Training in progress, step 4700, checkpoint

last-checkpoint/optimizer_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:279e6428681e993ce8a48022ead3b8c713c50978a84a38dfd6d7b59db31bad80
+oid sha256:103c8a005d78da93637edcfc6762cdbd98eff441bf18a70cfdcdb121a6d5e995
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f4292764140b3b5d6547609e67309b58fa73ede05ee2b3cb7e8b53b26e8318d
+oid sha256:ef52eca2efdfd0317da72350cf714e81dd5c4c5d6e632cfae2585b523403ada1
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e00c59ef3238e1888f9e4752c50131808aba6976c8432ec5f2f29acc2afd898d
+oid sha256:80a26b2c8f89f3f8b84da07e1aeb9f0709af0650f4ca3fbaa49a4428931c0623
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae6cfc2f90ad8dcf2705ccb11fd4d3d18c5db8e4341b12966f6f111755a26b74
+oid sha256:2017e2fc7b2ccb72a40248569f6bd96f707fa6f4d774b6352ba78c05aa6efb66
 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:d88bf1867b04593e5e64c0a5d73330a59ee86021a3dd789c4c6bf8ff2541b35d
+oid sha256:e3c12aaec549a143fe7ab549cd17f0036b68dc637327ba8a2a14970c64ab2d5c
 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:e0ad6edc9b3ab05a2775d6c1034c8dbbf6b476e007087a0703e56dfc7ab8331f
+oid sha256:056e8de7177eb64daa3a5d7255f493db59aa27884b406ae584093d475e73e7a2
 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:f584bbab27206eb6769fc4964c936d235e4a47ba4b449152bee06f6f3d8c0ee4
+oid sha256:1507ba4e93643e0633f068f88045cbde052f443f59faece96806379693cb2fbf
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:303a76afc784f6e92034a21e473ad6d1bfcbcefe9e677d721edbdddc89153a6a
+oid sha256:34a44e1b6ab0130f79783559f5b15123a73ca143aa800a361ea38ffd1ccdced5
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62296a2f51969b2a3bebf3b62ca668f980dc4095668a72faf1fdee144d9b1c93
+oid sha256:cf87269bba14eb85bf189ad70dbfb1d6e89c64d8f3d4ede5526f7021aeeca6dc
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64e36c3e7c90f639cad6034ef5a6d727ebd616b928a3c4171e2b766e4d9d76ff
+oid sha256:ef4bd1fc7ac298649bb4942dcbfaf8517f3c39dec48982740d74838127f865b8
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b77b9cf0c8799737f4dae3e13a308ec518d965eaa72a71baebdd7662151027c
+oid sha256:7858c279aa486a615cefb424056b504d18349585f4f84b6b4beb0a86ee49f8e2
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3449da71b077fcf61d509b79b0de58c61874f37d85ef9e39a56c22d5ac54c37e
+oid sha256:41d8ef42932b56917d4860294c573ed273684d0b32e96c29a3726f5280e43fc6
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9442cdff9c06d054391ab85177e7c5901e821f1b731a4d193a5e723555e8f61
+oid sha256:23eb92592a709d561f028a3a7e8550e3e801df557f06d2c5aad844da3f0ea42f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6787163408336407,
+  "epoch": 0.6934710438952416,
   "eval_steps": 20,
-  "global_step": 4600,
+  "global_step": 4700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -34979,6 +34979,766 @@
       "eval_samples_per_second": 5.894,
       "eval_steps_per_second": 0.203,
       "step": 4600
+    },
+    {
+      "epoch": 0.6788638878642568,
+      "grad_norm": 2.081822395324707,
+      "learning_rate": 5.650889182792748e-06,
+      "loss": 0.0279,
+      "step": 4601
+    },
+    {
+      "epoch": 0.6790114348948727,
+      "grad_norm": 1.4815239906311035,
+      "learning_rate": 5.6462514247810444e-06,
+      "loss": 0.052,
+      "step": 4602
