Hugging Face's logo

mtzig
/
lge_tests_prelim

Transformers
Safetensors
nanogpt
Generated from Trainer
Model card Files
xet
Community
mtzig commited on
Commit
bef9f8f
·
verified ·
1 Parent(s): b292807

Model save

Browse files
Files changed (3) hide show
  1. README.md +82 -35
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.4550
20
- - Accuracy: 0.66
21
 
22
  ## Model description
23
 
@@ -36,7 +36,7 @@ More information needed
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
- - learning_rate: 0.001
40
  - train_batch_size: 64
41
  - eval_batch_size: 64
42
  - seed: 42
@@ -49,38 +49,85 @@ The following hyperparameters were used during training:
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:------:|:----:|:---------------:|:--------:|
52
- | No log | 0 | 0 | 2.6203 | 0.0 |
53
- | 2.4848 | 0.0320 | 100 | 2.4757 | 0.0 |
54
- | 2.3355 | 0.0641 | 200 | 2.3212 | 0.0 |
55
- | 2.202 | 0.0961 | 300 | 2.2228 | 0.0 |
56
- | 2.068 | 0.1281 | 400 | 2.0466 | 0.0 |
57
- | 1.6899 | 0.1602 | 500 | 1.6584 | 0.0 |
58
- | 1.4558 | 0.1922 | 600 | 1.5536 | 0.005 |
59
- | 1.3624 | 0.2242 | 700 | 1.3155 | 0.015 |
60
- | 1.2388 | 0.2562 | 800 | 1.2468 | 0.025 |
61
- | 1.0832 | 0.2883 | 900 | 1.1109 | 0.095 |
62
- | 1.0392 | 0.3203 | 1000 | 1.0326 | 0.09 |
63
- | 0.968 | 0.3523 | 1100 | 0.9448 | 0.2 |
64
- | 0.8818 | 0.3844 | 1200 | 0.8892 | 0.205 |
65
- | 0.8384 | 0.4164 | 1300 | 0.8277 | 0.255 |
66
- | 0.7951 | 0.4484 | 1400 | 0.7869 | 0.28 |
67
- | 0.742 | 0.4805 | 1500 | 0.7629 | 0.275 |
68
- | 0.7107 | 0.5125 | 1600 | 0.7139 | 0.385 |
69
- | 0.6854 | 0.5445 | 1700 | 0.6708 | 0.41 |
70
- | 0.6381 | 0.5766 | 1800 | 0.6422 | 0.43 |
71
- | 0.6085 | 0.6086 | 1900 | 0.6061 | 0.49 |
72
- | 0.5915 | 0.6406 | 2000 | 0.5896 | 0.42 |
73
- | 0.5809 | 0.6726 | 2100 | 0.5598 | 0.53 |
74
- | 0.5303 | 0.7047 | 2200 | 0.5339 | 0.565 |
75
- | 0.5205 | 0.7367 | 2300 | 0.5170 | 0.585 |
76
- | 0.4997 | 0.7687 | 2400 | 0.5155 | 0.515 |
77
- | 0.4753 | 0.8008 | 2500 | 0.4972 | 0.55 |
78
- | 0.4797 | 0.8328 | 2600 | 0.4745 | 0.645 |
79
- | 0.4729 | 0.8648 | 2700 | 0.4737 | 0.6 |
80
- | 0.469 | 0.8969 | 2800 | 0.4661 | 0.65 |
81
- | 0.4562 | 0.9289 | 2900 | 0.4585 | 0.65 |
82
- | 0.4474 | 0.9609 | 3000 | 0.4557 | 0.64 |
83
- | 0.4462 | 0.9930 | 3100 | 0.4550 | 0.66 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
84
 
85
 
86
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.7046
20
+ - Accuracy: 0.89
21
 
22
  ## Model description
23
 
 
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
+ - learning_rate: 0.0002
40
  - train_batch_size: 64
41
  - eval_batch_size: 64
42
  - seed: 42
 
