Hugging Face's logo

adriansanz
/
te-zsc-synthetic_5ep_2805

Text Classification
Transformers
TensorBoard
Safetensors
roberta
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
adriansanz commited on
Commit
1fed65e
·
verified ·
1 Parent(s): 33e4045

End of training

Browse files
Files changed (5) hide show
  1. README.md +38 -38
  2. logs/events.out.tfevents.1716890725.a5a87f3fc98d.2577.2 +3 -0
  3. logs/events.out.tfevents.1716892646.a5a87f3fc98d.2577.5 +3 -0
  4. model.safetensors +1 -1
  5. training_args.bin +1 -1
README.md CHANGED
@@ -9,23 +9,23 @@ metrics:
9
  - recall
10
  - f1
11
  model-index:
12
- - name: 080524_epoch_1
13
  results: []
14
  ---
15
 
16
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
  should probably proofread and complete it, then remove this comment. -->
18
 
19
- # 080524_epoch_1
20
 
21
  This model is a fine-tuned version of [projecte-aina/roberta-base-ca-v2-cased-te](https://huggingface.co/projecte-aina/roberta-base-ca-v2-cased-te) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.3600
24
- - Accuracy: 0.969
25
- - Precision: 0.9692
26
- - Recall: 0.969
27
- - F1: 0.9690
28
- - Ratio: 0.489
29
 
30
  ## Model description
31
 
@@ -61,36 +61,36 @@ The following hyperparameters were used during training:
61
 
62
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Ratio |
63
  |:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:-----:|
64
- | 3.2945 | 0.0333 | 10 | 1.1037 | 0.725 | 0.7286 | 0.7250 | 0.7239 | 0.563 |
65
- | 0.9071 | 0.0667 | 20 | 0.7622 | 0.787 | 0.8184 | 0.7870 | 0.7816 | 0.343 |
66
- | 0.76 | 0.1 | 30 | 0.5554 | 0.904 | 0.9045 | 0.904 | 0.9040 | 0.482 |
67
- | 0.614 | 0.1333 | 40 | 0.5082 | 0.925 | 0.9253 | 0.925 | 0.9250 | 0.513 |
68
- | 0.5943 | 0.1667 | 50 | 0.4751 | 0.936 | 0.9376 | 0.9360 | 0.9359 | 0.47 |
69
- | 0.5569 | 0.2 | 60 | 0.4387 | 0.947 | 0.9472 | 0.9470 | 0.9470 | 0.489 |
70
- | 0.4397 | 0.2333 | 70 | 0.4339 | 0.937 | 0.9371 | 0.937 | 0.9370 | 0.491 |
71
- | 0.443 | 0.2667 | 80 | 0.4495 | 0.927 | 0.9299 | 0.927 | 0.9269 | 0.459 |
72
- | 0.5181 | 0.3 | 90 | 0.3937 | 0.949 | 0.9493 | 0.9490 | 0.9490 | 0.487 |
73
- | 0.4602 | 0.3333 | 100 | 0.4110 | 0.945 | 0.9467 | 0.9450 | 0.9449 | 0.531 |
74
- | 0.3992 | 0.3667 | 110 | 0.3943 | 0.951 | 0.9518 | 0.9510 | 0.9510 | 0.479 |
75
- | 0.3857 | 0.4 | 120 | 0.4006 | 0.951 | 0.9517 | 0.9510 | 0.9510 | 0.519 |
76
- | 0.4158 | 0.4333 | 130 | 0.3808 | 0.958 | 0.9581 | 0.958 | 0.9580 | 0.492 |
77
- | 0.422 | 0.4667 | 140 | 0.3809 | 0.956 | 0.9562 | 0.956 | 0.9560 | 0.49 |
78
- | 0.3816 | 0.5 | 150 | 0.3960 | 0.957 | 0.9573 | 0.957 | 0.9570 | 0.487 |
79
- | 0.4526 | 0.5333 | 160 | 0.3833 | 0.961 | 0.9610 | 0.961 | 0.9610 | 0.495 |
80
- | 0.4347 | 0.5667 | 170 | 0.3979 | 0.949 | 0.9510 | 0.9490 | 0.9489 | 0.467 |
81
- | 0.415 | 0.6 | 180 | 0.3673 | 0.963 | 0.9632 | 0.963 | 0.9630 | 0.491 |
82
- | 0.437 | 0.6333 | 190 | 0.3673 | 0.964 | 0.9640 | 0.964 | 0.9640 | 0.502 |
83
- | 0.3539 | 0.6667 | 200 | 0.3669 | 0.965 | 0.9650 | 0.965 | 0.9650 | 0.497 |
84
- | 0.4564 | 0.7 | 210 | 0.3713 | 0.964 | 0.9644 | 0.964 | 0.9640 | 0.486 |
85
- | 0.4008 | 0.7333 | 220 | 0.3639 | 0.966 | 0.9661 | 0.966 | 0.9660 | 0.492 |
86
- | 0.418 | 0.7667 | 230 | 0.3621 | 0.964 | 0.9640 | 0.964 | 0.9640 | 0.496 |
87
- | 0.4087 | 0.8 | 240 | 0.3581 | 0.968 | 0.9680 | 0.968 | 0.9680 | 0.498 |
88
- | 0.4132 | 0.8333 | 250 | 0.3579 | 0.967 | 0.9672 | 0.967 | 0.9670 | 0.489 |
89
- | 0.3861 | 0.8667 | 260 | 0.3622 | 0.967 | 0.9673 | 0.967 | 0.9670 | 0.487 |
90
- | 0.4345 | 0.9 | 270 | 0.3616 | 0.967 | 0.9673 | 0.967 | 0.9670 | 0.487 |
91
- | 0.3376 | 0.9333 | 280 | 0.3604 | 0.969 | 0.9692 | 0.969 | 0.9690 | 0.489 |
92
- | 0.4226 | 0.9667 | 290 | 0.3600 | 0.969 | 0.9692 | 0.969 | 0.9690 | 0.489 |
93
- | 0.3835 | 1.0 | 300 | 0.3600 | 0.969 | 0.9692 | 0.969 | 0.9690 | 0.489 |
94
 
