Initial Commit
Browse files- README.md +88 -0
- config.json +39 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: xlm-roberta-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
- f1
|
9 |
+
model-index:
|
10 |
+
- name: scenario-NON-KD-PR-COPY-CDF-CL-D2_data-cl-cardiff_cl_only_delta
|
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-NON-KD-PR-COPY-CDF-CL-D2_data-cl-cardiff_cl_only_delta
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 5.4388
|
22 |
+
- Accuracy: 0.4390
|
23 |
+
- F1: 0.4380
|
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: 11213
|
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 | 1.09 | 250 | 1.1982 | 0.4576 | 0.4521 |
|
55 |
+
| 0.9123 | 2.17 | 500 | 1.4363 | 0.4722 | 0.4650 |
|
56 |
+
| 0.9123 | 3.26 | 750 | 1.5173 | 0.4715 | 0.4672 |
|
57 |
+
| 0.5863 | 4.35 | 1000 | 1.8168 | 0.4545 | 0.4539 |
|
58 |
+
| 0.5863 | 5.43 | 1250 | 2.0339 | 0.4645 | 0.4643 |
|
59 |
+
| 0.3146 | 6.52 | 1500 | 2.0526 | 0.4753 | 0.4739 |
|
60 |
+
| 0.3146 | 7.61 | 1750 | 2.5574 | 0.4560 | 0.4543 |
|
61 |
+
| 0.1799 | 8.7 | 2000 | 2.7053 | 0.4537 | 0.4542 |
|
62 |
+
| 0.1799 | 9.78 | 2250 | 3.2816 | 0.4468 | 0.4462 |
|
63 |
+
| 0.1166 | 10.87 | 2500 | 3.5971 | 0.4414 | 0.4418 |
|
64 |
+
| 0.1166 | 11.96 | 2750 | 3.5830 | 0.4491 | 0.4477 |
|
65 |
+
| 0.0894 | 13.04 | 3000 | 3.7770 | 0.4537 | 0.4537 |
|
66 |
+
| 0.0894 | 14.13 | 3250 | 4.0171 | 0.4475 | 0.4464 |
|
67 |
+
| 0.0625 | 15.22 | 3500 | 4.3230 | 0.4383 | 0.4350 |
|
68 |
+
| 0.0625 | 16.3 | 3750 | 4.4061 | 0.4421 | 0.4402 |
|
69 |
+
| 0.0419 | 17.39 | 4000 | 4.5390 | 0.4468 | 0.4460 |
|
70 |
+
| 0.0419 | 18.48 | 4250 | 4.7343 | 0.4452 | 0.4445 |
|
71 |
+
| 0.0328 | 19.57 | 4500 | 4.5586 | 0.4514 | 0.4527 |
|
72 |
+
| 0.0328 | 20.65 | 4750 | 4.9107 | 0.4437 | 0.4424 |
|
73 |
+
| 0.0225 | 21.74 | 5000 | 5.1509 | 0.4313 | 0.4276 |
|
74 |
+
| 0.0225 | 22.83 | 5250 | 4.8634 | 0.4444 | 0.4436 |
|
75 |
+
| 0.0209 | 23.91 | 5500 | 5.1513 | 0.4352 | 0.4318 |
|
76 |
+
| 0.0209 | 25.0 | 5750 | 5.0801 | 0.4552 | 0.4555 |
|
77 |
+
| 0.0117 | 26.09 | 6000 | 5.2642 | 0.4468 | 0.4444 |
|
78 |
+
| 0.0117 | 27.17 | 6250 | 5.3801 | 0.4367 | 0.4342 |
|
79 |
+
| 0.0092 | 28.26 | 6500 | 5.4445 | 0.4367 | 0.4343 |
|
80 |
+
| 0.0092 | 29.35 | 6750 | 5.4388 | 0.4390 | 0.4380 |
|
81 |
+
|
82 |
+
|
83 |
+
### Framework versions
|
84 |
+
|
85 |
+
- Transformers 4.33.3
|
86 |
+
- Pytorch 2.1.1+cu121
|
87 |
+
- Datasets 2.14.5
|
88 |
+
- Tokenizers 0.13.3
|
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "xlm-roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"XLMRobertaForSequenceClassification"
|
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": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "LABEL_0",
|
15 |
+
"1": "LABEL_1",
|
16 |
+
"2": "LABEL_2"
|
17 |
+
},
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"intermediate_size": 3072,
|
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:c501bd7712869610576cc745951690ebd6b741dbd9f4ff30d666bfc816c0039c
|
3 |
+
size 942111086
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ba72b1e5c48bcc63fd1e3380129bb6a40fde6400bcf49cd66c67c6996a46faf
|
3 |
+
size 4600
|