Training in progress, epoch 28, checkpoint

last-checkpoint/global_step5718/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:bd38c8d53cef6a27f96f7b421d3d5acb19ce05f445d6d62035a1e97e79f3f627
+size 2506176112

last-checkpoint/global_step5718/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c89a6cfa9861549dfcd1590200365ce0c25a15d698599c5baa2997fa1792463
+size 2506176112

last-checkpoint/global_step5718/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fdba19db1d418e7b2ee177ec5fe1c0e2ccf008a0275c8f937268506bce9f05d
+size 2506176112

last-checkpoint/global_step5718/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42cee2fd79cd1d6b6c3a0ee111ad23945fdc848b6f088f9fc721f86c321c5fbc
+size 2506176112

last-checkpoint/global_step5718/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f93875499f8ce0120e6376255ad48ae9397e785acb633fde389a6b2ac49e11c
+size 2506176112

last-checkpoint/global_step5718/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b49d8c24ca0c52538af8feffe99d3278097e67a82b3dfb164a19abf75c1c5dd
+size 2506176112

last-checkpoint/global_step5718/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e093b6caed17faa9268d407698a34ff3a5353d8f6b104dada895df571c3a25e
+size 2506176112

last-checkpoint/global_step5718/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74f30ead704a9cc1b7b066f4a45d9736525415f9a92a8c31f4bac15e7e7b9763
+size 2506176112

last-checkpoint/global_step5718/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8252e479868a5e0a4dfa749f80a1e8d524dd4c975c140119cfbd5abd9bf8afec
+size 85570

last-checkpoint/global_step5718/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feeb32706d269794adf5b59514242cb1708a15909b313f060f2aef30bae63262
+size 85506

last-checkpoint/global_step5718/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:335cd955b91a12c7f066b1d5d2dbb9ecb39d21ac0b6de5e5b7fe280032ce5a7e
+size 85506

last-checkpoint/global_step5718/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db19ca119d186937dfec156f64ed5185ab10005181a4f3d860a9d55af32a8feb
+size 85506

last-checkpoint/global_step5718/zero_pp_rank_4_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14a134d7d307b5c30e4ad6723ea24295f2a5c589def33cb8ff5981d5b9632b0b
+size 85506

last-checkpoint/global_step5718/zero_pp_rank_5_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5101f24995338e1d56a12ada0fbc5ad6e72c43db79ad0c51f12b9255a2075ca0
+size 85506

last-checkpoint/global_step5718/zero_pp_rank_6_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fdccfa685649f28110d93e0604078495d43dc0a91bcf95d6794dfa8a6409447
+size 85506

last-checkpoint/global_step5718/zero_pp_rank_7_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38dcdf96ca2a336a1bbe49a3b62871afbdf6b077d44e4602872b45e38fcfb1b4
+size 85506

last-checkpoint/latest

@@ -1 +1 @@
-global_step5521
+global_step5718

last-checkpoint/model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49f4a9ae06898314b6bbf8ad9fca6ca16dea158bd29ecc0506863d601b8345f4
+oid sha256:cfa3379a77e192ab0af64fe78334db958cf6214addb3b4fbbc67569fb9f2e836
 size 4945242264

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4832308f86af667638feea3c3365de459978e8c0f49e3d367cf4d5379875a12f
+oid sha256:c217d7738abb0675dccca5614343dba054b625a983adb5b66bb33a2cf128b5c4
 size 67121608

