Training in progress, step 4100, checkpoint

last-checkpoint/optimizer_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f71094bbdfc86adfd0e4cd2e8f5cdfb8fb23b572bb3a7057c440f6642446286
+oid sha256:220e027271de2a6bca981d834f7395712314cca7c02305414cabfd4d907394b9
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:736ae73446c7e73991a7aa108d16f2c8f63b592f7f5d413749f3af923966fec0
+oid sha256:bdbf1466ca8cb6da23adffc3a9d441c4bf270030830776db3495411bf30dde2f
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a007d5bd7b277ed837e6b774fb21cad86605b6c2792109248722b392b77832d
+oid sha256:9d3cf736efca2ca5afb1ff734e3323f4737586324e573bcbdd4de927a5c7ac55
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e1313230694e7b018626eaab5bf74c5d71a02b86715f81d73865bbcc736e40a
+oid sha256:2907c9ceec430a743d8b5958c64bfded961bad1ebc5adcc439791c1a8c5fabc1
 size 13990904

last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04fd87942acc967b13a2cc97c213f6f023d8ea6c8f3b86e6aba951694cc60c03
+oid sha256:244f3efa7b67eb8bfc69c27fd23fa7caf5df1ced1f5c68de887c20baed02d7d4
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49f59f1be65a4b38e21ecba3d35e406476ba830c595929ef81315e36b323cf6f
+oid sha256:3e0063b190aace5bb7066fe5af51b050726c6dd3f5ed9a705bafd99f705a7154
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:087042691eef9c4937a2a163dd265167dd430b22bc891da7ae68b04dc3a8fb4e
+oid sha256:f2e9b062654cef9d071574ce1f75c51207902afc100de8eac5cb9d2e7fc2d72c
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00e4e3b89275aa38142e282f0acdc1852aad9201daa9db60ce74aab349da8e8c
+oid sha256:ff076e913b796296d8e60692fb01bd0e5a47c37332d1e793139546524a17f2f2
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:968955cb220e1ae35f6916db98ca0953528bc0b0580cc44027f9ff6c72b4d73d
+oid sha256:d82484635db9812eabc0d39f06f2ec1f3979cc8fc569f5b5bf6af51fa1296527
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fb9a66187901116c7ce192a0e06464a83baf7568d57dbf4446c504791ba1fd8
+oid sha256:e53e615308f52d8a3aedca989efd3d7a8b7e3129b0574033d873a81eb8fe7100
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b9fba2d1979e177b2e0a38c01cf410aa93382c082ecaee4a451ebf16fb9a486
+oid sha256:85b7fff2bf153b90d55c1a511523f13696e0829e5856e5a91f60cabef77f1b1a
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ff18c4e56da8055bac638cd3b97b907f1f88d39a60cc2fabc24e9a912f54674
+oid sha256:5148574490cb8bfec7e7410f8617f9a9ed3d76de73eae4e9fab71b9fcf30f0c2
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:805a5c79a44e78d3f6e0de6b84342b4362da541588b026e318ba0295379db9a1
+oid sha256:234b226f222d337a0922e7bd10ea7cc9e5627a84afb4207e01b9d2e67601fc17
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5901881224640354,
+  "epoch": 0.6049428255256363,
   "eval_steps": 20,
-  "global_step": 4000,
+  "global_step": 4100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30419,6 +30419,766 @@
       "eval_samples_per_second": 5.999,
       "eval_steps_per_second": 0.206,
       "step": 4000
+    },
+    {
+      "epoch": 0.5903356694946514,
+      "grad_norm": 1.614266276359558,
+      "learning_rate": 8.595857976752734e-06,
+      "loss": 0.0638,
+      "step": 4001
+    },
+    {
+      "epoch": 0.5904832165252675,
+      "grad_norm": 2.430948495864868,
+      "learning_rate": 8.590758198633071e-06,
+      "loss": 0.0608,
