Hugging Face's logo

fpadovani
/
german_clm_childes_30

Text Generation
Transformers
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Model card Files Community
fpadovani commited on
Commit
244b090
·
verified ·
1 Parent(s): cc5b975

Model save

Browse files
Files changed (2) hide show
  1. README.md +53 -53
  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: 4.3302
18
 
19
  ## Model description
20
 
@@ -47,58 +47,58 @@ The following hyperparameters were used during training:
47
 
48
  ### Training results
49
 
50
- | Training Loss | Epoch | Step | Validation Loss |
51
- |:-------------:|:-------:|:------:|:---------------:|
52
- | No log | 1.3276 | 2000 | 6.8483 |
53
- | 6.7292 | 2.6552 | 4000 | 5.2394 |
54
- | 6.7292 | 3.9827 | 6000 | 4.8291 |
55
- | 4.5966 | 5.3103 | 8000 | 4.5936 |
56
- | 4.5966 | 6.6379 | 10000 | 4.4492 |
57
- | 4.1336 | 7.9655 | 12000 | 4.3485 |
58
- | 4.1336 | 9.2931 | 14000 | 4.2777 |
59
- | 3.8576 | 10.6206 | 16000 | 4.2236 |
60
- | 3.8576 | 11.9482 | 18000 | 4.1838 |
61
- | 3.6557 | 13.2758 | 20000 | 4.1570 |
62
- | 3.6557 | 14.6034 | 22000 | 4.1305 |
63
- | 3.4956 | 15.9310 | 24000 | 4.1001 |
64
- | 3.4956 | 17.2585 | 26000 | 4.0964 |
65
- | 3.361 | 18.5861 | 28000 | 4.0740 |
66
- | 3.361 | 19.9137 | 30000 | 4.0631 |
67
- | 3.2519 | 21.2413 | 32000 | 4.0574 |
68
- | 3.2519 | 22.5689 | 34000 | 4.0463 |
69
- | 3.161 | 23.8964 | 36000 | 4.0326 |
70
- | 3.161 | 25.2240 | 38000 | 4.0403 |
71
- | 3.0792 | 26.5516 | 40000 | 4.0435 |
72
- | 3.0792 | 27.8792 | 42000 | 4.0342 |
73
- | 3.0042 | 29.2068 | 44000 | 4.0554 |
74
- | 3.0042 | 30.5344 | 46000 | 4.0496 |
75
- | 2.9291 | 31.8619 | 48000 | 4.0562 |
76
- | 2.9291 | 33.1895 | 50000 | 4.0766 |
77
- | 2.86 | 34.5171 | 52000 | 4.0811 |
78
- | 2.86 | 35.8447 | 54000 | 4.0908 |
79
- | 2.8053 | 37.1723 | 56000 | 4.1132 |
80
- | 2.8053 | 38.4998 | 58000 | 4.1227 |
81
- | 2.7515 | 39.8274 | 60000 | 4.1243 |
82
- | 2.7515 | 41.1550 | 62000 | 4.1491 |
83
- | 2.7025 | 42.4826 | 64000 | 4.1589 |
84
- | 2.7025 | 43.8102 | 66000 | 4.1770 |
85
- | 2.6629 | 45.1377 | 68000 | 4.1933 |
86
- | 2.6629 | 46.4653 | 70000 | 4.2059 |
87
- | 2.6223 | 47.7929 | 72000 | 4.2088 |
88
- | 2.6223 | 49.1205 | 74000 | 4.2310 |
89
- | 2.5854 | 50.4481 | 76000 | 4.2434 |
90
- | 2.5854 | 51.7756 | 78000 | 4.2453 |
91
- | 2.5556 | 53.1032 | 80000 | 4.2683 |
92
- | 2.5556 | 54.4308 | 82000 | 4.2743 |
93
- | 2.5244 | 55.7584 | 84000 | 4.2803 |
94
- | 2.5244 | 57.0860 | 86000 | 4.2939 |
95
- | 2.4973 | 58.4135 | 88000 | 4.3046 |
96
- | 2.4973 | 59.7411 | 90000 | 4.3050 |
97
- | 2.4747 | 61.0687 | 92000 | 4.3184 |
98
- | 2.4747 | 62.3963 | 94000 | 4.3228 |
99
- | 2.452 | 63.7239 | 96000 | 4.3226 |
100
- | 2.452 | 65.0514 | 98000 | 4.3298 |
101
- | 2.4362 | 66.3790 | 100000 | 4.3302 |
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: 5.6290
18
 
