Ayushk44 commited on
Commit
28b7d0f
·
verified ·
1 Parent(s): 451666c

Upload folder using huggingface_hub

Browse files
step150010-unsharded/config.yaml ADDED
@@ -0,0 +1,465 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ run_name: OLMo-560M-17values
2
+ seed: 6198
3
+ epoch: null
4
+ dry_run: false
5
+ model:
6
+ d_model: 1280
7
+ n_heads: 20
8
+ n_kv_heads: null
9
+ clip_qkv: null
10
+ n_layers: 24
11
+ mlp_ratio: 4
12
+ mlp_hidden_size: 6144
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: false
22
+ attention_dropout: 0.0
23
+ multi_query_attention: false
24
+ attention_layer_norm: false
25
+ residual_dropout: 0.0
26
+ embedding_dropout: 0.0
27
+ embedding_layer_norm: false
28
+ layer_norm_type: rms
29
+ layer_norm_with_affine: true
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: 50277
37
+ embedding_size: 50304
38
+ weight_tying: false
39
+ eos_token_id: 50277
40
+ pad_token_id: 1
41
+ init_device: meta
42
+ init_fn: mitchell
43
+ init_std: 0.02
44
+ init_cutoff_factor: null
45
+ precision: amp_bf16
46
+ scale_emb_init: false
47
+ emb_init_std: null
48
+ norm_after: false
49
+ linear_type: values17
50
+ num_trilm_matrix_scales: 1
51
+ optimizer:
52
+ name: adamw
53
+ learning_rate: 0.00028
54
+ weight_decay: 0.1
55
+ betas:
56
+ - 0.9
57
+ - 0.95
58
+ eps: 1.0e-05
59
+ no_decay_norm_and_bias: null
60
+ selective_updates: false
61
+ decay_norm_and_bias: false
62
+ decay_embeddings: false
63
+ metrics_log_interval: 10
64
+ record_update_metrics: false
65
+ scheduler:
66
+ name: cosine_with_warmup
67
+ units: steps
68
+ t_warmup: 375
69
+ t_max: null
70
+ alpha_f: 0.1
71
+ grad_clip_warmup_steps: null
72
+ grad_clip_warmup_factor: null
73
+ warmup_min_lr: null
74
+ remove_weight_decay_in_second_half: false
75
+ data:
76
+ paths:
77
+ - ../slimp/train/all_combined/combined_1/redpajamaarxiv_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
78
+ - ../slimp/train/all_combined/combined_1/redpajamabook_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
79
+ - ../slimp/train/all_combined/combined_1/redpajamabook_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
80
+ - ../slimp/train/all_combined/combined_1/redpajamac4_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
81
+ - ../slimp/train/all_combined/combined_1/redpajamac4_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
82
+ - ../slimp/train/all_combined/combined_1/redpajamac4_3.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
83
+ - ../slimp/train/all_combined/combined_1/redpajamac4_4.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
84
+ - ../slimp/train/all_combined/combined_1/redpajamac4_5.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
85
+ - ../slimp/train/all_combined/combined_1/redpajamac4_6.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
86
+ - ../slimp/train/all_combined/combined_1/redpajamac4_7.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
87
+ - ../slimp/train/all_combined/combined_1/redpajamac4_8.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
88
+ - ../slimp/train/all_combined/combined_1/redpajamacommoncrawl_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
89
+ - ../slimp/train/all_combined/combined_1/redpajamacommoncrawl_10.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
90
+ - ../slimp/train/all_combined/combined_1/redpajamacommoncrawl_11.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
91
+ - ../slimp/train/all_combined/combined_1/redpajamacommoncrawl_12.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
92
+ - ../slimp/train/all_combined/combined_1/redpajamacommoncrawl_13.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
93
+ - ../slimp/train/all_combined/combined_1/redpajamacommoncrawl_14.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
94
+ - ../slimp/train/all_combined/combined_1/redpajamacommoncrawl_15.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
95
+ - ../slimp/train/all_combined/combined_1/redpajamacommoncrawl_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
96
+ - ../slimp/train/all_combined/combined_1/redpajamacommoncrawl_3.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
97
+ - ../slimp/train/all_combined/combined_1/redpajamacommoncrawl_4.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
98
+ - ../slimp/train/all_combined/combined_1/redpajamacommoncrawl_5.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
99
+ - ../slimp/train/all_combined/combined_1/redpajamacommoncrawl_6.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
100
+ - ../slimp/train/all_combined/combined_1/redpajamacommoncrawl_7.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
101
+ - ../slimp/train/all_combined/combined_1/redpajamacommoncrawl_8.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
102
+ - ../slimp/train/all_combined/combined_1/redpajamacommoncrawl_9.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
103
+ - ../slimp/train/all_combined/combined_1/redpajamagithub_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
104
+ - ../slimp/train/all_combined/combined_1/redpajamagithub_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
105
+ - ../slimp/train/all_combined/combined_1/redpajamastackexchange_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