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:038329a940174c7998542fe9a3c903ee0c21d0a2351959a1cb53ac9af3988f89
+oid sha256:a205f64c86d241517037857e791fc7cdcfd1b2d8a26ca46ff4e6430fc9491c64
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc2eb62cd1e31d2c95a28eaadd97a496b27751983378626efc3ee2a53ae743ff
+oid sha256:384e04a3f342b13aa2aff82b03d67994ff48a7b6e7d90ad53291b0ccf1124755
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c76f1ee6b7bfb2e7a6ca68f028fe40297bc56fa8287959be7a51545af2a824b
+oid sha256:c75af15b2dde4bfa82f45cc3b48588a123bca20dd4b565a0312d5c1198d8bca9
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e4716e0a98e24ecef0261fa45d53aa531ce14f99b4992682e0257f7c483a80d
+oid sha256:8162e1d617d2045c999376967bb33455e9055c2882d00e9e6c3e5639106c7cf2
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:732644bf9682f11fe70f041a2575d5822769847a3b56320e6cfdbd3914eb98f9
+oid sha256:37df018beaaf1bcb0a0451dcfd03f257c34b245315c9d5243bad309614abb972
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3d90978ff8f9057d8587ec1258de11f4d5531805002e65d952f5725b93f51be
+oid sha256:bc45f95eb705f82fae244f5f5bb1d1d060492c8b55aba2aa58162687e28952bc
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a013a277003a33e8bb2418ae66c1488282f502fc920260b5fc9f337843415ab2
+oid sha256:d8ed548560db42b0406ce39f0d4bce5fac64c200cc3ab9248f1dd703dde9dfef
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9f8887e423cbfbb140f966733dae63123515ed5345b3e075eb892b0646282c8
+oid sha256:865e7aa49ec74e2e8e5ffbc2b62c9edb6308476119fe3e77f2fe29961dd5deaf
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2d39cfa3808e402183de5c305fcd5a81f2c9ffede37076a3856931095792cc0
+oid sha256:3921aadd9f9af170d702817ed4b4c15515108ff8717773c58f7ba3567a43d1be
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 28.0,
+  "epoch": 28.99746835443038,
   "eval_steps": 100,
-  "global_step": 5521,
+  "global_step": 5718,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8302,6 +8302,291 @@
       "rewards/margins": 0.5627579689025879,
       "rewards/rejected": -0.3508843779563904,
       "step": 5520
+    },
+    {
+      "epoch": 28.045569620253165,
+      "grad_norm": 221196.22582529782,
+      "learning_rate": 1.2237543089940458e-07,
+      "logits/chosen": -2.0594754219055176,
+      "logits/rejected": -0.8701013326644897,
+      "logps/chosen": -27.682659149169922,
+      "logps/rejected": -595.9862060546875,
+      "loss": 12458.1609,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.21054939925670624,
+      "rewards/margins": 0.5732256174087524,
+      "rewards/rejected": -0.362676203250885,
+      "step": 5530
+    },
+    {
+      "epoch": 28.09620253164557,
+      "grad_norm": 270569.55775822,
+      "learning_rate": 1.2159197743654026e-07,
+      "logits/chosen": -1.7393264770507812,
+      "logits/rejected": -1.1281194686889648,
+      "logps/chosen": -24.0075626373291,
+      "logps/rejected": -583.3763427734375,
+      "loss": 12198.0859,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.20713207125663757,
+      "rewards/margins": 0.5608252286911011,
+      "rewards/rejected": -0.35369327664375305,
+      "step": 5540
+    },
+    {
+      "epoch": 28.146835443037975,
+      "grad_norm": 294202.9420634267,
+      "learning_rate": 1.2080852397367596e-07,
+      "logits/chosen": -1.1881496906280518,
+      "logits/rejected": -1.9830278158187866,
+      "logps/chosen": -27.52215003967285,
+      "logps/rejected": -571.5521240234375,
+      "loss": 12035.3297,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": 0.198753222823143,
+      "rewards/margins": 0.5402897596359253,
+      "rewards/rejected": -0.34153658151626587,
+      "step": 5550
+    },
+    {
+      "epoch": 28.19746835443038,
+      "grad_norm": 250256.82251298483,
+      "learning_rate": 1.2002507051081164e-07,
+      "logits/chosen": -2.069603443145752,
+      "logits/rejected": -1.1806148290634155,
+      "logps/chosen": -32.80065155029297,
+      "logps/rejected": -584.74169921875,
+      "loss": 12394.9164,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.21380552649497986,
