Hugging Face's logo

lengocquangLAB
/
slac-single-head

Transformers
Safetensors
bert_model
Generated from Trainer
Model card Files
xet
 Community
lengocquangLAB commited on
Commit
c96a411
·
verified ·
1 Parent(s): a7f0958

End of training

Browse files
Files changed (4) hide show
  1. README.md +23 -23
  2. config.json +4 -4
  3. model.safetensors +1 -1
  4. training_args.bin +1 -1
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: 1.5583
18
- - F1 Macro: 0.2390
19
- - Precision Macro: 0.1576
20
- - Recall Macro: 0.5983
21
- - F1 Micro: 0.2661
22
- - Precision Micro: 0.1710
23
- - Recall Micro: 0.6
24
 
25
  ## Model description
26
 
@@ -45,28 +45,28 @@ The following hyperparameters were used during training:
45
  - seed: 42
46
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
  - lr_scheduler_type: linear
48
- - lr_scheduler_warmup_steps: 1
49
  - num_epochs: 15
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | F1 Macro | Precision Macro | Recall Macro | F1 Micro | Precision Micro | Recall Micro |
54
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------------:|:------------:|:--------:|:---------------:|:------------:|
55
- | 1.4025 | 1.0 | 2 | 1.6025 | 0.1875 | 0.1116 | 0.7115 | 0.2386 | 0.1414 | 0.7636 |
56
- | 1.082 | 2.0 | 4 | 1.5860 | 0.1866 | 0.1109 | 0.7204 | 0.2353 | 0.1391 | 0.7636 |
57
- | 1.1491 | 3.0 | 6 | 1.5860 | 0.2050 | 0.1298 | 0.7134 | 0.2363 | 0.1404 | 0.7455 |
58
- | 1.134 | 4.0 | 8 | 1.5785 | 0.2097 | 0.1311 | 0.7134 | 0.2405 | 0.1434 | 0.7455 |
59
- | 1.1738 | 5.0 | 10 | 1.5680 | 0.2450 | 0.1561 | 0.7589 | 0.2567 | 0.1536 | 0.7818 |
60
- | 1.2036 | 6.0 | 12 | 1.5670 | 0.2407 | 0.1538 | 0.7257 | 0.2611 | 0.1583 | 0.7455 |
61
- | 1.0812 | 7.0 | 14 | 1.5687 | 0.2399 | 0.1537 | 0.7065 | 0.2614 | 0.1594 | 0.7273 |
62
- | 1.2164 | 8.0 | 16 | 1.5680 | 0.2403 | 0.1551 | 0.6769 | 0.2648 | 0.1638 | 0.6909 |
63
- | 1.0811 | 9.0 | 18 | 1.5678 | 0.2085 | 0.1359 | 0.5807 | 0.2357 | 0.1467 | 0.6 |
64
- | 0.999 | 10.0 | 20 | 1.5698 | 0.2155 | 0.1397 | 0.5895 | 0.2444 | 0.1535 | 0.6 |
65
- | 1.071 | 11.0 | 22 | 1.5737 | 0.2212 | 0.1450 | 0.5807 | 0.2578 | 0.1642 | 0.6 |
66
- | 1.2738 | 12.0 | 24 | 1.5721 | 0.2291 | 0.1501 | 0.5911 | 0.2688 | 0.1717 | 0.6182 |
67
- | 0.9731 | 13.0 | 26 | 1.5666 | 0.2339 | 0.1541 | 0.5895 | 0.2672 | 0.1719 | 0.6 |
68
- | 1.072 | 14.0 | 28 | 1.5598 | 0.2405 | 0.1591 | 0.5983 | 0.2672 | 0.1719 | 0.6 |
69
- | 1.0495 | 15.0 | 30 | 1.5583 | 0.2390 | 0.1576 | 0.5983 | 0.2661 | 0.1710 | 0.6 |
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: 0.5482
18
+ - F1 Macro: 0.8380
19
+ - Precision Macro: 0.8096
20
+ - Recall Macro: 0.8688
21
+ - F1 Micro: 0.8552
22
+ - Precision Micro: 0.8252
23
+ - Recall Micro: 0.8874
24
 
