.
36
+ It achieves the following results on the evaluation set:
37
+ - Loss: 1.7059
38
+ - Wer: 0.6621
39
+
40
+ ## Model description
41
+
42
+ More information needed
43
+
44
+ ## Intended uses & limitations
45
+
46
+ More information needed
47
+
48
+ ## Training and evaluation data
49
+
50
+ More information needed
51
+
52
+ ## Training procedure
53
+
54
+ ### Training hyperparameters
55
+
56
+ The following hyperparameters were used during training:
57
+ - learning_rate: 3e-05
58
+ - train_batch_size: 16
59
+ - eval_batch_size: 16
60
+ - seed: 42
61
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
62
+ - lr_scheduler_type: linear
63
+ - lr_scheduler_warmup_steps: 1500
64
+ - training_steps: 40000
65
+ - mixed_precision_training: Native AMP
66
+
67
+ ### Training results
68
+
69
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
70
+ |:-------------:|:-------:|:-----:|:---------------:|:------:|
71
+ | 10.0415 | 0.0490 | 46 | 9.6072 | 2.7651 |
72
+ | 9.0102 | 0.0980 | 92 | 8.0153 | 2.6857 |
73
+ | 7.5035 | 0.1470 | 138 | 6.5609 | 1.0961 |
74
+ | 6.657 | 0.1960 | 184 | 6.2412 | 2.5347 |
75
+ | 6.467 | 0.2449 | 230 | 6.1566 | 2.8444 |
76
+ | 6.3998 | 0.2939 | 276 | 6.2421 | 2.7887 |
77
+ | 6.3478 | 0.3429 | 322 | 6.0328 | 2.7879 |
78
+ | 6.315 | 0.3919 | 368 | 6.0488 | 2.7872 |
79
+ | 6.2289 | 0.4409 | 414 | 6.0076 | 2.5553 |
80
+ | 6.1241 | 0.4899 | 460 | 5.9637 | 2.6240 |
81
+ | 6.0459 | 0.5389 | 506 | 5.7459 | 2.5721 |
82
+ | 5.9405 | 0.5879 | 552 | 5.6078 | 1.6834 |
83
+ | 5.8387 | 0.6368 | 598 | 5.7928 | 1.6934 |
84
+ | 5.7766 | 0.6858 | 644 | 5.4501 | 1.1274 |
85
+ | 5.6624 | 0.7348 | 690 | 5.2855 | 1.1091 |
86
+ | 5.6038 | 0.7838 | 736 | 5.1060 | 1.2662 |
87
+ | 5.5032 | 0.8328 | 782 | 5.1984 | 1.1968 |
88
+ | 5.4133 | 0.8818 | 828 | 5.2017 | 1.4813 |
89
+ | 5.3843 | 0.9308 | 874 | 5.1494 | 1.3059 |
90
+ | 5.2971 | 0.9798 | 920 | 5.2455 | 2.3707 |
91
+ | 5.2491 | 1.0288 | 966 | 5.1174 | 1.2235 |
92
+ | 5.2254 | 1.0777 | 1012 | 5.0736 | 1.0229 |
93
+ | 5.194 | 1.1267 | 1058 | 5.0790 | 1.3837 |
94
+ | 5.1989 | 1.1757 | 1104 | 4.8743 | 1.0969 |
95
+ | 5.1021 | 1.2247 | 1150 | 4.8653 | 1.1640 |
96
+ | 5.0841 | 1.2737 | 1196 | 4.6579 | 1.2822 |
97
+ | 5.0679 | 1.3227 | 1242 | 4.8070 | 1.6339 |
98
+ | 5.0172 | 1.3717 | 1288 | 4.6677 | 1.0656 |
99
+ | 4.9715 | 1.4207 | 1334 | 4.6763 | 2.3150 |
100
+ | 4.9885 | 1.4696 | 1380 | 4.9263 | 2.5736 |
101
+ | 4.9401 | 1.5186 | 1426 | 4.6204 | 1.9573 |
102
+ | 4.9149 | 1.5676 | 1472 | 5.0924 | 1.0267 |
103
+ | 4.9357 | 1.6166 | 1518 | 4.4960 | 1.4615 |
104
+ | 4.8663 | 1.6656 | 1564 | 4.6463 | 1.4371 |
105
+ | 4.8719 | 1.7146 | 1610 | 4.4370 | 2.8726 |
106
+ | 4.8715 | 1.7636 | 1656 | 4.6787 | 1.0778 |
107
+ | 4.809 | 1.8126 | 1702 | 4.4654 | 1.8726 |
108
+ | 4.765 | 1.8616 | 1748 | 4.5059 | 1.6987 |
109
+ | 4.7921 | 1.9105 | 1794 | 4.6007 | 2.1129 |
110
+ | 4.7512 | 1.9595 | 1840 | 4.2819 | 1.7407 |
111
