guanning commited on
Commit
dcad210
·
verified ·
1 Parent(s): 5b0f7bc

OLMo-150M-as_fm3_tg_omi1_omi2-pkwCU0: step58527-unsharded

Browse files
pretrain/OLMo-150M-as_fm3_tg_omi1_omi2-pkwCU0/step58527-unsharded/config.yaml ADDED
@@ -0,0 +1,629 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ run_name: OLMo-150M-as_fm3_tg_omi1_omi2-pkwCU0
2
+ seed: 6198
3
+ epoch: null
4
+ dry_run: false
5
+ model:
6
+ d_model: 768
7
+ n_heads: 12
8
+ n_kv_heads: null
9
+ clip_qkv: null
10
+ n_layers: 12
11
+ mlp_ratio: 8
12
+ mlp_hidden_size: null
13
+ activation_type: swiglu
14
+ block_type: sequential
15
+ block_group_size: 1
16
+ alibi: false
17
+ alibi_bias_max: 8.0
18
+ rope: true
19
+ rope_full_precision: true
20
+ rope_theta: 10000
21
+ flash_attention: true
22
+ attention_dropout: 0.0
23
+ multi_query_attention: null
24
+ attention_layer_norm: false
25
+ residual_dropout: 0.0
26
+ embedding_dropout: 0.0
27
+ embedding_layer_norm: false
28
+ layer_norm_type: default
29
+ layer_norm_with_affine: false
30
+ layer_norm_eps: 1.0e-05
31
+ attention_layer_norm_with_affine: false
32
+ max_sequence_length: 2048
33
+ include_bias: false
34
+ bias_for_layer_norm: false
35
+ scale_logits: false
36
+ vocab_size: 32000
37
+ embedding_size: 32000
38
+ weight_tying: false
39
+ eos_token_id: 0
40
+ pad_token_id: 1
41
+ init_device: cuda
42
+ init_fn: normal
43
+ init_std: 0.02
44
+ init_cutoff_factor: 3.0
45
+ precision: amp_bf16
46
+ scale_emb_init: false
47
+ emb_init_std: null
48
+ norm_after: false
49
+ optimizer:
50
+ name: adamw
51
+ learning_rate: 0.001
52
+ weight_decay: 0.1
53
+ betas:
54
+ - 0.9
55
+ - 0.95
56
+ eps: 1.0e-08
57
+ no_decay_norm_and_bias: null
58
+ selective_updates: false
59
+ decay_norm_and_bias: true
60
+ decay_embeddings: true
61
+ metrics_log_interval: 10
62
+ record_update_metrics: false
63
+ scheduler:
64
+ name: cosine_with_warmup
65
+ units: steps
66
+ t_warmup: 5000
67
+ t_max: null
68
+ alpha_f: 0.1
69
+ grad_clip_warmup_steps: null
70
+ grad_clip_warmup_factor: null
71
+ warmup_min_lr: 0.0
72
+ data:
73
+ paths:
74
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00000_00000_shuffled.ds
75
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00001_00000_shuffled.ds
76
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00002_00000_shuffled.ds
77
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00003_00000_shuffled.ds
78
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00004_00000_shuffled.ds
79
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00005_00000_shuffled.ds
80
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00006_00000_shuffled.ds
81
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00007_00000_shuffled.ds
82
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00008_00000_shuffled.ds
83
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00009_00000_shuffled.ds
84
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00010_00000_shuffled.ds
85
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00011_00000_shuffled.ds
86
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00012_00000_shuffled.ds
87
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00013_00000_shuffled.ds
88
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00014_00000_shuffled.ds
89
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00016_00000_shuffled.ds
90
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00019_00000_shuffled.ds
91
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00020_00000_shuffled.ds
92
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00021_00000_shuffled.ds
93
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00022_00000_shuffled.ds
94
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00023_00000_shuffled.ds
95
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00024_00000_shuffled.ds
96
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00025_00000_shuffled.ds
97
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00026_00000_shuffled.ds
98
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00027_00000_shuffled.ds
99
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00028_00000_shuffled.ds
100
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00029_00000_shuffled.ds
101
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00030_00000_shuffled.ds
102
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00031_00000_shuffled.ds
103
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00032_00000_shuffled.ds
104
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00033_00000_shuffled.ds
105
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00034_00000_shuffled.ds
106
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00035_00000_shuffled.ds
107
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00036_00000_shuffled.ds
108
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00037_00000_shuffled.ds
109
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00038_00000_shuffled.ds
110
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00039_00000_shuffled.ds
111
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00040_00000_shuffled.ds
112
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00041_00000_shuffled.ds
113
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00042_00000_shuffled.ds
114
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00043_00000_shuffled.ds
115
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00044_00000_shuffled.ds
116
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00045_00000_shuffled.ds
117
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00046_00000_shuffled.ds
118
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00047_00000_shuffled.ds