25
  ## Model description
26
 
 
45
  - seed: 42
46
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
  - lr_scheduler_type: linear
48
+ - lr_scheduler_warmup_steps: 212
49
  - num_epochs: 15
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | F1 Macro | Precision Macro | Recall Macro | F1 Micro | Precision Micro | Recall Micro |
54
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------------:|:------------:|:--------:|:---------------:|:------------:|
55
+ | 0.6444 | 1.0 | 213 | 0.5045 | 0.6683 | 0.5514 | 0.9416 | 0.6611 | 0.5087 | 0.9437 |
56
+ | 0.3875 | 2.0 | 426 | 0.3121 | 0.8016 | 0.7045 | 0.9342 | 0.8214 | 0.7272 | 0.9437 |
57
+ | 0.292 | 3.0 | 639 | 0.3003 | 0.8095 | 0.7256 | 0.9294 | 0.8265 | 0.7398 | 0.9361 |
58
+ | 0.2172 | 4.0 | 852 | 0.3231 | 0.8340 | 0.7807 | 0.8982 | 0.8509 | 0.7973 | 0.9122 |
59
+ | 0.1935 | 5.0 | 1065 | 0.3262 | 0.8262 | 0.7628 | 0.9073 | 0.8445 | 0.7826 | 0.9170 |
60
+ | 0.154 | 6.0 | 1278 | 0.3807 | 0.8351 | 0.7975 | 0.8794 | 0.8506 | 0.8183 | 0.8855 |
61
+ | 0.1007 | 7.0 | 1491 | 0.4045 | 0.8297 | 0.7774 | 0.8922 | 0.8456 | 0.7902 | 0.9094 |
62
+ | 0.0866 | 8.0 | 1704 | 0.4100 | 0.8289 | 0.7706 | 0.9010 | 0.8434 | 0.7863 | 0.9094 |
63
+ | 0.0671 | 9.0 | 1917 | 0.4667 | 0.8335 | 0.7981 | 0.8726 | 0.8497 | 0.8127 | 0.8903 |
64
+ | 0.0544 | 10.0 | 2130 | 0.5062 | 0.8412 | 0.8139 | 0.8707 | 0.8557 | 0.8254 | 0.8884 |
65
+ | 0.0482 | 11.0 | 2343 | 0.5141 | 0.8335 | 0.8076 | 0.8616 | 0.8521 | 0.8287 | 0.8769 |
66
+ | 0.0377 | 12.0 | 2556 | 0.5217 | 0.8346 | 0.8022 | 0.8699 | 0.8520 | 0.8194 | 0.8874 |
67
+ | 0.0304 | 13.0 | 2769 | 0.5419 | 0.8370 | 0.8104 | 0.8658 | 0.8537 | 0.8266 | 0.8826 |
68
+ | 0.0307 | 14.0 | 2982 | 0.5397 | 0.8367 | 0.8043 | 0.8721 | 0.8533 | 0.8210 | 0.8884 |
69
+ | 0.0238 | 15.0 | 3195 | 0.5482 | 0.8380 | 0.8096 | 0.8688 | 0.8552 | 0.8252 | 0.8874 |
70
 
71
 
72
  ### Framework versions
config.json CHANGED
@@ -5,10 +5,10 @@
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"
 
5
  "model_type": "bert_model",
6
  "num_classes": 4,
7
  "pos_weight": [
8
+ 6.803561171740379,
9
+ 7.997350993377483,
10
+ 2.8530913216108904,
11
+ 5.13086642599278
12
  ],
13
  "torch_dtype": "float32",
14
  "transformers_version": "4.47.0"
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:191121d51980d0d8c5013bc3635cdc65881e296ec8b5234d24986f51e87c2267
3
  size 437964888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0a8d66f9bde3494d37e915b2988a90446b69b7fe4d49d6f8d7c62a6dff08272
3
  size 437964888
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4014918409db83589f1bbd62c7b44833686b2ff8b3bad5a08246ddc7f29f031a
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da5fdee7b06418ccb0926044f31cc7ddb86ef91a16318e6916dc80154b687146
3
  size 5368