+      "step": 4002
+    },
+    {
+      "epoch": 0.5906307635558834,
+      "grad_norm": 1.02809476852417,
+      "learning_rate": 8.585658794424188e-06,
+      "loss": 0.0369,
+      "step": 4003
+    },
+    {
+      "epoch": 0.5907783105864994,
+      "grad_norm": 1.6501526832580566,
+      "learning_rate": 8.580559765479092e-06,
+      "loss": 0.0464,
+      "step": 4004
+    },
+    {
+      "epoch": 0.5909258576171155,
+      "grad_norm": 1.7904622554779053,
+      "learning_rate": 8.575461113150708e-06,
+      "loss": 0.0353,
+      "step": 4005
+    },
+    {
+      "epoch": 0.5910734046477315,
+      "grad_norm": 1.6023961305618286,
+      "learning_rate": 8.570362838791843e-06,
+      "loss": 0.0531,
+      "step": 4006
+    },
+    {
+      "epoch": 0.5912209516783474,
+      "grad_norm": 2.241295337677002,
+      "learning_rate": 8.56526494375521e-06,
+      "loss": 0.0251,
+      "step": 4007
+    },
+    {
+      "epoch": 0.5913684987089635,
+      "grad_norm": 1.1265102624893188,
+      "learning_rate": 8.560167429393416e-06,
+      "loss": 0.0591,
+      "step": 4008
+    },
+    {
+      "epoch": 0.5915160457395795,
+      "grad_norm": 0.996741771697998,
+      "learning_rate": 8.555070297058985e-06,
+      "loss": 0.0219,
+      "step": 4009
+    },
+    {
+      "epoch": 0.5916635927701955,
+      "grad_norm": 2.147981882095337,
+      "learning_rate": 8.549973548104316e-06,
+      "loss": 0.0758,
+      "step": 4010
+    },
+    {
+      "epoch": 0.5918111398008115,
+      "grad_norm": 4.8437604904174805,
+      "learning_rate": 8.544877183881724e-06,
+      "loss": 0.0822,
+      "step": 4011
+    },
+    {
+      "epoch": 0.5919586868314275,
+      "grad_norm": 2.6284608840942383,
+      "learning_rate": 8.53978120574341e-06,
+      "loss": 0.0591,
+      "step": 4012
+    },
+    {
+      "epoch": 0.5921062338620435,
+      "grad_norm": 2.1678919792175293,
+      "learning_rate": 8.534685615041479e-06,
+      "loss": 0.0597,
+      "step": 4013
+    },
+    {
+      "epoch": 0.5922537808926596,
+      "grad_norm": 3.9284839630126953,
+      "learning_rate": 8.529590413127934e-06,
+      "loss": 0.0968,
+      "step": 4014
+    },
+    {
+      "epoch": 0.5924013279232755,
+      "grad_norm": 1.429666519165039,
+      "learning_rate": 8.524495601354674e-06,
+      "loss": 0.0253,
+      "step": 4015
+    },
+    {
+      "epoch": 0.5925488749538915,
+      "grad_norm": 1.6633669137954712,
+      "learning_rate": 8.51940118107349e-06,
+      "loss": 0.0599,
+      "step": 4016
+    },
+    {
+      "epoch": 0.5926964219845076,
+      "grad_norm": 1.4551674127578735,
+      "learning_rate": 8.514307153636078e-06,
+      "loss": 0.031,
+      "step": 4017
+    },
+    {
+      "epoch": 0.5928439690151236,
+      "grad_norm": 1.0635619163513184,
+      "learning_rate": 8.509213520394012e-06,
+      "loss": 0.0334,
+      "step": 4018
+    },
+    {
+      "epoch": 0.5929915160457396,
+      "grad_norm": 1.568542242050171,
+      "learning_rate": 8.504120282698786e-06,
+      "loss": 0.0523,
+      "step": 4019
+    },
+    {
+      "epoch": 0.5931390630763556,
+      "grad_norm": 1.6317611932754517,
+      "learning_rate": 8.499027441901774e-06,
+      "loss": 0.0686,
+      "step": 4020
+    },
+    {
+      "epoch": 0.5931390630763556,
