Hugging Face's logo

haryoaw
/
scenario-KD-PR-MSV-D2_data-cl-cardiff_cl_only55

PyTorch
deberta-v2
Generated from Trainer
Model card Files Community
haryoaw commited on
Commit
464b0fd
•
1 Parent(s): e2e5107

Initial Commit

Browse files
Files changed (4) hide show
  1. README.md +30 -30
  2. eval_results_cardiff.json +1 -1
  3. pytorch_model.bin +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [haryoaw/scenario-MDBT-TCR_data-cl-cardiff_cl_only](https://huggingface.co/haryoaw/scenario-MDBT-TCR_data-cl-cardiff_cl_only) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 1.3667
22
- - Accuracy: 0.4498
23
- - F1: 0.4460
24
 
25
  ## Model description
26
 
@@ -51,33 +51,33 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
53
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
54
- | No log | 1.09 | 250 | 1.3274 | 0.4414 | 0.4329 |
55
- | 1.1951 | 2.17 | 500 | 1.3413 | 0.4313 | 0.4184 |
56
- | 1.1951 | 3.26 | 750 | 1.3228 | 0.4522 | 0.4520 |
57
- | 1.0525 | 4.35 | 1000 | 1.3619 | 0.4367 | 0.4264 |
58
- | 1.0525 | 5.43 | 1250 | 1.3559 | 0.4437 | 0.4391 |
59
- | 0.9861 | 6.52 | 1500 | 1.3555 | 0.4483 | 0.4452 |
60
- | 0.9861 | 7.61 | 1750 | 1.3473 | 0.4606 | 0.4614 |
61
- | 0.9551 | 8.7 | 2000 | 1.3542 | 0.4691 | 0.4702 |
62
- | 0.9551 | 9.78 | 2250 | 1.3718 | 0.4522 | 0.4521 |
63
- | 0.9387 | 10.87 | 2500 | 1.3580 | 0.4537 | 0.4518 |
64
- | 0.9387 | 11.96 | 2750 | 1.3680 | 0.4545 | 0.4516 |
65
- | 0.9251 | 13.04 | 3000 | 1.3844 | 0.4313 | 0.4213 |
66
- | 0.9251 | 14.13 | 3250 | 1.3735 | 0.4506 | 0.4474 |
67
- | 0.9159 | 15.22 | 3500 | 1.3642 | 0.4606 | 0.4579 |
68
- | 0.9159 | 16.3 | 3750 | 1.3736 | 0.4660 | 0.4603 |
69
- | 0.9092 | 17.39 | 4000 | 1.3857 | 0.4367 | 0.4268 |
70
- | 0.9092 | 18.48 | 4250 | 1.3742 | 0.4529 | 0.4490 |
71
- | 0.9052 | 19.57 | 4500 | 1.3529 | 0.4684 | 0.4682 |
72
- | 0.9052 | 20.65 | 4750 | 1.3394 | 0.4684 | 0.4694 |
73
- | 0.9005 | 21.74 | 5000 | 1.3525 | 0.4614 | 0.4616 |
74
- | 0.9005 | 22.83 | 5250 | 1.3792 | 0.4506 | 0.4429 |
75
- | 0.8972 | 23.91 | 5500 | 1.3778 | 0.4545 | 0.4525 |
76
- | 0.8972 | 25.0 | 5750 | 1.3631 | 0.4599 | 0.4566 |
77
- | 0.8951 | 26.09 | 6000 | 1.3585 | 0.4630 | 0.4607 |
78
- | 0.8951 | 27.17 | 6250 | 1.3579 | 0.4583 | 0.4556 |
79
- | 0.8924 | 28.26 | 6500 | 1.3543 | 0.4645 | 0.4634 |
80
- | 0.8924 | 29.35 | 6750 | 1.3667 | 0.4498 | 0.4460 |
81
 
82
 
83
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [haryoaw/scenario-MDBT-TCR_data-cl-cardiff_cl_only](https://huggingface.co/haryoaw/scenario-MDBT-TCR_data-cl-cardiff_cl_only) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 1.3677
22
+ - Accuracy: 0.4468
23
+ - F1: 0.4461
24
 
