Upload 11 files
Browse files- config.json +35 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +100 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"gradient_checkpointing": false,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": "O",
|
13 |
+
"1": "B",
|
14 |
+
"2": "I"
|
15 |
+
},
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 3072,
|
18 |
+
"label2id": {
|
19 |
+
"B": "1",
|
20 |
+
"I": "2",
|
21 |
+
"O": "0"
|
22 |
+
},
|
23 |
+
"layer_norm_eps": 1e-12,
|
24 |
+
"max_position_embeddings": 512,
|
25 |
+
"model_type": "bert",
|
26 |
+
"num_attention_heads": 12,
|
27 |
+
"num_hidden_layers": 12,
|
28 |
+
"pad_token_id": 0,
|
29 |
+
"position_embedding_type": "absolute",
|
30 |
+
"torch_dtype": "float32",
|
31 |
+
"transformers_version": "4.9.0",
|
32 |
+
"type_vocab_size": 2,
|
33 |
+
"use_cache": true,
|
34 |
+
"vocab_size": 30522
|
35 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f5a212b28955a36a70cf3580b62a69ccc94924473a66f22679654e2e4b243794
|
3 |
+
size 871267045
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7cae9454d709bb598b6005b01622ecf85b8a86aee85a6c81a78b9ced54b75c5
|
3 |
+
size 435659249
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14148820285ef194fede3d4908fbbebd51919988409312b1d1601542ee1fc2a6
|
3 |
+
size 14503
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60606d9200b936666fbaf0ce08352c28dfc7629786b462b5b03c74267492de3b
|
3 |
+
size 623
|
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
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}
|
trainer_state.json
ADDED
@@ -0,0 +1,100 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.010058270767331123,
|
3 |
+
"best_model_checkpoint": "data/models/cell_line/final/checkpoint-6129",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"global_step": 6129,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.08,
|
12 |
+
"learning_rate": 4.9704237796630406e-05,
|
13 |
+
"loss": 0.0765,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.16,
|
18 |
+
"learning_rate": 4.528922289197324e-05,
|
19 |
+
"loss": 0.0535,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.24,
|
24 |
+
"learning_rate": 4.087420798731607e-05,
|
25 |
+
"loss": 0.0458,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.33,
|
30 |
+
"learning_rate": 3.64591930826589e-05,
|
31 |
+
"loss": 0.0444,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.41,
|
36 |
+
"learning_rate": 3.204417817800173e-05,
|
37 |
+
"loss": 0.0423,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.49,
|
42 |
+
"learning_rate": 2.7629163273344564e-05,
|
43 |
+
"loss": 0.0428,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.57,
|
48 |
+
"learning_rate": 2.3214148368687394e-05,
|
49 |
+
"loss": 0.0373,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.65,
|
54 |
+
"learning_rate": 1.8799133464030227e-05,
|
55 |
+
"loss": 0.0345,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.73,
|
60 |
+
"learning_rate": 1.4384118559373056e-05,
|
61 |
+
"loss": 0.0276,
|
62 |
+
"step": 4500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.82,
|
66 |
+
"learning_rate": 9.969103654715888e-06,
|
67 |
+
"loss": 0.0297,
|
68 |
+
"step": 5000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.9,
|
72 |
+
"learning_rate": 5.554088750058719e-06,
|
73 |
+
"loss": 0.0282,
|
74 |
+
"step": 5500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.98,
|
78 |
+
"learning_rate": 1.1390738454015496e-06,
|
79 |
+
"loss": 0.0259,
|
80 |
+
"step": 6000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 1.0,
|
84 |
+
"eval_accuracy": 1.0,
|
85 |
+
"eval_f1": 1.0,
|
86 |
+
"eval_loss": 0.010058270767331123,
|
87 |
+
"eval_precision": 1.0,
|
88 |
+
"eval_recall": 1.0,
|
89 |
+
"eval_runtime": 1.3499,
|
90 |
+
"eval_samples_per_second": 0.741,
|
91 |
+
"eval_steps_per_second": 0.741,
|
92 |
+
"step": 6129
|
93 |
+
}
|
94 |
+
],
|
95 |
+
"max_steps": 6129,
|
96 |
+
"num_train_epochs": 1,
|
97 |
+
"total_flos": 6406009203953664.0,
|
98 |
+
"trial_name": null,
|
99 |
+
"trial_params": null
|
100 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94ea8d5cae346fe53972721f1963ddbf4d201c2d1e709de582e21cc8d528d349
|
3 |
+
size 2671
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|