Upload 5 files
Browse files- README.md +128 -1
- config.json +52 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- vocab.txt +0 -0
README.md
CHANGED
@@ -1,3 +1,130 @@
|
|
1 |
---
|
2 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
datasets:
|
5 |
+
- rubric
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: estbert128_lr5e-5_b16_s3
|
10 |
+
results:
|
11 |
+
- task:
|
12 |
+
name: Text Classification
|
13 |
+
type: text-classification
|
14 |
+
dataset:
|
15 |
+
name: rubric
|
16 |
+
type: rubric
|
17 |
+
args: rubric
|
18 |
+
metrics:
|
19 |
+
- name: Accuracy
|
20 |
+
type: accuracy
|
21 |
+
value: 0.8329238295555115
|
22 |
---
|
23 |
+
|
24 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
25 |
+
should probably proofread and complete it, then remove this comment. -->
|
26 |
+
|
27 |
+
# estbert128_lr5e-5_b16_s3
|
28 |
+
|
29 |
+
This model is a fine-tuned version of [tartuNLP/EstBERT](https://huggingface.co/tartuNLP/EstBERT) on the rubric dataset.
|
30 |
+
It achieves the following results on the evaluation set:
|
31 |
+
- Loss: 2.0552
|
32 |
+
- Accuracy: 0.8329
|
33 |
+
|
34 |
+
## Model description
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Intended uses & limitations
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Training and evaluation data
|
43 |
+
|
44 |
+
More information needed
|
45 |
+
|
46 |
+
## Training procedure
|
47 |
+
|
48 |
+
### Training hyperparameters
|
49 |
+
|
50 |
+
The following hyperparameters were used during training:
|
51 |
+
- learning_rate: 5e-05
|
52 |
+
- train_batch_size: 16
|
53 |
+
- eval_batch_size: 16
|
54 |
+
- seed: 3
|
55 |
+
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06
|
56 |
+
- lr_scheduler_type: polynomial
|
57 |
+
- num_epochs: 100
|
58 |
+
- mixed_precision_training: Native AMP
|
59 |
+
|
60 |
+
### Training results
|
61 |
+
|
62 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
63 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
64 |
+
| 1.1147 | 1.0 | 179 | 0.7421 | 0.7445 |
|
65 |
+
| 0.4323 | 2.0 | 358 | 0.6863 | 0.7813 |
|
66 |
+
| 0.1442 | 3.0 | 537 | 0.8545 | 0.7838 |
|
67 |
+
| 0.0496 | 4.0 | 716 | 1.2872 | 0.7494 |
|
68 |
+
| 0.0276 | 5.0 | 895 | 1.4702 | 0.7641 |
|
69 |
+
| 0.0202 | 6.0 | 1074 | 1.3764 | 0.7838 |
|
70 |
+
| 0.0144 | 7.0 | 1253 | 1.5762 | 0.7887 |
|
71 |
+
| 0.0078 | 8.0 | 1432 | 1.8806 | 0.7666 |
|
72 |
+
| 0.0177 | 9.0 | 1611 | 1.6159 | 0.7912 |
|
73 |
+
| 0.0223 | 10.0 | 1790 | 1.5863 | 0.7936 |
|
74 |
+
| 0.0108 | 11.0 | 1969 | 1.8051 | 0.7912 |
|
75 |
+
| 0.0201 | 12.0 | 2148 | 1.9344 | 0.7789 |
|
76 |
+
| 0.0252 | 13.0 | 2327 | 1.7978 | 0.8084 |
|
77 |
+
| 0.0104 | 14.0 | 2506 | 1.8779 | 0.7887 |
|
78 |
+
| 0.0138 | 15.0 | 2685 | 1.6456 | 0.8133 |
|
79 |
+
| 0.0066 | 16.0 | 2864 | 1.9668 | 0.7912 |
|
80 |
+
| 0.0148 | 17.0 | 3043 | 2.0068 | 0.7813 |
|
81 |
+
| 0.0128 | 18.0 | 3222 | 2.1539 | 0.7617 |
|
82 |
+
| 0.0115 | 19.0 | 3401 | 2.2490 | 0.7838 |
|
83 |
+
| 0.0186 | 20.0 | 3580 | 2.1768 | 0.7666 |
|
84 |
+
| 0.0051 | 21.0 | 3759 | 1.8859 | 0.7912 |
|
85 |
+
| 0.001 | 22.0 | 3938 | 2.0132 | 0.7912 |
|
86 |
+
| 0.0133 | 23.0 | 4117 | 1.8786 | 0.8084 |
|
87 |
+
| 0.0149 | 24.0 | 4296 | 2.2307 | 0.7961 |
|
88 |
+
| 0.014 | 25.0 | 4475 | 2.0041 | 0.8206 |