95
 
96
  ### Framework versions
 
9
  - recall
10
  - f1
11
  model-index:
12
+ - name: 080524_epoch_2
13
  results: []
14
  ---
15
 
16
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
  should probably proofread and complete it, then remove this comment. -->
18
 
19
+ # 080524_epoch_2
20
 
21
  This model is a fine-tuned version of [projecte-aina/roberta-base-ca-v2-cased-te](https://huggingface.co/projecte-aina/roberta-base-ca-v2-cased-te) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.3500
24
+ - Accuracy: 0.976
25
+ - Precision: 0.9760
26
+ - Recall: 0.976
27
+ - F1: 0.9760
28
+ - Ratio: 0.496
29
 
30
  ## Model description
31
 
 
61
 
62
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Ratio |
63
  |:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:-----:|
64
+ | 0.4257 | 0.0333 | 10 | 0.3627 | 0.963 | 0.9633 | 0.963 | 0.9630 | 0.487 |
65
+ | 0.4057 | 0.0667 | 20 | 0.4096 | 0.935 | 0.9399 | 0.935 | 0.9348 | 0.447 |
66
+ | 0.4257 | 0.1 | 30 | 0.3737 | 0.961 | 0.9622 | 0.9610 | 0.9610 | 0.475 |
67
+ | 0.3671 | 0.1333 | 40 | 0.3662 | 0.962 | 0.9633 | 0.962 | 0.9620 | 0.474 |
68
+ | 0.4061 | 0.1667 | 50 | 0.3580 | 0.972 | 0.972 | 0.972 | 0.972 | 0.5 |
69
+ | 0.39 | 0.2 | 60 | 0.3659 | 0.963 | 0.9632 | 0.963 | 0.9630 | 0.489 |
70
+ | 0.3443 | 0.2333 | 70 | 0.3766 | 0.966 | 0.9665 | 0.966 | 0.9660 | 0.516 |
71
+ | 0.3711 | 0.2667 | 80 | 0.4009 | 0.953 | 0.9547 | 0.9530 | 0.9530 | 0.469 |
72
+ | 0.3854 | 0.3 | 90 | 0.3621 | 0.97 | 0.9703 | 0.97 | 0.9700 | 0.488 |
73
+ | 0.3758 | 0.3333 | 100 | 0.3601 | 0.968 | 0.9681 | 0.968 | 0.9680 | 0.492 |
74
+ | 0.3348 | 0.3667 | 110 | 0.3739 | 0.969 | 0.9700 | 0.969 | 0.9690 | 0.477 |
75
+ | 0.3826 | 0.4 | 120 | 0.3846 | 0.964 | 0.9657 | 0.964 | 0.9640 | 0.47 |
76
+ | 0.384 | 0.4333 | 130 | 0.3473 | 0.977 | 0.9770 | 0.977 | 0.9770 | 0.497 |
77
+ | 0.3682 | 0.4667 | 140 | 0.3465 | 0.975 | 0.9750 | 0.975 | 0.9750 | 0.495 |
78
+ | 0.368 | 0.5 | 150 | 0.3551 | 0.973 | 0.9732 | 0.973 | 0.9730 | 0.489 |
79
+ | 0.3479 | 0.5333 | 160 | 0.3568 | 0.973 | 0.9732 | 0.973 | 0.9730 | 0.491 |
