Hugging Face's logo

pancake5000
/
calculator_model_test

Transformers
Safetensors
encoder-decoder
text2text-generation
Generated from Trainer
Model card Files
xet
 Community
pancake5000 commited on
Commit
c5fb1b8
·
verified ·
1 Parent(s): ae58701

End of training

Browse files
Files changed (1) hide show
  1. README.md +101 -101
README.md CHANGED
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 0.2194
18
 
19
  ## Model description
20
 
@@ -45,106 +45,106 @@ The following hyperparameters were used during training:
45
 
46
  | Training Loss | Epoch | Step | Validation Loss |
47
  |:-------------:|:-----:|:----:|:---------------:|
48
- | 0.7783 | 1.0 | 5 | 0.7444 |
49
- | 0.7419 | 2.0 | 10 | 0.7197 |
50
- | 0.7198 | 3.0 | 15 | 0.7016 |
51
- | 0.7003 | 4.0 | 20 | 0.6833 |
52
- | 0.6839 | 5.0 | 25 | 0.6673 |
53
- | 0.6668 | 6.0 | 30 | 0.6508 |
54
- | 0.6546 | 7.0 | 35 | 0.6350 |
55
- | 0.6424 | 8.0 | 40 | 0.6224 |
56
- | 0.6298 | 9.0 | 45 | 0.6088 |
57
- | 0.6166 | 10.0 | 50 | 0.5985 |
58
- | 0.6032 | 11.0 | 55 | 0.5866 |
59
- | 0.5930 | 12.0 | 60 | 0.5742 |
60
- | 0.5825 | 13.0 | 65 | 0.5622 |
61
- | 0.5695 | 14.0 | 70 | 0.5530 |
62
- | 0.5586 | 15.0 | 75 | 0.5394 |
63
- | 0.5491 | 16.0 | 80 | 0.5299 |
64
- | 0.5385 | 17.0 | 85 | 0.5197 |
65
- | 0.5276 | 18.0 | 90 | 0.5100 |
66
- | 0.5210 | 19.0 | 95 | 0.5008 |
67
- | 0.5110 | 20.0 | 100 | 0.4924 |
68
- | 0.5024 | 21.0 | 105 | 0.4831 |
69
- | 0.4930 | 22.0 | 110 | 0.4740 |
70
- | 0.4839 | 23.0 | 115 | 0.4648 |
71
- | 0.4753 | 24.0 | 120 | 0.4554 |
72
- | 0.4669 | 25.0 | 125 | 0.4496 |
73
- | 0.4617 | 26.0 | 130 | 0.4398 |
74
- | 0.4530 | 27.0 | 135 | 0.4321 |
75
- | 0.4466 | 28.0 | 140 | 0.4243 |
76
- | 0.4401 | 29.0 | 145 | 0.4188 |
77
- | 0.4353 | 30.0 | 150 | 0.4108 |
78
- | 0.4244 | 31.0 | 155 | 0.4021 |
79
- | 0.4196 | 32.0 | 160 | 0.3963 |
80
- | 0.4145 | 33.0 | 165 | 0.3898 |
81
- | 0.4085 | 34.0 | 170 | 0.3837 |
82
- | 0.3991 | 35.0 | 175 | 0.3761 |
83
- | 0.3955 | 36.0 | 180 | 0.3723 |
84
- | 0.3889 | 37.0 | 185 | 0.3666 |
85
- | 0.3851 | 38.0 | 190 | 0.3609 |
86
- | 0.3805 | 39.0 | 195 | 0.3560 |
87
- | 0.3747 | 40.0 | 200 | 0.3481 |
88
- | 0.3707 | 41.0 | 205 | 0.3438 |
89
- | 0.3653 | 42.0 | 210 | 0.3410 |
90
- | 0.3609 | 43.0 | 215 | 0.3353 |
