diff --git a/.gitattributes b/.gitattributes
index e2bd9596745619e190d7ca77212b3a38309c521e..4c1e8b826a8aa84cac709adba7d3642f2f2cd832 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -93,3 +93,7 @@ lr_2e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/credit/huggingface/toke
 lr_2e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 lr_2e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 lr_2e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
diff --git a/lr_2e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/optim_world_size_4_rank_0.pt b/lr_2e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/optim_world_size_4_rank_0.pt
new file mode 100644
index 0000000000000000000000000000000000000000..03c9c86ec6f5b9dcef597722d10fc0428e141b60
--- /dev/null
+++ b/lr_2e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/optim_world_size_4_rank_0.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8793de53310391414e6a7493e1442bcaa1f7da6e11ddb109b1c6fe619f4afaa8
+size 3441176616
diff --git a/lr_2e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/optim_world_size_4_rank_2.pt b/lr_2e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/optim_world_size_4_rank_2.pt
new file mode 100644
index 0000000000000000000000000000000000000000..71ad4d1c4630bc4d792dfdf840fa5097b7b8ffed
--- /dev/null
+++ b/lr_2e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/optim_world_size_4_rank_2.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:586b2bde2e8be23c8cf40d348e27f6181d9bb640db34f41df98c3f7c066f0666
+size 3441176616
diff --git a/lr_2e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/optim_world_size_4_rank_3.pt b/lr_2e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/optim_world_size_4_rank_3.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e156d8465fd0052af5f049171eff77513af7c8d2
--- /dev/null
+++ b/lr_2e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/optim_world_size_4_rank_3.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cefc9450f03972882712def24c76a67c24f66da2e4ae0a3752811fa410c0bc17
+size 3441176616
diff --git a/lr_2e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/model_world_size_4_rank_3.pt b/lr_2e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/model_world_size_4_rank_3.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f76a73a2da4eec7a3d91f230c8d3c3c0ed33dae6
--- /dev/null
+++ b/lr_2e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/model_world_size_4_rank_3.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4e3a9746389c8899baeeb41dd022c2194153a159cea21cd3448f61a0c637774
+size 2031935851
diff --git a/lr_2e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/optim_world_size_4_rank_1.pt b/lr_2e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/optim_world_size_4_rank_1.pt
new file mode 100644
index 0000000000000000000000000000000000000000..04c3a2f623320e9fb320b93fe83e03708ce1d282
--- /dev/null
+++ b/lr_2e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/optim_world_size_4_rank_1.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62d499eef387714ab5e287dad5810094187ae97f6f436f447b4d1de2bcf13db0
+size 3441180712
diff --git a/lr_2e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/optim_world_size_4_rank_2.pt b/lr_2e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/optim_world_size_4_rank_2.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5959901c936d74bf26d13943481365f52d514f8b
--- /dev/null
+++ b/lr_2e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/optim_world_size_4_rank_2.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a1486e9f0bf61a49c16dc232d01500a19723b570001cd6c0a8e2fbb26d732aa
+size 3441176616
diff --git a/lr_2e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/credit/optim_world_size_4_rank_1.pt b/lr_2e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/credit/optim_world_size_4_rank_1.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e9e293ff25ad4ecf76616a1e97638daeac21e4c4
--- /dev/null
+++ b/lr_2e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/credit/optim_world_size_4_rank_1.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e193d012c2f1208485b4143a1f295ddb8b1ded81198dc45abd05b7308d6908a
+size 3441180712
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/extra_state_world_size_4_rank_0.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/extra_state_world_size_4_rank_0.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d99cfccd78289983f84cd75931cb3ca7278a87ac
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/extra_state_world_size_4_rank_0.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2e9134a48319be59d7236eea7f6a86bf6908921c326ebd1a07c1f863534ef6a
+size 15077
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/extra_state_world_size_4_rank_1.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/extra_state_world_size_4_rank_1.pt
new file mode 100644
index 0000000000000000000000000000000000000000..39503134c5472955ca15bb891ba55f95e90a8ebc
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/extra_state_world_size_4_rank_1.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:986a2b8960a3d725cc387d73e3c6f96d360343fcfef0c639e4598019afb146bf
+size 15141
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/extra_state_world_size_4_rank_2.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/extra_state_world_size_4_rank_2.pt
new file mode 100644
index 0000000000000000000000000000000000000000..68972811e6d85fe87d2a2b0802e4cb650f7947ae
