Training in progress, epoch 3, checkpoint

last-checkpoint/global_step939/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:ff875785ab924ddd06a66be771594fe532d0d87d67059a754f87a79e011492f6
+size 16060527788

last-checkpoint/global_step939/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57602bd05fa70544df76925acf63ee24ea4316d87843ebc84abd169f793452f1
+size 16060527788

last-checkpoint/global_step939/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19747266673f3adc37eb34cd72e64194822c760661df80b1e4e1f14bd06413f0
+size 16060527788

last-checkpoint/global_step939/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62ea89cf520034e1a0d86ed2f8efed6dbcec31fe835a5303f632c173b9ce209b
+size 16060527788

last-checkpoint/global_step939/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bdb7dbee9c796f9aafc9eee12e5897c440ad5a648fd8df8520d6e2380a7c1a5
+size 150693

last-checkpoint/global_step939/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c0406da72cdfc68a165458ddeef11d1da49d6d97bb21ad9504edf784cedb97f
+size 150693

last-checkpoint/global_step939/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:332ccdbe01b4fa4b6a35acac97bc26143f603959f45d4d12c635ad4e6a2e8632
+size 150693

last-checkpoint/global_step939/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f7528f0ef5669d4d46b8576941e18d57af6e08eb71acd5ffb084bdd17ea161d
+size 150693

last-checkpoint/latest

@@ -1 +1 @@
-global_step626
+global_step939

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d54039dc041f3e015fb26a58181e18b15300073aa7f189906aa141eb163193c
+oid sha256:d7e8fb1adccd2e7fe2bbeefbafa82a4565057fab3010779fd5e5ab4c409bb496
 size 4976698672

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be7408aaad853291659cca456977f64b9c12df36e72fcf70bfbd86190f59689d
+oid sha256:dc8a42b274b60f2ed063dbc5a0db133fa0fba6e446796edd49203d49a11700aa
 size 4999802720

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94015a2bd29aadfc52d528f933601b3767e3e5d51650d43bc11706148be83fcb
+oid sha256:e4395bbcc01e2ccad78f50643525aed5bf2d95e1b0f624507fdeacc3d0870011
 size 4915916176

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74954b42e041e5dce92411f4519e39cc59ac7fb94ec1eabe1f6cc6ac121815b9
+oid sha256:f60fed5474de507e5cf5f93d70d0b84d7bf7848f88ce747be3d6fa3998258d84
 size 1168138808

