Hugging Face's logo

qfrodicio
/
roberta-finetuned-intention-prediction-es

Token Classification
Transformers
TensorBoard
Safetensors
roberta
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
qfrodicio commited on
Commit
1ce6bc6
•
1 Parent(s): 49efb43

Training complete

Browse files
Files changed (3) hide show
  1. README.md +25 -25
  2. model.safetensors +1 -1
  3. runs/Jan18_22-14-03_e4b89d56e316/events.out.tfevents.1705616046.e4b89d56e316.398.0 +2 -2
README.md CHANGED
@@ -19,11 +19,11 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [MMG/mlm-spanish-roberta-base](https://huggingface.co/MMG/mlm-spanish-roberta-base) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 1.8994
23
- - Accuracy: 0.6775
24
- - Precision: 0.6807
25
- - Recall: 0.6775
26
- - F1: 0.6699
27
 
28
  ## Model description
29
 
@@ -54,26 +54,26 @@ The following hyperparameters were used during training:
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
56
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
57
- | 2.2919 | 1.0 | 102 | 1.6955 | 0.5146 | 0.4756 | 0.5146 | 0.4444 |
58
- | 1.3437 | 2.0 | 204 | 1.3834 | 0.5850 | 0.5693 | 0.5850 | 0.5589 |
59
- | 0.8812 | 3.0 | 306 | 1.2719 | 0.6372 | 0.6285 | 0.6372 | 0.6200 |
60
- | 0.5649 | 4.0 | 408 | 1.3629 | 0.6361 | 0.6518 | 0.6361 | 0.6253 |
61
- | 0.39 | 5.0 | 510 | 1.4240 | 0.6439 | 0.6585 | 0.6439 | 0.6396 |
62
- | 0.2704 | 6.0 | 612 | 1.4209 | 0.6536 | 0.6583 | 0.6536 | 0.6383 |
63
- | 0.1785 | 7.0 | 714 | 1.4966 | 0.6647 | 0.6760 | 0.6647 | 0.6533 |
64
- | 0.1208 | 8.0 | 816 | 1.5681 | 0.6623 | 0.6764 | 0.6623 | 0.6504 |
65
- | 0.0802 | 9.0 | 918 | 1.6662 | 0.6612 | 0.6691 | 0.6612 | 0.6501 |
66
- | 0.0565 | 10.0 | 1020 | 1.6779 | 0.6752 | 0.6721 | 0.6752 | 0.6653 |
67
- | 0.0368 | 11.0 | 1122 | 1.6974 | 0.6735 | 0.6806 | 0.6735 | 0.6653 |
68
- | 0.0267 | 12.0 | 1224 | 1.7552 | 0.6842 | 0.6860 | 0.6842 | 0.6754 |
69
- | 0.0177 | 13.0 | 1326 | 1.8757 | 0.6714 | 0.6725 | 0.6714 | 0.6613 |
70
- | 0.0142 | 14.0 | 1428 | 1.8640 | 0.6723 | 0.6745 | 0.6723 | 0.6622 |
71
- | 0.0114 | 15.0 | 1530 | 1.8517 | 0.6795 | 0.6864 | 0.6795 | 0.6716 |
72
- | 0.0081 | 16.0 | 1632 | 1.8696 | 0.6755 | 0.6780 | 0.6755 | 0.6668 |
73
- | 0.0075 | 17.0 | 1734 | 1.8885 | 0.6752 | 0.6840 | 0.6752 | 0.6667 |
74
- | 0.0059 | 18.0 | 1836 | 1.8893 | 0.6775 | 0.6809 | 0.6775 | 0.6698 |
75
- | 0.0051 | 19.0 | 1938 | 1.9001 | 0.6775 | 0.6810 | 0.6775 | 0.6700 |
76
- | 0.0048 | 20.0 | 2040 | 1.8994 | 0.6775 | 0.6807 | 0.6775 | 0.6699 |
77
 
