SocialCompUW commited on
Commit
d6b298b
1 Parent(s): cc5cb7b

Uploading files

Browse files
adapter_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "lmsys/vicuna-13b-v1.5-16k",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 64,
13
+ "lora_dropout": 0.1,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 32,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "q_proj",
23
+ "v_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM",
26
+ "use_dora": false,
27
+ "use_rslora": false
28
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b14d218efc2a3dfa9047453957ee31466e688ca07154d5aa4d803aafc265fab5
3
+ size 104879176
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa3a56b6b0e5881070c71b42124ede954e6ea974b752365965a810c24f443fae
3
+ size 209850234
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb48a09ce98af6f94c1f8457d299b07514a20c17ce065bf23f70b6035ea179e4
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f5715ee569343a48b2ce13bbf07ba81a4dc21f7491b6fc45535183ede93c6af
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<s>",
31
+ "chat_template": "{% set system_message = 'A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user\\'s questions.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'USER: ' + content + ' ASSISTANT:' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": false,
35
+ "model_max_length": 16384,
36
+ "pad_token": "<unk>",
37
+ "padding_side": "right",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "split_special_tokens": false,
41
+ "tokenizer_class": "LlamaTokenizer",
42
+ "unk_token": "<unk>",
43
+ "use_default_system_prompt": false
44
+ }
trainer_state.json ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.7177914110429446,
5
+ "eval_steps": 500,
6
+ "global_step": 70,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.12,
13
+ "learning_rate": 4.951963201008076e-05,
14
+ "loss": 0.358,
15
+ "step": 5
16
+ },
17
+ {
18
+ "epoch": 0.25,
19
+ "learning_rate": 4.8096988312782174e-05,
20
+ "loss": 0.2466,
21
+ "step": 10
22
+ },
23
+ {
24
+ "epoch": 0.37,
25
+ "learning_rate": 4.5786740307563636e-05,
26
+ "loss": 0.2386,
27
+ "step": 15
28
+ },
29
+ {
30
+ "epoch": 0.49,
31
+ "learning_rate": 4.267766952966369e-05,
32
+ "loss": 0.2188,
33
+ "step": 20
34
+ },
35
+ {
36
+ "epoch": 0.61,
37
+ "learning_rate": 3.888925582549006e-05,
38
+ "loss": 0.1976,
39
+ "step": 25
40
+ },
41
+ {
42
+ "epoch": 0.74,
43
+ "learning_rate": 3.456708580912725e-05,
44
+ "loss": 0.2018,
45
+ "step": 30
46
+ },
47
+ {
48
+ "epoch": 0.86,
49
+ "learning_rate": 2.9877258050403212e-05,
50
+ "loss": 0.1729,
51
+ "step": 35
52
+ },
53
+ {
54
+ "epoch": 0.98,
55
+ "learning_rate": 2.5e-05,
56
+ "loss": 0.1742,
57
+ "step": 40
58
+ },
59
+ {
60
+ "epoch": 1.1,
61
+ "learning_rate": 2.0122741949596797e-05,
62
+ "loss": 0.1817,
63
+ "step": 45
64
+ },
65
+ {
66
+ "epoch": 1.23,
67
+ "learning_rate": 1.5432914190872757e-05,
68
+ "loss": 0.1517,
69
+ "step": 50
70
+ },
71
+ {
72
+ "epoch": 1.35,
73
+ "learning_rate": 1.1110744174509952e-05,
74
+ "loss": 0.1594,
75
+ "step": 55
76
+ },
77
+ {
78
+ "epoch": 1.47,
79
+ "learning_rate": 7.3223304703363135e-06,
80
+ "loss": 0.1513,
81
+ "step": 60
82
+ },
83
+ {
84
+ "epoch": 1.6,
85
+ "learning_rate": 4.213259692436367e-06,
86
+ "loss": 0.1482,
87
+ "step": 65
88
+ },
89
+ {
90
+ "epoch": 1.72,
91
+ "learning_rate": 1.9030116872178316e-06,
92
+ "loss": 0.1759,
93
+ "step": 70
94
+ }
95
+ ],
96
+ "logging_steps": 5,
97
+ "max_steps": 80,
98
+ "num_input_tokens_seen": 0,
99
+ "num_train_epochs": 2,
100
+ "save_steps": 10,
101
+ "total_flos": 3.1758602101161984e+17,
102
+ "train_batch_size": 8,
103
+ "trial_name": null,
104
+ "trial_params": null
105
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d1cc6d2ba1ede007343aa0469873d82c4debcee8c40f791f4421b7568c989c6
3
+ size 4920