19
  ## Model description
20
 
 
47
 
48
  ### Training results
49
 
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:--------:|:------:|:---------------:|
52
+ | No log | 3.1447 | 2000 | 6.6723 |
53
+ | 6.5359 | 6.2893 | 4000 | 5.1023 |
54
+ | 6.5359 | 9.4340 | 6000 | 4.6753 |
55
+ | 4.34 | 12.5786 | 8000 | 4.4299 |
56
+ | 4.34 | 15.7233 | 10000 | 4.2789 |
57
+ | 3.8692 | 18.8679 | 12000 | 4.1581 |
58
+ | 3.8692 | 22.0126 | 14000 | 4.0821 |
59
+ | 3.5905 | 25.1572 | 16000 | 4.0338 |
60
+ | 3.5905 | 28.3019 | 18000 | 3.9935 |
61
+ | 3.3778 | 31.4465 | 20000 | 3.9676 |
62
+ | 3.3778 | 34.5912 | 22000 | 3.9494 |
63
+ | 3.1983 | 37.7358 | 24000 | 3.9383 |
64
+ | 3.1983 | 40.8805 | 26000 | 3.9361 |
65
+ | 3.0374 | 44.0252 | 28000 | 3.9348 |
66
+ | 3.0374 | 47.1698 | 30000 | 3.9625 |
67
+ | 2.887 | 50.3145 | 32000 | 3.9900 |
68
+ | 2.887 | 53.4591 | 34000 | 4.0227 |
69
+ | 2.7426 | 56.6038 | 36000 | 4.0573 |
70
+ | 2.7426 | 59.7484 | 38000 | 4.1040 |
71
+ | 2.5994 | 62.8931 | 40000 | 4.1456 |
72
+ | 2.5994 | 66.0377 | 42000 | 4.2263 |
73
+ | 2.4407 | 69.1824 | 44000 | 4.2927 |
74
+ | 2.4407 | 72.3270 | 46000 | 4.3761 |
75
+ | 2.2824 | 75.4717 | 48000 | 4.4465 |
76
+ | 2.2824 | 78.6164 | 50000 | 4.5184 |
77
+ | 2.1444 | 81.7610 | 52000 | 4.5949 |
78
+ | 2.1444 | 84.9057 | 54000 | 4.6548 |
79
+ | 2.0229 | 88.0503 | 56000 | 4.7317 |
80
+ | 2.0229 | 91.1950 | 58000 | 4.8042 |
81
+ | 1.9145 | 94.3396 | 60000 | 4.8686 |
82
+ | 1.9145 | 97.4843 | 62000 | 4.9219 |
83
+ | 1.8236 | 100.6289 | 64000 | 4.9919 |
84
+ | 1.8236 | 103.7736 | 66000 | 5.0446 |
85
+ | 1.7439 | 106.9182 | 68000 | 5.0921 |
86
+ | 1.7439 | 110.0629 | 70000 | 5.1646 |
87
+ | 1.6698 | 113.2075 | 72000 | 5.2190 |
88
+ | 1.6698 | 116.3522 | 74000 | 5.2676 |
89
+ | 1.6065 | 119.4969 | 76000 | 5.3096 |
90
+ | 1.6065 | 122.6415 | 78000 | 5.3485 |
91
+ | 1.55 | 125.7862 | 80000 | 5.3839 |
92
+ | 1.55 | 128.9308 | 82000 | 5.4190 |
93
+ | 1.4991 | 132.0755 | 84000 | 5.4647 |
94
+ | 1.4991 | 135.2201 | 86000 | 5.5025 |
95
+ | 1.4526 | 138.3648 | 88000 | 5.5331 |
96
+ | 1.4526 | 141.5094 | 90000 | 5.5623 |
97
+ | 1.4134 | 144.6541 | 92000 | 5.5745 |
98
+ | 1.4134 | 147.7987 | 94000 | 5.6018 |
99
+ | 1.3793 | 150.9434 | 96000 | 5.6085 |
100
+ | 1.3793 | 154.0881 | 98000 | 5.6234 |
101
+ | 1.3512 | 157.2327 | 100000 | 5.6290 |
102
 
103
 
104
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a9d86e93883eb6d9a7d934e9d633f9ab1defad75e9d7ff1b2a1d2b10413bb7dc
3
  size 51007160
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c33f1a5131a2b10148070957416e5adc117285abf30eabc6f09f155c6ff76ac7
3
  size 51007160