+ | 4.7538 | 2.0085 | 1886 | 4.4597 | 1.6110 |
112
+ | 4.6738 | 2.0575 | 1932 | 4.3825 | 1.2044 |
113
+ | 4.6956 | 2.1065 | 1978 | 4.4944 | 2.0564 |
114
+ | 4.6334 | 2.1555 | 2024 | 4.6852 | 2.3867 |
115
+ | 4.6504 | 2.2045 | 2070 | 4.5122 | 1.1098 |
116
+ | 4.6666 | 2.2535 | 2116 | 4.8208 | 1.5004 |
117
+ | 4.6497 | 2.3024 | 2162 | 4.5412 | 1.9687 |
118
+ | 4.6257 | 2.3514 | 2208 | 4.1987 | 2.1243 |
119
+ | 4.5968 | 2.4004 | 2254 | 4.3092 | 1.6056 |
120
+ | 4.6385 | 2.4494 | 2300 | 4.6225 | 2.0061 |
121
+ | 4.5742 | 2.4984 | 2346 | 4.4123 | 1.6285 |
122
+ | 4.564 | 2.5474 | 2392 | 4.5732 | 1.1159 |
123
+ | 4.5809 | 2.5964 | 2438 | 4.8224 | 2.0870 |
124
+ | 4.5591 | 2.6454 | 2484 | 4.3851 | 2.4867 |
125
+ | 4.5448 | 2.6944 | 2530 | 4.3473 | 2.1106 |
126
+ | 4.5179 | 2.7433 | 2576 | 4.3758 | 1.9252 |
127
+ | 4.5827 | 2.7923 | 2622 | 4.7695 | 1.8726 |
128
+ | 4.5294 | 2.8413 | 2668 | 4.3450 | 1.7048 |
129
+ | 4.4741 | 2.8903 | 2714 | 4.1880 | 1.3837 |
130
+ | 4.4874 | 2.9393 | 2760 | 4.4765 | 2.0686 |
131
+ | 4.4538 | 2.9883 | 2806 | 4.1480 | 1.9443 |
132
+ | 4.4028 | 3.0373 | 2852 | 4.3618 | 1.7376 |
133
+ | 4.3593 | 3.0863 | 2898 | 3.9405 | 1.6773 |
134
+ | 4.3418 | 3.1353 | 2944 | 3.9904 | 1.5774 |
135
+ | 4.3513 | 3.1842 | 2990 | 4.3713 | 1.7605 |
136
+ | 4.3221 | 3.2332 | 3036 | 4.1550 | 1.8535 |
137
+ | 4.3248 | 3.2822 | 3082 | 4.0488 | 1.6377 |
138
+ | 4.2307 | 3.3312 | 3128 | 3.8885 | 1.4600 |
139
+ | 4.1828 | 3.3802 | 3174 | 4.0612 | 1.3616 |
140
+ | 4.1284 | 3.4292 | 3220 | 3.5489 | 1.3799 |
141
+ | 4.149 | 3.4782 | 3266 | 3.7420 | 1.3204 |
142
+ | 4.0879 | 3.5272 | 3312 | 3.6886 | 1.4066 |
143
+ | 4.0178 | 3.5761 | 3358 | 3.4516 | 1.5187 |
144
+ | 3.9297 | 3.6251 | 3404 | 3.3175 | 1.4645 |
145
+ | 3.8672 | 3.6741 | 3450 | 3.3851 | 1.1503 |
146
+ | 3.8899 | 3.7231 | 3496 | 3.4686 | 1.3394 |
147
+ | 3.7791 | 3.7721 | 3542 | 3.2141 | 1.2540 |
148
+ | 3.7556 | 3.8211 | 3588 | 3.4405 | 1.1495 |
149
+ | 3.6788 | 3.8701 | 3634 | 2.9653 | 1.2456 |
150
+ | 3.6308 | 3.9191 | 3680 | 3.2929 | 1.1823 |
151
+ | 3.6637 | 3.9681 | 3726 | 3.1619 | 1.0702 |
152
+ | 3.4924 | 4.0170 | 3772 | 3.0206 | 0.9779 |
153
+ | 3.4567 | 4.0660 | 3818 | 3.1071 | 1.0717 |
154
+ | 3.3797 | 4.1150 | 3864 | 3.0367 | 1.1465 |
155
+ | 3.3936 | 4.1640 | 3910 | 3.1383 | 1.0557 |
156
+ | 3.3144 | 4.2130 | 3956 | 2.8800 | 0.9100 |
157
+ | 3.2994 | 4.2620 | 4002 | 2.6442 | 0.9817 |
158
+ | 3.3083 | 4.3110 | 4048 | 2.7012 | 0.8696 |
159
+ | 3.2363 | 4.3600 | 4094 | 2.5279 | 0.9245 |
160
+ | 3.2239 | 4.4089 | 4140 | 2.7279 | 0.8719 |
161
+ | 3.2264 | 4.4579 | 4186 | 2.5810 | 0.9382 |
162
+ | 3.2002 | 4.5069 | 4232 | 2.6343 | 0.9497 |
163
+ | 3.1573 | 4.5559 | 4278 | 3.0085 | 1.0763 |
164
+ | 3.1325 | 4.6049 | 4324 | 2.6016 | 0.8978 |
165
+ | 3.112 | 4.6539 | 4370 | 2.5037 | 1.1907 |
166
+ | 3.0337 | 4.7029 | 4416 | 2.2567 | 1.0725 |
167
+ | 3.0665 | 4.7519 | 4462 | 2.6845 | 0.9596 |
168
