malmarjeh commited on
Commit
7b00810
1 Parent(s): e0f32ca

add model files

Browse files
config.json ADDED
@@ -0,0 +1,161 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./drive/MyDrive/newarabert2arabert/checkpoint-3000",
3
+ "architectures": [
4
+ "EncoderDecoderModel"
5
+ ],
6
+ "decoder": {
7
+ "_name_or_path": "aubmindlab/bert-base-arabertv02",
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
+ "decoder_start_token_id": null,
17
+ "diversity_penalty": 0.0,
18
+ "do_sample": false,
19
+ "early_stopping": false,
20
+ "encoder_no_repeat_ngram_size": 0,
21
+ "eos_token_id": null,
22
+ "finetuning_task": null,
23
+ "forced_bos_token_id": null,
24
+ "forced_eos_token_id": null,
25
+ "gradient_checkpointing": false,
26
+ "hidden_act": "gelu",
27
+ "hidden_dropout_prob": 0.1,
28
+ "hidden_size": 768,
29
+ "id2label": {
30
+ "0": "LABEL_0",
31
+ "1": "LABEL_1"
32
+ },
33
+ "initializer_range": 0.02,
34
+ "intermediate_size": 3072,
35
+ "is_decoder": true,
36
+ "is_encoder_decoder": false,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1
40
+ },
41
+ "layer_norm_eps": 1e-12,
42
+ "length_penalty": 1.0,
43
+ "max_length": 20,
44
+ "max_position_embeddings": 512,
45
+ "min_length": 0,
46
+ "model_type": "bert",
47
+ "no_repeat_ngram_size": 0,
48
+ "num_attention_heads": 12,
49
+ "num_beam_groups": 1,
50
+ "num_beams": 1,
51
+ "num_hidden_layers": 12,
52
+ "num_return_sequences": 1,
53
+ "output_attentions": false,
54
+ "output_hidden_states": false,
55
+ "output_scores": false,
56
+ "pad_token_id": 0,
57
+ "position_embedding_type": "absolute",
58
+ "prefix": null,
59
+ "pruned_heads": {},
60
+ "remove_invalid_values": false,
61
+ "repetition_penalty": 1.0,
62
+ "return_dict": true,
63
+ "return_dict_in_generate": false,
64
+ "sep_token_id": null,
65
+ "task_specific_params": null,
66
+ "temperature": 1.0,
67
+ "tie_encoder_decoder": false,
68
+ "tie_word_embeddings": true,
69
+ "tokenizer_class": null,
70
+ "top_k": 50,
71
+ "top_p": 1.0,
72
+ "torchscript": false,
73
+ "transformers_version": "4.5.1",
74
+ "type_vocab_size": 2,
75
+ "use_bfloat16": false,
76
+ "use_cache": true,
77
+ "vocab_size": 64000
78
+ },
79
+ "decoder_start_token_id": 2,
80
+ "encoder": {
81
+ "_name_or_path": "aubmindlab/bert-base-arabertv02",
82
+ "add_cross_attention": false,
83
+ "architectures": [
84
+ "BertForMaskedLM"
85
+ ],
86
+ "attention_probs_dropout_prob": 0.1,
87
+ "bad_words_ids": null,
88
+ "bos_token_id": null,
89
+ "chunk_size_feed_forward": 0,
90
+ "decoder_start_token_id": null,
91
+ "diversity_penalty": 0.0,
92
+ "do_sample": false,
93
+ "early_stopping": false,
94
+ "encoder_no_repeat_ngram_size": 0,
95
+ "eos_token_id": null,
96
+ "finetuning_task": null,
97
+ "forced_bos_token_id": null,
98
+ "forced_eos_token_id": null,
99
+ "gradient_checkpointing": false,
100
+ "hidden_act": "gelu",
101
+ "hidden_dropout_prob": 0.1,
102
+ "hidden_size": 768,
103
+ "id2label": {
104
+ "0": "LABEL_0",
105
+ "1": "LABEL_1"
106
+ },
107
+ "initializer_range": 0.02,
108
+ "intermediate_size": 3072,
109
+ "is_decoder": false,
110
+ "is_encoder_decoder": false,
111
+ "label2id": {
112
+ "LABEL_0": 0,
113
+ "LABEL_1": 1
114
+ },
115
+ "layer_norm_eps": 1e-12,
116
+ "length_penalty": 1.0,
117
+ "max_length": 20,
118
+ "max_position_embeddings": 512,
119
+ "min_length": 0,
120
+ "model_type": "bert",
121
+ "no_repeat_ngram_size": 0,
122
+ "num_attention_heads": 12,
123
+ "num_beam_groups": 1,
124
+ "num_beams": 1,
125
+ "num_hidden_layers": 12,
126
+ "num_return_sequences": 1,
127
+ "output_attentions": false,
128
+ "output_hidden_states": false,
129
+ "output_scores": false,
130
+ "pad_token_id": 0,
131
+ "position_embedding_type": "absolute",
132
+ "prefix": null,
133
+ "pruned_heads": {},
134
+ "remove_invalid_values": false,
135
+ "repetition_penalty": 1.0,
136
+ "return_dict": true,
137
+ "return_dict_in_generate": false,
138
+ "sep_token_id": null,
139
+ "task_specific_params": null,
140
+ "temperature": 1.0,
141
+ "tie_encoder_decoder": false,
142
+ "tie_word_embeddings": true,
143
+ "tokenizer_class": null,
