StevenLimcorn
commited on
Commit
•
52b38b3
1
Parent(s):
842713f
Upload 9 files
Browse files- config.json +3 -4
- optimizer.pt +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- train_results.txt +3 -0
- trainer_state.json +138 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
CHANGED
@@ -1,10 +1,9 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "/content/
|
3 |
"architectures": [
|
4 |
"BertModel"
|
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,
|
@@ -18,8 +17,8 @@
|
|
18 |
"num_hidden_layers": 12,
|
19 |
"pad_token_id": 0,
|
20 |
"position_embedding_type": "absolute",
|
21 |
-
"transformers_version": "4.
|
22 |
"type_vocab_size": 2,
|
23 |
"use_cache": true,
|
24 |
"vocab_size": 30522
|
25 |
-
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/content/result/semeval-unsup-promcse-bert-base-uncased-semeval2015-laptops",
|
3 |
"architectures": [
|
4 |
"BertModel"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
|
|
7 |
"gradient_checkpointing": false,
|
8 |
"hidden_act": "gelu",
|
9 |
"hidden_dropout_prob": 0.1,
|
|
|
17 |
"num_hidden_layers": 12,
|
18 |
"pad_token_id": 0,
|
19 |
"position_embedding_type": "absolute",
|
20 |
+
"transformers_version": "4.2.1",
|
21 |
"type_vocab_size": 2,
|
22 |
"use_cache": true,
|
23 |
"vocab_size": 30522
|
24 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:70afa9b8aff03eebaeb6f20083af496d8633ba33d7f69dad8d12dcda27a74701
|
3 |
+
size 7086823
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:36f294259ee4a8e4af624f3563e52f50ac02165905a3b8e9bd9c16def52f1755
|
3 |
+
size 627
|
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_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": "YuxinJiang/unsup-promcse-bert-base-uncased", "do_basic_tokenize": true, "never_split": null}
|
train_results.txt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
epoch = 30.0
|
2 |
+
train_runtime = 918.2758
|
3 |
+
train_samples_per_second = 1.797
|
trainer_state.json
ADDED
@@ -0,0 +1,138 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8195012863483878,
|
3 |
+
"best_model_checkpoint": "/content/result/semeval-unsup-promcse-bert-base-uncased-semeval2015-laptops",
|
4 |
+
"epoch": 30.0,
|
5 |
+
"global_step": 1650,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 2.27,
|
12 |
+
"eval_avg_sts": 0.7759609902852005,
|
13 |
+
"eval_sickr_spearman": 0.7324206942220131,
|
14 |
+
"eval_stsb_spearman": 0.8195012863483878,
|
15 |
+
"step": 125
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 4.55,
|
19 |
+
"eval_avg_sts": 0.7784093546258903,
|
20 |
+
"eval_sickr_spearman": 0.7452715595050845,
|
21 |
+
"eval_stsb_spearman": 0.8115471497466962,
|
22 |
+
"step": 250
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"epoch": 6.82,
|
26 |
+
"eval_avg_sts": 0.7707664035200109,
|
27 |
+
"eval_sickr_spearman": 0.7368935905434373,
|
28 |
+
"eval_stsb_spearman": 0.8046392164965845,
|
29 |
+
"step": 375
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 9.09,
|
33 |
+
"learning_rate": 0.02090909090909091,
|
34 |
+
"loss": 0.0008,
|
35 |
+
"step": 500
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 9.09,
|
39 |
+
"eval_avg_sts": 0.7691853718561973,
|
40 |
+
"eval_sickr_spearman": 0.7409284912508475,
|
41 |
+
"eval_stsb_spearman": 0.7974422524615471,
|
42 |
+
"step": 500
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 11.36,
|
46 |
+
"eval_avg_sts": 0.7761816506183419,
|
47 |
+
"eval_sickr_spearman": 0.7335257457727998,
|
48 |
+
"eval_stsb_spearman": 0.8188375554638838,
|
49 |
+
"step": 625
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"epoch": 13.64,
|
53 |
+
"eval_avg_sts": 0.7717556783657262,
|
54 |
+
"eval_sickr_spearman": 0.7335799728863233,
|
55 |
+
"eval_stsb_spearman": 0.8099313838451292,
|
56 |
+
"step": 750
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 15.91,
|
60 |
+
"eval_avg_sts": 0.7667458747207212,
|
61 |
+
"eval_sickr_spearman": 0.7327574883052972,
|
62 |
+
"eval_stsb_spearman": 0.8007342611361452,
|
63 |
+
"step": 875
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 18.18,
|
67 |
+
"learning_rate": 0.011818181818181818,
|
68 |
+
"loss": 0.0008,
|
69 |
+
"step": 1000
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 18.18,
|
73 |
+
"eval_avg_sts": 0.7711807960175332,
|
74 |
+
"eval_sickr_spearman": 0.7355917555700587,
|
75 |
+
"eval_stsb_spearman": 0.8067698364650077,
|
76 |
+
"step": 1000
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 20.45,
|
80 |
+
"eval_avg_sts": 0.7704725110642088,
|
81 |
+
"eval_sickr_spearman": 0.7421104405950365,
|
82 |
+
"eval_stsb_spearman": 0.7988345815333809,
|
83 |
+
"step": 1125
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 22.73,
|
87 |
+
"eval_avg_sts": 0.774103481691444,
|
88 |
+
"eval_sickr_spearman": 0.7408106229279183,
|
89 |
+
"eval_stsb_spearman": 0.8073963404549698,
|
90 |
+
"step": 1250
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 25.0,
|
94 |
+
"eval_avg_sts": 0.7741793991755762,
|
95 |
+
"eval_sickr_spearman": 0.7403053837718908,
|
96 |
+
"eval_stsb_spearman": 0.8080534145792616,
|
97 |
+
"step": 1375
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 25.0,
|
101 |
+
"eval_avg_sts": 0.7741793991755762,
|
102 |
+
"eval_sickr_spearman": 0.7403053837718908,
|
103 |
+
"eval_stsb_spearman": 0.8080534145792616,
|
104 |
+
"step": 1375
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 27.27,
|
108 |
+
"learning_rate": 0.002727272727272727,
|
109 |
+
"loss": 0.0003,
|
110 |
+
"step": 1500
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 27.27,
|
114 |
+
"eval_avg_sts": 0.7736536306207098,
|
115 |
+
"eval_sickr_spearman": 0.7402983712310808,
|
116 |
+
"eval_stsb_spearman": 0.8070088900103389,
|
117 |
+
"step": 1500
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 29.55,
|
121 |
+
"eval_avg_sts": 0.7730365480911703,
|
122 |
+
"eval_sickr_spearman": 0.7408807003049165,
|
123 |
+
"eval_stsb_spearman": 0.805192395877424,
|
124 |
+
"step": 1625
|
125 |
+
},
|
126 |
+
{
|
127 |
+
"epoch": 30.0,
|
128 |
+
"step": 1650,
|
129 |
+
"train_runtime": 918.2758,
|
130 |
+
"train_samples_per_second": 1.797
|
131 |
+
}
|
132 |
+
],
|
133 |
+
"max_steps": 1650,
|
134 |
+
"num_train_epochs": 30,
|
135 |
+
"total_flos": 2195013914127360,
|
136 |
+
"trial_name": null,
|
137 |
+
"trial_params": null
|
138 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db65998701304a7e8aa757bfc1f9f2991ce4d1320aac8108416eeafdde1d6ad2
|
3 |
+
size 2107
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|