Training in progress, epoch 10, checkpoint

last-checkpoint/global_step2172/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:f19b24231bc21aa4e4d0cd331778fe770e19ed409f4d000332d0aea0fe1b82af
+size 2506176112

last-checkpoint/global_step2172/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:dd8e4abed1d186a29fa43142708c035c2806592bc879f51cbef509d214d5fe9c
+size 2506176112

last-checkpoint/global_step2172/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:c46157adddaf9e20c84867b2b487178ecb31a90f997cc8dcf0e5594829c1cb90
+size 2506176112

last-checkpoint/global_step2172/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:269e943ec9884894109781afe0961afc97a7c91462ea7696ad59572dbd7eb8a7
+size 2506176112

last-checkpoint/global_step2172/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:ee23e1571ecf6591afd85ba14c2598e328b9411e71a221a2511ad7262e046a86
+size 2506176112

last-checkpoint/global_step2172/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:b68051918ee3bc0a1273054ff0bd61db4fd3392a597c905b97eff85c74f47ad0
+size 2506176112

last-checkpoint/global_step2172/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:c1aee53f20bc2ac5176e4f66ae345a4ed70bdc65904640f7dbce3c3886839dd9
+size 2506176112

last-checkpoint/global_step2172/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:f72c0f2ae4c692c31bd28496b8aa7eaf3f45a553af506b2f35cc005fc40fb4ce
+size 2506176112

last-checkpoint/global_step2172/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a16a1d252baf64ca0c1a09cd892d67246d9ae36576359c35bada80b3e49b897c
+size 85570

last-checkpoint/global_step2172/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0988b7567dbef8e7ec2a5567f8386a65baf2ea0a6658925019f6e2d60453fba1
+size 85506

last-checkpoint/global_step2172/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac7bfe5094d60d7e97ef0d3e66c2b45b8c06359caf0f8e9ef69149649cfe0490
+size 85506

last-checkpoint/global_step2172/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c62d76c8cd28224d79627d2f9d1a69f684cc60f84c9f43f368a3e7d5f5e228b
+size 85506

last-checkpoint/global_step2172/zero_pp_rank_4_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b34e266df3913f7af97f8ae3f18a4973f2ed31b11f443824e339f51fdf19b3c2
+size 85506

last-checkpoint/global_step2172/zero_pp_rank_5_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e6d2dd468cc766ae75e2be8de2dd3f67a65473c4f78136f21a0f5a344bd866c
+size 85506

last-checkpoint/global_step2172/zero_pp_rank_6_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce151848880d288bae33497aa4dec1579726f83c309cbfa28ea7589c735aae32
+size 85506

last-checkpoint/global_step2172/zero_pp_rank_7_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92bd6de8cef5db319837a21d363fc9143df2db7b6f7e918c680ab5398df77db0
+size 85506

last-checkpoint/latest

@@ -1 +1 @@
-global_step1975
+global_step2172

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7b38d08370373f75d0ead3a8dc90bdfbcde940100178a1e4d8444d44db03c6f
+oid sha256:34c2fdc6dc356fbd1457bd44a4aaf9ba031e2601ef060eb917fb58507b625392
 size 4945242264

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:258f456567db458691d028339987640e6c33e89da150b386c8f140c34d269bf8
+oid sha256:2855531bbf77a7757bdcaa0136c3f7ea44a90f0b68feedc3569b88783065fd99
 size 67121608

