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_delta
|
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_delta
|
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: 3.3760
|
24 |
+
- Accuracy: 0.5586
|
25 |
+
- F1: 0.5590
|
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: 7777
|
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 |
+
| 4.88 | 1.09 | 500 | 4.1661 | 0.4518 | 0.4462 |
|
57 |
+
| 3.9513 | 2.17 | 1000 | 3.7172 | 0.5154 | 0.5102 |
|
58 |
+
| 3.4556 | 3.26 | 1500 | 3.5612 | 0.5293 | 0.5221 |
|
59 |
+
| 3.0959 | 4.35 | 2000 | 3.5271 | 0.5440 | 0.5349 |
|
60 |
+
| 2.7593 | 5.43 | 2500 | 3.3105 | 0.5602 | 0.5595 |
|
61 |
+
| 2.548 | 6.52 | 3000 | 3.4842 | 0.5355 | 0.5360 |
|
62 |
+
| 2.3323 | 7.61 | 3500 | 3.2883 | 0.5575 | 0.5444 |
|
63 |
+
| 2.1215 | 8.7 | 4000 | 3.2282 | 0.5583 | 0.5607 |
|
64 |
+
| 1.9719 | 9.78 | 4500 | 3.5734 | 0.5594 | 0.5534 |
|
65 |
+
| 1.8238 | 10.87 | 5000 | 3.2866 | 0.5552 | 0.5538 |
|
66 |
+
| 1.703 | 11.96 | 5500 | 3.2345 | 0.5556 | 0.5557 |
|
67 |
+
| 1.5931 | 13.04 | 6000 | 3.2219 | 0.5583 | 0.5539 |
|
68 |
+
| 1.4959 | 14.13 | 6500 | 3.3073 | 0.5637 | 0.5644 |
|
69 |
+
| 1.4198 | 15.22 | 7000 | 3.5221 | 0.5579 | 0.5541 |
|
70 |
+
| 1.35 | 16.3 | 7500 | 3.5125 | 0.5660 | 0.5643 |
|
71 |
+
| 1.2937 | 17.39 | 8000 | 3.5089 | 0.5640 | 0.5637 |
|
72 |
+
| 1.2282 | 18.48 | 8500 | 3.4262 | 0.5664 | 0.5658 |
|
73 |
+
| 1.1698 | 19.57 | 9000 | 3.3739 | 0.5598 | 0.5593 |
|
74 |
+
| 1.1402 | 20.65 | 9500 | 3.4930 | 0.5521 | 0.5541 |
|
75 |
+
| 1.0874 | 21.74 | 10000 | 3.4935 | 0.5625 | 0.5602 |
|
76 |
+
| 1.0652 | 22.83 | 10500 | 3.3963 | 0.5482 | 0.5478 |
|
77 |
+
| 1.0191 | 23.91 | 11000 | 3.4823 | 0.5571 | 0.5583 |
|
78 |
+
| 0.9868 | 25.0 | 11500 | 3.6035 | 0.5579 | 0.5586 |
|
79 |
+
| 0.9487 | 26.09 | 12000 | 3.6034 | 0.5525 | 0.5488 |
|
80 |
+
| 0.936 | 27.17 | 12500 | 3.5428 | 0.5556 | 0.5542 |
|
81 |
+
| 0.9116 | 28.26 | 13000 | 3.6023 | 0.5532 | 0.5509 |
|
82 |
+
| 0.8868 | 29.35 | 13500 | 3.5292 | 0.5579 | 0.5581 |
|
83 |
+
| 0.8733 | 30.43 | 14000 | 3.4206 | 0.5594 | 0.5589 |
|
84 |
+
| 0.8538 | 31.52 | 14500 | 3.4417 | 0.5594 | 0.5592 |
|
85 |
+
| 0.8289 | 32.61 | 15000 | 3.4970 | 0.5579 | 0.5584 |
|
86 |
+
| 0.823 | 33.7 | 15500 | 3.4860 | 0.5625 | 0.5617 |
|
87 |
+
| 0.7992 | 34.78 | 16000 | 3.5193 | 0.5671 | 0.5659 |
|
88 |
+
| 0.7974 | 35.87 | 16500 | 3.3709 | 0.5490 | 0.5497 |
|
89 |
+
| 0.7775 | 36.96 | 17000 | 3.3854 | 0.5706 | 0.5720 |
|
90 |
+
| 0.7691 | 38.04 | 17500 | 3.3827 | 0.5698 | 0.5700 |
|
91 |
+
| 0.758 | 39.13 | 18000 | 3.4608 | 0.5818 | 0.5818 |
|
92 |
+
| 0.757 | 40.22 | 18500 | 3.3860 | 0.5683 | 0.5681 |
|
93 |
+
| 0.7481 | 41.3 | 19000 | 3.3757 | 0.5687 | 0.5686 |
|
94 |
+
| 0.7387 | 42.39 | 19500 | 3.4830 | 0.5714 | 0.5707 |
|
95 |
+
| 0.7276 | 43.48 | 20000 | 3.3942 | 0.5617 | 0.5611 |
|
96 |
+
| 0.7279 | 44.57 | 20500 | 3.3357 | 0.5725 | 0.5726 |
|
97 |
+
| 0.7127 | 45.65 | 21000 | 3.3856 | 0.5521 | 0.5523 |
|
98 |
+
| 0.7148 | 46.74 | 21500 | 3.4401 | 0.5660 | 0.5673 |
|
99 |
+
| 0.7219 | 47.83 | 22000 | 3.4684 | 0.5629 | 0.5627 |
|
100 |
+
| 0.7005 | 48.91 | 22500 | 3.3840 | 0.5625 | 0.5631 |
|
101 |
+
| 0.7114 | 50.0 | 23000 | 3.3760 | 0.5586 | 0.5590 |
|
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 sha256:52651a8396429e639ea99c381a5d9200ef9fee9ee71416938557e6515caa51ba
|
3 |
+
size 429199798
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf2446fd202457883c94d43ee74090ce1dd6f516a3b6cb4e2195a9cabf5416ec
|
3 |
+
size 4664
|