+      "eval_accuracy": 0.975397973950796,
+      "eval_f1": 0.9580246913580247,
+      "eval_loss": 0.058240365236997604,
+      "eval_precision": 0.9748743718592965,
+      "eval_recall": 0.941747572815534,
+      "eval_runtime": 50.1337,
+      "eval_samples_per_second": 5.804,
+      "eval_steps_per_second": 0.199,
+      "step": 4020
+    },
+    {
+      "epoch": 0.5932866101069716,
+      "grad_norm": 2.486640453338623,
+      "learning_rate": 8.493934999354243e-06,
+      "loss": 0.0781,
+      "step": 4021
+    },
+    {
+      "epoch": 0.5934341571375876,
+      "grad_norm": 1.7704969644546509,
+      "learning_rate": 8.488842956407361e-06,
+      "loss": 0.0276,
+      "step": 4022
+    },
+    {
+      "epoch": 0.5935817041682037,
+      "grad_norm": 3.37807559967041,
+      "learning_rate": 8.483751314412187e-06,
+      "loss": 0.0469,
+      "step": 4023
+    },
+    {
+      "epoch": 0.5937292511988196,
+      "grad_norm": 1.8829337358474731,
+      "learning_rate": 8.478660074719678e-06,
+      "loss": 0.0549,
+      "step": 4024
+    },
+    {
+      "epoch": 0.5938767982294356,
+      "grad_norm": 3.660616159439087,
+      "learning_rate": 8.473569238680677e-06,
+      "loss": 0.049,
+      "step": 4025
+    },
+    {
+      "epoch": 0.5940243452600517,
+      "grad_norm": 2.0410664081573486,
+      "learning_rate": 8.468478807645924e-06,
+      "loss": 0.0365,
+      "step": 4026
+    },
+    {
+      "epoch": 0.5941718922906677,
+      "grad_norm": 2.373417854309082,
+      "learning_rate": 8.463388782966048e-06,
+      "loss": 0.068,
+      "step": 4027
+    },
+    {
+      "epoch": 0.5943194393212836,
+      "grad_norm": 2.731009006500244,
+      "learning_rate": 8.458299165991579e-06,
+      "loss": 0.0239,
+      "step": 4028
+    },
+    {
+      "epoch": 0.5944669863518997,
+      "grad_norm": 1.7002266645431519,
+      "learning_rate": 8.45320995807293e-06,
+      "loss": 0.0444,
+      "step": 4029
+    },
+    {
+      "epoch": 0.5946145333825157,
+      "grad_norm": 2.2088232040405273,
+      "learning_rate": 8.44812116056041e-06,
+      "loss": 0.0417,
+      "step": 4030
+    },
+    {
+      "epoch": 0.5947620804131317,
+      "grad_norm": 1.181602120399475,
+      "learning_rate": 8.443032774804218e-06,
+      "loss": 0.0197,
+      "step": 4031
+    },
+    {
+      "epoch": 0.5949096274437476,
+      "grad_norm": 1.2374571561813354,
+      "learning_rate": 8.437944802154434e-06,
+      "loss": 0.0119,
+      "step": 4032
+    },
+    {
+      "epoch": 0.5950571744743637,
+      "grad_norm": 1.5645852088928223,
+      "learning_rate": 8.43285724396105e-06,
+      "loss": 0.034,
+      "step": 4033
+    },
+    {
+      "epoch": 0.5952047215049797,
+      "grad_norm": 1.6383975744247437,
+      "learning_rate": 8.427770101573933e-06,
+      "loss": 0.0459,
+      "step": 4034
+    },
+    {
+      "epoch": 0.5953522685355958,
+      "grad_norm": 1.1739534139633179,
+      "learning_rate": 8.422683376342839e-06,
+      "loss": 0.0214,
+      "step": 4035
+    },
+    {
+      "epoch": 0.5954998155662117,
+      "grad_norm": 2.949166774749756,
+      "learning_rate": 8.417597069617418e-06,
+      "loss": 0.0837,
+      "step": 4036
+    },
+    {
+      "epoch": 0.5956473625968277,