+    },
+    {
+      "epoch": 0.6791589819254887,
+      "grad_norm": 1.4074938297271729,
+      "learning_rate": 5.641614821939104e-06,
+      "loss": 0.0142,
+      "step": 4603
+    },
+    {
+      "epoch": 0.6793065289561048,
+      "grad_norm": 2.3841392993927,
+      "learning_rate": 5.636979375497151e-06,
+      "loss": 0.0638,
+      "step": 4604
+    },
+    {
+      "epoch": 0.6794540759867208,
+      "grad_norm": 2.219118595123291,
+      "learning_rate": 5.6323450866851e-06,
+      "loss": 0.0562,
+      "step": 4605
+    },
+    {
+      "epoch": 0.6796016230173367,
+      "grad_norm": 5.843283176422119,
+      "learning_rate": 5.627711956732553e-06,
+      "loss": 0.0699,
+      "step": 4606
+    },
+    {
+      "epoch": 0.6797491700479528,
+      "grad_norm": 3.2192442417144775,
+      "learning_rate": 5.623079986868799e-06,
+      "loss": 0.096,
+      "step": 4607
+    },
+    {
+      "epoch": 0.6798967170785688,
+      "grad_norm": 3.709993362426758,
+      "learning_rate": 5.618449178322844e-06,
+      "loss": 0.0356,
+      "step": 4608
+    },
+    {
+      "epoch": 0.6800442641091848,
+      "grad_norm": 4.850296974182129,
+      "learning_rate": 5.61381953232336e-06,
+      "loss": 0.0652,
+      "step": 4609
+    },
+    {
+      "epoch": 0.6801918111398008,
+      "grad_norm": 2.156365156173706,
+      "learning_rate": 5.6091910500987166e-06,
+      "loss": 0.0412,
+      "step": 4610
+    },
+    {
+      "epoch": 0.6803393581704168,
+      "grad_norm": 1.5853725671768188,
+      "learning_rate": 5.604563732876989e-06,
+      "loss": 0.037,
+      "step": 4611
+    },
+    {
+      "epoch": 0.6804869052010328,
+      "grad_norm": 1.649251937866211,
+      "learning_rate": 5.59993758188592e-06,
+      "loss": 0.0571,
+      "step": 4612
+    },
+    {
+      "epoch": 0.6806344522316489,
+      "grad_norm": 3.2777063846588135,
+      "learning_rate": 5.59531259835296e-06,
+      "loss": 0.0849,
+      "step": 4613
+    },
+    {
+      "epoch": 0.6807819992622648,
+      "grad_norm": 1.2833290100097656,
+      "learning_rate": 5.590688783505249e-06,
+      "loss": 0.0248,
+      "step": 4614
+    },
+    {
+      "epoch": 0.6809295462928808,
+      "grad_norm": 3.259247303009033,
+      "learning_rate": 5.586066138569608e-06,
+      "loss": 0.0439,
+      "step": 4615
+    },
+    {
+      "epoch": 0.6810770933234969,
+      "grad_norm": 1.504201889038086,
+      "learning_rate": 5.5814446647725574e-06,
+      "loss": 0.0436,
+      "step": 4616
+    },
+    {
+      "epoch": 0.6812246403541129,
+      "grad_norm": 3.5449728965759277,
+      "learning_rate": 5.576824363340293e-06,
+      "loss": 0.0643,
+      "step": 4617
+    },
+    {
+      "epoch": 0.6813721873847289,
+      "grad_norm": 4.240931987762451,
+      "learning_rate": 5.5722052354987154e-06,
+      "loss": 0.103,
+      "step": 4618
+    },
+    {
+      "epoch": 0.6815197344153449,
+      "grad_norm": 4.5008368492126465,
+      "learning_rate": 5.567587282473408e-06,
+      "loss": 0.0847,
+      "step": 4619
+    },
+    {
+      "epoch": 0.6816672814459609,
+      "grad_norm": 2.1032140254974365,
+      "learning_rate": 5.56297050548964e-06,
+      "loss": 0.0653,
+      "step": 4620
+    },
+    {
+      "epoch": 0.6816672814459609,