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:------:|:----:|:---------------:|:--------:|
52
+ | No log | 0 | 0 | 2.6041 | 0.0 |
53
+ | 2.5759 | 0.0128 | 100 | 2.5716 | 0.0 |
54
+ | 2.5431 | 0.0256 | 200 | 2.5401 | 0.0 |
55
+ | 2.4939 | 0.0384 | 300 | 2.4946 | 0.0 |
56
+ | 2.4394 | 0.0512 | 400 | 2.4409 | 0.0 |
57
+ | 2.4054 | 0.0640 | 500 | 2.3917 | 0.0 |
58
+ | 2.358 | 0.0768 | 600 | 2.3522 | 0.0 |
59
+ | 2.3347 | 0.0896 | 700 | 2.3202 | 0.0 |
60
+ | 2.2668 | 0.1024 | 800 | 2.2886 | 0.0 |
61
+ | 2.2672 | 0.1152 | 900 | 2.2555 | 0.0 |
62
+ | 2.2008 | 0.1280 | 1000 | 2.2229 | 0.0 |
63
+ | 2.2122 | 0.1408 | 1100 | 2.2021 | 0.0 |
64
+ | 2.1658 | 0.1536 | 1200 | 2.1683 | 0.0 |
65
+ | 2.1137 | 0.1665 | 1300 | 2.1486 | 0.0 |
66
+ | 2.1001 | 0.1793 | 1400 | 2.1288 | 0.0 |
67
+ | 2.1002 | 0.1921 | 1500 | 2.0900 | 0.0 |
68
+ | 2.0586 | 0.2049 | 1600 | 2.0488 | 0.0 |
69
+ | 2.0614 | 0.2177 | 1700 | 2.0373 | 0.0 |
70
+ | 1.9266 | 0.2305 | 1800 | 1.9368 | 0.0 |
71
+ | 1.9221 | 0.2433 | 1900 | 1.9320 | 0.0 |
72
+ | 1.8304 | 0.2561 | 2000 | 1.8094 | 0.005 |
73
+ | 1.7483 | 0.2689 | 2100 | 1.7452 | 0.01 |
74
+ | 1.6969 | 0.2817 | 2200 | 1.6949 | 0.005 |
75
+ | 1.6504 | 0.2945 | 2300 | 1.6370 | 0.03 |
76
+ | 1.5781 | 0.3073 | 2400 | 1.5857 | 0.0 |
77
+ | 1.5424 | 0.3201 | 2500 | 1.5904 | 0.015 |
78
+ | 1.5002 | 0.3329 | 2600 | 1.5054 | 0.03 |
79
+ | 1.4529 | 0.3457 | 2700 | 1.4718 | 0.085 |
80
+ | 1.4592 | 0.3585 | 2800 | 1.4271 | 0.115 |
81
+ | 1.4238 | 0.3713 | 2900 | 1.4112 | 0.12 |
82
+ | 1.3797 | 0.3841 | 3000 | 1.3719 | 0.135 |
83
+ | 1.3668 | 0.3969 | 3100 | 1.3646 | 0.12 |
84
+ | 1.3191 | 0.4097 | 3200 | 1.3303 | 0.15 |
85
+ | 1.3003 | 0.4225 | 3300 | 1.3101 | 0.23 |
86
+ | 1.2744 | 0.4353 | 3400 | 1.2733 | 0.235 |
87
+ | 1.2389 | 0.4481 | 3500 | 1.2386 | 0.345 |
88
+ | 1.2181 | 0.4609 | 3600 | 1.2098 | 0.27 |
89
+ | 1.2185 | 0.4738 | 3700 | 1.1906 | 0.31 |
90
+ | 1.1838 | 0.4866 | 3800 | 1.1732 | 0.355 |
91
+ | 1.1711 | 0.4994 | 3900 | 1.1513 | 0.395 |
92
+ | 1.1311 | 0.5122 | 4000 | 1.1274 | 0.445 |
93
+ | 1.1143 | 0.5250 | 4100 | 1.1042 | 0.49 |
94
+ | 1.0783 | 0.5378 | 4200 | 1.0734 | 0.58 |
95
+ | 1.0703 | 0.5506 | 4300 | 1.0540 | 0.56 |
96
+ | 1.0464 | 0.5634 | 4400 | 1.0415 | 0.39 |