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb1165242405b17b3d6a8186ae61b13dcb1faa5a54320bebd74ef8d71b964bf7
+oid sha256:ba4c26c615bd5830d41566fab54dc69174be292761b34514b27fbe82b45b630b
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:562c262916c9997ec644c42fed9655ab28706b74fca20290ca921c4761d6a4b0
+oid sha256:60c761d7f9b90c29c2d348a1133fd39be52c65e6bee4c2d179f6a6e564eb3a40
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8d40f8118f513299624ded0a9bcf09778b961635615090409394d4f96f928f6
+oid sha256:ccab847cc956e055fd3f9dcce06898826d065211e945b83576c8d487f87c5469
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4391f924238a4cb855c4cbdc6d1a14954f785431c75997d05c7a4ee6615dae7
+oid sha256:0e5f1dbdcf6ec820c22fd1e4258fcd7af2a2bce65c480988d3f111aa574c9c06
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be7b19bb9543a16bf9f4cd96466ac581436f63070f5815f3a7ba57980608994f
+oid sha256:2a23184c3e806d2649776427d1da2c0c9137f9b23a84468f3bdd5bbc75f696c9
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97da4a1ede0a3e0f96411cacd5bfdf84d9355198f7aadc9bcb8be41122043f63
+oid sha256:382fc01b809542bf6f5e26742e3e19e80a1f189ac5de24cf8cd822e303916b83
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:544cb6421b975bd5d2b2360a4e666003794e6197ae654d2ad963cd6572a86ede
+oid sha256:5b178265c7d2ae07bff10b7312e5e49b9f5b4914c38969d2f64a6ca006296bca
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8d6eb32a23f3bef6262bbcb2eda724b2fd6f5e579969aa27c71a5971331722b
+oid sha256:668825a859126c4cf32afb883895c91004130b6aee02178736ca2840e5429ad0
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8981ddaa6502db230aa8c1752f9e3ae4127b4c9a3bafb82f8ac10be916d022b6
+oid sha256:450ea4feab6edb2c0a6bc824ba5e7d3864d6d5f94f04f20b34071a93ed9c22f2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.0,
+  "epoch": 10.99746835443038,
   "eval_steps": 100,
-  "global_step": 1975,
+  "global_step": 2172,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2977,6 +2977,306 @@
       "rewards/margins": 0.4955335259437561,
       "rewards/rejected": -0.3303041160106659,
       "step": 1970
+    },
+    {
+      "epoch": 10.025316455696203,
+      "grad_norm": 1813632.2248899846,
+      "learning_rate": 2.453776245691006e-07,
+      "logits/chosen": -1.164282202720642,
+      "logits/rejected": -1.4965863227844238,
+      "logps/chosen": -64.31637573242188,
+      "logps/rejected": -555.818115234375,
+      "loss": 20145.1469,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": 0.17363281548023224,
+      "rewards/margins": 0.4858935475349426,
+      "rewards/rejected": -0.3122607469558716,
+      "step": 1980
+    },
+    {
+      "epoch": 10.075949367088608,
+      "grad_norm": 1332924.3073966086,
+      "learning_rate": 2.4381071764337194e-07,
+      "logits/chosen": -0.629298746585846,
+      "logits/rejected": -0.301331102848053,
+      "logps/chosen": -63.670082092285156,
+      "logps/rejected": -531.6769409179688,
+      "loss": 19644.3969,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": 0.17206737399101257,
+      "rewards/margins": 0.46868830919265747,
+      "rewards/rejected": -0.29662084579467773,
+      "step": 1990
+    },
+    {
+      "epoch": 10.126582278481013,
+      "grad_norm": 1851357.970280298,
+      "learning_rate": 2.4224381071764335e-07,
+      "logits/chosen": -0.845658004283905,
+      "logits/rejected": -0.27886706590652466,
+      "logps/chosen": -64.26731872558594,
+      "logps/rejected": -551.6077270507812,
+      "loss": 19949.7859,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.16876797378063202,
+      "rewards/margins": 0.4869278073310852,
+      "rewards/rejected": -0.318159818649292,
+      "step": 2000
+    },
+    {
+      "epoch": 10.177215189873417,
+      "grad_norm": 711674.3296077562,
+      "learning_rate": 2.4067690379191476e-07,
+      "logits/chosen": -0.5739536285400391,
+      "logits/rejected": -0.18802312016487122,
+      "logps/chosen": -68.64383697509766,
+      "logps/rejected": -557.96484375,
+      "loss": 18812.7141,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.16457512974739075,
+      "rewards/margins": 0.48935467004776,
+      "rewards/rejected": -0.3247795104980469,
+      "step": 2010
+    },
+    {
+      "epoch": 10.227848101265822,
