Wikidepia commited on
Commit
7852612
1 Parent(s): bfc5f7e

Initial models

Browse files

all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "init_mem_cpu_alloc_delta": 2323701760,
4
+ "init_mem_cpu_peaked_delta": 43028480,
5
+ "init_mem_gpu_alloc_delta": 44382720,
6
+ "init_mem_gpu_peaked_delta": 0,
7
+ "train_mem_cpu_alloc_delta": 1256140800,
8
+ "train_mem_cpu_peaked_delta": 8110080,
9
+ "train_mem_gpu_alloc_delta": 136292352,
10
+ "train_mem_gpu_peaked_delta": 22428033024,
11
+ "train_runtime": 3251.9473,
12
+ "train_samples": 130488,
13
+ "train_samples_per_second": 2.229
14
+ }
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Wikidepia/indobert-lite-squad",
3
+ "architectures": [
4
+ "AlbertForQuestionAnswering"
5
+ ],
6
+ "attention_probs_dropout_prob": 0,
7
+ "bos_token_id": 2,
8
+ "classifier_dropout_prob": 0.1,
9
+ "down_scale_factor": 1,
10
+ "embedding_size": 128,
11
+ "eos_token_id": 3,
12
+ "gap_size": 0,
13
+ "hidden_act": "gelu",
14
+ "hidden_dropout_prob": 0,
15
+ "hidden_size": 768,
16
+ "initializer_range": 0.02,
17
+ "inner_group_num": 1,
18
+ "intermediate_size": 3072,
19
+ "layer_norm_eps": 1e-12,
20
+ "max_position_embeddings": 512,
21
+ "model_type": "albert",
22
+ "net_structure_type": 0,
23
+ "num_attention_heads": 12,
24
+ "num_hidden_groups": 1,
25
+ "num_hidden_layers": 12,
26
+ "num_memory_blocks": 0,
27
+ "output_past": true,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "absolute",
30
+ "transformers_version": "4.5.0.dev0",
31
+ "type_vocab_size": 2,
32
+ "vocab_size": 30000
33
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eaa56d4096d9c817ace439adcd30ee72745a6ea2559a9aa2cd580bf7d300b2aa
3
+ size 44393497
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, "max_len": 512, "use_fast": true, "special_tokens_map_file": "indobert-lite-base-p2/special_tokens_map.json", "name_or_path": "Wikidepia/indobert-lite-squad", "do_basic_tokenize": true, "never_split": null}
train_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "init_mem_cpu_alloc_delta": 2323701760,
4
+ "init_mem_cpu_peaked_delta": 43028480,
5
+ "init_mem_gpu_alloc_delta": 44382720,
6
+ "init_mem_gpu_peaked_delta": 0,
7
+ "train_mem_cpu_alloc_delta": 1256140800,
8
+ "train_mem_cpu_peaked_delta": 8110080,
9
+ "train_mem_gpu_alloc_delta": 136292352,
10
+ "train_mem_gpu_peaked_delta": 22428033024,
11
+ "train_runtime": 3251.9473,
12
+ "train_samples": 130488,
13
+ "train_samples_per_second": 2.229
14
+ }
trainer_state.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "global_step": 7250,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.14,
12
+ "learning_rate": 2.793103448275862e-05,
13
+ "loss": 1.3311,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.28,
18
+ "learning_rate": 2.586206896551724e-05,
19
+ "loss": 1.3174,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.41,
24
+ "learning_rate": 2.3793103448275862e-05,
25
+ "loss": 1.2975,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.55,
30
+ "learning_rate": 2.1724137931034484e-05,
31
+ "loss": 1.2811,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.69,
36
+ "learning_rate": 1.9655172413793102e-05,
37
+ "loss": 1.2528,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.83,
42
+ "learning_rate": 1.7586206896551724e-05,
43
+ "loss": 1.2374,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.97,
48
+ "learning_rate": 1.5517241379310346e-05,
49
+ "loss": 1.2414,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 1.1,
54
+ "learning_rate": 1.3448275862068966e-05,
55
+ "loss": 0.9927,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 1.24,
60
+ "learning_rate": 1.1379310344827586e-05,
61
+ "loss": 0.9257,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 1.38,
66
+ "learning_rate": 9.310344827586207e-06,
67
+ "loss": 0.9237,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 1.52,
72
+ "learning_rate": 7.241379310344828e-06,
73
+ "loss": 0.9171,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 1.66,
78
+ "learning_rate": 5.172413793103449e-06,
79
+ "loss": 0.9109,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 1.79,
84
+ "learning_rate": 3.103448275862069e-06,
85
+ "loss": 0.8931,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 1.93,
90
+ "learning_rate": 1.0344827586206896e-06,
91
+ "loss": 0.878,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 2.0,
96
+ "step": 7250,
97
+ "total_flos": 8894687420252160.0,
98
+ "train_runtime": 3251.9473,
99
+ "train_samples_per_second": 2.229
100
+ }
101
+ ],
102
+ "max_steps": 7250,
103
+ "num_train_epochs": 2,
104
+ "total_flos": 8894687420252160.0,
105
+ "trial_name": null,
106
+ "trial_params": null
107
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9c75f5e62b7fd0e2f79c067f162b20c4653b0f3b38fa862d245a95d9d2eeb97
3
+ size 2287
vocab.txt ADDED
The diff for this file is too large to render. See raw diff