Training in progress, step 5700, checkpoint

last-checkpoint/optimizer_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37806c423ffa510c9faffb8fcdf7d6f3f3d6430073823f78aa481c974138955c
+oid sha256:323593aaf478654c4c84395f44d68d325be67e00b52048e7bf1265f40205678a
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:023c98c761123a6469e63215913655c80078e55de557b8b15af648c81661e6e9
+oid sha256:b47201053fbcc4557e60d3d17db4733b5710d94e7f48d1b5ac7f27ecc8f73c10
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cf2525a722d0baea6ee5b4d051305af13c04be8865e51da769c061c6e2f5e8d
+oid sha256:fc469c7929b4a16dd0af75e3463a471bb004d4df11e357a47195fe58f84c8b01
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ab02f121b24c4f099247f21063f07ccc86d2d609e4f0f272062ac91142c2c87
+oid sha256:f4abb2ee717d219800c0157e5c4da401a279c869c0e47fd10dfe920c43289ac0
 size 13990904

last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c156d539fb941d8eca70fc343bc26b6e5e2680912052f0c5d043878994e3637
+oid sha256:1bf8fc9f010947014eb27bb723b0612c83e5b7de0be1f60ae868bdf959211d98
 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:fcf533dc46ba2e89f475db9f93cc097d115d15b651341136ecad156313bc904f
+oid sha256:36a19bd3fe7713935f16cda1edce71e068c8e8540e208e282fbf5909f7b57eb9
 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:d452a45fbefd49a512f8431c38d58d1ed92c98b03f32fe52abc33ed4e2c9bebb
+oid sha256:b34e18a97bf62613b29d90cc266fd299a72f0aa1155a62d7cc3755ec36c07384
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d63805e93dd3776c59a93fd13dd7f7e691f2e2f39739c45e459a8e979ba576c
+oid sha256:9a56bcdbc7a93c77dd54b1f01e5d7075bcdb8cf5f5ef74ec957a9e0f490b3363
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f62f5d1f68530693e343eeb0c85f6b35054f1b82ac87fd2d84b07c17f9475c12
+oid sha256:a35f499a70a612db8820af15407688adb91e47e26a75b81f87a7bc2288c6b8e6
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0ce654a453607595850d9a2bb1c64d300d385aca02ac17b1fd384340d3af513
+oid sha256:14b08b2743b0b959b0b922a5d5ced611a23433d657351053a9aae6bec44f39c9
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:662dc63e1d06483103d61d6e12ec9b44149350a9bebbf824ea35c04cf29013cf
+oid sha256:3fbadcacf053d499aa403f31b5c34cca57e04f551d37d8d70090a5c39bfbcc99
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e20926d7802f13afedb3b8fdf42f121a1e2a80036c9938598c53c3254f6472f
+oid sha256:612f21a86961278058a69e3fbd5a869ab48adcaa082dde48ff32892df6d5831e
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55673d15759f216aa8bd4c18f2ce65bc93c3ecb8ef0e609b984c07fac8f727f7
+oid sha256:88cbf90edbc28a5c9f752799e3c9fb7e7a34d3763eec39b36fadc9beec06b79b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8262633714496496,
+  "epoch": 0.8410180745112504,
   "eval_steps": 20,
-  "global_step": 5600,
+  "global_step": 5700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -42579,6 +42579,766 @@
       "eval_samples_per_second": 5.952,
       "eval_steps_per_second": 0.205,
       "step": 5600
+    },
+    {
+      "epoch": 0.8264109184802656,
+      "grad_norm": 1.5956645011901855,
+      "learning_rate": 1.7792878588736262e-06,
+      "loss": 0.0605,
+      "step": 5601
+    },
+    {
+      "epoch": 0.8265584655108816,
+      "grad_norm": 2.7995615005493164,
+      "learning_rate": 1.7763560511817313e-06,
+      "loss": 0.0761,
+      "step": 5602
+    },
+    {
+      "epoch": 0.8267060125414976,
+      "grad_norm": 3.7268588542938232,
+      "learning_rate": 1.7734264254497492e-06,
+      "loss": 0.0905,
+      "step": 5603
+    },
+    {
+      "epoch": 0.8268535595721136,
+      "grad_norm": 1.0305407047271729,
+      "learning_rate": 1.7704989824549955e-06,
+      "loss": 0.019,
+      "step": 5604
+    },
+    {
+      "epoch": 0.8270011066027296,
+      "grad_norm": 2.4888436794281006,
