Training in progress, epoch 2, checkpoint

last-checkpoint/global_step626/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e4f36d36d089ec284f49d01b6c25639235a5e974c071eabc1642883616b090e
+size 16060527788

last-checkpoint/global_step626/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c099f3e18db8bbb1ef6dc295ad1d9225d1e05f5ffacf4131232e5fac2423a43
+size 16060527788

last-checkpoint/global_step626/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e540c2eec324ae38d2996aa41f684d9bdd84f97a88b4611a51548e185e4bad4
+size 16060527788

last-checkpoint/global_step626/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b473c84f348b9ef34b5dbba937e9f244444d346c7fdf1b4a09422496902ec38
+size 16060527788

last-checkpoint/global_step626/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abec8762cd151640ecff6bec742b3029077d87c015cc1e6ff2c99913a18e34ac
+size 150693

last-checkpoint/global_step626/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e861607615a2f30cc4a91224dab49c029d4ca20f8e79a03bac84dd4582db1386
+size 150693

last-checkpoint/global_step626/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3862a1ed2cf9d6e26e9d0d0f03033c2ce320801e6d9f5171504fa1c7896644a
+size 150693

last-checkpoint/global_step626/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e6cb6c96bef29946c7aa624f6f1756330136f0b4c04eed1561baaf57b75ea19
+size 150693

last-checkpoint/latest

@@ -1 +1 @@
-global_step313
+global_step626

last-checkpoint/model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2bf5a05227d5057c59052bbfabda6a0bcbe8358bd9c069999fbf86cf56e6855
+oid sha256:4d54039dc041f3e015fb26a58181e18b15300073aa7f189906aa141eb163193c
 size 4976698672

last-checkpoint/model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecb0232c358cbb7b5460aa229c4357355c34b58d03518af52a7ab2b168970429
+oid sha256:be7408aaad853291659cca456977f64b9c12df36e72fcf70bfbd86190f59689d
 size 4999802720

last-checkpoint/model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70e6aa6b3c441c4b4fc22fde4fe1558fb10883a7e3bd625ae897c0fe014d1952
+oid sha256:94015a2bd29aadfc52d528f933601b3767e3e5d51650d43bc11706148be83fcb
 size 4915916176

last-checkpoint/model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfdca69cfe2cac25c0afed950dfbf927bef0c46bbef4860929a31750f94e73cd
+oid sha256:74954b42e041e5dce92411f4519e39cc59ac7fb94ec1eabe1f6cc6ac121815b9
 size 1168138808

