Hugging Face's logo

trungpq
/
slac-new-appearance-upsample_replacement

Transformers
Safetensors
bert_model
Generated from Trainer
Model card Files
xet
 Community
trungpq commited on
Commit
27f8cb9
·
verified ·
1 Parent(s): f5a4d7b

End of training

Browse files
Files changed (3) hide show
  1. README.md +24 -24
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -16,12 +16,12 @@ 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: 0.3018
20
- - Accuracy: 0.91
21
- - F1 Macro: 0.7789
22
- - Precision Macro: 0.7901
23
- - Recall Macro: 0.7689
24
- - Total Tf: [91, 9, 91, 9]
25
 
26
  ## Model description
27
 
@@ -46,28 +46,28 @@ The following hyperparameters were used during training:
46
  - seed: 42
47
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
  - lr_scheduler_type: linear
49
- - lr_scheduler_warmup_steps: 2
50
  - num_epochs: 15
51
 
52
  ### Training results
53
 
54
- | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | Precision Macro | Recall Macro | Total Tf |
55
- |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:---------------:|:------------:|:----------------:|
56
- | 0.683 | 1.0 | 3 | 0.5989 | 0.87 | 0.5315 | 0.6100 | 0.5303 | [87, 13, 87, 13] |
57
- | 0.6398 | 2.0 | 6 | 0.5865 | 0.87 | 0.6807 | 0.6879 | 0.6742 | [87, 13, 87, 13] |
58
- | 0.5988 | 3.0 | 9 | 0.5538 | 0.89 | 0.6801 | 0.7427 | 0.6496 | [89, 11, 89, 11] |
59
- | 0.5735 | 4.0 | 12 | 0.5253 | 0.89 | 0.6801 | 0.7427 | 0.6496 | [89, 11, 89, 11] |
60
- | 0.5122 | 5.0 | 15 | 0.4897 | 0.89 | 0.7298 | 0.7390 | 0.7216 | [89, 11, 89, 11] |
61
- | 0.3797 | 6.0 | 18 | 0.4573 | 0.86 | 0.7255 | 0.6978 | 0.7765 | [86, 14, 86, 14] |
62
- | 0.3398 | 7.0 | 21 | 0.4187 | 0.88 | 0.7347 | 0.7209 | 0.7519 | [88, 12, 88, 12] |
63
- | 0.3337 | 8.0 | 24 | 0.3798 | 0.91 | 0.7789 | 0.7901 | 0.7689 | [91, 9, 91, 9] |
64
- | 0.2884 | 9.0 | 27 | 0.3550 | 0.91 | 0.7606 | 0.8004 | 0.7330 | [91, 9, 91, 9] |
65
- | 0.2525 | 10.0 | 30 | 0.3381 | 0.91 | 0.7606 | 0.8004 | 0.7330 | [91, 9, 91, 9] |
66
- | 0.2639 | 11.0 | 33 | 0.3255 | 0.91 | 0.7606 | 0.8004 | 0.7330 | [91, 9, 91, 9] |
67
- | 0.2462 | 12.0 | 36 | 0.3144 | 0.91 | 0.7606 | 0.8004 | 0.7330 | [91, 9, 91, 9] |
68
- | 0.2171 | 13.0 | 39 | 0.3073 | 0.91 | 0.7789 | 0.7901 | 0.7689 | [91, 9, 91, 9] |
69
- | 0.211 | 14.0 | 42 | 0.3035 | 0.91 | 0.7789 | 0.7901 | 0.7689 | [91, 9, 91, 9] |
70
- | 0.2252 | 15.0 | 45 | 0.3018 | 0.91 | 0.7789 | 0.7901 | 0.7689 | [91, 9, 91, 9] |
71
 
72
 
73
  ### 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: 0.2258
20
+ - Accuracy: 0.9735
21
+ - F1 Macro: 0.9525
22
+ - Precision Macro: 0.9561
23
+ - Recall Macro: 0.9491
24
+ - Total Tf: [1506, 41, 1506, 41]
25
 
26
  ## Model description
27
 
 
46
  - seed: 42
47
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
  - lr_scheduler_type: linear
49
+ - lr_scheduler_warmup_steps: 313
50
  - num_epochs: 15
51
 
52
  ### Training results
53
 
54
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | Precision Macro | Recall Macro | Total Tf |
55
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:---------------:|:------------:|:--------------------:|
56
+ | 0.1063 | 1.0 | 314 | 0.1240 | 0.9619 | 0.9354 | 0.9168 | 0.9573 | [1488, 59, 1488, 59] |
57
+ | 0.0273 | 2.0 | 628 | 0.1173 | 0.9741 | 0.9545 | 0.9504 | 0.9586 | [1507, 40, 1507, 40] |
58
+ | 0.0209 | 3.0 | 942 | 0.1238 | 0.9735 | 0.9528 | 0.9535 | 0.9521 | [1506, 41, 1506, 41] |
59
+ | 0.0153 | 4.0 | 1256 | 0.1414 | 0.9716 | 0.9493 | 0.9507 | 0.9479 | [1503, 44, 1503, 44] |
60
+ | 0.0034 | 5.0 | 1570 | 0.1748 | 0.9741 | 0.9533 | 0.9606 | 0.9465 | [1507, 40, 1507, 40] |
61
+ | 0.0144 | 6.0 | 1884 | 0.1686 | 0.9709 | 0.9482 | 0.9489 | 0.9475 | [1502, 45, 1502, 45] |
62
+ | 0.0033 | 7.0 | 2198 | 0.2072 | 0.9677 | 0.9420 | 0.9462 | 0.9380 | [1497, 50, 1497, 50] |
63
+ | 0.0065 | 8.0 | 2512 | 0.1792 | 0.9741 | 0.9535 | 0.9592 | 0.9480 | [1507, 40, 1507, 40] |
64
+ | 0.0024 | 9.0 | 2826 | 0.1889 | 0.9741 | 0.9540 | 0.9540 | 0.9540 | [1507, 40, 1507, 40] |
65
+ | 0.0031 | 10.0 | 3140 | 0.2047 | 0.9729 | 0.9522 | 0.9482 | 0.9563 | [1505, 42, 1505, 42] |
66
+ | 0.0006 | 11.0 | 3454 | 0.2151 | 0.9735 | 0.9521 | 0.9601 | 0.9445 | [1506, 41, 1506, 41] |
67
+ | 0.0011 | 12.0 | 3768 | 0.2255 | 0.9722 | 0.9504 | 0.9525 | 0.9483 | [1504, 43, 1504, 43] |
68
+ | 0.0011 | 13.0 | 4082 | 0.2239 | 0.9722 | 0.9505 | 0.9512 | 0.9498 | [1504, 43, 1504, 43] |
69
+ | 0.0004 | 14.0 | 4396 | 0.2233 | 0.9735 | 0.9525 | 0.9561 | 0.9491 | [1506, 41, 1506, 41] |
70
+ | 0.0011 | 15.0 | 4710 | 0.2258 | 0.9735 | 0.9525 | 0.9561 | 0.9491 | [1506, 41, 1506, 41] |
71
 
72
 
73
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:77285879e57db05bbac9fac685cb6183f1801b87d735c2b5e3497be33d240fe2
3
  size 437955556
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f732f5f20335837ac7b72dcf8b58d785ecfcbd8691b91edb060398e282797f3d
3
  size 437955556
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e3145ad148b899304801ab09f2d8084de9fd069bf958d25caf640e7bb199884
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2123b7828c73941c5ccb6d149825dfa773f42f2778d7824ec7748ffdc27d1a6
3
  size 5368