91
- | 0.3577 | 44.0 | 220 | 0.3295 |
92
- | 0.3537 | 45.0 | 225 | 0.3252 |
93
- | 0.3487 | 46.0 | 230 | 0.3217 |
94
- | 0.3458 | 47.0 | 235 | 0.3182 |
95
- | 0.3386 | 48.0 | 240 | 0.3129 |
96
- | 0.3355 | 49.0 | 245 | 0.3085 |
97
- | 0.3333 | 50.0 | 250 | 0.3043 |
98
- | 0.3296 | 51.0 | 255 | 0.3019 |
99
- | 0.3258 | 52.0 | 260 | 0.2975 |
100
- | 0.3215 | 53.0 | 265 | 0.2937 |
101
- | 0.3181 | 54.0 | 270 | 0.2909 |
102
- | 0.3161 | 55.0 | 275 | 0.2860 |
103
- | 0.3104 | 56.0 | 280 | 0.2839 |
104
- | 0.3098 | 57.0 | 285 | 0.2803 |
105
- | 0.3075 | 58.0 | 290 | 0.2773 |
106
- | 0.3058 | 59.0 | 295 | 0.2757 |
107
- | 0.3012 | 60.0 | 300 | 0.2712 |
108
- | 0.2986 | 61.0 | 305 | 0.2690 |
109
- | 0.2948 | 62.0 | 310 | 0.2659 |
110
- | 0.2963 | 63.0 | 315 | 0.2635 |
111
- | 0.2923 | 64.0 | 320 | 0.2608 |
112
- | 0.2888 | 65.0 | 325 | 0.2582 |
113
- | 0.2848 | 66.0 | 330 | 0.2574 |
114
- | 0.2877 | 67.0 | 335 | 0.2534 |
115
- | 0.2841 | 68.0 | 340 | 0.2508 |
116
- | 0.2820 | 69.0 | 345 | 0.2493 |
117
- | 0.2795 | 70.0 | 350 | 0.2471 |
118
- | 0.2781 | 71.0 | 355 | 0.2459 |
119
- | 0.2760 | 72.0 | 360 | 0.2441 |
120
- | 0.2746 | 73.0 | 365 | 0.2435 |
121
- | 0.2713 | 74.0 | 370 | 0.2401 |
122
- | 0.2696 | 75.0 | 375 | 0.2398 |
123
- | 0.2709 | 76.0 | 380 | 0.2384 |
124
- | 0.2682 | 77.0 | 385 | 0.2353 |
125
- | 0.2636 | 78.0 | 390 | 0.2340 |
126
- | 0.2640 | 79.0 | 395 | 0.2335 |
127
- | 0.2647 | 80.0 | 400 | 0.2322 |
128
- | 0.2648 | 81.0 | 405 | 0.2309 |
129
- | 0.2628 | 82.0 | 410 | 0.2297 |
130
- | 0.2605 | 83.0 | 415 | 0.2291 |
131
- | 0.2593 | 84.0 | 420 | 0.2272 |
132
- | 0.2599 | 85.0 | 425 | 0.2264 |
133
- | 0.2578 | 86.0 | 430 | 0.2249 |
134
- | 0.2553 | 87.0 | 435 | 0.2246 |
135
- | 0.2560 | 88.0 | 440 | 0.2239 |
136
- | 0.2550 | 89.0 | 445 | 0.2230 |
137
- | 0.2548 | 90.0 | 450 | 0.2227 |
138
- | 0.2554 | 91.0 | 455 | 0.2220 |
139
- | 0.2562 | 92.0 | 460 | 0.2212 |
140
- | 0.2546 | 93.0 | 465 | 0.2208 |
141
- | 0.2527 | 94.0 | 470 | 0.2209 |
142
- | 0.2541 | 95.0 | 475 | 0.2200 |
143
- | 0.2527 | 96.0 | 480 | 0.2198 |
144
- | 0.2520 | 97.0 | 485 | 0.2196 |
145
- | 0.2513 | 98.0 | 490 | 0.2195 |
146
- | 0.2538 | 99.0 | 495 | 0.2195 |
147
- | 0.2528 | 100.0 | 500 | 0.2194 |
148
 
