Hugging Face's logo

fpadovani
/
fr_childes_42

Fill-Mask
Transformers
Safetensors
roberta
Generated from Trainer
Model card Files Community
fpadovani commited on
Commit
58d335c
·
verified ·
1 Parent(s): 52e1c72

Model save

Browse files
Files changed (1) hide show
  1. README.md +51 -52
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: 4.1449
18
 
19
  ## Model description
20
 
@@ -43,62 +43,61 @@ The following hyperparameters were used during training:
43
  - lr_scheduler_type: linear
44
  - lr_scheduler_warmup_steps: 40000
45
  - training_steps: 100000
46
- - mixed_precision_training: Native AMP
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:-----:|:------:|:---------------:|
52
- | No log | 2.5 | 2000 | 6.5725 |
53
- | 6.5185 | 5.0 | 4000 | 4.9264 |
54
- | 6.5185 | 7.5 | 6000 | 4.4682 |
55
- | 4.3057 | 10.0 | 8000 | 4.2043 |
56
- | 4.3057 | 12.5 | 10000 | 4.0196 |
57
- | 3.8252 | 15.0 | 12000 | 3.8793 |
58
- | 3.8252 | 17.5 | 14000 | 3.7737 |
59
- | 3.5527 | 20.0 | 16000 | 3.6714 |
60
- | 3.5527 | 22.5 | 18000 | 3.5939 |
61
- | 3.3505 | 25.0 | 20000 | 3.5267 |
62
- | 3.3505 | 27.5 | 22000 | 3.4637 |
63
- | 3.183 | 30.0 | 24000 | 3.4215 |
64
- | 3.183 | 32.5 | 26000 | 3.3818 |
65
- | 3.0393 | 35.0 | 28000 | 3.3493 |
66
- | 3.0393 | 37.5 | 30000 | 3.3345 |
67
- | 2.9118 | 40.0 | 32000 | 3.3137 |
68
- | 2.9118 | 42.5 | 34000 | 3.3158 |
69
- | 2.7946 | 45.0 | 36000 | 3.3074 |
70
- | 2.7946 | 47.5 | 38000 | 3.3315 |
71
- | 2.682 | 50.0 | 40000 | 3.3343 |
72
- | 2.682 | 52.5 | 42000 | 3.3576 |
73
- | 2.5612 | 55.0 | 44000 | 3.3741 |
74
- | 2.5612 | 57.5 | 46000 | 3.4210 |
75
- | 2.4371 | 60.0 | 48000 | 3.4420 |
76
- | 2.4371 | 62.5 | 50000 | 3.4921 |
77
- | 2.3257 | 65.0 | 52000 | 3.5113 |
78
- | 2.3257 | 67.5 | 54000 | 3.5672 |
79
- | 2.2264 | 70.0 | 56000 | 3.5861 |
80
- | 2.2264 | 72.5 | 58000 | 3.6404 |
81
- | 2.1379 | 75.0 | 60000 | 3.6712 |
82
- | 2.1379 | 77.5 | 62000 | 3.7178 |
83
- | 2.0592 | 80.0 | 64000 | 3.7306 |
84
- | 2.0592 | 82.5 | 66000 | 3.7847 |
85
- | 1.9888 | 85.0 | 68000 | 3.8042 |
86
- | 1.9888 | 87.5 | 70000 | 3.8581 |
87
- | 1.9259 | 90.0 | 72000 | 3.8752 |
88
- | 1.9259 | 92.5 | 74000 | 3.9158 |
89
- | 1.8696 | 95.0 | 76000 | 3.9281 |
90
- | 1.8696 | 97.5 | 78000 | 3.9651 |
91
- | 1.8186 | 100.0 | 80000 | 3.9848 |
92
- | 1.8186 | 102.5 | 82000 | 4.0198 |
93
- | 1.7735 | 105.0 | 84000 | 4.0294 |
94
- | 1.7735 | 107.5 | 86000 | 4.0608 |
95
- | 1.7319 | 110.0 | 88000 | 4.0724 |
96
- | 1.7319 | 112.5 | 90000 | 4.0939 |
97
- | 1.6956 | 115.0 | 92000 | 4.1053 |
98
- | 1.6956 | 117.5 | 94000 | 4.1268 |
99
- | 1.6642 | 120.0 | 96000 | 4.1355 |
100
- | 1.6642 | 122.5 | 98000 | 4.1429 |
101
- | 1.639 | 125.0 | 100000 | 4.1449 |
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: 1.8718
18
 