+      "grad_norm": 1.6540577411651611,
+      "learning_rate": 8.412511182747205e-06,
+      "loss": 0.0374,
+      "step": 4037
+    },
+    {
+      "epoch": 0.5957949096274437,
+      "grad_norm": 0.655131459236145,
+      "learning_rate": 8.407425717081632e-06,
+      "loss": 0.0124,
+      "step": 4038
+    },
+    {
+      "epoch": 0.5959424566580598,
+      "grad_norm": 2.0629687309265137,
+      "learning_rate": 8.402340673970012e-06,
+      "loss": 0.0561,
+      "step": 4039
+    },
+    {
+      "epoch": 0.5960900036886758,
+      "grad_norm": 1.758529782295227,
+      "learning_rate": 8.397256054761544e-06,
+      "loss": 0.0269,
+      "step": 4040
+    },
+    {
+      "epoch": 0.5960900036886758,
+      "eval_accuracy": 0.9768451519536903,
+      "eval_f1": 0.96,
+      "eval_loss": 0.062456224113702774,
+      "eval_precision": 0.9896907216494846,
+      "eval_recall": 0.9320388349514563,
+      "eval_runtime": 50.2756,
+      "eval_samples_per_second": 5.788,
+      "eval_steps_per_second": 0.199,
+      "step": 4040
+    },
+    {
+      "epoch": 0.5962375507192917,
+      "grad_norm": 2.973538398742676,
+      "learning_rate": 8.39217186080532e-06,
+      "loss": 0.0644,
+      "step": 4041
+    },
+    {
+      "epoch": 0.5963850977499078,
+      "grad_norm": 2.3122551441192627,
+      "learning_rate": 8.387088093450315e-06,
+      "loss": 0.0636,
+      "step": 4042
+    },
+    {
+      "epoch": 0.5965326447805238,
+      "grad_norm": 1.2486623525619507,
+      "learning_rate": 8.382004754045397e-06,
+      "loss": 0.0249,
+      "step": 4043
+    },
+    {
+      "epoch": 0.5966801918111398,
+      "grad_norm": 3.0583341121673584,
+      "learning_rate": 8.376921843939315e-06,
+      "loss": 0.0912,
+      "step": 4044
+    },
+    {
+      "epoch": 0.5968277388417558,
+      "grad_norm": 3.5858421325683594,
+      "learning_rate": 8.371839364480707e-06,
+      "loss": 0.0306,
+      "step": 4045
+    },
+    {
+      "epoch": 0.5969752858723718,
+      "grad_norm": 4.066762447357178,
+      "learning_rate": 8.366757317018086e-06,
+      "loss": 0.0965,
+      "step": 4046
+    },
+    {
+      "epoch": 0.5971228329029878,
+      "grad_norm": 1.7109265327453613,
+      "learning_rate": 8.361675702899873e-06,
+      "loss": 0.0576,
+      "step": 4047
+    },
+    {
+      "epoch": 0.5972703799336039,
+      "grad_norm": 1.577673316001892,
+      "learning_rate": 8.356594523474353e-06,
+      "loss": 0.031,
+      "step": 4048
+    },
+    {
+      "epoch": 0.5974179269642198,
+      "grad_norm": 3.5720999240875244,
+      "learning_rate": 8.351513780089704e-06,
+      "loss": 0.0749,
+      "step": 4049
+    },
+    {
+      "epoch": 0.5975654739948358,
+      "grad_norm": 1.7540377378463745,
+      "learning_rate": 8.346433474093989e-06,
+      "loss": 0.0471,
+      "step": 4050
+    },
+    {
+      "epoch": 0.5977130210254519,
+      "grad_norm": 1.669903039932251,
+      "learning_rate": 8.341353606835148e-06,
+      "loss": 0.0229,
+      "step": 4051
+    },
+    {
+      "epoch": 0.5978605680560679,
+      "grad_norm": 3.7939202785491943,
+      "learning_rate": 8.336274179661018e-06,
+      "loss": 0.1389,
+      "step": 4052
+    },
+    {
+      "epoch": 0.5980081150866838,
+      "grad_norm": 5.558625221252441,
