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 +196 -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:e8070acd6beb99b5eb0fddf6eacf1e53073580fea284999a74938450251c6c7e
|
3 |
+
size 871267045
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd38c0afd5baee82170b184ad306b1ed769a5f96cb2c1abf45e7bf9100993e53
|
3 |
+
size 435659249
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:553ae272f829ad08d2ac07a4f66f9166cfaccce3ed45f457287813ee5a8abb20
|
3 |
+
size 14503
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6924d775943af8347366bfe0de14e5f7df0338deabc562b7460c30c538b9c8f0
|
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 +1,196 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.03207630664110184,
|
3 |
+
"best_model_checkpoint": "data/models/anatomical/final/checkpoint-14152",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"global_step": 14152,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.04,
|
12 |
+
"learning_rate": 5.394676819942119e-05,
|
13 |
+
"loss": 0.1026,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.07,
|
18 |
+
"learning_rate": 5.1970985596160816e-05,
|
19 |
+
"loss": 0.0751,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.11,
|
24 |
+
"learning_rate": 4.999520299290044e-05,
|
25 |
+
"loss": 0.0684,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.14,
|
30 |
+
"learning_rate": 4.801942038964007e-05,
|
31 |
+
"loss": 0.0695,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.18,
|
36 |
+
"learning_rate": 4.6043637786379705e-05,
|
37 |
+
"loss": 0.0657,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.21,
|
42 |
+
"learning_rate": 4.406785518311933e-05,
|
43 |
+
"loss": 0.0558,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.25,
|
48 |
+
"learning_rate": 4.2092072579858955e-05,
|
49 |
+
"loss": 0.0603,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.28,
|
54 |
+
"learning_rate": 4.011628997659859e-05,
|
55 |
+
"loss": 0.0521,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.32,
|
60 |
+
"learning_rate": 3.814050737333821e-05,
|
61 |
+
"loss": 0.0527,
|
62 |
+
"step": 4500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.35,
|
66 |
+
"learning_rate": 3.6164724770077844e-05,
|
67 |
+
"loss": 0.055,
|
68 |
+
"step": 5000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.39,
|
72 |
+
"learning_rate": 3.418894216681747e-05,
|
73 |
+
"loss": 0.0523,
|
74 |
+
"step": 5500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.42,
|
78 |
+
"learning_rate": 3.2213159563557095e-05,
|
79 |
+
"loss": 0.055,
|
80 |
+
"step": 6000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.46,
|
84 |
+
"learning_rate": 3.0237376960296726e-05,
|
85 |
+
"loss": 0.0516,
|
86 |
+
"step": 6500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.49,
|
90 |
+
"learning_rate": 2.826159435703636e-05,
|
91 |
+
"loss": 0.053,
|
92 |
+
"step": 7000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.53,
|
96 |
+
"learning_rate": 2.6285811753775984e-05,
|
97 |
+
"loss": 0.0518,
|
98 |
+
"step": 7500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.57,
|
102 |
+
"learning_rate": 2.4310029150515615e-05,
|
103 |
+
"loss": 0.0422,
|
104 |
+
"step": 8000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.6,
|
108 |
+
"learning_rate": 2.233424654725524e-05,
|
109 |
+
"loss": 0.0474,
|
110 |
+
"step": 8500
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.64,
|
114 |
+
"learning_rate": 2.035846394399487e-05,
|
115 |
+
"loss": 0.0479,
|
116 |
+
"step": 9000
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.67,
|
120 |
+
"learning_rate": 1.8382681340734498e-05,
|
121 |
+
"loss": 0.0491,
|
122 |
+
"step": 9500
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.71,
|
126 |
+
"learning_rate": 1.6406898737474126e-05,
|
127 |
+
"loss": 0.0449,
|
128 |
+
"step": 10000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.74,
|
132 |
+
"learning_rate": 1.4431116134213753e-05,
|
133 |
+
"loss": 0.0482,
|
134 |
+
"step": 10500
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.78,
|
138 |
+
"learning_rate": 1.2455333530953383e-05,
|
139 |
+
"loss": 0.0445,
|
140 |
+
"step": 11000
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.81,
|
144 |
+
"learning_rate": 1.0479550927693012e-05,
|
145 |
+
"loss": 0.044,
|
146 |
+
"step": 11500
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.85,
|
150 |
+
"learning_rate": 8.50376832443264e-06,
|
151 |
+
"loss": 0.0361,
|
152 |
+
"step": 12000
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 0.88,
|
156 |
+
"learning_rate": 6.527985721172267e-06,
|
157 |
+
"loss": 0.0445,
|
158 |
+
"step": 12500
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.92,
|
162 |
+
"learning_rate": 4.552203117911897e-06,
|
163 |
+
"loss": 0.0406,
|
164 |
+
"step": 13000
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.95,
|
168 |
+
"learning_rate": 2.5764205146515243e-06,
|
169 |
+
"loss": 0.0433,
|
170 |
+
"step": 13500
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.99,
|
174 |
+
"learning_rate": 6.00637911391153e-07,
|
175 |
+
"loss": 0.0438,
|
176 |
+
"step": 14000
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 1.0,
|
180 |
+
"eval_accuracy": 0.9555555555555556,
|
181 |
+
"eval_f1": 0.0,
|
182 |
+
"eval_loss": 0.03207630664110184,
|
183 |
+
"eval_precision": 0.0,
|
184 |
+
"eval_recall": 0.0,
|
185 |
+
"eval_runtime": 1.4439,
|
186 |
+
"eval_samples_per_second": 0.693,
|
187 |
+
"eval_steps_per_second": 0.693,
|
188 |
+
"step": 14152
|
189 |
+
}
|
190 |
+
],
|
191 |
+
"max_steps": 14152,
|
192 |
+
"num_train_epochs": 1,
|
193 |
+
"total_flos": 1.4791620534239232e+16,
|
194 |
+
"trial_name": null,
|
195 |
+
"trial_params": null
|
196 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e06973ab205d56dc9e984f40dcd716c02e2fdf85afbe5f6c603edf5ca85bcb0
|
3 |
+
size 2671
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|