rubentium commited on
Commit
0188de4
·
verified ·
1 Parent(s): 86ec5f1

Upload paper checkpoint l30k1_2b_dense checkpoint-37465

Browse files
checkpoints/scale_1p2b_factorial/l30k1_2b_dense/checkpoint-37465/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "attention_bias": false,
18
+ "attention_dropout": 0.0,
19
+ "bos_token_id": 151643,
20
+ "eos_token_id": 151643,
21
+ "checkpoint_activations": true,
22
+ "attention_type": "sparse_stochastic",
23
+ "sparse_block_size": 128,
24
+ "sparse_num_random_blocks": 120,
25
+ "sparse_mask_pool_size": 1,
26
+ "sparse_max_seq_length": 30720,
27
+ "sparse_layer_indices": null,
28
+ "sparse_mask_cache_dir": null,
29
+ "sparse_mask_seed": 0
30
+ }
checkpoints/scale_1p2b_factorial/l30k1_2b_dense/checkpoint-37465/loader_gen_state_rank0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f59a1416dd062038a7e2dbac8c330163f45326660faeb92a199f62460447539
3
+ size 6802
checkpoints/scale_1p2b_factorial/l30k1_2b_dense/checkpoint-37465/loader_gen_state_rank1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9907050ee7aa7455a32aae231218aac0666dd0bc7b78294eeb2cb3adc77e63c8
3
+ size 6802
checkpoints/scale_1p2b_factorial/l30k1_2b_dense/checkpoint-37465/loader_gen_state_rank2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3adc40f4c25919716a49dee06d626601e0abca351145ddf1ed45e0bbfca3ea0c
3
+ size 6802
checkpoints/scale_1p2b_factorial/l30k1_2b_dense/checkpoint-37465/loader_gen_state_rank3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e32dfbaa9aad434214e9087e9315fae33fa445ebde26c320765a117f68a6465
3
+ size 6802
checkpoints/scale_1p2b_factorial/l30k1_2b_dense/checkpoint-37465/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dae3605f86fa1b434305e580e801c55916f9403da4df66bfc009cfd23044c419
3
+ size 2404819483
checkpoints/scale_1p2b_factorial/l30k1_2b_dense/checkpoint-37465/rng_state_rank0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1128ac6f5b9344c031d0a7f7e0256bba80ad6aa48aa6554c2e5e8598694094c4
3
+ size 14821
checkpoints/scale_1p2b_factorial/l30k1_2b_dense/checkpoint-37465/rng_state_rank1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a605f60b47b40b6f08a174c88decd590dab3aa3d66a8000013988181e8c7174c
3
+ size 14821
checkpoints/scale_1p2b_factorial/l30k1_2b_dense/checkpoint-37465/rng_state_rank2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65fb72ddc8f9968964a7f0d6b33b0e35d9b28f0d19be6f991b53baeb9b5efdb9
3
+ size 14821
checkpoints/scale_1p2b_factorial/l30k1_2b_dense/checkpoint-37465/rng_state_rank3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99df05375a53a99b7bdd980373bf3b533a3b5ed8c38051b202a46c688fddb753
3
+ size 14821
checkpoints/scale_1p2b_factorial/l30k1_2b_dense/checkpoint-37465/training_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:934c510ad1264e55e48c3fbd57a10ed8b15d67f4022fb2ad7c1eaee04299623b
3
+ size 4809681879