119
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00048_00000_shuffled.ds
120
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00049_00000_shuffled.ds
121
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00050_00000_shuffled.ds
122
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00051_00000_shuffled.ds
123
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00052_00000_shuffled.ds
124
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00053_00000_shuffled.ds
125
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00054_00000_shuffled.ds
126
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00055_00000_shuffled.ds
127
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00056_00000_shuffled.ds
128
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00057_00000_shuffled.ds
129
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00058_00000_shuffled.ds
130
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00059_00000_shuffled.ds
131
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00060_00000_shuffled.ds
132
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00061_00000_shuffled.ds
133
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00062_00000_shuffled.ds
134
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/algebraic-stack-tokenized/00063_00000_shuffled.ds
135
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00000_00000_shuffled.ds
136
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00001_00000_shuffled.ds
137
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00002_00000_shuffled.ds
138
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00003_00000_shuffled.ds
139
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00004_00000_shuffled.ds
140
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00005_00000_shuffled.ds
141
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00006_00000_shuffled.ds
142
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00007_00000_shuffled.ds
143
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00008_00000_shuffled.ds
144
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00009_00000_shuffled.ds
145
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00010_00000_shuffled.ds
146
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00011_00000_shuffled.ds
147
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00012_00000_shuffled.ds
148
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00013_00000_shuffled.ds
149
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00014_00000_shuffled.ds
150
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00015_00000_shuffled.ds
151
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00016_00000_shuffled.ds
152
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00017_00000_shuffled.ds
153
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00018_00000_shuffled.ds
154
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00019_00000_shuffled.ds
155
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00020_00000_shuffled.ds
156
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00021_00000_shuffled.ds
157
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00022_00000_shuffled.ds
158
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00023_00000_shuffled.ds
159
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00024_00000_shuffled.ds
160
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00025_00000_shuffled.ds
161
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00026_00000_shuffled.ds
162
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00027_00000_shuffled.ds
163
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00028_00000_shuffled.ds
164
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00029_00000_shuffled.ds
165
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00030_00000_shuffled.ds
166
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00031_00000_shuffled.ds
167
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00032_00000_shuffled.ds
168
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00033_00000_shuffled.ds
169
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00034_00000_shuffled.ds
170
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00035_00000_shuffled.ds
171
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00036_00000_shuffled.ds
172
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00037_00000_shuffled.ds
173
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00038_00000_shuffled.ds
174
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00039_00000_shuffled.ds
175
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00040_00000_shuffled.ds
176
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00041_00000_shuffled.ds
177
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00042_00000_shuffled.ds
178
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00043_00000_shuffled.ds
179
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00044_00000_shuffled.ds
180
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00045_00000_shuffled.ds
181
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00046_00000_shuffled.ds
182
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00047_00000_shuffled.ds
183
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00048_00000_shuffled.ds
184
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00049_00000_shuffled.ds
185
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00050_00000_shuffled.ds
186
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00051_00000_shuffled.ds
187
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00052_00000_shuffled.ds
188
