Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/latest +1 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3 -0
- 1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3 -0
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/latest
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
pytorch_model
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98254f848a924e279982c14d5a1241a3798fe9c12c0cf0f74487053a36598200
|
3 |
+
size 106611632
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc6d8ef72ede544384b0c1bcbcf972ae8a6b4a1210fd90a0ce19852df75ba915
|
3 |
+
size 106611968
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:185570b578bc4113e5e1cffb0c12f9b55bfa28b01c651c13c9ee48ee2fb51fa1
|
3 |
+
size 106611584
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d9c1542e870eb8e722463eb9a8de930f9b55630fec9e591cc187119dcf75d1bd
|
3 |
+
size 106611456
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87552a885a7acedaab8373fee97d46ac8cdc0975cbc6e9e31b8abef299a55f1f
|
3 |
+
size 106612224
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93b4ebf9d3193bed0617b9fd525855ed16ba90f782c1061df04e62bd85888d47
|
3 |
+
size 106611776
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:524daa245a4e9abeaf428ecb6c872de2931249a7405689bf5c7625c15911446f
|
3 |
+
size 106611584
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44fd88fc063856072b042554730a90c438046dd24c7913a107e070fa0c2cb03e
|
3 |
+
size 106612224
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a9d6e4af4ec68844e58a94d3c2a1f512832069e32f0fef5c70fafc9701b74c6
|
3 |
+
size 106611776
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d5cb6e1b4e9dc19d70a7676caac83630806ac2dad2360b1eafb51be824b4916
|
3 |
+
size 106611456
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:337360033e803e272157e513144defe1c35dd82f7602140f0d703833e2c0ea72
|
3 |
+
size 106611456
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28851f1c00f5c987ccd8cc3ac5da31135fe273163102761d036aa72edfba1477
|
3 |
+
size 106611960
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a6f35b617d5a5b6e048805dbba372007c37b3d85fc13ae50349e391a0e14f09
|
3 |
+
size 106612224
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:803429b1f079b8424678bc152187126d7af24b75b58036e5db25ccfea4ec20b2
|
3 |
+
size 106611776
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3353fa83aae8ae829f69f54aa16e029451208d8b02dd451522e59c16089600f0
|
3 |
+
size 106611584
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02e058f80e2928ad2cdbfa4cf7cbdaae96f033f5dc7765b425160785788cd004
|
3 |
+
size 106612224
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1808b9a8e0b12ee19bd3694a82c1b9694b4ec9c861dd70634d66ba72e063d0e
|
3 |
+
size 106611776
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8121fcd2af01ba1c89b300b7c57d897e0d52567ab361f50a1756c79eba624812
|
3 |
+
size 106611456
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa6e224e9b51246c95819f20f60b91458a191e550a23be841135f33b97d087db
|
3 |
+
size 106611712
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d4553f8f173efee0e45138861209a75b2b181e735cd64ea8ec711bc7e7d573b
|
3 |
+
size 106612288
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83da3f2fe1aee28ccc9a68f6038844a70d9eebb41664eaea3645df0079796084
|
3 |
+
size 106611584
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:042857d7951dbbc2941fb9f183fb8e936586cceece72fc25b50a4d511382984b
|
3 |
+
size 106611456
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:36267623c1420b8f15ac8ca09dd4966fc34454c1ff1f5dcad7c06b3c95a1adb2
|
3 |
+
size 106611960
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:30e9deb920ae9e9cbca4551f1eaf7669bafea2ce98882cb4d16a3c42971dcb80
|
3 |
+
size 106612224
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f5d4368febb63f41127e700f277cd556d1d417057acbdf7327083cf9aa5af90
|
3 |
+
size 106611776
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:217ce02818bc3bbb64553c9ad469047676f2f03ac699fb7347c2a75bd16fd8e4
|
3 |
+
size 106611456
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27b32b7488b7a68c5d6a36c9b415639ce17936a68315ef2e50c704981cf3c453
|
3 |
+
size 106612032
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb2df97b80a7215a92f72dc7e2ad02af4f59184b3641e8d14fd094974a9db7f8
|
3 |
+
size 106611968
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:496e06b51c8c905fbbec8ea695620ab7ec36a98fa8e5f2011f6bdebc9eecb70e
|
3 |
+
size 106611584
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f525aa25b166144efd0f01ceea32c946c5ae476bdffe88e67e3430cce9e5958
|
3 |
+
size 106611456
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f00c94acd3a080d3d8be34f5f55474f8d18fe8c41a222bd4bc8e8227f448d7f
|
3 |
+
size 106612288
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f32f335014640bf86bb3cdec07d7bedb808647e7b262127298d002e04b00213
|
3 |
+
size 106611576
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e93c0821d3586c2e936294c91feb74badfe8f08acbab71e2b960765747a5f03
|
3 |
+
size 106611448
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:826c765acc2325509d95474e41d34c5c99e5f2caf2a10e2d92acb568f62c3e78
|
3 |
+
size 106612216
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b76371bd90a8d37fd6bfc2d63a2be5baaabfcdb01779c9f6e608baf78dbb3c1
|
3 |
+
size 106611768
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9456f4504c9c98f52b06ddcb76d36edcb93236c6cf2cc0c27195d304bec71362
|
3 |
+
size 106611576
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c80841424cf28a932dc32786149257877f86b4c2e4d363e3d7a06543bd9e3c83
|
3 |
+
size 106612216
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8da422be93993f27588bbcdb4d7122213eae16af37a8fcda9ffdf1c7a0a87b56
|
3 |
+
size 106611768
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f1ac7c2f1a0c36437a4783b7747e9ccdfd17103255e6a0eca0c097da378a21f
|
3 |
+
size 106611448
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e102b70cb117a42fe044c9bf92b83222be9ee70ccdd5e22418f4f320a7988d5e
|
3 |
+
size 106611440
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0081898f42f5da24484ab18b2c7285d639c147b13f1e274b89e14cdb417142ac
|
3 |
+
size 106611448
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:42da05ed9fab32d27dd78120fac3e31a3ffdabea86a8fbf3608de962f5d02169
|
3 |
+
size 106612216
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b54426359fe8b772eedd8569e20acd8281966c278b0ca7aa25ac1d8951dbde28
|
3 |
+
size 106611768
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb51127b0f1851e61644cd105dc724c68f5c367393065ee1b7545f91452b1670
|
3 |
+
size 106611576
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a14405d113ea3a34097f53ff3204583e1971caa774d06e5c00754faca5524cbe
|
3 |
+
size 106612216
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da4b6a06f27fa9bc3a135d85069971c8311dafbd758913b13aab8d7cb0e6ca70
|
3 |
+
size 106611768
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08314edb4b9238d1d4974623a1ba06cc5fb77a1486ef2b0e296f7eb28aa1dc38
|
3 |
+
size 106611448
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d0c352e0116b00e9e64c1d3a20b997ba08c9df4d21dfb5660b9864371e03b6e
|
3 |
+
size 106611704
|
1B_10K_bs1024_ff15_ln_warmup_ds_v2/checkpoint-370000/pytorch_model/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2059f857c2bc7f180a35c95339bcb5513433a20dd6fa175395da95cbea1fdeb3
|
3 |
+
size 106612216
|