hyesunyun commited on
Commit
7f4b2f3
1 Parent(s): ecd4c02

First model version

Browse files
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<EV>": 50265, "<abs>": 50267, "<t>": 50266}
config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "allenai/led-large-16384",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "gelu",
6
+ "architectures": [
7
+ "LEDForConditionalGeneration"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "attention_window": [
11
+ 1024,
12
+ 1024,
13
+ 1024,
14
+ 1024,
15
+ 1024,
16
+ 1024,
17
+ 1024,
18
+ 1024,
19
+ 1024,
20
+ 1024,
21
+ 1024,
22
+ 1024
23
+ ],
24
+ "bos_token_id": 0,
25
+ "classif_dropout": 0.0,
26
+ "classifier_dropout": 0.0,
27
+ "d_model": 1024,
28
+ "decoder_attention_heads": 16,
29
+ "decoder_ffn_dim": 4096,
30
+ "decoder_layerdrop": 0.0,
31
+ "decoder_layers": 12,
32
+ "decoder_start_token_id": 2,
33
+ "dropout": 0.1,
34
+ "early_stopping": true,
35
+ "encoder_attention_heads": 16,
36
+ "encoder_ffn_dim": 4096,
37
+ "encoder_layerdrop": 0.0,
38
+ "encoder_layers": 12,
39
+ "eos_token_id": 2,
40
+ "gradient_checkpointing": true,
41
+ "id2label": {
42
+ "0": "LABEL_0",
43
+ "1": "LABEL_1",
44
+ "2": "LABEL_2"
45
+ },
46
+ "init_std": 0.02,
47
+ "is_encoder_decoder": true,
48
+ "label2id": {
49
+ "LABEL_0": 0,
50
+ "LABEL_1": 1,
51
+ "LABEL_2": 2
52
+ },
53
+ "length_penalty": 2.0,
54
+ "max_decoder_position_embeddings": 1024,
55
+ "max_encoder_position_embeddings": 16384,
56
+ "max_length": 512,
57
+ "min_length": 128,
58
+ "model_type": "led",
59
+ "no_repeat_ngram_size": 3,
60
+ "num_beams": 4,
61
+ "num_hidden_layers": 12,
62
+ "output_past": false,
63
+ "pad_token_id": 1,
64
+ "prefix": " ",
65
+ "transformers_version": "4.8.2",
66
+ "use_cache": false,
67
+ "vocab_size": 50268
68
+ }
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:d8ebafe071cf28b7540d463374bbbc141af0a197c466d2e84f20e92e3dc50b58
3
+ size 3678803885
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffc0c9ce2c2c3e0a95ffb4aec42247ae7b419bf53f1bfb5e98b2aacca7330c4c
3
+ size 1839654263
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71fa475ba405c266f205bf1fdc4252fbe6de61775873c5e3a41554514a578fc2
3
+ size 14593
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d02133ce8fe03e15b5bb47de95f55e7423f40925e163ff1b1d2523a1fc9d33c5
3
+ size 623
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, "additional_special_tokens": ["<EV>", "<t>", "<abs>"]}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 16384, "additional_special_tokens": ["<EV>", "<t>", "<abs>"], "special_tokens_map_file": "/home/yun.hy/.cache/huggingface/transformers/2ad921573d53ebf0c0450d63a211e61d8e328324e84830c365abff01f2d115f1.cb2244924ab24d706b02fd7fcedaea4531566537687a539ebb94db511fd122a0", "name_or_path": "allenai/led-large-16384", "tokenizer_class": "LEDTokenizer"}
trainer_state.json ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.710801393728223,
5
+ "global_step": 3500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.19,
12
+ "learning_rate": 8.333333333333334e-06,
13
+ "loss": 2.4875,
14
+ "step": 250
15
+ },
16
+ {
17
+ "epoch": 0.39,
18
+ "learning_rate": 1.6666666666666667e-05,
19
+ "loss": 2.2619,
20
+ "step": 500
21
+ },
22
+ {
23
+ "epoch": 0.58,
24
+ "learning_rate": 2.5e-05,
25
+ "loss": 2.2339,
26
+ "step": 750
27
+ },
28
+ {
29
+ "epoch": 0.77,
30
+ "learning_rate": 3.3333333333333335e-05,
31
+ "loss": 2.2639,
32
+ "step": 1000
33
+ },
34
+ {
35
+ "epoch": 0.97,
36
+ "learning_rate": 4.166666666666667e-05,
37
+ "loss": 2.1806,
38
+ "step": 1250
39
+ },
40
+ {
41
+ "epoch": 1.16,
42
+ "learning_rate": 5e-05,
43
+ "loss": 2.012,
44
+ "step": 1500
45
+ },
46
+ {
47
+ "epoch": 1.36,
48
+ "learning_rate": 4.473240623683102e-05,
49
+ "loss": 1.9184,
50
+ "step": 1750
51
+ },
52
+ {
53
+ "epoch": 1.55,
54
+ "learning_rate": 3.946481247366203e-05,
55
+ "loss": 1.925,
56
+ "step": 2000
57
+ },
58
+ {
59
+ "epoch": 1.74,
60
+ "learning_rate": 3.419721871049305e-05,
61
+ "loss": 1.8519,
62
+ "step": 2250
63
+ },
64
+ {
65
+ "epoch": 1.94,
66
+ "learning_rate": 2.8929624947324065e-05,
67
+ "loss": 1.8232,
68
+ "step": 2500
69
+ },
70
+ {
71
+ "epoch": 2.13,
72
+ "learning_rate": 2.366203118415508e-05,
73
+ "loss": 1.5126,
74
+ "step": 2750
75
+ },
76
+ {
77
+ "epoch": 2.32,
78
+ "learning_rate": 1.8394437420986094e-05,
79
+ "loss": 1.3707,
80
+ "step": 3000
81
+ },
82
+ {
83
+ "epoch": 2.52,
84
+ "learning_rate": 1.3126843657817109e-05,
85
+ "loss": 1.311,
86
+ "step": 3250
87
+ },
88
+ {
89
+ "epoch": 2.71,
90
+ "learning_rate": 7.859249894648125e-06,
91
+ "loss": 1.2866,
92
+ "step": 3500
93
+ }
94
+ ],
95
+ "max_steps": 3873,
96
+ "num_train_epochs": 3,
97
+ "total_flos": 3.956185882637107e+17,
98
+ "trial_name": null,
99
+ "trial_params": null
100
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d07837650b7ad4bf370b0b43f78ffd044fececba27f1eb8fe76fbb7ea21152d4
3
+ size 2735
vocab.json ADDED
The diff for this file is too large to render. See raw diff