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/extra_state_world_size_4_rank_2.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2e7a4b3377edc7676ce6d748d4c97b9408038d303c3b5bc24ee871a31be8fc0
+size 15205
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/extra_state_world_size_4_rank_3.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/extra_state_world_size_4_rank_3.pt
new file mode 100644
index 0000000000000000000000000000000000000000..33ce8cfd7c2db71396cacf21ce56fa71be56046b
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/extra_state_world_size_4_rank_3.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f165126b0ea5c8ec5bd57d6ba4bf7a865a8125229e408846f0413ef73d9d2b1b
+size 15141
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/huggingface/tokenizer.json b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/huggingface/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..cd71f61a15a522601badb3dc960d800d9cb3766c
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/huggingface/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/model_world_size_4_rank_0.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/model_world_size_4_rank_0.pt
new file mode 100644
index 0000000000000000000000000000000000000000..eb7daa14f5ab26be02005eb5b7834c543b376fb5
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/model_world_size_4_rank_0.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19f9d165c0054783e70cd443a4e1776879c7cc9eb51916941d6026e11e3f9744
+size 2031920747
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/model_world_size_4_rank_1.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/model_world_size_4_rank_1.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f1611f36b67a2f9109c0143bb9b321b433e5660a
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/model_world_size_4_rank_1.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1490824f5b510f064485cea02f270c405086d16e251f1cb984df8ec7923829fd
+size 2031920747
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/model_world_size_4_rank_2.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/model_world_size_4_rank_2.pt
new file mode 100644
index 0000000000000000000000000000000000000000..84ed5665a43cf9df57ed40339a7993d542e93548
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/model_world_size_4_rank_2.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c66ab610ee2b6ef6aa5a940fa0cc2ffceb0ccd366fad6124f0da3b4b6bb11ec7
+size 2031920747
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/model_world_size_4_rank_3.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/model_world_size_4_rank_3.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8b39e391cdd2bb2790ae15efb97bd7b6c7cf68b2
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/model_world_size_4_rank_3.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09279186aa2ba71e466eaa32a3f17193b70277cede3c3a43899e2740d5918e5f
+size 2031920747
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/optim_world_size_4_rank_0.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/optim_world_size_4_rank_0.pt
new file mode 100644
index 0000000000000000000000000000000000000000..99b0ab0284e13b07bf43047a0d148ae4f859f58a
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/optim_world_size_4_rank_0.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2da0b7cb3b5f7967586b4028291ef15ca5e42dd2ffd4ebc55642670d8255a5cf
+size 3441176616
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/optim_world_size_4_rank_1.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/optim_world_size_4_rank_1.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d753df6a2ffa13e1ecb6afa0a646e90eb78b7940
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/optim_world_size_4_rank_1.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cae19342afde258e471dadfabb7ed0c7807148779a29b06b2b995660970c39cf
+size 3441176616
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/optim_world_size_4_rank_2.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/optim_world_size_4_rank_2.pt
new file mode 100644
index 0000000000000000000000000000000000000000..effd329d87bdffe8d748f20309c257a6a84eb22a
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/optim_world_size_4_rank_2.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81e3d0fc9b5acab46d5f8c84c6c3167078a5f93aec196e53b121ca8f48775474
+size 3441176616
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/optim_world_size_4_rank_3.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/optim_world_size_4_rank_3.pt
new file mode 100644
index 0000000000000000000000000000000000000000..71c629d8284c12249c2ad3e9100f94adc3afa408
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/optim_world_size_4_rank_3.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da640efb30c878e4be0e00cc98e95cc60e9a5d52b47c03239ab02cebb5a14781
+size 3441176616
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/extra_state_world_size_4_rank_0.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/extra_state_world_size_4_rank_0.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e2853ff0dee2a52d697b4f23795abf7181f8774f
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/extra_state_world_size_4_rank_0.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ff354ade55a6c6626a0dcfabb9ef91b37e606893144a87a9662ad6994409a79
+size 15077
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/extra_state_world_size_4_rank_1.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/extra_state_world_size_4_rank_1.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a9af1e4a18a60058cabc6efdce75a7a36f1e6dfe
