MoritzLaurer
commited on
Commit
•
e911c39
1
Parent(s):
f359ecc
from local
Browse files- config.json +72 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- trainer_state.json +104 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilroberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "Anti-Disinformation Measures",
|
15 |
+
"1": "Closure and Regulation of Schools",
|
16 |
+
"10": "Lockdown",
|
17 |
+
"11": "New Task Force, Bureau or Administrative Configuration",
|
18 |
+
"12": "Other Policy Not Listed Above",
|
19 |
+
"13": "Public Awareness Measures",
|
20 |
+
"14": "Quarantine",
|
21 |
+
"15": "Restriction and Regulation of Businesses",
|
22 |
+
"16": "Restriction and Regulation of Government Services",
|
23 |
+
"17": "Restrictions of Mass Gatherings",
|
24 |
+
"18": "Social Distancing",
|
25 |
+
"19": "COVID-19 Vaccines",
|
26 |
+
"2": "Curfew",
|
27 |
+
"20": "Other",
|
28 |
+
"3": "Declaration of Emergency",
|
29 |
+
"4": "External Border Restrictions",
|
30 |
+
"5": "Health Monitoring",
|
31 |
+
"6": "Health Resources",
|
32 |
+
"7": "Health Testing",
|
33 |
+
"8": "Hygiene",
|
34 |
+
"9": "Internal Border Restrictions"
|
35 |
+
},
|
36 |
+
"initializer_range": 0.02,
|
37 |
+
"intermediate_size": 3072,
|
38 |
+
"label2id": {
|
39 |
+
"Anti-Disinformation Measures": 0,
|
40 |
+
"COVID-19 Vaccines": 19,
|
41 |
+
"Closure and Regulation of Schools": 1,
|
42 |
+
"Curfew": 2,
|
43 |
+
"Declaration of Emergency": 3,
|
44 |
+
"External Border Restrictions": 4,
|
45 |
+
"Health Monitoring": 5,
|
46 |
+
"Health Resources": 6,
|
47 |
+
"Health Testing": 7,
|
48 |
+
"Hygiene": 8,
|
49 |
+
"Internal Border Restrictions": 9,
|
50 |
+
"Lockdown": 10,
|
51 |
+
"New Task Force, Bureau or Administrative Configuration": 11,
|
52 |
+
"Other": 20,
|
53 |
+
"Other Policy Not Listed Above": 12,
|
54 |
+
"Public Awareness Measures": 13,
|
55 |
+
"Quarantine": 14,
|
56 |
+
"Restriction and Regulation of Businesses": 15,
|
57 |
+
"Restriction and Regulation of Government Services": 16,
|
58 |
+
"Restrictions of Mass Gatherings": 17,
|
59 |
+
"Social Distancing": 18
|
60 |
+
},
|
61 |
+
"layer_norm_eps": 1e-05,
|
62 |
+
"max_position_embeddings": 514,
|
63 |
+
"model_type": "roberta",
|
64 |
+
"num_attention_heads": 12,
|
65 |
+
"num_hidden_layers": 6,
|
66 |
+
"pad_token_id": 1,
|
67 |
+
"position_embedding_type": "absolute",
|
68 |
+
"transformers_version": "4.3.2",
|
69 |
+
"type_vocab_size": 1,
|
70 |
+
"use_cache": true,
|
71 |
+
"vocab_size": 50265
|
72 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9739c017981598faa45e6e015951db2c203f5cba23cbff4d4e4e650f0aec1452
|
3 |
+
size 328586297
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e5a6b6006fadfb00ee3dd5fcd118d0a822298975a84c198e00c3c0f7bc8a14a
|
3 |
+
size 623
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
1 |
+
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "name_or_path": "distilroberta-base"}
|
trainer_state.json
ADDED
@@ -0,0 +1,104 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.7558827552193487,
|
3 |
+
"best_model_checkpoint": "./results/coronanet_classi_roberta/checkpoint-3372",
|
4 |
+
"epoch": 4.0,
|
5 |
+
"global_step": 3372,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.59,