106
+ - ../slimp/train/all_combined/combined_1/redpajamawikipedia_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
107
+ - ../slimp/train/all_combined/combined_1/redpajamawikipedia_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
108
+ - ../slimp/train/all_combined/combined_2/redpajamaarxiv_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
109
+ - ../slimp/train/all_combined/combined_2/redpajamabook_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
110
+ - ../slimp/train/all_combined/combined_2/redpajamabook_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
111
+ - ../slimp/train/all_combined/combined_2/redpajamac4_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
112
+ - ../slimp/train/all_combined/combined_2/redpajamac4_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
113
+ - ../slimp/train/all_combined/combined_2/redpajamac4_3.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
114
+ - ../slimp/train/all_combined/combined_2/redpajamac4_4.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
115
+ - ../slimp/train/all_combined/combined_2/redpajamac4_5.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
116
+ - ../slimp/train/all_combined/combined_2/redpajamac4_6.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
117
+ - ../slimp/train/all_combined/combined_2/redpajamac4_7.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
118
+ - ../slimp/train/all_combined/combined_2/redpajamac4_8.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
119
+ - ../slimp/train/all_combined/combined_2/redpajamacommoncrawl_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
120
+ - ../slimp/train/all_combined/combined_2/redpajamacommoncrawl_10.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
121
+ - ../slimp/train/all_combined/combined_2/redpajamacommoncrawl_11.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
122
+ - ../slimp/train/all_combined/combined_2/redpajamacommoncrawl_12.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
123
+ - ../slimp/train/all_combined/combined_2/redpajamacommoncrawl_13.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
124
+ - ../slimp/train/all_combined/combined_2/redpajamacommoncrawl_14.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
125
+ - ../slimp/train/all_combined/combined_2/redpajamacommoncrawl_15.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
126
+ - ../slimp/train/all_combined/combined_2/redpajamacommoncrawl_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
127
+ - ../slimp/train/all_combined/combined_2/redpajamacommoncrawl_3.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
128
+ - ../slimp/train/all_combined/combined_2/redpajamacommoncrawl_4.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
129
+ - ../slimp/train/all_combined/combined_2/redpajamacommoncrawl_5.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
130
+ - ../slimp/train/all_combined/combined_2/redpajamacommoncrawl_6.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
131
+ - ../slimp/train/all_combined/combined_2/redpajamacommoncrawl_7.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
132
+ - ../slimp/train/all_combined/combined_2/redpajamacommoncrawl_8.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
133
+ - ../slimp/train/all_combined/combined_2/redpajamacommoncrawl_9.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
134
+ - ../slimp/train/all_combined/combined_2/redpajamagithub_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
135
+ - ../slimp/train/all_combined/combined_2/redpajamagithub_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
136
+ - ../slimp/train/all_combined/combined_2/redpajamastackexchange_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
137
+ - ../slimp/train/all_combined/combined_2/redpajamawikipedia_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
138
+ - ../slimp/train/all_combined/combined_2/redpajamawikipedia_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
139
+ - ../slimp/train/all_combined/combined_3/redpajamaarxiv_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
140
+ - ../slimp/train/all_combined/combined_3/redpajamabook_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
141
+ - ../slimp/train/all_combined/combined_3/redpajamabook_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
142
+ - ../slimp/train/all_combined/combined_3/redpajamac4_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
143
+ - ../slimp/train/all_combined/combined_3/redpajamac4_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
144
+ - ../slimp/train/all_combined/combined_3/redpajamac4_3.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
145
+ - ../slimp/train/all_combined/combined_3/redpajamac4_4.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
146
+ - ../slimp/train/all_combined/combined_3/redpajamac4_5.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
147
+ - ../slimp/train/all_combined/combined_3/redpajamac4_6.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
148
+ - ../slimp/train/all_combined/combined_3/redpajamac4_7.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
149
+ - ../slimp/train/all_combined/combined_3/redpajamac4_8.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
150