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00053_00000_shuffled.ds
189
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00054_00000_shuffled.ds
190
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00055_00000_shuffled.ds
191
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00056_00000_shuffled.ds
192
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00057_00000_shuffled.ds
193
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00058_00000_shuffled.ds
194
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00059_00000_shuffled.ds
195
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00060_00000_shuffled.ds
196
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00061_00000_shuffled.ds
197
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00062_00000_shuffled.ds
198
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/finemath3-tokenized/00063_00000_shuffled.ds
199
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/openmathinstruct1-tokenized/00000_00000_shuffled.ds
200
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/openmathinstruct2-tokenized/00000_00000_shuffled.ds
201
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/openmathinstruct2-tokenized/00001_00000_shuffled.ds
202
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/openmathinstruct2-tokenized/00002_00000_shuffled.ds
203
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/openmathinstruct2-tokenized/00003_00000_shuffled.ds
204
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/openmathinstruct2-tokenized/00004_00000_shuffled.ds
205
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/openmathinstruct2-tokenized/00005_00000_shuffled.ds
206
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/openmathinstruct2-tokenized/00006_00000_shuffled.ds
207
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/openmathinstruct2-tokenized/00007_00000_shuffled.ds
208
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/openmathinstruct2-tokenized/00008_00000_shuffled.ds
209
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/openmathinstruct2-tokenized/00009_00000_shuffled.ds
210
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/openmathinstruct2-tokenized/00010_00000_shuffled.ds
211
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/openmathinstruct2-tokenized/00011_00000_shuffled.ds
212
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/openmathinstruct2-tokenized/00012_00000_shuffled.ds
213
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/openmathinstruct2-tokenized/00013_00000_shuffled.ds
214
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/openmathinstruct2-tokenized/00014_00000_shuffled.ds
215
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/openmathinstruct2-tokenized/00015_00000_shuffled.ds
216
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/openmathinstruct2-tokenized/00016_00000_shuffled.ds
217
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/openmathinstruct2-tokenized/00017_00000_shuffled.ds
218
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/openmathinstruct2-tokenized/00018_00000_shuffled.ds
219
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/openmathinstruct2-tokenized/00019_00000_shuffled.ds
220
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/openmathinstruct2-tokenized/00020_00000_shuffled.ds
221
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/openmathinstruct2-tokenized/00021_00000_shuffled.ds
222
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/openmathinstruct2-tokenized/00022_00000_shuffled.ds
223
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/openmathinstruct2-tokenized/00023_00000_shuffled.ds
224
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/openmathinstruct2-tokenized/00024_00000_shuffled.ds
225
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/openmathinstruct2-tokenized/00025_00000_shuffled.ds
226
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/openmathinstruct2-tokenized/00026_00000_shuffled.ds
227
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/openmathinstruct2-tokenized/00027_00000_shuffled.ds
228
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/openmathinstruct2-tokenized/00028_00000_shuffled.ds
229
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/openmathinstruct2-tokenized/00029_00000_shuffled.ds
230
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/openmathinstruct2-tokenized/00030_00000_shuffled.ds
231
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/openmathinstruct2-tokenized/00031_00000_shuffled.ds
232
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/tinygsm-tokenized/00000_00000_shuffled.ds
233
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/tinygsm-tokenized/00001_00000_shuffled.ds
234
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/tinygsm-tokenized/00002_00000_shuffled.ds
235
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/tinygsm-tokenized/00003_00000_shuffled.ds
236
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/tinygsm-tokenized/00004_00000_shuffled.ds
237
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/tinygsm-tokenized/00005_00000_shuffled.ds
238
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/tinygsm-tokenized/00006_00000_shuffled.ds
239
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/tinygsm-tokenized/00007_00000_shuffled.ds
240
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/tinygsm-tokenized/00008_00000_shuffled.ds
241
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/tinygsm-tokenized/00009_00000_shuffled.ds
242
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/tinygsm-tokenized/00010_00000_shuffled.ds
243
