Publishing model
Browse files- .gitattributes +5 -0
- .gitignore +1 -0
- README.md +101 -0
- config.json +3 -51
- pytorch_model.bin +2 -2
- special_tokens_map.json +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +3 -0
- train_results.json +3 -0
- vocab.json +3 -0
.gitattributes
CHANGED
@@ -1,3 +1,4 @@
|
|
|
|
1 |
*.7z filter=lfs diff=lfs merge=lfs -text
|
2 |
*.arrow filter=lfs diff=lfs merge=lfs -text
|
3 |
*.bin filter=lfs diff=lfs merge=lfs -text
|
@@ -25,3 +26,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
1 |
+
<<<<<<< HEAD
|
2 |
*.7z filter=lfs diff=lfs merge=lfs -text
|
3 |
*.arrow filter=lfs diff=lfs merge=lfs -text
|
4 |
*.bin filter=lfs diff=lfs merge=lfs -text
|
|
|
26 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
27 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
28 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
29 |
+
=======
|
30 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
31 |
+
*.json filter=lfs diff=lfs merge=lfs -text
|
32 |
+
>>>>>>> Publishing model
|
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
.DS_Store
|
README.md
ADDED
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- ju-bezdek/conll2003-SK-NER
|
7 |
+
metrics:
|
8 |
+
- precision
|
9 |
+
- recall
|
10 |
+
- f1
|
11 |
+
- accuracy
|
12 |
+
model-index:
|
13 |
+
- name: outputs
|
14 |
+
results:
|
15 |
+
- task:
|
16 |
+
name: Token Classification
|
17 |
+
type: token-classification
|
18 |
+
dataset:
|
19 |
+
name: ju-bezdek/conll2003-SK-NER
|
20 |
+
type: ju-bezdek/conll2003-SK-NER
|
21 |
+
args: conll2003-SK-NER
|
22 |
+
metrics:
|
23 |
+
- name: Precision
|
24 |
+
type: precision
|
25 |
+
value: 0.8189727994593682
|
26 |
+
- name: Recall
|
27 |
+
type: recall
|
28 |
+
value: 0.8389581169955002
|
29 |
+
- name: F1
|
30 |
+
type: f1
|
31 |
+
value: 0.8288450029922203
|
32 |
+
- name: Accuracy
|
33 |
+
type: accuracy
|
34 |
+
value: 0.9526157920337243
|
35 |
+
---
|
36 |
+
|
37 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
38 |
+
should probably proofread and complete it, then remove this comment. -->
|
39 |
+
|
40 |
+
# outputs
|
41 |
+
|
42 |
+
This model is a fine-tuned version of [gerulata/slovakbert](https://huggingface.co/gerulata/slovakbert) on the ju-bezdek/conll2003-SK-NER dataset.
|
43 |
+
It achieves the following results on the evaluation (validation) set:
|
44 |
+
- Loss: 0.1752
|
45 |
+
- Precision: 0.8190
|
46 |
+
- Recall: 0.8390
|
47 |
+
- F1: 0.8288
|
48 |
+
- Accuracy: 0.9526
|
49 |
+
|
50 |
+
## Model description
|
51 |
+
|
52 |
+
More information needed
|
53 |
+
|
54 |
+
## Intended uses & limitations
|
55 |
+
|
56 |
+
More information needed
|
57 |
+
|
58 |
+
## Training and evaluation data
|
59 |
+
|
60 |
+
More information needed
|
61 |
+
|
62 |
+
## Training procedure
|
63 |
+
|
64 |
+
### Training hyperparameters
|
65 |
+
|
66 |
+
The following hyperparameters were used during training:
|
67 |
+
- learning_rate: 0.0001
|
68 |
+
- train_batch_size: 16
|
69 |
+
- eval_batch_size: 16
|
70 |
+
- seed: 42
|
71 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
72 |
+
- lr_scheduler_type: linear
|
73 |
+
- num_epochs: 15
|
74 |
+
|
75 |
+
### Training results
|
76 |
+
|
77 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
78 |
+
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
79 |
+
| 0.3237 | 1.0 | 878 | 0.2541 | 0.7125 | 0.8059 | 0.7563 | 0.9283 |
|
80 |
+
| 0.1663 | 2.0 | 1756 | 0.2370 | 0.7775 | 0.8090 | 0.7929 | 0.9394 |
|
81 |
+
| 0.1251 | 3.0 | 2634 | 0.2289 | 0.7732 | 0.8029 | 0.7878 | 0.9385 |