+ | 2.9849 | 4.8009 | 4508 | 2.5989 | 0.9947 |
169
+ | 3.0215 | 4.8498 | 4554 | 2.5089 | 1.0 |
170
+ | 2.9487 | 4.8988 | 4600 | 2.2910 | 0.9649 |
171
+ | 2.8958 | 4.9478 | 4646 | 2.3740 | 1.0427 |
172
+ | 2.9507 | 4.9968 | 4692 | 2.3876 | 1.0359 |
173
+ | 2.8907 | 5.0458 | 4738 | 2.6031 | 0.9146 |
174
+ | 2.7608 | 5.0948 | 4784 | 1.9331 | 0.9977 |
175
+ | 2.8235 | 5.1438 | 4830 | 2.2818 | 0.8558 |
176
+ | 2.8225 | 5.1928 | 4876 | 2.4052 | 0.9687 |
177
+ | 2.7794 | 5.2417 | 4922 | 2.0690 | 0.7246 |
178
+ | 2.8446 | 5.2907 | 4968 | 2.1208 | 1.0458 |
179
+ | 2.7446 | 5.3397 | 5014 | 2.6368 | 0.9123 |
180
+ | 2.7906 | 5.3887 | 5060 | 2.3725 | 0.7635 |
181
+ | 2.7419 | 5.4377 | 5106 | 1.8286 | 0.7803 |
182
+ | 2.7482 | 5.4867 | 5152 | 2.4683 | 0.7757 |
183
+ | 2.71 | 5.5357 | 5198 | 2.1428 | 0.8284 |
184
+ | 2.748 | 5.5847 | 5244 | 2.4891 | 0.7521 |
185
+ | 2.7128 | 5.6337 | 5290 | 2.1653 | 0.7025 |
186
+ | 2.6697 | 5.6826 | 5336 | 2.3304 | 0.7536 |
187
+ | 2.7055 | 5.7316 | 5382 | 2.1923 | 0.8314 |
188
+ | 2.7485 | 5.7806 | 5428 | 1.9645 | 0.6957 |
189
+ | 2.6862 | 5.8296 | 5474 | 2.4469 | 0.7857 |
190
+ | 2.6268 | 5.8786 | 5520 | 2.0508 | 0.8223 |
191
+ | 2.6629 | 5.9276 | 5566 | 3.1371 | 0.7857 |
192
+ | 2.7136 | 5.9766 | 5612 | 2.3568 | 0.8124 |
193
+ | 2.5939 | 6.0256 | 5658 | 2.2982 | 0.7902 |
194
+ | 2.5209 | 6.0745 | 5704 | 2.1673 | 0.9092 |
195
+ | 2.5205 | 6.1235 | 5750 | 1.6860 | 0.8078 |
196
+ | 2.5426 | 6.1725 | 5796 | 2.5552 | 0.8223 |
197
+ | 2.4915 | 6.2215 | 5842 | 2.5377 | 0.8146 |
198
+ | 2.5388 | 6.2705 | 5888 | 2.0584 | 0.9443 |
199
+ | 2.5655 | 6.3195 | 5934 | 2.1900 | 0.6613 |
200
+ | 2.5462 | 6.3685 | 5980 | 1.9014 | 0.6461 |
201
+ | 2.4827 | 6.4175 | 6026 | 2.0078 | 0.7864 |
202
+ | 2.5831 | 6.4665 | 6072 | 2.0717 | 0.8002 |
203
+ | 2.4698 | 6.5154 | 6118 | 2.1906 | 0.7262 |
204
+ | 2.4836 | 6.5644 | 6164 | 1.9154 | 0.8246 |
205
+ | 2.5318 | 6.6134 | 6210 | 2.1880 | 0.6133 |
206
+ | 2.5121 | 6.6624 | 6256 | 1.7957 | 0.7719 |
207
+ | 2.468 | 6.7114 | 6302 | 1.9780 | 0.6522 |
208
+ | 2.4082 | 6.7604 | 6348 | 1.9565 | 0.8063 |
209
+ | 2.4947 | 6.8094 | 6394 | 1.6497 | 0.7086 |
210
+ | 2.4975 | 6.8584 | 6440 | 2.3719 | 0.6659 |
211
+ | 2.4624 | 6.9073 | 6486 | 1.6827 | 0.6743 |
212
+ | 2.4428 | 6.9563 | 6532 | 2.0943 | 0.6949 |
213
+ | 2.4522 | 7.0053 | 6578 | 2.1424 | 0.7483 |
214
+ | 2.3723 | 7.0543 | 6624 | 1.9519 | 0.8505 |
215
+ | 2.3791 | 7.1033 | 6670 | 2.3679 | 0.7780 |
216
+ | 2.3894 | 7.1523 | 6716 | 1.5468 | 0.8047 |
217
+ | 2.3466 | 7.2013 | 6762 | 1.9894 | 0.6026 |
218
+ | 2.3545 | 7.2503 | 6808 | 2.1756 | 0.8131 |
219
+ | 2.4152 | 7.2993 | 6854 | 1.6656 | 0.9161 |
220
+ | 2.2915 | 7.3482 | 6900 | 2.6449 | 0.7353 |
221
+ | 2.3213 | 7.3972 | 6946 | 1.8635 | 0.6880 |
222
+ | 2.3227 | 7.4462 | 6992 | 1.9249 | 0.7590 |
223
+ | 2.3498 | 7.4952 | 7038 | 2.2339 | 0.6697 |
224
+ | 2.3458 | 7.5442 | 7084 | 1.7145 | 0.6690 |
225
+ | 2.2996 | 7.5932 | 7130 | 2.0018 | 0.6384 |