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/tinygsm-tokenized/00011_00000_shuffled.ds
244
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/tinygsm-tokenized/00012_00000_shuffled.ds
245
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/tinygsm-tokenized/00013_00000_shuffled.ds
246
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/tinygsm-tokenized/00014_00000_shuffled.ds
247
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/tinygsm-tokenized/00015_00000_shuffled.ds
248
+ - /data/home/guanning/olmo_data/mathonly/mix/as_fm3_tg_omi1_omi2/tinygsm-tokenized/00016_00000_shuffled.ds
249
+ memmap_dtype: uint16
250
+ datasets: null
251
+ label_mask_paths:
252
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00000_00000_shuffled.ds
253
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00001_00000_shuffled.ds
254
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00002_00000_shuffled.ds
255
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00003_00000_shuffled.ds
256
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00004_00000_shuffled.ds
257
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00005_00000_shuffled.ds
258
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00006_00000_shuffled.ds
259
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00007_00000_shuffled.ds
260
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00008_00000_shuffled.ds
261
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00009_00000_shuffled.ds
262
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00010_00000_shuffled.ds
263
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00011_00000_shuffled.ds
264
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00012_00000_shuffled.ds
265
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00013_00000_shuffled.ds
266
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00014_00000_shuffled.ds
267
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00016_00000_shuffled.ds
268
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00019_00000_shuffled.ds
269
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00020_00000_shuffled.ds
270
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00021_00000_shuffled.ds
271
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00022_00000_shuffled.ds
272
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00023_00000_shuffled.ds
273
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00024_00000_shuffled.ds
274
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00025_00000_shuffled.ds
275
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00026_00000_shuffled.ds
276
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00027_00000_shuffled.ds
277
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00028_00000_shuffled.ds
278
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00029_00000_shuffled.ds
279
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00030_00000_shuffled.ds
280
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00031_00000_shuffled.ds
281
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00032_00000_shuffled.ds
282
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00033_00000_shuffled.ds
283
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00034_00000_shuffled.ds
284
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00035_00000_shuffled.ds
285
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00036_00000_shuffled.ds
286
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00037_00000_shuffled.ds
287
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00038_00000_shuffled.ds
288
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00039_00000_shuffled.ds
289
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00040_00000_shuffled.ds
290
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00041_00000_shuffled.ds
291
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00042_00000_shuffled.ds
292
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00043_00000_shuffled.ds
293
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00044_00000_shuffled.ds
294
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00045_00000_shuffled.ds
295
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00046_00000_shuffled.ds
296
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00047_00000_shuffled.ds
297
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00048_00000_shuffled.ds
298
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00049_00000_shuffled.ds
299
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00050_00000_shuffled.ds
300
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00051_00000_shuffled.ds
301
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00052_00000_shuffled.ds
302
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00053_00000_shuffled.ds
303
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00054_00000_shuffled.ds
304
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00055_00000_shuffled.ds
305
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00056_00000_shuffled.ds
306
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00057_00000_shuffled.ds
307
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00058_00000_shuffled.ds
308
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00059_00000_shuffled.ds
309
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00060_00000_shuffled.ds
310
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00061_00000_shuffled.ds
311
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00062_00000_shuffled.ds
312
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/algebraic-stack-tokenized/00063_00000_shuffled.ds
313