97
+ | 1.0445 | 0.5762 | 4500 | 1.0150 | 0.57 |
98
+ | 0.9972 | 0.5890 | 4600 | 1.0007 | 0.66 |
99
+ | 0.9835 | 0.6018 | 4700 | 0.9798 | 0.71 |
100
+ | 0.9762 | 0.6146 | 4800 | 0.9745 | 0.62 |
101
+ | 0.9408 | 0.6274 | 4900 | 0.9448 | 0.785 |
102
+ | 0.9184 | 0.6402 | 5000 | 0.9427 | 0.625 |
103
+ | 0.9119 | 0.6530 | 5100 | 0.9229 | 0.66 |
104
+ | 0.9068 | 0.6658 | 5200 | 0.9005 | 0.755 |
105
+ | 0.9112 | 0.6786 | 5300 | 0.9036 | 0.65 |
106
+ | 0.8669 | 0.6914 | 5400 | 0.8721 | 0.77 |
107
+ | 0.8703 | 0.7042 | 5500 | 0.8597 | 0.77 |
108
+ | 0.8376 | 0.7170 | 5600 | 0.8428 | 0.815 |
109
+ | 0.8379 | 0.7298 | 5700 | 0.8324 | 0.835 |
110
+ | 0.8203 | 0.7426 | 5800 | 0.8170 | 0.84 |
111
+ | 0.8157 | 0.7554 | 5900 | 0.8021 | 0.83 |
112
+ | 0.7674 | 0.7682 | 6000 | 0.7916 | 0.845 |
113
+ | 0.7709 | 0.7810 | 6100 | 0.7801 | 0.88 |
114
+ | 0.7595 | 0.7939 | 6200 | 0.7714 | 0.84 |
115
+ | 0.7476 | 0.8067 | 6300 | 0.7584 | 0.87 |
116
+ | 0.7338 | 0.8195 | 6400 | 0.7497 | 0.865 |
117
+ | 0.7375 | 0.8323 | 6500 | 0.7422 | 0.86 |
118
+ | 0.7377 | 0.8451 | 6600 | 0.7351 | 0.875 |
119
+ | 0.757 | 0.8579 | 6700 | 0.7306 | 0.865 |
120
+ | 0.7341 | 0.8707 | 6800 | 0.7235 | 0.89 |
121
+ | 0.7128 | 0.8835 | 6900 | 0.7208 | 0.865 |
122
+ | 0.6991 | 0.8963 | 7000 | 0.7151 | 0.895 |
123
+ | 0.7139 | 0.9091 | 7100 | 0.7120 | 0.89 |
124
+ | 0.7126 | 0.9219 | 7200 | 0.7102 | 0.895 |
125
+ | 0.694 | 0.9347 | 7300 | 0.7076 | 0.895 |
126
+ | 0.7196 | 0.9475 | 7400 | 0.7065 | 0.885 |
127
+ | 0.7013 | 0.9603 | 7500 | 0.7055 | 0.89 |
128
+ | 0.7137 | 0.9731 | 7600 | 0.7049 | 0.89 |
129
+ | 0.6975 | 0.9859 | 7700 | 0.7046 | 0.89 |
130
+ | 0.7038 | 0.9987 | 7800 | 0.7046 | 0.89 |
131
 
132
 
133
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa0603ece3929422b888f23221e98480b6d32c1176d3c3e2f5d0b0cd73c2bb00
3
  size 30712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6aa0ef5fd1d39bfaaab96d41886e743db6c8fb248124044f61f95bb43b87b4f3
3
  size 30712
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:511d17a231a8ec58e85fb1f54877faf32200a2a55cd2bea78f6affa8e4d10c86
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbebaf27dd3eee879709fdbd9f1c86d181d554e88e46e2d1feefcf870d1e2827
3
  size 5240