+      "learning_rate": 8.331195193919308e-06,
+      "loss": 0.1058,
+      "step": 4053
+    },
+    {
+      "epoch": 0.5981556621172999,
+      "grad_norm": 2.3846969604492188,
+      "learning_rate": 8.326116650957615e-06,
+      "loss": 0.0832,
+      "step": 4054
+    },
+    {
+      "epoch": 0.5983032091479159,
+      "grad_norm": 3.1761257648468018,
+      "learning_rate": 8.321038552123413e-06,
+      "loss": 0.0729,
+      "step": 4055
+    },
+    {
+      "epoch": 0.5984507561785319,
+      "grad_norm": 2.646514654159546,
+      "learning_rate": 8.315960898764063e-06,
+      "loss": 0.0708,
+      "step": 4056
+    },
+    {
+      "epoch": 0.5985983032091479,
+      "grad_norm": 3.5044147968292236,
+      "learning_rate": 8.31088369222681e-06,
+      "loss": 0.0732,
+      "step": 4057
+    },
+    {
+      "epoch": 0.5987458502397639,
+      "grad_norm": 1.22723388671875,
+      "learning_rate": 8.305806933858773e-06,
+      "loss": 0.0127,
+      "step": 4058
+    },
+    {
+      "epoch": 0.5988933972703799,
+      "grad_norm": 3.667985200881958,
+      "learning_rate": 8.30073062500696e-06,
+      "loss": 0.0657,
+      "step": 4059
+    },
+    {
+      "epoch": 0.599040944300996,
+      "grad_norm": 2.531170606613159,
+      "learning_rate": 8.295654767018254e-06,
+      "loss": 0.0478,
+      "step": 4060
+    },
+    {
+      "epoch": 0.599040944300996,
+      "eval_accuracy": 0.975397973950796,
+      "eval_f1": 0.9582309582309583,
+      "eval_loss": 0.05882137268781662,
+      "eval_precision": 0.9701492537313433,
+      "eval_recall": 0.9466019417475728,
+      "eval_runtime": 49.6056,
+      "eval_samples_per_second": 5.866,
+      "eval_steps_per_second": 0.202,
+      "step": 4060
+    },
+    {
+      "epoch": 0.599188491331612,
+      "grad_norm": 4.068436622619629,
+      "learning_rate": 8.290579361239415e-06,
+      "loss": 0.1229,
+      "step": 4061
+    },
+    {
+      "epoch": 0.5993360383622279,
+      "grad_norm": 3.970015287399292,
+      "learning_rate": 8.2855044090171e-06,
+      "loss": 0.0344,
+      "step": 4062
+    },
+    {
+      "epoch": 0.599483585392844,
+      "grad_norm": 3.391155242919922,
+      "learning_rate": 8.280429911697825e-06,
+      "loss": 0.07,
+      "step": 4063
+    },
+    {
+      "epoch": 0.59963113242346,
+      "grad_norm": 2.5408804416656494,
+      "learning_rate": 8.275355870627998e-06,
+      "loss": 0.0836,
+      "step": 4064
+    },
+    {
+      "epoch": 0.599778679454076,
+      "grad_norm": 3.025726795196533,
+      "learning_rate": 8.2702822871539e-06,
+      "loss": 0.1013,
+      "step": 4065
+    },
+    {
+      "epoch": 0.599926226484692,
+      "grad_norm": 2.77030348777771,
+      "learning_rate": 8.265209162621694e-06,
+      "loss": 0.0593,
+      "step": 4066
+    },
+    {
+      "epoch": 0.600073773515308,
+      "grad_norm": 1.9434685707092285,
+      "learning_rate": 8.260136498377421e-06,
+      "loss": 0.043,
+      "step": 4067
+    },
+    {
+      "epoch": 0.600221320545924,
+      "grad_norm": 1.3754554986953735,
+      "learning_rate": 8.255064295766997e-06,
+      "loss": 0.0251,
+      "step": 4068
+    },
+    {
+      "epoch": 0.6003688675765401,
+      "grad_norm": 2.7446134090423584,
+      "learning_rate": 8.249992556136221e-06,
+      "loss": 0.0717,