+      "learning_rate": 1.7675737229741963e-06,
+      "loss": 0.0588,
+      "step": 5605
+    },
+    {
+      "epoch": 0.8271486536333457,
+      "grad_norm": 2.30344557762146,
+      "learning_rate": 1.7646506477835068e-06,
+      "loss": 0.0518,
+      "step": 5606
+    },
+    {
+      "epoch": 0.8272962006639616,
+      "grad_norm": 1.7901335954666138,
+      "learning_rate": 1.7617297576585023e-06,
+      "loss": 0.0673,
+      "step": 5607
+    },
+    {
+      "epoch": 0.8274437476945776,
+      "grad_norm": 2.1730308532714844,
+      "learning_rate": 1.7588110533741698e-06,
+      "loss": 0.0287,
+      "step": 5608
+    },
+    {
+      "epoch": 0.8275912947251937,
+      "grad_norm": 3.6601784229278564,
+      "learning_rate": 1.7558945357049273e-06,
+      "loss": 0.0583,
+      "step": 5609
+    },
+    {
+      "epoch": 0.8277388417558097,
+      "grad_norm": 1.5753626823425293,
+      "learning_rate": 1.7529802054246027e-06,
+      "loss": 0.0249,
+      "step": 5610
+    },
+    {
+      "epoch": 0.8278863887864256,
+      "grad_norm": 2.235729694366455,
+      "learning_rate": 1.7500680633064515e-06,
+      "loss": 0.0934,
+      "step": 5611
+    },
+    {
+      "epoch": 0.8280339358170417,
+      "grad_norm": 1.4514387845993042,
+      "learning_rate": 1.7471581101231472e-06,
+      "loss": 0.0258,
+      "step": 5612
+    },
+    {
+      "epoch": 0.8281814828476577,
+      "grad_norm": 1.4143081903457642,
+      "learning_rate": 1.7442503466467785e-06,
+      "loss": 0.0555,
+      "step": 5613
+    },
+    {
+      "epoch": 0.8283290298782737,
+      "grad_norm": 2.5379421710968018,
+      "learning_rate": 1.7413447736488531e-06,
+      "loss": 0.0422,
+      "step": 5614
+    },
+    {
+      "epoch": 0.8284765769088898,
+      "grad_norm": 3.532888174057007,
+      "learning_rate": 1.7384413919003008e-06,
+      "loss": 0.0462,
+      "step": 5615
+    },
+    {
+      "epoch": 0.8286241239395057,
+      "grad_norm": 5.810385227203369,
+      "learning_rate": 1.735540202171474e-06,
+      "loss": 0.09,
+      "step": 5616
+    },
+    {
+      "epoch": 0.8287716709701217,
+      "grad_norm": 2.430147647857666,
+      "learning_rate": 1.7326412052321317e-06,
+      "loss": 0.0377,
+      "step": 5617
+    },
+    {
+      "epoch": 0.8289192180007378,
+      "grad_norm": 1.4339234828948975,
+      "learning_rate": 1.729744401851463e-06,
+      "loss": 0.019,
+      "step": 5618
+    },
+    {
+      "epoch": 0.8290667650313538,
+      "grad_norm": 2.2027747631073,
+      "learning_rate": 1.7268497927980655e-06,
+      "loss": 0.0351,
+      "step": 5619
+    },
+    {
+      "epoch": 0.8292143120619697,
+      "grad_norm": 1.9734925031661987,
+      "learning_rate": 1.723957378839961e-06,
+      "loss": 0.0306,
+      "step": 5620
+    },
+    {
+      "epoch": 0.8292143120619697,
+      "eval_accuracy": 0.9782923299565847,
+      "eval_f1": 0.9629629629629629,
+      "eval_loss": 0.0573807954788208,
+      "eval_precision": 0.9798994974874372,
+      "eval_recall": 0.9466019417475728,
+      "eval_runtime": 48.7321,
+      "eval_samples_per_second": 5.971,
+      "eval_steps_per_second": 0.205,
+      "step": 5620
+    },
+    {
+      "epoch": 0.8293618590925858,
+      "grad_norm": 1.7956327199935913,
+      "learning_rate": 1.7210671607445905e-06,
+      "loss": 0.0343,
+      "step": 5621
+    },
+    {
+      "epoch": 0.8295094061232018,
+      "grad_norm": 1.7271618843078613,
+      "learning_rate": 1.7181791392788017e-06,
+      "loss": 0.0357,
+      "step": 5622
+    },
+    {
+      "epoch": 0.8296569531538178,
+      "grad_norm": 1.1316182613372803,
+      "learning_rate": 1.7152933152088725e-06,
+      "loss": 0.0153,
+      "step": 5623
+    },
+    {
+      "epoch": 0.8298045001844337,