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1ce770862b76ceecb3453a5d0b9ef65311eab0f6a60f52997726a89d718de08
+oid sha256:2307c03867cef25b5028feb9a23f80e784b9af9a615de13ddca560a6a90fb593
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bcae6573442578b752be3e988d4ccb38056b45c31b5c02eb579ec6cebcfa62e
+oid sha256:50218cfaecdd818354e567b7167c13899e3b42297e7d8f58bd7e732cfa547800
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:398ff45072fee2975e88b9e078f915103d75d94bc08753303cf855b915973623
+oid sha256:9814a66b49861f5495b06dae3be12ddf7185b88e2cae1fb808ca9efd99d5807f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f4b210bc832d4c648e3bee8c21dca26e5a8b365d6ec90c638062005a052e57b
+oid sha256:a7be93040a65e0a29975f6c70b94418e1fdf88423a50c58aa572141d3c92fbfc
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b9aad3a748e15719e20120f0a760f22686338e176ee3f1c011b6dab2f3ab19b
+oid sha256:f7725b44c69725321786f1e58dccd7ea4d3ae5794ea47bd49c0d4a139aec266d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0,
+  "epoch": 2.0,
   "eval_steps": 500,
-  "global_step": 313,
+  "global_step": 626,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -503,6 +503,487 @@
       "eval_samples_per_second": 16.096,
       "eval_steps_per_second": 0.563,
       "step": 313
+    },
+    {
+      "epoch": 1.0223642172523961,
+      "grad_norm": 11.604345250214385,
+      "learning_rate": 3.662721893491124e-07,
+      "logits/chosen": -0.859375,
+      "logits/rejected": -0.8828125,
+      "logps/chosen": -41.75,
+      "logps/rejected": -44.25,
+      "loss": 0.4945,
+      "rewards/accuracies": 0.5375000238418579,
+      "rewards/chosen": -0.51171875,
+      "rewards/margins": 0.921875,
+      "rewards/rejected": -1.4296875,
+      "step": 320
+    },
+    {
+      "epoch": 1.0543130990415335,
+      "grad_norm": 8.164279499540298,
+      "learning_rate": 3.603550295857988e-07,
+      "logits/chosen": -0.93359375,
+      "logits/rejected": -0.8359375,
+      "logps/chosen": -41.5,
+      "logps/rejected": -47.0,
+      "loss": 0.487,
+      "rewards/accuracies": 0.550000011920929,
+      "rewards/chosen": -0.51171875,
+      "rewards/margins": 0.98046875,
+      "rewards/rejected": -1.4921875,
+      "step": 330
+    },
+    {
+      "epoch": 1.0862619808306708,
+      "grad_norm": 10.098456650224257,
+      "learning_rate": 3.544378698224852e-07,
+      "logits/chosen": -0.90234375,
+      "logits/rejected": -0.89453125,
+      "logps/chosen": -38.25,
+      "logps/rejected": -46.5,
+      "loss": 0.4921,
+      "rewards/accuracies": 0.42500001192092896,
+      "rewards/chosen": -0.74609375,
+      "rewards/margins": 0.71875,
+      "rewards/rejected": -1.4609375,
+      "step": 340
+    },
+    {
+      "epoch": 1.1182108626198084,
+      "grad_norm": 12.312245605594391,
+      "learning_rate": 3.485207100591716e-07,
+      "logits/chosen": -0.8984375,
+      "logits/rejected": -0.9140625,
+      "logps/chosen": -41.75,
+      "logps/rejected": -44.0,
+      "loss": 0.4951,
+      "rewards/accuracies": 0.42500001192092896,
+      "rewards/chosen": -0.671875,
+      "rewards/margins": 0.86328125,
+      "rewards/rejected": -1.5390625,
+      "step": 350
+    },
+    {
+      "epoch": 1.1501597444089458,
+      "grad_norm": 7.6387271402180925,
+      "learning_rate": 3.42603550295858e-07,
+      "logits/chosen": -0.95703125,
+      "logits/rejected": -0.875,
+      "logps/chosen": -39.5,
+      "logps/rejected": -43.5,
+      "loss": 0.5121,
+      "rewards/accuracies": 0.3499999940395355,
+      "rewards/chosen": -0.74609375,
+      "rewards/margins": 0.8125,
+      "rewards/rejected": -1.5625,
+      "step": 360
+    },
+    {
+      "epoch": 1.182108626198083,
+      "grad_norm": 9.066794201428493,
+      "learning_rate": 3.366863905325444e-07,
+      "logits/chosen": -0.91796875,
+      "logits/rejected": -0.890625,
+      "logps/chosen": -39.25,
+      "logps/rejected": -43.25,
+      "loss": 0.5005,
+      "rewards/accuracies": 0.375,
+      "rewards/chosen": -0.9140625,
+      "rewards/margins": 0.7890625,
+      "rewards/rejected": -1.703125,