226
+ | 2.309 | 7.6422 | 7176 | 2.4001 | 0.6697 |
227
+ | 2.3566 | 7.6912 | 7222 | 1.9882 | 0.6827 |
228
+ | 2.3619 | 7.7401 | 7268 | 2.2134 | 0.7452 |
229
+ | 2.3768 | 7.7891 | 7314 | 1.9402 | 0.6499 |
230
+ | 2.343 | 7.8381 | 7360 | 2.3600 | 0.6377 |
231
+ | 2.3364 | 7.8871 | 7406 | 2.3632 | 0.7277 |
232
+ | 2.2965 | 7.9361 | 7452 | 2.0428 | 0.7597 |
233
+ | 2.3314 | 7.9851 | 7498 | 1.8117 | 0.6522 |
234
+ | 2.2367 | 8.0341 | 7544 | 1.8227 | 0.7818 |
235
+ | 2.2004 | 8.0831 | 7590 | 1.8653 | 0.8986 |
236
+ | 2.2355 | 8.1321 | 7636 | 1.5815 | 0.7193 |
237
+ | 2.2735 | 8.1810 | 7682 | 1.8200 | 0.7376 |
238
+ | 2.2016 | 8.2300 | 7728 | 2.1064 | 0.7757 |
239
+ | 2.2236 | 8.2790 | 7774 | 2.1960 | 0.7277 |
240
+ | 2.2629 | 8.3280 | 7820 | 1.8969 | 1.0153 |
241
+ | 2.2333 | 8.3770 | 7866 | 1.9392 | 0.7780 |
242
+ | 2.3081 | 8.4260 | 7912 | 2.0788 | 0.7773 |
243
+ | 2.2394 | 8.4750 | 7958 | 1.7624 | 0.8307 |
244
+ | 2.2689 | 8.5240 | 8004 | 1.6819 | 0.7483 |
245
+ | 2.2141 | 8.5729 | 8050 | 2.2714 | 0.6941 |
246
+ | 2.2491 | 8.6219 | 8096 | 1.5813 | 0.8749 |
247
+ | 2.2547 | 8.6709 | 8142 | 1.7303 | 0.7376 |
248
+ | 2.2452 | 8.7199 | 8188 | 2.1367 | 0.7086 |
249
+ | 2.1973 | 8.7689 | 8234 | 2.5364 | 0.7948 |
250
+ | 2.1983 | 8.8179 | 8280 | 2.5068 | 0.6560 |
251
+ | 2.2147 | 8.8669 | 8326 | 1.8437 | 0.6834 |
252
+ | 2.1853 | 8.9159 | 8372 | 2.0133 | 0.5652 |
253
+ | 2.1776 | 8.9649 | 8418 | 2.0903 | 0.5866 |
254
+ | 2.1158 | 9.0138 | 8464 | 1.8758 | 0.5660 |
255
+ | 2.1226 | 9.0628 | 8510 | 2.0116 | 0.7002 |
256
+ | 2.0988 | 9.1118 | 8556 | 1.7681 | 0.6041 |
257
+ | 2.1063 | 9.1608 | 8602 | 2.2456 | 0.6964 |
258
+ | 2.0862 | 9.2098 | 8648 | 1.7496 | 0.5858 |
259
+ | 2.177 | 9.2588 | 8694 | 1.9786 | 0.7414 |
260
+ | 2.113 | 9.3078 | 8740 | 2.1259 | 0.6987 |
261
+ | 2.152 | 9.3568 | 8786 | 1.8785 | 0.7269 |
262
+ | 2.1315 | 9.4058 | 8832 | 1.9563 | 0.6911 |
263
+ | 2.1425 | 9.4547 | 8878 | 1.9474 | 0.7170 |
264
+ | 2.1126 | 9.5037 | 8924 | 1.9101 | 0.7109 |
265
+ | 2.1793 | 9.5527 | 8970 | 2.1603 | 0.6895 |
266
+ | 2.1184 | 9.6017 | 9016 | 1.9047 | 0.6903 |
267
+ | 2.1878 | 9.6507 | 9062 | 1.7960 | 0.6903 |
268
+ | 2.1172 | 9.6997 | 9108 | 1.9387 | 0.6842 |
269
+ | 2.16 | 9.7487 | 9154 | 1.9603 | 0.5286 |
270
+ | 2.1817 | 9.7977 | 9200 | 2.0296 | 0.8032 |
271
+ | 2.1776 | 9.8466 | 9246 | 2.3591 | 0.6705 |
272
+ | 2.1488 | 9.8956 | 9292 | 2.1115 | 0.6728 |
273
+ | 2.1173 | 9.9446 | 9338 | 2.0452 | 0.7879 |
274
+ | 2.1313 | 9.9936 | 9384 | 1.6271 | 0.6621 |
275
+ | 2.0773 | 10.0426 | 9430 | 1.6572 | 0.5576 |
276
+ | 2.0741 | 10.0916 | 9476 | 1.7347 | 0.5736 |
277
+ | 2.0192 | 10.1406 | 9522 | 1.9669 | 0.6514 |
278
+ | 2.0133 | 10.1896 | 9568 | 2.3957 | 0.5324 |
279
+ | 2.0137 | 10.2386 | 9614 | 1.9313 | 0.5523 |
280
+ | 2.0878 | 10.2875 | 9660 | 1.7588 | 0.6781 |
281
+ | 2.0918 | 10.3365 | 9706 | 1.5897 | 0.6583 |
282
+ | 2.1368 | 10.3855 | 9752 | 1.8707 | 0.6552 |
