Commit
•
b1c5630
1
Parent(s):
cf194dc
Upload 9 files
Browse files- config.json +39 -0
- pytorch_model.bin +3 -0
- run_config.json +47 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- trainer_state.json +163 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dbmdz/bert-base-german-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": "LABEL_0",
|
13 |
+
"1": "LABEL_1",
|
14 |
+
"2": "LABEL_2",
|
15 |
+
"3": "LABEL_3"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"label2id": {
|
20 |
+
"LABEL_0": 0,
|
21 |
+
"LABEL_1": 1,
|
22 |
+
"LABEL_2": 2,
|
23 |
+
"LABEL_3": 3
|
24 |
+
},
|
25 |
+
"layer_norm_eps": 1e-12,
|
26 |
+
"max_position_embeddings": 512,
|
27 |
+
"model_type": "bert",
|
28 |
+
"num_attention_heads": 12,
|
29 |
+
"num_hidden_layers": 12,
|
30 |
+
"output_past": true,
|
31 |
+
"pad_token_id": 0,
|
32 |
+
"position_embedding_type": "absolute",
|
33 |
+
"problem_type": "single_label_classification",
|
34 |
+
"torch_dtype": "float32",
|
35 |
+
"transformers_version": "4.23.1",
|
36 |
+
"type_vocab_size": 2,
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 31102
|
39 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f83b9c46c86ba410d5915ee9bf0fb539cc727836e56432c9bf9e0927c4aba246
|
3 |
+
size 439794029
|
run_config.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_CHeeSEArguments": "CHeeSEArguments",
|
3 |
+
"model_name_or_path": "dbmdz/bert-base-german-cased",
|
4 |
+
"dataset_path": "./dataset.py",
|
5 |
+
"metric_path": "./metric.py",
|
6 |
+
"task": "stance_detection",
|
7 |
+
"first_sentence_inputs": [
|
8 |
+
"question"
|
9 |
+
],
|
10 |
+
"second_sentence_inputs": [
|
11 |
+
"title",
|
12 |
+
"snippet",
|
13 |
+
"paragraphs"
|
14 |
+
],
|
15 |
+
"labels_to_predict": [
|
16 |
+
"stance"
|
17 |
+
],
|
18 |
+
"_CHeeSETrainingArguments": "CHeeSETrainingArguments",
|
19 |
+
"do_train": true,
|
20 |
+
"do_eval": true,
|
21 |
+
"do_predict": true,
|
22 |
+
"do_cross_validation": false,
|
23 |
+
"output_dir": "/netscratch/schnitzler/bert",
|
24 |
+
"logging_dir": "/netscratch/schnitzler/bert",
|
25 |
+
"save_total_limit": 2,
|
26 |
+
"log_to_file": true,
|
27 |
+
"logging_strategy": "steps",
|
28 |
+
"logging_steps": 50,
|
29 |
+
"cross_validation_folds": 5,
|
30 |
+
"num_train_epochs": 4,
|
31 |
+
"per_device_train_batch_size": 8,
|
32 |
+
"per_device_eval_batch_size": 8,
|
33 |
+
"fp16": false,
|
34 |
+
"learning_rate": 3e-05,
|
35 |
+
"prediction_csv_kwargs": {
|
36 |
+
"index": false
|
37 |
+
},
|
38 |
+
"prediction_columns_to_include": [
|
39 |
+
"title",
|
40 |
+
"snippet",
|
41 |
+
"paragraphs",
|
42 |
+
"question",
|
43 |
+
"labels",
|
44 |
+
"stance"
|
45 |
+
],
|
46 |
+
"overwrite_output_dir": true
|
47 |
+
}
|
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": false,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"max_len": 512,
|
7 |
+
"name_or_path": "dbmdz/bert-base-german-cased",
|
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 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,163 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.0,
|
5 |
+
"global_step": 1196,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.17,
|
12 |
+
"learning_rate": 2.874581939799331e-05,
|
13 |
+
"loss": 1.1476,
|
14 |
+
"step": 50
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.33,
|
18 |
+
"learning_rate": 2.7491638795986622e-05,
|
19 |
+
"loss": 0.9973,
|
20 |
+
"step": 100
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.5,
|
24 |
+
"learning_rate": 2.6237458193979933e-05,
|
25 |
+
"loss": 1.0316,
|
26 |
+
"step": 150
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.67,
|
30 |
+
"learning_rate": 2.4983277591973243e-05,
|
31 |
+
"loss": 0.9801,