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2307c03867cef25b5028feb9a23f80e784b9af9a615de13ddca560a6a90fb593
+oid sha256:ab7cf0d34d60dfda516cf9661904550e2e294e723edd07c25c738f05e8ba92d1
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50218cfaecdd818354e567b7167c13899e3b42297e7d8f58bd7e732cfa547800
+oid sha256:f7b183324e8227a51a9556d86b2ad893a8c4c52205ed4a737356c6611dac7353
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9814a66b49861f5495b06dae3be12ddf7185b88e2cae1fb808ca9efd99d5807f
+oid sha256:ac69e994090f4818cb1fa6f6cefa363178552c3c731c6507ff195bcb07fd5bef
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7be93040a65e0a29975f6c70b94418e1fdf88423a50c58aa572141d3c92fbfc
+oid sha256:f68e61b63402f8afb1f69c960f7944965655dac11e3ccf29919c282f23931f86
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7725b44c69725321786f1e58dccd7ea4d3ae5794ea47bd49c0d4a139aec266d
+oid sha256:fe7d17fbcfa5bee1bf6cb5aedab3ff5a70436912c200d7301d173be443809d63
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.0,
+  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 626,
+  "global_step": 939,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -984,6 +984,487 @@
       "eval_samples_per_second": 16.066,
       "eval_steps_per_second": 0.562,
       "step": 626
+    },
+    {
+      "epoch": 2.012779552715655,
+      "grad_norm": 4.74652717171804,
+      "learning_rate": 1.8284023668639053e-07,
+      "logits/chosen": -0.875,
+      "logits/rejected": -0.96484375,
+      "logps/chosen": -40.75,
+      "logps/rejected": -56.0,
+      "loss": 0.4227,
+      "rewards/accuracies": 0.4625000059604645,
+      "rewards/chosen": -1.25,
+      "rewards/margins": 1.078125,
+      "rewards/rejected": -2.328125,
+      "step": 630
+    },
+    {
+      "epoch": 2.0447284345047922,
+      "grad_norm": 9.093805196751525,
+      "learning_rate": 1.7692307692307693e-07,
+      "logits/chosen": -0.95703125,
+      "logits/rejected": -0.96484375,
+      "logps/chosen": -46.25,
+      "logps/rejected": -56.75,
+      "loss": 0.4062,
+      "rewards/accuracies": 0.5249999761581421,
+      "rewards/chosen": -1.234375,
+      "rewards/margins": 1.6640625,
+      "rewards/rejected": -2.90625,
+      "step": 640
+    },
+    {
+      "epoch": 2.07667731629393,
+      "grad_norm": 7.904913836224486,
+      "learning_rate": 1.710059171597633e-07,
+      "logits/chosen": -0.94140625,
+      "logits/rejected": -0.84765625,
+      "logps/chosen": -44.75,
+      "logps/rejected": -53.75,
+      "loss": 0.403,
+      "rewards/accuracies": 0.4625000059604645,
+      "rewards/chosen": -1.265625,
+      "rewards/margins": 1.34375,
+      "rewards/rejected": -2.609375,
+      "step": 650
+    },
+    {
+      "epoch": 2.108626198083067,
+      "grad_norm": 9.216092905835959,
+      "learning_rate": 1.650887573964497e-07,
+      "logits/chosen": -0.85546875,
+      "logits/rejected": -0.81640625,
+      "logps/chosen": -42.5,
+      "logps/rejected": -47.0,
+      "loss": 0.4476,
+      "rewards/accuracies": 0.4124999940395355,
+      "rewards/chosen": -1.15625,
+      "rewards/margins": 1.1796875,
+      "rewards/rejected": -2.34375,
+      "step": 660
+    },
+    {
+      "epoch": 2.1405750798722045,
+      "grad_norm": 8.710740799549797,
+      "learning_rate": 1.591715976331361e-07,
+      "logits/chosen": -1.0234375,
+      "logits/rejected": -0.875,
+      "logps/chosen": -44.5,
+      "logps/rejected": -54.25,
+      "loss": 0.4187,
+      "rewards/accuracies": 0.512499988079071,
+      "rewards/chosen": -0.92578125,
+      "rewards/margins": 1.625,
+      "rewards/rejected": -2.546875,
+      "step": 670
+    },
+    {
+      "epoch": 2.1725239616613417,
+      "grad_norm": 8.094002644119932,
+      "learning_rate": 1.5325443786982248e-07,
+      "logits/chosen": -1.0703125,
+      "logits/rejected": -0.8984375,
+      "logps/chosen": -43.5,
+      "logps/rejected": -59.0,
+      "loss": 0.3973,
+      "rewards/accuracies": 0.5375000238418579,
+      "rewards/chosen": -0.7578125,
+      "rewards/margins": 2.0,
+      "rewards/rejected": -2.765625,
