Training in progress, step 496, checkpoint

last-checkpoint/global_step496/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b4cdd6b81f94e65310be6e1e52106d46f10ee558c06bf6c0d6718424b78dcdf
+size 14483467880

last-checkpoint/global_step496/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c4bf14393e6ec22d3bd790bc9a39f0558c740b337d5ac0384c18a648a8b4861
+size 14483467880

last-checkpoint/global_step496/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:230415a467393c078f8a710e70bd7085157d82eac70296b38027f02b45a0a871
+size 14483467880

last-checkpoint/global_step496/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0135fcbe40d8d2f4416732065cc5ffa88e0c4082e840242dede0a294c1eca318
+size 14483467880

last-checkpoint/global_step496/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a030eba951bd1aa25c9bd76a5990de7b6d75a6368b31c0ba89883264969207b6
+size 150629

last-checkpoint/global_step496/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4b57c7fd218d93bd682196f95281ed3fd2b880cd8f0d694a77f56a3d6bfffc9
+size 150629

last-checkpoint/global_step496/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98f058fa5f757d8597733073ed6b09257eae70b11212ecb083d55284229c4c17
+size 150629

last-checkpoint/global_step496/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adb9ffc4c9f6b664766500e42a24fdd1c76dc6ac1947006a448eb0cbd34a8955
+size 150629

last-checkpoint/latest

@@ -1 +1 @@
-global_step434
+global_step496

last-checkpoint/model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:958716f2df1897ad484fdf7bd07ec6d719787775a371768ed3c7437e70de2232
+oid sha256:d9a7a17d4560692c6bbac7a5803c9ef7966094cd085d51b14cecd1df2d86e64a
 size 4943162336

last-checkpoint/model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39c4675562a0a001a6edf29b49c1472e3f7ec329ca9c5cde5f458022e6dd467c
+oid sha256:d20ac5c3151e609b424576af7297e14857b8b7da6100a1a7704e41612dd7bc42
 size 4999819336

last-checkpoint/model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6f60fa901b8ebbd827b9acb1118f03a3eade9e3e3fc451be3522245d27b7d06
+oid sha256:0fbc99432985410ff6c43ff6c0882c1950b2b1368324dc2ad9f035c1fb4e9ac4
 size 4540516344