|
82 |
+
| 0.0984 | 4.0 | 3512 | 0.2818 | 0.7294 | 0.8189 | 0.7715 | 0.9294 |
|
83 |
+
| 0.0808 | 5.0 | 4390 | 0.3138 | 0.7615 | 0.7900 | 0.7755 | 0.9326 |
|
84 |
+
| 0.0578 | 6.0 | 5268 | 0.3072 | 0.7548 | 0.8222 | 0.7871 | 0.9370 |
|
85 |
+
| 0.0481 | 7.0 | 6146 | 0.2778 | 0.7897 | 0.8156 | 0.8025 | 0.9408 |
|
86 |
+
| 0.0414 | 8.0 | 7024 | 0.3336 | 0.7695 | 0.8201 | 0.7940 | 0.9389 |
|
87 |
+
| 0.0268 | 9.0 | 7902 | 0.3294 | 0.7868 | 0.8140 | 0.8002 | 0.9409 |
|
88 |
+
| 0.0204 | 10.0 | 8780 | 0.3693 | 0.7657 | 0.8239 | 0.7938 | 0.9376 |
|
89 |
+
| 0.016 | 11.0 | 9658 | 0.3816 | 0.7932 | 0.8242 | 0.8084 | 0.9425 |
|
90 |
+
| 0.0108 | 12.0 | 10536 | 0.3607 | 0.7929 | 0.8256 | 0.8089 | 0.9431 |
|
91 |
+
| 0.0078 | 13.0 | 11414 | 0.3980 | 0.7915 | 0.8240 | 0.8074 | 0.9423 |
|
92 |
+
| 0.0062 | 14.0 | 12292 | 0.4096 | 0.7995 | 0.8247 | 0.8119 | 0.9436 |
|
93 |
+
| 0.0035 | 15.0 | 13170 | 0.4177 | 0.8006 | 0.8251 | 0.8127 | 0.9438 |
|
94 |
+
|
95 |
+
|
96 |
+
### Framework versions
|
97 |
+
|
98 |
+
- Transformers 4.15.0
|
99 |
+
- Pytorch 1.10.1+cu102
|
100 |
+
- Datasets 1.17.0
|
101 |
+
- Tokenizers 0.10.3
|
config.json
CHANGED
@@ -1,51 +1,3 @@
|
|
1 |
-
|
2 |
-
|
3 |
-
|
4 |
-
"RobertaModel"
|
5 |
-
],
|
6 |
-
"attention_probs_dropout_prob": 0.1,
|
7 |
-
"bos_token_id": 0,
|
8 |
-
"classifier_dropout": null,
|
9 |
-
"eos_token_id": 2,
|
10 |
-
"finetuning_task": "ner",
|
11 |
-
"gradient_checkpointing": false,
|
12 |
-
"hidden_act": "gelu",
|
13 |
-
"hidden_dropout_prob": 0.1,
|
14 |
-
"hidden_size": 768,
|
15 |
-
"id2label": {
|
16 |
-
"0": "O",
|
17 |
-
"1": "B-PER",
|
18 |
-
"2": "I-PER",
|
19 |
-
"3": "B-ORG",
|
20 |
-
"4": "I-ORG",
|
21 |
-
"5": "B-LOC",
|
22 |
-
"6": "I-LOC",
|
23 |
-
"7": "B-MISC",
|
24 |
-
"8": "I-MISC"
|
25 |
-
},
|
26 |
-
"initializer_range": 0.02,
|
27 |
-
"intermediate_size": 3072,
|
28 |
-
"label2id": {
|
29 |
-
"B-LOC": 5,
|
30 |
-
"B-MISC": 7,
|
31 |
-
"B-ORG": 3,
|
32 |
-
"B-PER": 1,
|
33 |
-
"I-LOC": 6,
|
34 |
-
"I-MISC": 8,
|
35 |
-
"I-ORG": 4,
|
36 |
-
"I-PER": 2,
|
37 |
-
"O": 0
|
38 |
-
},
|
39 |
-
"layer_norm_eps": 1e-05,
|
40 |
-
"max_position_embeddings": 514,
|
41 |
-
"model_type": "roberta",
|
42 |
-
"num_attention_heads": 12,
|
43 |
-
"num_hidden_layers": 12,
|
44 |
-
"pad_token_id": 1,
|
45 |
-
"position_embedding_type": "absolute",
|
46 |
-
"torch_dtype": "float32",
|
47 |
-
"transformers_version": "4.15.0",
|
48 |
-
"type_vocab_size": 1,
|
49 |
-
"use_cache": true,
|
50 |
-
"vocab_size": 50264
|
51 |
-
}
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d35a1a372e23da813f2d4e9c7fcb07eaeb5022857617fa9c12fc0dbad20f04f2
|
3 |
+
size 1256
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:767ca4c288d62426b9712fb70b230db7e78b77ae850d0f325198f0b361f5c13b
|
3 |
+
size 271
|
special_tokens_map.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c611b1f7d416eb001ee4f293d903ea8c88e703463f1d403f1866a0352743fd00
|
3 |
+
size 772
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:abef51df8e357559d0f1eb3213621a11c2984d640f65dce953e4aba1debcb77f
|
3 |
+
size 1508651
|
tokenizer_config.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:34441ea75c71dec47663c8193a54891302b53560d20c68d62fdcd884279e501d
|
3 |
+
size 1145
|
train_results.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:812a7c0a5fe27b04ac426c29086051e2a6e41a7ba548299468e77004af9c71aa
|
3 |
+
size 197
|
vocab.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a9d4ff71e32998a10570dadce36179053a7086a1638b402e65ae85a320242f9
|
3 |
+
size 874618
|