+      "step": 4069
+    },
+    {
+      "epoch": 0.600516414607156,
+      "grad_norm": 3.1507766246795654,
+      "learning_rate": 8.24492128083076e-06,
+      "loss": 0.0741,
+      "step": 4070
+    },
+    {
+      "epoch": 0.600663961637772,
+      "grad_norm": 1.6349372863769531,
+      "learning_rate": 8.239850471196169e-06,
+      "loss": 0.0221,
+      "step": 4071
+    },
+    {
+      "epoch": 0.6008115086683881,
+      "grad_norm": 1.8611254692077637,
+      "learning_rate": 8.23478012857787e-06,
+      "loss": 0.0359,
+      "step": 4072
+    },
+    {
+      "epoch": 0.6009590556990041,
+      "grad_norm": 2.038020372390747,
+      "learning_rate": 8.229710254321169e-06,
+      "loss": 0.0434,
+      "step": 4073
+    },
+    {
+      "epoch": 0.60110660272962,
+      "grad_norm": 2.05490779876709,
+      "learning_rate": 8.224640849771242e-06,
+      "loss": 0.0667,
+      "step": 4074
+    },
+    {
+      "epoch": 0.6012541497602361,
+      "grad_norm": 2.0123698711395264,
+      "learning_rate": 8.219571916273134e-06,
+      "loss": 0.0536,
+      "step": 4075
+    },
+    {
+      "epoch": 0.6014016967908521,
+      "grad_norm": 2.4281039237976074,
+      "learning_rate": 8.214503455171788e-06,
+      "loss": 0.0722,
+      "step": 4076
+    },
+    {
+      "epoch": 0.6015492438214681,
+      "grad_norm": 3.9477169513702393,
+      "learning_rate": 8.209435467811998e-06,
+      "loss": 0.0925,
+      "step": 4077
+    },
+    {
+      "epoch": 0.601696790852084,
+      "grad_norm": 1.8821567296981812,
+      "learning_rate": 8.20436795553844e-06,
+      "loss": 0.0727,
+      "step": 4078
+    },
+    {
+      "epoch": 0.6018443378827001,
+      "grad_norm": 1.2030612230300903,
+      "learning_rate": 8.19930091969567e-06,
+      "loss": 0.0227,
+      "step": 4079
+    },
+    {
+      "epoch": 0.6019918849133161,
+      "grad_norm": 2.11921763420105,
+      "learning_rate": 8.194234361628106e-06,
+      "loss": 0.0405,
+      "step": 4080
+    },
+    {
+      "epoch": 0.6019918849133161,
+      "eval_accuracy": 0.9768451519536903,
+      "eval_f1": 0.9605911330049262,
+      "eval_loss": 0.05782787501811981,
+      "eval_precision": 0.975,
+      "eval_recall": 0.9466019417475728,
+      "eval_runtime": 50.1986,
+      "eval_samples_per_second": 5.797,
+      "eval_steps_per_second": 0.199,
+      "step": 4080
+    },
+    {
+      "epoch": 0.6021394319439322,
+      "grad_norm": 2.6245100498199463,
+      "learning_rate": 8.189168282680052e-06,
+      "loss": 0.0816,
+      "step": 4081
+    },
+    {
+      "epoch": 0.6022869789745481,
+      "grad_norm": 1.9298090934753418,
+      "learning_rate": 8.184102684195677e-06,
+      "loss": 0.0542,
+      "step": 4082
+    },
+    {
+      "epoch": 0.6024345260051641,
+      "grad_norm": 2.777143716812134,
+      "learning_rate": 8.17903756751902e-06,
+      "loss": 0.0844,
+      "step": 4083
+    },
+    {
+      "epoch": 0.6025820730357802,
+      "grad_norm": 1.914462685585022,
+      "learning_rate": 8.173972933994003e-06,
+      "loss": 0.0559,
+      "step": 4084
+    },
+    {
+      "epoch": 0.6027296200663962,
+      "grad_norm": 4.3868279457092285,
+      "learning_rate": 8.168908784964407e-06,
+      "loss": 0.0825,
+      "step": 4085
+    },
+    {