|
32 |
+
"step": 200
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.84,
|
36 |
+
"learning_rate": 2.3729096989966557e-05,
|
37 |
+
"loss": 0.9947,
|
38 |
+
"step": 250
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 1.0,
|
42 |
+
"learning_rate": 2.2474916387959865e-05,
|
43 |
+
"loss": 0.9882,
|
44 |
+
"step": 300
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 1.17,
|
48 |
+
"learning_rate": 2.122073578595318e-05,
|
49 |
+
"loss": 0.8896,
|
50 |
+
"step": 350
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 1.34,
|
54 |
+
"learning_rate": 1.996655518394649e-05,
|
55 |
+
"loss": 0.7913,
|
56 |
+
"step": 400
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 1.51,
|
60 |
+
"learning_rate": 1.87123745819398e-05,
|
61 |
+
"loss": 0.8249,
|
62 |
+
"step": 450
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 1.67,
|
66 |
+
"learning_rate": 1.745819397993311e-05,
|
67 |
+
"loss": 0.7808,
|
68 |
+
"step": 500
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 1.84,
|
72 |
+
"learning_rate": 1.620401337792642e-05,
|
73 |
+
"loss": 0.7632,
|
74 |
+
"step": 550
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 2.01,
|
78 |
+
"learning_rate": 1.4949832775919733e-05,
|
79 |
+
"loss": 0.7577,
|
80 |
+
"step": 600
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 2.17,
|
84 |
+
"learning_rate": 1.3695652173913042e-05,
|
85 |
+
"loss": 0.6454,
|
86 |
+
"step": 650
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 2.34,
|
90 |
+
"learning_rate": 1.2441471571906355e-05,
|
91 |
+
"loss": 0.5908,
|
92 |
+
"step": 700
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 2.51,
|
96 |
+
"learning_rate": 1.1187290969899665e-05,
|
97 |
+
"loss": 0.6114,
|
98 |
+
"step": 750
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 2.68,
|
102 |
+
"learning_rate": 9.933110367892978e-06,
|
103 |
+
"loss": 0.6383,
|
104 |
+
"step": 800
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 2.84,
|
108 |
+
"learning_rate": 8.678929765886286e-06,
|
109 |
+
"loss": 0.6207,
|
110 |
+
"step": 850
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 3.01,
|
114 |
+
"learning_rate": 7.424749163879599e-06,
|
115 |
+
"loss": 0.5649,
|
116 |
+
"step": 900
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 3.18,
|
120 |
+
"learning_rate": 6.17056856187291e-06,
|
121 |
+
"loss": 0.4894,
|
122 |
+
"step": 950
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 3.34,
|
126 |
+
"learning_rate": 4.916387959866221e-06,
|
127 |
+
"loss": 0.4434,
|
128 |
+
"step": 1000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 3.51,
|
132 |
+
"learning_rate": 3.662207357859532e-06,
|
133 |
+
"loss": 0.3991,
|
134 |
+
"step": 1050
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 3.68,
|
138 |
+
"learning_rate": 2.408026755852843e-06,
|
139 |
+
"loss": 0.4938,
|
140 |
+
"step": 1100
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 3.85,
|
144 |
+
"learning_rate": 1.153846153846154e-06,
|
145 |
+
"loss": 0.3628,
|
146 |
+
"step": 1150
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 4.0,
|
150 |
+
"step": 1196,
|
151 |
+
"total_flos": 2517491783958528.0,
|
152 |
+
"train_loss": 0.7212204247414069,
|
153 |
+
"train_runtime": 362.6132,
|
154 |
+
"train_samples_per_second": 26.386,
|
155 |
+
"train_steps_per_second": 3.298
|
156 |
+
}
|
157 |
+
],
|
158 |
+
"max_steps": 1196,
|
159 |
+
"num_train_epochs": 4,
|
160 |
+
"total_flos": 2517491783958528.0,
|
161 |
+
"trial_name": null,
|
162 |
+
"trial_params": null
|
163 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:67333a28e4f00c43e9463296a39729f46fe5c9db2cf32d65e5509c6350eceec2
|
3 |
+
size 3631
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|