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 sha256:5c3ce640877b2d8ecc0e24be100a3e0ce7a6976179a0fa4fead2fa8644c4fc5f
+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 sha256:5bf4c498bff350ad34e921d9c242d36feb45270e06107b47671851bf36bea253
+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:e1d0e7d4b0af35a6ca7d6c6fd0e30316dde6141a9217f8afba4c4b621446ae31
+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 sha256:8b55b89cb59cbc4d9ef18449658cc50b4cb6f3bc0a1be87c8f0a460f2d290214
+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 sha256:8e326a1dbd8fc14b10637832fdeb8d0c03940664a8c4f58f99100b04f96138e8
+oid sha256:46ac6018d17786570971da89cecd7aaffdb9d63a2072fae064faa2c5b0a93c12
 size 4976698672

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd4ce9e4ed9d86334b47f18822649eb3f59b7a5fd11b4110414b589b19b2233e
+oid sha256:32689ebf53fcd70921122bdc80046eed42c996eb195c4560b866b942a53081e0
 size 4999802720

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b18151b5ab7ae4151110e5c07fedb062428d352acd2bb8b2f6d66b6153fcaa0
+oid sha256:9dd166601af186aa19f46d4004691f139017666113085746962395993f64b61d
 size 4915916176

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8aef27c1aab1f1cdcc79db0469c18cc56b552142b9f4a6a7c33f91ef67626901
+oid sha256:1db89e3fbb78fffeac7ec37b3b503ad4ec981c570400f0d5e503a2dcae74a888
 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": 15.873,
       "eval_steps_per_second": 0.556,
       "step": 626
+    },
+    {
+      "epoch": 2.012779552715655,
+      "grad_norm": 15.955204221662331,
+      "learning_rate": 1.8284023668639053e-07,
+      "logits/chosen": -1.7421875,
+      "logits/rejected": -1.734375,
+      "logps/chosen": -244.0,
+      "logps/rejected": -278.0,
+      "loss": 0.2415,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 0.1376953125,
+      "rewards/margins": 1.9296875,
+      "rewards/rejected": -1.796875,
+      "step": 630
+    },
+    {
+      "epoch": 2.0447284345047922,
+      "grad_norm": 14.058307718181862,
+      "learning_rate": 1.7692307692307693e-07,
+      "logits/chosen": -1.71875,
+      "logits/rejected": -1.7265625,
+      "logps/chosen": -237.0,
+      "logps/rejected": -280.0,
+      "loss": 0.1544,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": 0.21484375,
+      "rewards/margins": 2.53125,
+      "rewards/rejected": -2.3125,
+      "step": 640
+    },
+    {
+      "epoch": 2.07667731629393,
+      "grad_norm": 14.300114625147318,
+      "learning_rate": 1.710059171597633e-07,
+      "logits/chosen": -1.75,
+      "logits/rejected": -1.75,
+      "logps/chosen": -241.0,
+      "logps/rejected": -282.0,
+      "loss": 0.1729,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": 0.33203125,
+      "rewards/margins": 2.234375,
+      "rewards/rejected": -1.8984375,
+      "step": 650
+    },
+    {
+      "epoch": 2.108626198083067,
+      "grad_norm": 15.65574607331697,
+      "learning_rate": 1.650887573964497e-07,
+      "logits/chosen": -1.7578125,
+      "logits/rejected": -1.734375,
+      "logps/chosen": -238.0,
+      "logps/rejected": -290.0,
+      "loss": 0.1595,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": 0.015869140625,
+      "rewards/margins": 2.421875,
+      "rewards/rejected": -2.40625,
+      "step": 660
+    },
+    {
+      "epoch": 2.1405750798722045,
+      "grad_norm": 17.250707654114066,
+      "learning_rate": 1.591715976331361e-07,
+      "logits/chosen": -1.6796875,
+      "logits/rejected": -1.7265625,
+      "logps/chosen": -240.0,
+      "logps/rejected": -288.0,
+      "loss": 0.1731,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 0.1396484375,
+      "rewards/margins": 2.53125,
+      "rewards/rejected": -2.390625,
+      "step": 670
+    },
+    {
+      "epoch": 2.1725239616613417,
+      "grad_norm": 18.514625043103106,
+      "learning_rate": 1.5325443786982248e-07,
+      "logits/chosen": -1.75,
+      "logits/rejected": -1.703125,
+      "logps/chosen": -238.0,
+      "logps/rejected": -286.0,
+      "loss": 0.1608,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": 0.36328125,
+      "rewards/margins": 2.65625,
+      "rewards/rejected": -2.296875,
+      "step": 680
+    },
+    {
+      "epoch": 2.2044728434504792,
+      "grad_norm": 24.10831456497685,
+      "learning_rate": 1.4733727810650885e-07,
+      "logits/chosen": -1.6953125,
+      "logits/rejected": -1.703125,
+      "logps/chosen": -246.0,
+      "logps/rejected": -282.0,
+      "loss": 0.1953,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": 0.068359375,
+      "rewards/margins": 2.28125,
+      "rewards/rejected": -2.21875,
+      "step": 690
+    },
+    {
+      "epoch": 2.236421725239617,
+      "grad_norm": 17.181045102958997,
+      "learning_rate": 1.4142011834319526e-07,
+      "logits/chosen": -1.7109375,
+      "logits/rejected": -1.71875,
+      "logps/chosen": -235.0,
+      "logps/rejected": -284.0,
+      "loss": 0.1535,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": 0.259765625,
+      "rewards/margins": 2.5,
+      "rewards/rejected": -2.234375,
+      "step": 700
+    },
+    {
+      "epoch": 2.268370607028754,
+      "grad_norm": 14.135092040427887,
+      "learning_rate": 1.3550295857988164e-07,
+      "logits/chosen": -1.6875,
+      "logits/rejected": -1.75,
+      "logps/chosen": -235.0,
+      "logps/rejected": -280.0,
+      "loss": 0.154,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": 0.23046875,
+      "rewards/margins": 2.59375,
+      "rewards/rejected": -2.359375,
+      "step": 710
+    },
+    {
+      "epoch": 2.3003194888178915,
+      "grad_norm": 14.760186737903501,
+      "learning_rate": 1.2958579881656802e-07,
+      "logits/chosen": -1.7109375,
+      "logits/rejected": -1.71875,
+      "logps/chosen": -234.0,
+      "logps/rejected": -290.0,
+      "loss": 0.1606,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 0.265625,
+      "rewards/margins": 2.65625,
+      "rewards/rejected": -2.390625,
+      "step": 720
+    },
+    {
+      "epoch": 2.3322683706070286,
+      "grad_norm": 19.868109224808542,
+      "learning_rate": 1.2366863905325443e-07,
+      "logits/chosen": -1.7109375,
+      "logits/rejected": -1.7578125,
+      "logps/chosen": -235.0,
+      "logps/rejected": -282.0,
+      "loss": 0.1487,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": 0.267578125,
+      "rewards/margins": 2.625,
+      "rewards/rejected": -2.359375,
+      "step": 730
+    },
+    {
+      "epoch": 2.364217252396166,
+      "grad_norm": 23.28653194497905,
+      "learning_rate": 1.1775147928994082e-07,
+      "logits/chosen": -1.71875,
+      "logits/rejected": -1.7265625,
+      "logps/chosen": -244.0,
+      "logps/rejected": -286.0,
+      "loss": 0.1478,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": 0.10595703125,
+      "rewards/margins": 2.59375,
+      "rewards/rejected": -2.484375,
+      "step": 740
+    },
+    {
+      "epoch": 2.3961661341853033,
+      "grad_norm": 17.120801675488444,
+      "learning_rate": 1.1183431952662721e-07,
+      "logits/chosen": -1.71875,
+      "logits/rejected": -1.6796875,
+      "logps/chosen": -236.0,
+      "logps/rejected": -288.0,
+      "loss": 0.1446,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": 0.1015625,
+      "rewards/margins": 2.75,
+      "rewards/rejected": -2.65625,
+      "step": 750
+    },
+    {
+      "epoch": 2.428115015974441,
+      "grad_norm": 15.22339588033004,
+      "learning_rate": 1.059171597633136e-07,
+      "logits/chosen": -1.7265625,
+      "logits/rejected": -1.71875,
+      "logps/chosen": -239.0,
+      "logps/rejected": -280.0,
+      "loss": 0.1655,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": 0.1962890625,
+      "rewards/margins": 2.453125,
+      "rewards/rejected": -2.25,
+      "step": 760
+    },
+    {
+      "epoch": 2.460063897763578,
+      "grad_norm": 11.99984881863295,
+      "learning_rate": 1e-07,
+      "logits/chosen": -1.734375,
+      "logits/rejected": -1.7578125,
+      "logps/chosen": -232.0,
+      "logps/rejected": -296.0,