283
+ | 2.031 | 10.4345 | 9798 | 1.8737 | 0.6636 |
284
+ | 2.0823 | 10.4835 | 9844 | 2.0404 | 0.6705 |
285
+ | 2.0599 | 10.5325 | 9890 | 2.6899 | 0.5362 |
286
+ | 2.0768 | 10.5815 | 9936 | 2.2819 | 0.6690 |
287
+ | 2.0301 | 10.6305 | 9982 | 1.8063 | 0.6636 |
288
+ | 2.0973 | 10.6794 | 10028 | 1.7077 | 0.6758 |
289
+ | 2.0989 | 10.7284 | 10074 | 2.0836 | 0.6735 |
290
+ | 2.0378 | 10.7774 | 10120 | 1.9060 | 0.6659 |
291
+ | 2.0974 | 10.8264 | 10166 | 2.1084 | 0.6461 |
292
+ | 2.054 | 10.8754 | 10212 | 1.7876 | 0.7994 |
293
+ | 2.0315 | 10.9244 | 10258 | 1.7286 | 0.7643 |
294
+ | 2.0554 | 10.9734 | 10304 | 1.5515 | 0.6598 |
295
+ | 2.0493 | 11.0224 | 10350 | 1.7260 | 0.6529 |
296
+ | 2.0261 | 11.0714 | 10396 | 1.7375 | 0.6834 |
297
+ | 2.0386 | 11.1203 | 10442 | 2.3579 | 0.6560 |
298
+ | 1.9837 | 11.1693 | 10488 | 1.7646 | 0.6529 |
299
+ | 1.98 | 11.2183 | 10534 | 1.8462 | 0.6354 |
300
+ | 2.0112 | 11.2673 | 10580 | 2.2094 | 0.6354 |
301
+ | 2.013 | 11.3163 | 10626 | 1.6524 | 0.7818 |
302
+ | 1.9644 | 11.3653 | 10672 | 1.9840 | 0.6400 |
303
+ | 2.0306 | 11.4143 | 10718 | 1.7322 | 0.6377 |
304
+ | 1.9994 | 11.4633 | 10764 | 1.6268 | 0.6323 |
305
+ | 1.9911 | 11.5122 | 10810 | 1.5183 | 0.6423 |
306
+ | 2.0069 | 11.5612 | 10856 | 1.8589 | 0.6590 |
307
+ | 1.9997 | 11.6102 | 10902 | 1.4175 | 0.6392 |
308
+ | 2.0322 | 11.6592 | 10948 | 1.7353 | 0.6461 |
309
+ | 2.0006 | 11.7082 | 10994 | 1.7597 | 0.6461 |
310
+ | 1.9669 | 11.7572 | 11040 | 1.3823 | 0.6377 |
311
+ | 1.9959 | 11.8062 | 11086 | 1.8571 | 0.7048 |
312
+ | 1.9959 | 11.8552 | 11132 | 1.7335 | 0.6789 |
313
+ | 2.0528 | 11.9042 | 11178 | 2.1097 | 0.6522 |
314
+ | 2.034 | 11.9531 | 11224 | 1.9425 | 0.7460 |
315
+ | 1.9614 | 12.0021 | 11270 | 1.7729 | 0.6712 |
316
+ | 1.962 | 12.0511 | 11316 | 1.5280 | 0.6461 |
317
+ | 1.9259 | 12.1001 | 11362 | 1.8746 | 0.6758 |
318
+ | 1.9713 | 12.1491 | 11408 | 1.8781 | 0.6209 |
319
+ | 1.9583 | 12.1981 | 11454 | 1.6248 | 0.7796 |
320
+ | 1.9185 | 12.2471 | 11500 | 1.7218 | 0.8063 |
321
+ | 1.9682 | 12.2961 | 11546 | 1.6681 | 0.6491 |
322
+ | 1.9236 | 12.3450 | 11592 | 1.7581 | 0.7902 |
323
+ | 1.9506 | 12.3940 | 11638 | 1.5125 | 0.7079 |
324
+ | 1.9488 | 12.4430 | 11684 | 1.2381 | 0.6568 |
325
+ | 1.9377 | 12.4920 | 11730 | 2.0817 | 0.5339 |
326
+ | 2.0095 | 12.5410 | 11776 | 2.3150 | 0.6705 |
327
+ | 1.9564 | 12.5900 | 11822 | 1.9439 | 0.6499 |
328
+ | 1.9855 | 12.6390 | 11868 | 1.4350 | 0.6377 |
329
+ | 1.9712 | 12.6880 | 11914 | 1.6765 | 0.5072 |
330
+ | 1.9449 | 12.7370 | 11960 | 1.6882 | 0.7429 |
331
+ | 1.9315 | 12.7859 | 12006 | 2.1650 | 0.6690 |
332
+ | 1.9938 | 12.8349 | 12052 | 1.7770 | 0.5217 |
333
+ | 1.9731 | 12.8839 | 12098 | 2.0976 | 0.5217 |
334
+ | 1.8989 | 12.9329 | 12144 | 1.3949 | 0.7544 |
335
+ | 1.9263 | 12.9819 | 12190 | 1.6227 | 0.6590 |
336
+ | 1.8839 | 13.0309 | 12236 | 2.0962 | 0.7620 |
337
+ | 1.8477 | 13.0799 | 12282 | 1.9402 | 0.6705 |
338
