amodaresi commited on
Commit
074cbdb
1 Parent(s): 020a20b

Add model and its dependencies

Browse files
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/electra-base-discriminator",
3
+ "architectures": [
4
+ "ElectraForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "embedding_size": 768,
8
+ "finetuning_task": "mnli",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "LABEL_0": 0,
21
+ "LABEL_1": 1,
22
+ "LABEL_2": 2
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "electra",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "pad_token_id": 0,
30
+ "position_embedding_type": "absolute",
31
+ "problem_type": "single_label_classification",
32
+ "summary_activation": "gelu",
33
+ "summary_last_dropout": 0.1,
34
+ "summary_type": "first",
35
+ "summary_use_proj": true,
36
+ "transformers_version": "4.9.0.dev0",
37
+ "type_vocab_size": 2,
38
+ "vocab_size": 30522
39
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03bc7060469f053a0e7015daafc20c7428cf675edf280a1dc3d97efb4eabd34d
3
+ size 438023533
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.json ADDED
The diff for this file is too large to render. See raw diff
 
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, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "google/electra-base-discriminator", "tokenizer_class": "ElectraTokenizer"}
trainer_state.json ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8860927152317881,
3
+ "best_model_checkpoint": "./outputs/electra-base-uncased/fine_tuned_models/checkpoint-36816",
4
+ "epoch": 5.0,
5
+ "global_step": 61360,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 1.7388593694651082e-05,
13
+ "loss": 0.4571,
14
+ "step": 12272
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.8808965868568518,
19
+ "eval_loss": 0.3177725374698639,
20
+ "eval_runtime": 24.4511,
21
+ "eval_samples_per_second": 401.414,
22
+ "eval_steps_per_second": 50.182,
23
+ "step": 12272
24
+ },
25
+ {
26
+ "epoch": 2.0,
27
+ "learning_rate": 1.3041445270988312e-05,
28
+ "loss": 0.2786,
29
+ "step": 24544
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "eval_accuracy": 0.8843606724401426,
34
+ "eval_loss": 0.3345130681991577,
35
+ "eval_runtime": 24.46,
36
+ "eval_samples_per_second": 401.267,
37
+ "eval_steps_per_second": 50.163,
38
+ "step": 24544
39
+ },
40
+ {
41
+ "epoch": 3.0,
42
+ "learning_rate": 8.694296847325541e-06,
43
+ "loss": 0.1852,
44
+ "step": 36816
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_accuracy": 0.8860927152317881,
49
+ "eval_loss": 0.41067004203796387,
50
+ "eval_runtime": 24.4548,
51
+ "eval_samples_per_second": 401.352,
52
+ "eval_steps_per_second": 50.174,
53
+ "step": 36816
54
+ },
55
+ {
56
+ "epoch": 4.0,
57
+ "learning_rate": 4.3471484236627705e-06,
58
+ "loss": 0.1257,
59
+ "step": 49088
60
+ },
61
+ {
62
+ "epoch": 4.0,
63
+ "eval_accuracy": 0.8854814060112073,
64
+ "eval_loss": 0.4864971339702606,
65
+ "eval_runtime": 24.4819,
66
+ "eval_samples_per_second": 400.909,
67
+ "eval_steps_per_second": 50.119,
68
+ "step": 49088
69
+ },
70
+ {
71
+ "epoch": 5.0,
72
+ "learning_rate": 0.0,
73
+ "loss": 0.0892,
74
+ "step": 61360
75
+ },
76
+ {
77
+ "epoch": 5.0,
78
+ "eval_accuracy": 0.8858889454915945,
79
+ "eval_loss": 0.5802900791168213,
80
+ "eval_runtime": 24.5033,
81
+ "eval_samples_per_second": 400.558,
82
+ "eval_steps_per_second": 50.075,
83
+ "step": 61360
84
+ },
85
+ {
86
+ "epoch": 5.0,
87
+ "step": 61360,
88
+ "total_flos": 1.6510003421181696e+17,
89
+ "train_loss": 0.2271464799187174,
90
+ "train_runtime": 13411.6836,
91
+ "train_samples_per_second": 146.403,
92
+ "train_steps_per_second": 4.575
93
+ }
94
+ ],
95
+ "max_steps": 61360,
96
+ "num_train_epochs": 5,
97
+ "total_flos": 1.6510003421181696e+17,
98
+ "trial_name": null,
99
+ "trial_params": null
100
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff