Add final paper checkpoint: checkpoints/scale_1p2b_factorial/l8k1_2b_dense_legacy42/checkpoint-50462
Browse files- checkpoints/scale_1p2b_factorial/l8k1_2b_dense_legacy42/checkpoint-50462/config.json +29 -0
- checkpoints/scale_1p2b_factorial/l8k1_2b_dense_legacy42/checkpoint-50462/loader_gen_state_rank0.pt +3 -0
- checkpoints/scale_1p2b_factorial/l8k1_2b_dense_legacy42/checkpoint-50462/loader_gen_state_rank1.pt +3 -0
- checkpoints/scale_1p2b_factorial/l8k1_2b_dense_legacy42/checkpoint-50462/loader_gen_state_rank2.pt +3 -0
- checkpoints/scale_1p2b_factorial/l8k1_2b_dense_legacy42/checkpoint-50462/model.pt +3 -0
- checkpoints/scale_1p2b_factorial/l8k1_2b_dense_legacy42/checkpoint-50462/rng_state_rank0.pt +3 -0
- checkpoints/scale_1p2b_factorial/l8k1_2b_dense_legacy42/checkpoint-50462/rng_state_rank1.pt +3 -0
- checkpoints/scale_1p2b_factorial/l8k1_2b_dense_legacy42/checkpoint-50462/rng_state_rank2.pt +3 -0
- checkpoints/scale_1p2b_factorial/l8k1_2b_dense_legacy42/checkpoint-50462/training_state.pt +3 -0
checkpoints/scale_1p2b_factorial/l8k1_2b_dense_legacy42/checkpoint-50462/config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": false,
|
| 22 |
+
"attention_type": "dense",
|
| 23 |
+
"sparse_block_size": 128,
|
| 24 |
+
"sparse_num_random_blocks": 31,
|
| 25 |
+
"sparse_mask_pool_size": 10000,
|
| 26 |
+
"sparse_max_seq_length": 8192,
|
| 27 |
+
"sparse_layer_indices": null,
|
| 28 |
+
"sparse_mask_cache_dir": "/mloscratch/homes/navasard/sparse/mask_cache"
|
| 29 |
+
}
|
checkpoints/scale_1p2b_factorial/l8k1_2b_dense_legacy42/checkpoint-50462/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/l8k1_2b_dense_legacy42/checkpoint-50462/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/l8k1_2b_dense_legacy42/checkpoint-50462/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/l8k1_2b_dense_legacy42/checkpoint-50462/model.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c261e09608d8c9b47a775c4b3f411962e1e578394ab4d689434bff1dd74edc4a
|
| 3 |
+
size 2404819483
|
checkpoints/scale_1p2b_factorial/l8k1_2b_dense_legacy42/checkpoint-50462/rng_state_rank0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d66132173225a4acb20151e039d5fc29136a50308afb4057d1dfa318c274c937
|
| 3 |
+
size 14821
|
checkpoints/scale_1p2b_factorial/l8k1_2b_dense_legacy42/checkpoint-50462/rng_state_rank1.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f53c4542beab4fe2dd57bf3655da5047915c871acc0074aa90961494b34ae1c
|
| 3 |
+
size 14821
|
checkpoints/scale_1p2b_factorial/l8k1_2b_dense_legacy42/checkpoint-50462/rng_state_rank2.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bdae53fe6463ea7533e340b6acd3ff2ddfd576bc95e2d7935380cf17271aa8fb
|
| 3 |
+
size 14821
|
checkpoints/scale_1p2b_factorial/l8k1_2b_dense_legacy42/checkpoint-50462/training_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d860efcc23642bfabde7f68bddaf216c0a406ce332e0963ad2ea19ae5bc7e7a0
|
| 3 |
+
size 4809681879
|