+      "step": 370
+    },
+    {
+      "epoch": 1.2140575079872205,
+      "grad_norm": 13.248069014797954,
+      "learning_rate": 3.3076923076923075e-07,
+      "logits/chosen": -0.91796875,
+      "logits/rejected": -0.91796875,
+      "logps/chosen": -37.5,
+      "logps/rejected": -51.0,
+      "loss": 0.4653,
+      "rewards/accuracies": 0.512499988079071,
+      "rewards/chosen": -0.71484375,
+      "rewards/margins": 1.015625,
+      "rewards/rejected": -1.7265625,
+      "step": 380
+    },
+    {
+      "epoch": 1.2460063897763578,
+      "grad_norm": 10.867663199240486,
+      "learning_rate": 3.2485207100591716e-07,
+      "logits/chosen": -0.94140625,
+      "logits/rejected": -0.890625,
+      "logps/chosen": -42.25,
+      "logps/rejected": -45.75,
+      "loss": 0.4909,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.5625,
+      "rewards/margins": 1.109375,
+      "rewards/rejected": -1.671875,
+      "step": 390
+    },
+    {
+      "epoch": 1.2779552715654952,
+      "grad_norm": 12.647214530771212,
+      "learning_rate": 3.189349112426035e-07,
+      "logits/chosen": -0.84765625,
+      "logits/rejected": -0.921875,
+      "logps/chosen": -29.625,
+      "logps/rejected": -60.0,
+      "loss": 0.4816,
+      "rewards/accuracies": 0.5375000238418579,
+      "rewards/chosen": -0.96484375,
+      "rewards/margins": 1.0,
+      "rewards/rejected": -1.96875,
+      "step": 400
+    },
+    {
+      "epoch": 1.3099041533546325,
+      "grad_norm": 13.831769507648124,
+      "learning_rate": 3.130177514792899e-07,
+      "logits/chosen": -0.89453125,
+      "logits/rejected": -0.85546875,
+      "logps/chosen": -32.5,
+      "logps/rejected": -43.75,
+      "loss": 0.5379,
+      "rewards/accuracies": 0.3375000059604645,
+      "rewards/chosen": -1.078125,
+      "rewards/margins": 0.50390625,
+      "rewards/rejected": -1.578125,
+      "step": 410
+    },
+    {
+      "epoch": 1.34185303514377,
+      "grad_norm": 12.24140890124011,
+      "learning_rate": 3.071005917159763e-07,
+      "logits/chosen": -0.9375,
+      "logits/rejected": -0.9375,
+      "logps/chosen": -41.0,
+      "logps/rejected": -53.25,
+      "loss": 0.4786,
+      "rewards/accuracies": 0.48750001192092896,
+      "rewards/chosen": -1.265625,
+      "rewards/margins": 1.046875,
+      "rewards/rejected": -2.3125,
+      "step": 420
+    },
+    {
+      "epoch": 1.3738019169329074,
+      "grad_norm": 8.001226654192951,
+      "learning_rate": 3.011834319526627e-07,
+      "logits/chosen": -0.95703125,
+      "logits/rejected": -0.8984375,
+      "logps/chosen": -44.5,
+      "logps/rejected": -50.0,
+      "loss": 0.4892,
+      "rewards/accuracies": 0.4749999940395355,
+      "rewards/chosen": -1.0703125,
+      "rewards/margins": 0.984375,
+      "rewards/rejected": -2.046875,
+      "step": 430
+    },
+    {
+      "epoch": 1.4057507987220448,
+      "grad_norm": 13.90707171430186,
+      "learning_rate": 2.952662721893491e-07,
+      "logits/chosen": -0.95703125,
+      "logits/rejected": -0.87890625,
+      "logps/chosen": -44.0,
+      "logps/rejected": -47.25,
+      "loss": 0.4805,
+      "rewards/accuracies": 0.42500001192092896,
+      "rewards/chosen": -1.03125,
+      "rewards/margins": 1.0546875,
+      "rewards/rejected": -2.09375,
+      "step": 440
+    },
+    {
+      "epoch": 1.4376996805111821,
+      "grad_norm": 11.71134112335707,
+      "learning_rate": 2.893491124260355e-07,
+      "logits/chosen": -0.91796875,
+      "logits/rejected": -0.86328125,
+      "logps/chosen": -46.5,
+      "logps/rejected": -45.25,
+      "loss": 0.4582,
+      "rewards/accuracies": 0.42500001192092896,
+      "rewards/chosen": -1.171875,
+      "rewards/margins": 0.83984375,
+      "rewards/rejected": -2.015625,
+      "step": 450
+    },
+    {
+      "epoch": 1.4696485623003195,
+      "grad_norm": 10.206570733769754,
+      "learning_rate": 2.834319526627219e-07,
+      "logits/chosen": -1.0,
+      "logits/rejected": -0.921875,
+      "logps/chosen": -44.25,
+      "logps/rejected": -46.75,
+      "loss": 0.4662,
