Hugging Face's logo

esahit
/
ul2-large-dutch-finetuned-oba-book-search

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
esahit commited on
Commit
6569b85
·
verified ·
1 Parent(s): 7e4c280

Rerun first training run on increased dataset

Browse files
Files changed (1) hide show
  1. README.md +64 -44
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 [yhavinga/ul2-large-dutch](https://huggingface.co/yhavinga/ul2-large-dutch) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 4.1161
20
- - Top-5-accuracy: 4.1679
21
 
22
  ## Model description
23
 
@@ -36,56 +36,76 @@ More information needed
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
- - learning_rate: 0.3
40
  - train_batch_size: 16
41
  - eval_batch_size: 16
42
  - seed: 42
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
- - num_epochs: 10
46
 
47
  ### Training results
48
 
49
- | Training Loss | Epoch | Step | Validation Loss | Top-5-accuracy |
50
- |:-------------:|:------:|:----:|:---------------:|:--------------:|
51
- | 6.2541 | 0.2577 | 200 | 4.6137 | 0.0579 |
52
- | 5.8635 | 0.5155 | 400 | 4.5076 | 0.1158 |
53
- | 5.5301 | 0.7732 | 600 | 4.4350 | 0.1447 |
54
- | 5.5298 | 1.0309 | 800 | 4.4449 | 0.1447 |
55
- | 5.3296 | 1.2887 | 1000 | 4.4621 | 0.1158 |
56
- | 5.3336 | 1.5464 | 1200 | 4.4232 | 0.1447 |
57
- | 5.2192 | 1.8041 | 1400 | 4.3842 | 0.1447 |
58
- | 5.2348 | 2.0619 | 1600 | 4.3465 | 0.1447 |
59
- | 5.0988 | 2.3196 | 1800 | 4.3129 | 0.2026 |
60
- | 5.1633 | 2.5773 | 2000 | 4.3007 | 0.1737 |
61
- | 5.1103 | 2.8351 | 2200 | 4.2722 | 0.2026 |
62
- | 5.0057 | 3.0928 | 2400 | 4.3158 | 0.1447 |
63
- | 5.0554 | 3.3505 | 2600 | 4.2731 | 0.4342 |
64
- | 4.9774 | 3.6082 | 2800 | 4.2467 | 0.3763 |
65
- | 4.9769 | 3.8660 | 3000 | 4.2320 | 0.5789 |
66
- | 4.9825 | 4.1237 | 3200 | 4.2115 | 0.8394 |
67
- | 4.9692 | 4.3814 | 3400 | 4.2172 | 1.3893 |
68
- | 4.9681 | 4.6392 | 3600 | 4.2093 | 1.5630 |
69
- | 4.8661 | 4.8969 | 3800 | 4.2003 | 2.2865 |
70
- | 4.942 | 5.1546 | 4000 | 4.2047 | 2.3734 |
71
- | 4.8974 | 5.4124 | 4200 | 4.1583 | 2.8654 |
72
- | 4.8827 | 5.6701 | 4400 | 4.1852 | 2.9522 |
73
- | 4.8705 | 5.9278 | 4600 | 4.1661 | 3.4732 |
74
- | 4.8714 | 6.1856 | 4800 | 4.1478 | 3.7916 |
75
- | 4.7909 | 6.4433 | 5000 | 4.1748 | 3.6179 |
76
- | 4.8357 | 6.7010 | 5200 | 4.1471 | 3.9074 |
77
- | 4.8723 | 6.9588 | 5400 | 4.1518 | 4.0232 |
78
- | 4.8838 | 7.2165 | 5600 | 4.1428 | 4.1389 |
79
- | 4.804 | 7.4742 | 5800 | 4.1468 | 4.0232 |
80
- | 4.8232 | 7.7320 | 6000 | 4.1390 | 4.1389 |
81
- | 4.8571 | 7.9897 | 6200 | 4.1305 | 4.0810 |
82
- | 4.7454 | 8.2474 | 6400 | 4.1297 | 4.1679 |
83
- | 4.8652 | 8.5052 | 6600 | 4.1262 | 4.1968 |
84
- | 4.7882 | 8.7629 | 6800 | 4.1227 | 4.1679 |
85
- | 4.8025 | 9.0206 | 7000 | 4.1134 | 4.1679 |
86
- | 4.8124 | 9.2784 | 7200 | 4.1211 | 4.1389 |
87
- | 4.7157 | 9.5361 | 7400 | 4.1122 | 4.1389 |
88
- | 4.8666 | 9.7938 | 7600 | 4.1161 | 4.1679 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
89
 
90
 
91
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [yhavinga/ul2-large-dutch](https://huggingface.co/yhavinga/ul2-large-dutch) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 5.2081
20
+ - Top-5-accuracy: 0.0
21
 
22
  ## Model description
23
 
 
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
+ - learning_rate: 0.001
40
  - train_batch_size: 16
41
  - eval_batch_size: 16
42
  - seed: 42
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
+ - num_epochs: 1
46
 