+ - ../slimp/train/all_combined/combined_3/redpajamacommoncrawl_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
151
+ - ../slimp/train/all_combined/combined_3/redpajamacommoncrawl_10.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
152
+ - ../slimp/train/all_combined/combined_3/redpajamacommoncrawl_11.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
153
+ - ../slimp/train/all_combined/combined_3/redpajamacommoncrawl_12.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
154
+ - ../slimp/train/all_combined/combined_3/redpajamacommoncrawl_13.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
155
+ - ../slimp/train/all_combined/combined_3/redpajamacommoncrawl_14.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
156
+ - ../slimp/train/all_combined/combined_3/redpajamacommoncrawl_15.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
157
+ - ../slimp/train/all_combined/combined_3/redpajamacommoncrawl_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
158
+ - ../slimp/train/all_combined/combined_3/redpajamacommoncrawl_3.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
159
+ - ../slimp/train/all_combined/combined_3/redpajamacommoncrawl_4.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
160
+ - ../slimp/train/all_combined/combined_3/redpajamacommoncrawl_5.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
161
+ - ../slimp/train/all_combined/combined_3/redpajamacommoncrawl_6.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
162
+ - ../slimp/train/all_combined/combined_3/redpajamacommoncrawl_7.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
163
+ - ../slimp/train/all_combined/combined_3/redpajamacommoncrawl_8.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
164
+ - ../slimp/train/all_combined/combined_3/redpajamacommoncrawl_9.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
165
+ - ../slimp/train/all_combined/combined_3/redpajamagithub_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
166
+ - ../slimp/train/all_combined/combined_3/redpajamagithub_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
167
+ - ../slimp/train/all_combined/combined_3/redpajamastackexchange_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
168
+ - ../slimp/train/all_combined/combined_3/redpajamawikipedia_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
169
+ - ../slimp/train/all_combined/combined_3/redpajamawikipedia_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
170
+ - ../slimp/train/all_combined/combined_4/redpajamaarxiv_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
171
+ - ../slimp/train/all_combined/combined_4/redpajamabook_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
172
+ - ../slimp/train/all_combined/combined_4/redpajamabook_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
173
+ - ../slimp/train/all_combined/combined_4/redpajamac4_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
174
+ - ../slimp/train/all_combined/combined_4/redpajamac4_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
175
+ - ../slimp/train/all_combined/combined_4/redpajamac4_3.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
176
+ - ../slimp/train/all_combined/combined_4/redpajamac4_4.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
177
+ - ../slimp/train/all_combined/combined_4/redpajamac4_5.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
178
+ - ../slimp/train/all_combined/combined_4/redpajamac4_6.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
179
+ - ../slimp/train/all_combined/combined_4/redpajamac4_7.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
180
+ - ../slimp/train/all_combined/combined_4/redpajamac4_8.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
181
+ - ../slimp/train/all_combined/combined_4/redpajamacommoncrawl_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
182
+ - ../slimp/train/all_combined/combined_4/redpajamacommoncrawl_10.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
183
+ - ../slimp/train/all_combined/combined_4/redpajamacommoncrawl_11.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
184
+ - ../slimp/train/all_combined/combined_4/redpajamacommoncrawl_12.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
185
+ - ../slimp/train/all_combined/combined_4/redpajamacommoncrawl_13.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
186
+ - ../slimp/train/all_combined/combined_4/redpajamacommoncrawl_14.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
187
+ - ../slimp/train/all_combined/combined_4/redpajamacommoncrawl_15.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
188
+ - ../slimp/train/all_combined/combined_4/redpajamacommoncrawl_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
189
+ - ../slimp/train/all_combined/combined_4/redpajamacommoncrawl_3.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
190
+ - ../slimp/train/all_combined/combined_4/redpajamacommoncrawl_4.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
191
+ - ../slimp/train/all_combined/combined_4/redpajamacommoncrawl_5.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
192
+ - ../slimp/train/all_combined/combined_4/redpajamacommoncrawl_6.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
193
