Hugging Face's logo

CAMeL-Lab
/
arabart-zaebuc-gec-ged-13

Text2Text Generation
Transformers
PyTorch
Arabic
mbart
Inference Endpoints
Model card Files Community
balhafni commited on
Commit
cd99634
•
1 Parent(s): 6669d9d

Uploading model

Browse files
Files changed (8) hide show
  1. config.json +90 -0
  2. pytorch_model.bin +3 -0
  3. sentencepiece.bpe.model +3 -0
  4. special_tokens_map.json +15 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +20 -0
  7. trainer_state.json +148 -0
  8. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/scratch/ba63/BERT_models/AraBART",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": true,
7
+ "architectures": [
8
+ "MBartForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.1,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.1,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 768,
15
+ "decoder_attention_heads": 12,
16
+ "decoder_ffn_dim": 3072,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 6,
19
+ "decoder_start_token_id": 2,
20
+ "do_blenderbot_90_layernorm": false,
21
+ "dropout": 0.1,
22
+ "early_stopping": true,
23
+ "encoder_attention_heads": 12,
24
+ "encoder_ffn_dim": 3072,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 6,
27
+ "eos_token_id": 2,
28
+ "extra_pos_embeddings": 2,
29
+ "force_bos_token_to_be_generated": false,
30
+ "forced_eos_token_id": 2,
31
+ "ged_id2label": {
32
+ "0": "<pad>",
33
+ "1": "DELETE",
34
+ "2": "MERGE-B",
35
+ "3": "MERGE-I",
36
+ "4": "REPLACE_M",
37
+ "5": "REPLACE_M+REPLACE_O",
38
+ "6": "REPLACE_O",
39
+ "7": "REPLACE_O+REPLACE_X",
40
+ "8": "REPLACE_P",
41
+ "9": "REPLACE_S",
42
+ "10": "REPLACE_X",
43
+ "11": "SPLIT",
44
+ "12": "UC"
45
+ },
46
+ "ged_label2id": {
47
+ "<pad>": 0,
48
+ "DELETE": 1,
49
+ "MERGE-B": 2,
50
+ "MERGE-I": 3,
51
+ "REPLACE_M": 4,
52
+ "REPLACE_M+REPLACE_O": 5,
53
+ "REPLACE_O": 6,
54
+ "REPLACE_O+REPLACE_X": 7,
55
+ "REPLACE_P": 8,
56
+ "REPLACE_S": 9,
57
+ "REPLACE_X": 10,
58
+ "SPLIT": 11,
59
+ "UC": 12
60
+ },
61
+ "ged_num_labels": 13,
62
+ "gradient_checkpointing": false,
63
+ "id2label": {
64
+ "0": "LABEL_0",
65
+ "1": "LABEL_1",
66
+ "2": "LABEL_2"
67
+ },
68
+ "init_std": 0.02,
69
+ "is_encoder_decoder": true,
70
+ "label2id": {
71
+ "LABEL_0": 0,
72
+ "LABEL_1": 1,
73
+ "LABEL_2": 2
74
+ },
75
+ "max_position_embeddings": 1024,
76
+ "model_type": "mbart",
77
+ "no_repeat_ngram_size": 3,
78
+ "normalize_before": true,
79
+ "normalize_embedding": true,
80
+ "num_beams": 4,
81
+ "num_hidden_layers": 6,
82
+ "pad_token_id": 1,
83
+ "scale_embedding": false,
84
+ "static_position_embeddings": false,
85
+ "tokenizer_class": "BarthezTokenizer",
86
+ "torch_dtype": "float32",
87
+ "transformers_version": "4.22.2",
88
+ "use_cache": true,
89
+ "vocab_size": 50002
90
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb29d62e91a92b0363929d97567764d43398eab438f28bc4968a3d62a84a25a7
3
+ size 557213999
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbb59d772bc9bb2da5dc4a73a00c61c0912c6d2596aad970fa2cd3d69898b245
3
+ size 1315170
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "__type": "AddedToken",
7
+ "content": "<mask>",
8
+ "lstrip": true,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "name_or_path": "/scratch/ba63/BERT_models/AraBART",
14
+ "pad_token": "<pad>",
15
+ "sep_token": "</s>",
16
+ "sp_model_kwargs": {},
17
+ "special_tokens_map_file": null,
18
+ "tokenizer_class": "BarthezTokenizer",
19
+ "unk_token": "<unk>"
20
+ }
trainer_state.json ADDED
@@ -0,0 +1,148 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 8.856682769726248,
5
+ "global_step": 11000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.4,
12
+ "learning_rate": 4.7987117552334945e-05,
13
+ "loss": 0.6228,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.81,
18
+ "learning_rate": 4.597423510466989e-05,
19
+ "loss": 0.4692,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 1.21,
24
+ "learning_rate": 4.396135265700484e-05,
25
+ "loss": 0.4092,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 1.61,
30
+ "learning_rate": 4.194847020933977e-05,
31
+ "loss": 0.3743,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 2.01,
36
+ "learning_rate": 3.993558776167472e-05,
37
+ "loss": 0.3588,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 2.42,
42
+ "learning_rate": 3.7922705314009665e-05,
43
+ "loss": 0.3095,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 2.82,
48
+ "learning_rate": 3.590982286634461e-05,
49
+ "loss": 0.3107,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 3.22,
54
+ "learning_rate": 3.389694041867955e-05,
55
+ "loss": 0.2899,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 3.62,
60
+ "learning_rate": 3.188405797101449e-05,
61
+ "loss": 0.2695,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 4.03,
66
+ "learning_rate": 2.9871175523349438e-05,
67
+ "loss": 0.2674,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 4.43,
72
+ "learning_rate": 2.7858293075684384e-05,
73
+ "loss": 0.2422,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 4.83,
78
+ "learning_rate": 2.5845410628019323e-05,
79
+ "loss": 0.2407,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 5.23,
84
+ "learning_rate": 2.383252818035427e-05,
85
+ "loss": 0.2228,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 5.64,
90
+ "learning_rate": 2.1819645732689212e-05,
91
+ "loss": 0.2172,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 6.04,
96
+ "learning_rate": 1.9806763285024154e-05,
97
+ "loss": 0.2167,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 6.44,
102
+ "learning_rate": 1.77938808373591e-05,
103
+ "loss": 0.1963,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 6.84,
108
+ "learning_rate": 1.5780998389694043e-05,
109
+ "loss": 0.2008,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 7.25,
114
+ "learning_rate": 1.3768115942028985e-05,
115
+ "loss": 0.1892,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 7.65,
120
+ "learning_rate": 1.175523349436393e-05,
121
+ "loss": 0.1842,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 8.05,
126
+ "learning_rate": 9.742351046698874e-06,
127
+ "loss": 0.1843,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 8.45,
132
+ "learning_rate": 7.729468599033817e-06,
133
+ "loss": 0.1742,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 8.86,
138
+ "learning_rate": 5.71658615136876e-06,
139
+ "loss": 0.1733,
140
+ "step": 11000
141
+ }
142
+ ],
143
+ "max_steps": 12420,
144
+ "num_train_epochs": 10,
145
+ "total_flos": 1.2707766784548864e+16,
146
+ "trial_name": null,
147
+ "trial_params": null
148
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acb9f91702ab3f1e9ca3eec46e9a7938dfe15cf130f5ecf75331628163566223
3
+ size 3567