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00000_00000_shuffled.ds
314
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00001_00000_shuffled.ds
315
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00002_00000_shuffled.ds
316
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00003_00000_shuffled.ds
317
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00004_00000_shuffled.ds
318
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00005_00000_shuffled.ds
319
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00006_00000_shuffled.ds
320
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00007_00000_shuffled.ds
321
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00008_00000_shuffled.ds
322
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00009_00000_shuffled.ds
323
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00010_00000_shuffled.ds
324
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00011_00000_shuffled.ds
325
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00012_00000_shuffled.ds
326
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00013_00000_shuffled.ds
327
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00014_00000_shuffled.ds
328
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00015_00000_shuffled.ds
329
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00016_00000_shuffled.ds
330
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00017_00000_shuffled.ds
331
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00018_00000_shuffled.ds
332
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00019_00000_shuffled.ds
333
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00020_00000_shuffled.ds
334
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00021_00000_shuffled.ds
335
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00022_00000_shuffled.ds
336
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00023_00000_shuffled.ds
337
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00024_00000_shuffled.ds
338
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00025_00000_shuffled.ds
339
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00026_00000_shuffled.ds
340
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00027_00000_shuffled.ds
341
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00028_00000_shuffled.ds
342
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00029_00000_shuffled.ds
343
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00030_00000_shuffled.ds
344
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00031_00000_shuffled.ds
345
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00032_00000_shuffled.ds
346
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00033_00000_shuffled.ds
347
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00034_00000_shuffled.ds
348
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00035_00000_shuffled.ds
349
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00036_00000_shuffled.ds
350
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00037_00000_shuffled.ds
351
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00038_00000_shuffled.ds
352
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00039_00000_shuffled.ds
353
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00040_00000_shuffled.ds
354
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00041_00000_shuffled.ds
355
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00042_00000_shuffled.ds
356
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00043_00000_shuffled.ds
357
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00044_00000_shuffled.ds
358
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00045_00000_shuffled.ds
359
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00046_00000_shuffled.ds
360
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00047_00000_shuffled.ds
361
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00048_00000_shuffled.ds
362
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00049_00000_shuffled.ds
363
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00050_00000_shuffled.ds
364
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00051_00000_shuffled.ds
365
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00052_00000_shuffled.ds
366
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00053_00000_shuffled.ds
367
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00054_00000_shuffled.ds
368
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00055_00000_shuffled.ds
369
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00056_00000_shuffled.ds
370
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00057_00000_shuffled.ds
371
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00058_00000_shuffled.ds
372
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00059_00000_shuffled.ds
373
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00060_00000_shuffled.ds
374
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00061_00000_shuffled.ds
375
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00062_00000_shuffled.ds
376
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/finemath3-tokenized/00063_00000_shuffled.ds
377
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/openmathinstruct1-tokenized/00000_00000_shuffled.ds
378
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/openmathinstruct2-tokenized/00000_00000_shuffled.ds
379
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/openmathinstruct2-tokenized/00001_00000_shuffled.ds
380
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/openmathinstruct2-tokenized/00002_00000_shuffled.ds
381