+ - ../slimp/train/all_combined/combined_4/redpajamacommoncrawl_7.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
194
+ - ../slimp/train/all_combined/combined_4/redpajamacommoncrawl_8.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
195
+ - ../slimp/train/all_combined/combined_4/redpajamacommoncrawl_9.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
196
+ - ../slimp/train/all_combined/combined_4/redpajamagithub_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
197
+ - ../slimp/train/all_combined/combined_4/redpajamagithub_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
198
+ - ../slimp/train/all_combined/combined_4/redpajamastackexchange_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
199
+ - ../slimp/train/all_combined/combined_4/redpajamawikipedia_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
200
+ - ../slimp/train/all_combined/combined_4/redpajamawikipedia_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
201
+ - ../slimp/train/all_combined/combined_5/redpajamaarxiv_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
202
+ - ../slimp/train/all_combined/combined_5/redpajamabook_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
203
+ - ../slimp/train/all_combined/combined_5/redpajamabook_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
204
+ - ../slimp/train/all_combined/combined_5/redpajamac4_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
205
+ - ../slimp/train/all_combined/combined_5/redpajamac4_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
206
+ - ../slimp/train/all_combined/combined_5/redpajamac4_3.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
207
+ - ../slimp/train/all_combined/combined_5/redpajamac4_4.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
208
+ - ../slimp/train/all_combined/combined_5/redpajamac4_5.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
209
+ - ../slimp/train/all_combined/combined_5/redpajamac4_6.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
210
+ - ../slimp/train/all_combined/combined_5/redpajamac4_7.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
211
+ - ../slimp/train/all_combined/combined_5/redpajamac4_8.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
212
+ - ../slimp/train/all_combined/combined_5/redpajamacommoncrawl_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
213
+ - ../slimp/train/all_combined/combined_5/redpajamacommoncrawl_10.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
214
+ - ../slimp/train/all_combined/combined_5/redpajamacommoncrawl_11.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
215
+ - ../slimp/train/all_combined/combined_5/redpajamacommoncrawl_12.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
216
+ - ../slimp/train/all_combined/combined_5/redpajamacommoncrawl_13.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
217
+ - ../slimp/train/all_combined/combined_5/redpajamacommoncrawl_14.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
218
+ - ../slimp/train/all_combined/combined_5/redpajamacommoncrawl_15.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
219
+ - ../slimp/train/all_combined/combined_5/redpajamacommoncrawl_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
220
+ - ../slimp/train/all_combined/combined_5/redpajamacommoncrawl_3.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
221
+ - ../slimp/train/all_combined/combined_5/redpajamacommoncrawl_4.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
222
+ - ../slimp/train/all_combined/combined_5/redpajamacommoncrawl_5.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
223
+ - ../slimp/train/all_combined/combined_5/redpajamacommoncrawl_6.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
224
+ - ../slimp/train/all_combined/combined_5/redpajamacommoncrawl_7.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
225
+ - ../slimp/train/all_combined/combined_5/redpajamacommoncrawl_8.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
226
+ - ../slimp/train/all_combined/combined_5/redpajamacommoncrawl_9.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
227
+ - ../slimp/train/all_combined/combined_5/redpajamagithub_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
228
+ - ../slimp/train/all_combined/combined_5/redpajamagithub_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
229
+ - ../slimp/train/all_combined/combined_5/redpajamastackexchange_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
230
+ - ../slimp/train/all_combined/combined_5/redpajamawikipedia_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
231
+ - ../slimp/train/all_combined/combined_5/redpajamawikipedia_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
232
+ - ../slimp/train/all_combined/combined_6/redpajamaarxiv_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
233
+ - ../slimp/train/all_combined/combined_6/redpajamabook_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
234
+ - ../slimp/train/all_combined/combined_6/redpajamabook_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
235
+ - ../slimp/train/all_combined/combined_6/redpajamac4_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
236
+ - ../slimp/train/all_combined/combined_6/redpajamac4_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
237
