rubentium commited on
Commit
be6e336
·
verified ·
1 Parent(s): 34b4e9a

Upload paper checkpoint l8k1p2b_mixed_seed70 checkpoint-48962

Browse files
checkpoints/scale_1p2b_current/l8k1p2b_mixed_seed70/checkpoint-48962/config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "vocab_size": 151936,
3
+ "hidden_size": 1536,
4
+ "intermediate_size": 6144,
5
+ "num_hidden_layers": 28,
6
+ "num_attention_heads": 12,
7
+ "num_key_value_heads": 4,
8
+ "head_dim": 128,
9
+ "hidden_act": "silu",
10
+ "max_position_embeddings": 32768,
11
+ "initializer_range": 0.02,
12
+ "rms_norm_eps": 1e-06,
13
+ "use_cache": true,
14
+ "tie_word_embeddings": true,
15
+ "rope_theta": 1000000,
16
+ "rope_scaling": null,
17
+ "rope_train_position_scale_set": null,
18
+ "attention_bias": false,
19
+ "attention_dropout": 0.0,
20
+ "bos_token_id": 151643,
21
+ "eos_token_id": 151643,
22
+ "checkpoint_activations": true,
23
+ "attention_type": "sparse_stochastic",
24
+ "sparse_block_size": 128,
25
+ "sparse_num_random_blocks": 35,
26
+ "sparse_mask_pool_size": 10000,
27
+ "sparse_max_seq_length": 8192,
28
+ "sparse_layer_indices": null,
29
+ "sparse_mask_cache_dir": "/mloscratch/homes/navasard/sparse/mask_cache_8k_mixed",
30
+ "sparse_mask_seed": 70,
31
+ "sparse_mixed_nrb_set": [
32
+ 63,
33
+ 47,
34
+ 31,
35
+ 21,
36
+ 11
37
+ ],
38
+ "moba_block_size": 128,
39
+ "moba_top_k": 32,
40
+ "asentmax_alpha": 1.5,
41
+ "asentmax_learn_temp": true,
42
+ "asentmax_init_temp": 1.0
43
+ }
checkpoints/scale_1p2b_current/l8k1p2b_mixed_seed70/checkpoint-48962/loader_gen_state_rank0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3d3d87a844d4fd6548dfc4c1235a1ee3e262506bc6260da75e7cbf9d9da819c
3
+ size 6802
checkpoints/scale_1p2b_current/l8k1p2b_mixed_seed70/checkpoint-48962/loader_gen_state_rank1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2c029e9127ff4c346ab99e6af8377a6903003909fec0b073b70bfafc01d4517
3
+ size 6802
checkpoints/scale_1p2b_current/l8k1p2b_mixed_seed70/checkpoint-48962/loader_gen_state_rank2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:917e752ef93a10f1da3dc49f9c18adc43ae1bb568ee13d528c9824ee4513b511
3
+ size 6802
checkpoints/scale_1p2b_current/l8k1p2b_mixed_seed70/checkpoint-48962/loader_gen_state_rank3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:389dee6373df6f406c9ae897b97bc5acc1b426bc8c9810e2754f7d2f892a256f
3
+ size 6802
checkpoints/scale_1p2b_current/l8k1p2b_mixed_seed70/checkpoint-48962/loader_gen_state_rank4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:003f8a68f6377e121aa1e72c457466320b22898c8d61a840ded7da21790b0d73
3
+ size 6802
checkpoints/scale_1p2b_current/l8k1p2b_mixed_seed70/checkpoint-48962/loader_gen_state_rank5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3e0c9bf4dad32ac42f0c9f053baa4af26df892924de882f06738359b36322b1
3
+ size 6802
checkpoints/scale_1p2b_current/l8k1p2b_mixed_seed70/checkpoint-48962/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3943fcd16602bec5cca2c724336457fd581362385a38edf20fada03c134930b9
3
+ size 2404819483
checkpoints/scale_1p2b_current/l8k1p2b_mixed_seed70/checkpoint-48962/rng_state_rank0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98c2c6112862ca86a947ff2a24e7be4e6217a4bc6d25459e55c34e9146001fc5
3
+ size 14821
checkpoints/scale_1p2b_current/l8k1p2b_mixed_seed70/checkpoint-48962/rng_state_rank1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb76b82282ca8aa4e88abb381bef17ac3515e5696025391a81749733fda45441
3
+ size 14821
checkpoints/scale_1p2b_current/l8k1p2b_mixed_seed70/checkpoint-48962/rng_state_rank2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cfbc77c504bb6ec7579b4492ef8ed8d9cf0c813e6fb5ff339c2a464fb19447f
3
+ size 14821
checkpoints/scale_1p2b_current/l8k1p2b_mixed_seed70/checkpoint-48962/rng_state_rank3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58f353e0f89039c2e2296b646a62d36e393996466461901ec71c1192e01f280a
3
+ size 14821
checkpoints/scale_1p2b_current/l8k1p2b_mixed_seed70/checkpoint-48962/rng_state_rank4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4213fda7006147a6e18d28b76d9f9ba2341b7c40a6a4b68308945ae3aa700bd
3
+ size 14821
checkpoints/scale_1p2b_current/l8k1p2b_mixed_seed70/checkpoint-48962/rng_state_rank5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f9a9bc86812ca8205a22ba7f11de909783b6a4e7fb4143a687c6f2140bd08c0
3
+ size 14885
checkpoints/scale_1p2b_current/l8k1p2b_mixed_seed70/checkpoint-48962/training_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee38cc10d72036358793d2ed8abff622670282f7eab247620cd4de5dd993906a
3
+ size 4809681879