+      "rewards/margins": 0.5591468811035156,
+      "rewards/rejected": -0.345341295003891,
+      "step": 5560
+    },
+    {
+      "epoch": 28.248101265822786,
+      "grad_norm": 295332.47087175207,
+      "learning_rate": 1.1924161704794735e-07,
+      "logits/chosen": -1.0471255779266357,
+      "logits/rejected": -0.4857943654060364,
+      "logps/chosen": -21.058979034423828,
+      "logps/rejected": -572.4304809570312,
+      "loss": 12514.1922,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": 0.1976846158504486,
+      "rewards/margins": 0.548615574836731,
+      "rewards/rejected": -0.35093095898628235,
+      "step": 5570
+    },
+    {
+      "epoch": 28.29873417721519,
+      "grad_norm": 206143.0104728106,
+      "learning_rate": 1.1845816358508304e-07,
+      "logits/chosen": -2.556028366088867,
+      "logits/rejected": -1.9551620483398438,
+      "logps/chosen": -35.4798698425293,
+      "logps/rejected": -586.085693359375,
+      "loss": 12969.0906,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": 0.20620682835578918,
+      "rewards/margins": 0.5480517148971558,
+      "rewards/rejected": -0.34184494614601135,
+      "step": 5580
+    },
+    {
+      "epoch": 28.349367088607593,
+      "grad_norm": 264961.57508088043,
+      "learning_rate": 1.1767471012221873e-07,
+      "logits/chosen": -1.3203023672103882,
+      "logits/rejected": -0.41819173097610474,
+      "logps/chosen": -35.34379959106445,
+      "logps/rejected": -582.7780151367188,
+      "loss": 11659.4484,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": 0.21271836757659912,
+      "rewards/margins": 0.5540838837623596,
+      "rewards/rejected": -0.3413654863834381,
+      "step": 5590
+    },
+    {
+      "epoch": 28.4,
+      "grad_norm": 475056.8558156038,
+      "learning_rate": 1.1689125665935443e-07,
+      "logits/chosen": 0.2806483507156372,
+      "logits/rejected": 0.8025129437446594,
+      "logps/chosen": -32.23934555053711,
+      "logps/rejected": -571.2871704101562,
+      "loss": 12715.6078,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": 0.20215098559856415,
+      "rewards/margins": 0.5371149778366089,
+      "rewards/rejected": -0.33496397733688354,
+      "step": 5600
+    },
+    {
+      "epoch": 28.450632911392404,
+      "grad_norm": 197134.08463352287,
+      "learning_rate": 1.1610780319649012e-07,
+      "logits/chosen": -0.42449599504470825,
+      "logits/rejected": 0.20755800604820251,
+      "logps/chosen": -30.612218856811523,
+      "logps/rejected": -578.2881469726562,
+      "loss": 12352.6281,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": 0.2100987732410431,
+      "rewards/margins": 0.5525861978530884,
+      "rewards/rejected": -0.34248748421669006,
+      "step": 5610
+    },
+    {
+      "epoch": 28.50126582278481,
+      "grad_norm": 345771.22083863505,
+      "learning_rate": 1.1532434973362581e-07,
+      "logits/chosen": -1.5660457611083984,
+      "logits/rejected": -0.7327693700790405,
+      "logps/chosen": -22.58321762084961,
+      "logps/rejected": -566.7658081054688,
+      "loss": 11851.4547,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": 0.19859129190444946,
+      "rewards/margins": 0.5416545271873474,
+      "rewards/rejected": -0.3430632948875427,
+      "step": 5620
+    },
+    {
+      "epoch": 28.551898734177215,
+      "grad_norm": 168585.12783774585,
+      "learning_rate": 1.145408962707615e-07,
+      "logits/chosen": -0.2972283363342285,
+      "logits/rejected": -0.3674158453941345,
+      "logps/chosen": -29.131546020507812,
+      "logps/rejected": -597.9761962890625,
+      "loss": 11512.6836,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.21312180161476135,
+      "rewards/margins": 0.5691269040107727,
+      "rewards/rejected": -0.35600510239601135,
+      "step": 5630
+    },
+    {
+      "epoch": 28.60253164556962,
+      "grad_norm": 208909.02036407648,
+      "learning_rate": 1.137574428078972e-07,
+      "logits/chosen": -1.0681560039520264,
+      "logits/rejected": -0.39094457030296326,
