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_only55
|
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_only55
|
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: 1.3279
|
22 |
+
- Accuracy: 0.4881
|
23 |
+
- F1: 0.4855
|
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: 55
|
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 | 1.3136 | 0.4599 | 0.4267 |
|
55 |
+
| No log | 3.45 | 200 | 1.4057 | 0.4506 | 0.4056 |
|
56 |
+
| No log | 5.17 | 300 | 1.3382 | 0.4797 | 0.4752 |
|
57 |
+
| No log | 6.9 | 400 | 1.3472 | 0.4890 | 0.4858 |
|
58 |
+
| 1.1235 | 8.62 | 500 | 1.3400 | 0.4863 | 0.4865 |
|
59 |
+
| 1.1235 | 10.34 | 600 | 1.3593 | 0.4837 | 0.4776 |
|
60 |
+
| 1.1235 | 12.07 | 700 | 1.3787 | 0.4638 | 0.4526 |
|
61 |
+
| 1.1235 | 13.79 | 800 | 1.3508 | 0.4868 | 0.4853 |
|
62 |
+
| 1.1235 | 15.52 | 900 | 1.3393 | 0.4912 | 0.4895 |
|
63 |
+
| 0.9596 | 17.24 | 1000 | 1.3570 | 0.4802 | 0.4693 |
|
64 |
+
| 0.9596 | 18.97 | 1100 | 1.3359 | 0.4929 | 0.4905 |
|
65 |
+
| 0.9596 | 20.69 | 1200 | 1.3386 | 0.4846 | 0.4816 |
|
66 |
+
| 0.9596 | 22.41 | 1300 | 1.3372 | 0.4916 | 0.4903 |
|
67 |
+
| 0.9596 | 24.14 | 1400 | 1.3271 | 0.4956 | 0.4932 |
|
68 |
+
| 0.9384 | 25.86 | 1500 | 1.3313 | 0.4921 | 0.4913 |
|
69 |
+
| 0.9384 | 27.59 | 1600 | 1.3341 | 0.4907 | 0.4897 |
|
70 |
+
| 0.9384 | 29.31 | 1700 | 1.3279 | 0.4881 | 0.4855 |
|
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": 0.4971009552168196, "accuracy": 0.5, "confusion_matrix": [[191, 81, 18], [132, 135, 23], [103, 78, 109]]}, "english": {"f1": 0.59591337327029, "accuracy": 0.6011494252873564, "confusion_matrix": [[231, 43, 16], [118, 134, 38], [57, 75, 158]]}, "french": {"f1": 0.42712253677008477, "accuracy": 0.45517241379310347, "confusion_matrix": [[135, 135, 20], [60, 208, 22], [72, 165, 53]]}, "german": {"f1": 0.5737966513684558, "accuracy": 0.5770114942528736, "confusion_matrix": [[155, 101, 34], [42, 214, 34], [45, 112, 133]]}, "hindi": {"f1": 0.48973802418661555, "accuracy": 0.49195402298850577, "confusion_matrix": [[118, 105, 67], [57, 169, 64], [56, 93, 141]]}, "italian": {"f1": 0.5685132027618679, "accuracy": 0.5781609195402299, "confusion_matrix": [[230, 35, 25], [74, 149, 67], [108, 58, 124]]}, "portuguese": {"f1": 0.4978849681994417, "accuracy": 0.49885057471264366, "confusion_matrix": [[121, 134, 35], [70, 183, 37], [58, 102, 130]]}, "spanish": {"f1": 0.5209822031739703, "accuracy": 0.5183908045977011, "confusion_matrix": [[169, 96, 25], [107, 136, 47], [66, 78, 146]]}, "all": {"f1": 0.5284687008618958, "accuracy": 0.5298850574712644, "confusion_matrix": [[1379, 706, 235], [661, 1321, 338], [597, 735, 988]]}}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:59cde461882acda862782975160da1875570758bbc881a8b5f643dded021f137
|
3 |
+
size 946740394
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed4b256f02938f1e11a8c26c7f4129bb3ac647b45445df28513c3ee01ae7baca
|
3 |
+
size 4600
|