+ | 1.901 | 13.1289 | 12328 | 1.8062 | 0.6354 |
339
+ | 1.8702 | 13.1778 | 12374 | 2.0144 | 0.6407 |
340
+ | 1.8507 | 13.2268 | 12420 | 1.9302 | 0.6613 |
341
+ | 1.8718 | 13.2758 | 12466 | 1.7976 | 0.6316 |
342
+ | 1.8647 | 13.3248 | 12512 | 1.7692 | 0.7597 |
343
+ | 1.9419 | 13.3738 | 12558 | 1.7708 | 0.7773 |
344
+ | 1.9313 | 13.4228 | 12604 | 2.2976 | 0.5645 |
345
+ | 1.9554 | 13.4718 | 12650 | 1.7321 | 0.5118 |
346
+ | 1.9277 | 13.5208 | 12696 | 2.1339 | 0.6697 |
347
+ | 1.9022 | 13.5698 | 12742 | 1.7016 | 0.6445 |
348
+ | 1.9343 | 13.6187 | 12788 | 1.3628 | 0.6606 |
349
+ | 1.8859 | 13.6677 | 12834 | 1.8999 | 0.5347 |
350
+ | 1.9809 | 13.7167 | 12880 | 1.7508 | 0.7849 |
351
+ | 1.9133 | 13.7657 | 12926 | 1.7578 | 0.6568 |
352
+ | 1.8508 | 13.8147 | 12972 | 1.9824 | 0.6468 |
353
+ | 1.9198 | 13.8637 | 13018 | 1.7049 | 0.6430 |
354
+ | 1.9591 | 13.9127 | 13064 | 2.1335 | 0.6537 |
355
+ | 1.9544 | 13.9617 | 13110 | 1.6545 | 0.6667 |
356
+ | 1.9176 | 14.0106 | 13156 | 1.8152 | 0.6606 |
357
+ | 1.8167 | 14.0596 | 13202 | 1.6567 | 0.6392 |
358
+ | 1.8611 | 14.1086 | 13248 | 1.7093 | 0.6484 |
359
+ | 1.8082 | 14.1576 | 13294 | 1.7650 | 0.7216 |
360
+ | 1.852 | 14.2066 | 13340 | 1.7747 | 0.6537 |
361
+ | 1.8505 | 14.2556 | 13386 | 2.0744 | 0.6438 |
362
+ | 1.854 | 14.3046 | 13432 | 1.9691 | 0.6369 |
363
+ | 1.9041 | 14.3536 | 13478 | 2.0058 | 0.6438 |
364
+ | 1.8661 | 14.4026 | 13524 | 1.9013 | 0.5156 |
365
+ | 1.8366 | 14.4515 | 13570 | 1.7564 | 0.7162 |
366
+ | 1.8687 | 14.5005 | 13616 | 2.0942 | 0.6499 |
367
+ | 1.821 | 14.5495 | 13662 | 1.6824 | 0.6392 |
368
+ | 1.9413 | 14.5985 | 13708 | 1.5903 | 0.6247 |
369
+ | 1.8735 | 14.6475 | 13754 | 1.6288 | 0.6034 |
370
+ | 1.8829 | 14.6965 | 13800 | 1.6204 | 0.6285 |
371
+ | 1.8803 | 14.7455 | 13846 | 1.4950 | 0.6423 |
372
+ | 1.8325 | 14.7945 | 13892 | 1.5955 | 0.6445 |
373
+ | 1.905 | 14.8435 | 13938 | 1.7597 | 0.6308 |
374
+ | 1.9291 | 14.8924 | 13984 | 1.6754 | 0.6453 |
375
+ | 1.8646 | 14.9414 | 14030 | 1.7679 | 0.6400 |
376
+ | 1.8707 | 14.9904 | 14076 | 1.4442 | 0.6430 |
377
+ | 1.8016 | 15.0394 | 14122 | 2.3060 | 0.5294 |
378
+ | 1.787 | 15.0884 | 14168 | 1.5995 | 0.5393 |
379
+ | 1.8801 | 15.1374 | 14214 | 1.8316 | 0.6529 |
380
+ | 1.837 | 15.1864 | 14260 | 2.0738 | 0.6400 |
381
+ | 1.7394 | 15.2354 | 14306 | 1.5721 | 0.6423 |
382
+ | 1.8477 | 15.2843 | 14352 | 1.3338 | 0.6400 |
383
+ | 1.7935 | 15.3333 | 14398 | 1.9281 | 0.6468 |
384
+ | 1.8399 | 15.3823 | 14444 | 1.5838 | 0.7788 |
385
+ | 1.8112 | 15.4313 | 14490 | 1.9815 | 0.6583 |
386
+ | 1.8274 | 15.4803 | 14536 | 2.2566 | 0.6575 |
387
+ | 1.8122 | 15.5293 | 14582 | 2.0499 | 0.6331 |
388
+ | 1.8572 | 15.5783 | 14628 | 2.1192 | 0.6598 |
389
+ | 1.8645 | 15.6273 | 14674 | 1.6720 | 0.6423 |
390
+ | 1.8131 | 15.6763 | 14720 | 1.8248 | 0.6301 |
391
+ | 1.8575 | 15.7252 | 14766 | 1.4994 | 0.6453 |
392
+ | 1.8619 | 15.7742 | 14812 | 1.6240 | 0.6438 |
393