+      "logps/chosen": -36.012596130371094,
+      "logps/rejected": -586.0516357421875,
+      "loss": 12808.1297,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": 0.20493356883525848,
+      "rewards/margins": 0.5560083389282227,
+      "rewards/rejected": -0.3510746955871582,
+      "step": 5640
+    },
+    {
+      "epoch": 28.653164556962025,
+      "grad_norm": 311846.42372199957,
+      "learning_rate": 1.1297398934503289e-07,
+      "logits/chosen": 0.5105953216552734,
+      "logits/rejected": 1.009169101715088,
+      "logps/chosen": -27.007156372070312,
+      "logps/rejected": -599.7515258789062,
+      "loss": 11991.1812,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.21386167407035828,
+      "rewards/margins": 0.572094202041626,
+      "rewards/rejected": -0.3582325577735901,
+      "step": 5650
+    },
+    {
+      "epoch": 28.70379746835443,
+      "grad_norm": 268717.3291778612,
+      "learning_rate": 1.1219053588216858e-07,
+      "logits/chosen": -0.8255645036697388,
+      "logits/rejected": -0.8527682423591614,
+      "logps/chosen": -21.579692840576172,
+      "logps/rejected": -585.7736206054688,
+      "loss": 12543.1672,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.2072766274213791,
+      "rewards/margins": 0.5643941760063171,
+      "rewards/rejected": -0.35711759328842163,
+      "step": 5660
+    },
+    {
+      "epoch": 28.754430379746836,
+      "grad_norm": 251846.43966430755,
+      "learning_rate": 1.1140708241930429e-07,
+      "logits/chosen": -1.6031732559204102,
+      "logits/rejected": -0.6178330779075623,
+      "logps/chosen": -30.777385711669922,
+      "logps/rejected": -578.4786376953125,
+      "loss": 12538.3711,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": 0.20804066956043243,
+      "rewards/margins": 0.5539838075637817,
+      "rewards/rejected": -0.3459431827068329,
+      "step": 5670
+    },
+    {
+      "epoch": 28.80506329113924,
+      "grad_norm": 362284.87054599967,
+      "learning_rate": 1.1062362895643998e-07,
+      "logits/chosen": -0.6538245677947998,
+      "logits/rejected": -0.3702305555343628,
+      "logps/chosen": -26.261932373046875,
+      "logps/rejected": -577.5454711914062,
+      "loss": 13020.9297,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.20354709029197693,
+      "rewards/margins": 0.5529359579086304,
+      "rewards/rejected": -0.34938886761665344,
+      "step": 5680
+    },
+    {
+      "epoch": 28.855696202531647,
+      "grad_norm": 205761.31564795828,
+      "learning_rate": 1.0984017549357568e-07,
+      "logits/chosen": -2.4821999073028564,
+      "logits/rejected": -2.7491514682769775,
+      "logps/chosen": -33.985538482666016,
+      "logps/rejected": -588.4347534179688,
+      "loss": 12498.5609,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.2070481777191162,
+      "rewards/margins": 0.5542899370193481,
+      "rewards/rejected": -0.34724172949790955,
+      "step": 5690
+    },
+    {
+      "epoch": 28.906329113924052,
+      "grad_norm": 269249.39255954395,
+      "learning_rate": 1.0905672203071137e-07,
+      "logits/chosen": 0.24643035233020782,
+      "logits/rejected": 0.39688020944595337,
+      "logps/chosen": -22.365093231201172,
+      "logps/rejected": -572.4009399414062,
+      "loss": 12145.2008,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.20018497109413147,
+      "rewards/margins": 0.5481060147285461,
+      "rewards/rejected": -0.3479210138320923,
+      "step": 5700
+    },
+    {
+      "epoch": 28.956962025316457,
+      "grad_norm": 274939.7399900873,
+      "learning_rate": 1.0827326856784706e-07,
+      "logits/chosen": 0.24328431487083435,
+      "logits/rejected": 0.056040357798337936,
+      "logps/chosen": -27.859899520874023,
+      "logps/rejected": -582.8697509765625,
+      "loss": 12038.6203,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.20646706223487854,
+      "rewards/margins": 0.5581387281417847,
+      "rewards/rejected": -0.35167163610458374,
+      "step": 5710
     }
   ],
   "logging_steps": 10,