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/openmathinstruct2-tokenized/00003_00000_shuffled.ds
382
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/openmathinstruct2-tokenized/00004_00000_shuffled.ds
383
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/openmathinstruct2-tokenized/00005_00000_shuffled.ds
384
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/openmathinstruct2-tokenized/00006_00000_shuffled.ds
385
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/openmathinstruct2-tokenized/00007_00000_shuffled.ds
386
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/openmathinstruct2-tokenized/00008_00000_shuffled.ds
387
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/openmathinstruct2-tokenized/00009_00000_shuffled.ds
388
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/openmathinstruct2-tokenized/00010_00000_shuffled.ds
389
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/openmathinstruct2-tokenized/00011_00000_shuffled.ds
390
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/openmathinstruct2-tokenized/00012_00000_shuffled.ds
391
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/openmathinstruct2-tokenized/00013_00000_shuffled.ds
392
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/openmathinstruct2-tokenized/00014_00000_shuffled.ds
393
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/openmathinstruct2-tokenized/00015_00000_shuffled.ds
394
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/openmathinstruct2-tokenized/00016_00000_shuffled.ds
395
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/openmathinstruct2-tokenized/00017_00000_shuffled.ds
396
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/openmathinstruct2-tokenized/00018_00000_shuffled.ds
397
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/openmathinstruct2-tokenized/00019_00000_shuffled.ds
398
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/openmathinstruct2-tokenized/00020_00000_shuffled.ds
399
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/openmathinstruct2-tokenized/00021_00000_shuffled.ds
400
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/openmathinstruct2-tokenized/00022_00000_shuffled.ds
401
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/openmathinstruct2-tokenized/00023_00000_shuffled.ds
402
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/openmathinstruct2-tokenized/00024_00000_shuffled.ds
403
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/openmathinstruct2-tokenized/00025_00000_shuffled.ds
404
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/openmathinstruct2-tokenized/00026_00000_shuffled.ds
405
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/openmathinstruct2-tokenized/00027_00000_shuffled.ds
406
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/openmathinstruct2-tokenized/00028_00000_shuffled.ds
407
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/openmathinstruct2-tokenized/00029_00000_shuffled.ds
408
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/openmathinstruct2-tokenized/00030_00000_shuffled.ds
409
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/openmathinstruct2-tokenized/00031_00000_shuffled.ds
410
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/tinygsm-tokenized/00000_00000_shuffled.ds
411
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/tinygsm-tokenized/00001_00000_shuffled.ds
412
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/tinygsm-tokenized/00002_00000_shuffled.ds
413
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/tinygsm-tokenized/00003_00000_shuffled.ds
414
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/tinygsm-tokenized/00004_00000_shuffled.ds
415
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/tinygsm-tokenized/00005_00000_shuffled.ds
416
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/tinygsm-tokenized/00006_00000_shuffled.ds
417
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/tinygsm-tokenized/00007_00000_shuffled.ds
418
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/tinygsm-tokenized/00008_00000_shuffled.ds
419
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/tinygsm-tokenized/00009_00000_shuffled.ds
420
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/tinygsm-tokenized/00010_00000_shuffled.ds
421
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/tinygsm-tokenized/00011_00000_shuffled.ds
422
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/tinygsm-tokenized/00012_00000_shuffled.ds
423
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/tinygsm-tokenized/00013_00000_shuffled.ds
424
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/tinygsm-tokenized/00014_00000_shuffled.ds
425
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/tinygsm-tokenized/00015_00000_shuffled.ds
426
+ - /data/home/guanning/olmo_runs/mathonly/pkw/masks/CU0/tinygsm-tokenized/00016_00000_shuffled.ds
427
+ pad_direction: right
428
+ generate_attention_mask: false
429
+ generate_doc_lengths: false
430
+ num_workers: 32
431
+ drop_last: true
432
+ pin_memory: true
433
+ prefetch_factor: 8
434
+ persistent_workers: true
435
+ timeout: 0
436
+ seed: null
437
+ instance_filter: null
438
+ custom_dataset: null
439
+ restore_dataloader: true
440
+ fast_forward_batches: null
441
+ evaluators:
442
+ - label: gsm8k-test
443
+ type: lm
444
+ data:
445
+ paths:
446
+ - /data/home/guanning/olmo_data/mathonly/eval/gsm8k-test-tokenized/00000_00000_shuffled.ds
447
+ memmap_dtype: uint16
448
+ datasets: null
449
+ label_mask_paths: null
450
+ pad_direction: right
451
+ generate_attention_mask: false
452
+ generate_doc_lengths: false
453
+ num_workers: 0
454
+ drop_last: true
455
+ pin_memory: false
