Upload paper checkpoint l8k1p2b_dense_seed71 checkpoint-50462
Browse files- checkpoints/scale_1p2b_current/l8k1p2b_dense_seed71/checkpoint-50462/config.json +37 -0
- checkpoints/scale_1p2b_current/l8k1p2b_dense_seed71/checkpoint-50462/loader_gen_state_rank0.pt +3 -0
- checkpoints/scale_1p2b_current/l8k1p2b_dense_seed71/checkpoint-50462/loader_gen_state_rank1.pt +3 -0
- checkpoints/scale_1p2b_current/l8k1p2b_dense_seed71/checkpoint-50462/loader_gen_state_rank2.pt +3 -0
- checkpoints/scale_1p2b_current/l8k1p2b_dense_seed71/checkpoint-50462/loader_gen_state_rank3.pt +3 -0
- checkpoints/scale_1p2b_current/l8k1p2b_dense_seed71/checkpoint-50462/loader_gen_state_rank4.pt +3 -0
- checkpoints/scale_1p2b_current/l8k1p2b_dense_seed71/checkpoint-50462/loader_gen_state_rank5.pt +3 -0
- checkpoints/scale_1p2b_current/l8k1p2b_dense_seed71/checkpoint-50462/model.pt +3 -0
- checkpoints/scale_1p2b_current/l8k1p2b_dense_seed71/checkpoint-50462/rng_state_rank0.pt +3 -0
- checkpoints/scale_1p2b_current/l8k1p2b_dense_seed71/checkpoint-50462/rng_state_rank1.pt +3 -0
- checkpoints/scale_1p2b_current/l8k1p2b_dense_seed71/checkpoint-50462/rng_state_rank2.pt +3 -0
- checkpoints/scale_1p2b_current/l8k1p2b_dense_seed71/checkpoint-50462/rng_state_rank3.pt +3 -0
- checkpoints/scale_1p2b_current/l8k1p2b_dense_seed71/checkpoint-50462/rng_state_rank4.pt +3 -0
- checkpoints/scale_1p2b_current/l8k1p2b_dense_seed71/checkpoint-50462/rng_state_rank5.pt +3 -0
- checkpoints/scale_1p2b_current/l8k1p2b_dense_seed71/checkpoint-50462/training_state.pt +3 -0
checkpoints/scale_1p2b_current/l8k1p2b_dense_seed71/checkpoint-50462/config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": false,
|
| 23 |
+
"attention_type": "sparse_stochastic",
|
| 24 |
+
"sparse_block_size": 128,
|
| 25 |
+
"sparse_num_random_blocks": 31,
|
| 26 |
+
"sparse_mask_pool_size": 1,
|
| 27 |
+
"sparse_max_seq_length": 8192,
|
| 28 |
+
"sparse_layer_indices": null,
|
| 29 |
+
"sparse_mask_cache_dir": null,
|
| 30 |
+
"sparse_mask_seed": 0,
|
| 31 |
+
"sparse_mixed_nrb_set": null,
|
| 32 |
+
"moba_block_size": 128,
|
| 33 |
+
"moba_top_k": 32,
|
| 34 |
+
"asentmax_alpha": 1.5,
|
| 35 |
+
"asentmax_learn_temp": true,
|
| 36 |
+
"asentmax_init_temp": 1.0
|
| 37 |
+
}
|
checkpoints/scale_1p2b_current/l8k1p2b_dense_seed71/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
|
checkpoints/scale_1p2b_current/l8k1p2b_dense_seed71/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
|
checkpoints/scale_1p2b_current/l8k1p2b_dense_seed71/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
|
checkpoints/scale_1p2b_current/l8k1p2b_dense_seed71/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
|
checkpoints/scale_1p2b_current/l8k1p2b_dense_seed71/checkpoint-50462/loader_gen_state_rank4.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bfbfec0835c96b36ef9ba70883464f2f6d43f18c86b9fcd7ec1edf04672cb51e
|
| 3 |
+
size 6802
|
checkpoints/scale_1p2b_current/l8k1p2b_dense_seed71/checkpoint-50462/loader_gen_state_rank5.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:998aa5e419a1db81568bcb5727cd5ed68729ea9492d8f6f1dedd6517fc295b01
|
| 3 |
+
size 6802
|
checkpoints/scale_1p2b_current/l8k1p2b_dense_seed71/checkpoint-50462/model.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95c122886a4d972d0eb50fe7989de994b4bde8ba65cb424780b2d3152dffa764
|
| 3 |
+
size 2404819483
|
checkpoints/scale_1p2b_current/l8k1p2b_dense_seed71/checkpoint-50462/rng_state_rank0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ccee5b4e7fd58a12a990fd9538c1aed245a45bd5556b01d9c06bf0535cdba35
|
| 3 |
+
size 14821
|
checkpoints/scale_1p2b_current/l8k1p2b_dense_seed71/checkpoint-50462/rng_state_rank1.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6f4515e21c45da4604daf9d38399e2467cbf918534d4efb755984c8709258647
|
| 3 |
+
size 14821
|
checkpoints/scale_1p2b_current/l8k1p2b_dense_seed71/checkpoint-50462/rng_state_rank2.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:51c79c0d97b5e77fbc0ab241c9db6f5131bcad2ceb4a5e579c21cce4380dd6bc
|
| 3 |
+
size 14821
|
checkpoints/scale_1p2b_current/l8k1p2b_dense_seed71/checkpoint-50462/rng_state_rank3.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b8624de07d8164f12d11113519e8be8e9be334336d1a12ac562cace82d7d0b0
|
| 3 |
+
size 14821
|
checkpoints/scale_1p2b_current/l8k1p2b_dense_seed71/checkpoint-50462/rng_state_rank4.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9276907d9e449ef84e3cfe61d989b3d6b0350d4686d993281442e142e6ebde15
|
| 3 |
+
size 14821
|
checkpoints/scale_1p2b_current/l8k1p2b_dense_seed71/checkpoint-50462/rng_state_rank5.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59f711fe1d5cc92c88db3e5a29b6fe6dbbff5f774a0b9b05163466b4d009f439
|
| 3 |
+
size 14821
|
checkpoints/scale_1p2b_current/l8k1p2b_dense_seed71/checkpoint-50462/training_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8431de880e79c90a904c23eb755325fd1491a662f6aba37f150c7ffc2b2750da
|
| 3 |
+
size 4809681879
|