+      "eval_accuracy": 0.9797395079594791,
+      "eval_f1": 0.9653465346534653,
+      "eval_loss": 0.0547698512673378,
+      "eval_precision": 0.9848484848484849,
+      "eval_recall": 0.9466019417475728,
+      "eval_runtime": 49.8649,
+      "eval_samples_per_second": 5.836,
+      "eval_steps_per_second": 0.201,
+      "step": 4620
+    },
+    {
+      "epoch": 0.6818148284765769,
+      "grad_norm": 1.6405268907546997,
+      "learning_rate": 5.558354905772363e-06,
+      "loss": 0.0211,
+      "step": 4621
+    },
+    {
+      "epoch": 0.681962375507193,
+      "grad_norm": 3.434992551803589,
+      "learning_rate": 5.553740484546229e-06,
+      "loss": 0.1316,
+      "step": 4622
+    },
+    {
+      "epoch": 0.6821099225378089,
+      "grad_norm": 2.5380048751831055,
+      "learning_rate": 5.549127243035574e-06,
+      "loss": 0.0606,
+      "step": 4623
+    },
+    {
+      "epoch": 0.6822574695684249,
+      "grad_norm": 1.9085692167282104,
+      "learning_rate": 5.544515182464414e-06,
+      "loss": 0.0258,
+      "step": 4624
+    },
+    {
+      "epoch": 0.682405016599041,
+      "grad_norm": 2.6448922157287598,
+      "learning_rate": 5.53990430405646e-06,
+      "loss": 0.0737,
+      "step": 4625
+    },
+    {
+      "epoch": 0.682552563629657,
+      "grad_norm": 0.7642562985420227,
+      "learning_rate": 5.535294609035099e-06,
+      "loss": 0.0093,
+      "step": 4626
+    },
+    {
+      "epoch": 0.6827001106602729,
+      "grad_norm": 1.6839114427566528,
+      "learning_rate": 5.530686098623414e-06,
+      "loss": 0.0351,
+      "step": 4627
+    },
+    {
+      "epoch": 0.682847657690889,
+      "grad_norm": 1.5677410364151,
+      "learning_rate": 5.526078774044174e-06,
+      "loss": 0.0597,
+      "step": 4628
+    },
+    {
+      "epoch": 0.682995204721505,
+      "grad_norm": 4.345653533935547,
+      "learning_rate": 5.521472636519823e-06,
+      "loss": 0.1201,
+      "step": 4629
+    },
+    {
+      "epoch": 0.683142751752121,
+      "grad_norm": 1.3154315948486328,
+      "learning_rate": 5.516867687272504e-06,
+      "loss": 0.0283,
+      "step": 4630
+    },
+    {
+      "epoch": 0.683290298782737,
+      "grad_norm": 1.605300784111023,
+      "learning_rate": 5.512263927524026e-06,
+      "loss": 0.0409,
+      "step": 4631
+    },
+    {
+      "epoch": 0.683437845813353,
+      "grad_norm": 3.8189263343811035,
+      "learning_rate": 5.5076613584959035e-06,
+      "loss": 0.053,
+      "step": 4632
+    },
+    {
+      "epoch": 0.683585392843969,
+      "grad_norm": 4.527725696563721,
+      "learning_rate": 5.503059981409325e-06,
+      "loss": 0.046,
+      "step": 4633
+    },
+    {
+      "epoch": 0.683732939874585,
+      "grad_norm": 6.160957336425781,
+      "learning_rate": 5.498459797485158e-06,
+      "loss": 0.095,
+      "step": 4634
+    },
+    {
+      "epoch": 0.683880486905201,
+      "grad_norm": 2.801215171813965,
+      "learning_rate": 5.493860807943958e-06,
+      "loss": 0.0699,
+      "step": 4635
+    },
+    {
+      "epoch": 0.684028033935817,
+      "grad_norm": 5.829277515411377,
+      "learning_rate": 5.4892630140059665e-06,
+      "loss": 0.0592,
+      "step": 4636
+    },
+    {
+      "epoch": 0.684175580966433,
+      "grad_norm": 2.45528244972229,