149
 
150
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 0.4887
18
 
19
  ## Model description
20
 
 
45
 
46
  | Training Loss | Epoch | Step | Validation Loss |
47
  |:-------------:|:-----:|:----:|:---------------:|
48
+ | 3.7992 | 1.0 | 4 | 3.3759 |
49
+ | 3.2713 | 2.0 | 8 | 3.0747 |
50
+ | 3.0077 | 3.0 | 12 | 2.8470 |
51
+ | 2.8017 | 4.0 | 16 | 2.6776 |
52
+ | 2.6544 | 5.0 | 20 | 2.5598 |
53
+ | 2.5406 | 6.0 | 24 | 2.4680 |
54
+ | 2.4533 | 7.0 | 28 | 2.3877 |
55
+ | 2.3706 | 8.0 | 32 | 2.3072 |
56
+ | 2.2888 | 9.0 | 36 | 2.2281 |
57
+ | 2.2113 | 10.0 | 40 | 2.1635 |
58
+ | 2.1521 | 11.0 | 44 | 2.0968 |
59
+ | 2.0820 | 12.0 | 48 | 2.0234 |
60
+ | 2.0103 | 13.0 | 52 | 1.9459 |
61
+ | 1.9386 | 14.0 | 56 | 1.8604 |
62
+ | 1.8504 | 15.0 | 60 | 1.7755 |
63
+ | 1.7743 | 16.0 | 64 | 1.6988 |
64
+ | 1.7016 | 17.0 | 68 | 1.6309 |
65
+ | 1.6317 | 18.0 | 72 | 1.5733 |
66
+ | 1.5746 | 19.0 | 76 | 1.5232 |
67
+ | 1.5296 | 20.0 | 80 | 1.4786 |
68
+ | 1.4842 | 21.0 | 84 | 1.4378 |
69
+ | 1.4424 | 22.0 | 88 | 1.3982 |
70
+ | 1.4026 | 23.0 | 92 | 1.3584 |
71
+ | 1.3666 | 24.0 | 96 | 1.3200 |
72
+ | 1.3270 | 25.0 | 100 | 1.2837 |
73
+ | 1.2885 | 26.0 | 104 | 1.2460 |
74
+ | 1.2536 | 27.0 | 108 | 1.2117 |
75
+ | 1.2224 | 28.0 | 112 | 1.1795 |
76
+ | 1.1877 | 29.0 | 116 | 1.1505 |
77
+ | 1.1601 | 30.0 | 120 | 1.1205 |
78
+ | 1.1318 | 31.0 | 124 | 1.0939 |
79
+ | 1.1067 | 32.0 | 128 | 1.0691 |
80
+ | 1.0819 | 33.0 | 132 | 1.0422 |
81
+ | 1.0510 | 34.0 | 136 | 1.0184 |
82
+ | 1.0321 | 35.0 | 140 | 0.9936 |
83
+ | 1.0098 | 36.0 | 144 | 0.9706 |
84
+ | 0.9784 | 37.0 | 148 | 0.9458 |
85
+ | 0.9552 | 38.0 | 152 | 0.9205 |
86
+ | 0.9388 | 39.0 | 156 | 0.8972 |
87
+ | 0.9144 | 40.0 | 160 | 0.8710 |
88
+ | 0.8855 | 41.0 | 164 | 0.8509 |
89
+ | 0.8683 | 42.0 | 168 | 0.8277 |
90
+ | 0.8407 | 43.0 | 172 | 0.8134 |
91
+ | 0.8343 | 44.0 | 176 | 0.7972 |
92
+ | 0.8074 | 45.0 | 180 | 0.7759 |
93
+ | 0.7915 | 46.0 | 184 | 0.7621 |
94
+ | 0.7782 | 47.0 | 188 | 0.7481 |
95
+ | 0.7615 | 48.0 | 192 | 0.7329 |
96
+ | 0.7475 | 49.0 | 196 | 0.7170 |