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe3f96a2fff0ebd8dbcc2b4789c9dd47a218358381d8dc0c22453d73cc18c13a
+oid sha256:6115ef4a3972dc95f8b5f42d8b349e0290ad816095675fd656394e06736eed54
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03c2e37b3b994a43a2c3a96dca7647061b052e8930abe99d16ea118bb9a4e2bc
+oid sha256:e8698a8fe21a6c40aa81c13fa783f7b480800d0e1c8b8bbfc0f7d795856c9a9d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd2fb470636af306fe33bfa071a70c5e89bbc147a17ff3351e6d952861610b64
+oid sha256:22995e1828e61a6ae15a2c3ebe4ca0a2b8b2daa337082a4762176b1ca46f3953
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42f403a555728d319355f2901e7ccab38b27c2ffdef1825aa77e363c48d96a77
+oid sha256:49f599372909f19fb45797a334f06b5100cf004b284caa24cedf789d1047c5c7
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffb2c72a1d7475512f08b2573f4f5ec2d68a3f42a3844b97c4df08ba0cc7a09b
+oid sha256:239793f1a741f8e5a4de788cdc2c78f5187e67d38900b549f3e1a188c27ddb9c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.3888,
+  "epoch": 1.5872000000000002,
   "eval_steps": 62,
-  "global_step": 434,
+  "global_step": 496,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -779,6 +779,112 @@
       "eval_samples_per_second": 5.359,
       "eval_steps_per_second": 0.348,
       "step": 434
+    },
+    {
+      "epoch": 1.408,
+      "grad_norm": 59.86596162814969,
+      "learning_rate": 2.9453681710213776e-07,
+      "logits/generated": -2.5212674140930176,
+      "logits/real": -2.6616861820220947,
+      "logps/generated": -124.64134216308594,
+      "logps/real": -119.5413818359375,
+      "loss": 0.4341,
+      "rewards/accuracies": 0.9375,
+      "rewards/generated": 0.546046257019043,
+      "rewards/margins": 2.7997288703918457,
+      "rewards/real": 3.3457748889923096,
+      "step": 440
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 25.921657044180346,
+      "learning_rate": 2.885985748218527e-07,
+      "logits/generated": -2.4825379848480225,
+      "logits/real": -2.5802297592163086,
+      "logps/generated": -134.5606231689453,
+      "logps/real": -103.09733581542969,
+      "loss": 0.2921,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/generated": 0.3280000686645508,
+      "rewards/margins": 3.0266566276550293,
+      "rewards/real": 3.35465669631958,
+      "step": 450
+    },
+    {
+      "epoch": 1.472,
+      "grad_norm": 60.488510196254985,
+      "learning_rate": 2.8266033254156767e-07,
+      "logits/generated": -2.463170289993286,
+      "logits/real": -2.5204989910125732,
+      "logps/generated": -117.78157043457031,
+      "logps/real": -94.84367370605469,
+      "loss": 0.4117,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/generated": 0.7249609231948853,
+      "rewards/margins": 2.5204477310180664,
+      "rewards/real": 3.245408535003662,
+      "step": 460
+    },
+    {
+      "epoch": 1.504,
+      "grad_norm": 42.83019835762152,
+      "learning_rate": 2.7672209026128263e-07,
+      "logits/generated": -2.474457263946533,
+      "logits/real": -2.513317584991455,
+      "logps/generated": -133.95883178710938,
+      "logps/real": -112.54573059082031,
+      "loss": 0.3241,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/generated": -0.05931330472230911,
+      "rewards/margins": 2.9567954540252686,
+      "rewards/real": 2.897481918334961,
+      "step": 470
+    },
+    {
+      "epoch": 1.536,
+      "grad_norm": 55.17709070072599,
+      "learning_rate": 2.7078384798099764e-07,
+      "logits/generated": -2.442061185836792,
+      "logits/real": -2.411407947540283,
+      "logps/generated": -124.24302673339844,
+      "logps/real": -105.8341293334961,
+      "loss": 0.3585,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/generated": 0.2026868313550949,
+      "rewards/margins": 2.592716932296753,
+      "rewards/real": 2.7954039573669434,
+      "step": 480
+    },
+    {
+      "epoch": 1.568,
+      "grad_norm": 38.62958702650794,
+      "learning_rate": 2.648456057007126e-07,
+      "logits/generated": -2.338289737701416,
+      "logits/real": -2.3997902870178223,
+      "logps/generated": -128.10601806640625,
+      "logps/real": -111.6781234741211,
+      "loss": 0.4053,
+      "rewards/accuracies": 0.9375,
+      "rewards/generated": -0.04702238366007805,
+      "rewards/margins": 3.0088653564453125,
+      "rewards/real": 2.961843490600586,
+      "step": 490
+    },
+    {
+      "epoch": 1.5872000000000002,
+      "eval_logits/generated": -2.403900623321533,
+      "eval_logits/real": -2.4069132804870605,
+      "eval_logps/generated": -104.69697570800781,
+      "eval_logps/real": -115.92328643798828,
+      "eval_loss": 0.7082696557044983,
+      "eval_rewards/accuracies": 0.6730769276618958,
+      "eval_rewards/generated": 1.6618565320968628,
+      "eval_rewards/margins": 0.6372315287590027,
+      "eval_rewards/real": 2.2990880012512207,
+      "eval_runtime": 37.8337,
+      "eval_samples_per_second": 5.286,
+      "eval_steps_per_second": 0.344,
+      "step": 496
     }
   ],
   "logging_steps": 10,