+      "learning_rate": 5.484666416891109e-06,
+      "loss": 0.0606,
+      "step": 4637
+    },
+    {
+      "epoch": 0.6843231279970491,
+      "grad_norm": 1.8605555295944214,
+      "learning_rate": 5.480071017818982e-06,
+      "loss": 0.0521,
+      "step": 4638
+    },
+    {
+      "epoch": 0.6844706750276651,
+      "grad_norm": 1.5198736190795898,
+      "learning_rate": 5.475476818008878e-06,
+      "loss": 0.0358,
+      "step": 4639
+    },
+    {
+      "epoch": 0.684618222058281,
+      "grad_norm": 2.3037924766540527,
+      "learning_rate": 5.470883818679761e-06,
+      "loss": 0.05,
+      "step": 4640
+    },
+    {
+      "epoch": 0.684618222058281,
+      "eval_accuracy": 0.9811866859623734,
+      "eval_f1": 0.9679012345679012,
+      "eval_loss": 0.05457611009478569,
+      "eval_precision": 0.9849246231155779,
+      "eval_recall": 0.9514563106796117,
+      "eval_runtime": 49.3996,
+      "eval_samples_per_second": 5.891,
+      "eval_steps_per_second": 0.202,
+      "step": 4640
+    },
+    {
+      "epoch": 0.6847657690888971,
+      "grad_norm": 2.474771499633789,
+      "learning_rate": 5.466292021050281e-06,
+      "loss": 0.048,
+      "step": 4641
+    },
+    {
+      "epoch": 0.6849133161195131,
+      "grad_norm": 0.7616437673568726,
+      "learning_rate": 5.461701426338775e-06,
+      "loss": 0.0069,
+      "step": 4642
+    },
+    {
+      "epoch": 0.6850608631501292,
+      "grad_norm": 3.2531471252441406,
+      "learning_rate": 5.457112035763243e-06,
+      "loss": 0.0453,
+      "step": 4643
+    },
+    {
+      "epoch": 0.6852084101807451,
+      "grad_norm": 3.4857687950134277,
+      "learning_rate": 5.452523850541391e-06,
+      "loss": 0.1229,
+      "step": 4644
+    },
+    {
+      "epoch": 0.6853559572113611,
+      "grad_norm": 1.3255691528320312,
+      "learning_rate": 5.447936871890578e-06,
+      "loss": 0.037,
+      "step": 4645
+    },
+    {
+      "epoch": 0.6855035042419771,
+      "grad_norm": 2.3378636837005615,
+      "learning_rate": 5.443351101027863e-06,
+      "loss": 0.0385,
+      "step": 4646
+    },
+    {
+      "epoch": 0.6856510512725932,
+      "grad_norm": 2.0383617877960205,
+      "learning_rate": 5.438766539169982e-06,
+      "loss": 0.0611,
+      "step": 4647
+    },
+    {
+      "epoch": 0.6857985983032091,
+      "grad_norm": 3.790567398071289,
+      "learning_rate": 5.434183187533335e-06,
+      "loss": 0.1215,
+      "step": 4648
+    },
+    {
+      "epoch": 0.6859461453338251,
+      "grad_norm": 2.1201913356781006,
+      "learning_rate": 5.429601047334022e-06,
+      "loss": 0.0217,
+      "step": 4649
+    },
+    {
+      "epoch": 0.6860936923644412,
+      "grad_norm": 1.737138032913208,
+      "learning_rate": 5.425020119787803e-06,
+      "loss": 0.0609,
+      "step": 4650
+    },
+    {
+      "epoch": 0.6862412393950572,
+      "grad_norm": 2.2892613410949707,
+      "learning_rate": 5.420440406110129e-06,
+      "loss": 0.0591,
+      "step": 4651
+    },
+    {
+      "epoch": 0.6863887864256731,
+      "grad_norm": 2.4004242420196533,
+      "learning_rate": 5.415861907516129e-06,
+      "loss": 0.0333,
+      "step": 4652
+    },
+    {
+      "epoch": 0.6865363334562892,
+      "grad_norm": 2.855923891067505,
+      "learning_rate": 5.4112846252205985e-06,
