Hugging Face's logo

moderntalker
/
efficient_pretrain_checkpoints

Model card Files
xet
 Community
moderntalker commited on
Commit
fce2793
·
verified ·
1 Parent(s): d936480

Upload intermediate checkpoint for Loss_Scaling_fineweb_adamw_lr1e-3_wd0.1_bf16_grad_clip1e0_4C at iteration 70650

Browse files
Files changed (9) hide show
  1. intermediate-checkpoints/4C_8gpus/Loss_Scaling_fineweb_adamw_lr1e-3_wd0.1_bf16_grad_clip1e0_4C/inter-ckpt-70650/main.pt +3 -0
  2. intermediate-checkpoints/4C_8gpus/Loss_Scaling_fineweb_adamw_lr1e-3_wd0.1_bf16_grad_clip1e0_4C/inter-ckpt-70650/worker_0.pt +3 -0
  3. intermediate-checkpoints/4C_8gpus/Loss_Scaling_fineweb_adamw_lr1e-3_wd0.1_bf16_grad_clip1e0_4C/inter-ckpt-70650/worker_1.pt +3 -0
  4. intermediate-checkpoints/4C_8gpus/Loss_Scaling_fineweb_adamw_lr1e-3_wd0.1_bf16_grad_clip1e0_4C/inter-ckpt-70650/worker_2.pt +3 -0
  5. intermediate-checkpoints/4C_8gpus/Loss_Scaling_fineweb_adamw_lr1e-3_wd0.1_bf16_grad_clip1e0_4C/inter-ckpt-70650/worker_3.pt +3 -0
  6. intermediate-checkpoints/4C_8gpus/Loss_Scaling_fineweb_adamw_lr1e-3_wd0.1_bf16_grad_clip1e0_4C/inter-ckpt-70650/worker_4.pt +3 -0
  7. intermediate-checkpoints/4C_8gpus/Loss_Scaling_fineweb_adamw_lr1e-3_wd0.1_bf16_grad_clip1e0_4C/inter-ckpt-70650/worker_5.pt +3 -0
  8. intermediate-checkpoints/4C_8gpus/Loss_Scaling_fineweb_adamw_lr1e-3_wd0.1_bf16_grad_clip1e0_4C/inter-ckpt-70650/worker_6.pt +3 -0
  9. intermediate-checkpoints/4C_8gpus/Loss_Scaling_fineweb_adamw_lr1e-3_wd0.1_bf16_grad_clip1e0_4C/inter-ckpt-70650/worker_7.pt +3 -0
intermediate-checkpoints/4C_8gpus/Loss_Scaling_fineweb_adamw_lr1e-3_wd0.1_bf16_grad_clip1e0_4C/inter-ckpt-70650/main.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:071daf9915cbd58bff351b0f8bd7cf6a51411deeeccd4cca6c1c032e9233586a
3
+ size 3086382138
intermediate-checkpoints/4C_8gpus/Loss_Scaling_fineweb_adamw_lr1e-3_wd0.1_bf16_grad_clip1e0_4C/inter-ckpt-70650/worker_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1f04587a0762527c520725b6e6388cbbbb46d9550ec8882f028b3d62b599302
3
+ size 120990
intermediate-checkpoints/4C_8gpus/Loss_Scaling_fineweb_adamw_lr1e-3_wd0.1_bf16_grad_clip1e0_4C/inter-ckpt-70650/worker_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c69cb186dbe420b686139289381fd724161cccf8980e5609e2a4f6c8e6db40c6
3
+ size 150558
intermediate-checkpoints/4C_8gpus/Loss_Scaling_fineweb_adamw_lr1e-3_wd0.1_bf16_grad_clip1e0_4C/inter-ckpt-70650/worker_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:672626c9de91f2b9dd6ff16bcb38bf4c4cac5fbfe2dc93f4a17abcddfe5b0c0c
3
+ size 56798
intermediate-checkpoints/4C_8gpus/Loss_Scaling_fineweb_adamw_lr1e-3_wd0.1_bf16_grad_clip1e0_4C/inter-ckpt-70650/worker_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5cff4358149b3920411f394580916a277efada9ea0def1d39a190ea3d8b5865
3
+ size 277022
intermediate-checkpoints/4C_8gpus/Loss_Scaling_fineweb_adamw_lr1e-3_wd0.1_bf16_grad_clip1e0_4C/inter-ckpt-70650/worker_4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f57498cea2fe74be423fb7a08850fed39293874b9b4accee3b35b8388f217d43
3
+ size 51422
intermediate-checkpoints/4C_8gpus/Loss_Scaling_fineweb_adamw_lr1e-3_wd0.1_bf16_grad_clip1e0_4C/inter-ckpt-70650/worker_5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddffb4302fe84f358db4a28f3c1137c2678ae016fa605199fcc2aa7fa73ae6be
3
+ size 95390
intermediate-checkpoints/4C_8gpus/Loss_Scaling_fineweb_adamw_lr1e-3_wd0.1_bf16_grad_clip1e0_4C/inter-ckpt-70650/worker_6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3558ddd0e181d7d9fdb74d764dd9c10208ff70654533f313a0db3c5db4041997
3
+ size 31646
intermediate-checkpoints/4C_8gpus/Loss_Scaling_fineweb_adamw_lr1e-3_wd0.1_bf16_grad_clip1e0_4C/inter-ckpt-70650/worker_7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d5e63a732a83956c0c78f3003f8019e84d99efd8ee1fe883f16bcffc9efa312
3
+ size 186654