Hugging Face's logo

lucienbaumgartner
/
multilabel_classification

PEFT
Safetensors
Generated from Trainer
Model card Files Community
lucienbaumgartner commited on
Commit
07cd446
·
verified ·
1 Parent(s): eb71f2d

lucienbaumgartner/mtg-spike-multilabel-distilbert

Browse files
Files changed (4) hide show
  1. README.md +17 -17
  2. adapter_config.json +2 -2
  3. adapter_model.safetensors +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -20,13 +20,13 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.3549
24
- - F1 Micro: 0.8864
25
- - F1 Macro: 0.8088
26
- - F1 Weighted: 0.8819
27
- - Precision: 0.8811
28
- - Recall: 0.8864
29
- - Accuracy: 0.8864
30
 
31
  ## Model description
32
 
@@ -57,16 +57,16 @@ The following hyperparameters were used during training:
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | F1 Micro | F1 Macro | F1 Weighted | Precision | Recall | Accuracy |
59
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:-----------:|:---------:|:------:|:--------:|
60
- | No log | 1.0 | 406 | 0.3510 | 0.8886 | 0.8121 | 0.8841 | 0.8834 | 0.8886 | 0.8886 |
61
- | 0.082 | 2.0 | 812 | 0.3618 | 0.8909 | 0.8193 | 0.8875 | 0.8864 | 0.8909 | 0.8909 |
62
- | 0.0848 | 3.0 | 1218 | 0.3768 | 0.8925 | 0.8206 | 0.8887 | 0.8879 | 0.8925 | 0.8925 |
63
- | 0.0703 | 4.0 | 1624 | 0.3706 | 0.8953 | 0.8242 | 0.8913 | 0.8908 | 0.8953 | 0.8953 |
64
- | 0.0806 | 5.0 | 2030 | 0.3868 | 0.8903 | 0.8169 | 0.8864 | 0.8855 | 0.8903 | 0.8903 |
65
- | 0.0806 | 6.0 | 2436 | 0.3988 | 0.8920 | 0.8211 | 0.8887 | 0.8876 | 0.8920 | 0.8920 |
66
- | 0.0721 | 7.0 | 2842 | 0.4085 | 0.8898 | 0.8174 | 0.8864 | 0.8853 | 0.8898 | 0.8898 |
67
- | 0.0701 | 8.0 | 3248 | 0.4035 | 0.8881 | 0.8149 | 0.8847 | 0.8835 | 0.8881 | 0.8881 |
68
- | 0.0704 | 9.0 | 3654 | 0.4072 | 0.8886 | 0.8152 | 0.8851 | 0.8840 | 0.8886 | 0.8886 |
69
- | 0.0665 | 10.0 | 4060 | 0.4010 | 0.8909 | 0.8184 | 0.8872 | 0.8863 | 0.8909 | 0.8909 |
70
 
71
 
72
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.2810
24
+ - F1 Micro: 0.8770
25
+ - F1 Macro: 0.7787
26
+ - F1 Weighted: 0.8672
27
+ - Precision: 0.8702
28
+ - Recall: 0.8770
29
+ - Accuracy: 0.8770
30
 
31
  ## Model description
32
 
 
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | F1 Micro | F1 Macro | F1 Weighted | Precision | Recall | Accuracy |
59
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:-----------:|:---------:|:------:|:--------:|
60
+ | No log | 1.0 | 406 | 0.2865 | 0.8643 | 0.7287 | 0.8438 | 0.8620 | 0.8643 | 0.8643 |
61
+ | 0.2729 | 2.0 | 812 | 0.2924 | 0.8737 | 0.7671 | 0.8616 | 0.8671 | 0.8737 | 0.8737 |
62
+ | 0.216 | 3.0 | 1218 | 0.2810 | 0.8770 | 0.7787 | 0.8672 | 0.8702 | 0.8770 | 0.8770 |
63
+ | 0.1868 | 4.0 | 1624 | 0.2813 | 0.8787 | 0.7802 | 0.8685 | 0.8725 | 0.8787 | 0.8787 |
64
+ | 0.1728 | 5.0 | 2030 | 0.2944 | 0.8748 | 0.7794 | 0.8664 | 0.8673 | 0.8748 | 0.8748 |
65
+ | 0.1728 | 6.0 | 2436 | 0.2937 | 0.8825 | 0.7967 | 0.8760 | 0.8762 | 0.8825 | 0.8825 |
66
+ | 0.155 | 7.0 | 2842 | 0.3007 | 0.8848 | 0.8039 | 0.8795 | 0.8789 | 0.8848 | 0.8848 |
67
+ | 0.151 | 8.0 | 3248 | 0.3007 | 0.8875 | 0.8070 | 0.8818 | 0.8819 | 0.8875 | 0.8875 |
68
+ | 0.1359 | 9.0 | 3654 | 0.3031 | 0.8870 | 0.8077 | 0.8818 | 0.8814 | 0.8870 | 0.8870 |
69
+ | 0.1359 | 10.0 | 4060 | 0.3035 | 0.8881 | 0.8086 | 0.8826 | 0.8826 | 0.8881 | 0.8881 |
70
 
71
 
72
  ### Framework versions
adapter_config.json CHANGED
@@ -23,9 +23,9 @@
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
26
- "k_lin",
27
  "q_lin",
28
- "v_lin"
29
  ],
30
  "task_type": "SEQ_CLS",
31
  "use_dora": false,
 
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
26
+ "v_lin",
27
  "q_lin",
28
+ "k_lin"
29
  ],
30
  "task_type": "SEQ_CLS",
31
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83428c0c4847c3d7b9fd3e39b946436ee665e4ceeddeaac0f78a0da561412275
3
  size 3268052
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2809a6cfea6ccf854bea549f0dce48f3cd79a4d2bee8c88c39129803b63a659
3
  size 3268052
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea4ef1805460e6423c4cf8a3939aa4616be6e262a52a74d96056b70c2375b8cc
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7e9faa9b323f582e5fbc0aae386cb40cb3e645de7133b573cb73640dbb8ee59
3
  size 4728