+ - ../slimp/train/all_combined/combined_6/redpajamac4_3.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
238
+ - ../slimp/train/all_combined/combined_6/redpajamac4_4.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
239
+ - ../slimp/train/all_combined/combined_6/redpajamac4_5.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
240
+ - ../slimp/train/all_combined/combined_6/redpajamac4_6.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
241
+ - ../slimp/train/all_combined/combined_6/redpajamac4_7.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
242
+ - ../slimp/train/all_combined/combined_6/redpajamac4_8.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
243
+ - ../slimp/train/all_combined/combined_6/redpajamacommoncrawl_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
244
+ - ../slimp/train/all_combined/combined_6/redpajamacommoncrawl_10.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
245
+ - ../slimp/train/all_combined/combined_6/redpajamacommoncrawl_11.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
246
+ - ../slimp/train/all_combined/combined_6/redpajamacommoncrawl_12.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
247
+ - ../slimp/train/all_combined/combined_6/redpajamacommoncrawl_13.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
248
+ - ../slimp/train/all_combined/combined_6/redpajamacommoncrawl_14.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
249
+ - ../slimp/train/all_combined/combined_6/redpajamacommoncrawl_15.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
250
+ - ../slimp/train/all_combined/combined_6/redpajamacommoncrawl_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
251
+ - ../slimp/train/all_combined/combined_6/redpajamacommoncrawl_3.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
252
+ - ../slimp/train/all_combined/combined_6/redpajamacommoncrawl_4.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
253
+ - ../slimp/train/all_combined/combined_6/redpajamacommoncrawl_5.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
254
+ - ../slimp/train/all_combined/combined_6/redpajamacommoncrawl_6.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
255
+ - ../slimp/train/all_combined/combined_6/redpajamacommoncrawl_7.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
256
+ - ../slimp/train/all_combined/combined_6/redpajamacommoncrawl_8.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
257
+ - ../slimp/train/all_combined/combined_6/redpajamacommoncrawl_9.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
258
+ - ../slimp/train/all_combined/combined_6/redpajamagithub_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
259
+ - ../slimp/train/all_combined/combined_6/redpajamagithub_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
260
+ - ../slimp/train/all_combined/combined_6/redpajamastackexchange_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
261
+ - ../slimp/train/all_combined/combined_6/redpajamawikipedia_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
262
+ - ../slimp/train/all_combined/combined_6/redpajamawikipedia_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
263
+ - ../slimp/train/all_combined/combined_7/redpajamaarxiv_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
264
+ - ../slimp/train/all_combined/combined_7/redpajamabook_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
265
+ - ../slimp/train/all_combined/combined_7/redpajamabook_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
266
+ - ../slimp/train/all_combined/combined_7/redpajamac4_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
267
+ - ../slimp/train/all_combined/combined_7/redpajamac4_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
268
+ - ../slimp/train/all_combined/combined_7/redpajamac4_3.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
269
+ - ../slimp/train/all_combined/combined_7/redpajamac4_4.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
270
+ - ../slimp/train/all_combined/combined_7/redpajamac4_5.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
271
+ - ../slimp/train/all_combined/combined_7/redpajamac4_6.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
272
+ - ../slimp/train/all_combined/combined_7/redpajamac4_7.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
273
+ - ../slimp/train/all_combined/combined_7/redpajamac4_8.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
274
+ - ../slimp/train/all_combined/combined_7/redpajamacommoncrawl_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
275
+ - ../slimp/train/all_combined/combined_7/redpajamacommoncrawl_10.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
276
+ - ../slimp/train/all_combined/combined_7/redpajamacommoncrawl_11.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
277
+ - ../slimp/train/all_combined/combined_7/redpajamacommoncrawl_12.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
278
+ - ../slimp/train/all_combined/combined_7/redpajamacommoncrawl_13.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
279
+ - ../slimp/train/all_combined/combined_7/redpajamacommoncrawl_14.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
280
+ - ../slimp/train/all_combined/combined_7/redpajamacommoncrawl_15.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