144
+ "top_k": 50,
145
+ "top_p": 1.0,
146
+ "torchscript": false,
147
+ "transformers_version": "4.5.1",
148
+ "type_vocab_size": 2,
149
+ "use_bfloat16": false,
150
+ "use_cache": true,
151
+ "vocab_size": 64000
152
+ },
153
+ "eos_token_id": 3,
154
+ "is_encoder_decoder": true,
155
+ "max_length": 40,
156
+ "min_length": 5,
157
+ "model_type": "encoder-decoder",
158
+ "pad_token_id": 0,
159
+ "tie_encoder_decoder": true,
160
+ "vocab_size": 64000
161
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dceeb5a8a01c897a7d7c06777b8b2fce0d66b7066b09415ba69ab46d506bc7f1
3
+ size 657051701
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1044ceb5b647c56afbb08c6929b94dc48bb0c2857ce2535924aa0d7aeee1751
3
+ size 623
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "max_len": 512, "do_basic_tokenize": true, "never_split": ["[بريد]", "[مستخدم]", "[رابط]"], "special_tokens_map_file": null, "name_or_path": "aubmindlab/bert-base-arabertv02"}
trainer_state.json ADDED
@@ -0,0 +1,128 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9546317788562986,
5
+ "global_step": 7000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.42,
12
+ "learning_rate": 3.3333333333333335e-05,
13
+ "loss": 6.0161,
14
+ "step": 1000
15
+ },
16
+ {
17
+ "epoch": 0.42,
18
+ "eval_loss": 3.9784154891967773,
19
+ "eval_rouge-1": 0.1824,
20
+ "eval_rouge-2": 0.046,
21
+ "eval_rouge-l": 0.1728,
22
+ "eval_runtime": 265.003,
23
+ "eval_samples_per_second": 15.751,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.84,
28
+ "learning_rate": 4.8873366381252815e-05,
29
+ "loss": 3.6793,
30
+ "step": 2000
31
+ },
32
+ {
33
+ "epoch": 0.84,
34
+ "eval_loss": 2.9924702644348145,
35
+ "eval_rouge-1": 0.3283,
36
+ "eval_rouge-2": 0.1385,
37
+ "eval_rouge-l": 0.3123,
38
+ "eval_runtime": 236.629,
39
+ "eval_samples_per_second": 17.639,
40
+ "step": 2000
41
+ },
42
+ {
43
+ "epoch": 1.27,
44
+ "learning_rate": 4.662009914375845e-05,
45
+ "loss": 2.7635,
46
+ "step": 3000
47
+ },
48
+ {
49
+ "epoch": 1.27,
50
+ "eval_loss": 2.58980655670166,
51
+ "eval_rouge-1": 0.3955,
52
+ "eval_rouge-2": 0.2061,
53
+ "eval_rouge-l": 0.3776,
54
+ "eval_runtime": 233.9394,
55
+ "eval_samples_per_second": 17.842,
56
+ "step": 3000
57
+ },
58
+ {
59
+ "epoch": 1.69,
60
+ "learning_rate": 4.4366831906264086e-05,
61
+ "loss": 2.2888,
62
+ "step": 4000
63
+ },
64
+ {
65
+ "epoch": 1.69,
66
+ "eval_loss": 2.4224066734313965,
67
+ "eval_rouge-1": 0.42,
68
+ "eval_rouge-2": 0.2296,
69
+ "eval_rouge-l": 0.4011,
70
+ "eval_runtime": 459.7714,
71
+ "eval_samples_per_second": 9.078,
72
+ "step": 4000
73
+ },
74
+ {
75
+ "epoch": 2.11,
76
+ "learning_rate": 4.211356466876972e-05,
77
+ "loss": 2.1166,
78
+ "step": 5000
79
+ },
80
+ {
81
+ "epoch": 2.11,
82
+ "eval_loss": 2.343660593032837,
83
+ "eval_rouge-1": 0.4335,
84
+ "eval_rouge-2": 0.2425,
85
+ "eval_rouge-l": 0.413,
86
+ "eval_runtime": 449.5335,
87
+ "eval_samples_per_second": 9.285,
88
+ "step": 5000
89
+ },
90
+ {
91
+ "epoch": 2.53,
92
+ "learning_rate": 3.986029743127535e-05,
93
+ "loss": 1.8642,
94
+ "step": 6000
95
+ },
96
+ {
97
+ "epoch": 2.53,
98
+ "eval_loss": 2.2839481830596924,
99
+ "eval_rouge-1": 0.4426,
100
+ "eval_rouge-2": 0.2535,
101
+ "eval_rouge-l": 0.4222,
102
+ "eval_runtime": 453.1272,
103
+ "eval_samples_per_second": 9.212,
104
+ "step": 6000
105
+ },
106
+ {
107
+ "epoch": 2.95,
108
+ "learning_rate": 3.760703019378098e-05,
109
+ "loss": 1.8616,
110
+ "step": 7000
111
+ },
112
+ {
113
+ "epoch": 2.95,
114
+ "eval_loss": 2.220813035964966,
115
+ "eval_rouge-1": 0.4475,
116
+ "eval_rouge-2": 0.262,
117
+ "eval_rouge-l": 0.4285,
118
+ "eval_runtime": 443.175,
119
+ "eval_samples_per_second": 9.418,
120
+ "step": 7000
121
+ }
122
+ ],
123
+ "max_steps": 23690,
124
+ "num_train_epochs": 10,
125
+ "total_flos": 3.3108670416384e+16,
126
+ "trial_name": null,
127
+ "trial_params": null
128
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4145272078873899f09993f5a6a2afb00703ef597e2f79410f79f3571ba2e3d1
3
+ size 2415
vocab.txt ADDED
The diff for this file is too large to render. See raw diff