+      "loss": 0.0308,
+      "step": 4653
+    },
+    {
+      "epoch": 0.6866838804869052,
+      "grad_norm": 1.8993141651153564,
+      "learning_rate": 5.406708560438015e-06,
+      "loss": 0.0476,
+      "step": 4654
+    },
+    {
+      "epoch": 0.6868314275175212,
+      "grad_norm": 2.9163031578063965,
+      "learning_rate": 5.40213371438254e-06,
+      "loss": 0.0792,
+      "step": 4655
+    },
+    {
+      "epoch": 0.6869789745481372,
+      "grad_norm": 1.5787954330444336,
+      "learning_rate": 5.397560088268008e-06,
+      "loss": 0.0358,
+      "step": 4656
+    },
+    {
+      "epoch": 0.6871265215787532,
+      "grad_norm": 2.2038626670837402,
+      "learning_rate": 5.392987683307922e-06,
+      "loss": 0.0468,
+      "step": 4657
+    },
+    {
+      "epoch": 0.6872740686093692,
+      "grad_norm": 2.4745113849639893,
+      "learning_rate": 5.388416500715474e-06,
+      "loss": 0.0929,
+      "step": 4658
+    },
+    {
+      "epoch": 0.6874216156399853,
+      "grad_norm": 1.4698036909103394,
+      "learning_rate": 5.383846541703519e-06,
+      "loss": 0.0305,
+      "step": 4659
+    },
+    {
+      "epoch": 0.6875691626706013,
+      "grad_norm": 1.6903125047683716,
+      "learning_rate": 5.379277807484596e-06,
+      "loss": 0.048,
+      "step": 4660
+    },
+    {
+      "epoch": 0.6875691626706013,
+      "eval_accuracy": 0.9811866859623734,
+      "eval_f1": 0.9679012345679012,
+      "eval_loss": 0.054064974188804626,
+      "eval_precision": 0.9849246231155779,
+      "eval_recall": 0.9514563106796117,
+      "eval_runtime": 50.136,
+      "eval_samples_per_second": 5.804,
+      "eval_steps_per_second": 0.199,
+      "step": 4660
+    },
+    {
+      "epoch": 0.6877167097012172,
+      "grad_norm": 1.3866111040115356,
+      "learning_rate": 5.374710299270921e-06,
+      "loss": 0.0273,
+      "step": 4661
+    },
+    {
+      "epoch": 0.6878642567318333,
+      "grad_norm": 3.9755289554595947,
+      "learning_rate": 5.370144018274372e-06,
+      "loss": 0.0478,
+      "step": 4662
+    },
+    {
+      "epoch": 0.6880118037624493,
+      "grad_norm": 2.0998730659484863,
+      "learning_rate": 5.365578965706516e-06,
+      "loss": 0.0599,
+      "step": 4663
+    },
+    {
+      "epoch": 0.6881593507930653,
+      "grad_norm": 2.7026755809783936,
+      "learning_rate": 5.361015142778582e-06,
+      "loss": 0.0394,
+      "step": 4664
+    },
+    {
+      "epoch": 0.6883068978236813,
+      "grad_norm": 3.7726657390594482,
+      "learning_rate": 5.356452550701481e-06,
+      "loss": 0.0823,
+      "step": 4665
+    },
+    {
+      "epoch": 0.6884544448542973,
+      "grad_norm": 3.169844627380371,
+      "learning_rate": 5.3518911906857985e-06,
+      "loss": 0.1038,
+      "step": 4666
+    },
+    {
+      "epoch": 0.6886019918849133,
+      "grad_norm": 1.8277506828308105,
+      "learning_rate": 5.347331063941786e-06,
+      "loss": 0.023,
+      "step": 4667
+    },
+    {
+      "epoch": 0.6887495389155294,
+      "grad_norm": 1.5094001293182373,
+      "learning_rate": 5.342772171679364e-06,
+      "loss": 0.0413,
+      "step": 4668
+    },
+    {
+      "epoch": 0.6888970859461453,
+      "grad_norm": 2.628838539123535,
+      "learning_rate": 5.3382145151081435e-06,
+      "loss": 0.0724,
