Hugging Face's logo

haryoaw
/
scenario-KD-SCR-PO-CDF-EN-FROM-EN-D2_data-en-cardiff_eng_only66

Transformers
PyTorch
Safetensors
deberta-v2
Generated from Trainer
Inference Endpoints
Model card Files Community
haryoaw commited on
Commit
c3291e6
•
1 Parent(s): 21ea7e0

Initial Commit

Browse files
Files changed (5) hide show
  1. README.md +28 -25
  2. config.json +1 -1
  3. eval_results_cardiff.json +1 -1
  4. model.safetensors +3 -0
  5. training_args.bin +2 -2
README.md CHANGED
@@ -1,4 +1,5 @@
1
  ---
 
2
  license: mit
3
  base_model: haryoaw/scenario-MDBT-TCR_data-en-cardiff_eng_only
4
  tags:
@@ -18,9 +19,9 @@ 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-en-cardiff_eng_only](https://huggingface.co/haryoaw/scenario-MDBT-TCR_data-en-cardiff_eng_only) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: nan
22
- - Accuracy: 0.3333
23
- - F1: 0.1667
24
 
25
  ## Model description
26
 
@@ -40,39 +41,41 @@ More information needed
40
 
41
  The following hyperparameters were used during training:
42
  - learning_rate: 5e-05
43
- - train_batch_size: 32
44
  - eval_batch_size: 32
45
  - seed: 66
 
 
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - num_epochs: 30
49
 
50
  ### Training results
51
 
52
- | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
53
- |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
54
- | No log | 1.72 | 100 | nan | 0.3333 | 0.1667 |
55
- | No log | 3.45 | 200 | nan | 0.3333 | 0.1667 |
56
- | No log | 5.17 | 300 | nan | 0.3333 | 0.1667 |
57
- | No log | 6.9 | 400 | nan | 0.3333 | 0.1667 |
58
- | 1.0869 | 8.62 | 500 | nan | 0.3333 | 0.1667 |
59
- | 1.0869 | 10.34 | 600 | nan | 0.3333 | 0.1667 |
60
- | 1.0869 | 12.07 | 700 | nan | 0.3333 | 0.1667 |
61
- | 1.0869 | 13.79 | 800 | nan | 0.3333 | 0.1667 |
62
- | 1.0869 | 15.52 | 900 | nan | 0.3333 | 0.1667 |
63
- | 0.0 | 17.24 | 1000 | nan | 0.3333 | 0.1667 |
64
- | 0.0 | 18.97 | 1100 | nan | 0.3333 | 0.1667 |
65
- | 0.0 | 20.69 | 1200 | nan | 0.3333 | 0.1667 |
66
- | 0.0 | 22.41 | 1300 | nan | 0.3333 | 0.1667 |
67
- | 0.0 | 24.14 | 1400 | nan | 0.3333 | 0.1667 |
68
- | 0.0 | 25.86 | 1500 | nan | 0.3333 | 0.1667 |
69
- | 0.0 | 27.59 | 1600 | nan | 0.3333 | 0.1667 |
70
- | 0.0 | 29.31 | 1700 | nan | 0.3333 | 0.1667 |
71
 
72
 
73
  ### Framework versions
74
 
75
- - Transformers 4.33.3
76
  - Pytorch 2.1.1+cu121
77
  - Datasets 2.14.5
78
- - Tokenizers 0.13.3
 
1
  ---
2
+ library_name: transformers
3
  license: mit
4
  base_model: haryoaw/scenario-MDBT-TCR_data-en-cardiff_eng_only
5
  tags:
 
19
 
20
  This model is a fine-tuned version of [haryoaw/scenario-MDBT-TCR_data-en-cardiff_eng_only](https://huggingface.co/haryoaw/scenario-MDBT-TCR_data-en-cardiff_eng_only) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 533.0406
23
+ - Accuracy: 0.3444
24
+ - F1: 0.2711
25
 
26
  ## Model description
27
 
 
41
 
42
  The following hyperparameters were used during training:
43
  - learning_rate: 5e-05
44
+ - train_batch_size: 8
45
  - eval_batch_size: 32
46
  - seed: 66
47
+ - gradient_accumulation_steps: 4
48
+ - total_train_batch_size: 32
49
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
  - lr_scheduler_type: linear
51
  - num_epochs: 30
52
 
53
  ### Training results
54
 
55
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
56
+ |:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|
57
+ | No log | 1.7391 | 100 | 631.4247 | 0.3302 | 0.2694 |
58
+ | No log | 3.4783 | 200 | 605.5723 | 0.3413 | 0.2651 |
59
+ | No log | 5.2174 | 300 | 589.1194 | 0.3369 | 0.2521 |
60
+ | No log | 6.9565 | 400 | 580.2668 | 0.3501 | 0.2633 |
61
+ | 574.1509 | 8.6957 | 500 | 571.8079 | 0.3254 | 0.2189 |
62
+ | 574.1509 | 10.4348 | 600 | 564.8586 | 0.3360 | 0.2072 |
63
+ | 574.1509 | 12.1739 | 700 | 559.2232 | 0.3417 | 0.2567 |
64
+ | 574.1509 | 13.9130 | 800 | 552.7770 | 0.3391 | 0.2289 |
65
+ | 574.1509 | 15.6522 | 900 | 549.6864 | 0.3333 | 0.2295 |
66
+ | 468.9151 | 17.3913 | 1000 | 545.1831 | 0.3338 | 0.2429 |
67
+ | 468.9151 | 19.1304 | 1100 | 541.3506 | 0.3466 | 0.2794 |
68
+ | 468.9151 | 20.8696 | 1200 | 538.9130 | 0.3355 | 0.2612 |
69
+ | 468.9151 | 22.6087 | 1300 | 537.2876 | 0.3470 | 0.2807 |
70
+ | 468.9151 | 24.3478 | 1400 | 535.7286 | 0.3426 | 0.2346 |
71
+ | 433.9469 | 26.0870 | 1500 | 533.7326 | 0.3492 | 0.2730 |
72
+ | 433.9469 | 27.8261 | 1600 | 533.2730 | 0.3338 | 0.2553 |
73
+ | 433.9469 | 29.5652 | 1700 | 533.0406 | 0.3444 | 0.2711 |
74
 