281
+ - ../slimp/train/all_combined/combined_7/redpajamacommoncrawl_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
282
+ - ../slimp/train/all_combined/combined_7/redpajamacommoncrawl_3.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
283
+ - ../slimp/train/all_combined/combined_7/redpajamacommoncrawl_4.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
284
+ - ../slimp/train/all_combined/combined_7/redpajamacommoncrawl_5.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
285
+ - ../slimp/train/all_combined/combined_7/redpajamacommoncrawl_6.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
286
+ - ../slimp/train/all_combined/combined_7/redpajamacommoncrawl_7.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
287
+ - ../slimp/train/all_combined/combined_7/redpajamacommoncrawl_8.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
288
+ - ../slimp/train/all_combined/combined_7/redpajamacommoncrawl_9.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
289
+ - ../slimp/train/all_combined/combined_7/redpajamagithub_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
290
+ - ../slimp/train/all_combined/combined_7/redpajamagithub_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
291
+ - ../slimp/train/all_combined/combined_7/redpajamastackexchange_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
292
+ - ../slimp/train/all_combined/combined_7/redpajamawikipedia_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
293
+ - ../slimp/train/all_combined/combined_7/redpajamawikipedia_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
294
+ - ../slimp/train/all_combined/combined_8/redpajamaarxiv_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
295
+ - ../slimp/train/all_combined/combined_8/redpajamabook_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
296
+ - ../slimp/train/all_combined/combined_8/redpajamabook_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
297
+ - ../slimp/train/all_combined/combined_8/redpajamac4_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
298
+ - ../slimp/train/all_combined/combined_8/redpajamac4_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
299
+ - ../slimp/train/all_combined/combined_8/redpajamac4_3.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
300
+ - ../slimp/train/all_combined/combined_8/redpajamac4_4.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
301
+ - ../slimp/train/all_combined/combined_8/redpajamac4_5.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
302
+ - ../slimp/train/all_combined/combined_8/redpajamac4_6.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
303
+ - ../slimp/train/all_combined/combined_8/redpajamac4_7.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
304
+ - ../slimp/train/all_combined/combined_8/redpajamac4_8.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
305
+ - ../slimp/train/all_combined/combined_8/redpajamacommoncrawl_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
306
+ - ../slimp/train/all_combined/combined_8/redpajamacommoncrawl_10.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
307
+ - ../slimp/train/all_combined/combined_8/redpajamacommoncrawl_11.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
308
+ - ../slimp/train/all_combined/combined_8/redpajamacommoncrawl_12.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
309
+ - ../slimp/train/all_combined/combined_8/redpajamacommoncrawl_13.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
310
+ - ../slimp/train/all_combined/combined_8/redpajamacommoncrawl_14.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
311
+ - ../slimp/train/all_combined/combined_8/redpajamacommoncrawl_15.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
312
+ - ../slimp/train/all_combined/combined_8/redpajamacommoncrawl_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
313
+ - ../slimp/train/all_combined/combined_8/redpajamacommoncrawl_3.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
314
+ - ../slimp/train/all_combined/combined_8/redpajamacommoncrawl_4.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
315
+ - ../slimp/train/all_combined/combined_8/redpajamacommoncrawl_5.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
316
+ - ../slimp/train/all_combined/combined_8/redpajamacommoncrawl_6.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
317
+ - ../slimp/train/all_combined/combined_8/redpajamacommoncrawl_7.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
318
+ - ../slimp/train/all_combined/combined_8/redpajamacommoncrawl_8.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
319
+ - ../slimp/train/all_combined/combined_8/redpajamacommoncrawl_9.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
320
+ - ../slimp/train/all_combined/combined_8/redpajamagithub_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
321
+ - ../slimp/train/all_combined/combined_8/redpajamagithub_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
322
+ - ../slimp/train/all_combined/combined_8/redpajamastackexchange_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
323
+ - ../slimp/train/all_combined/combined_8/redpajamawikipedia_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
324
