Commit
•
9fb571d
1
Parent(s):
cc87a46
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 +104 -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-restaurants",
|
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 sha256:303d1ab4ee42465fcd778e5264f5eae9a7c09151424bcb3590c72296b99ef405
|
3 |
+
size 7086823
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7723faefbeab276316e6625cc11f65c9c2991cb9e7f3be932d9ef5f162b38363
|
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 = 659.1275
|
3 |
+
train_samples_per_second = 1.912
|
trainer_state.json
ADDED
@@ -0,0 +1,104 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8233371272282494,
|
3 |
+
"best_model_checkpoint": "/content/result/semeval-unsup-promcse-bert-base-uncased-semeval2015-restaurants",
|
4 |
+
"epoch": 30.0,
|
5 |
+
"global_step": 1260,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 2.98,
|
12 |
+
"eval_avg_sts": 0.7757513995180081,
|
13 |
+
"eval_sickr_spearman": 0.7322881283820439,
|
14 |
+
"eval_stsb_spearman": 0.8192146706539722,
|
15 |
+
"step": 125
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 5.95,
|
19 |
+
"eval_avg_sts": 0.7698413621949267,
|
20 |
+
"eval_sickr_spearman": 0.7163455971616041,
|
21 |
+
"eval_stsb_spearman": 0.8233371272282494,
|
22 |
+
"step": 250
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"epoch": 8.93,
|
26 |
+
"eval_avg_sts": 0.7731286838565641,
|
27 |
+
"eval_sickr_spearman": 0.731383126368747,
|
28 |
+
"eval_stsb_spearman": 0.814874241344381,
|
29 |
+
"step": 375
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 11.9,
|
33 |
+
"learning_rate": 0.018095238095238095,
|
34 |
+
"loss": 0.0008,
|
35 |
+
"step": 500
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 11.9,
|
39 |
+
"eval_avg_sts": 0.776810425073202,
|
40 |
+
"eval_sickr_spearman": 0.7312739516751782,
|
41 |
+
"eval_stsb_spearman": 0.8223468984712257,
|
42 |
+
"step": 500
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 14.88,
|
46 |
+
"eval_avg_sts": 0.7739310482649151,
|
47 |
+
"eval_sickr_spearman": 0.7315272196730613,
|
48 |
+
"eval_stsb_spearman": 0.8163348768567688,
|
49 |
+
"step": 625
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"epoch": 17.86,
|
53 |
+
"eval_avg_sts": 0.7730642466327569,
|
54 |
+
"eval_sickr_spearman": 0.7297671679919632,
|
55 |
+
"eval_stsb_spearman": 0.8163613252735507,
|
56 |
+
"step": 750
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 20.83,
|
60 |
+
"eval_avg_sts": 0.7720903369997629,
|
61 |
+
"eval_sickr_spearman": 0.7313365362003521,
|
62 |
+
"eval_stsb_spearman": 0.8128441377991739,
|
63 |
+
"step": 875
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 23.81,
|
67 |
+
"learning_rate": 0.00619047619047619,
|
68 |
+
"loss": 0.0003,
|
69 |
+
"step": 1000
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 23.81,
|
73 |
+
"eval_avg_sts": 0.7706636855212914,
|
74 |
+
"eval_sickr_spearman": 0.7281604315866554,
|
75 |
+
"eval_stsb_spearman": 0.8131669394559274,
|
76 |
+
"step": 1000
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 26.79,
|
80 |
+
"eval_avg_sts": 0.7713602521546277,
|
81 |
+
"eval_sickr_spearman": 0.7285470819532321,
|
82 |
+
"eval_stsb_spearman": 0.8141734223560232,
|
83 |
+
"step": 1125
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 29.76,
|
87 |
+
"eval_avg_sts": 0.7713639733054263,
|
88 |
+
"eval_sickr_spearman": 0.727316333009982,
|
89 |
+
"eval_stsb_spearman": 0.8154116136008706,
|
90 |
+
"step": 1250
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 30.0,
|
94 |
+
"step": 1260,
|
95 |
+
"train_runtime": 659.1275,
|
96 |
+
"train_samples_per_second": 1.912
|
97 |
+
}
|
98 |
+
],
|
99 |
+
"max_steps": 1260,
|
100 |
+
"num_train_epochs": 30,
|
101 |
+
"total_flos": 1652728834722816,
|
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:d519803637aadd414fb9f26a18b8fbc3dca4394489fac760a93dd063008de9cc
|
3 |
+
size 2107
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|