+      "grad_norm": 1174456.0466990366,
+      "learning_rate": 2.391099968661861e-07,
+      "logits/chosen": -1.7381559610366821,
+      "logits/rejected": -0.10386524349451065,
+      "logps/chosen": -62.054725646972656,
+      "logps/rejected": -570.2944946289062,
+      "loss": 19933.8734,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.17416052520275116,
+      "rewards/margins": 0.515259861946106,
+      "rewards/rejected": -0.3410993218421936,
+      "step": 2020
+    },
+    {
+      "epoch": 10.278481012658228,
+      "grad_norm": 1096601.381122318,
+      "learning_rate": 2.375430899404575e-07,
+      "logits/chosen": -0.8541361093521118,
+      "logits/rejected": -0.3781866133213043,
+      "logps/chosen": -56.479164123535156,
+      "logps/rejected": -554.1986694335938,
+      "loss": 19863.0656,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": 0.17042097449302673,
+      "rewards/margins": 0.4970123767852783,
+      "rewards/rejected": -0.3265914022922516,
+      "step": 2030
+    },
+    {
+      "epoch": 10.329113924050633,
+      "grad_norm": 840837.174069809,
+      "learning_rate": 2.3597618301472892e-07,
+      "logits/chosen": -1.694748878479004,
+      "logits/rejected": -1.400233268737793,
+      "logps/chosen": -75.36106872558594,
+      "logps/rejected": -590.9649047851562,
+      "loss": 19475.8531,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.1772707998752594,
+      "rewards/margins": 0.5156514644622803,
+      "rewards/rejected": -0.33838069438934326,
+      "step": 2040
+    },
+    {
+      "epoch": 10.379746835443038,
+      "grad_norm": 803470.3932805886,
+      "learning_rate": 2.344092760890003e-07,
+      "logits/chosen": -1.5708272457122803,
+      "logits/rejected": -1.7595367431640625,
+      "logps/chosen": -67.97745513916016,
+      "logps/rejected": -574.4043579101562,
+      "loss": 20348.9719,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.1695125252008438,
+      "rewards/margins": 0.5006899237632751,
+      "rewards/rejected": -0.33117741346359253,
+      "step": 2050
+    },
+    {
+      "epoch": 10.430379746835444,
+      "grad_norm": 1004663.9694340345,
+      "learning_rate": 2.328423691632717e-07,
+      "logits/chosen": -1.962457299232483,
+      "logits/rejected": -1.3877923488616943,
+      "logps/chosen": -68.37916564941406,
+      "logps/rejected": -552.3621826171875,
+      "loss": 19908.175,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.17361022531986237,
+      "rewards/margins": 0.4852239489555359,
+      "rewards/rejected": -0.31161370873451233,
+      "step": 2060
+    },
+    {
+      "epoch": 10.481012658227849,
+      "grad_norm": 907359.5128728322,
+      "learning_rate": 2.3127546223754308e-07,
+      "logits/chosen": -0.9135034680366516,
+      "logits/rejected": -0.6688288450241089,
+      "logps/chosen": -66.34752655029297,
+      "logps/rejected": -564.5549926757812,
+      "loss": 19321.1625,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": 0.17101381719112396,
+      "rewards/margins": 0.49828824400901794,
+      "rewards/rejected": -0.3272744417190552,
+      "step": 2070
+    },
+    {
+      "epoch": 10.531645569620252,
+      "grad_norm": 846691.3768602766,
+      "learning_rate": 2.2970855531181446e-07,
+      "logits/chosen": -0.16942422091960907,
+      "logits/rejected": 0.07732643932104111,
+      "logps/chosen": -70.53272247314453,
+      "logps/rejected": -561.4410400390625,
+      "loss": 20015.3156,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": 0.16945675015449524,
+      "rewards/margins": 0.4873596131801605,
+      "rewards/rejected": -0.31790289282798767,
+      "step": 2080
+    },
+    {
+      "epoch": 10.582278481012658,
+      "grad_norm": 1071818.197184184,
+      "learning_rate": 2.2814164838608585e-07,
+      "logits/chosen": -3.7376797199249268,
+      "logits/rejected": -3.6469883918762207,
+      "logps/chosen": -74.2595443725586,
+      "logps/rejected": -581.4434814453125,
+      "loss": 19872.15,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": 0.17747794091701508,
+      "rewards/margins": 0.5011757612228394,
+      "rewards/rejected": -0.3236978054046631,
+      "step": 2090
+    },
+    {
+      "epoch": 10.632911392405063,