|
89 |
+
| 0.0132 | 26.0 | 4654 | 1.8872 | 0.8133 |
|
90 |
+
| 0.0079 | 27.0 | 4833 | 1.9357 | 0.7961 |
|
91 |
+
| 0.0078 | 28.0 | 5012 | 2.1891 | 0.7936 |
|
92 |
+
| 0.0126 | 29.0 | 5191 | 2.0207 | 0.8034 |
|
93 |
+
| 0.0003 | 30.0 | 5370 | 2.1917 | 0.8010 |
|
94 |
+
| 0.0015 | 31.0 | 5549 | 2.0417 | 0.8157 |
|
95 |
+
| 0.0056 | 32.0 | 5728 | 2.1172 | 0.8084 |
|
96 |
+
| 0.0058 | 33.0 | 5907 | 2.1921 | 0.8206 |
|
97 |
+
| 0.0001 | 34.0 | 6086 | 2.0079 | 0.8206 |
|
98 |
+
| 0.0031 | 35.0 | 6265 | 2.2447 | 0.8206 |
|
99 |
+
| 0.0007 | 36.0 | 6444 | 2.1802 | 0.8084 |
|
100 |
+
| 0.0061 | 37.0 | 6623 | 2.1103 | 0.8157 |
|
101 |
+
| 0.0 | 38.0 | 6802 | 2.2265 | 0.8084 |
|
102 |
+
| 0.0035 | 39.0 | 6981 | 2.0549 | 0.8329 |
|
103 |
+
| 0.0038 | 40.0 | 7160 | 2.1352 | 0.8182 |
|
104 |
+
| 0.0001 | 41.0 | 7339 | 2.0975 | 0.8108 |
|
105 |
+
| 0.0 | 42.0 | 7518 | 2.0833 | 0.8256 |
|
106 |
+
| 0.0 | 43.0 | 7697 | 2.1020 | 0.8280 |
|
107 |
+
| 0.0 | 44.0 | 7876 | 2.0841 | 0.8305 |
|
108 |
+
| 0.0 | 45.0 | 8055 | 2.2085 | 0.8182 |
|
109 |
+
| 0.0 | 46.0 | 8234 | 2.0756 | 0.8329 |
|
110 |
+
| 0.0 | 47.0 | 8413 | 2.1237 | 0.8305 |
|
111 |
+
| 0.0 | 48.0 | 8592 | 2.1217 | 0.8280 |
|
112 |
+
| 0.0052 | 49.0 | 8771 | 2.3567 | 0.8059 |
|
113 |
+
| 0.0014 | 50.0 | 8950 | 2.1710 | 0.8206 |
|
114 |
+
| 0.0032 | 51.0 | 9129 | 2.1452 | 0.8206 |
|
115 |
+
| 0.0 | 52.0 | 9308 | 2.2820 | 0.8133 |
|
116 |
+
| 0.0001 | 53.0 | 9487 | 2.2279 | 0.8157 |
|
117 |
+
| 0.0 | 54.0 | 9666 | 2.1841 | 0.8182 |
|
118 |
+
| 0.0 | 55.0 | 9845 | 2.1208 | 0.8231 |
|
119 |
+
| 0.0 | 56.0 | 10024 | 2.0967 | 0.8256 |
|
120 |
+
| 0.0002 | 57.0 | 10203 | 2.1911 | 0.8231 |
|
121 |
+
| 0.0 | 58.0 | 10382 | 2.2014 | 0.8231 |
|
122 |
+
| 0.0 | 59.0 | 10561 | 2.2014 | 0.8182 |
|
123 |
+
|
124 |
+
|
125 |
+
### Framework versions
|
126 |
+
|
127 |
+
- Transformers 4.14.1
|
128 |
+
- Pytorch 1.10.1+cu113
|
129 |
+
- Datasets 1.16.1
|
130 |
+
- Tokenizers 0.10.3
|
config.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "tartuNLP/EstBERT",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_ids": 0,
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "ARVAMUS",
|
16 |
+
"1": "EESTI",
|
17 |
+
"2": "ELU-O",
|
18 |
+
"3": "KOMM-O-ELU",
|
19 |
+
"4": "KOMM-P-EESTI",
|
20 |
+
"5": "KRIMI",
|
21 |
+
"6": "KULTUUR",
|
22 |
+
"7": "SPORT",
|
23 |
+
"8": "VALISMAA"
|
24 |
+
},
|
25 |
+
"initializer_range": 0.02,
|
26 |
+
"intermediate_size": 3072,
|
27 |
+
"label2id": {
|
28 |
+
"ARVAMUS": 0,
|
29 |
+
"EESTI": 1,
|
30 |
+
"ELU-O": 2,
|
31 |
+
"KOMM-O-ELU": 3,
|
32 |
+
"KOMM-P-EESTI": 4,
|
33 |
+
"KRIMI": 5,
|
34 |
+
"KULTUUR": 6,
|
35 |
+
"SPORT": 7,
|
36 |
+
"VALISMAA": 8
|
37 |
+
},
|
38 |
+
"layer_norm_eps": 1e-12,
|
39 |
+
"max_position_embeddings": 512,
|
40 |
+
"model_type": "bert",
|
41 |
+
"num_attention_heads": 12,
|
42 |
+
"num_hidden_layers": 12,
|
43 |
+
"output_past": true,
|
44 |
+
"pad_token_id": 0,
|
45 |
+
"position_embedding_type": "absolute",
|
46 |
+
"problem_type": "single_label_classification",
|
47 |
+
"torch_dtype": "float32",
|
48 |
+
"transformers_version": "4.14.1",
|
49 |
+
"type_vocab_size": 2,
|
50 |
+
"use_cache": true,
|
51 |
+
"vocab_size": 50000
|
52 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|