Hugging Face's logo

fpadovani
/
german_clm_childes_42

Text Generation
Transformers
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Model card Files Community
fpadovani commited on
Commit
53fcd37
·
verified ·
1 Parent(s): 5836e2b

Model save

Browse files
Files changed (2) hide show
  1. README.md +51 -51
  2. model.safetensors +1 -1
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 an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 5.6292
18
 
19
  ## Model description
20
 
@@ -49,56 +49,56 @@ The following hyperparameters were used during training:
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:--------:|:------:|:---------------:|
52
- | No log | 3.1447 | 2000 | 6.6666 |
53
- | 6.5315 | 6.2893 | 4000 | 5.1019 |
54
- | 6.5315 | 9.4340 | 6000 | 4.6770 |
55
- | 4.3407 | 12.5786 | 8000 | 4.4404 |
56
- | 4.3407 | 15.7233 | 10000 | 4.2867 |
57
- | 3.8725 | 18.8679 | 12000 | 4.1719 |
58
- | 3.8725 | 22.0126 | 14000 | 4.0966 |
59
- | 3.5953 | 25.1572 | 16000 | 4.0332 |
60
- | 3.5953 | 28.3019 | 18000 | 3.9956 |
61
- | 3.3822 | 31.4465 | 20000 | 3.9709 |
62
- | 3.3822 | 34.5912 | 22000 | 3.9515 |
63
- | 3.2038 | 37.7358 | 24000 | 3.9379 |
64
- | 3.2038 | 40.8805 | 26000 | 3.9355 |
65
- | 3.0443 | 44.0252 | 28000 | 3.9516 |
66
- | 3.0443 | 47.1698 | 30000 | 3.9560 |
67
- | 2.8937 | 50.3145 | 32000 | 3.9868 |
68
- | 2.8937 | 53.4591 | 34000 | 4.0257 |
69
- | 2.7503 | 56.6038 | 36000 | 4.0503 |
70
- | 2.7503 | 59.7484 | 38000 | 4.0912 |
71
- | 2.6083 | 62.8931 | 40000 | 4.1437 |
72
- | 2.6083 | 66.0377 | 42000 | 4.2207 |
73
- | 2.4507 | 69.1824 | 44000 | 4.2918 |
74
- | 2.4507 | 72.3270 | 46000 | 4.3598 |
75
- | 2.2924 | 75.4717 | 48000 | 4.4447 |
76
- | 2.2924 | 78.6164 | 50000 | 4.5189 |
77
- | 2.1545 | 81.7610 | 52000 | 4.5722 |
78
- | 2.1545 | 84.9057 | 54000 | 4.6449 |
79
- | 2.0329 | 88.0503 | 56000 | 4.7517 |
80
- | 2.0329 | 91.1950 | 58000 | 4.8083 |
81
- | 1.9237 | 94.3396 | 60000 | 4.8806 |
82
- | 1.9237 | 97.4843 | 62000 | 4.9335 |
83
- | 1.833 | 100.6289 | 64000 | 4.9898 |
84
- | 1.833 | 103.7736 | 66000 | 5.0513 |
85
- | 1.7526 | 106.9182 | 68000 | 5.1019 |
86
- | 1.7526 | 110.0629 | 70000 | 5.1573 |
87
- | 1.6779 | 113.2075 | 72000 | 5.2098 |
88
- | 1.6779 | 116.3522 | 74000 | 5.2536 |
89
- | 1.6143 | 119.4969 | 76000 | 5.3061 |
90
- | 1.6143 | 122.6415 | 78000 | 5.3506 |
91
- | 1.5572 | 125.7862 | 80000 | 5.3889 |
92
- | 1.5572 | 128.9308 | 82000 | 5.4262 |
93
- | 1.5054 | 132.0755 | 84000 | 5.4681 |
94
- | 1.5054 | 135.2201 | 86000 | 5.5066 |
95
- | 1.4587 | 138.3648 | 88000 | 5.5313 |
96
- | 1.4587 | 141.5094 | 90000 | 5.5517 |
97
- | 1.4189 | 144.6541 | 92000 | 5.5767 |
98
- | 1.4189 | 147.7987 | 94000 | 5.5990 |
99
- | 1.3839 | 150.9434 | 96000 | 5.6174 |
100
- | 1.3839 | 154.0881 | 98000 | 5.6240 |
101
- | 1.3559 | 157.2327 | 100000 | 5.6292 |
102
 
