Hugging Face's logo

CAMeL-Lab
/
arabart-qalb15-gec-ged-13

Text2Text Generation
Transformers
PyTorch
Arabic
mbart
Inference Endpoints
Model card Files Community
1
balhafni commited on
Commit
4a8db7b
•
1 Parent(s): 74cce35

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 +169 -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:ba06a93c432f7dcc2816cbea198ad61dcf1adff82e3cbdd0deb92493c202cbe7
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 +1,169 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 10.0,
5
+ "global_step": 12330,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.41,
12
+ "learning_rate": 4.797242497972425e-05,
13
+ "loss": 0.6204,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.81,
18
+ "learning_rate": 4.59448499594485e-05,
19
+ "loss": 0.48,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 1.22,
24
+ "learning_rate": 4.3917274939172754e-05,
25
+ "loss": 0.4046,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 1.62,
30
+ "learning_rate": 4.1889699918897e-05,
31
+ "loss": 0.3753,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 2.03,
36
+ "learning_rate": 3.986212489862125e-05,
37
+ "loss": 0.3585,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 2.43,
42
+ "learning_rate": 3.78345498783455e-05,
43
+ "loss": 0.3135,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 2.84,
48
+ "learning_rate": 3.580697485806975e-05,
49
+ "loss": 0.3133,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 3.24,
54
+ "learning_rate": 3.3779399837794e-05,
55
+ "loss": 0.2859,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 3.65,
60
+ "learning_rate": 3.175182481751825e-05,
61
+ "loss": 0.2699,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 4.06,
66
+ "learning_rate": 2.9724249797242497e-05,
67
+ "loss": 0.2659,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 4.46,
72
+ "learning_rate": 2.7696674776966745e-05,
73
+ "loss": 0.2406,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 4.87,
78
+ "learning_rate": 2.5669099756691e-05,
79
+ "loss": 0.243,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 5.27,
84
+ "learning_rate": 2.3641524736415248e-05,
85
+ "loss": 0.2233,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 5.68,
90
+ "learning_rate": 2.1613949716139496e-05,
91
+ "loss": 0.2175,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 6.08,
96
+ "learning_rate": 1.9586374695863748e-05,
97
+ "loss": 0.2141,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 6.49,
102
+ "learning_rate": 1.7558799675587996e-05,
103
+ "loss": 0.1998,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 6.89,
108
+ "learning_rate": 1.5531224655312247e-05,
109
+ "loss": 0.1982,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 7.3,
114
+ "learning_rate": 1.3503649635036497e-05,
115
+ "loss": 0.188,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 7.7,
120
+ "learning_rate": 1.1476074614760747e-05,
121
+ "loss": 0.1835,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 8.11,
126
+ "learning_rate": 9.448499594484997e-06,
127
+ "loss": 0.1825,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 8.52,
132
+ "learning_rate": 7.420924574209247e-06,
133
+ "loss": 0.1745,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 8.92,
138
+ "learning_rate": 5.393349553933496e-06,
139
+ "loss": 0.1752,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 9.33,
144
+ "learning_rate": 3.365774533657746e-06,
145
+ "loss": 0.17,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 9.73,
150
+ "learning_rate": 1.3381995133819951e-06,
151
+ "loss": 0.167,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 10.0,
156
+ "step": 12330,
157
+ "total_flos": 1.2986290396643328e+16,
158
+ "train_loss": 0.26658661773508385,
159
+ "train_runtime": 2799.7511,
160
+ "train_samples_per_second": 70.438,
161
+ "train_steps_per_second": 4.404
162
+ }
163
+ ],
164
+ "max_steps": 12330,
165
+ "num_train_epochs": 10,
166
+ "total_flos": 1.2986290396643328e+16,
167
+ "trial_name": null,
168
+ "trial_params": null
169
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5097a21d0f2768c74a30fbcaaa9e2b3fd522d5f21915d3bd3b57cb1df0e4c349
3
+ size 3631