+      "rewards/accuracies": 0.44999998807907104,
+      "rewards/chosen": -1.1015625,
+      "rewards/margins": 0.8984375,
+      "rewards/rejected": -2.015625,
+      "step": 460
+    },
+    {
+      "epoch": 1.5015974440894568,
+      "grad_norm": 8.481816160880287,
+      "learning_rate": 2.7751479289940824e-07,
+      "logits/chosen": -0.97265625,
+      "logits/rejected": -0.8671875,
+      "logps/chosen": -43.0,
+      "logps/rejected": -54.0,
+      "loss": 0.4951,
+      "rewards/accuracies": 0.44999998807907104,
+      "rewards/chosen": -1.2421875,
+      "rewards/margins": 1.078125,
+      "rewards/rejected": -2.3125,
+      "step": 470
+    },
+    {
+      "epoch": 1.5335463258785942,
+      "grad_norm": 9.450961138318995,
+      "learning_rate": 2.715976331360947e-07,
+      "logits/chosen": -0.96484375,
+      "logits/rejected": -0.859375,
+      "logps/chosen": -45.0,
+      "logps/rejected": -50.5,
+      "loss": 0.4609,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.8359375,
+      "rewards/margins": 1.359375,
+      "rewards/rejected": -2.1875,
+      "step": 480
+    },
+    {
+      "epoch": 1.5654952076677318,
+      "grad_norm": 10.079665777936816,
+      "learning_rate": 2.6568047337278106e-07,
+      "logits/chosen": -0.9140625,
+      "logits/rejected": -0.8671875,
+      "logps/chosen": -40.5,
+      "logps/rejected": -46.25,
+      "loss": 0.484,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": -1.171875,
+      "rewards/margins": 0.91796875,
+      "rewards/rejected": -2.09375,
+      "step": 490
+    },
+    {
+      "epoch": 1.5974440894568689,
+      "grad_norm": 5.892858649998084,
+      "learning_rate": 2.5976331360946746e-07,
+      "logits/chosen": -0.90234375,
+      "logits/rejected": -0.85546875,
+      "logps/chosen": -43.5,
+      "logps/rejected": -44.0,
+      "loss": 0.4725,
+      "rewards/accuracies": 0.42500001192092896,
+      "rewards/chosen": -0.96875,
+      "rewards/margins": 0.8984375,
+      "rewards/rejected": -1.8671875,
+      "step": 500
+    },
+    {
+      "epoch": 1.6293929712460065,
+      "grad_norm": 19.866826656455657,
+      "learning_rate": 2.538461538461538e-07,
+      "logits/chosen": -0.88671875,
+      "logits/rejected": -0.875,
+      "logps/chosen": -37.0,
+      "logps/rejected": -49.0,
+      "loss": 0.4713,
+      "rewards/accuracies": 0.44999998807907104,
+      "rewards/chosen": -1.015625,
+      "rewards/margins": 1.09375,
+      "rewards/rejected": -2.109375,
+      "step": 510
+    },
+    {
+      "epoch": 1.6613418530351438,
+      "grad_norm": 11.462164104029984,
+      "learning_rate": 2.479289940828402e-07,
+      "logits/chosen": -1.0,
+      "logits/rejected": -0.86328125,
+      "logps/chosen": -48.25,
+      "logps/rejected": -46.5,
+      "loss": 0.4437,
+      "rewards/accuracies": 0.512499988079071,
+      "rewards/chosen": -0.69140625,
+      "rewards/margins": 1.28125,
+      "rewards/rejected": -1.9765625,
+      "step": 520
+    },
+    {
+      "epoch": 1.6932907348242812,
+      "grad_norm": 4.754132390092114,
+      "learning_rate": 2.420118343195266e-07,
+      "logits/chosen": -0.984375,
+      "logits/rejected": -0.89453125,
+      "logps/chosen": -43.5,
+      "logps/rejected": -44.5,
+      "loss": 0.4539,
+      "rewards/accuracies": 0.44999998807907104,
+      "rewards/chosen": -1.0234375,
+      "rewards/margins": 1.0234375,
+      "rewards/rejected": -2.046875,
+      "step": 530
+    },
+    {
+      "epoch": 1.7252396166134185,
+      "grad_norm": 13.855605681924747,
+      "learning_rate": 2.36094674556213e-07,
+      "logits/chosen": -1.0234375,
+      "logits/rejected": -0.828125,
+      "logps/chosen": -50.0,
+      "logps/rejected": -45.75,
+      "loss": 0.4537,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.81640625,
+      "rewards/margins": 1.203125,
+      "rewards/rejected": -2.015625,
+      "step": 540
+    },
+    {
+      "epoch": 1.7571884984025559,
+      "grad_norm": 13.694710524562387,
+      "learning_rate": 2.301775147928994e-07,
+      "logits/chosen": -0.98828125,
+      "logits/rejected": -0.91796875,