+ | 1.8769 | 15.8232 | 14858 | 1.5106 | 0.5278 |
394
+ | 1.8663 | 15.8722 | 14904 | 1.3819 | 0.6529 |
395
+ | 1.8752 | 15.9212 | 14950 | 1.3656 | 0.6568 |
396
+ | 1.8053 | 15.9702 | 14996 | 1.7036 | 0.6690 |
397
+ | 1.8678 | 16.0192 | 15042 | 1.5174 | 0.6346 |
398
+ | 1.7752 | 16.0682 | 15088 | 1.4907 | 0.6537 |
399
+ | 1.7651 | 16.1171 | 15134 | 1.6303 | 0.5767 |
400
+ | 1.757 | 16.1661 | 15180 | 1.7852 | 0.6781 |
401
+ | 1.8053 | 16.2151 | 15226 | 1.9609 | 0.7643 |
402
+ | 1.8682 | 16.2641 | 15272 | 1.8553 | 0.7620 |
403
+ | 1.7658 | 16.3131 | 15318 | 1.4196 | 0.6468 |
404
+ | 1.8486 | 16.3621 | 15364 | 1.5508 | 0.5286 |
405
+ | 1.8058 | 16.4111 | 15410 | 1.8765 | 0.6552 |
406
+ | 1.7903 | 16.4601 | 15456 | 1.4543 | 0.6362 |
407
+ | 1.792 | 16.5091 | 15502 | 1.4766 | 0.7582 |
408
+ | 1.8187 | 16.5580 | 15548 | 1.6855 | 0.6545 |
409
+ | 1.7796 | 16.6070 | 15594 | 1.6344 | 0.6484 |
410
+ | 1.8007 | 16.6560 | 15640 | 1.7046 | 0.6728 |
411
+ | 1.8026 | 16.7050 | 15686 | 2.1069 | 0.7346 |
412
+ | 1.7634 | 16.7540 | 15732 | 1.5729 | 0.6384 |
413
+ | 1.8301 | 16.8030 | 15778 | 2.1951 | 0.6301 |
414
+ | 1.8223 | 16.8520 | 15824 | 1.6852 | 0.6423 |
415
+ | 1.8118 | 16.9010 | 15870 | 2.2032 | 0.7689 |
416
+ | 1.816 | 16.9499 | 15916 | 1.7206 | 0.6537 |
417
+ | 1.8374 | 16.9989 | 15962 | 1.6348 | 0.5278 |
418
+ | 1.7789 | 17.0479 | 16008 | 1.6877 | 0.6529 |
419
+ | 1.7469 | 17.0969 | 16054 | 1.7128 | 0.6331 |
420
+ | 1.7637 | 17.1459 | 16100 | 1.5377 | 0.6423 |
421
+ | 1.7372 | 17.1949 | 16146 | 2.0307 | 0.6384 |
422
+ | 1.7499 | 17.2439 | 16192 | 1.7091 | 0.5111 |
423
+ | 1.7931 | 17.2929 | 16238 | 2.0855 | 0.5339 |
424
+ | 1.7451 | 17.3419 | 16284 | 1.6822 | 0.6476 |
425
+ | 1.8153 | 17.3908 | 16330 | 1.7438 | 0.6560 |
426
+ | 1.7375 | 17.4398 | 16376 | 1.4717 | 0.6430 |
427
+ | 1.7428 | 17.4888 | 16422 | 1.8217 | 0.6438 |
428
+ | 1.7769 | 17.5378 | 16468 | 2.3484 | 0.6484 |
429
+ | 1.7796 | 17.5868 | 16514 | 1.5592 | 0.6240 |
430
+ | 1.7906 | 17.6358 | 16560 | 1.6696 | 0.5400 |
431
+ | 1.7823 | 17.6848 | 16606 | 1.8514 | 0.6415 |
432
+ | 1.7789 | 17.7338 | 16652 | 1.9547 | 0.6369 |
433
+ | 1.7961 | 17.7827 | 16698 | 1.6291 | 0.6072 |
434
+ | 1.8065 | 17.8317 | 16744 | 1.7687 | 0.5118 |
435
+ | 1.7731 | 17.8807 | 16790 | 1.8033 | 0.6247 |
436
+ | 1.7882 | 17.9297 | 16836 | 1.7939 | 0.6232 |
437
+ | 1.8064 | 17.9787 | 16882 | 1.5902 | 0.6217 |
438
+ | 1.7373 | 18.0277 | 16928 | 1.7263 | 0.6522 |
439
+ | 1.6917 | 18.0767 | 16974 | 1.6079 | 0.6240 |
440
+ | 1.7446 | 18.1257 | 17020 | 1.7779 | 0.5004 |
441
+ | 1.7153 | 18.1747 | 17066 | 1.8259 | 0.6339 |
442
+ | 1.7126 | 18.2236 | 17112 | 2.3720 | 0.6148 |
443
+ | 1.7564 | 18.2726 | 17158 | 1.7281 | 0.6209 |
444
+ | 1.7314 | 18.3216 | 17204 | 1.9946 | 0.6392 |
445
+ | 1.7026 | 18.3706 | 17250 | 1.8865 | 0.5011 |
446
+ | 1.7182 | 18.4196 | 17296 | 1.9260 | 0.6171 |
447
+ | 1.7455 | 18.4686 | 17342 | 1.4056 | 0.5317 |
448
