lilouuch commited on
Commit
de90efa
1 Parent(s): 45f9514

Training in progress, step 500

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,187 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "malmarjeh/mbert2mbert-arabic-text-summarization",
3
+ "architectures": [
4
+ "EncoderDecoderModel"
5
+ ],
6
+ "decoder": {
7
+ "_name_or_path": "bert-base-multilingual-cased",
8
+ "add_cross_attention": true,
9
+ "architectures": [
10
+ "BertForMaskedLM"
11
+ ],
12
+ "attention_probs_dropout_prob": 0.1,
13
+ "bad_words_ids": null,
14
+ "bos_token_id": null,
15
+ "chunk_size_feed_forward": 0,
16
+ "classifier_dropout": null,
17
+ "cross_attention_hidden_size": null,
18
+ "decoder_start_token_id": null,
19
+ "directionality": "bidi",
20
+ "diversity_penalty": 0.0,
21
+ "do_sample": false,
22
+ "early_stopping": false,
23
+ "encoder_no_repeat_ngram_size": 0,
24
+ "eos_token_id": null,
25
+ "exponential_decay_length_penalty": null,
26
+ "finetuning_task": null,
27
+ "forced_bos_token_id": null,
28
+ "forced_eos_token_id": null,
29
+ "gradient_checkpointing": false,
30
+ "hidden_act": "gelu",
31
+ "hidden_dropout_prob": 0.1,
32
+ "hidden_size": 768,
33
+ "id2label": {
34
+ "0": "LABEL_0",
35
+ "1": "LABEL_1"
36
+ },
37
+ "initializer_range": 0.02,
38
+ "intermediate_size": 3072,
39
+ "is_decoder": true,
40
+ "is_encoder_decoder": false,
41
+ "label2id": {
42
+ "LABEL_0": 0,
43
+ "LABEL_1": 1
44
+ },
45
+ "layer_norm_eps": 1e-12,
46
+ "length_penalty": 1.0,
47
+ "max_length": 20,
48
+ "max_position_embeddings": 512,
49
+ "min_length": 0,
50
+ "model_type": "bert",
51
+ "no_repeat_ngram_size": 0,
52
+ "num_attention_heads": 12,
53
+ "num_beam_groups": 1,
54
+ "num_beams": 1,
55
+ "num_hidden_layers": 12,
56
+ "num_return_sequences": 1,
57
+ "output_attentions": false,
58
+ "output_hidden_states": false,
59
+ "output_scores": false,
60
+ "pad_token_id": 0,
61
+ "pooler_fc_size": 768,
62
+ "pooler_num_attention_heads": 12,
63
+ "pooler_num_fc_layers": 3,
64
+ "pooler_size_per_head": 128,
65
+ "pooler_type": "first_token_transform",
66
+ "position_embedding_type": "absolute",
67
+ "prefix": null,
68
+ "problem_type": null,
69
+ "pruned_heads": {},
70
+ "remove_invalid_values": false,
71
+ "repetition_penalty": 1.0,
72
+ "return_dict": true,
73
+ "return_dict_in_generate": false,
74
+ "sep_token_id": null,
75
+ "task_specific_params": null,
76
+ "temperature": 1.0,
77
+ "tie_encoder_decoder": false,
78
+ "tie_word_embeddings": true,
79
+ "tokenizer_class": null,
80
+ "top_k": 50,
81
+ "top_p": 1.0,
82
+ "torch_dtype": null,
83
+ "torchscript": false,
84
+ "transformers_version": "4.20.1",
85
+ "type_vocab_size": 2,
86
+ "typical_p": 1.0,
87
+ "use_bfloat16": false,
88
+ "use_cache": true,
89
+ "vocab_size": 119547
90
+ },
91
+ "decoder_start_token_id": 101,
92
+ "encoder": {
93
+ "_name_or_path": "bert-base-multilingual-cased",
94
+ "add_cross_attention": false,
95
+ "architectures": [
96
+ "BertForMaskedLM"
97
+ ],
98
+ "attention_probs_dropout_prob": 0.1,
99
+ "bad_words_ids": null,
100
+ "bos_token_id": null,
101
+ "chunk_size_feed_forward": 0,
102
+ "classifier_dropout": null,
103
+ "cross_attention_hidden_size": null,
104
+ "decoder_start_token_id": null,
105
+ "directionality": "bidi",
106
+ "diversity_penalty": 0.0,
107
+ "do_sample": false,
108
+ "early_stopping": false,
109
+ "encoder_no_repeat_ngram_size": 0,
110
+ "eos_token_id": null,
111
+ "exponential_decay_length_penalty": null,
112
+ "finetuning_task": null,
113
+ "forced_bos_token_id": null,