75
 
76
  ### Framework versions
77
 
78
+ - Transformers 4.44.2
79
  - Pytorch 2.1.1+cu121
80
  - Datasets 2.14.5
81
+ - Tokenizers 0.19.1
config.json CHANGED
@@ -39,7 +39,7 @@
39
  "relative_attention": true,
40
  "share_att_key": true,
41
  "torch_dtype": "float32",
42
- "transformers_version": "4.33.3",
43
  "type_vocab_size": 0,
44
  "vocab_size": 251000
45
  }
 
39
  "relative_attention": true,
40
  "share_att_key": true,
41
  "torch_dtype": "float32",
42
+ "transformers_version": "4.44.2",
43
  "type_vocab_size": 0,
44
  "vocab_size": 251000
45
  }
eval_results_cardiff.json CHANGED
@@ -1 +1 @@
1
- {"arabic": {"f1": 0.16666666666666666, "accuracy": 0.3333333333333333, "confusion_matrix": [[290, 0, 0], [290, 0, 0], [290, 0, 0]]}, "english": {"f1": 0.16666666666666666, "accuracy": 0.3333333333333333, "confusion_matrix": [[290, 0, 0], [290, 0, 0], [290, 0, 0]]}, "french": {"f1": 0.16666666666666666, "accuracy": 0.3333333333333333, "confusion_matrix": [[290, 0, 0], [290, 0, 0], [290, 0, 0]]}, "german": {"f1": 0.16666666666666666, "accuracy": 0.3333333333333333, "confusion_matrix": [[290, 0, 0], [290, 0, 0], [290, 0, 0]]}, "hindi": {"f1": 0.16666666666666666, "accuracy": 0.3333333333333333, "confusion_matrix": [[290, 0, 0], [290, 0, 0], [290, 0, 0]]}, "italian": {"f1": 0.16666666666666666, "accuracy": 0.3333333333333333, "confusion_matrix": [[290, 0, 0], [290, 0, 0], [290, 0, 0]]}, "portuguese": {"f1": 0.16666666666666666, "accuracy": 0.3333333333333333, "confusion_matrix": [[290, 0, 0], [290, 0, 0], [290, 0, 0]]}, "spanish": {"f1": 0.16666666666666666, "accuracy": 0.3333333333333333, "confusion_matrix": [[290, 0, 0], [290, 0, 0], [290, 0, 0]]}, "all": {"f1": 0.16666666666666666, "accuracy": 0.3333333333333333, "confusion_matrix": [[2320, 0, 0], [2320, 0, 0], [2320, 0, 0]]}}
 
1
+ {"arabic": {"f1": 0.28620417681149485, "accuracy": 0.35747126436781607, "confusion_matrix": [[163, 0, 127], [129, 0, 161], [141, 1, 148]]}, "english": {"f1": 0.3215552226394243, "accuracy": 0.4011494252873563, "confusion_matrix": [[193, 0, 97], [145, 1, 144], [135, 0, 155]]}, "french": {"f1": 0.27630863809500567, "accuracy": 0.34022988505747126, "confusion_matrix": [[163, 0, 127], [125, 3, 162], [160, 0, 130]]}, "german": {"f1": 0.2871860588026614, "accuracy": 0.35747126436781607, "confusion_matrix": [[116, 1, 173], [118, 3, 169], [94, 4, 192]]}, "hindi": {"f1": 0.2716721663906872, "accuracy": 0.33793103448275863, "confusion_matrix": [[108, 1, 181], [82, 3, 205], [106, 1, 183]]}, "italian": {"f1": 0.303020455281475, "accuracy": 0.37701149425287356, "confusion_matrix": [[179, 1, 110], [134, 1, 155], [141, 1, 148]]}, "portuguese": {"f1": 0.30380648608488964, "accuracy": 0.3758620689655172, "confusion_matrix": [[136, 2, 152], [134, 3, 153], [102, 0, 188]]}, "spanish": {"f1": 0.27510022929420136, "accuracy": 0.335632183908046, "confusion_matrix": [[132, 4, 154], [140, 4, 146], [132, 2, 156]]}, "all": {"f1": 0.2876940961781527, "accuracy": 0.35474137931034483, "confusion_matrix": [[1180, 13, 1127], [989, 17, 1314], [1038, 10, 1272]]}}
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71d801bce7c967ed8303bd0d55fcd4092f8962b218044c932d5e9ee52439b705
3
+ size 945150428
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db581356d4021de2173ba62d89b5cc66f7a929d85f129154a451c19a24f84387
3
- size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20d7cb13f7bf6b9f0c9c03f7ab121bbe26ed18e8ec2e52bfb49b787ad3708f4a
3
+ size 5304