78
 
79
  ### Framework versions
 
19
 
20
  This model is a fine-tuned version of [MMG/mlm-spanish-roberta-base](https://huggingface.co/MMG/mlm-spanish-roberta-base) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 1.9210
23
+ - Accuracy: 0.6612
24
+ - Precision: 0.6636
25
+ - Recall: 0.6612
26
+ - F1: 0.6548
27
 
28
  ## Model description
29
 
 
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
56
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
57
+ | 2.2916 | 1.0 | 102 | 1.7136 | 0.5086 | 0.4698 | 0.5086 | 0.4377 |
58
+ | 1.3326 | 2.0 | 204 | 1.4443 | 0.5805 | 0.5827 | 0.5805 | 0.5601 |
59
+ | 0.8798 | 3.0 | 306 | 1.2932 | 0.6344 | 0.6276 | 0.6344 | 0.6150 |
60
+ | 0.5609 | 4.0 | 408 | 1.3591 | 0.6350 | 0.6465 | 0.6350 | 0.6264 |
61
+ | 0.3819 | 5.0 | 510 | 1.4155 | 0.6455 | 0.6559 | 0.6455 | 0.6400 |
62
+ | 0.2587 | 6.0 | 612 | 1.4981 | 0.6462 | 0.6592 | 0.6462 | 0.6296 |
63
+ | 0.1779 | 7.0 | 714 | 1.5921 | 0.6382 | 0.6529 | 0.6382 | 0.6343 |
64
+ | 0.108 | 8.0 | 816 | 1.6453 | 0.6585 | 0.6634 | 0.6585 | 0.6508 |
65
+ | 0.0788 | 9.0 | 918 | 1.6822 | 0.6509 | 0.6510 | 0.6509 | 0.6422 |
66
+ | 0.0577 | 10.0 | 1020 | 1.7348 | 0.6641 | 0.6663 | 0.6641 | 0.6562 |
67
+ | 0.0455 | 11.0 | 1122 | 1.8055 | 0.6458 | 0.6550 | 0.6458 | 0.6411 |
68
+ | 0.0292 | 12.0 | 1224 | 1.8641 | 0.6640 | 0.6763 | 0.6640 | 0.6579 |
69
+ | 0.0212 | 13.0 | 1326 | 1.8370 | 0.6551 | 0.6545 | 0.6551 | 0.6472 |
70
+ | 0.0154 | 14.0 | 1428 | 1.8450 | 0.6649 | 0.6703 | 0.6649 | 0.6583 |
71
+ | 0.0107 | 15.0 | 1530 | 1.8809 | 0.6569 | 0.6572 | 0.6569 | 0.6494 |
72
+ | 0.0096 | 16.0 | 1632 | 1.8759 | 0.6594 | 0.6651 | 0.6594 | 0.6539 |
73
+ | 0.0074 | 17.0 | 1734 | 1.9035 | 0.6652 | 0.6704 | 0.6652 | 0.6597 |
74
+ | 0.0067 | 18.0 | 1836 | 1.9184 | 0.6636 | 0.6672 | 0.6636 | 0.6565 |
75
+ | 0.0059 | 19.0 | 1938 | 1.9216 | 0.6603 | 0.6640 | 0.6603 | 0.6540 |
76
+ | 0.005 | 20.0 | 2040 | 1.9210 | 0.6612 | 0.6636 | 0.6612 | 0.6548 |
77
 
78
 
79
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d4608165a722fd9aa88a465fd09a0bd2fc2276bb04d4e9754b955083023a6c2
3
  size 501743200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9dbd6d95fc4ee317eddfd7bc547e3a408c42bfac3023c7d46c0b6d911dbff43
3
  size 501743200
runs/Jan18_22-14-03_e4b89d56e316/events.out.tfevents.1705616046.e4b89d56e316.398.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:12e14d44ea4480465f8489191eaccacb2725ced71efc10f6856d71a369ce7b75
3
- size 19566
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b837a6d0b13d1095bab3d627a78dde6e1b6853aec4fa608d31287281fb29a080
3
+ size 20549