Initial Commit
Browse files- README.md +78 -0
- config.json +39 -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-TCR_data-cl-cardiff_cl_only2
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
- f1
|
9 |
+
model-index:
|
10 |
+
- name: scenario-KD-PO-CDF-EN-FROM-CL-D2_data-en-cardiff_eng_only_beta-jason
|
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-PO-CDF-EN-FROM-CL-D2_data-en-cardiff_eng_only_beta-jason
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [haryoaw/scenario-TCR_data-cl-cardiff_cl_only2](https://huggingface.co/haryoaw/scenario-TCR_data-cl-cardiff_cl_only2) on the None dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 16.2943
|
22 |
+
- Accuracy: 0.4026
|
23 |
+
- F1: 0.3951
|
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: 6666
|
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 | 12.5546 | 0.3884 | 0.3802 |
|
55 |
+
| No log | 3.45 | 200 | 12.5713 | 0.3889 | 0.3881 |
|
56 |
+
| No log | 5.17 | 300 | 12.7463 | 0.4017 | 0.3840 |
|
57 |
+
| No log | 6.9 | 400 | 13.0469 | 0.3884 | 0.3865 |
|
58 |
+
| 12.7004 | 8.62 | 500 | 13.4306 | 0.3964 | 0.3948 |
|
59 |
+
| 12.7004 | 10.34 | 600 | 13.5764 | 0.3964 | 0.3952 |
|
60 |
+
| 12.7004 | 12.07 | 700 | 13.8288 | 0.4074 | 0.4072 |
|
61 |
+
| 12.7004 | 13.79 | 800 | 14.3994 | 0.3955 | 0.3835 |
|
62 |
+
| 12.7004 | 15.52 | 900 | 14.4145 | 0.4171 | 0.4126 |
|
63 |
+
| 8.7663 | 17.24 | 1000 | 14.7236 | 0.4039 | 0.3966 |
|
64 |
+
| 8.7663 | 18.97 | 1100 | 15.3258 | 0.3920 | 0.3750 |
|
65 |
+
| 8.7663 | 20.69 | 1200 | 15.4501 | 0.3973 | 0.3945 |
|
66 |
+
| 8.7663 | 22.41 | 1300 | 15.6468 | 0.4026 | 0.3945 |
|
67 |
+
| 8.7663 | 24.14 | 1400 | 15.8710 | 0.4096 | 0.4019 |
|
68 |
+
| 6.1643 | 25.86 | 1500 | 15.9974 | 0.4136 | 0.4077 |
|
69 |
+
| 6.1643 | 27.59 | 1600 | 16.6029 | 0.3840 | 0.3721 |
|
70 |
+
| 6.1643 | 29.31 | 1700 | 16.2943 | 0.4026 | 0.3951 |
|
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 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "haryoaw/scenario-TCR_data-cl-cardiff_cl_only2",
|
3 |
+
"architectures": [
|
4 |
+
"XLMRobertaForSequenceClassificationKD"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 384,
|
13 |
+
"id2label": {
|
14 |
+
"0": "LABEL_0",
|
15 |
+
"1": "LABEL_1",
|
16 |
+
"2": "LABEL_2"
|
17 |
+
},
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"intermediate_size": 1536,
|
20 |
+
"label2id": {
|
21 |
+
"LABEL_0": 0,
|
22 |
+
"LABEL_1": 1,
|
23 |
+
"LABEL_2": 2
|
24 |
+
},
|
25 |
+
"layer_norm_eps": 1e-05,
|
26 |
+
"max_position_embeddings": 514,
|
27 |
+
"model_type": "xlm-roberta",
|
28 |
+
"num_attention_heads": 12,
|
29 |
+
"num_hidden_layers": 6,
|
30 |
+
"output_past": true,
|
31 |
+
"pad_token_id": 1,
|
32 |
+
"position_embedding_type": "absolute",
|
33 |
+
"problem_type": "single_label_classification",
|
34 |
+
"torch_dtype": "float32",
|
35 |
+
"transformers_version": "4.33.3",
|
36 |
+
"type_vocab_size": 1,
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 250002
|
39 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c89e4ec4901e78c445bd2698460e5ca48d6365dfe4e539b0ed0c637552500f8
|
3 |
+
size 429199798
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce4cffe40e8efba15014fbc51b6842187eb8c2f985cddf1194790c1713a0fc7f
|
3 |
+
size 4600
|