Initial Commit
Browse files- README.md +109 -0
- config.json +39 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: haryoaw/scenario-TCR_data-cardiffnlp_tweet_sentiment_multilingual_all_a
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- tweet_sentiment_multilingual
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
- f1
|
11 |
+
model-index:
|
12 |
+
- name: scenario-KD-PO-CDF-ALL-D2_data-cardiffnlp_tweet_sentiment_multilingual_all_alpha
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# scenario-KD-PO-CDF-ALL-D2_data-cardiffnlp_tweet_sentiment_multilingual_all_alpha
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [haryoaw/scenario-TCR_data-cardiffnlp_tweet_sentiment_multilingual_all_a](https://huggingface.co/haryoaw/scenario-TCR_data-cardiffnlp_tweet_sentiment_multilingual_all_a) on the tweet_sentiment_multilingual dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 3.4750
|
24 |
+
- Accuracy: 0.5637
|
25 |
+
- F1: 0.5640
|
26 |
+
|
27 |
+
## Model description
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Intended uses & limitations
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training and evaluation data
|
36 |
+
|
37 |
+
More information needed
|
38 |
+
|
39 |
+
## Training procedure
|
40 |
+
|
41 |
+
### Training hyperparameters
|
42 |
+
|
43 |
+
The following hyperparameters were used during training:
|
44 |
+
- learning_rate: 5e-05
|
45 |
+
- train_batch_size: 32
|
46 |
+
- eval_batch_size: 32
|
47 |
+
- seed: 2222
|
48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
+
- lr_scheduler_type: linear
|
50 |
+
- num_epochs: 50
|
51 |
+
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
55 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|
|
56 |
+
| 4.905 | 1.09 | 500 | 4.5461 | 0.4363 | 0.4113 |
|
57 |
+
| 4.0059 | 2.17 | 1000 | 3.6093 | 0.5058 | 0.5040 |
|
58 |
+
| 3.4109 | 3.26 | 1500 | 3.4190 | 0.5208 | 0.5131 |
|
59 |
+
| 3.0676 | 4.35 | 2000 | 3.2675 | 0.5490 | 0.5477 |
|
60 |
+
| 2.7673 | 5.43 | 2500 | 3.2746 | 0.5467 | 0.5412 |
|
61 |
+
| 2.5421 | 6.52 | 3000 | 3.1951 | 0.5475 | 0.5367 |
|
62 |
+
| 2.3609 | 7.61 | 3500 | 3.3137 | 0.5432 | 0.5410 |
|
63 |
+
| 2.1176 | 8.7 | 4000 | 3.5963 | 0.5451 | 0.5303 |
|
64 |
+
| 1.9583 | 9.78 | 4500 | 3.5109 | 0.5571 | 0.5583 |
|
65 |
+
| 1.8268 | 10.87 | 5000 | 3.3664 | 0.5471 | 0.5477 |
|
66 |
+
| 1.7388 | 11.96 | 5500 | 3.3858 | 0.5517 | 0.5528 |
|
67 |
+
| 1.5976 | 13.04 | 6000 | 3.4404 | 0.5617 | 0.5577 |
|
68 |
+
| 1.4912 | 14.13 | 6500 | 3.3307 | 0.5586 | 0.5585 |
|
69 |
+
| 1.4157 | 15.22 | 7000 | 3.5579 | 0.5432 | 0.5355 |
|
70 |
+