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/extra_state_world_size_4_rank_1.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6ddea6882fce89dd215aa07f5578d53a1498eaa4523d508aefac9c558e6c1ac
+size 15141
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/extra_state_world_size_4_rank_2.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/extra_state_world_size_4_rank_2.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2f355d668838e4c8e417757603c90c2400acfeb7
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/extra_state_world_size_4_rank_2.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2620930b6d9e674053da9c3c92f9a6ff46a70555410ac457ff0f6d23fcd758e
+size 15205
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/extra_state_world_size_4_rank_3.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/extra_state_world_size_4_rank_3.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b3513c4b4dd507f8e5bbfc551b8950b11bc2c92d
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/extra_state_world_size_4_rank_3.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dbd601438ccf78686c496390351e49afaa0a2824f106adaed637a011c49c073
+size 15141
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/huggingface/tokenizer.json b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/huggingface/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..cd71f61a15a522601badb3dc960d800d9cb3766c
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/huggingface/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/model_world_size_4_rank_0.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/model_world_size_4_rank_0.pt
new file mode 100644
index 0000000000000000000000000000000000000000..94b733df8761d9322a56817842a2365918df58d1
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/model_world_size_4_rank_0.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a4196628c2a11fc84f55fce050b08bbe4c7177a5b1542763e068503652aab68
+size 2031944043
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/model_world_size_4_rank_1.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/model_world_size_4_rank_1.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4187fc34866a61213a599de441bce6a52b616c56
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/model_world_size_4_rank_1.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bc7a1d646ae46a9f89f494f580d34063e39d648a5e4e8fcb539a16f637fc896
+size 2031935851
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/model_world_size_4_rank_2.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/model_world_size_4_rank_2.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2f4a676ff7227b80f9763efe2f62119acfe18ad7
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/model_world_size_4_rank_2.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bf5b10559e8460df21efa7f9d8db89ec418c7c83b12337736964dba3b917a70
+size 2031935851
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/model_world_size_4_rank_3.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/model_world_size_4_rank_3.pt
new file mode 100644
index 0000000000000000000000000000000000000000..cc0344de2cb6cdccaa4000d1b0544540d3cfb41d
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/model_world_size_4_rank_3.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6930382dfc6cb3886ff664762ef83a41563ae3358fd00c4c7ec2e713a95e1ec2
+size 2031935851
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/optim_world_size_4_rank_0.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/optim_world_size_4_rank_0.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9ce557812ab54ac196a709cc527625fbebdd0ff6
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/optim_world_size_4_rank_0.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edfb5d99f33fb9c8b31bcefb596b4248295693a963183549b74c20d6f836555d
+size 3441180712
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/optim_world_size_4_rank_1.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/optim_world_size_4_rank_1.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9a33015932e9f9ced1b2d0efe140a6b035fe6c94
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/optim_world_size_4_rank_1.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66635cff6fba1d5db56a5108cf8cd37de050e00471da641077af2826798b6518
+size 3441180712
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/optim_world_size_4_rank_2.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/optim_world_size_4_rank_2.pt
new file mode 100644
index 0000000000000000000000000000000000000000..242845e3a6b78c74cb05a4b1df2ad6d372dc00f2
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/optim_world_size_4_rank_2.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2415d97e6aa3cd1894832cbc62ff5cbec355fad094beba565e34a9e6858d0c7
+size 3441180712
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/optim_world_size_4_rank_3.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/optim_world_size_4_rank_3.pt
new file mode 100644
index 0000000000000000000000000000000000000000..fe197c5f6753315e4f6dbd180fa41b016a14e4a5
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/optim_world_size_4_rank_3.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7cc9346f2395667fa720959ba00e928b17399192174e83758c1d8129ea3c752
+size 3441180712
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/data.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/data.pt
new file mode 100644
index 0000000000000000000000000000000000000000..61ff287b83651ca81354c13111b1a17ffeb7bd9a
