syke9p3 commited on
Commit
3da74c2
1 Parent(s): 766cdbf

Upload 11 files

Browse files
config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gklmip/bert-tagalog-base-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "Age",
15
+ "1": "Gender",
16
+ "2": "Physical",
17
+ "3": "Race",
18
+ "4": "Religion",
19
+ "5": "Others"
20
+ },
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 3072,
23
+ "label2id": {
24
+ "Age": 0,
25
+ "Gender": 1,
26
+ "Others": 5,
27
+ "Physical": 2,
28
+ "Race": 3,
29
+ "Religion": 4
30
+ },
31
+ "layer_norm_eps": 1e-12,
32
+ "max_position_embeddings": 512,
33
+ "model_type": "bert",
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 12,
36
+ "pad_token_id": 0,
37
+ "pooler_fc_size": 768,
38
+ "pooler_num_attention_heads": 12,
39
+ "pooler_num_fc_layers": 3,
40
+ "pooler_size_per_head": 128,
41
+ "pooler_type": "first_token_transform",
42
+ "position_embedding_type": "absolute",
43
+ "problem_type": "multi_label_classification",
44
+ "torch_dtype": "float32",
45
+ "transformers_version": "4.41.2",
46
+ "type_vocab_size": 2,
47
+ "use_cache": true,
48
+ "vocab_size": 52099
49
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfacbd6ce1e1f00afa0f95a9c83999336188eb37235f79bd3b544f668d3b89e8
3
+ size 504255504
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96627a13cb0f9557d9d8049dae3fd2c12494609e980e7efc95baad43607eba5f
3
+ size 1008632058
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10751bce6411252ba7ea497c44ee39e5601afdea1b3956302c9677e6e73470af
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9b82c227050b6c3f704bc63c89f4c99ed1b0e1d71eefea8dbbc7985739a0434
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
trainer_state.json ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.876997915218902,
3
+ "best_model_checkpoint": "bert-multilabel-tagalog-hate-speech-classifier/checkpoint-790",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 790,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.4650793650793651,
14
+ "eval_f1": 0.6538124452234881,
15
+ "eval_loss": 0.2858085036277771,
16
+ "eval_roc_auc": 0.749062395824874,
17
+ "eval_runtime": 16.739,
18
+ "eval_samples_per_second": 37.637,
19
+ "eval_steps_per_second": 4.72,
20
+ "step": 158
21
+ },
22
+ {
23
+ "epoch": 2.0,
24
+ "eval_accuracy": 0.7285714285714285,
25
+ "eval_f1": 0.8368690563277249,
26
+ "eval_loss": 0.1806272566318512,
27
+ "eval_roc_auc": 0.8807496256986324,
28
+ "eval_runtime": 16.7646,
29
+ "eval_samples_per_second": 37.579,
30
+ "eval_steps_per_second": 4.712,
31
+ "step": 316
32
+ },
33
+ {
34
+ "epoch": 3.0,
35
+ "eval_accuracy": 0.7682539682539683,
36
+ "eval_f1": 0.8638631503920171,
37
+ "eval_loss": 0.14880089461803436,
38
+ "eval_roc_auc": 0.9036774632664203,
39
+ "eval_runtime": 17.0606,
40
+ "eval_samples_per_second": 36.927,
41
+ "eval_steps_per_second": 4.631,
42
+ "step": 474
43
+ },
44
+ {
45
+ "epoch": 3.1645569620253164,
46
+ "grad_norm": 1.8442691564559937,
47
+ "learning_rate": 7.341772151898735e-06,
48
+ "loss": 0.2518,
49
+ "step": 500
50
+ },
51
+ {
52
+ "epoch": 4.0,
53
+ "eval_accuracy": 0.7761904761904762,
54
+ "eval_f1": 0.8720848056537103,
55
+ "eval_loss": 0.14489033818244934,
56
+ "eval_roc_auc": 0.911037414882052,
57
+ "eval_runtime": 17.6671,
58
+ "eval_samples_per_second": 35.66,
59
+ "eval_steps_per_second": 4.472,
60
+ "step": 632
61
+ },
62
+ {
63
+ "epoch": 5.0,
64
+ "eval_accuracy": 0.780952380952381,
65
+ "eval_f1": 0.876997915218902,
66
+ "eval_loss": 0.13758358359336853,
67
+ "eval_roc_auc": 0.9189734563461635,
68
+ "eval_runtime": 17.8108,
69
+ "eval_samples_per_second": 35.372,
70
+ "eval_steps_per_second": 4.436,
71
+ "step": 790
72
+ }
73
+ ],
74
+ "logging_steps": 500,
75
+ "max_steps": 790,
76
+ "num_input_tokens_seen": 0,
77
+ "num_train_epochs": 5,
78
+ "save_steps": 500,
79
+ "stateful_callbacks": {
80
+ "TrainerControl": {
81
+ "args": {
82
+ "should_epoch_stop": false,
83
+ "should_evaluate": false,
84
+ "should_log": false,
85
+ "should_save": true,
86
+ "should_training_stop": true
87
+ },
88
+ "attributes": {}
89
+ }
90
+ },
91
+ "total_flos": 414414795110400.0,
92
+ "train_batch_size": 8,
93
+ "trial_name": null,
94
+ "trial_params": null
95
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64dd6df4367f52352575621681c3862aeeaa1921cdc2c22c20704c357240ad31
3
+ size 5176
vocab.txt ADDED
The diff for this file is too large to render. See raw diff