+      "loss": 0.1466,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": 0.10009765625,
+      "rewards/margins": 2.8125,
+      "rewards/rejected": -2.71875,
+      "step": 770
+    },
+    {
+      "epoch": 2.4920127795527156,
+      "grad_norm": 13.471810930026255,
+      "learning_rate": 9.408284023668639e-08,
+      "logits/chosen": -1.7109375,
+      "logits/rejected": -1.734375,
+      "logps/chosen": -242.0,
+      "logps/rejected": -286.0,
+      "loss": 0.1451,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": 0.2119140625,
+      "rewards/margins": 2.578125,
+      "rewards/rejected": -2.359375,
+      "step": 780
+    },
+    {
+      "epoch": 2.523961661341853,
+      "grad_norm": 25.459720363700047,
+      "learning_rate": 8.816568047337278e-08,
+      "logits/chosen": -1.71875,
+      "logits/rejected": -1.6875,
+      "logps/chosen": -241.0,
+      "logps/rejected": -300.0,
+      "loss": 0.1488,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": 0.142578125,
+      "rewards/margins": 2.796875,
+      "rewards/rejected": -2.640625,
+      "step": 790
+    },
+    {
+      "epoch": 2.5559105431309903,
+      "grad_norm": 18.20570925745819,
+      "learning_rate": 8.224852071005916e-08,
+      "logits/chosen": -1.765625,
+      "logits/rejected": -1.7265625,
+      "logps/chosen": -237.0,
+      "logps/rejected": -292.0,
+      "loss": 0.1676,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": 0.06298828125,
+      "rewards/margins": 2.796875,
+      "rewards/rejected": -2.734375,
+      "step": 800
+    },
+    {
+      "epoch": 2.587859424920128,
+      "grad_norm": 22.009878869215555,
+      "learning_rate": 7.633136094674555e-08,
+      "logits/chosen": -1.7421875,
+      "logits/rejected": -1.7265625,
+      "logps/chosen": -244.0,
+      "logps/rejected": -288.0,
+      "loss": 0.1575,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -0.03759765625,
+      "rewards/margins": 2.78125,
+      "rewards/rejected": -2.828125,
+      "step": 810
+    },
+    {
+      "epoch": 2.619808306709265,
+      "grad_norm": 11.203003537220331,
+      "learning_rate": 7.041420118343195e-08,
+      "logits/chosen": -1.71875,
+      "logits/rejected": -1.75,
+      "logps/chosen": -236.0,
+      "logps/rejected": -280.0,
+      "loss": 0.1623,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 0.032470703125,
+      "rewards/margins": 2.46875,
+      "rewards/rejected": -2.4375,
+      "step": 820
+    },
+    {
+      "epoch": 2.6517571884984026,
+      "grad_norm": 11.09178228981755,
+      "learning_rate": 6.449704142011835e-08,
+      "logits/chosen": -1.734375,
+      "logits/rejected": -1.7265625,
+      "logps/chosen": -245.0,
+      "logps/rejected": -300.0,
+      "loss": 0.1548,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": 0.0235595703125,
+      "rewards/margins": 3.078125,
+      "rewards/rejected": -3.046875,
+      "step": 830
+    },
+    {
+      "epoch": 2.68370607028754,
+      "grad_norm": 18.04056695002969,
+      "learning_rate": 5.857988165680473e-08,
+      "logits/chosen": -1.71875,
+      "logits/rejected": -1.71875,
+      "logps/chosen": -244.0,
+      "logps/rejected": -286.0,
+      "loss": 0.1733,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": 0.169921875,
+      "rewards/margins": 2.703125,
+      "rewards/rejected": -2.53125,
+      "step": 840
+    },
+    {
+      "epoch": 2.7156549520766773,
+      "grad_norm": 20.112810364895005,
+      "learning_rate": 5.266272189349112e-08,
+      "logits/chosen": -1.6953125,
+      "logits/rejected": -1.7265625,
+      "logps/chosen": -241.0,
+      "logps/rejected": -288.0,
+      "loss": 0.1534,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": 0.1796875,
+      "rewards/margins": 2.65625,
+      "rewards/rejected": -2.484375,
+      "step": 850
+    },
+    {
+      "epoch": 2.747603833865815,
+      "grad_norm": 15.351717469363905,
+      "learning_rate": 4.674556213017751e-08,
+      "logits/chosen": -1.703125,
+      "logits/rejected": -1.703125,
