Hugging Face's logo

Bruno
/
Caramelo_7B

Text Generation
Adapters
Portuguese
English
Model card Files Community
1
Bruno commited on
Commit
00efc34
•
1 Parent(s): 6d5232d

Upload 9 files

Browse files
Files changed (9) hide show
  1. adapter_config.json +22 -0
  2. adapter_model.bin +3 -0
  3. optimizer.pt +3 -0
  4. rng_state.pth +3 -0
  5. scheduler.pt +3 -0
  6. special_tokens_map.json +17 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +7 -0
  9. trainer_state.json +124 -0
adapter_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_name_or_path": "ybelkada/falcon-7b-sharded-bf16",
3
+ "bias": "none",
4
+ "fan_in_fan_out": false,
5
+ "inference_mode": true,
6
+ "init_lora_weights": true,
7
+ "layers_pattern": null,
8
+ "layers_to_transform": null,
9
+ "lora_alpha": 16,
10
+ "lora_dropout": 0.1,
11
+ "modules_to_save": null,
12
+ "peft_type": "LORA",
13
+ "r": 64,
14
+ "revision": null,
15
+ "target_modules": [
16
+ "query_key_value",
17
+ "dense",
18
+ "dense_h_to_4h",
19
+ "dense_4h_to_h"
20
+ ],
21
+ "task_type": "CAUSAL_LM"
22
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8226ae4d55e2d10e2f53740668498d95bb59a106c90f3117c7793f82b06f7017
3
+ size 522284877
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5187b7a8123c2d49ae6e441e4f1d651b6fb94816a7d1784e9359f98abad94d26
3
+ size 1044539653
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c3fe6bb9481843836c6835440a3304e7e61717c0737b7168e485aa93a17a8b2
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9ead5770d47e9ed8382117ff63b08f811804acf4664a1d31b1d336db76762ca
3
+ size 627
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ ">>TITLE<<",
4
+ ">>ABSTRACT<<",
5
+ ">>INTRODUCTION<<",
6
+ ">>SUMMARY<<",
7
+ ">>COMMENT<<",
8
+ ">>ANSWER<<",
9
+ ">>QUESTION<<",
10
+ ">>DOMAIN<<",
11
+ ">>PREFIX<<",
12
+ ">>SUFFIX<<",
13
+ ">>MIDDLE<<"
14
+ ],
15
+ "eos_token": "<|endoftext|>",
16
+ "pad_token": "<|endoftext|>"
17
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "clean_up_tokenization_spaces": true,
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 2048,
6
+ "tokenizer_class": "PreTrainedTokenizerFast"
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,124 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 180.0,
5
+ "global_step": 180,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 10.0,
12
+ "learning_rate": 0.0002,
13
+ "loss": 0.4973,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 20.0,
18
+ "learning_rate": 0.0002,
19
+ "loss": 0.1772,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 30.0,
24
+ "learning_rate": 0.0002,
25
+ "loss": 0.0441,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 40.0,
30
+ "learning_rate": 0.0002,
31
+ "loss": 0.0221,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 50.0,
36
+ "learning_rate": 0.0002,
37
+ "loss": 0.0174,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 60.0,
42
+ "learning_rate": 0.0002,
43
+ "loss": 0.0132,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 70.0,
48
+ "learning_rate": 0.0002,
49
+ "loss": 0.0088,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 80.0,
54
+ "learning_rate": 0.0002,
55
+ "loss": 0.0071,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 90.0,
60
+ "learning_rate": 0.0002,
61
+ "loss": 0.0061,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 100.0,
66
+ "learning_rate": 0.0002,
67
+ "loss": 0.0056,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 110.0,
72
+ "learning_rate": 0.0002,
73
+ "loss": 0.0055,
74
+ "step": 110
75
+ },
76
+ {
77
+ "epoch": 120.0,
78
+ "learning_rate": 0.0002,
79
+ "loss": 0.0055,
80
+ "step": 120
81
+ },
82
+ {
83
+ "epoch": 130.0,
84
+ "learning_rate": 0.0002,
85
+ "loss": 0.0055,
86
+ "step": 130
87
+ },
88
+ {
89
+ "epoch": 140.0,
90
+ "learning_rate": 0.0002,
91
+ "loss": 0.0055,
92
+ "step": 140
93
+ },
94
+ {
95
+ "epoch": 150.0,
96
+ "learning_rate": 0.0002,
97
+ "loss": 0.0055,
98
+ "step": 150
99
+ },
100
+ {
101
+ "epoch": 160.0,
102
+ "learning_rate": 0.0002,
103
+ "loss": 0.0055,
104
+ "step": 160
105
+ },
106
+ {
107
+ "epoch": 170.0,
108
+ "learning_rate": 0.0002,
109
+ "loss": 0.0055,
110
+ "step": 170
111
+ },
112
+ {
113
+ "epoch": 180.0,
114
+ "learning_rate": 0.0002,
115
+ "loss": 0.0055,
116
+ "step": 180
117
+ }
118
+ ],
119
+ "max_steps": 500,
120
+ "num_train_epochs": 500,
121
+ "total_flos": 3.046874617479168e+16,
122
+ "trial_name": null,
123
+ "trial_params": null
124
+ }