+      "grad_norm": 1004256.8801454039,
+      "learning_rate": 2.2657474146035723e-07,
+      "logits/chosen": -3.6712310314178467,
+      "logits/rejected": -2.93229603767395,
+      "logps/chosen": -71.2375259399414,
+      "logps/rejected": -567.6956787109375,
+      "loss": 19287.7531,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": 0.17674970626831055,
+      "rewards/margins": 0.4991089403629303,
+      "rewards/rejected": -0.322359174489975,
+      "step": 2100
+    },
+    {
+      "epoch": 10.683544303797468,
+      "grad_norm": 1106280.1198113484,
+      "learning_rate": 2.2500783453462862e-07,
+      "logits/chosen": -0.8213077783584595,
+      "logits/rejected": 0.14719510078430176,
+      "logps/chosen": -63.996498107910156,
+      "logps/rejected": -572.0599975585938,
+      "loss": 19310.0187,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": 0.17046719789505005,
+      "rewards/margins": 0.5157285928726196,
+      "rewards/rejected": -0.34526145458221436,
+      "step": 2110
+    },
+    {
+      "epoch": 10.734177215189874,
+      "grad_norm": 1464811.168383667,
+      "learning_rate": 2.234409276089e-07,
+      "logits/chosen": -0.11996922641992569,
+      "logits/rejected": 0.22597141563892365,
+      "logps/chosen": -76.11662292480469,
+      "logps/rejected": -563.3325805664062,
+      "loss": 19843.4688,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": 0.16797539591789246,
+      "rewards/margins": 0.4910767078399658,
+      "rewards/rejected": -0.32310131192207336,
+      "step": 2120
+    },
+    {
+      "epoch": 10.784810126582279,
+      "grad_norm": 1138818.9289973595,
+      "learning_rate": 2.218740206831714e-07,
+      "logits/chosen": -1.5511647462844849,
+      "logits/rejected": -0.5638203620910645,
+      "logps/chosen": -54.634178161621094,
+      "logps/rejected": -540.9115600585938,
+      "loss": 19217.1797,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.16898050904273987,
+      "rewards/margins": 0.4923567771911621,
+      "rewards/rejected": -0.32337623834609985,
+      "step": 2130
+    },
+    {
+      "epoch": 10.835443037974684,
+      "grad_norm": 927204.123761474,
+      "learning_rate": 2.203071137574428e-07,
+      "logits/chosen": -0.11952924728393555,
+      "logits/rejected": 0.11829443275928497,
+      "logps/chosen": -68.7413101196289,
+      "logps/rejected": -549.9212036132812,
+      "loss": 19664.7969,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.16766998171806335,
+      "rewards/margins": 0.4846928119659424,
+      "rewards/rejected": -0.31702274084091187,
+      "step": 2140
+    },
+    {
+      "epoch": 10.886075949367088,
+      "grad_norm": 987326.8653252205,
+      "learning_rate": 2.187402068317142e-07,
+      "logits/chosen": -0.7956012487411499,
+      "logits/rejected": -0.13277845084667206,
+      "logps/chosen": -66.15580749511719,
+      "logps/rejected": -539.9743041992188,
+      "loss": 19319.2359,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": 0.16284069418907166,
+      "rewards/margins": 0.47170519828796387,
+      "rewards/rejected": -0.3088645040988922,
+      "step": 2150
+    },
+    {
+      "epoch": 10.936708860759493,
+      "grad_norm": 1490559.10150877,
+      "learning_rate": 2.1717329990598557e-07,
+      "logits/chosen": 0.23329691588878632,
+      "logits/rejected": 0.3798617720603943,
+      "logps/chosen": -65.20997619628906,
+      "logps/rejected": -566.1799926757812,
+      "loss": 18358.2687,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.15990014374256134,
+      "rewards/margins": 0.502142608165741,
+      "rewards/rejected": -0.34224241971969604,
+      "step": 2160
+    },
+    {
+      "epoch": 10.987341772151899,
+      "grad_norm": 910221.5561234908,
+      "learning_rate": 2.1560639298025696e-07,
+      "logits/chosen": -1.0350775718688965,
+      "logits/rejected": -0.4896017909049988,
+      "logps/chosen": -80.80205535888672,
+      "logps/rejected": -605.629150390625,
+      "loss": 19122.5234,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.17700453102588654,
+      "rewards/margins": 0.5280236601829529,
+      "rewards/rejected": -0.35101914405822754,
+      "step": 2170
     }
   ],
   "logging_steps": 10,