25
  ## Model description
26
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
53
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
54
+ | No log | 1.09 | 250 | 1.2834 | 0.4591 | 0.4503 |
55
+ | 1.2011 | 2.17 | 500 | 1.3504 | 0.4483 | 0.4403 |
56
+ | 1.2011 | 3.26 | 750 | 1.3205 | 0.4468 | 0.4415 |
57
+ | 1.0583 | 4.35 | 1000 | 1.3622 | 0.4406 | 0.4355 |
58
+ | 1.0583 | 5.43 | 1250 | 1.3754 | 0.4375 | 0.4333 |
59
+ | 0.9917 | 6.52 | 1500 | 1.3816 | 0.4398 | 0.4380 |
60
+ | 0.9917 | 7.61 | 1750 | 1.3783 | 0.4475 | 0.4434 |
61
+ | 0.9569 | 8.7 | 2000 | 1.3621 | 0.4529 | 0.4497 |
62
+ | 0.9569 | 9.78 | 2250 | 1.3658 | 0.4460 | 0.4450 |
63
+ | 0.939 | 10.87 | 2500 | 1.3567 | 0.4630 | 0.4616 |
64
+ | 0.939 | 11.96 | 2750 | 1.3631 | 0.4676 | 0.4675 |
65
+ | 0.9262 | 13.04 | 3000 | 1.3922 | 0.4421 | 0.4304 |
66
+ | 0.9262 | 14.13 | 3250 | 1.3950 | 0.4275 | 0.4135 |
67
+ | 0.9176 | 15.22 | 3500 | 1.3653 | 0.4660 | 0.4658 |
68
+ | 0.9176 | 16.3 | 3750 | 1.3690 | 0.4498 | 0.4449 |
69
+ | 0.9114 | 17.39 | 4000 | 1.3964 | 0.4398 | 0.4336 |
70
+ | 0.9114 | 18.48 | 4250 | 1.3738 | 0.4614 | 0.4600 |
71
+ | 0.9058 | 19.57 | 4500 | 1.3574 | 0.4730 | 0.4728 |
72
+ | 0.9058 | 20.65 | 4750 | 1.3716 | 0.4606 | 0.4577 |
73
+ | 0.9018 | 21.74 | 5000 | 1.3684 | 0.4583 | 0.4578 |
74
+ | 0.9018 | 22.83 | 5250 | 1.3791 | 0.4568 | 0.4534 |
75
+ | 0.8988 | 23.91 | 5500 | 1.3708 | 0.4560 | 0.4549 |
76
+ | 0.8988 | 25.0 | 5750 | 1.3438 | 0.4730 | 0.4728 |
77
+ | 0.8963 | 26.09 | 6000 | 1.3544 | 0.4622 | 0.4615 |
78
+ | 0.8963 | 27.17 | 6250 | 1.3508 | 0.4622 | 0.4590 |
79
+ | 0.8937 | 28.26 | 6500 | 1.3531 | 0.4637 | 0.4633 |
80
+ | 0.8937 | 29.35 | 6750 | 1.3677 | 0.4468 | 0.4461 |
81
 
82
 
83
  ### Framework versions
eval_results_cardiff.json CHANGED
@@ -1 +1 @@
1
- {"arabic": {"f1": 0.5477163921550751, "accuracy": 0.5517241379310345, "confusion_matrix": [[124, 88, 78], [53, 162, 75], [27, 69, 194]]}, "english": {"f1": 0.6083231700895375, "accuracy": 0.6206896551724138, "confusion_matrix": [[229, 31, 30], [100, 113, 77], [49, 43, 198]]}, "french": {"f1": 0.44551446288496427, "accuracy": 0.4666666666666667, "confusion_matrix": [[98, 155, 37], [34, 227, 29], [34, 175, 81]]}, "german": {"f1": 0.6944740777398785, "accuracy": 0.6954022988505747, "confusion_matrix": [[212, 35, 43], [60, 177, 53], [50, 24, 216]]}, "hindi": {"f1": 0.467304903508853, "accuracy": 0.4724137931034483, "confusion_matrix": [[142, 47, 101], [86, 100, 104], [72, 49, 169]]}, "italian": {"f1": 0.627327314615502, "accuracy": 0.6275862068965518, "confusion_matrix": [[155, 44, 91], [28, 183, 79], [34, 48, 208]]}, "portuguese": {"f1": 0.4971975864122023, "accuracy": 0.5091954022988506, "confusion_matrix": [[141, 52, 97], [84, 95, 111], [36, 47, 207]]}, "spanish": {"f1": 0.5224108529074224, "accuracy": 0.5367816091954023, "confusion_matrix": [[177, 52, 61], [100, 89, 101], [59, 30, 201]]}, "all": {"f1": 0.5588937027636228, "accuracy": 0.5600574712643678, "confusion_matrix": [[1297, 514, 509], [549, 1141, 630], [361, 499, 1460]]}}
 
1
+ {"arabic": {"f1": 0.5653548543002577, "accuracy": 0.5678160919540229, "confusion_matrix": [[144, 78, 68], [66, 152, 72], [32, 60, 198]]}, "english": {"f1": 0.5933965749508691, "accuracy": 0.6149425287356322, "confusion_matrix": [[260, 14, 16], [142, 93, 55], [68, 40, 182]]}, "french": {"f1": 0.4488432183733592, "accuracy": 0.47011494252873565, "confusion_matrix": [[113, 137, 40], [33, 223, 34], [45, 172, 73]]}, "german": {"f1": 0.6631181222639263, "accuracy": 0.6689655172413793, "confusion_matrix": [[239, 15, 36], [95, 139, 56], [70, 16, 204]]}, "hindi": {"f1": 0.45893771359544494, "accuracy": 0.46436781609195404, "confusion_matrix": [[154, 59, 77], [100, 95, 95], [79, 56, 155]]}, "italian": {"f1": 0.6132363021127065, "accuracy": 0.6137931034482759, "confusion_matrix": [[156, 58, 76], [31, 190, 69], [48, 54, 188]]}, "portuguese": {"f1": 0.536626977768274, "accuracy": 0.5413793103448276, "confusion_matrix": [[170, 60, 60], [97, 116, 77], [52, 53, 185]]}, "spanish": {"f1": 0.5421045782076221, "accuracy": 0.5551724137931034, "confusion_matrix": [[202, 38, 50], [113, 95, 82], [75, 29, 186]]}, "all": {"f1": 0.5651175684949207, "accuracy": 0.5668103448275862, "confusion_matrix": [[1462, 453, 405], [689, 1108, 523], [472, 473, 1375]]}}
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:daa9b72f66c02002a2d3d394fab95a53d1f691e1d5fd2f9594144cee6c4ffeb1
3
  size 946740394
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:622fdea6345639c6ae7f00bba08ab68c54f007ed4803b96b52a1367fb64260b7
3
  size 946740394
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5084800e00e908b7180ad9be2583dc6cf81d98f051601c2340f4006c7f7be75e
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06b0f09e9442f3751ec6c3106fa1d5e748cbdac82462eed9b6641799bb7d018c
3
  size 4600