StevenLimcorn
commited on
Commit
•
719f5ba
1
Parent(s):
0cd1a2a
Upload 10 files
Browse files- config.json +26 -0
- merges.txt +0 -0
- 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 +111 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/content/result/unsup-simcse-roberta-large-facebook-election-ads",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaModel"
|
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": 1024,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 4096,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 514,
|
17 |
+
"model_type": "roberta",
|
18 |
+
"num_attention_heads": 16,
|
19 |
+
"num_hidden_layers": 24,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"position_embedding_type": "absolute",
|
22 |
+
"transformers_version": "4.2.1",
|
23 |
+
"type_vocab_size": 1,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 50265
|
26 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee209292f0c462b44fa27584c37db8bba93d8929d21a83588a3ab686cd670517
|
3 |
+
size 2843107269
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a687f9d7485a015c729dfaa40611008bb7b28660a228def572680b43efa5caa
|
3 |
+
size 627
|
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": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "name_or_path": "princeton-nlp/unsup-simcse-roberta-large", "special_tokens_map_file": "/root/.cache/huggingface/transformers/6d59ec8e128c32fbf5663dad4484f60104c7f3b2520047fbaf57bc63b260e0fd.a11ebb04664c067c8fe5ef8f8068b0f721263414a26058692f7b2e4ba2a1b342"}
|
train_results.txt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
epoch = 5.0
|
2 |
+
train_runtime = 3104.0027
|
3 |
+
train_samples_per_second = 0.459
|
trainer_state.json
ADDED
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8268827257542107,
|
3 |
+
"best_model_checkpoint": "/content/result/unsup-simcse-roberta-large-facebook-election-ads",
|
4 |
+
"epoch": 5.0,
|
5 |
+
"global_step": 1425,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.44,
|
12 |
+
"eval_avg_sts": 0.7713986248458491,
|
13 |
+
"eval_sickr_spearman": 0.7196138734589604,
|
14 |
+
"eval_stsb_spearman": 0.8231833762327377,
|
15 |
+
"step": 125
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.88,
|
19 |
+
"eval_avg_sts": 0.7816935841568983,
|
20 |
+
"eval_sickr_spearman": 0.7365044425595858,
|
21 |
+
"eval_stsb_spearman": 0.8268827257542107,
|
22 |
+
"step": 250
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"epoch": 1.32,
|
26 |
+
"eval_avg_sts": 0.7645407603583253,
|
27 |
+
"eval_sickr_spearman": 0.7141448601248113,
|
28 |
+
"eval_stsb_spearman": 0.8149366605918393,
|
29 |
+
"step": 375
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 1.75,
|
33 |
+
"learning_rate": 3.24561403508772e-05,
|
34 |
+
"loss": 0.0019,
|
35 |
+
"step": 500
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 1.75,
|
39 |
+
"eval_avg_sts": 0.7604863072298488,
|
40 |
+
"eval_sickr_spearman": 0.7226733585583653,
|
41 |
+
"eval_stsb_spearman": 0.7982992559013322,
|
42 |
+
"step": 500
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 2.19,
|
46 |
+
"eval_avg_sts": 0.7556532453851812,
|
47 |
+
"eval_sickr_spearman": 0.7095467467219377,
|
48 |
+
"eval_stsb_spearman": 0.8017597440484248,
|
49 |
+
"step": 625
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"epoch": 2.63,
|
53 |
+
"eval_avg_sts": 0.7581763481027948,
|
54 |
+
"eval_sickr_spearman": 0.7125405183600657,
|
55 |
+
"eval_stsb_spearman": 0.803812177845524,
|
56 |
+
"step": 750
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 3.07,
|
60 |
+
"eval_avg_sts": 0.7366916009615327,
|
61 |
+
"eval_sickr_spearman": 0.6934594017306621,
|
62 |
+
"eval_stsb_spearman": 0.7799238001924034,
|
63 |
+
"step": 875
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 3.51,
|
67 |
+
"learning_rate": 1.4912280701754386e-05,
|
68 |
+
"loss": 0.0011,
|
69 |
+
"step": 1000
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 3.51,
|
73 |
+
"eval_avg_sts": 0.7261565018963125,
|
74 |
+
"eval_sickr_spearman": 0.6887153218105183,
|
75 |
+
"eval_stsb_spearman": 0.7635976819821068,
|
76 |
+
"step": 1000
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 3.95,
|
80 |
+
"eval_avg_sts": 0.73942694473879,
|
81 |
+
"eval_sickr_spearman": 0.699325680304806,
|
82 |
+
"eval_stsb_spearman": 0.7795282091727741,
|
83 |
+
"step": 1125
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 4.39,
|
87 |
+
"eval_avg_sts": 0.7486781326241809,
|
88 |
+
"eval_sickr_spearman": 0.707213684000683,
|
89 |
+
"eval_stsb_spearman": 0.7901425812476789,
|
90 |
+
"step": 1250
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 4.82,
|
94 |
+
"eval_avg_sts": 0.753180147484883,
|
95 |
+
"eval_sickr_spearman": 0.7108770641384692,
|
96 |
+
"eval_stsb_spearman": 0.7954832308312969,
|
97 |
+
"step": 1375
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 5.0,
|
101 |
+
"step": 1425,
|
102 |
+
"train_runtime": 3104.0027,
|
103 |
+
"train_samples_per_second": 0.459
|
104 |
+
}
|
105 |
+
],
|
106 |
+
"max_steps": 1425,
|
107 |
+
"num_train_epochs": 5,
|
108 |
+
"total_flos": 12419737766461440,
|
109 |
+
"trial_name": null,
|
110 |
+
"trial_params": null
|
111 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d6894c90de19e3418c3a16a0a6219865ea0a0eae6660d6b8aa9918e9d7848fc
|
3 |
+
size 2107
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|