osazuwa commited on
Commit
9cf95b5
1 Parent(s): 64ad6f7

Trained model

Browse files
README.md DELETED
@@ -1,3 +0,0 @@
1
- ---
2
- license: unknown
3
- ---
 
 
 
 
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b2ec1788f9c8e48243dbf85ae52c3d108b9da07d395ee05f99a5e4c773e6a55
3
  size 1625426996
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03b6b815106612530f1c59e5ac783391a1b4288625b2427ef954060fe06f3249
3
  size 1625426996
optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8165a2708d97b42db31640048781dbdd4dac5c129cfd341f2880cc0b7c7bc555
3
- size 3250759951
 
 
 
 
rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:cbe8e0e44b4c13ab05326c6c60eca19733d46ff21431ad7dd2087077d271d063
3
- size 14244
 
 
 
 
scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5da07f4bc6a42da189cc0168c278eeb6c954af047743c7cc8ef9379424d71370
3
- size 1064
 
 
 
 
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": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "</s>",
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 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 1024,
52
+ "pad_token": "</s>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "BartTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
trainer_state.json DELETED
@@ -1,115 +0,0 @@
1
- {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 2.857142857142857,
5
- "eval_steps": 500,
6
- "global_step": 8000,
7
- "is_hyper_param_search": false,
8
- "is_local_process_zero": true,
9
- "is_world_process_zero": true,
10
- "log_history": [
11
- {
12
- "epoch": 0.18,
13
- "learning_rate": 5e-05,
14
- "loss": 0.0898,
15
- "step": 500
16
- },
17
- {
18
- "epoch": 0.36,
19
- "learning_rate": 4.683544303797468e-05,
20
- "loss": 0.0637,
21
- "step": 1000
22
- },
23
- {
24
- "epoch": 0.54,
25
- "learning_rate": 4.367088607594937e-05,
26
- "loss": 0.0706,
27
- "step": 1500
28
- },
29
- {
30
- "epoch": 0.71,
31
- "learning_rate": 4.050632911392405e-05,
32
- "loss": 0.0894,
33
- "step": 2000
34
- },
35
- {
36
- "epoch": 0.89,
37
- "learning_rate": 3.7341772151898736e-05,
38
- "loss": 0.1138,
39
- "step": 2500
40
- },
41
- {
42
- "epoch": 1.07,
43
- "learning_rate": 3.4177215189873416e-05,
44
- "loss": 0.1484,
45
- "step": 3000
46
- },
47
- {
48
- "epoch": 1.25,
49
- "learning_rate": 3.10126582278481e-05,
50
- "loss": 0.1201,
51
- "step": 3500
52
- },
53
- {
54
- "epoch": 1.43,
55
- "learning_rate": 2.7848101265822786e-05,
56
- "loss": 0.1216,
57
- "step": 4000
58
- },
59
- {
60
- "epoch": 1.61,
61
- "learning_rate": 2.468354430379747e-05,
62
- "loss": 0.1238,
63
- "step": 4500
64
- },
65
- {
66
- "epoch": 1.79,
67
- "learning_rate": 2.1518987341772153e-05,
68
- "loss": 0.1255,
69
- "step": 5000
70
- },
71
- {
72
- "epoch": 1.96,
73
- "learning_rate": 1.8354430379746836e-05,
74
- "loss": 0.1305,
75
- "step": 5500
76
- },
77
- {
78
- "epoch": 2.14,
79
- "learning_rate": 1.5189873417721521e-05,
80
- "loss": 0.1012,
81
- "step": 6000
82
- },
83
- {
84
- "epoch": 2.32,
85
- "learning_rate": 1.2025316455696203e-05,
86
- "loss": 0.0969,
87
- "step": 6500
88
- },
89
- {
90
- "epoch": 2.5,
91
- "learning_rate": 8.860759493670886e-06,
92
- "loss": 0.1036,
93
- "step": 7000
94
- },
95
- {
96
- "epoch": 2.68,
97
- "learning_rate": 5.69620253164557e-06,
98
- "loss": 0.1146,
99
- "step": 7500
100
- },
101
- {
102
- "epoch": 2.86,
103
- "learning_rate": 2.531645569620253e-06,
104
- "loss": 0.1198,
105
- "step": 8000
106
- }
107
- ],
108
- "logging_steps": 500,
109
- "max_steps": 8400,
110
- "num_train_epochs": 3,
111
- "save_steps": 500,
112
- "total_flos": 3.4673673633792e+16,
113
- "trial_name": null,
114
- "trial_params": null
115
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:747828469188eed9e710be3490b8946d03d6473ac83e16c89b65d7577a9ea3a7
3
- size 4728
 
 
 
 
vocab.json ADDED
The diff for this file is too large to render. See raw diff