Hugging Face's logo

haryoaw
/
scenario-KD-PO-CDF-CL-D2_data-cl-cardiff_cl_only66

PyTorch
deberta-v2
Generated from Trainer
Model card Files Community
haryoaw commited on
Commit
e7d90de
•
1 Parent(s): 5588bee

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: 31.7416
22
- - Accuracy: 0.4560
23
- - F1: 0.4541
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 | 19.9794 | 0.4306 | 0.4241 |
55
- | 22.4123 | 2.17 | 500 | 21.3481 | 0.4336 | 0.4260 |
56
- | 22.4123 | 3.26 | 750 | 24.4238 | 0.4560 | 0.4561 |
57
- | 12.6859 | 4.35 | 1000 | 25.0953 | 0.4352 | 0.4316 |
58
- | 12.6859 | 5.43 | 1250 | 27.9114 | 0.4360 | 0.4335 |
59
- | 6.8096 | 6.52 | 1500 | 29.7395 | 0.4321 | 0.4237 |
60
- | 6.8096 | 7.61 | 1750 | 29.6224 | 0.4360 | 0.4305 |
61
- | 4.5159 | 8.7 | 2000 | 31.3276 | 0.4390 | 0.4333 |
62
- | 4.5159 | 9.78 | 2250 | 32.6593 | 0.4398 | 0.4354 |
63
- | 3.2964 | 10.87 | 2500 | 33.0071 | 0.4352 | 0.4235 |
64
- | 3.2964 | 11.96 | 2750 | 34.0500 | 0.4352 | 0.4265 |
65
- | 2.4206 | 13.04 | 3000 | 33.9132 | 0.4344 | 0.4289 |
66
- | 2.4206 | 14.13 | 3250 | 31.9401 | 0.4576 | 0.4554 |
67
- | 1.78 | 15.22 | 3500 | 33.3465 | 0.4491 | 0.4410 |
68
- | 1.78 | 16.3 | 3750 | 33.5318 | 0.4259 | 0.4209 |
69
- | 1.3706 | 17.39 | 4000 | 34.5140 | 0.4583 | 0.4564 |
70
- | 1.3706 | 18.48 | 4250 | 32.4824 | 0.4483 | 0.4475 |
71
- | 1.1506 | 19.57 | 4500 | 33.5403 | 0.4460 | 0.4435 |
72
- | 1.1506 | 20.65 | 4750 | 33.4105 | 0.4352 | 0.4321 |
73
- | 0.9541 | 21.74 | 5000 | 32.5699 | 0.4468 | 0.4467 |
74
- | 0.9541 | 22.83 | 5250 | 32.0965 | 0.4390 | 0.4375 |
75
- | 0.7436 | 23.91 | 5500 | 33.0832 | 0.4290 | 0.4200 |
76
- | 0.7436 | 25.0 | 5750 | 31.5703 | 0.4367 | 0.4327 |
77
- | 0.6718 | 26.09 | 6000 | 33.3243 | 0.4313 | 0.4274 |
78
- | 0.6718 | 27.17 | 6250 | 32.8775 | 0.4375 | 0.4328 |
79
- | 0.5245 | 28.26 | 6500 | 32.0762 | 0.4437 | 0.4418 |
80
- | 0.5245 | 29.35 | 6750 | 31.7416 | 0.4560 | 0.4541 |
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: 31.9406
22
+ - Accuracy: 0.4514
23
+ - F1: 0.4492
24
 
25
  ## Model description
26
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
53
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
54
+ | No log | 1.09 | 250 | 20.8325 | 0.4190 | 0.4115 |
55
+ | 23.5832 | 2.17 | 500 | 21.6265 | 0.4383 | 0.4264 |
56
+ | 23.5832 | 3.26 | 750 | 24.4598 | 0.4390 | 0.4314 |
57
+ | 13.3807 | 4.35 | 1000 | 25.7243 | 0.4306 | 0.4204 |
58
+ | 13.3807 | 5.43 | 1250 | 27.8222 | 0.4421 | 0.4357 |
59
+ | 7.1567 | 6.52 | 1500 | 30.2248 | 0.4290 | 0.4199 |
60
+ | 7.1567 | 7.61 | 1750 | 32.3466 | 0.4352 | 0.4337 |
61
+ | 4.6016 | 8.7 | 2000 | 31.6725 | 0.4460 | 0.4463 |
62
+ | 4.6016 | 9.78 | 2250 | 33.4776 | 0.4506 | 0.4513 |
63
+ | 3.1024 | 10.87 | 2500 | 31.5436 | 0.4606 | 0.4599 |
64
+ | 3.1024 | 11.96 | 2750 | 35.7505 | 0.4452 | 0.4382 |
65
+ | 2.4119 | 13.04 | 3000 | 34.6801 | 0.4244 | 0.4166 |
66
+ | 2.4119 | 14.13 | 3250 | 33.5802 | 0.4568 | 0.4556 |
67
+ | 1.9999 | 15.22 | 3500 | 33.1767 | 0.4498 | 0.4447 |
68
+ | 1.9999 | 16.3 | 3750 | 35.5967 | 0.4174 | 0.3975 |
69
+ | 1.4653 | 17.39 | 4000 | 33.7180 | 0.4537 | 0.4452 |
70
+ | 1.4653 | 18.48 | 4250 | 32.4131 | 0.4468 | 0.4408 |
71
+ | 1.2591 | 19.57 | 4500 | 33.4033 | 0.4352 | 0.4323 |
72
+ | 1.2591 | 20.65 | 4750 | 34.4563 | 0.4290 | 0.4207 |
73
+ | 1.0464 | 21.74 | 5000 | 33.1647 | 0.4514 | 0.4498 |
74
+ | 1.0464 | 22.83 | 5250 | 32.5475 | 0.4414 | 0.4385 |
75
+ | 0.7931 | 23.91 | 5500 | 33.5871 | 0.4498 | 0.4466 |
76
+ | 0.7931 | 25.0 | 5750 | 33.1142 | 0.4452 | 0.4455 |
77
+ | 0.7164 | 26.09 | 6000 | 33.0320 | 0.4321 | 0.4300 |
78
+ | 0.7164 | 27.17 | 6250 | 34.2533 | 0.4306 | 0.4257 |
79
+ | 0.6057 | 28.26 | 6500 | 32.7754 | 0.4483 | 0.4464 |
80
+ | 0.6057 | 29.35 | 6750 | 31.9406 | 0.4514 | 0.4492 |
81
 
82
 
83
  ### Framework versions
eval_results_cardiff.json CHANGED
@@ -1 +1 @@
1
- {"arabic": {"f1": 0.5487636664855445, "accuracy": 0.5528735632183908, "confusion_matrix": [[138, 72, 80], [73, 141, 76], [26, 62, 202]]}, "english": {"f1": 0.6081898842970522, "accuracy": 0.6195402298850575, "confusion_matrix": [[216, 28, 46], [109, 114, 67], [39, 42, 209]]}, "french": {"f1": 0.4506655910432762, "accuracy": 0.4632183908045977, "confusion_matrix": [[95, 132, 63], [23, 208, 59], [27, 163, 100]]}, "german": {"f1": 0.6451204514921933, "accuracy": 0.6494252873563219, "confusion_matrix": [[160, 35, 95], [49, 163, 78], [27, 21, 242]]}, "hindi": {"f1": 0.42293421121909186, "accuracy": 0.4413793103448276, "confusion_matrix": [[97, 41, 152], [61, 80, 149], [39, 44, 207]]}, "italian": {"f1": 0.6123113412900704, "accuracy": 0.6137931034482759, "confusion_matrix": [[154, 40, 96], [35, 161, 94], [31, 40, 219]]}, "portuguese": {"f1": 0.48163998236246214, "accuracy": 0.4942528735632184, "confusion_matrix": [[103, 71, 116], [61, 116, 113], [27, 52, 211]]}, "spanish": {"f1": 0.5250823061394478, "accuracy": 0.539080459770115, "confusion_matrix": [[170, 61, 59], [83, 90, 117], [43, 38, 209]]}, "all": {"f1": 0.5355126575777598, "accuracy": 0.5395114942528736, "confusion_matrix": [[1098, 487, 735], [476, 1068, 776], [256, 475, 1589]]}}
 
1
+ {"arabic": {"f1": 0.5289360001049693, "accuracy": 0.5298850574712644, "confusion_matrix": [[127, 103, 60], [65, 179, 46], [34, 101, 155]]}, "english": {"f1": 0.6107032001951423, "accuracy": 0.6172413793103448, "confusion_matrix": [[227, 33, 30], [107, 131, 52], [56, 55, 179]]}, "french": {"f1": 0.41749490426436847, "accuracy": 0.4482758620689655, "confusion_matrix": [[95, 172, 23], [26, 236, 28], [26, 205, 59]]}, "german": {"f1": 0.6655029446000299, "accuracy": 0.6655172413793103, "confusion_matrix": [[207, 43, 40], [66, 183, 41], [59, 42, 189]]}, "hindi": {"f1": 0.47717299507262423, "accuracy": 0.4781609195402299, "confusion_matrix": [[162, 71, 57], [112, 122, 56], [84, 74, 132]]}, "italian": {"f1": 0.5822331426687083, "accuracy": 0.5885057471264368, "confusion_matrix": [[122, 82, 86], [21, 209, 60], [32, 77, 181]]}, "portuguese": {"f1": 0.5010584468574327, "accuracy": 0.5022988505747127, "confusion_matrix": [[124, 95, 71], [82, 143, 65], [45, 75, 170]]}, "spanish": {"f1": 0.5602746750339045, "accuracy": 0.5666666666666667, "confusion_matrix": [[191, 57, 42], [90, 115, 85], [51, 52, 187]]}, "all": {"f1": 0.5383966720645431, "accuracy": 0.5376436781609195, "confusion_matrix": [[1210, 684, 426], [562, 1295, 463], [392, 691, 1237]]}}
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a7ed82b8d8d76745ffd06030f49daa039c711871307eadbf35536cfa984c148f
3
  size 946740394
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cf570142d37c35e6ab0c5ab9b8ede1b271c55c163feb2d0349dc2b0b4f40883
3
  size 946740394
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c0ca527e3c526fe996bf2124c9f19a71533761b9afcfa76fc47f429569334397
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e942e1c4c30630a9727629dd22be86bec2fc066ac0bb72587f2e9511074d6d0
3
  size 4600