Marko Tasic
commited on
Commit
·
c2fc44c
1
Parent(s):
9b182f7
out/pretrain-core/final
Browse files
out/pretrain-core/final/hyperparameters.yaml
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
model_name: tangled-alpha-0.1-core
|
2 |
+
model_config:
|
3 |
+
name: tangled-alpha-0.1-core
|
4 |
+
hf_config: {}
|
5 |
+
block_size: 131072
|
6 |
+
n_layer: 32
|
7 |
+
n_embd: 512
|
8 |
+
vocab_size: 32064
|
9 |
+
padding_multiple: 512
|
10 |
+
padded_vocab_size: 32064
|
11 |
+
norm_class_name: RMSNorm
|
12 |
+
norm_eps: 1.0e-05
|
13 |
+
norm_qk: false
|
14 |
+
post_attention_norm: false
|
15 |
+
post_mlp_norm: false
|
16 |
+
parallel_residual: false
|
17 |
+
shared_attention_norm: false
|
18 |
+
n_head: 4
|
19 |
+
head_size: 128
|
20 |
+
n_query_groups: 4
|
21 |
+
attn_bias: false
|
22 |
+
rope_base: 500000
|
23 |
+
rotary_percentage: 1.0
|
24 |
+
rope_condense_ratio: 1
|
25 |
+
rope_adjustments:
|
26 |
+
factor: 32.0
|
27 |
+
low_freq_factor: 1.0
|
28 |
+
high_freq_factor: 4.0
|
29 |
+
original_max_seq_len: 8192
|
30 |
+
intermediate_size: 2688
|
31 |
+
bias: false
|
32 |
+
mlp_class_name: LLaMAMLP
|
33 |
+
gelu_approximate: none
|
34 |
+
n_expert: 0
|
35 |
+
n_expert_per_token: 0
|
36 |
+
scale_embeddings: false
|
37 |
+
lm_head_bias: false
|
38 |
+
out_dir: ../out/pretrain-core
|
39 |
+
precision: bf16-true
|
40 |
+
resume: auto
|
41 |
+
data:
|
42 |
+
class_path: litgpt.data.LitData
|
43 |
+
init_args:
|
44 |
+
data_path: ../core-data-0-8192-2000/
|
45 |
+
seed: 42
|
46 |
+
num_workers: 32
|
47 |
+
train:
|
48 |
+
save_interval: 100
|
49 |
+
log_interval: 1
|
50 |
+
global_batch_size: 512
|
51 |
+
micro_batch_size: 2
|
52 |
+
lr_warmup_steps: 200
|
53 |
+
max_tokens: 7318364160
|
54 |
+
max_seq_length: 8192
|
55 |
+
tie_embeddings: true
|
56 |
+
max_norm: 1.0
|
57 |
+
min_lr: 1.0e-05
|
58 |
+
eval:
|
59 |
+
interval: 50
|
60 |
+
max_iters: 100
|
61 |
+
initial_validation: false
|
62 |
+
final_validation: true
|
63 |
+
evaluate_example: first
|
64 |
+
optimizer:
|
65 |
+
class_path: grokadamw.GrokAdamW
|
66 |
+
init_args:
|
67 |
+
lr: 0.0001
|
68 |
+
weight_decay: 0.01
|
69 |
+
betas:
|
70 |
+
- 0.9
|
71 |
+
- 0.999
|
72 |
+
devices: auto
|
73 |
+
num_nodes: 1
|
74 |
+
tokenizer_dir: ..
|
75 |
+
logger_name: wandb
|
76 |
+
seed: 23
|
out/pretrain-core/final/lit_model.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be0538fc89f974444adc06478e996ec1649bc85720e177e8830eddbc286a1a20
|
3 |
+
size 1457331426
|
out/pretrain-core/final/model_config.yaml
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
attention_logit_softcapping: null
|
2 |
+
attention_scores_scalar: null
|
3 |
+
attn_bias: false
|
4 |
+
bias: false
|
5 |
+
block_size: 131072
|
6 |
+
final_logit_softcapping: null
|
7 |
+
gelu_approximate: none
|
8 |
+
head_size: 128
|
9 |
+
hf_config: {}
|
10 |
+
intermediate_size: 2688
|
11 |
+
lm_head_bias: false
|
12 |
+
mlp_class_name: LLaMAMLP
|
13 |
+
n_embd: 512
|
14 |
+
n_expert: 0
|
15 |
+
n_expert_per_token: 0
|
16 |
+
n_head: 4
|
17 |
+
n_layer: 32
|
18 |
+
n_query_groups: 4
|
19 |
+
name: tangled-alpha-0.1-core
|
20 |
+
norm_class_name: RMSNorm
|
21 |
+
norm_eps: 1.0e-05
|
22 |
+
norm_qk: false
|
23 |
+
padded_vocab_size: 32064
|
24 |
+
padding_multiple: 512
|
25 |
+
parallel_residual: false
|
26 |
+
post_attention_norm: false
|
27 |
+
post_mlp_norm: false
|
28 |
+
rope_adjustments:
|
29 |
+
factor: 32.0
|
30 |
+
high_freq_factor: 4.0
|
31 |
+
low_freq_factor: 1.0
|
32 |
+
original_max_seq_len: 8192
|
33 |
+
rope_base: 500000
|
34 |
+
rope_condense_ratio: 1
|
35 |
+
rotary_percentage: 1.0
|
36 |
+
scale_embeddings: false
|
37 |
+
shared_attention_norm: false
|
38 |
+
sliding_window_layer_placing: null
|
39 |
+
sliding_window_size: null
|
40 |
+
vocab_size: 32064
|
out/pretrain-core/final/tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83b2d408ebeae398f24964d4e7ce0c847cd7ff554519941355641c7d0f68b09b
|
3 |
+
size 1845893
|
out/pretrain-core/final/tokenizer_config.json
ADDED
@@ -0,0 +1,194 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
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": true,
|
26 |
+
"single_word": false,
|
27 |
+
"special": false
|
28 |
+
},
|
29 |
+
"32000": {
|
30 |
+
