mbruton commited on
Commit
b99b502
1 Parent(s): 2d8d955

Upload 11 files

Browse files
config.json ADDED
@@ -0,0 +1,135 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "liaad/srl-en_mbert-base",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "O",
14
+ "1": "r0:arg0",
15
+ "2": "r0:arg1",
16
+ "3": "r0:arg2",
17
+ "4": "r0:root",
18
+ "5": "r10:arg0",
19
+ "6": "r10:arg1",
20
+ "7": "r10:root",
21
+ "8": "r11:arg0",
22
+ "9": "r11:root",
23
+ "10": "r12:arg1",
24
+ "11": "r12:root",
25
+ "12": "r13:arg1",
26
+ "13": "r13:root",
27
+ "14": "r1:arg0",
28
+ "15": "r1:arg1",
29
+ "16": "r1:arg2",
30
+ "17": "r1:root",
31
+ "18": "r2:arg0",
32
+ "19": "r2:arg1",
33
+ "20": "r2:arg2",
34
+ "21": "r2:root",
35
+ "22": "r3:arg0",
36
+ "23": "r3:arg1",
37
+ "24": "r3:arg2",
38
+ "25": "r3:root",
39
+ "26": "r4:arg0",
40
+ "27": "r4:arg1",
41
+ "28": "r4:arg2",
42
+ "29": "r4:root",
43
+ "30": "r5:arg0",
44
+ "31": "r5:arg1",
45
+ "32": "r5:arg2",
46
+ "33": "r5:root",
47
+ "34": "r6:arg0",
48
+ "35": "r6:arg1",
49
+ "36": "r6:arg2",
50
+ "37": "r6:root",
51
+ "38": "r7:arg0",
52
+ "39": "r7:arg1",
53
+ "40": "r7:arg2",
54
+ "41": "r7:root",
55
+ "42": "r8:arg0",
56
+ "43": "r8:arg1",
57
+ "44": "r8:arg2",
58
+ "45": "r8:root",
59
+ "46": "r9:arg0",
60
+ "47": "r9:arg1",
61
+ "48": "r9:arg2",
62
+ "49": "r9:root"
63
+ },
64
+ "initializer_range": 0.02,
65
+ "intermediate_size": 3072,
66
+ "label2id": {
67
+ "O": 0,
68
+ "r0:arg0": 1,
69
+ "r0:arg1": 2,
70
+ "r0:arg2": 3,
71
+ "r0:root": 4,
72
+ "r10:arg0": 5,
73
+ "r10:arg1": 6,
74
+ "r10:root": 7,
75
+ "r11:arg0": 8,
76
+ "r11:root": 9,
77
+ "r12:arg1": 10,
78
+ "r12:root": 11,
79
+ "r13:arg1": 12,
80
+ "r13:root": 13,
81
+ "r1:arg0": 14,
82
+ "r1:arg1": 15,
83
+ "r1:arg2": 16,
84
+ "r1:root": 17,
85
+ "r2:arg0": 18,
86
+ "r2:arg1": 19,
87
+ "r2:arg2": 20,
88
+ "r2:root": 21,
89
+ "r3:arg0": 22,
90
+ "r3:arg1": 23,
91
+ "r3:arg2": 24,
92
+ "r3:root": 25,
93
+ "r4:arg0": 26,
94
+ "r4:arg1": 27,
95
+ "r4:arg2": 28,
96
+ "r4:root": 29,
97
+ "r5:arg0": 30,
98
+ "r5:arg1": 31,
99
+ "r5:arg2": 32,
100
+ "r5:root": 33,
101
+ "r6:arg0": 34,
102
+ "r6:arg1": 35,
103
+ "r6:arg2": 36,
104
+ "r6:root": 37,
105
+ "r7:arg0": 38,
106
+ "r7:arg1": 39,
107
+ "r7:arg2": 40,
108
+ "r7:root": 41,
109
+ "r8:arg0": 42,
110
+ "r8:arg1": 43,
111
+ "r8:arg2": 44,
112
+ "r8:root": 45,
113
+ "r9:arg0": 46,
114
+ "r9:arg1": 47,
115
+ "r9:arg2": 48,
116
+ "r9:root": 49
117
+ },
118
+ "layer_norm_eps": 1e-12,
119
+ "max_position_embeddings": 512,
120
+ "model_type": "bert",
121
+ "num_attention_heads": 12,
122
+ "num_hidden_layers": 12,
123
+ "pad_token_id": 0,
124
+ "pooler_fc_size": 768,
125
+ "pooler_num_attention_heads": 12,
126
+ "pooler_num_fc_layers": 3,
127
+ "pooler_size_per_head": 128,
128
+ "pooler_type": "first_token_transform",
129
+ "position_embedding_type": "absolute",
130
+ "torch_dtype": "float32",
131
+ "transformers_version": "4.27.4",
132
+ "type_vocab_size": 2,
133
+ "use_cache": true,
134
+ "vocab_size": 119547
135
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5d8973f363cfc6d8de8d44368d7778f6dbe6e2b079346fcea0c455397c2576e
3
+ size 1418525797
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c40bb8048ab950c5b3507fcdf9863a438f3268ec23662eafe8a9be7dfab0d872
3
+ size 709275633
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28238529fef29fb763aa58326402157c5346334cabb7c711b05d5a3f1e020c9e
3
+ size 14503
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b14881f8352737c801b7e15ff2544419ace05937680ded1c03cfe4be45005e78
3
+ size 623