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/data.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2239bd807144dba11bc72f34725ed893449c62089792bdc2b0b043e0ef219dd4
+size 21489
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/extra_state_world_size_4_rank_0.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/extra_state_world_size_4_rank_0.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b36059de0ba3bcb149662b8dbe202ecd895dbd51
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/extra_state_world_size_4_rank_0.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:720898f167e8d1396c35d0639374147dc654470d5aaea028b67141302e27c5d3
+size 15077
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/extra_state_world_size_4_rank_1.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/extra_state_world_size_4_rank_1.pt
new file mode 100644
index 0000000000000000000000000000000000000000..aef6f375e00022e7ce4c4fb53a13275b52aed229
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/extra_state_world_size_4_rank_1.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73d3155d689687b27c849e95852e9ac36a5428c911e2569ededb6f413715aa0f
+size 15141
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/extra_state_world_size_4_rank_2.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/extra_state_world_size_4_rank_2.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d6664533bbdbd6e4fae55a99ce601d23e40d8eb8
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/extra_state_world_size_4_rank_2.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38875fcb3d69ab0b634c073be9b17b0fdbcc6cafbd6a2d00e18657cecbcd1cdd
+size 15205
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/extra_state_world_size_4_rank_3.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/extra_state_world_size_4_rank_3.pt
new file mode 100644
index 0000000000000000000000000000000000000000..89b24f3d74ef187d6ef804e666f35b0d7e0e99d5
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/extra_state_world_size_4_rank_3.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f6ba2f29c40db93e70bce1aafeb245dadecb81b40720585abb5d02fd5a80eab
+size 15141
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/huggingface/tokenizer.json b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/huggingface/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..cd71f61a15a522601badb3dc960d800d9cb3766c
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/huggingface/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/model_world_size_4_rank_0.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/model_world_size_4_rank_0.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5b548e7a475cdf1fd268a17174b20c1207d789dd
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/model_world_size_4_rank_0.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b78710948038441b486f1fd1e3c2204d538c6dd905c4f2d3b48c6030fcf9d811
+size 2031920747
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/model_world_size_4_rank_1.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/model_world_size_4_rank_1.pt
new file mode 100644
index 0000000000000000000000000000000000000000..75bd70b5587f072db330af1803c0ed634358ebfb
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/model_world_size_4_rank_1.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b37619c38d8fc0ba477c4af111368e13b194a922cc65dfb8ae0fcdd35595676f
+size 2031920747
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/model_world_size_4_rank_2.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/model_world_size_4_rank_2.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2ccc3d423bf105b960e8f0b5b2aa4c7d728c0851
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/model_world_size_4_rank_2.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f752bfdf304834b9e3b0db08bc2dae41b84dee981124ddb6c4ccaae4671a2ffb
+size 2031920747
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/model_world_size_4_rank_3.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/model_world_size_4_rank_3.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5a247d042d2198a73a7e8ce27ae984a556ded770
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/model_world_size_4_rank_3.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ecef586e9ce633b5d4658e62710774a4f60816343330c5f316a41fcf5b9836b
+size 2031920747
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/optim_world_size_4_rank_0.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/optim_world_size_4_rank_0.pt
new file mode 100644
index 0000000000000000000000000000000000000000..65a4006bb66f6f46c8779a5c905c2b8cc8da92b7
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/optim_world_size_4_rank_0.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4878c6c039355200fc44d29a7d7920f8ebcd7fb8b8d287d7e54fd7a26ebadee
+size 3441176616
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/optim_world_size_4_rank_2.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/optim_world_size_4_rank_2.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8272c95968432af75420138bfc614f57c5bb1692
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/optim_world_size_4_rank_2.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ed8a60b1bb1e809176dca3232adb8d99efcb6a0416122b3f37083021f8b10b9
+size 3441176616
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/optim_world_size_4_rank_3.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/optim_world_size_4_rank_3.pt
new file mode 100644
index 0000000000000000000000000000000000000000..fb6c17f4b1633c9da116974fb04e4baa6cc554a4