19
  ## Model description
20
 
 
43
  - lr_scheduler_type: linear
44
  - lr_scheduler_warmup_steps: 40000
45
  - training_steps: 100000
 
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:------:|:---------------:|
51
+ | No log | 2.5 | 2000 | 7.2323 |
52
+ | 7.2283 | 5.0 | 4000 | 5.9768 |
53
+ | 7.2283 | 7.5 | 6000 | 5.8268 |
54
+ | 5.6892 | 10.0 | 8000 | 5.7444 |
55
+ | 5.6892 | 12.5 | 10000 | 5.6708 |
56
+ | 5.4694 | 15.0 | 12000 | 5.5713 |
57
+ | 5.4694 | 17.5 | 14000 | 5.5270 |
58
+ | 5.3091 | 20.0 | 16000 | 5.4483 |
59
+ | 5.3091 | 22.5 | 18000 | 5.3926 |
60
+ | 5.1707 | 25.0 | 20000 | 5.2315 |
61
+ | 5.1707 | 27.5 | 22000 | 4.9059 |
62
+ | 4.6992 | 30.0 | 24000 | 4.1680 |
63
+ | 4.6992 | 32.5 | 26000 | 3.6409 |
64
+ | 3.5699 | 35.0 | 28000 | 3.2064 |
65
+ | 3.5699 | 37.5 | 30000 | 3.0010 |
66
+ | 2.9074 | 40.0 | 32000 | 2.8509 |
67
+ | 2.9074 | 42.5 | 34000 | 2.7339 |
68
+ | 2.6073 | 45.0 | 36000 | 2.6182 |
69
+ | 2.6073 | 47.5 | 38000 | 2.5613 |
70
+ | 2.4166 | 50.0 | 40000 | 2.4946 |
71
+ | 2.4166 | 52.5 | 42000 | 2.4197 |
72
+ | 2.2667 | 55.0 | 44000 | 2.3687 |
73
+ | 2.2667 | 57.5 | 46000 | 2.2802 |
74
+ | 2.146 | 60.0 | 48000 | 2.2621 |
75
+ | 2.146 | 62.5 | 50000 | 2.2170 |
76
+ | 2.0465 | 65.0 | 52000 | 2.1907 |
77
+ | 2.0465 | 67.5 | 54000 | 2.1659 |
78
+ | 1.969 | 70.0 | 56000 | 2.1273 |
79
+ | 1.969 | 72.5 | 58000 | 2.0874 |
80
+ | 1.9056 | 75.0 | 60000 | 2.0743 |
81
+ | 1.9056 | 77.5 | 62000 | 2.0583 |
82
+ | 1.8492 | 80.0 | 64000 | 2.0371 |
83
+ | 1.8492 | 82.5 | 66000 | 2.0039 |
84
+ | 1.8024 | 85.0 | 68000 | 1.9901 |
85
+ | 1.8024 | 87.5 | 70000 | 1.9754 |
86
+ | 1.7652 | 90.0 | 72000 | 1.9566 |
87
+ | 1.7652 | 92.5 | 74000 | 1.9404 |
88
+ | 1.7344 | 95.0 | 76000 | 1.9128 |
89
+ | 1.7344 | 97.5 | 78000 | 1.9396 |
90
+ | 1.7055 | 100.0 | 80000 | 1.9591 |
91
+ | 1.7055 | 102.5 | 82000 | 1.9078 |
92
+ | 1.6779 | 105.0 | 84000 | 1.9178 |
93
+ | 1.6779 | 107.5 | 86000 | 1.9046 |
94
+ | 1.6529 | 110.0 | 88000 | 1.8918 |
95
+ | 1.6529 | 112.5 | 90000 | 1.9010 |
96
+ | 1.6347 | 115.0 | 92000 | 1.8959 |
97
+ | 1.6347 | 117.5 | 94000 | 1.9094 |
98
+ | 1.6225 | 120.0 | 96000 | 1.8838 |
99
+ | 1.6225 | 122.5 | 98000 | 1.8972 |
100
+ | 1.6132 | 125.0 | 100000 | 1.8718 |
101
 
102
 
103
  ### Framework versions