rubentium commited on
Commit
d8f62e6
·
verified ·
1 Parent(s): 7f2f9e8

Archive FINAL5 seed71_dense checkpoint checkpoint-50462

Browse files
FINAL5_20261014/seed71_dense/checkpoint-50462/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "qk_gain_fp32": true,
18
+ "rope_train_position_scale_set": null,
19
+ "attention_bias": false,
20
+ "attention_dropout": 0.0,
21
+ "bos_token_id": 151643,
22
+ "eos_token_id": 151643,
23
+ "checkpoint_activations": false,
24
+ "attention_type": "sparse_stochastic",
25
+ "sparse_block_size": 128,
26
+ "sparse_num_random_blocks": 31,
27
+ "sparse_mask_pool_size": 1,
28
+ "sparse_max_seq_length": 8192,
29
+ "sparse_layer_indices": null,
30
+ "sparse_mask_cache_dir": null,
31
+ "sparse_mask_seed": 0,
32
+ "sparse_mixed_nrb_set": null,
33
+ "moba_block_size": 128,
34
+ "moba_top_k": 32,
35
+ "asentmax_alpha": 1.5,
36
+ "asentmax_learn_temp": true,
37
+ "asentmax_init_temp": 1.0
38
+ }
FINAL5_20261014/seed71_dense/checkpoint-50462/loader_gen_state_rank0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a52ec8b470b53d99a4266717af513dc1335821eeccae71d7b1c741ea30fe7ecf
3
+ size 6802
FINAL5_20261014/seed71_dense/checkpoint-50462/loader_gen_state_rank1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4541d1270159558df57f6c4e0010eba014b22528730f001f281418c58c04068a
3
+ size 6802
FINAL5_20261014/seed71_dense/checkpoint-50462/loader_gen_state_rank2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cf7e766b6e265a6ca4408e0b3f07da4b27afda571643a5ed4bb29203e9ed62e
3
+ size 6802
FINAL5_20261014/seed71_dense/checkpoint-50462/loader_gen_state_rank3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63240e883e17d9a5d38fb7fd9fad2e0cc50b4e2a0e13b5d39232b6c19795a4f1
3
+ size 6802
FINAL5_20261014/seed71_dense/checkpoint-50462/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5da209cd55096d1bc02644094c1155e4a1d91aecb7af20fe09176ce886a9ff92
3
+ size 2404833883
FINAL5_20261014/seed71_dense/checkpoint-50462/rng_state_rank0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cad564dcc31cf2060b64ae518c5168994c5c109bbcbf7f31d1b1c6dd0c9cafb3
3
+ size 14821
FINAL5_20261014/seed71_dense/checkpoint-50462/rng_state_rank1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:808e5329ccc8690dc12a0ebcd8d0a1cd8a537646f59fb35fffb316975d48c9a2
3
+ size 14821
FINAL5_20261014/seed71_dense/checkpoint-50462/rng_state_rank2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91681667a7262c9ff27f8ddfefa4f05f83295b0d212eb63c4d2c75a573a8232b
3
+ size 14821
FINAL5_20261014/seed71_dense/checkpoint-50462/rng_state_rank3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08aee764d012e4e004d622bd67649087d65f04d90c51d0e89ad0a60c1fb9ec65
3
+ size 14821
FINAL5_20261014/seed71_dense/checkpoint-50462/training_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbb5ebbdf65c89a7152e47ffcc2311ca6ea246aad5af084b2bb32b23047154c7
3
+ size 4809712479