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/optim_world_size_4_rank_3.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59b162f6aab3c37e872b7c26e3816dc796a02319eaa13c121dc615a157618154
+size 3441176616
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/credit/extra_state_world_size_4_rank_0.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/credit/extra_state_world_size_4_rank_0.pt
new file mode 100644
index 0000000000000000000000000000000000000000..62aaacdac6ad36b56fd2976427c7d1653692d8f3
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/credit/extra_state_world_size_4_rank_0.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f429e88ba8d14a1270a444637502f5482c1dd62c17d9b624d311860c62aa4157
+size 15077
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/credit/extra_state_world_size_4_rank_1.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/credit/extra_state_world_size_4_rank_1.pt
new file mode 100644
index 0000000000000000000000000000000000000000..59ef4a7aa23d66e3a8b9d0946d3f75833b003287
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/credit/extra_state_world_size_4_rank_1.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba83f05564e91e68ed2bc7fc5084b7e44a3ce5ca5a51d9e3ed8410a25f5fe07c
+size 15141
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/credit/extra_state_world_size_4_rank_2.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/credit/extra_state_world_size_4_rank_2.pt
new file mode 100644
index 0000000000000000000000000000000000000000..888766d92f28584f081d3be42711a22ed6674728
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/credit/extra_state_world_size_4_rank_2.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e78f22b27757358ced2eba5cf6734a532488b728f2c0a3bc68b41ab3c8a2ddff
+size 15205
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/credit/extra_state_world_size_4_rank_3.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/credit/extra_state_world_size_4_rank_3.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d3ba533dd96f1d4bd33e1fa09f78f1844bd327b5
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/credit/extra_state_world_size_4_rank_3.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:739f64dffd17800df689835ba4e7ed6d9c7d1c66aa9776d5d9e0e7751a6dafbf
+size 15141
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/credit/huggingface/tokenizer.json b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/credit/huggingface/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..cd71f61a15a522601badb3dc960d800d9cb3766c
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/credit/huggingface/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/credit/model_world_size_4_rank_0.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/credit/model_world_size_4_rank_0.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e38f69d02e0a69dbda401b0dde4e98f30b7e18dd
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/credit/model_world_size_4_rank_0.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7864053fac8bfe7a7f9a2ee052f83d54907f3e9385cd47653c646afe8912e9b4
+size 2031944043
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/credit/model_world_size_4_rank_1.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/credit/model_world_size_4_rank_1.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5aa599f14fefd1ea0c889db08af73c856ffa72b3
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/credit/model_world_size_4_rank_1.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d29ae9c72cdfadee26a3a94ac14df78a48f7797acff92694c134b8679d9a8e7
+size 2031935851
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/credit/model_world_size_4_rank_2.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/credit/model_world_size_4_rank_2.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1aded73435f9fdbb01498e77e5648cfc407c447c
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/credit/model_world_size_4_rank_2.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89f7b3a1676bf8f5735a7a89a8d079aa27e455f84576a18c7fee59bb6fcdaa93
+size 2031935851
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/credit/optim_world_size_4_rank_0.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/credit/optim_world_size_4_rank_0.pt
new file mode 100644
index 0000000000000000000000000000000000000000..13b2881caa978b0bc99da32b702cbfb92296bd1e
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/credit/optim_world_size_4_rank_0.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad26232332d44038d296e38860f686bfa6aba2d78d972bdd680cb9b2cd5b27e2
+size 3441180712
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/credit/optim_world_size_4_rank_3.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/credit/optim_world_size_4_rank_3.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1ae3e9cd14eb8884405eb78527af59288f85e43b
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/credit/optim_world_size_4_rank_3.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:755a217591eed0046743317bb383fba1dedc3810110c1afed4cf3b5f2a7c2c93
+size 3441180712
diff --git a/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/data.pt b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/data.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9e3d46fc9bf31664980e5d1e87786756249e504a
--- /dev/null
+++ b/lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/data.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea60695ab08f48d2aecc6cb4f6bd0f01a9f08195f7044e87717324a75b4e63ce
+size 21489