114
+ "forced_eos_token_id": null,
115
+ "gradient_checkpointing": false,
116
+ "hidden_act": "gelu",
117
+ "hidden_dropout_prob": 0.1,
118
+ "hidden_size": 768,
119
+ "id2label": {
120
+ "0": "LABEL_0",
121
+ "1": "LABEL_1"
122
+ },
123
+ "initializer_range": 0.02,
124
+ "intermediate_size": 3072,
125
+ "is_decoder": false,
126
+ "is_encoder_decoder": false,
127
+ "label2id": {
128
+ "LABEL_0": 0,
129
+ "LABEL_1": 1
130
+ },
131
+ "layer_norm_eps": 1e-12,
132
+ "length_penalty": 1.0,
133
+ "max_length": 20,
134
+ "max_position_embeddings": 512,
135
+ "min_length": 0,
136
+ "model_type": "bert",
137
+ "no_repeat_ngram_size": 0,
138
+ "num_attention_heads": 12,
139
+ "num_beam_groups": 1,
140
+ "num_beams": 1,
141
+ "num_hidden_layers": 12,
142
+ "num_return_sequences": 1,
143
+ "output_attentions": false,
144
+ "output_hidden_states": false,
145
+ "output_scores": false,
146
+ "pad_token_id": 0,
147
+ "pooler_fc_size": 768,
148
+ "pooler_num_attention_heads": 12,
149
+ "pooler_num_fc_layers": 3,
150
+ "pooler_size_per_head": 128,
151
+ "pooler_type": "first_token_transform",
152
+ "position_embedding_type": "absolute",
153
+ "prefix": null,
154
+ "problem_type": null,
155
+ "pruned_heads": {},
156
+ "remove_invalid_values": false,
157
+ "repetition_penalty": 1.0,
158
+ "return_dict": true,
159
+ "return_dict_in_generate": false,
160
+ "sep_token_id": null,
161
+ "task_specific_params": null,
162
+ "temperature": 1.0,
163
+ "tie_encoder_decoder": false,
164
+ "tie_word_embeddings": true,
165
+ "tokenizer_class": null,
166
+ "top_k": 50,
167
+ "top_p": 1.0,
168
+ "torch_dtype": null,
169
+ "torchscript": false,
170
+ "transformers_version": "4.20.1",
171
+ "type_vocab_size": 2,
172
+ "typical_p": 1.0,
173
+ "use_bfloat16": false,
174
+ "use_cache": true,
175
+ "vocab_size": 119547
176
+ },
177
+ "eos_token_id": 102,
178
+ "is_encoder_decoder": true,
179
+ "max_length": 42,
180
+ "min_length": 5,
181
+ "model_type": "encoder-decoder",
182
+ "pad_token_id": 0,
183
+ "tie_encoder_decoder": true,
184
+ "torch_dtype": "float32",
185
+ "transformers_version": null,
186
+ "vocab_size": 119547
187
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff4164b7200e9903258c06c53e58e7fafcab8a44d8659539113a0bdd568a0e5b
3
+ size 827876341
runs/Nov04_20-44-33_36bba7ac77d6/1667594688.0566673/events.out.tfevents.1667594688.36bba7ac77d6.84.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8c65dd1731b40176fbb4c04d112acf4d56bd4d8b4603ed76ff1f1809abf1ab7
3
+ size 5770
runs/Nov04_20-44-33_36bba7ac77d6/events.out.tfevents.1667594688.36bba7ac77d6.84.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7abf244f2bc0769302f0fa92cf51d62ee67f95184c21b607b5cb78bbba13a2be
3
+ size 8604
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_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "name_or_path": "malmarjeh/mbert2mbert-arabic-text-summarization",
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "special_tokens_map_file": null,
12
+ "strip_accents": null,
13
+ "tokenize_chinese_chars": true,
14
+ "tokenizer_class": "BertTokenizer",
15
+ "tokenizer_file": "/root/.cache/huggingface/transformers/46880f3b0081fda494a4e15b05787692aa4c1e21e0ff2428ba8b14d4eda0784d.b33e51591f94f17c238ee9b1fac75b96ff2678cbaed6e108feadb3449d18dc24",
16
+ "unk_token": "[UNK]"
17
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46bd3877c818d705b711c688dbf904c6c8cd25dcccb9231aff612836f5a8b8f6
3
+ size 3567
vocab.txt ADDED
The diff for this file is too large to render. See raw diff