+      "step": 680
+    },
+    {
+      "epoch": 2.2044728434504792,
+      "grad_norm": 8.249215092288534,
+      "learning_rate": 1.4733727810650885e-07,
+      "logits/chosen": -0.96875,
+      "logits/rejected": -0.9765625,
+      "logps/chosen": -41.75,
+      "logps/rejected": -59.75,
+      "loss": 0.3862,
+      "rewards/accuracies": 0.5375000238418579,
+      "rewards/chosen": -1.2109375,
+      "rewards/margins": 1.59375,
+      "rewards/rejected": -2.8125,
+      "step": 690
+    },
+    {
+      "epoch": 2.236421725239617,
+      "grad_norm": 8.713919175156146,
+      "learning_rate": 1.4142011834319526e-07,
+      "logits/chosen": -1.015625,
+      "logits/rejected": -0.81640625,
+      "logps/chosen": -44.25,
+      "logps/rejected": -52.25,
+      "loss": 0.3898,
+      "rewards/accuracies": 0.512499988079071,
+      "rewards/chosen": -1.109375,
+      "rewards/margins": 1.6875,
+      "rewards/rejected": -2.796875,
+      "step": 700
+    },
+    {
+      "epoch": 2.268370607028754,
+      "grad_norm": 2.4789298662571055,
+      "learning_rate": 1.3550295857988164e-07,
+      "logits/chosen": -1.0703125,
+      "logits/rejected": -0.75,
+      "logps/chosen": -49.0,
+      "logps/rejected": -55.0,
+      "loss": 0.387,
+      "rewards/accuracies": 0.4625000059604645,
+      "rewards/chosen": -1.421875,
+      "rewards/margins": 1.6015625,
+      "rewards/rejected": -3.03125,
+      "step": 710
+    },
+    {
+      "epoch": 2.3003194888178915,
+      "grad_norm": 13.408171707422571,
+      "learning_rate": 1.2958579881656802e-07,
+      "logits/chosen": -0.81640625,
+      "logits/rejected": -0.859375,
+      "logps/chosen": -42.0,
+      "logps/rejected": -54.5,
+      "loss": 0.4224,
+      "rewards/accuracies": 0.4625000059604645,
+      "rewards/chosen": -1.546875,
+      "rewards/margins": 1.3984375,
+      "rewards/rejected": -2.953125,
+      "step": 720
+    },
+    {
+      "epoch": 2.3322683706070286,
+      "grad_norm": 5.024401475671983,
+      "learning_rate": 1.2366863905325443e-07,
+      "logits/chosen": -0.95703125,
+      "logits/rejected": -0.89453125,
+      "logps/chosen": -47.0,
+      "logps/rejected": -57.0,
+      "loss": 0.393,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -1.2421875,
+      "rewards/margins": 1.671875,
+      "rewards/rejected": -2.921875,
+      "step": 730
+    },
+    {
+      "epoch": 2.364217252396166,
+      "grad_norm": 27.208339044008937,
+      "learning_rate": 1.1775147928994082e-07,
+      "logits/chosen": -0.97265625,
+      "logits/rejected": -0.921875,
+      "logps/chosen": -47.0,
+      "logps/rejected": -63.0,
+      "loss": 0.4028,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -1.4375,
+      "rewards/margins": 1.640625,
+      "rewards/rejected": -3.078125,
+      "step": 740
+    },
+    {
+      "epoch": 2.3961661341853033,
+      "grad_norm": 10.51991490071309,
+      "learning_rate": 1.1183431952662721e-07,
+      "logits/chosen": -0.98046875,
+      "logits/rejected": -1.03125,
+      "logps/chosen": -43.5,
+      "logps/rejected": -69.0,
+      "loss": 0.4102,
+      "rewards/accuracies": 0.612500011920929,
+      "rewards/chosen": -1.5546875,
+      "rewards/margins": 2.125,
+      "rewards/rejected": -3.671875,
+      "step": 750
+    },
+    {
+      "epoch": 2.428115015974441,
+      "grad_norm": 11.046462734712232,
+      "learning_rate": 1.059171597633136e-07,
+      "logits/chosen": -0.9375,
+      "logits/rejected": -0.77734375,
+      "logps/chosen": -46.5,
+      "logps/rejected": -53.5,
+      "loss": 0.374,
+      "rewards/accuracies": 0.512499988079071,
+      "rewards/chosen": -1.265625,
+      "rewards/margins": 1.78125,
+      "rewards/rejected": -3.03125,
+      "step": 760
+    },
+    {
+      "epoch": 2.460063897763578,
+      "grad_norm": 7.941784467499254,
+      "learning_rate": 1e-07,
+      "logits/chosen": -0.79296875,
+      "logits/rejected": -0.921875,
+      "logps/chosen": -40.5,
+      "logps/rejected": -67.5,
+      "loss": 0.3808,
+      "rewards/accuracies": 0.5375000238418579,
+      "rewards/chosen": -1.6328125,
