Hugging Face's logo

Hanish2007
/
brand-safety-model

Text Classification
Transformers
ONNX
Safetensors
distilbert
Generated from Trainer
Model card Files Community
Hanish2007 commited on
Commit
dd84f58
·
verified ·
1 Parent(s): d31e2fb

End of training

Browse files
Files changed (3) hide show
  1. README.md +21 -56
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.8417
22
- - Accuracy: 0.8307
23
 
24
  ## Model description
25
 
@@ -38,68 +38,33 @@ More information needed
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
- - learning_rate: 1e-05
42
- - train_batch_size: 32
43
- - eval_batch_size: 32
44
  - seed: 42
45
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
  - lr_scheduler_type: linear
47
- - num_epochs: 50
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
- | 2.5625 | 1.0 | 182 | 2.0756 | 0.5829 |
54
- | 1.4594 | 2.0 | 364 | 1.2750 | 0.7047 |
55
- | 1.0505 | 3.0 | 546 | 0.9622 | 0.7619 |
56
- | 0.7865 | 4.0 | 728 | 0.8141 | 0.7860 |
57
- | 0.6403 | 5.0 | 910 | 0.7084 | 0.8162 |
58
- | 0.5567 | 6.0 | 1092 | 0.6579 | 0.8211 |
59
- | 0.4132 | 7.0 | 1274 | 0.6144 | 0.8238 |
60
- | 0.3801 | 8.0 | 1456 | 0.6065 | 0.8190 |
61
- | 0.3124 | 9.0 | 1638 | 0.5895 | 0.8238 |
62
- | 0.2824 | 10.0 | 1820 | 0.6027 | 0.8224 |
63
- | 0.2438 | 11.0 | 2002 | 0.5920 | 0.8273 |
64
- | 0.199 | 12.0 | 2184 | 0.6172 | 0.8176 |
65
- | 0.1534 | 13.0 | 2366 | 0.6165 | 0.8211 |
66
- | 0.1549 | 14.0 | 2548 | 0.6399 | 0.8238 |
67
- | 0.1345 | 15.0 | 2730 | 0.6416 | 0.8245 |
68
- | 0.1009 | 16.0 | 2912 | 0.6678 | 0.8231 |
69
- | 0.1044 | 17.0 | 3094 | 0.6740 | 0.8224 |
70
- | 0.0772 | 18.0 | 3276 | 0.6965 | 0.8197 |
71
- | 0.0887 | 19.0 | 3458 | 0.7031 | 0.8266 |
72
- | 0.0734 | 20.0 | 3640 | 0.7171 | 0.8252 |
73
- | 0.0684 | 21.0 | 3822 | 0.7423 | 0.8259 |
74
- | 0.0645 | 22.0 | 4004 | 0.7384 | 0.8252 |
75
- | 0.0582 | 23.0 | 4186 | 0.7866 | 0.8197 |
76
- | 0.049 | 24.0 | 4368 | 0.7721 | 0.8231 |
77
- | 0.0382 | 25.0 | 4550 | 0.7791 | 0.8279 |
78
- | 0.0407 | 26.0 | 4732 | 0.7815 | 0.8300 |
79
- | 0.0431 | 27.0 | 4914 | 0.8023 | 0.8231 |
80
- | 0.0424 | 28.0 | 5096 | 0.8114 | 0.8266 |
81
- | 0.0477 | 29.0 | 5278 | 0.8185 | 0.8252 |
82
- | 0.0337 | 30.0 | 5460 | 0.8229 | 0.8259 |
83
- | 0.037 | 31.0 | 5642 | 0.8141 | 0.8286 |
84
- | 0.0304 | 32.0 | 5824 | 0.8272 | 0.8259 |
85
- | 0.0299 | 33.0 | 6006 | 0.8365 | 0.8273 |
86
- | 0.0175 | 34.0 | 6188 | 0.8417 | 0.8307 |
87
- | 0.0364 | 35.0 | 6370 | 0.8430 | 0.8286 |
88
- | 0.0247 | 36.0 | 6552 | 0.8539 | 0.8259 |
89
- | 0.026 | 37.0 | 6734 | 0.8562 | 0.8293 |
90
- | 0.024 | 38.0 | 6916 | 0.8610 | 0.8293 |
91
- | 0.0176 | 39.0 | 7098 | 0.8495 | 0.8293 |
92
- | 0.0159 | 40.0 | 7280 | 0.8643 | 0.8266 |
93
- | 0.0218 | 41.0 | 7462 | 0.8681 | 0.8293 |
94
- | 0.0197 | 42.0 | 7644 | 0.8669 | 0.8279 |
95
- | 0.0293 | 43.0 | 7826 | 0.8597 | 0.8307 |
96
- | 0.027 | 44.0 | 8008 | 0.8641 | 0.8286 |
97
- | 0.0242 | 45.0 | 8190 | 0.8795 | 0.8300 |
98
- | 0.0196 | 46.0 | 8372 | 0.8684 | 0.8286 |
99
- | 0.0175 | 47.0 | 8554 | 0.8710 | 0.8279 |
100
- | 0.022 | 48.0 | 8736 | 0.8773 | 0.8259 |
101
- | 0.0149 | 49.0 | 8918 | 0.8780 | 0.8279 |
102
- | 0.0195 | 50.0 | 9100 | 0.8778 | 0.8279 |
103
 
104
 
105
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.5795
22
+ - Accuracy: 0.8630
23
 
24
  ## Model description
25
 
 
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
+ - learning_rate: 3e-05
42
+ - train_batch_size: 64
43
+ - eval_batch_size: 64
44
  - seed: 42
45
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
  - lr_scheduler_type: linear
47
+ - num_epochs: 15
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | 1.435 | 1.0 | 106 | 1.1905 | 0.7450 |
54
+ | 0.8006 | 2.0 | 212 | 0.7220 | 0.8152 |
55
+ | 0.5227 | 3.0 | 318 | 0.5708 | 0.8406 |
56
+ | 0.4252 | 4.0 | 424 | 0.5011 | 0.8501 |
57
+ | 0.3078 | 5.0 | 530 | 0.4905 | 0.8506 |
58
+ | 0.2471 | 6.0 | 636 | 0.5174 | 0.8447 |
59
+ | 0.1752 | 7.0 | 742 | 0.5095 | 0.8589 |
60
+ | 0.2241 | 8.0 | 848 | 0.5265 | 0.8524 |
61
+ | 0.1165 | 9.0 | 954 | 0.5525 | 0.8577 |
62
+ | 0.102 | 10.0 | 1060 | 0.5510 | 0.8512 |
63
+ | 0.0691 | 11.0 | 1166 | 0.5730 | 0.8577 |
64
+ | 0.0809 | 12.0 | 1272 | 0.5670 | 0.8619 |
65
+ | 0.0631 | 13.0 | 1378 | 0.5715 | 0.8625 |
66
+ | 0.0589 | 14.0 | 1484 | 0.5756 | 0.8625 |
67
+ | 0.0628 | 15.0 | 1590 | 0.5795 | 0.8630 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68
 
69
 
70
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c80e76b58d5a7152a61841bb9c37ec309d9d8fb9a27f4fdc425db3e790381353
3
  size 267937160
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d07ae015aae003d01f97b5a1a3c9e3dc364765b7cc7eff695ee3035d9cf0ac56
3
  size 267937160
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4af805ea007b2bcdc9794a53df0c5aca5005efe40df073cf440e37d0f2290937
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c863f887a899b47469fab8a8080de592e8d9b33244add6965c6e3f9fe01692d9
3
  size 5240