"content": "<|endoftext|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"32001": {
|
38 |
+
"content": "<|assistant|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": true,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"32002": {
|
46 |
+
"content": "<|placeholder1|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": true,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"32003": {
|
54 |
+
"content": "<|placeholder2|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": true,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"32004": {
|
62 |
+
"content": "<|placeholder3|>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": true,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"32005": {
|
70 |
+
"content": "<|placeholder4|>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": true,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"32006": {
|
78 |
+
"content": "<|system|>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": true,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"32007": {
|
86 |
+
"content": "<|end|>",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": true,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
},
|
93 |
+
"32008": {
|
94 |
+
"content": "<|placeholder5|>",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": true,
|
98 |
+
"single_word": false,
|
99 |
+
"special": true
|
100 |
+
},
|
101 |
+
"32009": {
|
102 |
+
"content": "<|placeholder6|>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": true,
|
106 |
+
"single_word": false,
|
107 |
+
"special": true
|
108 |
+
},
|
109 |
+
"32010": {
|
110 |
+
"content": "<|user|>",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": true,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
},
|
117 |
+
"32011": {
|
118 |
+
"content": "<tools>",
|
119 |
+
"lstrip": false,
|
120 |
+
"normalized": false,
|
121 |
+
"rstrip": true,
|
122 |
+
"single_word": false,
|
123 |
+
"special": true
|
124 |
+
},
|
125 |
+
"32012": {
|
126 |
+
"content": "</tools>",
|
127 |
+
"lstrip": false,
|
128 |
+
"normalized": false,
|
129 |
+
"rstrip": true,
|
130 |
+
"single_word": false,
|
131 |
+
"special": true
|
132 |
+
},
|
133 |
+
"32013": {
|
134 |
+
"content": "<tool_call>",
|
135 |
+
"lstrip": false,
|
136 |
+
"normalized": false,
|
137 |
+
"rstrip": true,
|
138 |
+
"single_word": false,
|
139 |
+
"special": true
|
140 |
+
},
|
141 |
+
"32014": {
|
142 |
+
"content": "</tool_call>",
|
143 |
+
"lstrip": false,
|
144 |
+
"normalized": false,
|
145 |
+
"rstrip": true,
|
146 |
+
"single_word": false,
|
147 |
+
"special": true
|
148 |
+
},
|
149 |
+
"32015": {
|
150 |
+
"content": "<tool_response>",
|
151 |
+
"lstrip": false,
|
152 |
+
"normalized": false,
|
153 |
+
"rstrip": true,
|
154 |
+
"single_word": false,
|
155 |
+
"special": true
|
156 |
+
},
|
157 |
+
"32016": {
|
158 |
+
"content": "</tool_response>",
|
159 |
+
"lstrip": false,
|
160 |
+
"normalized": false,
|
161 |
+
"rstrip": true,
|
162 |
+
"single_word": false,
|
163 |
+
"special": true
|
164 |
+
},
|
165 |
+
"32017": {
|
166 |
+
"content": "<think>",
|
167 |
+
"lstrip": false,
|
168 |
+
"normalized": false,
|
169 |
+
"rstrip": true,
|
170 |
+
"single_word": false,
|
171 |
+
"special": true
|
172 |
+
},
|
173 |
+
"32018": {
|
174 |
+
"content": "</think>",
|
175 |
+
"lstrip": false,
|
176 |
+
"normalized": false,
|
177 |
+
"rstrip": true,
|
178 |
+
"single_word": false,
|
179 |
+
"special": true
|
180 |
+
}
|
181 |
+
},
|
182 |
+
"bos_token": "<s>",
|
183 |
+
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|system|>' + message['content'] + '<|end|>'}}{% elif message['role'] == 'user' %}{{'<|user|>' + message['content'] + '<|end|>'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>' + message['content'] + '<|end|>'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}",
|
184 |
+
"clean_up_tokenization_spaces": false,
|
185 |
+
"eos_token": "<|endoftext|>",
|
186 |
+
"legacy": false,
|
187 |
+
"model_max_length": 131072,
|
188 |
+
"pad_token": "<|endoftext|>",
|
189 |
+
"padding_side": "left",
|
190 |
+
"sp_model_kwargs": {},
|
191 |
+
"tokenizer_class": "LlamaTokenizer",
|
192 |
+
"unk_token": "<unk>",
|
193 |
+
"use_default_system_prompt": false
|
194 |
+
}
|