DimasikKurd
commited on
Commit
•
5c5041d
1
Parent(s):
5408d54
Training complete
Browse files- README.md +88 -0
- config.json +38 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- runs/May06_21-18-12_634985d315af/events.out.tfevents.1715030294.634985d315af.34.0 +3 -0
- runs/May06_21-21-30_634985d315af/events.out.tfevents.1715030492.634985d315af.34.1 +3 -0
- runs/May06_21-21-30_634985d315af/events.out.tfevents.1715031573.634985d315af.34.2 +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: DmitryPogrebnoy/MedRuRobertaLarge
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
- f1
|
10 |
+
- accuracy
|
11 |
+
model-index:
|
12 |
+
- name: MedRuRobertaLarge_pos
|
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 |
+
# MedRuRobertaLarge_pos
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [DmitryPogrebnoy/MedRuRobertaLarge](https://huggingface.co/DmitryPogrebnoy/MedRuRobertaLarge) on the None dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.4823
|
24 |
+
- Precision: 0.4746
|
25 |
+
- Recall: 0.5274
|
26 |
+
- F1: 0.4996
|
27 |
+
- Accuracy: 0.9031
|
28 |
+
|
29 |
+
## Model description
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Intended uses & limitations
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training and evaluation data
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Training procedure
|
42 |
+
|
43 |
+
### Training hyperparameters
|
44 |
+
|
45 |
+
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 5e-05
|
47 |
+
- train_batch_size: 4
|
48 |
+
- eval_batch_size: 8
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- num_epochs: 100
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
58 |
+
| No log | 1.0 | 50 | 0.6491 | 0.0 | 0.0 | 0.0 | 0.7598 |
|
59 |
+
| No log | 2.0 | 100 | 0.6401 | 0.0 | 0.0 | 0.0 | 0.7664 |
|
60 |
+
| No log | 3.0 | 150 | 0.4835 | 0.0195 | 0.0193 | 0.0194 | 0.8187 |
|
61 |
+
| No log | 4.0 | 200 | 0.4325 | 0.0790 | 0.1368 | 0.1001 | 0.8181 |
|
62 |
+
| No log | 5.0 | 250 | 0.3456 | 0.1653 | 0.2370 | 0.1948 | 0.8675 |
|
63 |
+
| No log | 6.0 | 300 | 0.3438 | 0.2128 | 0.2697 | 0.2379 | 0.8744 |
|
64 |
+
| No log | 7.0 | 350 | 0.3814 | 0.3415 | 0.2948 | 0.3164 | 0.8832 |
|
65 |
+
| No log | 8.0 | 400 | 0.3005 | 0.3026 | 0.3854 | 0.3390 | 0.8877 |
|
66 |
+
| No log | 9.0 | 450 | 0.2641 | 0.3718 | 0.5279 | 0.4363 | 0.8997 |
|
67 |
+
| 0.4044 | 10.0 | 500 | 0.2754 | 0.4036 | 0.5164 | 0.4531 | 0.9057 |
|
68 |
+
| 0.4044 | 11.0 | 550 | 0.3153 | 0.4041 | 0.6416 | 0.4959 | 0.8949 |
|
69 |
+
| 0.4044 | 12.0 | 600 | 0.3362 | 0.4428 | 0.5222 | 0.4792 | 0.9094 |
|
70 |
+
| 0.4044 | 13.0 | 650 | 0.3325 | 0.4433 | 0.5645 | 0.4966 | 0.9109 |
|
71 |
+
| 0.4044 | 14.0 | 700 | 0.2921 | 0.4320 | 0.5568 | 0.4865 | 0.9064 |
|
72 |
+
| 0.4044 | 15.0 | 750 | 0.3871 | 0.4630 | 0.5780 | 0.5141 | 0.9080 |
|
73 |
+
| 0.4044 | 16.0 | 800 | 0.3479 | 0.4218 | 0.6339 | 0.5065 | 0.8946 |
|
74 |
+
| 0.4044 | 17.0 | 850 | 0.3886 | 0.4914 | 0.6031 | 0.5415 | 0.9096 |
|
75 |
+
| 0.4044 | 18.0 | 900 | 0.5079 | 0.5108 | 0.5491 | 0.5292 | 0.9076 |
|
76 |
+