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 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": false,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 512,
7
+ "never_split": null,
8
+ "pad_token": "[PAD]",
9
+ "sep_token": "[SEP]",
10
+ "special_tokens_map_file": "/root/.cache/huggingface/hub/models--liaad--srl-en_mbert-base/snapshots/0c963b783ca3a81aafce1c53c0bb17715a7f0903/special_tokens_map.json",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
trainer_state.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.3187411427497864,
3
+ "best_model_checkpoint": "gal_en_mBERT/checkpoint-1250",
4
+ "epoch": 6.0,
5
+ "global_step": 1500,
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
+ "eval_accuracy": 0.8779133954857704,
13
+ "eval_f1": 0.5262912258867455,
14
+ "eval_loss": 0.44472846388816833,
15
+ "eval_precision": 0.5704890387858348,
16
+ "eval_recall": 0.4884493213976321,
17
+ "eval_runtime": 5.3275,
18
+ "eval_samples_per_second": 187.141,
19
+ "eval_steps_per_second": 11.825,
20
+ "step": 250
21
+ },
22
+ {
23
+ "epoch": 2.0,
24
+ "learning_rate": 1.9600000000000002e-05,
25
+ "loss": 0.5654,
26
+ "step": 500
27
+ },
28
+ {
29
+ "epoch": 2.0,
30
+ "eval_accuracy": 0.897479146221786,
31
+ "eval_f1": 0.6228456315750205,
32
+ "eval_loss": 0.36001163721084595,
33
+ "eval_precision": 0.6444341516134012,
34
+ "eval_recall": 0.6026566560785446,
35
+ "eval_runtime": 5.2617,
36
+ "eval_samples_per_second": 189.481,
37
+ "eval_steps_per_second": 11.973,
38
+ "step": 500
39
+ },
40
+ {
41
+ "epoch": 3.0,
42
+ "eval_accuracy": 0.9003312070657508,
43
+ "eval_f1": 0.6522937725312786,
44
+ "eval_loss": 0.3470691740512848,
45
+ "eval_precision": 0.6389696717906107,
46
+ "eval_recall": 0.666185388391568,
47
+ "eval_runtime": 5.3516,
48
+ "eval_samples_per_second": 186.3,
49
+ "eval_steps_per_second": 11.772,
50
+ "step": 750
51
+ },
52
+ {
53
+ "epoch": 4.0,
54
+ "learning_rate": 1.9200000000000003e-05,
55
+ "loss": 0.2726,
56
+ "step": 1000
57
+ },
58
+ {
59
+ "epoch": 4.0,
60
+ "eval_accuracy": 0.9087953876349362,
61
+ "eval_f1": 0.6704950207167261,
62
+ "eval_loss": 0.32999733090400696,
63
+ "eval_precision": 0.6751573708095447,
64
+ "eval_recall": 0.6658966214265089,
65
+ "eval_runtime": 5.2725,
66
+ "eval_samples_per_second": 189.094,
67
+ "eval_steps_per_second": 11.949,
68
+ "step": 1000
69
+ },
70
+ {
71
+ "epoch": 5.0,
72
+ "eval_accuracy": 0.914407507360157,
73
+ "eval_f1": 0.6932259245697546,
74
+ "eval_loss": 0.3187411427497864,
75
+ "eval_precision": 0.7033734581661465,
76
+ "eval_recall": 0.6833670228125902,
77
+ "eval_runtime": 5.3299,
78
+ "eval_samples_per_second": 187.056,
79
+ "eval_steps_per_second": 11.82,
80
+ "step": 1250
81
+ },
82
+ {
83
+ "epoch": 6.0,
84
+ "learning_rate": 1.88e-05,
85
+ "loss": 0.1882,
86
+ "step": 1500
87
+ },
88
+ {
89
+ "epoch": 6.0,
90
+ "eval_accuracy": 0.9141008341511285,
91
+ "eval_f1": 0.7037852425253888,
92
+ "eval_loss": 0.33032578229904175,
93
+ "eval_precision": 0.6925227113906359,
94
+ "eval_recall": 0.7154201559341611,
95
+ "eval_runtime": 5.4015,
96
+ "eval_samples_per_second": 184.577,
97
+ "eval_steps_per_second": 11.663,
98
+ "step": 1500
99
+ }
100
+ ],
101
+ "max_steps": 25000,
102
+ "num_train_epochs": 100,
103
+ "total_flos": 934904811170400.0,
104
+ "trial_name": null,
105
+ "trial_params": null
106
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:999e47d0e57ea1a36c9092deb6b1fe05b1351f5189bf370df1e0c1d68c5798a6
3
+ size 3503
vocab.txt ADDED
The diff for this file is too large to render. See raw diff