+      "epoch": 0.6028771670970122,
+      "grad_norm": 1.8260278701782227,
+      "learning_rate": 8.163845121773896e-06,
+      "loss": 0.0479,
+      "step": 4086
+    },
+    {
+      "epoch": 0.6030247141276281,
+      "grad_norm": 3.0764830112457275,
+      "learning_rate": 8.158781945765998e-06,
+      "loss": 0.0525,
+      "step": 4087
+    },
+    {
+      "epoch": 0.6031722611582442,
+      "grad_norm": 2.1458253860473633,
+      "learning_rate": 8.153719258284113e-06,
+      "loss": 0.0484,
+      "step": 4088
+    },
+    {
+      "epoch": 0.6033198081888602,
+      "grad_norm": 2.5246200561523438,
+      "learning_rate": 8.148657060671507e-06,
+      "loss": 0.0476,
+      "step": 4089
+    },
+    {
+      "epoch": 0.6034673552194763,
+      "grad_norm": 2.05627703666687,
+      "learning_rate": 8.14359535427133e-06,
+      "loss": 0.0211,
+      "step": 4090
+    },
+    {
+      "epoch": 0.6036149022500922,
+      "grad_norm": 2.763218879699707,
+      "learning_rate": 8.13853414042659e-06,
+      "loss": 0.0548,
+      "step": 4091
+    },
+    {
+      "epoch": 0.6037624492807082,
+      "grad_norm": 3.247293472290039,
+      "learning_rate": 8.133473420480163e-06,
+      "loss": 0.0679,
+      "step": 4092
+    },
+    {
+      "epoch": 0.6039099963113242,
+      "grad_norm": 1.4476892948150635,
+      "learning_rate": 8.128413195774798e-06,
+      "loss": 0.0401,
+      "step": 4093
+    },
+    {
+      "epoch": 0.6040575433419403,
+      "grad_norm": 1.8784327507019043,
+      "learning_rate": 8.123353467653115e-06,
+      "loss": 0.0586,
+      "step": 4094
+    },
+    {
+      "epoch": 0.6042050903725562,
+      "grad_norm": 3.985814332962036,
+      "learning_rate": 8.118294237457598e-06,
+      "loss": 0.087,
+      "step": 4095
+    },
+    {
+      "epoch": 0.6043526374031722,
+      "grad_norm": 1.7837779521942139,
+      "learning_rate": 8.113235506530603e-06,
+      "loss": 0.0377,
+      "step": 4096
+    },
+    {
+      "epoch": 0.6045001844337883,
+      "grad_norm": 1.724265694618225,
+      "learning_rate": 8.10817727621435e-06,
+      "loss": 0.0259,
+      "step": 4097
+    },
+    {
+      "epoch": 0.6046477314644043,
+      "grad_norm": 1.8024345636367798,
+      "learning_rate": 8.103119547850924e-06,
+      "loss": 0.0447,
+      "step": 4098
+    },
+    {
+      "epoch": 0.6047952784950202,
+      "grad_norm": 2.173997640609741,
+      "learning_rate": 8.098062322782283e-06,
+      "loss": 0.0394,
+      "step": 4099
+    },
+    {
+      "epoch": 0.6049428255256363,
+      "grad_norm": 1.8738340139389038,
+      "learning_rate": 8.093005602350249e-06,
+      "loss": 0.0824,
+      "step": 4100
+    },
+    {
+      "epoch": 0.6049428255256363,
+      "eval_accuracy": 0.9782923299565847,
+      "eval_f1": 0.9631449631449631,
+      "eval_loss": 0.05601954460144043,
+      "eval_precision": 0.9751243781094527,
+      "eval_recall": 0.9514563106796117,
+      "eval_runtime": 49.1339,
+      "eval_samples_per_second": 5.923,
+      "eval_steps_per_second": 0.204,
+      "step": 4100
     }
   ],
   "logging_steps": 1,
@@ -30438,7 +31198,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.232499821898629e+18,
+  "total_flos": 1.2632673160244756e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null