| 0.4044 | 19.0 | 950 | 0.3963 | 0.4344 | 0.6763 | 0.5290 | 0.8999 |
|
77 |
+
| 0.0912 | 20.0 | 1000 | 0.3845 | 0.5033 | 0.5915 | 0.5438 | 0.9145 |
|
78 |
+
| 0.0912 | 21.0 | 1050 | 0.5141 | 0.3986 | 0.4239 | 0.4108 | 0.8925 |
|
79 |
+
| 0.0912 | 22.0 | 1100 | 0.4587 | 0.4706 | 0.5395 | 0.5027 | 0.9028 |
|
80 |
+
| 0.0912 | 23.0 | 1150 | 0.4360 | 0.5017 | 0.5800 | 0.5380 | 0.9075 |
|
81 |
+
|
82 |
+
|
83 |
+
### Framework versions
|
84 |
+
|
85 |
+
- Transformers 4.38.2
|
86 |
+
- Pytorch 2.1.2
|
87 |
+
- Datasets 2.1.0
|
88 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "DmitryPogrebnoy/MedRuRobertaLarge",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 1024,
|
14 |
+
"id2label": {
|
15 |
+
"0": "O",
|
16 |
+
"1": "B-symp",
|
17 |
+
"2": "I-symp"
|
18 |
+
},
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"intermediate_size": 4096,
|
21 |
+
"label2id": {
|
22 |
+
"0": "O",
|
23 |
+
"1": "B-symp",
|
24 |
+
"2": "I-symp"
|
25 |
+
},
|
26 |
+
"layer_norm_eps": 1e-05,
|
27 |
+
"max_position_embeddings": 514,
|
28 |
+
"model_type": "roberta",
|
29 |
+
"num_attention_heads": 16,
|
30 |
+
"num_hidden_layers": 24,
|
31 |
+
"pad_token_id": 1,
|
32 |
+
"position_embedding_type": "absolute",
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.38.2",
|
35 |
+
"type_vocab_size": 1,
|
36 |
+
"use_cache": true,
|
37 |
+
"vocab_size": 50257
|
38 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed9f08356fd9aaf7dad36e296be9b75c573d69830fee50cc8be61906140b10ed
|
3 |
+
size 1417268116
|
runs/May06_21-18-12_634985d315af/events.out.tfevents.1715030294.634985d315af.34.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76986d83f30d9438ee2fe6813acd273709e88bdb1f0c4cb4de0dddfcd16c40a4
|
3 |
+
size 4815
|
runs/May06_21-21-30_634985d315af/events.out.tfevents.1715030492.634985d315af.34.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e652885cd5879253757e34bff6025062902bc986df3cd11c79c76bde66c27b5
|
3 |
+
size 16429
|
runs/May06_21-21-30_634985d315af/events.out.tfevents.1715031573.634985d315af.34.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e12948b7a573bfe8efb7e37b8217b2b870e4bd6461f5b63d0381cee55ea76bc6
|
3 |
+
size 560
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": true,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<pad>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<s>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"4": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": true,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"bos_token": "<s>",
|
46 |
+
"clean_up_tokenization_spaces": true,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"errors": "replace",
|
50 |
+
"mask_token": "<mask>",
|
51 |
+
"model_max_length": 1000000000000000019884624838656,
|
52 |
+
"pad_token": "<pad>",
|
53 |
+
"sep_token": "</s>",
|
54 |
+
"tokenizer_class": "RobertaTokenizer",
|
55 |
+
"trim_offsets": true,
|
56 |
+
"unk_token": "<unk>"
|
57 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c1fc6a97c14019c974f9fcc8e7a166f22f0b0234fd80d770e26cfbd82631799
|
3 |
+
size 4920
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|