+      "step": 4669
+    },
+    {
+      "epoch": 0.6890446329767613,
+      "grad_norm": 2.540367364883423,
+      "learning_rate": 5.333658095437395e-06,
+      "loss": 0.0624,
+      "step": 4670
+    },
+    {
+      "epoch": 0.6891921800073774,
+      "grad_norm": 2.2520368099212646,
+      "learning_rate": 5.329102913876055e-06,
+      "loss": 0.0609,
+      "step": 4671
+    },
+    {
+      "epoch": 0.6893397270379934,
+      "grad_norm": 1.8281601667404175,
+      "learning_rate": 5.324548971632748e-06,
+      "loss": 0.0628,
+      "step": 4672
+    },
+    {
+      "epoch": 0.6894872740686093,
+      "grad_norm": 2.0493619441986084,
+      "learning_rate": 5.319996269915755e-06,
+      "loss": 0.0245,
+      "step": 4673
+    },
+    {
+      "epoch": 0.6896348210992254,
+      "grad_norm": 4.497646331787109,
+      "learning_rate": 5.315444809933032e-06,
+      "loss": 0.1471,
+      "step": 4674
+    },
+    {
+      "epoch": 0.6897823681298414,
+      "grad_norm": 0.9106382727622986,
+      "learning_rate": 5.310894592892217e-06,
+      "loss": 0.0064,
+      "step": 4675
+    },
+    {
+      "epoch": 0.6899299151604574,
+      "grad_norm": 1.2549246549606323,
+      "learning_rate": 5.3063456200005965e-06,
+      "loss": 0.0402,
+      "step": 4676
+    },
+    {
+      "epoch": 0.6900774621910734,
+      "grad_norm": 3.292407989501953,
+      "learning_rate": 5.301797892465148e-06,
+      "loss": 0.0655,
+      "step": 4677
+    },
+    {
+      "epoch": 0.6902250092216894,
+      "grad_norm": 1.2164607048034668,
+      "learning_rate": 5.297251411492503e-06,
+      "loss": 0.0145,
+      "step": 4678
+    },
+    {
+      "epoch": 0.6903725562523054,
+      "grad_norm": 3.410823106765747,
+      "learning_rate": 5.292706178288966e-06,
+      "loss": 0.0675,
+      "step": 4679
+    },
+    {
+      "epoch": 0.6905201032829215,
+      "grad_norm": 3.0682482719421387,
+      "learning_rate": 5.288162194060523e-06,
+      "loss": 0.0746,
+      "step": 4680
+    },
+    {
+      "epoch": 0.6905201032829215,
+      "eval_accuracy": 0.9797395079594791,
+      "eval_f1": 0.9653465346534653,
+      "eval_loss": 0.056046705693006516,
+      "eval_precision": 0.9848484848484849,
+      "eval_recall": 0.9466019417475728,
+      "eval_runtime": 50.476,
+      "eval_samples_per_second": 5.765,
+      "eval_steps_per_second": 0.198,
+      "step": 4680
+    },
+    {
+      "epoch": 0.6906676503135374,
+      "grad_norm": 2.1872940063476562,
+      "learning_rate": 5.283619460012814e-06,
+      "loss": 0.0564,
+      "step": 4681
+    },
+    {
+      "epoch": 0.6908151973441534,
+      "grad_norm": 3.5949339866638184,
+      "learning_rate": 5.279077977351146e-06,
+      "loss": 0.1179,
+      "step": 4682
+    },
+    {
+      "epoch": 0.6909627443747695,
+      "grad_norm": 1.711521863937378,
+      "learning_rate": 5.274537747280505e-06,
+      "loss": 0.0486,
+      "step": 4683
+    },
+    {
+      "epoch": 0.6911102914053855,
+      "grad_norm": 1.7035961151123047,
+      "learning_rate": 5.269998771005542e-06,
+      "loss": 0.072,
+      "step": 4684
+    },
+    {
+      "epoch": 0.6912578384360015,
+      "grad_norm": 3.3933184146881104,
+      "learning_rate": 5.265461049730568e-06,
+      "loss": 0.1412,
+      "step": 4685
+    },
+    {