47
  ### Training results
48
 
49
+ | Training Loss | Epoch | Step | Validation Loss | Top-5-accuracy |
50
+ |:-------------:|:------:|:-----:|:---------------:|:--------------:|
51
+ | 8.6533 | 0.0170 | 200 | 5.8825 | 0.0 |
52
+ | 8.5044 | 0.0339 | 400 | 5.8463 | 0.0 |
53
+ | 8.3692 | 0.0509 | 600 | 5.7566 | 0.0 |
54
+ | 8.3791 | 0.0678 | 800 | 5.7155 | 0.0 |
55
+ | 8.4643 | 0.0848 | 1000 | 5.6913 | 0.0 |
56
+ | 8.3406 | 0.1017 | 1200 | 5.6508 | 0.0 |
57
+ | 8.2752 | 0.1187 | 1400 | 5.6089 | 0.0 |
58
+ | 8.2495 | 0.1357 | 1600 | 5.5855 | 0.0 |
59
+ | 8.1244 | 0.1526 | 1800 | 5.5783 | 0.0 |
60
+ | 7.8897 | 0.1696 | 2000 | 5.5554 | 0.0 |
61
+ | 8.2289 | 0.1865 | 2200 | 5.5600 | 0.0 |
62
+ | 7.9151 | 0.2035 | 2400 | 5.5427 | 0.0 |
63
+ | 7.9956 | 0.2205 | 2600 | 5.5188 | 0.0 |
64
+ | 8.0472 | 0.2374 | 2800 | 5.4894 | 0.0 |
65
+ | 8.0208 | 0.2544 | 3000 | 5.4734 | 0.0 |
66
+ | 8.2228 | 0.2713 | 3200 | 5.4615 | 0.0 |
67
+ | 8.0756 | 0.2883 | 3400 | 5.4534 | 0.0 |
68
+ | 7.8076 | 0.3052 | 3600 | 5.4456 | 0.0 |
69
+ | 7.8418 | 0.3222 | 3800 | 5.4461 | 0.0 |
70
+ | 7.7266 | 0.3392 | 4000 | 5.4373 | 0.0 |
71
+ | 8.0607 | 0.3561 | 4200 | 5.4281 | 0.0 |
72
+ | 7.7716 | 0.3731 | 4400 | 5.4081 | 0.0 |
73
+ | 7.9324 | 0.3900 | 4600 | 5.3989 | 0.0 |
74
+ | 7.9461 | 0.4070 | 4800 | 5.3803 | 0.0 |
75
+ | 7.8788 | 0.4239 | 5000 | 5.3734 | 0.0 |
76
+ | 7.8748 | 0.4409 | 5200 | 5.3667 | 0.0 |
77
+ | 7.8891 | 0.4579 | 5400 | 5.3629 | 0.0 |
78
+ | 7.9697 | 0.4748 | 5600 | 5.3624 | 0.0 |
79
+ | 7.8402 | 0.4918 | 5800 | 5.3463 | 0.0 |
80
+ | 7.8671 | 0.5087 | 6000 | 5.3332 | 0.0 |
81
+ | 7.6464 | 0.5257 | 6200 | 5.3190 | 0.0 |
82
+ | 7.7773 | 0.5426 | 6400 | 5.3144 | 0.0 |
83
+ | 7.723 | 0.5596 | 6600 | 5.3052 | 0.0 |
84
+ | 7.8489 | 0.5766 | 6800 | 5.2988 | 0.0 |
85
+ | 7.7925 | 0.5935 | 7000 | 5.2946 | 0.0 |
86
+ | 7.8374 | 0.6105 | 7200 | 5.2924 | 0.0 |
87
+ | 7.4971 | 0.6274 | 7400 | 5.2914 | 0.0 |
88
+ | 7.6408 | 0.6444 | 7600 | 5.2859 | 0.0 |
89
+ | 7.7993 | 0.6614 | 7800 | 5.2770 | 0.0 |
90
+ | 7.5283 | 0.6783 | 8000 | 5.2680 | 0.0 |
91
+ | 7.4715 | 0.6953 | 8200 | 5.2637 | 0.0 |
92
+ | 7.4699 | 0.7122 | 8400 | 5.2624 | 0.0 |
93
+ | 7.6275 | 0.7292 | 8600 | 5.2571 | 0.0 |
94
+ | 7.4884 | 0.7461 | 8800 | 5.2509 | 0.0 |
95
+ | 7.47 | 0.7631 | 9000 | 5.2448 | 0.0 |
96
+ | 7.5765 | 0.7801 | 9200 | 5.2324 | 0.0 |
97
+ | 7.6802 | 0.7970 | 9400 | 5.2331 | 0.0 |
98
+ | 7.4827 | 0.8140 | 9600 | 5.2346 | 0.0 |
99
+ | 7.4127 | 0.8309 | 9800 | 5.2346 | 0.0 |
100
+ | 7.5217 | 0.8479 | 10000 | 5.2248 | 0.0 |
101
+ | 7.4794 | 0.8648 | 10200 | 5.2201 | 0.0 |
102
+ | 7.4414 | 0.8818 | 10400 | 5.2179 | 0.0 |
103
+ | 7.5095 | 0.8988 | 10600 | 5.2104 | 0.0 |
104
+ | 7.4934 | 0.9157 | 10800 | 5.2084 | 0.0 |
105
+ | 7.3595 | 0.9327 | 11000 | 5.2098 | 0.0 |
106
+ | 7.6305 | 0.9496 | 11200 | 5.2097 | 0.0 |
107
+ | 7.5846 | 0.9666 | 11400 | 5.2084 | 0.0 |
108
+ | 7.4536 | 0.9836 | 11600 | 5.2081 | 0.0 |
109
 
110
 
111
  ### Framework versions