+      "logps/chosen": -240.0,
+      "logps/rejected": -284.0,
+      "loss": 0.1448,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": 0.1796875,
+      "rewards/margins": 2.671875,
+      "rewards/rejected": -2.484375,
+      "step": 860
+    },
+    {
+      "epoch": 2.779552715654952,
+      "grad_norm": 19.628185598163178,
+      "learning_rate": 4.082840236686391e-08,
+      "logits/chosen": -1.7421875,
+      "logits/rejected": -1.71875,
+      "logps/chosen": -236.0,
+      "logps/rejected": -282.0,
+      "loss": 0.1584,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 0.2373046875,
+      "rewards/margins": 2.703125,
+      "rewards/rejected": -2.46875,
+      "step": 870
+    },
+    {
+      "epoch": 2.8115015974440896,
+      "grad_norm": 18.902685630993297,
+      "learning_rate": 3.4911242603550294e-08,
+      "logits/chosen": -1.7578125,
+      "logits/rejected": -1.71875,
+      "logps/chosen": -242.0,
+      "logps/rejected": -282.0,
+      "loss": 0.1584,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": 0.1396484375,
+      "rewards/margins": 2.625,
+      "rewards/rejected": -2.484375,
+      "step": 880
+    },
+    {
+      "epoch": 2.8434504792332267,
+      "grad_norm": 14.629776336594917,
+      "learning_rate": 2.8994082840236687e-08,
+      "logits/chosen": -1.6953125,
+      "logits/rejected": -1.6953125,
+      "logps/chosen": -238.0,
+      "logps/rejected": -284.0,
+      "loss": 0.1549,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": 0.283203125,
+      "rewards/margins": 2.734375,
+      "rewards/rejected": -2.453125,
+      "step": 890
+    },
+    {
+      "epoch": 2.8753993610223643,
+      "grad_norm": 23.27853134409678,
+      "learning_rate": 2.3076923076923076e-08,
+      "logits/chosen": -1.7421875,
+      "logits/rejected": -1.71875,
+      "logps/chosen": -241.0,
+      "logps/rejected": -284.0,
+      "loss": 0.1677,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": 0.08251953125,
+      "rewards/margins": 2.5,
+      "rewards/rejected": -2.40625,
+      "step": 900
+    },
+    {
+      "epoch": 2.9073482428115014,
+      "grad_norm": 23.121981374950852,
+      "learning_rate": 1.7159763313609465e-08,
+      "logits/chosen": -1.7109375,
+      "logits/rejected": -1.7265625,
+      "logps/chosen": -237.0,
+      "logps/rejected": -282.0,
+      "loss": 0.1647,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 0.18359375,
+      "rewards/margins": 2.5625,
+      "rewards/rejected": -2.375,
+      "step": 910
+    },
+    {
+      "epoch": 2.939297124600639,
+      "grad_norm": 17.364099329669724,
+      "learning_rate": 1.1242603550295858e-08,
+      "logits/chosen": -1.7109375,
+      "logits/rejected": -1.6796875,
+      "logps/chosen": -242.0,
+      "logps/rejected": -298.0,
+      "loss": 0.1599,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": 0.10888671875,
+      "rewards/margins": 2.765625,
+      "rewards/rejected": -2.65625,
+      "step": 920
+    },
+    {
+      "epoch": 2.9712460063897765,
+      "grad_norm": 17.00765803212867,
+      "learning_rate": 5.325443786982248e-09,
+      "logits/chosen": -1.703125,
+      "logits/rejected": -1.71875,
+      "logps/chosen": -236.0,
+      "logps/rejected": -286.0,
+      "loss": 0.1526,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 0.058837890625,
+      "rewards/margins": 2.640625,
+      "rewards/rejected": -2.578125,
+      "step": 930
+    },
+    {
+      "epoch": 3.0,
+      "eval_logits/chosen": -1.6953125,
+      "eval_logits/rejected": -1.7265625,
+      "eval_logps/chosen": -243.0,
+      "eval_logps/rejected": -284.0,
+      "eval_loss": 0.5425000190734863,
+      "eval_rewards/accuracies": 0.75,
+      "eval_rewards/chosen": -0.65234375,
+      "eval_rewards/margins": 1.078125,
+      "eval_rewards/rejected": -1.734375,
+      "eval_runtime": 15.5349,
+      "eval_samples_per_second": 12.874,
+      "eval_steps_per_second": 0.451,
+      "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": {}
     }