103
 
104
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 5.3390
18
 
19
  ## Model description
20
 
 
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:--------:|:------:|:---------------:|
52
+ | No log | 2.0964 | 2000 | 7.0908 |
53
+ | 6.9765 | 4.1929 | 4000 | 5.8746 |
54
+ | 6.9765 | 6.2893 | 6000 | 5.5441 |
55
+ | 5.2182 | 8.3857 | 8000 | 5.2788 |
56
+ | 5.2182 | 10.4822 | 10000 | 5.0992 |
57
+ | 4.7379 | 12.5786 | 12000 | 4.9710 |
58
+ | 4.7379 | 14.6751 | 14000 | 4.8759 |
59
+ | 4.4249 | 16.7715 | 16000 | 4.8005 |
60
+ | 4.4249 | 18.8679 | 18000 | 4.7436 |
61
+ | 4.1842 | 20.9644 | 20000 | 4.6922 |
62
+ | 4.1842 | 23.0608 | 22000 | 4.6481 |
63
+ | 3.9843 | 25.1572 | 24000 | 4.6155 |
64
+ | 3.9843 | 27.2537 | 26000 | 4.5982 |
65
+ | 3.8181 | 29.3501 | 28000 | 4.5845 |
66
+ | 3.8181 | 31.4465 | 30000 | 4.5811 |
67
+ | 3.6751 | 33.5430 | 32000 | 4.5796 |
68
+ | 3.6751 | 35.6394 | 34000 | 4.5828 |
69
+ | 3.5484 | 37.7358 | 36000 | 4.5869 |
70
+ | 3.5484 | 39.8323 | 38000 | 4.5976 |
71
+ | 3.4328 | 41.9287 | 40000 | 4.6090 |
72
+ | 3.4328 | 44.0252 | 42000 | 4.6298 |
73
+ | 3.31 | 46.1216 | 44000 | 4.6598 |
74
+ | 3.31 | 48.2180 | 46000 | 4.6983 |
75
+ | 3.1908 | 50.3145 | 48000 | 4.7263 |
76
+ | 3.1908 | 52.4109 | 50000 | 4.7624 |
77
+ | 3.0864 | 54.5073 | 52000 | 4.7913 |
78
+ | 3.0864 | 56.6038 | 54000 | 4.8263 |
79
+ | 2.993 | 58.7002 | 56000 | 4.8538 |
80
+ | 2.993 | 60.7966 | 58000 | 4.8770 |
81
+ | 2.9108 | 62.8931 | 60000 | 4.9097 |
82
+ | 2.9108 | 64.9895 | 62000 | 4.9486 |
83
+ | 2.8352 | 67.0860 | 64000 | 4.9929 |
84
+ | 2.8352 | 69.1824 | 66000 | 5.0339 |
85
+ | 2.7677 | 71.2788 | 68000 | 5.0516 |
86
+ | 2.7677 | 73.3753 | 70000 | 5.0869 |
87
+ | 2.708 | 75.4717 | 72000 | 5.1078 |
88
+ | 2.708 | 77.5681 | 74000 | 5.1317 |
89
+ | 2.6552 | 79.6646 | 76000 | 5.1598 |
90
+ | 2.6552 | 81.7610 | 78000 | 5.1774 |
91
+ | 2.6082 | 83.8574 | 80000 | 5.1928 |
92
+ | 2.6082 | 85.9539 | 82000 | 5.2273 |
93
+ | 2.5633 | 88.0503 | 84000 | 5.2497 |
94
+ | 2.5633 | 90.1468 | 86000 | 5.2644 |
95
+ | 2.5227 | 92.2432 | 88000 | 5.2840 |
96
+ | 2.5227 | 94.3396 | 90000 | 5.2921 |
97
+ | 2.4873 | 96.4361 | 92000 | 5.3118 |
98
+ | 2.4873 | 98.5325 | 94000 | 5.3205 |
99
+ | 2.458 | 100.6289 | 96000 | 5.3308 |
100
+ | 2.458 | 102.7254 | 98000 | 5.3365 |
101
+ | 2.4331 | 104.8218 | 100000 | 5.3390 |
102
 
103
 
104
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dbd5a39fbd798a7604003ab05f0e5f0aaa03c3745e48864e76293c496062a15a
3
  size 51007160
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:833069af2eb13b6b569aa259b3fa49f36e4ee124dc3c838bb6ddff926b82ffd9
3
  size 51007160