karim-Mohamed2018 commited on
Commit
e099ed9
1 Parent(s): 66d0e57

Training in progress, step 500

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,194 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": "3b2e7db2977b89b818b35d9eae4fcd6244ef2c40",
3
+ "_name_or_path": "malmarjeh/mbert2mbert-arabic-text-summarization",
4
+ "architectures": [
5
+ "EncoderDecoderModel"
6
+ ],
7
+ "decoder": {
8
+ "_name_or_path": "bert-base-multilingual-cased",
9
+ "add_cross_attention": true,
10
+ "architectures": [
11
+ "BertForMaskedLM"
12
+ ],
13
+ "attention_probs_dropout_prob": 0.1,
14
+ "bad_words_ids": null,
15
+ "begin_suppress_tokens": null,
16
+ "bos_token_id": null,
17
+ "chunk_size_feed_forward": 0,
18
+ "classifier_dropout": null,
19
+ "cross_attention_hidden_size": null,
20
+ "decoder_start_token_id": null,
21
+ "directionality": "bidi",
22
+ "diversity_penalty": 0.0,
23
+ "do_sample": false,
24
+ "early_stopping": false,
25
+ "encoder_no_repeat_ngram_size": 0,
26
+ "eos_token_id": null,
27
+ "exponential_decay_length_penalty": null,
28
+ "finetuning_task": null,
29
+ "forced_bos_token_id": null,
30
+ "forced_eos_token_id": null,
31
+ "gradient_checkpointing": false,
32
+ "hidden_act": "gelu",
33
+ "hidden_dropout_prob": 0.1,
34
+ "hidden_size": 768,
35
+ "id2label": {
36
+ "0": "LABEL_0",
37
+ "1": "LABEL_1"
38
+ },
39
+ "initializer_range": 0.02,
40
+ "intermediate_size": 3072,
41
+ "is_decoder": true,
42
+ "is_encoder_decoder": false,
43
+ "label2id": {
44
+ "LABEL_0": 0,
45
+ "LABEL_1": 1
46
+ },
47
+ "layer_norm_eps": 1e-12,
48
+ "length_penalty": 1.0,
49
+ "max_length": 20,
50
+ "max_position_embeddings": 512,
51
+ "min_length": 0,
52
+ "model_type": "bert",
53
+ "no_repeat_ngram_size": 0,
54
+ "num_attention_heads": 12,
55
+ "num_beam_groups": 1,
56
+ "num_beams": 1,
57
+ "num_hidden_layers": 12,
58
+ "num_return_sequences": 1,
59
+ "output_attentions": false,
60
+ "output_hidden_states": false,
61
+ "output_scores": false,
62
+ "pad_token_id": 0,
63
+ "pooler_fc_size": 768,
64
+ "pooler_num_attention_heads": 12,
65
+ "pooler_num_fc_layers": 3,
66
+ "pooler_size_per_head": 128,
67
+ "pooler_type": "first_token_transform",
68
+ "position_embedding_type": "absolute",
69
+ "prefix": null,
70
+ "problem_type": null,
71
+ "pruned_heads": {},
72
+ "remove_invalid_values": false,
73
+ "repetition_penalty": 1.0,
74
+ "return_dict": true,
75
+ "return_dict_in_generate": false,
76
+ "sep_token_id": null,
77
+ "suppress_tokens": null,
78
+ "task_specific_params": null,
79
+ "temperature": 1.0,
80
+ "tf_legacy_loss": false,
81
+ "tie_encoder_decoder": false,
82
+ "tie_word_embeddings": true,
83
+ "tokenizer_class": null,
84
+ "top_k": 50,
85
+ "top_p": 1.0,
86
+ "torch_dtype": null,
87
+ "torchscript": false,
88
+ "transformers_version": "4.31.0",
89
+ "type_vocab_size": 2,
90
+ "typical_p": 1.0,
91
+ "use_bfloat16": false,
92
+ "use_cache": true,
93
+ "vocab_size": 119547
94
+ },
95
+ "decoder_start_token_id": 101,
96
+ "encoder": {
97
+ "_name_or_path": "bert-base-multilingual-cased",
98
+ "add_cross_attention": false,
99
+ "architectures": [
100
+ "BertForMaskedLM"
101
+ ],
102
+ "attention_probs_dropout_prob": 0.1,
103
+ "bad_words_ids": null,
104
+ "begin_suppress_tokens": null,
105
+ "bos_token_id": null,
106
+ "chunk_size_feed_forward": 0,
107
+ "classifier_dropout": null,
108
+ "cross_attention_hidden_size": null,
109
+ "decoder_start_token_id": null,
110
+ "directionality": "bidi",
111