+ | 1.7392 | 18.5176 | 17388 | 1.6926 | 0.7338 |
449
+ | 1.7899 | 18.5666 | 17434 | 1.8091 | 0.6240 |
450
+ | 1.7806 | 18.6155 | 17480 | 1.7749 | 0.7681 |
451
+ | 1.7724 | 18.6645 | 17526 | 1.8705 | 0.7429 |
452
+ | 1.7587 | 18.7135 | 17572 | 2.3208 | 0.6331 |
453
+ | 1.7952 | 18.7625 | 17618 | 1.3462 | 0.6201 |
454
+ | 1.7307 | 18.8115 | 17664 | 1.8886 | 0.6224 |
455
+ | 1.753 | 18.8605 | 17710 | 1.3937 | 0.6041 |
456
+ | 1.7489 | 18.9095 | 17756 | 1.7212 | 0.6285 |
457
+ | 1.7813 | 18.9585 | 17802 | 1.4511 | 0.6339 |
458
+ | 1.809 | 19.0075 | 17848 | 1.8004 | 0.7109 |
459
+ | 1.7159 | 19.0564 | 17894 | 1.3388 | 0.6217 |
460
+ | 1.6689 | 19.1054 | 17940 | 1.5340 | 0.6369 |
461
+ | 1.7843 | 19.1544 | 17986 | 2.0322 | 0.6377 |
462
+ | 1.6666 | 19.2034 | 18032 | 1.6485 | 0.5050 |
463
+ | 1.687 | 19.2524 | 18078 | 1.6644 | 0.6316 |
464
+ | 1.749 | 19.3014 | 18124 | 1.6634 | 0.6415 |
465
+ | 1.7424 | 19.3504 | 18170 | 1.2414 | 0.6583 |
466
+ | 1.7427 | 19.3994 | 18216 | 1.6178 | 0.6194 |
467
+ | 1.7569 | 19.4483 | 18262 | 1.7098 | 0.6537 |
468
+ | 1.7066 | 19.4973 | 18308 | 1.9851 | 0.6079 |
469
+ | 1.6939 | 19.5463 | 18354 | 1.5820 | 0.6461 |
470
+ | 1.753 | 19.5953 | 18400 | 2.1611 | 0.6178 |
471
+ | 1.7409 | 19.6443 | 18446 | 1.6006 | 0.6293 |
472
+ | 1.7067 | 19.6933 | 18492 | 1.8803 | 0.6392 |
473
+ | 1.7357 | 19.7423 | 18538 | 1.7975 | 0.6285 |
474
+ | 1.7447 | 19.7913 | 18584 | 1.2941 | 0.6262 |
475
+ | 1.7333 | 19.8403 | 18630 | 1.5589 | 0.6323 |
476
+ | 1.6887 | 19.8892 | 18676 | 1.5650 | 0.6415 |
477
+ | 1.7471 | 19.9382 | 18722 | 1.8929 | 0.6354 |
478
+ | 1.7192 | 19.9872 | 18768 | 1.5802 | 0.6377 |
479
+ | 1.663 | 20.0362 | 18814 | 1.8607 | 0.6476 |
480
+ | 1.6894 | 20.0852 | 18860 | 1.7199 | 0.6461 |
481
+ | 1.6571 | 20.1342 | 18906 | 2.1788 | 0.5011 |
482
+ | 1.7115 | 20.1832 | 18952 | 1.6524 | 0.6484 |
483
+ | 1.7307 | 20.2322 | 18998 | 1.4865 | 0.6262 |
484
+ | 1.6654 | 20.2812 | 19044 | 2.1040 | 0.6590 |
485
+ | 1.6871 | 20.3301 | 19090 | 1.6146 | 0.6468 |
486
+ | 1.6979 | 20.3791 | 19136 | 1.3820 | 0.6522 |
487
+ | 1.7569 | 20.4281 | 19182 | 1.4875 | 0.6369 |
488
+ | 1.6833 | 20.4771 | 19228 | 2.1289 | 0.6316 |
489
+ | 1.6981 | 20.5261 | 19274 | 1.7743 | 0.6278 |
490
+ | 1.6844 | 20.5751 | 19320 | 1.7059 | 0.6621 |
491
+
492
+
493
+ ### Framework versions
494
+
495
+ - Transformers 4.49.0
496
+ - Pytorch 2.6.0+cu124
497
+ - Datasets 3.4.0
498
+ - Tokenizers 0.21.0
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 0,
3
+ "decoder_start_token_id": 2,
4
+ "early_stopping": true,
5
+ "eos_token_id": 2,
6
+ "max_length": 200,
7
+ "num_beams": 5,
8
+ "pad_token_id": 1,
9
+ "transformers_version": "4.49.0"
10
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be4d977ab699f549ba44197076d2437d125f4528fcc7e2904992c8091c23e856
3
  size 130512784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26c8c0845ca72af3ec08c40f0b400f31be5a9d538df210e8ba7df6b9c9c961be
3
  size 130512784