Training in progress, step 558, checkpoint

last-checkpoint/global_step558/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48f47872b153568880f63e929f3bdd430ab3ca165a871dd7f35283aa5d93a46a
+size 14483467880

last-checkpoint/global_step558/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31af3feb2ec011fbc257818fdd66bf54c64e3e6ec1df17f7899a6b1810530e7f
+size 14483467880

last-checkpoint/global_step558/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69abf6db88945f5bb6be0b9788b523a8a5a12986dbdd173ee2aa9ffbf50dd455
+size 14483467880

last-checkpoint/global_step558/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5083abeebe436b485703d56249238c09c2540c14bc747f5a94d83da7bb496bb7
+size 14483467880

last-checkpoint/global_step558/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d3c39cc7165a6ee3bd278e657b74091c7d7445454546c0632393fe1b8f5dbe7
+size 150629

last-checkpoint/global_step558/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:246a94e167835a45d3933514047a1ec029f5a0b7f89c6dee634f7d034f972677
+size 150629

last-checkpoint/global_step558/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7470e6434a5c8e46bb43a523a725387c3308156d296ee1210e546cad75ca81e
+size 150629

last-checkpoint/global_step558/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12d186b915651468c281bfc724da55a5e8e424664df1f100081a2cdc05745ae4
+size 150629

last-checkpoint/latest

@@ -1 +1 @@
-global_step496
+global_step558

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9a7a17d4560692c6bbac7a5803c9ef7966094cd085d51b14cecd1df2d86e64a
+oid sha256:1c6a528fcebfa81ad94dc98b813bc2eaf50e2093983c66f1cf062eee248c9ce3
 size 4943162336

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d20ac5c3151e609b424576af7297e14857b8b7da6100a1a7704e41612dd7bc42
+oid sha256:87205acf168a99a505e46e06b76a61a6a87e6e70876881ff030e4dad2cd7aa43
 size 4999819336

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fbc99432985410ff6c43ff6c0882c1950b2b1368324dc2ad9f035c1fb4e9ac4
+oid sha256:5c09c12a0ba4fd95fb32e1df06312c869712e92aa026283345f20f3f5ad8b86a
 size 4540516344

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6115ef4a3972dc95f8b5f42d8b349e0290ad816095675fd656394e06736eed54
+oid sha256:fb3d4793d6c7fda650513b6f3d24fe7afd643475a576b0104a85cb659ed441d3
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8698a8fe21a6c40aa81c13fa783f7b480800d0e1c8b8bbfc0f7d795856c9a9d
+oid sha256:e44567105884943a8351ea71e9a71011cceee34a8f2a067be69948ea21390f49
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22995e1828e61a6ae15a2c3ebe4ca0a2b8b2daa337082a4762176b1ca46f3953
+oid sha256:8c3a6f11c1c82a313f717b58d29d20267d0bfc621c79116ac6f752e0c1ba1f50
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49f599372909f19fb45797a334f06b5100cf004b284caa24cedf789d1047c5c7
+oid sha256:aaa97839e10563397740560600a86ccaf5a6fe1e5f41084453cab0f732a05570
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:239793f1a741f8e5a4de788cdc2c78f5187e67d38900b549f3e1a188c27ddb9c
+oid sha256:41569355a67e5d54cd2e41fbdb883692602ceaf27587e7a1c779dc0f9f2d51fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.5872000000000002,
+  "epoch": 1.7856,
   "eval_steps": 62,
-  "global_step": 496,
+  "global_step": 558,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -885,6 +885,112 @@
       "eval_samples_per_second": 5.286,
       "eval_steps_per_second": 0.344,
       "step": 496
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 33.14482905038865,
+      "learning_rate": 2.589073634204275e-07,
+      "logits/generated": -2.348078727722168,
+      "logits/real": -2.3059887886047363,
+      "logps/generated": -123.2630615234375,
+      "logps/real": -101.59033966064453,
+      "loss": 0.3313,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/generated": -0.09043073654174805,
+      "rewards/margins": 3.036623477935791,
+      "rewards/real": 2.946192502975464,
+      "step": 500
+    },
+    {
+      "epoch": 1.6320000000000001,
+      "grad_norm": 58.37181281947162,
+      "learning_rate": 2.529691211401425e-07,
+      "logits/generated": -2.3784213066101074,
+      "logits/real": -2.445460557937622,
+      "logps/generated": -137.46278381347656,
+      "logps/real": -98.52521514892578,
+      "loss": 0.3326,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/generated": -0.19049878418445587,
+      "rewards/margins": 3.1443653106689453,
+      "rewards/real": 2.953866958618164,
+      "step": 510
+    },
+    {
+      "epoch": 1.6640000000000001,
+      "grad_norm": 51.7755109683276,
+      "learning_rate": 2.4703087885985747e-07,
+      "logits/generated": -2.6047139167785645,
+      "logits/real": -2.575225353240967,
+      "logps/generated": -125.86954498291016,
+      "logps/real": -115.58686828613281,
+      "loss": 0.3731,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/generated": 0.010144609026610851,
+      "rewards/margins": 2.9819352626800537,
+      "rewards/real": 2.9920802116394043,
+      "step": 520
+    },
+    {
+      "epoch": 1.696,
+      "grad_norm": 61.11300533777711,
+      "learning_rate": 2.410926365795724e-07,
+      "logits/generated": -2.598510503768921,
+      "logits/real": -2.6134636402130127,
+      "logps/generated": -130.40304565429688,
+      "logps/real": -119.8432846069336,
+      "loss": 0.4011,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/generated": 0.22392193973064423,
+      "rewards/margins": 3.1454458236694336,
+      "rewards/real": 3.3693675994873047,
+      "step": 530
+    },
+    {
+      "epoch": 1.728,
+      "grad_norm": 52.94216878715562,
+      "learning_rate": 2.351543942992874e-07,
+      "logits/generated": -2.54017972946167,
+      "logits/real": -2.611607074737549,
+      "logps/generated": -123.71136474609375,
+      "logps/real": -117.9095687866211,
+      "loss": 0.3699,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/generated": 0.34511905908584595,
+      "rewards/margins": 2.8268630504608154,
+      "rewards/real": 3.1719822883605957,
+      "step": 540
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 34.291195649117704,
+      "learning_rate": 2.2921615201900234e-07,
+      "logits/generated": -2.530885696411133,
+      "logits/real": -2.5769619941711426,
+      "logps/generated": -129.57070922851562,
+      "logps/real": -107.8799057006836,
+      "loss": 0.3611,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/generated": 0.188289612531662,
+      "rewards/margins": 3.124110460281372,
+      "rewards/real": 3.3124001026153564,
+      "step": 550
+    },
+    {
+      "epoch": 1.7856,
+      "eval_logits/generated": -2.432302951812744,
+      "eval_logits/real": -2.436417818069458,
+      "eval_logps/generated": -104.27023315429688,
+      "eval_logps/real": -115.58291625976562,
+      "eval_loss": 0.7119041681289673,
+      "eval_rewards/accuracies": 0.6730769276618958,
+      "eval_rewards/generated": 1.704530119895935,
+      "eval_rewards/margins": 0.6285931468009949,
+      "eval_rewards/real": 2.333123207092285,
+      "eval_runtime": 37.2029,
+      "eval_samples_per_second": 5.376,
+      "eval_steps_per_second": 0.349,
+      "step": 558
     }
   ],
   "logging_steps": 10,