| 1.3536 | 16.3 | 7500 | 3.3542 | 0.5617 | 0.5603 |
|
71 |
+
| 1.2883 | 17.39 | 8000 | 3.6026 | 0.5571 | 0.5543 |
|
72 |
+
| 1.2443 | 18.48 | 8500 | 3.6866 | 0.5478 | 0.5458 |
|
73 |
+
| 1.1637 | 19.57 | 9000 | 3.6125 | 0.5536 | 0.5547 |
|
74 |
+
| 1.1391 | 20.65 | 9500 | 3.5456 | 0.5613 | 0.5574 |
|
75 |
+
| 1.1029 | 21.74 | 10000 | 3.4366 | 0.5513 | 0.5526 |
|
76 |
+
| 1.0417 | 22.83 | 10500 | 3.6791 | 0.5586 | 0.5585 |
|
77 |
+
| 1.0169 | 23.91 | 11000 | 3.6637 | 0.5656 | 0.5607 |
|
78 |
+
| 1.0107 | 25.0 | 11500 | 3.5452 | 0.5575 | 0.5578 |
|
79 |
+
| 0.9502 | 26.09 | 12000 | 3.4362 | 0.5748 | 0.5742 |
|
80 |
+
| 0.9455 | 27.17 | 12500 | 3.4865 | 0.5694 | 0.5703 |
|
81 |
+
| 0.9194 | 28.26 | 13000 | 3.4523 | 0.5737 | 0.5716 |
|
82 |
+
| 0.9053 | 29.35 | 13500 | 3.5411 | 0.5586 | 0.5572 |
|
83 |
+
| 0.8737 | 30.43 | 14000 | 3.6550 | 0.5586 | 0.5586 |
|
84 |
+
| 0.865 | 31.52 | 14500 | 3.5079 | 0.5594 | 0.5611 |
|
85 |
+
| 0.8444 | 32.61 | 15000 | 3.4885 | 0.5509 | 0.5526 |
|
86 |
+
| 0.8343 | 33.7 | 15500 | 3.5705 | 0.5710 | 0.5698 |
|
87 |
+
| 0.8122 | 34.78 | 16000 | 3.4910 | 0.5521 | 0.5519 |
|
88 |
+
| 0.8161 | 35.87 | 16500 | 3.5302 | 0.5559 | 0.5563 |
|
89 |
+
| 0.7923 | 36.96 | 17000 | 3.5031 | 0.5656 | 0.5632 |
|
90 |
+
| 0.7824 | 38.04 | 17500 | 3.4182 | 0.5594 | 0.5592 |
|
91 |
+
| 0.7658 | 39.13 | 18000 | 3.5265 | 0.5594 | 0.5586 |
|
92 |
+
| 0.7588 | 40.22 | 18500 | 3.4465 | 0.5706 | 0.5711 |
|
93 |
+
| 0.7541 | 41.3 | 19000 | 3.4879 | 0.5540 | 0.5534 |
|
94 |
+
| 0.7488 | 42.39 | 19500 | 3.4246 | 0.5687 | 0.5693 |
|
95 |
+
| 0.7412 | 43.48 | 20000 | 3.4806 | 0.5745 | 0.5750 |
|
96 |
+
| 0.7314 | 44.57 | 20500 | 3.5638 | 0.5590 | 0.5586 |
|
97 |
+
| 0.7283 | 45.65 | 21000 | 3.4212 | 0.5664 | 0.5667 |
|
98 |
+
| 0.7179 | 46.74 | 21500 | 3.4444 | 0.5556 | 0.5560 |
|
99 |
+
| 0.7168 | 47.83 | 22000 | 3.4104 | 0.5602 | 0.5606 |
|
100 |
+
| 0.7161 | 48.91 | 22500 | 3.3766 | 0.5667 | 0.5676 |
|
101 |
+
| 0.7052 | 50.0 | 23000 | 3.4750 | 0.5637 | 0.5640 |
|
102 |
+
|
103 |
+
|
104 |
+
### Framework versions
|
105 |
+
|
106 |
+
- Transformers 4.33.3
|
107 |
+
- Pytorch 2.1.1+cu121
|
108 |
+
- Datasets 2.14.5
|
109 |
+
- Tokenizers 0.13.3
|
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "haryoaw/scenario-TCR_data-cardiffnlp_tweet_sentiment_multilingual_all_a",
|
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:b4b9a0d991ae63a7f8e99cacf277f5dc6e3aa5f1be73c20d8c5ba71606ed603c
|
3 |
+
size 429199798
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54034a8fae33a570c0031aafd3ee3cc01479dc15aa104598462213adf8cb0ddb
|
3 |
+
size 4664
|