+ - ../slimp/train/all_combined/combined_8/redpajamawikipedia_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
325
+ - ../slimp/train/all_combined/combined_9/redpajamaarxiv_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
326
+ - ../slimp/train/all_combined/combined_9/redpajamabook_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
327
+ - ../slimp/train/all_combined/combined_9/redpajamabook_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
328
+ - ../slimp/train/all_combined/combined_9/redpajamac4_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
329
+ - ../slimp/train/all_combined/combined_9/redpajamac4_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
330
+ - ../slimp/train/all_combined/combined_9/redpajamac4_3.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
331
+ - ../slimp/train/all_combined/combined_9/redpajamac4_4.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
332
+ - ../slimp/train/all_combined/combined_9/redpajamac4_5.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
333
+ - ../slimp/train/all_combined/combined_9/redpajamac4_6.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
334
+ - ../slimp/train/all_combined/combined_9/redpajamac4_7.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
335
+ - ../slimp/train/all_combined/combined_9/redpajamac4_8.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
336
+ - ../slimp/train/all_combined/combined_9/redpajamacommoncrawl_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
337
+ - ../slimp/train/all_combined/combined_9/redpajamacommoncrawl_10.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
338
+ - ../slimp/train/all_combined/combined_9/redpajamacommoncrawl_11.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
339
+ - ../slimp/train/all_combined/combined_9/redpajamacommoncrawl_12.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
340
+ - ../slimp/train/all_combined/combined_9/redpajamacommoncrawl_13.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
341
+ - ../slimp/train/all_combined/combined_9/redpajamacommoncrawl_14.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
342
+ - ../slimp/train/all_combined/combined_9/redpajamacommoncrawl_15.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
343
+ - ../slimp/train/all_combined/combined_9/redpajamacommoncrawl_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
344
+ - ../slimp/train/all_combined/combined_9/redpajamacommoncrawl_3.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
345
+ - ../slimp/train/all_combined/combined_9/redpajamacommoncrawl_4.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
346
+ - ../slimp/train/all_combined/combined_9/redpajamacommoncrawl_5.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
347
+ - ../slimp/train/all_combined/combined_9/redpajamacommoncrawl_6.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
348
+ - ../slimp/train/all_combined/combined_9/redpajamacommoncrawl_7.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
349
+ - ../slimp/train/all_combined/combined_9/redpajamacommoncrawl_8.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
350
+ - ../slimp/train/all_combined/combined_9/redpajamacommoncrawl_9.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
351
+ - ../slimp/train/all_combined/combined_9/redpajamagithub_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
352
+ - ../slimp/train/all_combined/combined_9/redpajamagithub_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
353
+ - ../slimp/train/all_combined/combined_9/redpajamastackexchange_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
354
+ - ../slimp/train/all_combined/combined_9/redpajamawikipedia_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
355
+ - ../slimp/train/all_combined/combined_9/redpajamawikipedia_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
356
+ - ../slimp/train/all_combined/combined_10/redpajamaarxiv_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
357
+ - ../slimp/train/all_combined/combined_10/redpajamabook_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
358
+ - ../slimp/train/all_combined/combined_10/redpajamabook_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
359
+ - ../slimp/train/all_combined/combined_10/redpajamac4_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
360
+ - ../slimp/train/all_combined/combined_10/redpajamac4_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
361
+ - ../slimp/train/all_combined/combined_10/redpajamac4_3.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
362
+ - ../slimp/train/all_combined/combined_10/redpajamac4_4.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
363
+ - ../slimp/train/all_combined/combined_10/redpajamac4_5.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
364
+ - ../slimp/train/all_combined/combined_10/redpajamac4_6.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
365
+ - ../slimp/train/all_combined/combined_10/redpajamac4_7.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
366
+ - ../slimp/train/all_combined/combined_10/redpajamac4_8.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
367
+ - ../slimp/train/all_combined/combined_10/redpajamacommoncrawl_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
368
