janbakker commited on
Commit
61e26ca
1 Parent(s): 0d1cddc

Upload BartForConditionalGeneration

Browse files
Files changed (3) hide show
  1. config.json +176 -0
  2. generation_config.json +13 -0
  3. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,176 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/bart-base",
3
+ "accelerator": null,
4
+ "accumulate_grad_batches": 2,
5
+ "activation_dropout": 0.1,
6
+ "activation_function": "gelu",
7
+ "add_bias_logits": false,
8
+ "add_context": false,
9
+ "add_final_layer_norm": false,
10
+ "amp_backend": null,
11
+ "amp_level": null,
12
+ "architectures": [
13
+ "BartForConditionalGeneration"
14
+ ],
15
+ "attention_dropout": 0.1,
16
+ "auto_lr_find": false,
17
+ "auto_scale_batch_size": false,
18
+ "auto_select_gpus": null,
19
+ "batch_size": 8,
20
+ "benchmark": null,
21
+ "bos_token_id": 0,
22
+ "check_val_every_n_epoch": 1,
23
+ "checkpoint": null,
24
+ "class_labels": {
25
+ "delete": 3,
26
+ "ignore": 0,
27
+ "rephrase": 1,
28
+ "split": 2
29
+ },
30
+ "classif_dropout": 0.1,
31
+ "classifier_dropout": 0.0,
32
+ "context_dir": null,
33
+ "context_doc_id": null,
34
+ "context_window": 13,
35
+ "d_model": 768,
36
+ "decoder_attention_heads": 12,
37
+ "decoder_ffn_dim": 3072,
38
+ "decoder_layerdrop": 0.0,
39
+ "decoder_layers": 6,
40
+ "decoder_start_token_id": 2,
41
+ "default_root_dir": null,
42
+ "detect_anomaly": false,
43
+ "devices": "2",
44
+ "dropout": 0.1,
45
+ "early_stopping": true,
46
+ "enable_checkpointing": true,
47
+ "enable_model_summary": true,
48
+ "enable_progress_bar": true,
49
+ "encoder_attention_heads": 12,
50
+ "encoder_ffn_dim": 3072,
51
+ "encoder_layerdrop": 0.0,
52
+ "encoder_layers": 6,
53
+ "eos_token_id": 2,
54
+ "eval_beams": null,
55
+ "eval_max_length": null,
56
+ "fast_dev_run": false,
57
+ "forced_bos_token_id": 0,
58
+ "forced_eos_token_id": 2,
59
+ "gpus": null,
60
+ "gradient_checkpointing": false,
61
+ "gradient_clip_algorithm": null,
62
+ "gradient_clip_val": null,
63
+ "id2label": {
64
+ "0": "LABEL_0",
65
+ "1": "LABEL_1",
66
+ "2": "LABEL_2"
67
+ },
68
+ "inference_mode": true,
69
+ "init_std": 0.02,
70
+ "ipus": null,
71
+ "is_encoder_decoder": true,
72
+ "label2id": {
73
+ "LABEL_0": 0,
74
+ "LABEL_1": 1,
75
+ "LABEL_2": 2
76
+ },
77
+ "limit_predict_batches": null,
78
+ "limit_test_batches": null,
79
+ "limit_train_batches": null,
80
+ "limit_val_batches": null,
81
+ "log_every_n_steps": 50,
82
+ "logger": true,
83
+ "longformer": false,
84
+ "lr": 2e-05,
85
+ "lr_scheduler": false,
86
+ "max_epochs": null,
87
+ "max_length": 1024,
88
+ "max_position_embeddings": 1024,
89
+ "max_samples": -1,
90
+ "max_steps": -1,
91
+ "max_time": null,
92
+ "min_epochs": null,
93
+ "min_steps": null,
94
+ "model_type": "bart",
95
+ "move_metrics_to_cpu": false,
96
+ "multiple_trainloader_mode": "max_size_cycle",
97
+ "name": "o-bart-para",
98
+ "no_repeat_ngram_size": 3,
99
+ "normalize_before": false,
100
+ "normalize_embedding": true,
101
+ "num_beams": 4,
102
+ "num_hidden_layers": 6,
103
+ "num_nodes": 1,
104
+ "num_processes": null,
105
+ "num_sanity_val_steps": 2,
106
+ "op_col": "label",
107
+ "op_tokens": [
108
+ "<COPY>",
109
+ "<REPHRASE>",
110
+ "<SPLIT>",
111
+ "<DELETE>"
112
+ ],
113
+ "overfit_batches": 0.0,
114
+ "pad_token_id": 1,
115
+ "plan_col": "labels",
116
+ "plan_loss": null,
117
+ "plan_prefix": false,
118
+ "plan_sep": false,
119
+ "plugins": null,
120
+ "precision": 32,
121
+ "prefix_only": false,
122
+ "profiler": null,
123
+ "project": "simplification_models",
124
+ "reading_lvl": null,
125
+ "reload_dataloaders_every_n_epochs": 0,
126
+ "replace_sampler_ddp": true,
127
+ "resume_from_checkpoint": null,
128
+ "save_dir": null,
129
+ "scale_embedding": false,
130
+ "sent_level": true,
131
+ "simple_context_dir": null,
132
+ "simple_context_doc_id": null,
133
+ "skip_val_gen": true,
134
+ "strategy": null,
135
+ "sync_batchnorm": false,
136
+ "task_specific_params": {
137
+ "summarization": {
138
+ "length_penalty": 1.0,
139
+ "max_length": 128,
140
+ "min_length": 12,
141
+ "num_beams": 4
142
+ },
143
+ "summarization_cnn": {
144
+ "length_penalty": 2.0,
145
+ "max_length": 142,
146
+ "min_length": 56,
147
+ "num_beams": 4
148
+ },
149
+ "summarization_xsum": {
150
+ "length_penalty": 1.0,
151
+ "max_length": 62,
152
+ "min_length": 11,
153
+ "num_beams": 6
154
+ }
155
+ },
156
+ "torch_dtype": "float32",
157
+ "tpu_cores": null,
158
+ "track_grad_norm": -1,
159
+ "train_check_interval": 0.01,
160
+ "train_data_dir": null,
161
+ "train_file": "data/wikiauto_para_train.csv",
162
+ "train_split": 0.9,
163
+ "train_workers": 32,
164
+ "transformers_version": "4.29.1",
165
+ "use_cache": true,
166
+ "val_check_interval": null,
167
+ "val_file": "data/wikiauto_para_valid.csv",
168
+ "val_metric": "bleu",
169
+ "val_split": 0.05,
170
+ "val_workers": 8,
171
+ "valid_data_dir": null,
172
+ "vocab_size": 50274,
173
+ "wandb_id": null,
174
+ "x_col": "complex",
175
+ "y_col": "simple"
176
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "early_stopping": true,
6
+ "eos_token_id": 2,
7
+ "forced_bos_token_id": 0,
8
+ "forced_eos_token_id": 2,
9
+ "no_repeat_ngram_size": 3,
10
+ "num_beams": 4,
11
+ "pad_token_id": 1,
12
+ "transformers_version": "4.29.1"
13
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:220dd285903d49bbadafe91ffdd8b1c4f52d1ead754d6f7927ee894c63726a6a
3
+ size 557998941