Upload 12 files
Browse files- README.md +62 -0
- all_results.json +14 -0
- config.json +37 -0
- eval_results.json +9 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- train_results.json +8 -0
- trainer_state.json +70 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- accuracy
|
7 |
+
model-index:
|
8 |
+
- name: blinding
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# blinding
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [michiyasunaga/BioLinkBERT-base](https://huggingface.co/michiyasunaga/BioLinkBERT-base) on an unknown dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.7158
|
20 |
+
- Accuracy: 0.6842
|
21 |
+
|
22 |
+
## Model description
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Intended uses & limitations
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training and evaluation data
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training procedure
|
35 |
+
|
36 |
+
### Training hyperparameters
|
37 |
+
|
38 |
+
The following hyperparameters were used during training:
|
39 |
+
- learning_rate: 5e-05
|
40 |
+
- train_batch_size: 8
|
41 |
+
- eval_batch_size: 16
|
42 |
+
- seed: 42
|
43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
+
- lr_scheduler_type: linear
|
45 |
+
- lr_scheduler_warmup_ratio: 0.1
|
46 |
+
- num_epochs: 6.0
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
51 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
52 |
+
| 0.9949 | 2.0 | 20 | 0.9573 | 0.4737 |
|
53 |
+
| 0.5907 | 4.0 | 40 | 0.9047 | 0.5789 |
|
54 |
+
| 0.2675 | 6.0 | 60 | 0.7158 | 0.6842 |
|
55 |
+
|
56 |
+
|
57 |
+
### Framework versions
|
58 |
+
|
59 |
+
- Transformers 4.26.0.dev0
|
60 |
+
- Pytorch 1.13.0+cu116
|
61 |
+
- Datasets 2.8.0
|
62 |
+
- Tokenizers 0.13.2
|
all_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 6.0,
|
3 |
+
"eval_accuracy": 0.6842105388641357,
|
4 |
+
"eval_loss": 0.7158014178276062,
|
5 |
+
"eval_runtime": 0.6843,
|
6 |
+
"eval_samples": 19,
|
7 |
+
"eval_samples_per_second": 27.765,
|
8 |
+
"eval_steps_per_second": 2.923,
|
9 |
+
"train_loss": 0.617707633972168,
|
10 |
+
"train_runtime": 43.1317,
|
11 |
+
"train_samples": 75,
|
12 |
+
"train_samples_per_second": 10.433,
|
13 |
+
"train_steps_per_second": 1.391
|
14 |
+
}
|
config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "michiyasunaga/BioLinkBERT-base",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "blinded",
|
14 |
+
"1": "unblinded",
|
15 |
+
"2": "unknown"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"label2id": {
|
20 |
+
"blinded": 0,
|
21 |
+
"unblinded": 1,
|
22 |
+
"unknown": 2
|
23 |
+
},
|
24 |
+
"layer_norm_eps": 1e-12,
|
25 |
+
"max_position_embeddings": 512,
|
26 |
+
"model_type": "bert",
|
27 |
+
"num_attention_heads": 12,
|
28 |
+
"num_hidden_layers": 12,
|
29 |
+
"pad_token_id": 0,
|
30 |
+
"position_embedding_type": "absolute",
|
31 |
+
"problem_type": "single_label_classification",
|
32 |
+
"torch_dtype": "float32",
|
33 |
+
"transformers_version": "4.26.0.dev0",
|
34 |
+
"type_vocab_size": 2,
|
35 |
+
"use_cache": true,
|
36 |
+
"vocab_size": 28895
|
37 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 6.0,
|
3 |
+
"eval_accuracy": 0.6842105388641357,
|
4 |
+
"eval_loss": 0.7158014178276062,
|
5 |
+
"eval_runtime": 0.6843,
|
6 |
+
"eval_samples": 19,
|
7 |
+
"eval_samples_per_second": 27.765,
|
8 |
+
"eval_steps_per_second": 2.923
|
9 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a134ad3139d0541044b21a3a8862cce29dc06ac32ca03004850fa4d4ed2d587
|
3 |
+
size 433012853
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_basic_tokenize": true,
|
4 |
+
"do_lower_case": true,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"model_max_length": 1000000000000000019884624838656,
|
7 |
+
"name_or_path": "michiyasunaga/BioLinkBERT-base",
|
8 |
+
"never_split": null,
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"sep_token": "[SEP]",
|
11 |
+
"special_tokens_map_file": null,
|
12 |
+
"strip_accents": null,
|
13 |
+
"tokenize_chinese_chars": true,
|
14 |
+
"tokenizer_class": "BertTokenizer",
|
15 |
+
"unk_token": "[UNK]"
|
16 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 6.0,
|
3 |
+
"train_loss": 0.617707633972168,
|
4 |
+
"train_runtime": 43.1317,
|
5 |
+
"train_samples": 75,
|
6 |
+
"train_samples_per_second": 10.433,
|
7 |
+
"train_steps_per_second": 1.391
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 6.0,
|
5 |
+
"global_step": 60,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 2.0,
|
12 |
+
"learning_rate": 3.7037037037037037e-05,
|
13 |
+
"loss": 0.9949,
|
14 |
+
"step": 20
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 2.0,
|
18 |
+
"eval_accuracy": 0.4736842215061188,
|
19 |
+
"eval_loss": 0.957302987575531,
|
20 |
+
"eval_runtime": 0.5922,
|
21 |
+
"eval_samples_per_second": 32.083,
|
22 |
+
"eval_steps_per_second": 3.377,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 4.0,
|
27 |
+
"learning_rate": 1.8518518518518518e-05,
|
28 |
+
"loss": 0.5907,
|
29 |
+
"step": 40
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 4.0,
|
33 |
+
"eval_accuracy": 0.5789473652839661,
|
34 |
+
"eval_loss": 0.9047484397888184,
|
35 |
+
"eval_runtime": 0.6154,
|
36 |
+
"eval_samples_per_second": 30.876,
|
37 |
+
"eval_steps_per_second": 3.25,
|
38 |
+
"step": 40
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 6.0,
|
42 |
+
"learning_rate": 0.0,
|
43 |
+
"loss": 0.2675,
|
44 |
+
"step": 60
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 6.0,
|
48 |
+
"eval_accuracy": 0.6842105388641357,
|
49 |
+
"eval_loss": 0.7158014178276062,
|
50 |
+
"eval_runtime": 0.6188,
|
51 |
+
"eval_samples_per_second": 30.703,
|
52 |
+
"eval_steps_per_second": 3.232,
|
53 |
+
"step": 60
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 6.0,
|
57 |
+
"step": 60,
|
58 |
+
"total_flos": 118401037977600.0,
|
59 |
+
"train_loss": 0.617707633972168,
|
60 |
+
"train_runtime": 43.1317,
|
61 |
+
"train_samples_per_second": 10.433,
|
62 |
+
"train_steps_per_second": 1.391
|
63 |
+
}
|
64 |
+
],
|
65 |
+
"max_steps": 60,
|
66 |
+
"num_train_epochs": 6,
|
67 |
+
"total_flos": 118401037977600.0,
|
68 |
+
"trial_name": null,
|
69 |
+
"trial_params": null
|
70 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:59c38e362ed223d42af30e64b05a9b91d45606b1bf95b398d5af7d39fa69efa4
|
3 |
+
size 3515
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|