|
12 |
+
"learning_rate": 8.92132907519561e-05,
|
13 |
+
"loss": 1.7123,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_accuracy_balanced": 0.6744778154481599,
|
19 |
+
"eval_accuracy_not_balanced": 0.7375055613228533,
|
20 |
+
"eval_f1_macro": 0.6774596453859705,
|
21 |
+
"eval_f1_weighted": 0.7344846513012891,
|
22 |
+
"eval_loss": 0.8972207307815552,
|
23 |
+
"eval_precision": 0.7429861548781078,
|
24 |
+
"eval_recall": 0.7375055613228533,
|
25 |
+
"eval_runtime": 29.1161,
|
26 |
+
"eval_samples_per_second": 231.59,
|
27 |
+
"step": 843
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 1.19,
|
31 |
+
"learning_rate": 7.368172899151806e-05,
|
32 |
+
"loss": 0.8779,
|
33 |
+
"step": 1000
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 1.78,
|
37 |
+
"learning_rate": 5.815016723108002e-05,
|
38 |
+
"loss": 0.7389,
|
39 |
+
"step": 1500
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 2.0,
|
43 |
+
"eval_accuracy_balanced": 0.744417109661457,
|
44 |
+
"eval_accuracy_not_balanced": 0.7655346285036334,
|
45 |
+
"eval_f1_macro": 0.7393973656051112,
|
46 |
+
"eval_f1_weighted": 0.7626792308967099,
|
47 |
+
"eval_loss": 0.8118156790733337,
|
48 |
+
"eval_precision": 0.7652843843532866,
|
49 |
+
"eval_recall": 0.7655346285036334,
|
50 |
+
"eval_runtime": 29.1071,
|
51 |
+
"eval_samples_per_second": 231.661,
|
52 |
+
"step": 1686
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 2.37,
|
56 |
+
"learning_rate": 4.261860547064198e-05,
|
57 |
+
"loss": 0.5835,
|
58 |
+
"step": 2000
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 2.97,
|
62 |
+
"learning_rate": 2.708704371020394e-05,
|
63 |
+
"loss": 0.4919,
|
64 |
+
"step": 2500
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 3.0,
|
68 |
+
"eval_accuracy_balanced": 0.7503794754553327,
|
69 |
+
"eval_accuracy_not_balanced": 0.773987839240694,
|
70 |
+
"eval_f1_macro": 0.7470579664348881,
|
71 |
+
"eval_f1_weighted": 0.7724065863470936,
|
72 |
+
"eval_loss": 0.7920669913291931,
|
73 |
+
"eval_precision": 0.7736999040473431,
|
74 |
+
"eval_recall": 0.773987839240694,
|
75 |
+
"eval_runtime": 29.1029,
|
76 |
+
"eval_samples_per_second": 231.695,
|
77 |
+
"step": 2529
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"epoch": 3.56,
|
81 |
+
"learning_rate": 1.15554819497659e-05,
|
82 |
+
"loss": 0.33,
|
83 |
+
"step": 3000
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 4.0,
|
87 |
+
"eval_accuracy_balanced": 0.7558827552193487,
|
88 |
+
"eval_accuracy_not_balanced": 0.7773987839240694,
|
89 |
+
"eval_f1_macro": 0.7509844357682027,
|
90 |
+
"eval_f1_weighted": 0.7760847284277537,
|
91 |
+
"eval_loss": 0.853062629699707,
|
92 |
+
"eval_precision": 0.7759580640894472,
|
93 |
+
"eval_recall": 0.7773987839240694,
|
94 |
+
"eval_runtime": 29.115,
|
95 |
+
"eval_samples_per_second": 231.599,
|
96 |
+
"step": 3372
|
97 |
+
}
|
98 |
+
],
|
99 |
+
"max_steps": 3372,
|
100 |
+
"num_train_epochs": 4,
|
101 |
+
"total_flos": 27219994048880640,
|
102 |
+
"trial_name": null,
|
103 |
+
"trial_params": null
|
104 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:91022129e920b39082d6cea43f8780a688e8dca84ef94c74574eb920b12fb698
|
3 |
+
size 2159
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|