+      "epoch": 0.6914053854666175,
+      "grad_norm": 1.9112924337387085,
+      "learning_rate": 5.26092458465957e-06,
+      "loss": 0.0739,
+      "step": 4686
+    },
+    {
+      "epoch": 0.6915529324972335,
+      "grad_norm": 3.6496407985687256,
+      "learning_rate": 5.256389376996192e-06,
+      "loss": 0.0548,
+      "step": 4687
+    },
+    {
+      "epoch": 0.6917004795278495,
+      "grad_norm": 1.4398243427276611,
+      "learning_rate": 5.251855427943753e-06,
+      "loss": 0.0415,
+      "step": 4688
+    },
+    {
+      "epoch": 0.6918480265584656,
+      "grad_norm": 3.6281752586364746,
+      "learning_rate": 5.247322738705239e-06,
+      "loss": 0.1014,
+      "step": 4689
+    },
+    {
+      "epoch": 0.6919955735890815,
+      "grad_norm": 2.4000320434570312,
+      "learning_rate": 5.242791310483288e-06,
+      "loss": 0.0639,
+      "step": 4690
+    },
+    {
+      "epoch": 0.6921431206196975,
+      "grad_norm": 2.0405635833740234,
+      "learning_rate": 5.238261144480225e-06,
+      "loss": 0.0538,
+      "step": 4691
+    },
+    {
+      "epoch": 0.6922906676503136,
+      "grad_norm": 1.8086013793945312,
+      "learning_rate": 5.233732241898021e-06,
+      "loss": 0.0505,
+      "step": 4692
+    },
+    {
+      "epoch": 0.6924382146809296,
+      "grad_norm": 2.220877170562744,
+      "learning_rate": 5.2292046039383115e-06,
+      "loss": 0.042,
+      "step": 4693
+    },
+    {
+      "epoch": 0.6925857617115455,
+      "grad_norm": 2.452057361602783,
+      "learning_rate": 5.22467823180242e-06,
+      "loss": 0.0892,
+      "step": 4694
+    },
+    {
+      "epoch": 0.6927333087421615,
+      "grad_norm": 1.4002968072891235,
+      "learning_rate": 5.220153126691312e-06,
+      "loss": 0.0412,
+      "step": 4695
+    },
+    {
+      "epoch": 0.6928808557727776,
+      "grad_norm": 2.3197379112243652,
+      "learning_rate": 5.215629289805616e-06,
+      "loss": 0.048,
+      "step": 4696
+    },
+    {
+      "epoch": 0.6930284028033936,
+      "grad_norm": 1.9746086597442627,
+      "learning_rate": 5.21110672234564e-06,
+      "loss": 0.0294,
+      "step": 4697
+    },
+    {
+      "epoch": 0.6931759498340095,
+      "grad_norm": 2.7834994792938232,
+      "learning_rate": 5.206585425511339e-06,
+      "loss": 0.0497,
+      "step": 4698
+    },
+    {
+      "epoch": 0.6933234968646256,
+      "grad_norm": 2.4984586238861084,
+      "learning_rate": 5.202065400502341e-06,
+      "loss": 0.058,
+      "step": 4699
+    },
+    {
+      "epoch": 0.6934710438952416,
+      "grad_norm": 1.4515494108200073,
+      "learning_rate": 5.197546648517937e-06,
+      "loss": 0.036,
+      "step": 4700
+    },
+    {
+      "epoch": 0.6934710438952416,
+      "eval_accuracy": 0.9811866859623734,
+      "eval_f1": 0.9679012345679012,
+      "eval_loss": 0.05514227971434593,
+      "eval_precision": 0.9849246231155779,
+      "eval_recall": 0.9514563106796117,
+      "eval_runtime": 49.5267,
+      "eval_samples_per_second": 5.876,
+      "eval_steps_per_second": 0.202,
+      "step": 4700
     }
   ],
   "logging_steps": 1,
@@ -34998,7 +35758,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4173918143855985e+18,
+  "total_flos": 1.4479325969514496e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null