Hugging Face's logo

lengocquangLAB
/
slac-single-head

Transformers
Safetensors
bert_model
Generated from Trainer
Model card Files
xet
Community
lengocquangLAB commited on
Commit
5d5f5d4
·
verified ·
1 Parent(s): d9455af

End of training

Browse files
Files changed (3) hide show
  1. README.md +22 -22
  2. config.json +1 -6
  3. model.safetensors +2 -2
README.md CHANGED
@@ -14,13 +14,13 @@ 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: 1.5153
18
- - F1 Macro: 0.3202
19
- - Precision Macro: 0.2175
20
- - Recall Macro: 0.6571
21
- - F1 Micro: 0.3451
22
- - Precision Micro: 0.2281
23
- - Recall Micro: 0.7091
24
 
25
  ## Model description
26
 
@@ -52,21 +52,21 @@ The following hyperparameters were used during training:
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | F1 Macro | Precision Macro | Recall Macro | F1 Micro | Precision Micro | Recall Micro |
54
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------------:|:------------:|:--------:|:---------------:|:------------:|
55
- | 1.3757 | 1.0 | 2 | 1.6881 | 0.1334 | 0.1078 | 0.2213 | 0.1699 | 0.1327 | 0.2364 |
56
- | 1.0487 | 2.0 | 4 | 1.6485 | 0.2149 | 0.2115 | 0.3791 | 0.2418 | 0.1732 | 0.4 |
57
- | 1.0743 | 3.0 | 6 | 1.6470 | 0.2522 | 0.2857 | 0.3791 | 0.2895 | 0.2268 | 0.4 |
58
- | 1.0245 | 4.0 | 8 | 1.6460 | 0.2222 | 0.1721 | 0.3475 | 0.2877 | 0.2308 | 0.3818 |
59
- | 1.1128 | 5.0 | 10 | 1.6505 | 0.2230 | 0.1862 | 0.3075 | 0.2812 | 0.2466 | 0.3273 |
60
- | 1.1014 | 6.0 | 12 | 1.6555 | 0.2402 | 0.2075 | 0.3075 | 0.2927 | 0.2647 | 0.3273 |
61
- | 1.0573 | 7.0 | 14 | 1.6526 | 0.2448 | 0.2038 | 0.3267 | 0.2946 | 0.2568 | 0.3455 |
62
- | 1.1008 | 8.0 | 16 | 1.6273 | 0.2472 | 0.1970 | 0.3579 | 0.2993 | 0.2391 | 0.4 |
63
- | 1.0884 | 9.0 | 18 | 1.5901 | 0.2887 | 0.2171 | 0.4627 | 0.3256 | 0.2393 | 0.5091 |
64
- | 0.9172 | 10.0 | 20 | 1.5491 | 0.3261 | 0.2319 | 0.5814 | 0.3518 | 0.2431 | 0.6364 |
65
- | 1.0732 | 11.0 | 22 | 1.5236 | 0.3359 | 0.2291 | 0.6799 | 0.3587 | 0.2381 | 0.7273 |
66
- | 1.2515 | 12.0 | 24 | 1.5132 | 0.3258 | 0.2200 | 0.6799 | 0.3463 | 0.2273 | 0.7273 |
67
- | 0.9967 | 13.0 | 26 | 1.5129 | 0.3258 | 0.2200 | 0.6799 | 0.3463 | 0.2273 | 0.7273 |
68
- | 1.009 | 14.0 | 28 | 1.5137 | 0.3182 | 0.2159 | 0.6571 | 0.3421 | 0.2254 | 0.7091 |
69
- | 0.9672 | 15.0 | 30 | 1.5153 | 0.3202 | 0.2175 | 0.6571 | 0.3451 | 0.2281 | 0.7091 |
70
 
71
 
72
  ### 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: 0.4198
18
+ - F1 Macro: 0.0
19
+ - Precision Macro: 0.0
20
+ - Recall Macro: 0.0
21
+ - F1 Micro: 0.0
22
+ - Precision Micro: 0.0
23
+ - Recall Micro: 0.0
24
 
25
  ## Model description
26
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | F1 Macro | Precision Macro | Recall Macro | F1 Micro | Precision Micro | Recall Micro |
54
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------------:|:------------:|:--------:|:---------------:|:------------:|
55
+ | 0.66 | 1.0 | 2 | 0.5815 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
56
+ | 0.547 | 2.0 | 4 | 0.5486 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
57
+ | 0.5301 | 3.0 | 6 | 0.5299 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
58
+ | 0.5108 | 4.0 | 8 | 0.5097 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
59
+ | 0.488 | 5.0 | 10 | 0.4892 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
60
+ | 0.4685 | 6.0 | 12 | 0.4751 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
61
+ | 0.4426 | 7.0 | 14 | 0.4647 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
62
+ | 0.4519 | 8.0 | 16 | 0.4542 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
63
+ | 0.4134 | 9.0 | 18 | 0.4444 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
64
+ | 0.4029 | 10.0 | 20 | 0.4363 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
65
+ | 0.3892 | 11.0 | 22 | 0.4297 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
66
+ | 0.4437 | 12.0 | 24 | 0.4252 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
67
+ | 0.4007 | 13.0 | 26 | 0.4223 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
68
+ | 0.4018 | 14.0 | 28 | 0.4205 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
69
+ | 0.4107 | 15.0 | 30 | 0.4198 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
70
 
71
 
72
  ### Framework versions
config.json CHANGED
@@ -4,12 +4,7 @@
4
  ],
5
  "model_type": "bert_model",
6
  "num_classes": 4,
7
- "pos_weight": [
8
- 24.0,
9
- 15.666666666666666,
10
- 4.555555555555555,
11
- 6.142857142857143
12
- ],
13
  "torch_dtype": "float32",
14
  "transformers_version": "4.47.0"
15
  }
 
4
  ],
5
  "model_type": "bert_model",
6
  "num_classes": 4,
7
+ "pos_weight": null,
 
 
 
 
 
8
  "torch_dtype": "float32",
9
  "transformers_version": "4.47.0"
10
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d8c6b5a354e4768b82ed9a8917121d01d9207a04b17e4226ae76eafb9f1e7e88
3
- size 437964888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02438d595c6cc2a6c817f9b9f7483ebba9edc253325362fc02c613de353c8e42
3
+ size 437964784