+ "diversity_penalty": 0.0,
112
+ "do_sample": false,
113
+ "early_stopping": false,
114
+ "encoder_no_repeat_ngram_size": 0,
115
+ "eos_token_id": null,
116
+ "exponential_decay_length_penalty": null,
117
+ "finetuning_task": null,
118
+ "forced_bos_token_id": null,
119
+ "forced_eos_token_id": null,
120
+ "gradient_checkpointing": false,
121
+ "hidden_act": "gelu",
122
+ "hidden_dropout_prob": 0.1,
123
+ "hidden_size": 768,
124
+ "id2label": {
125
+ "0": "LABEL_0",
126
+ "1": "LABEL_1"
127
+ },
128
+ "initializer_range": 0.02,
129
+ "intermediate_size": 3072,
130
+ "is_decoder": false,
131
+ "is_encoder_decoder": false,
132
+ "label2id": {
133
+ "LABEL_0": 0,
134
+ "LABEL_1": 1
135
+ },
136
+ "layer_norm_eps": 1e-12,
137
+ "length_penalty": 1.0,
138
+ "max_length": 20,
139
+ "max_position_embeddings": 512,
140
+ "min_length": 0,
141
+ "model_type": "bert",
142
+ "no_repeat_ngram_size": 0,
143
+ "num_attention_heads": 12,
144
+ "num_beam_groups": 1,
145
+ "num_beams": 1,
146
+ "num_hidden_layers": 12,
147
+ "num_return_sequences": 1,
148
+ "output_attentions": false,
149
+ "output_hidden_states": false,
150
+ "output_scores": false,
151
+ "pad_token_id": 0,
152
+ "pooler_fc_size": 768,
153
+ "pooler_num_attention_heads": 12,
154
+ "pooler_num_fc_layers": 3,
155
+ "pooler_size_per_head": 128,
156
+ "pooler_type": "first_token_transform",
157
+ "position_embedding_type": "absolute",
158
+ "prefix": null,
159
+ "problem_type": null,
160
+ "pruned_heads": {},
161
+ "remove_invalid_values": false,
162
+ "repetition_penalty": 1.0,
163
+ "return_dict": true,
164
+ "return_dict_in_generate": false,
165
+ "sep_token_id": null,
166
+ "suppress_tokens": null,
167
+ "task_specific_params": null,
168
+ "temperature": 1.0,
169
+ "tf_legacy_loss": false,
170
+ "tie_encoder_decoder": false,
171
+ "tie_word_embeddings": true,
172
+ "tokenizer_class": null,
173
+ "top_k": 50,
174
+ "top_p": 1.0,
175
+ "torch_dtype": null,
176
+ "torchscript": false,
177
+ "transformers_version": "4.31.0",
178
+ "type_vocab_size": 2,
179
+ "typical_p": 1.0,
180
+ "use_bfloat16": false,
181
+ "use_cache": true,
182
+ "vocab_size": 119547
183
+ },
184
+ "eos_token_id": 102,
185
+ "is_encoder_decoder": true,
186
+ "max_length": 42,
187
+ "min_length": 5,
188
+ "model_type": "encoder-decoder",
189
+ "pad_token_id": 0,
190
+ "tie_encoder_decoder": true,
191
+ "torch_dtype": "float32",
192
+ "transformers_version": null,
193
+ "vocab_size": 119547
194
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e90d74e2a3c0fb7fd1d1b13dcb1f15a965c2e1469cb90c64f40df409d3427f3
3
+ size 827870045
runs/Aug12_20-37-38_98917316cc08/events.out.tfevents.1691872817.98917316cc08.7515.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b67b0e30db063da9770bd5cec005abd488ad0bd3cbdbb52cfaf902c291c0bf83
3
+ size 9221
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 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": false,
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 512,
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "tokenizer_file": "/root/.cache/huggingface/transformers/46880f3b0081fda494a4e15b05787692aa4c1e21e0ff2428ba8b14d4eda0784d.b33e51591f94f17c238ee9b1fac75b96ff2678cbaed6e108feadb3449d18dc24",
15
+ "unk_token": "[UNK]"
16
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db1a98a30e5c5bf291544d12d384cefe9fdbcb7fc85828f81790d410fed238a5
3
+ size 4155
vocab.txt ADDED
The diff for this file is too large to render. See raw diff