+      "rewards/margins": 1.96875,
+      "rewards/rejected": -3.609375,
+      "step": 770
+    },
+    {
+      "epoch": 2.4920127795527156,
+      "grad_norm": 18.383843736884476,
+      "learning_rate": 9.408284023668639e-08,
+      "logits/chosen": -0.953125,
+      "logits/rejected": -0.953125,
+      "logps/chosen": -44.5,
+      "logps/rejected": -63.0,
+      "loss": 0.3853,
+      "rewards/accuracies": 0.44999998807907104,
+      "rewards/chosen": -1.6015625,
+      "rewards/margins": 1.8046875,
+      "rewards/rejected": -3.390625,
+      "step": 780
+    },
+    {
+      "epoch": 2.523961661341853,
+      "grad_norm": 12.735279104095845,
+      "learning_rate": 8.816568047337278e-08,
+      "logits/chosen": -0.95703125,
+      "logits/rejected": -0.859375,
+      "logps/chosen": -46.5,
+      "logps/rejected": -53.75,
+      "loss": 0.4527,
+      "rewards/accuracies": 0.375,
+      "rewards/chosen": -1.7421875,
+      "rewards/margins": 1.2421875,
+      "rewards/rejected": -2.984375,
+      "step": 790
+    },
+    {
+      "epoch": 2.5559105431309903,
+      "grad_norm": 25.31092617144284,
+      "learning_rate": 8.224852071005916e-08,
+      "logits/chosen": -0.75,
+      "logits/rejected": -1.03125,
+      "logps/chosen": -44.25,
+      "logps/rejected": -72.0,
+      "loss": 0.3664,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -1.8671875,
+      "rewards/margins": 1.890625,
+      "rewards/rejected": -3.765625,
+      "step": 800
+    },
+    {
+      "epoch": 2.587859424920128,
+      "grad_norm": 28.35128868207696,
+      "learning_rate": 7.633136094674555e-08,
+      "logits/chosen": -0.953125,
+      "logits/rejected": -0.83203125,
+      "logps/chosen": -50.5,
+      "logps/rejected": -55.0,
+      "loss": 0.4429,
+      "rewards/accuracies": 0.42500001192092896,
+      "rewards/chosen": -1.6796875,
+      "rewards/margins": 1.5703125,
+      "rewards/rejected": -3.25,
+      "step": 810
+    },
+    {
+      "epoch": 2.619808306709265,
+      "grad_norm": 8.972843974408116,
+      "learning_rate": 7.041420118343195e-08,
+      "logits/chosen": -1.03125,
+      "logits/rejected": -0.94140625,
+      "logps/chosen": -51.0,
+      "logps/rejected": -70.0,
+      "loss": 0.3984,
+      "rewards/accuracies": 0.5874999761581421,
+      "rewards/chosen": -1.46875,
+      "rewards/margins": 2.421875,
+      "rewards/rejected": -3.890625,
+      "step": 820
+    },
+    {
+      "epoch": 2.6517571884984026,
+      "grad_norm": 8.613351315510789,
+      "learning_rate": 6.449704142011835e-08,
+      "logits/chosen": -0.96875,
+      "logits/rejected": -1.0546875,
+      "logps/chosen": -50.25,
+      "logps/rejected": -69.0,
+      "loss": 0.4115,
+      "rewards/accuracies": 0.512499988079071,
+      "rewards/chosen": -1.46875,
+      "rewards/margins": 2.03125,
+      "rewards/rejected": -3.5,
+      "step": 830
+    },
+    {
+      "epoch": 2.68370607028754,
+      "grad_norm": 9.70223823689821,
+      "learning_rate": 5.857988165680473e-08,
+      "logits/chosen": -1.03125,
+      "logits/rejected": -0.75,
+      "logps/chosen": -49.0,
+      "logps/rejected": -53.5,
+      "loss": 0.3931,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": -1.2890625,
+      "rewards/margins": 1.890625,
+      "rewards/rejected": -3.171875,
+      "step": 840
+    },
+    {
+      "epoch": 2.7156549520766773,
+      "grad_norm": 14.809661385875646,
+      "learning_rate": 5.266272189349112e-08,
+      "logits/chosen": -0.96875,
+      "logits/rejected": -0.953125,
+      "logps/chosen": -47.25,
+      "logps/rejected": -62.75,
+      "loss": 0.4115,
+      "rewards/accuracies": 0.4749999940395355,
+      "rewards/chosen": -1.6484375,
+      "rewards/margins": 1.7734375,
+      "rewards/rejected": -3.421875,
+      "step": 850
+    },
+    {
+      "epoch": 2.747603833865815,
+      "grad_norm": 5.380820798764086,
+      "learning_rate": 4.674556213017751e-08,
+      "logits/chosen": -0.98046875,
+      "logits/rejected": -0.8828125,
+      "logps/chosen": -47.0,
+      "logps/rejected": -61.25,
+      "loss": 0.3984,