80
+ | 0.3971 | 0.5667 | 170 | 0.3517 | 0.974 | 0.9741 | 0.974 | 0.9740 | 0.492 |
81
+ | 0.3359 | 0.6 | 180 | 0.3482 | 0.976 | 0.9761 | 0.976 | 0.9760 | 0.494 |
82
+ | 0.3441 | 0.6333 | 190 | 0.3495 | 0.977 | 0.9770 | 0.977 | 0.9770 | 0.499 |
83
+ | 0.3319 | 0.6667 | 200 | 0.3500 | 0.977 | 0.9770 | 0.977 | 0.9770 | 0.495 |
84
+ | 0.4326 | 0.7 | 210 | 0.3561 | 0.975 | 0.9754 | 0.975 | 0.9750 | 0.485 |
85
+ | 0.4003 | 0.7333 | 220 | 0.3499 | 0.978 | 0.9783 | 0.978 | 0.9780 | 0.488 |
86
+ | 0.3653 | 0.7667 | 230 | 0.3503 | 0.976 | 0.9760 | 0.976 | 0.9760 | 0.498 |
87
+ | 0.3427 | 0.8 | 240 | 0.3522 | 0.974 | 0.9740 | 0.974 | 0.9740 | 0.498 |
88
+ | 0.3706 | 0.8333 | 250 | 0.3495 | 0.975 | 0.9750 | 0.975 | 0.9750 | 0.497 |
89
+ | 0.3726 | 0.8667 | 260 | 0.3498 | 0.975 | 0.9751 | 0.975 | 0.9750 | 0.493 |
90
+ | 0.4217 | 0.9 | 270 | 0.3501 | 0.974 | 0.9741 | 0.974 | 0.9740 | 0.494 |
91
+ | 0.317 | 0.9333 | 280 | 0.3506 | 0.976 | 0.9760 | 0.976 | 0.9760 | 0.496 |
92
+ | 0.3976 | 0.9667 | 290 | 0.3502 | 0.975 | 0.9750 | 0.975 | 0.9750 | 0.497 |
93
+ | 0.3378 | 1.0 | 300 | 0.3500 | 0.976 | 0.9760 | 0.976 | 0.9760 | 0.496 |
94
 
95
 
96
  ### Framework versions
logs/events.out.tfevents.1716890725.a5a87f3fc98d.2577.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:683bb7650f82857db4878141b088cb1c3146aecb8f7b584ab3f310491c9a179d
3
+ size 6793
logs/events.out.tfevents.1716892646.a5a87f3fc98d.2577.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77a7f9fbab198f88b2116441b72b7b9411a6d1225ffcf4db35850c4217c9c9a8
3
+ size 609
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed25ebc0de1c925f88483578d3e736c48baae5c50dc1be553e90cdb97bf2e480
3
  size 498606684
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:547244b1713bc5a802d6d237aa1bada305a6bf6f2c185632eff036c4ff7f9ba2
3
  size 498606684
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1c24c5f75828526fdb58ea86eb1646744a8f5c63474fdba7874c2f00ae62083
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fc0082546c1d7fb28388a7807cbe6329e79cbc7a11783f2538d2b4fbe58cab9
3
  size 5112