+      "logps/chosen": -41.75,
+      "logps/rejected": -52.5,
+      "loss": 0.4505,
+      "rewards/accuracies": 0.4749999940395355,
+      "rewards/chosen": -1.09375,
+      "rewards/margins": 1.265625,
+      "rewards/rejected": -2.359375,
+      "step": 550
+    },
+    {
+      "epoch": 1.7891373801916934,
+      "grad_norm": 12.265823828649788,
+      "learning_rate": 2.242603550295858e-07,
+      "logits/chosen": -0.98828125,
+      "logits/rejected": -0.92578125,
+      "logps/chosen": -39.75,
+      "logps/rejected": -59.0,
+      "loss": 0.4626,
+      "rewards/accuracies": 0.5249999761581421,
+      "rewards/chosen": -0.86328125,
+      "rewards/margins": 1.3828125,
+      "rewards/rejected": -2.25,
+      "step": 560
+    },
+    {
+      "epoch": 1.8210862619808306,
+      "grad_norm": 15.811792160256678,
+      "learning_rate": 2.1834319526627217e-07,
+      "logits/chosen": -0.95703125,
+      "logits/rejected": -0.8984375,
+      "logps/chosen": -40.5,
+      "logps/rejected": -50.5,
+      "loss": 0.4507,
+      "rewards/accuracies": 0.4749999940395355,
+      "rewards/chosen": -0.609375,
+      "rewards/margins": 1.28125,
+      "rewards/rejected": -1.8828125,
+      "step": 570
+    },
+    {
+      "epoch": 1.8530351437699681,
+      "grad_norm": 12.03300574763422,
+      "learning_rate": 2.1242603550295858e-07,
+      "logits/chosen": -1.046875,
+      "logits/rejected": -0.91015625,
+      "logps/chosen": -42.25,
+      "logps/rejected": -49.25,
+      "loss": 0.45,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.62890625,
+      "rewards/margins": 1.3984375,
+      "rewards/rejected": -2.03125,
+      "step": 580
+    },
+    {
+      "epoch": 1.8849840255591053,
+      "grad_norm": 6.498105360999796,
+      "learning_rate": 2.0650887573964496e-07,
+      "logits/chosen": -0.9921875,
+      "logits/rejected": -0.8828125,
+      "logps/chosen": -45.75,
+      "logps/rejected": -52.75,
+      "loss": 0.4347,
+      "rewards/accuracies": 0.512499988079071,
+      "rewards/chosen": -0.94921875,
+      "rewards/margins": 1.546875,
+      "rewards/rejected": -2.5,
+      "step": 590
+    },
+    {
+      "epoch": 1.9169329073482428,
+      "grad_norm": 17.196261475524192,
+      "learning_rate": 2.0059171597633133e-07,
+      "logits/chosen": -0.91796875,
+      "logits/rejected": -0.859375,
+      "logps/chosen": -39.25,
+      "logps/rejected": -50.75,
+      "loss": 0.4452,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": -1.1875,
+      "rewards/margins": 1.171875,
+      "rewards/rejected": -2.359375,
+      "step": 600
+    },
+    {
+      "epoch": 1.9488817891373802,
+      "grad_norm": 6.682211779881807,
+      "learning_rate": 1.9467455621301774e-07,
+      "logits/chosen": -0.81640625,
+      "logits/rejected": -0.93359375,
+      "logps/chosen": -42.25,
+      "logps/rejected": -57.25,
+      "loss": 0.4483,
+      "rewards/accuracies": 0.4749999940395355,
+      "rewards/chosen": -1.2890625,
+      "rewards/margins": 1.265625,
+      "rewards/rejected": -2.546875,
+      "step": 610
+    },
+    {
+      "epoch": 1.9808306709265175,
+      "grad_norm": 8.358366031471173,
+      "learning_rate": 1.8875739644970412e-07,
+      "logits/chosen": -0.9921875,
+      "logits/rejected": -0.90234375,
+      "logps/chosen": -45.25,
+      "logps/rejected": -57.75,
+      "loss": 0.4365,
+      "rewards/accuracies": 0.5249999761581421,
+      "rewards/chosen": -1.296875,
+      "rewards/margins": 1.40625,
+      "rewards/rejected": -2.703125,
+      "step": 620
+    },
+    {
+      "epoch": 2.0,
+      "eval_logits/chosen": -1.03125,
+      "eval_logits/rejected": -0.9375,
+      "eval_logps/chosen": -51.75,
+      "eval_logps/rejected": -49.75,
+      "eval_loss": 0.5380077958106995,
+      "eval_rewards/accuracies": 0.5,
+      "eval_rewards/chosen": -1.2890625,
+      "eval_rewards/margins": 1.078125,
+      "eval_rewards/rejected": -2.375,
+      "eval_runtime": 12.4486,
+      "eval_samples_per_second": 16.066,
+      "eval_steps_per_second": 0.562,
+      "step": 626
     }
   ],
   "logging_steps": 10,