+      "rewards/accuracies": 0.4625000059604645,
+      "rewards/chosen": -1.625,
+      "rewards/margins": 1.703125,
+      "rewards/rejected": -3.328125,
+      "step": 860
+    },
+    {
+      "epoch": 2.779552715654952,
+      "grad_norm": 19.658075353925057,
+      "learning_rate": 4.082840236686391e-08,
+      "logits/chosen": -0.90625,
+      "logits/rejected": -0.7578125,
+      "logps/chosen": -49.25,
+      "logps/rejected": -57.5,
+      "loss": 0.3908,
+      "rewards/accuracies": 0.4749999940395355,
+      "rewards/chosen": -1.8984375,
+      "rewards/margins": 1.578125,
+      "rewards/rejected": -3.46875,
+      "step": 870
+    },
+    {
+      "epoch": 2.8115015974440896,
+      "grad_norm": 10.442407160730754,
+      "learning_rate": 3.4911242603550294e-08,
+      "logits/chosen": -0.84375,
+      "logits/rejected": -0.91796875,
+      "logps/chosen": -41.75,
+      "logps/rejected": -63.75,
+      "loss": 0.4039,
+      "rewards/accuracies": 0.48750001192092896,
+      "rewards/chosen": -1.8125,
+      "rewards/margins": 1.53125,
+      "rewards/rejected": -3.34375,
+      "step": 880
+    },
+    {
+      "epoch": 2.8434504792332267,
+      "grad_norm": 29.6132532828452,
+      "learning_rate": 2.8994082840236687e-08,
+      "logits/chosen": -0.95703125,
+      "logits/rejected": -0.82421875,
+      "logps/chosen": -46.75,
+      "logps/rejected": -62.5,
+      "loss": 0.3814,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": -1.5859375,
+      "rewards/margins": 2.0625,
+      "rewards/rejected": -3.640625,
+      "step": 890
+    },
+    {
+      "epoch": 2.8753993610223643,
+      "grad_norm": 5.3338488869709035,
+      "learning_rate": 2.3076923076923076e-08,
+      "logits/chosen": -0.7578125,
+      "logits/rejected": -0.81640625,
+      "logps/chosen": -37.5,
+      "logps/rejected": -55.0,
+      "loss": 0.4095,
+      "rewards/accuracies": 0.4124999940395355,
+      "rewards/chosen": -1.671875,
+      "rewards/margins": 1.34375,
+      "rewards/rejected": -3.015625,
+      "step": 900
+    },
+    {
+      "epoch": 2.9073482428115014,
+      "grad_norm": 8.959126987075347,
+      "learning_rate": 1.7159763313609465e-08,
+      "logits/chosen": -1.0078125,
+      "logits/rejected": -0.84375,
+      "logps/chosen": -45.75,
+      "logps/rejected": -55.5,
+      "loss": 0.3631,
+      "rewards/accuracies": 0.5249999761581421,
+      "rewards/chosen": -1.3984375,
+      "rewards/margins": 1.6015625,
+      "rewards/rejected": -3.0,
+      "step": 910
+    },
+    {
+      "epoch": 2.939297124600639,
+      "grad_norm": 12.28972695659583,
+      "learning_rate": 1.1242603550295858e-08,
+      "logits/chosen": -1.015625,
+      "logits/rejected": -0.9765625,
+      "logps/chosen": -49.75,
+      "logps/rejected": -69.0,
+      "loss": 0.4118,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -1.703125,
+      "rewards/margins": 2.09375,
+      "rewards/rejected": -3.796875,
+      "step": 920
+    },
+    {
+      "epoch": 2.9712460063897765,
+      "grad_norm": 7.913983074444077,
+      "learning_rate": 5.325443786982248e-09,
+      "logits/chosen": -0.984375,
+      "logits/rejected": -0.7734375,
+      "logps/chosen": -46.5,
+      "logps/rejected": -49.0,
+      "loss": 0.4176,
+      "rewards/accuracies": 0.42500001192092896,
+      "rewards/chosen": -1.6484375,
+      "rewards/margins": 1.28125,
+      "rewards/rejected": -2.921875,
+      "step": 930
+    },
+    {
+      "epoch": 3.0,
+      "eval_logits/chosen": -1.078125,
+      "eval_logits/rejected": -0.91796875,
+      "eval_logps/chosen": -57.0,
+      "eval_logps/rejected": -56.75,
+      "eval_loss": 0.5467187762260437,
+      "eval_rewards/accuracies": 0.4642857015132904,
+      "eval_rewards/chosen": -1.828125,
+      "eval_rewards/margins": 1.234375,
+      "eval_rewards/rejected": -3.0625,
+      "eval_runtime": 14.7769,
+      "eval_samples_per_second": 13.535,
+      "eval_steps_per_second": 0.474,
+      "step": 939
     }
   ],
   "logging_steps": 10,
@@ -998,7 +1479,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }