Hugging Face's logo

haryoaw
/
scenario-KD-PR-MSV-D2_data-cl-cardiff_cl_only44

PyTorch
deberta-v2
Generated from Trainer
Model card Files Community
haryoaw commited on
Commit
12ee9e3
•
1 Parent(s): 8ef4f41

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: 1.3609
22
- - Accuracy: 0.4452
23
- - F1: 0.4416
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 | 1.3276 | 0.4375 | 0.4182 |
55
- | 1.2002 | 2.17 | 500 | 1.3064 | 0.4491 | 0.4447 |
56
- | 1.2002 | 3.26 | 750 | 1.3438 | 0.4475 | 0.4448 |
57
- | 1.0539 | 4.35 | 1000 | 1.3894 | 0.4267 | 0.4160 |
58
- | 1.0539 | 5.43 | 1250 | 1.4000 | 0.4344 | 0.4264 |
59
- | 0.9882 | 6.52 | 1500 | 1.3466 | 0.4583 | 0.4562 |
60
- | 0.9882 | 7.61 | 1750 | 1.3578 | 0.4444 | 0.4408 |
61
- | 0.9564 | 8.7 | 2000 | 1.4067 | 0.4568 | 0.4523 |
62
- | 0.9564 | 9.78 | 2250 | 1.3719 | 0.4437 | 0.4402 |
63
- | 0.9368 | 10.87 | 2500 | 1.3744 | 0.4390 | 0.4379 |
64
- | 0.9368 | 11.96 | 2750 | 1.3943 | 0.4282 | 0.4142 |
65
- | 0.9254 | 13.04 | 3000 | 1.3961 | 0.4398 | 0.4268 |
66
- | 0.9254 | 14.13 | 3250 | 1.3819 | 0.4390 | 0.4286 |
67
- | 0.918 | 15.22 | 3500 | 1.3727 | 0.4444 | 0.4354 |
68
- | 0.918 | 16.3 | 3750 | 1.3785 | 0.4576 | 0.4518 |
69
- | 0.9099 | 17.39 | 4000 | 1.3963 | 0.4336 | 0.4140 |
70
- | 0.9099 | 18.48 | 4250 | 1.3821 | 0.4437 | 0.4395 |
71
- | 0.9064 | 19.57 | 4500 | 1.3580 | 0.4583 | 0.4556 |
72
- | 0.9064 | 20.65 | 4750 | 1.3634 | 0.4630 | 0.4640 |
73
- | 0.9022 | 21.74 | 5000 | 1.3714 | 0.4522 | 0.4457 |
74
- | 0.9022 | 22.83 | 5250 | 1.3784 | 0.4398 | 0.4284 |
75
- | 0.898 | 23.91 | 5500 | 1.3601 | 0.4552 | 0.4528 |
76
- | 0.898 | 25.0 | 5750 | 1.3740 | 0.4545 | 0.4535 |
77
- | 0.8952 | 26.09 | 6000 | 1.3574 | 0.4576 | 0.4568 |
78
- | 0.8952 | 27.17 | 6250 | 1.3536 | 0.4691 | 0.4682 |
79
- | 0.8933 | 28.26 | 6500 | 1.3632 | 0.4514 | 0.4492 |
80
- | 0.8933 | 29.35 | 6750 | 1.3609 | 0.4452 | 0.4416 |
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: 1.3590
22
+ - Accuracy: 0.4630
23
+ - F1: 0.4628
24
 
25
  ## Model description
26
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
53
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
54
+ | No log | 1.09 | 250 | 1.3195 | 0.4390 | 0.4186 |
55
+ | 1.1991 | 2.17 | 500 | 1.2866 | 0.4537 | 0.4542 |
56
+ | 1.1991 | 3.26 | 750 | 1.3622 | 0.4383 | 0.4293 |
57
+ | 1.0569 | 4.35 | 1000 | 1.3662 | 0.4252 | 0.4155 |
58
+ | 1.0569 | 5.43 | 1250 | 1.3920 | 0.4275 | 0.4229 |
59
+ | 0.9882 | 6.52 | 1500 | 1.3607 | 0.4560 | 0.4549 |
60
+ | 0.9882 | 7.61 | 1750 | 1.3742 | 0.4468 | 0.4429 |
61
+ | 0.9542 | 8.7 | 2000 | 1.4048 | 0.4329 | 0.4284 |
62
+ | 0.9542 | 9.78 | 2250 | 1.3944 | 0.4344 | 0.4227 |
63
+ | 0.9374 | 10.87 | 2500 | 1.3725 | 0.4414 | 0.4417 |
64
+ | 0.9374 | 11.96 | 2750 | 1.3790 | 0.4491 | 0.4464 |
65
+ | 0.9261 | 13.04 | 3000 | 1.3687 | 0.4552 | 0.4510 |
66
+ | 0.9261 | 14.13 | 3250 | 1.3778 | 0.4475 | 0.4438 |
67
+ | 0.9164 | 15.22 | 3500 | 1.3888 | 0.4583 | 0.4554 |
68
+ | 0.9164 | 16.3 | 3750 | 1.3785 | 0.4498 | 0.4415 |
69
+ | 0.9101 | 17.39 | 4000 | 1.3778 | 0.4568 | 0.4530 |
70
+ | 0.9101 | 18.48 | 4250 | 1.4075 | 0.4398 | 0.4261 |
71
+ | 0.9053 | 19.57 | 4500 | 1.3610 | 0.4576 | 0.4575 |
72
+ | 0.9053 | 20.65 | 4750 | 1.3679 | 0.4568 | 0.4570 |
73
+ | 0.9026 | 21.74 | 5000 | 1.3653 | 0.4614 | 0.4617 |
74
+ | 0.9026 | 22.83 | 5250 | 1.3701 | 0.4468 | 0.4465 |
75
+ | 0.8977 | 23.91 | 5500 | 1.3753 | 0.4498 | 0.4475 |
76
+ | 0.8977 | 25.0 | 5750 | 1.3781 | 0.4545 | 0.4532 |
77
+ | 0.8953 | 26.09 | 6000 | 1.3811 | 0.4468 | 0.4455 |
78
+ | 0.8953 | 27.17 | 6250 | 1.3609 | 0.4545 | 0.4527 |
79
+ | 0.893 | 28.26 | 6500 | 1.3696 | 0.4452 | 0.4433 |
80
+ | 0.893 | 29.35 | 6750 | 1.3590 | 0.4630 | 0.4628 |
81
 
82
 
83
  ### Framework versions
eval_results_cardiff.json CHANGED
@@ -1 +1 @@
1
- {"arabic": {"f1": 0.5590435294578455, "accuracy": 0.5597701149425287, "confusion_matrix": [[132, 106, 52], [57, 191, 42], [27, 99, 164]]}, "english": {"f1": 0.6319463790734942, "accuracy": 0.6379310344827587, "confusion_matrix": [[231, 38, 21], [104, 135, 51], [44, 57, 189]]}, "french": {"f1": 0.4035409035409035, "accuracy": 0.4436781609195402, "confusion_matrix": [[83, 182, 25], [22, 248, 20], [25, 210, 55]]}, "german": {"f1": 0.7011914698462777, "accuracy": 0.7011494252873564, "confusion_matrix": [[200, 47, 43], [49, 204, 37], [42, 42, 206]]}, "hindi": {"f1": 0.45461040370758016, "accuracy": 0.45632183908045976, "confusion_matrix": [[121, 67, 102], [71, 119, 100], [60, 73, 157]]}, "italian": {"f1": 0.6091612569541606, "accuracy": 0.6137931034482759, "confusion_matrix": [[133, 71, 86], [26, 205, 59], [29, 65, 196]]}, "portuguese": {"f1": 0.5548098277927002, "accuracy": 0.5540229885057472, "confusion_matrix": [[140, 100, 50], [64, 174, 52], [32, 90, 168]]}, "spanish": {"f1": 0.5660568988932057, "accuracy": 0.5689655172413793, "confusion_matrix": [[163, 76, 51], [70, 135, 85], [45, 48, 197]]}, "all": {"f1": 0.5742140395648633, "accuracy": 0.5738505747126437, "confusion_matrix": [[1221, 668, 431], [451, 1440, 429], [305, 682, 1333]]}}
 
1
+ {"arabic": {"f1": 0.5709998137901682, "accuracy": 0.5724137931034483, "confusion_matrix": [[135, 96, 59], [56, 177, 57], [27, 77, 186]]}, "english": {"f1": 0.610460926462823, "accuracy": 0.6218390804597701, "confusion_matrix": [[251, 25, 14], [120, 122, 48], [56, 66, 168]]}, "french": {"f1": 0.4197425314918571, "accuracy": 0.45977011494252873, "confusion_matrix": [[114, 161, 15], [31, 242, 17], [39, 207, 44]]}, "german": {"f1": 0.6944838199618814, "accuracy": 0.6942528735632184, "confusion_matrix": [[207, 40, 43], [59, 194, 37], [51, 36, 203]]}, "hindi": {"f1": 0.4450759378527575, "accuracy": 0.4471264367816092, "confusion_matrix": [[113, 85, 92], [71, 121, 98], [60, 75, 155]]}, "italian": {"f1": 0.6027079746733218, "accuracy": 0.6068965517241379, "confusion_matrix": [[134, 85, 71], [23, 210, 57], [32, 74, 184]]}, "portuguese": {"f1": 0.5586491594110915, "accuracy": 0.5586206896551724, "confusion_matrix": [[146, 84, 60], [73, 162, 55], [35, 77, 178]]}, "spanish": {"f1": 0.5557949250279285, "accuracy": 0.5609195402298851, "confusion_matrix": [[192, 63, 35], [90, 118, 82], [60, 52, 178]]}, "all": {"f1": 0.5696398588780106, "accuracy": 0.5689655172413793, "confusion_matrix": [[1284, 630, 406], [500, 1379, 441], [356, 667, 1297]]}}
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dba3961c8597a1fbcb35c70e4e9b9e61bdc6aee44e9ac9f995cccc440663feca
3
  size 946740394
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ba7531e0d7a0a4c757e12e4bba20d06c35623db19c5a7b4376ae7ccd93542da
3
  size 946740394
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a4b9e046152e20cc01012557876e9533d5792bb87ab37ceae23cafb0332874a8
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98b91b1de3bf14d1618d65c9d7bbcd9eae19a51be2c51c20732e21e23d424bb4
3
  size 4600