97
+ | 0.7301 | 50.0 | 200 | 0.7028 |
98
+ | 0.7258 | 51.0 | 204 | 0.6922 |
99
+ | 0.7165 | 52.0 | 208 | 0.6794 |
100
+ | 0.7019 | 53.0 | 212 | 0.6723 |
101
+ | 0.6936 | 54.0 | 216 | 0.6623 |
102
+ | 0.6817 | 55.0 | 220 | 0.6507 |
103
+ | 0.6698 | 56.0 | 224 | 0.6422 |
104
+ | 0.6609 | 57.0 | 228 | 0.6360 |
105
+ | 0.6599 | 58.0 | 232 | 0.6297 |
106
+ | 0.6467 | 59.0 | 236 | 0.6223 |
107
+ | 0.6475 | 60.0 | 240 | 0.6133 |
108
+ | 0.6388 | 61.0 | 244 | 0.6070 |
109
+ | 0.6265 | 62.0 | 248 | 0.5988 |
110
+ | 0.6248 | 63.0 | 252 | 0.5900 |
111
+ | 0.6150 | 64.0 | 256 | 0.5890 |
112
+ | 0.6124 | 65.0 | 260 | 0.5820 |
113
+ | 0.6042 | 66.0 | 264 | 0.5772 |
114
+ | 0.6059 | 67.0 | 268 | 0.5699 |
115
+ | 0.5938 | 68.0 | 272 | 0.5640 |
116
+ | 0.5920 | 69.0 | 276 | 0.5596 |
117
+ | 0.5904 | 70.0 | 280 | 0.5550 |
118
+ | 0.5843 | 71.0 | 284 | 0.5520 |
119
+ | 0.5784 | 72.0 | 288 | 0.5443 |
120
+ | 0.5716 | 73.0 | 292 | 0.5434 |
121
+ | 0.5674 | 74.0 | 296 | 0.5381 |
122
+ | 0.5629 | 75.0 | 300 | 0.5369 |
123
+ | 0.5635 | 76.0 | 304 | 0.5301 |
124
+ | 0.5572 | 77.0 | 308 | 0.5274 |
125
+ | 0.5574 | 78.0 | 312 | 0.5248 |
126
+ | 0.5529 | 79.0 | 316 | 0.5207 |
127
+ | 0.5472 | 80.0 | 320 | 0.5171 |
128
+ | 0.5497 | 81.0 | 324 | 0.5148 |
129
+ | 0.5475 | 82.0 | 328 | 0.5108 |
130
+ | 0.5360 | 83.0 | 332 | 0.5090 |
131
+ | 0.5498 | 84.0 | 336 | 0.5069 |
132
+ | 0.5367 | 85.0 | 340 | 0.5039 |
133
+ | 0.5377 | 86.0 | 344 | 0.5025 |
134
+ | 0.5403 | 87.0 | 348 | 0.5025 |
135
+ | 0.5321 | 88.0 | 352 | 0.5008 |
136
+ | 0.5340 | 89.0 | 356 | 0.4972 |
137
+ | 0.5292 | 90.0 | 360 | 0.4955 |
138
+ | 0.5299 | 91.0 | 364 | 0.4958 |
139
+ | 0.5316 | 92.0 | 368 | 0.4942 |
140
+ | 0.5237 | 93.0 | 372 | 0.4927 |
141
+ | 0.5258 | 94.0 | 376 | 0.4924 |
142
+ | 0.5258 | 95.0 | 380 | 0.4916 |
143
+ | 0.5180 | 96.0 | 384 | 0.4909 |
144
+ | 0.5249 | 97.0 | 388 | 0.4901 |
145
+ | 0.5210 | 98.0 | 392 | 0.4895 |
146
+ | 0.5207 | 99.0 | 396 | 0.4889 |
147
+ | 0.5229 | 100.0 | 400 | 0.4887 |
148
 
149
 
150
  ### Framework versions