ireneli1024 commited on
Commit
25da4af
1 Parent(s): e511347

Upload 13 files

Browse files
config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/bart-large",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "BartForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.1,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.1,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 1024,
15
+ "decoder_attention_heads": 16,
16
+ "decoder_ffn_dim": 4096,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 12,
19
+ "decoder_start_token_id": 2,
20
+ "dropout": 0.1,
21
+ "early_stopping": true,
22
+ "encoder_attention_heads": 16,
23
+ "encoder_ffn_dim": 4096,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 12,
26
+ "eos_token_id": 2,
27
+ "forced_bos_token_id": 0,
28
+ "forced_eos_token_id": 2,
29
+ "gradient_checkpointing": false,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1",
33
+ "2": "LABEL_2"
34
+ },
35
+ "init_std": 0.02,
36
+ "is_encoder_decoder": true,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1,
40
+ "LABEL_2": 2
41
+ },
42
+ "max_position_embeddings": 1024,
43
+ "model_type": "bart",
44
+ "no_repeat_ngram_size": 3,
45
+ "normalize_before": false,
46
+ "num_beams": 4,
47
+ "num_hidden_layers": 12,
48
+ "pad_token_id": 1,
49
+ "scale_embedding": false,
50
+ "task_specific_params": {
51
+ "summarization": {
52
+ "length_penalty": 1.0,
53
+ "max_length": 128,
54
+ "min_length": 12,
55
+ "num_beams": 4
56
+ },
57
+ "summarization_cnn": {
58
+ "length_penalty": 2.0,
59
+ "max_length": 142,
60
+ "min_length": 56,
61
+ "num_beams": 4
62
+ },
63
+ "summarization_xsum": {
64
+ "length_penalty": 1.0,
65
+ "max_length": 62,
66
+ "min_length": 11,
67
+ "num_beams": 6
68
+ }
69
+ },
70
+ "torch_dtype": "float32",
71
+ "transformers_version": "4.28.0",
72
+ "use_cache": true,
73
+ "vocab_size": 50265
74
+ }
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": "4.28.0"
13
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41fb03dd51a9d541a9ba4d4449ac81e61c4618fb5cf21881540b2042a2b3da8a
3
+ size 3250632155
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f96552718640c76cfc1c452bf23d56ca99b8a1622b2dd3512a928f81df35fb22
3
+ size 1625541389
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32b0836ed24a530fcb991c87dc4a1bd004f6ca357c92d41a8209443dd8147a70
3
+ size 15597
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdb3a07d02472a0c7263892683f16fb010db062c726c2f5630f74b29bd08c4bc
3
+ size 627
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": false,
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 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "cls_token": "<s>",
6
+ "eos_token": "</s>",
7
+ "errors": "replace",
8
+ "mask_token": "<mask>",
9
+ "model_max_length": 1024,
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "tokenizer_class": "BartTokenizer",
13
+ "trim_offsets": true,
14
+ "unk_token": "<unk>"
15
+ }
trainer_state.json ADDED
@@ -0,0 +1,136 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.4188034188034186,
5
+ "global_step": 10000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.17,
12
+ "learning_rate": 1e-05,
13
+ "loss": 2.58,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.34,
18
+ "learning_rate": 2e-05,
19
+ "loss": 2.3914,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.51,
24
+ "learning_rate": 1.888888888888889e-05,
25
+ "loss": 2.3582,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.68,
30
+ "learning_rate": 1.7777777777777777e-05,
31
+ "loss": 2.302,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.85,
36
+ "learning_rate": 1.6666666666666667e-05,
37
+ "loss": 2.2656,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 1.03,
42
+ "learning_rate": 1.555555555555556e-05,
43
+ "loss": 2.2412,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 1.2,
48
+ "learning_rate": 1.4444444444444446e-05,
49
+ "loss": 2.1706,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 1.37,
54
+ "learning_rate": 1.3333333333333333e-05,
55
+ "loss": 2.1528,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 1.54,
60
+ "learning_rate": 1.2222222222222224e-05,
61
+ "loss": 2.1447,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 1.71,
66
+ "learning_rate": 1.1111111111111113e-05,
67
+ "loss": 2.1432,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 1.88,
72
+ "learning_rate": 1e-05,
73
+ "loss": 2.1247,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 2.05,
78
+ "learning_rate": 8.888888888888888e-06,
79
+ "loss": 2.0947,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 2.22,
84
+ "learning_rate": 7.77777777777778e-06,
85
+ "loss": 2.0619,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 2.39,
90
+ "learning_rate": 6.666666666666667e-06,
91
+ "loss": 2.0574,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 2.56,
96
+ "learning_rate": 5.555555555555557e-06,
97
+ "loss": 2.0467,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 2.74,
102
+ "learning_rate": 4.444444444444444e-06,
103
+ "loss": 2.042,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 2.91,
108
+ "learning_rate": 3.3333333333333333e-06,
109
+ "loss": 2.0343,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 3.08,
114
+ "learning_rate": 2.222222222222222e-06,
115
+ "loss": 2.0168,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 3.25,
120
+ "learning_rate": 1.111111111111111e-06,
121
+ "loss": 1.9944,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 3.42,
126
+ "learning_rate": 0.0,
127
+ "loss": 1.9889,
128
+ "step": 10000
129
+ }
130
+ ],
131
+ "max_steps": 10000,
132
+ "num_train_epochs": 4,
133
+ "total_flos": 1.73348864227541e+17,
134
+ "trial_name": null,
135
+ "trial_params": null
136
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38881bf54ce75c75fdb4b3a69773e4ea7489c9e79b88ea104df84c11a48a2a44
3
+ size 3771
vocab.json ADDED
The diff for this file is too large to render. See raw diff