StevenLimcorn
commited on
Commit
•
81a6bc8
1
Parent(s):
095b8c4
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 +172 -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-semeval2016-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 sha256:789dc68dbe5560d3c092719952d7fb37e3e809230ed08b6b24b0141b4966f6b1
|
3 |
+
size 7086823
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fcfebd507a1cf0e5894681cde27fa4055b16ee4feec723135b66f42d66d3eff1
|
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 = 1196.069
|
3 |
+
train_samples_per_second = 1.981
|
trainer_state.json
ADDED
@@ -0,0 +1,172 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.7913689415224279,
|
3 |
+
"best_model_checkpoint": "/content/result/semeval-unsup-promcse-bert-base-uncased-semeval2016-laptops",
|
4 |
+
"epoch": 30.0,
|
5 |
+
"global_step": 2370,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.58,
|
12 |
+
"eval_avg_sts": 0.7662035438889292,
|
13 |
+
"eval_sickr_spearman": 0.7410381462554306,
|
14 |
+
"eval_stsb_spearman": 0.7913689415224279,
|
15 |
+
"step": 125
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 3.16,
|
19 |
+
"eval_avg_sts": 0.7622844935042077,
|
20 |
+
"eval_sickr_spearman": 0.7436556491594021,
|
21 |
+
"eval_stsb_spearman": 0.7809133378490134,
|
22 |
+
"step": 250
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"epoch": 4.75,
|
26 |
+
"eval_avg_sts": 0.7643160286763296,
|
27 |
+
"eval_sickr_spearman": 0.7401467850749421,
|
28 |
+
"eval_stsb_spearman": 0.7884852722777171,
|
29 |
+
"step": 375
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 6.33,
|
33 |
+
"learning_rate": 0.023670886075949367,
|
34 |
+
"loss": 0.0008,
|
35 |
+
"step": 500
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 6.33,
|
39 |
+
"eval_avg_sts": 0.736147879900914,
|
40 |
+
"eval_sickr_spearman": 0.7162090447402155,
|
41 |
+
"eval_stsb_spearman": 0.7560867150616126,
|
42 |
+
"step": 500
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 7.91,
|
46 |
+
"eval_avg_sts": 0.7436231350118074,
|
47 |
+
"eval_sickr_spearman": 0.7186257776401757,
|
48 |
+
"eval_stsb_spearman": 0.7686204923834391,
|
49 |
+
"step": 625
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"epoch": 9.49,
|
53 |
+
"eval_avg_sts": 0.7393926207347856,
|
54 |
+
"eval_sickr_spearman": 0.7195540747376701,
|
55 |
+
"eval_stsb_spearman": 0.7592311667319013,
|
56 |
+
"step": 750
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 11.08,
|
60 |
+
"eval_avg_sts": 0.7452291779176539,
|
61 |
+
"eval_sickr_spearman": 0.723164908850483,
|
62 |
+
"eval_stsb_spearman": 0.7672934469848247,
|
63 |
+
"step": 875
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 12.66,
|
67 |
+
"learning_rate": 0.017341772151898735,
|
68 |
+
"loss": 0.0012,
|
69 |
+
"step": 1000
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 12.66,
|
73 |
+
"eval_avg_sts": 0.7565861527485951,
|
74 |
+
"eval_sickr_spearman": 0.7287989090180722,
|
75 |
+
"eval_stsb_spearman": 0.7843733964791179,
|
76 |
+
"step": 1000
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 14.24,
|
80 |
+
"eval_avg_sts": 0.7438608566065805,
|
81 |
+
"eval_sickr_spearman": 0.7231068392488443,
|
82 |
+
"eval_stsb_spearman": 0.7646148739643166,
|
83 |
+
"step": 1125
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 15.82,
|
87 |
+
"eval_avg_sts": 0.7467030170884223,
|
88 |
+
"eval_sickr_spearman": 0.7322541703933272,
|
89 |
+
"eval_stsb_spearman": 0.7611518637835176,
|
90 |
+
"step": 1250
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 17.41,
|
94 |
+
"eval_avg_sts": 0.7515738063184808,
|
95 |
+
"eval_sickr_spearman": 0.7319930252948081,
|
96 |
+
"eval_stsb_spearman": 0.7711545873421535,
|
97 |
+
"step": 1375
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 18.99,
|
101 |
+
"learning_rate": 0.011012658227848101,
|
102 |
+
"loss": 0.0008,
|
103 |
+
"step": 1500
|
104 |
+
},
|
105 |
+
{
|
106 |
+
"epoch": 18.99,
|
107 |
+
"eval_avg_sts": 0.7547593596864199,
|
108 |
+
"eval_sickr_spearman": 0.7316824081618079,
|
109 |
+
"eval_stsb_spearman": 0.777836311211032,
|
110 |
+
"step": 1500
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 20.57,
|
114 |
+
"eval_avg_sts": 0.7546503164567119,
|
115 |
+
"eval_sickr_spearman": 0.7284250829555794,
|
116 |
+
"eval_stsb_spearman": 0.7808755499578444,
|
117 |
+
"step": 1625
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 22.15,
|
121 |
+
"eval_avg_sts": 0.7412961666365114,
|
122 |
+
"eval_sickr_spearman": 0.7141825165083387,
|
123 |
+
"eval_stsb_spearman": 0.7684098167646841,
|
124 |
+
"step": 1750
|
125 |
+
},
|
126 |
+
{
|
127 |
+
"epoch": 23.73,
|
128 |
+
"eval_avg_sts": 0.7444813377835273,
|
129 |
+
"eval_sickr_spearman": 0.7180804325144473,
|
130 |
+
"eval_stsb_spearman": 0.7708822430526072,
|
131 |
+
"step": 1875
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 25.32,
|
135 |
+
"learning_rate": 0.0046835443037974685,
|
136 |
+
"loss": 0.0005,
|
137 |
+
"step": 2000
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 25.32,
|
141 |
+
"eval_avg_sts": 0.7457798773906168,
|
142 |
+
"eval_sickr_spearman": 0.7201111394521492,
|
143 |
+
"eval_stsb_spearman": 0.7714486153290844,
|
144 |
+
"step": 2000
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 26.9,
|
148 |
+
"eval_avg_sts": 0.7454552356177395,
|
149 |
+
"eval_sickr_spearman": 0.7205938039905009,
|
150 |
+
"eval_stsb_spearman": 0.7703166672449782,
|
151 |
+
"step": 2125
|
152 |
+
},
|
153 |
+
{
|
154 |
+
"epoch": 28.48,
|
155 |
+
"eval_avg_sts": 0.7438784407146768,
|
156 |
+
"eval_sickr_spearman": 0.7192442261022928,
|
157 |
+
"eval_stsb_spearman": 0.7685126553270608,
|
158 |
+
"step": 2250
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 30.0,
|
162 |
+
"step": 2370,
|
163 |
+
"train_runtime": 1196.069,
|
164 |
+
"train_samples_per_second": 1.981
|
165 |
+
}
|
166 |
+
],
|
167 |
+
"max_steps": 2370,
|
168 |
+
"num_train_epochs": 30,
|
169 |
+
"total_flos": 3153372403064832,
|
170 |
+
"trial_name": null,
|
171 |
+
"trial_params": null
|
172 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:883f76222b3134ca992270bc321f7618f926f4b6fe6a37f8e6b998e9ca737dd0
|
3 |
+
size 2107
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|