Initial Commit
Browse files- README.md +78 -0
- config.json +45 -0
- eval_results_cardiff.json +1 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: haryoaw/scenario-MDBT-TCR_data-cl-cardiff_cl_only
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
- f1
|
9 |
+
model-index:
|
10 |
+
- name: scenario-KD-PR-CDF-EN-FROM-CL-D2_data-en-cardiff_eng_only44
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# scenario-KD-PR-CDF-EN-FROM-CL-D2_data-en-cardiff_eng_only44
|
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: 1.3448
|
22 |
+
- Accuracy: 0.4780
|
23 |
+
- F1: 0.4765
|
24 |
+
|
25 |
+
## Model description
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Intended uses & limitations
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training and evaluation data
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training procedure
|
38 |
+
|
39 |
+
### Training hyperparameters
|
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: 44
|
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 | 1.3140 | 0.4810 | 0.4710 |
|
55 |
+
| No log | 3.45 | 200 | 1.3058 | 0.4859 | 0.4712 |
|
56 |
+
| No log | 5.17 | 300 | 1.3692 | 0.4810 | 0.4758 |
|
57 |
+
| No log | 6.9 | 400 | 1.3751 | 0.4872 | 0.4822 |
|
58 |
+
| 1.1234 | 8.62 | 500 | 1.3743 | 0.4780 | 0.4771 |
|
59 |
+
| 1.1234 | 10.34 | 600 | 1.3539 | 0.4757 | 0.4743 |
|
60 |
+
| 1.1234 | 12.07 | 700 | 1.3873 | 0.4709 | 0.4680 |
|
61 |
+
| 1.1234 | 13.79 | 800 | 1.3612 | 0.4819 | 0.4821 |
|
62 |
+
| 1.1234 | 15.52 | 900 | 1.3503 | 0.4956 | 0.4957 |
|
63 |
+
| 0.9609 | 17.24 | 1000 | 1.3617 | 0.4841 | 0.4841 |
|
64 |
+
| 0.9609 | 18.97 | 1100 | 1.3602 | 0.4877 | 0.4849 |
|
65 |
+
| 0.9609 | 20.69 | 1200 | 1.3520 | 0.4881 | 0.4864 |
|
66 |
+
| 0.9609 | 22.41 | 1300 | 1.3598 | 0.4802 | 0.4738 |
|
67 |
+
| 0.9609 | 24.14 | 1400 | 1.3580 | 0.4722 | 0.4679 |
|
68 |
+
| 0.9422 | 25.86 | 1500 | 1.3409 | 0.4797 | 0.4797 |
|
69 |
+
| 0.9422 | 27.59 | 1600 | 1.3385 | 0.4903 | 0.4888 |
|
70 |
+
| 0.9422 | 29.31 | 1700 | 1.3448 | 0.4780 | 0.4765 |
|
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
|
config.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "haryoaw/scenario-MDBT-TCR_data-cl-cardiff_cl_only",
|
3 |
+
"architectures": [
|
4 |
+
"DebertaForSequenceClassificationKD"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"hidden_act": "gelu",
|
8 |
+
"hidden_dropout_prob": 0.1,
|
9 |
+
"hidden_size": 768,
|
10 |
+
"id2label": {
|
11 |
+
"0": "LABEL_0",
|
12 |
+
"1": "LABEL_1",
|
13 |
+
"2": "LABEL_2"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"intermediate_size": 3072,
|
17 |
+
"label2id": {
|
18 |
+
"LABEL_0": 0,
|
19 |
+
"LABEL_1": 1,
|
20 |
+
"LABEL_2": 2
|
21 |
+
},
|
22 |
+
"layer_norm_eps": 1e-07,
|
23 |
+
"max_position_embeddings": 512,
|
24 |
+
"max_relative_positions": -1,
|
25 |
+
"model_type": "deberta-v2",
|
26 |
+
"norm_rel_ebd": "layer_norm",
|
27 |
+
"num_attention_heads": 12,
|
28 |
+
"num_hidden_layers": 6,
|
29 |
+
"pad_token_id": 0,
|
30 |
+
"pooler_dropout": 0,
|
31 |
+
"pooler_hidden_act": "gelu",
|
32 |
+
"pooler_hidden_size": 768,
|
33 |
+
"pos_att_type": [
|
34 |
+
"p2c",
|
35 |
+
"c2p"
|
36 |
+
],
|
37 |
+
"position_biased_input": false,
|
38 |
+
"position_buckets": 256,
|
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 |
+
}
|
eval_results_cardiff.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"arabic": {"f1": 0.5241583746342374, "accuracy": 0.5333333333333333, "confusion_matrix": [[160, 59, 71], [103, 103, 84], [55, 34, 201]]}, "english": {"f1": 0.6211458947087118, "accuracy": 0.6229885057471264, "confusion_matrix": [[218, 54, 18], [91, 147, 52], [36, 77, 177]]}, "french": {"f1": 0.45101839231782376, "accuracy": 0.46781609195402296, "confusion_matrix": [[139, 124, 27], [49, 197, 44], [76, 143, 71]]}, "german": {"f1": 0.5601124993407652, "accuracy": 0.5597701149425287, "confusion_matrix": [[156, 88, 46], [55, 178, 57], [50, 87, 153]]}, "hindi": {"f1": 0.45527997069726256, "accuracy": 0.46436781609195404, "confusion_matrix": [[98, 72, 120], [49, 115, 126], [35, 64, 191]]}, "italian": {"f1": 0.5645135270940971, "accuracy": 0.5666666666666667, "confusion_matrix": [[195, 47, 48], [59, 149, 82], [78, 63, 149]]}, "portuguese": {"f1": 0.46822152728258803, "accuracy": 0.4747126436781609, "confusion_matrix": [[93, 145, 52], [56, 185, 49], [43, 112, 135]]}, "spanish": {"f1": 0.536485743383544, "accuracy": 0.5367816091954023, "confusion_matrix": [[140, 102, 48], [70, 145, 75], [41, 67, 182]]}, "all": {"f1": 0.5318703062000898, "accuracy": 0.5311781609195402, "confusion_matrix": [[1204, 684, 432], [514, 1251, 555], [412, 666, 1242]]}}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84b0c94e800cc757d3f7fa576bfffde4dd3589ee88b955fd8701bbf5f08a2aef
|
3 |
+
size 946740394
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:47f2be308e27b01a78c542169a93dbc2261ef9922ab6ecee63d2413e1f5559b2
|
3 |
+
size 4600
|