+ - ../slimp/train/all_combined/combined_10/redpajamacommoncrawl_10.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
369
+ - ../slimp/train/all_combined/combined_10/redpajamacommoncrawl_11.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
370
+ - ../slimp/train/all_combined/combined_10/redpajamacommoncrawl_12.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
371
+ - ../slimp/train/all_combined/combined_10/redpajamacommoncrawl_13.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
372
+ - ../slimp/train/all_combined/combined_10/redpajamacommoncrawl_14.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
373
+ - ../slimp/train/all_combined/combined_10/redpajamacommoncrawl_15.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
374
+ - ../slimp/train/all_combined/combined_10/redpajamacommoncrawl_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
375
+ - ../slimp/train/all_combined/combined_10/redpajamacommoncrawl_3.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
376
+ - ../slimp/train/all_combined/combined_10/redpajamacommoncrawl_4.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
377
+ - ../slimp/train/all_combined/combined_10/redpajamacommoncrawl_5.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
378
+ - ../slimp/train/all_combined/combined_10/redpajamacommoncrawl_6.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
379
+ - ../slimp/train/all_combined/combined_10/redpajamacommoncrawl_7.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
380
+ - ../slimp/train/all_combined/combined_10/redpajamacommoncrawl_8.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
381
+ - ../slimp/train/all_combined/combined_10/redpajamacommoncrawl_9.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
382
+ - ../slimp/train/all_combined/combined_10/redpajamagithub_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
383
+ - ../slimp/train/all_combined/combined_10/redpajamagithub_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
384
+ - ../slimp/train/all_combined/combined_10/redpajamastackexchange_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
385
+ - ../slimp/train/all_combined/combined_10/redpajamawikipedia_1.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
386
+ - ../slimp/train/all_combined/combined_10/redpajamawikipedia_2.jsonl.gz.tokenized.spectra.out.npy/0_00000.npy
387
+ memmap_dtype: uint16
388
+ datasets: null
389
+ label_mask_paths: null
390
+ pad_direction: right
391
+ generate_attention_mask: false
392
+ generate_doc_lengths: false
393
+ num_workers: 0
394
+ drop_last: true
395
+ pin_memory: true
396
+ prefetch_factor: 16
397
+ persistent_workers: true
398
+ timeout: 0
399
+ seed: null
400
+ instance_filter: null
401
+ restore_dataloader: true
402
+ fast_forward_batches: null
403
+ evaluators: []
404
+ eval_interval: 500
405
+ tokenizer:
406
+ identifier: ../spectra_tokenizer/tokenizer.json
407
+ truncate_direction: right
408
+ save_folder: checkpoints/olmo-560M-17values/
409
+ remote_save_folder: null
410
+ canceled_check_interval: 50
411
+ save_interval: 500
412
+ save_interval_unsharded: 10000
413
+ save_interval_ephemeral: null
414
+ save_num_checkpoints_to_keep: 4
415
+ save_num_unsharded_checkpoints_to_keep: -1
416
+ save_overwrite: true
417
+ force_save_unsharded: false
418
+ no_pre_train_checkpoint: false
419
+ load_path: checkpoints/olmo-560M-17values//latest
420
+ load_path_sharded_checkpointer: null
421
+ try_load_latest_save: false
422
+ reset_optimizer_state: false
423
+ reset_trainer_state: false
424
+ sharded_checkpointer: torch_legacy
425
+ new_style_checkpoints: null
426
+ max_duration: 150000
427
+ global_train_batch_size: 1024
428
+ device_train_batch_size: 4
429
+ device_train_microbatch_size: 4
430
+ device_eval_batch_size: 4
431
+ eval_subset_num_batches: -1
432
+ eval_on_load: false
433
+ device_train_grad_accum: 1
434
+ max_grad_norm: 1.0
435
+ max_grad_norm_ratio: null
436
+ precision: amp_bf16
437
+ wandb: null
438
+ speed_monitor:
439
+ window_size: 20
440
+ gpu_flops_available: null
441
+ console_log_interval: 1
442
+ gen1_gc_interval: 1
443
+ compile: null
444
+ distributed_strategy: fsdp
445
+ fsdp:
446
+ use_orig_params: true
447
+ sharding_strategy: _HYBRID_SHARD_ZERO2
448
+ wrapping_strategy: null
449
+ precision: pure
450
+ hybrid_sharding_num_model_replicas: null
451
+ ddp: null
452
+ softmax_auxiliary_loss: false
453
+ auxiliary_loss_multiplier: 0.0001
454
+ time_limit: null
455
+ extra_steps_after_cancel: 10
456
+ early_stopping_factor: null
457
+ save_data_indices: true
458
+ python_profiling: false
459
+ torch_profiling: false
460
+ stop_at: 150010
461
+ stop_after: null
462
+ activation_checkpointing: null
463
+ fused_loss: null
464
+ hf_datasets_cache_dir: null
465
+ module_outputs_save_steps: null
step150010-unsharded/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc8a245efc8789ddd409d0f816f8e3314fd3e778935699c6144cd8e155558b7f
3
+ size 2277037726
step150010-unsharded/optim.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78dec8e031854eefcd35fc90d3c84ce0d3ecce2217f7ec20e0ee502b422a68f3
3
+ size 4554069146
step150010-unsharded/train.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea4d057043ea595704b9cfe75b2d8f4db492e53b0ca9e31d4349131cba5693fd
3
+ size 15116