456
+ prefetch_factor: null
457
+ persistent_workers: false
458
+ timeout: 0
459
+ seed: null
460
+ instance_filter: null
461
+ custom_dataset: null
462
+ device_eval_batch_size: null
463
+ subset_num_batches: null
464
+ - label: math500
465
+ type: lm
466
+ data:
467
+ paths:
468
+ - /data/home/guanning/olmo_data/mathonly/eval/math500-tokenized/00000_00000_shuffled.ds
469
+ memmap_dtype: uint16
470
+ datasets: null
471
+ label_mask_paths: null
472
+ pad_direction: right
473
+ generate_attention_mask: false
474
+ generate_doc_lengths: false
475
+ num_workers: 0
476
+ drop_last: true
477
+ pin_memory: false
478
+ prefetch_factor: null
479
+ persistent_workers: false
480
+ timeout: 0
481
+ seed: null
482
+ instance_filter: null
483
+ custom_dataset: null
484
+ device_eval_batch_size: null
485
+ subset_num_batches: null
486
+ - label: openmathinstruct1-validation
487
+ type: lm
488
+ data:
489
+ paths:
490
+ - /data/home/guanning/olmo_data/mathonly/eval/openmathinstruct1-validation-tokenized/00000_00000_shuffled.ds
491
+ memmap_dtype: uint16
492
+ datasets: null
493
+ label_mask_paths: null
494
+ pad_direction: right
495
+ generate_attention_mask: false
496
+ generate_doc_lengths: false
497
+ num_workers: 0
498
+ drop_last: true
499
+ pin_memory: false
500
+ prefetch_factor: null
501
+ persistent_workers: false
502
+ timeout: 0
503
+ seed: null
504
+ instance_filter: null
505
+ custom_dataset: null
506
+ device_eval_batch_size: null
507
+ subset_num_batches: 50
508
+ - label: gsm8k_gold_bpb_5shot
509
+ type: downstream
510
+ data:
511
+ paths: null
512
+ memmap_dtype: uint16
513
+ datasets: null
514
+ label_mask_paths: null
515
+ pad_direction: right
516
+ generate_attention_mask: false
517
+ generate_doc_lengths: false
518
+ num_workers: 0
519
+ drop_last: false
520
+ pin_memory: false
521
+ prefetch_factor: null
522
+ persistent_workers: false
523
+ timeout: 0
524
+ seed: null
525
+ instance_filter: null
526
+ custom_dataset: null
527
+ device_eval_batch_size: null
528
+ subset_num_batches: null
529
+ - label: basic_arithmetic
530
+ type: downstream
531
+ data:
532
+ paths: null
533
+ memmap_dtype: uint16
534
+ datasets: null
535
+ label_mask_paths: null
536
+ pad_direction: right
537
+ generate_attention_mask: false
538
+ generate_doc_lengths: false
539
+ num_workers: 0
540
+ drop_last: false
541
+ pin_memory: false
542
+ prefetch_factor: null
543
+ persistent_workers: false
544
+ timeout: 0
545
+ seed: null
546
+ instance_filter: null
547
+ custom_dataset: null
548
+ device_eval_batch_size: null
549
+ subset_num_batches: null
550
+ eval_interval: 1000
551
+ tokenizer:
552
+ identifier: rosieyzh/OLMo-150M-4xtg
553
+ truncate_direction: right
554
+ save_folder: /data/home/guanning/olmo_runs/mathonly/OLMo-150M-as_fm3_tg_omi1_omi2-pkwCU0
555
+ remote_save_folder: null
556
+ canceled_check_interval: 50
557
+ save_interval: 2000
558
+ save_interval_unsharded: 5000
559
+ save_interval_ephemeral: null
560
+ save_num_checkpoints_to_keep: 1
561
+ save_num_unsharded_checkpoints_to_keep: 2
562
+ save_overwrite: true
563
+ force_save_unsharded: false
564
+ no_pre_train_checkpoint: false
565
+ load_path: /data/home/guanning/olmo_runs/mathonly/OLMo-150M-as_fm3_tg_omi1_omi2-pkwCU0/step30000-unsharded
566
+ load_path_sharded_checkpointer: null
567
+ try_load_latest_save: true
568
+ reset_optimizer_state: false
569
+ reset_trainer_state: false
570
+ sharded_checkpointer: torch_legacy
571
+ new_style_checkpoints: null
572
+ max_duration: 1ep
573
+ global_train_batch_size: 512
574
+ device_train_batch_size: 64
575
+ device_train_microbatch_size: 16
576
+ device_eval_batch_size: 16
577
+ eval_subset_num_batches: -1
578
+ eval_on_load: false
579
+ device_train_grad_accum: 4
580
+ max_grad_norm: 1.0
581
+ max_grad_norm_ratio: null
582
+ precision: amp_bf16
583
+ wandb:
584
+ project: olmo-mathonly-1018
585
+ entity: train-llm
586
+ group: OLMo-150M
587
+ name: OLMo-150M-as_fm3_tg_omi1_omi2-pkwCU0
588
+ tags:
589
+ - mathonly
590
+ - 150M
591
+ - k1
592
+ log_artifacts: false
593
+ rank_zero_only: true
594
+ log_interval: 1
595
+ speed_monitor:
596
+ window_size: 20
597
+ gpu_flops_available: null
598
+ console_log_interval: 1
599
+ gen1_gc_interval: 1
600
+ compile: null
601
+ distributed_strategy: ddp
602
+ fsdp:
603
+ use_orig_params: true
604
+ sharding_strategy: FULL_SHARD
605
+ wrapping_strategy: null
606
+ precision: pure
607
+ hybrid_sharding_num_model_replicas: null
608
+ ddp:
609
+ grad_sync_mode: batch
610
+ find_unused_params: false
611
+ single:
612
+ device: auto
613
+ softmax_auxiliary_loss: false
614
+ auxiliary_loss_multiplier: 0.0001
615
+ passk_k: 1
616
+ passk_mix: 0
617
+ passk_log_top: 65536
618
+ time_limit: null
619
+ extra_steps_after_cancel: 10
620
+ early_stopping_factor: null
621
+ save_data_indices: true
622
+ python_profiling: false
623
+ torch_profiling: false
624
+ stop_at: 58537
625
+ stop_after: null
626
+ activation_checkpointing: null
627
+ fused_loss: null
628
+ hf_datasets_cache_dir: null
629
+ module_outputs_save_steps: null
pretrain/OLMo-150M-as_fm3_tg_omi1_omi2-pkwCU0/step58527-unsharded/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e8f53b587289ea4d47947bcb9e8e95e87a9c90f0c21859bfe9593bffdc6f64d
3
+ size 649612628
pretrain/OLMo-150M-as_fm3_tg_omi1_omi2-pkwCU0/step58527-unsharded/optim.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5320c1f6b3a95f17b93e5e73526131721c6c0c96ced816cbe90d77901c67bff4
3
+ size 1299223890
pretrain/OLMo-150M-as_fm3_tg_omi1_omi2-pkwCU0/step58527-unsharded/train.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7101dfa956b0431d5d70ccab456a4b8622131f33a81d21575105dd9868958add
3
+ size 14668