+      "grad_norm": 4.591516971588135,
+      "learning_rate": 1.712409689300487e-06,
+      "loss": 0.0781,
+      "step": 5624
+    },
+    {
+      "epoch": 0.8299520472150498,
+      "grad_norm": 2.654439687728882,
+      "learning_rate": 1.7095282623187526e-06,
+      "loss": 0.0458,
+      "step": 5625
+    },
+    {
+      "epoch": 0.8300995942456658,
+      "grad_norm": 2.633575439453125,
+      "learning_rate": 1.706649035028194e-06,
+      "loss": 0.0396,
+      "step": 5626
+    },
+    {
+      "epoch": 0.8302471412762819,
+      "grad_norm": 2.340981960296631,
+      "learning_rate": 1.7037720081927468e-06,
+      "loss": 0.0524,
+      "step": 5627
+    },
+    {
+      "epoch": 0.8303946883068978,
+      "grad_norm": 2.159475326538086,
+      "learning_rate": 1.7008971825757669e-06,
+      "loss": 0.0867,
+      "step": 5628
+    },
+    {
+      "epoch": 0.8305422353375138,
+      "grad_norm": 2.9038820266723633,
+      "learning_rate": 1.6980245589400234e-06,
+      "loss": 0.0921,
+      "step": 5629
+    },
+    {
+      "epoch": 0.8306897823681298,
+      "grad_norm": 8.652804374694824,
+      "learning_rate": 1.6951541380477032e-06,
+      "loss": 0.0816,
+      "step": 5630
+    },
+    {
+      "epoch": 0.8308373293987459,
+      "grad_norm": 1.2753736972808838,
+      "learning_rate": 1.6922859206604126e-06,
+      "loss": 0.0314,
+      "step": 5631
+    },
+    {
+      "epoch": 0.8309848764293618,
+      "grad_norm": 1.063549280166626,
+      "learning_rate": 1.6894199075391638e-06,
+      "loss": 0.0159,
+      "step": 5632
+    },
+    {
+      "epoch": 0.8311324234599778,
+      "grad_norm": 2.372098922729492,
+      "learning_rate": 1.6865560994443886e-06,
+      "loss": 0.0532,
+      "step": 5633
+    },
+    {
+      "epoch": 0.8312799704905939,
+      "grad_norm": 1.112519383430481,
+      "learning_rate": 1.683694497135937e-06,
+      "loss": 0.0319,
+      "step": 5634
+    },
+    {
+      "epoch": 0.8314275175212099,
+      "grad_norm": 1.4782158136367798,
+      "learning_rate": 1.6808351013730727e-06,
+      "loss": 0.0266,
+      "step": 5635
+    },
+    {
+      "epoch": 0.831575064551826,
+      "grad_norm": 2.3959615230560303,
+      "learning_rate": 1.677977912914468e-06,
+      "loss": 0.0283,
+      "step": 5636
+    },
+    {
+      "epoch": 0.8317226115824419,
+      "grad_norm": 7.045351982116699,
+      "learning_rate": 1.6751229325182194e-06,
+      "loss": 0.0397,
+      "step": 5637
+    },
+    {
+      "epoch": 0.8318701586130579,
+      "grad_norm": 7.252335548400879,
+      "learning_rate": 1.6722701609418257e-06,
+      "loss": 0.0823,
+      "step": 5638
+    },
+    {
+      "epoch": 0.8320177056436739,
+      "grad_norm": 1.0566500425338745,
+      "learning_rate": 1.669419598942209e-06,
+      "loss": 0.023,
+      "step": 5639
+    },
+    {
+      "epoch": 0.83216525267429,
+      "grad_norm": 0.6527475118637085,
+      "learning_rate": 1.6665712472757057e-06,
+      "loss": 0.0112,
+      "step": 5640
+    },
+    {
+      "epoch": 0.83216525267429,
+      "eval_accuracy": 0.9782923299565847,
+      "eval_f1": 0.9625935162094763,
+      "eval_loss": 0.0587141215801239,
+      "eval_precision": 0.9897435897435898,
+      "eval_recall": 0.9368932038834952,
+      "eval_runtime": 48.6591,
+      "eval_samples_per_second": 5.98,
+      "eval_steps_per_second": 0.206,
+      "step": 5640
+    },
+    {
+      "epoch": 0.8323127997049059,
+      "grad_norm": 1.9920316934585571,
+      "learning_rate": 1.6637251066980554e-06,
+      "loss": 0.0494,
+      "step": 5641
+    },
+    {
+      "epoch": 0.8324603467355219,
+      "grad_norm": 5.416084289550781,
+      "learning_rate": 1.660881177964424e-06,
+      "loss": 0.0762,
+      "step": 5642
+    },
+    {
+      "epoch": 0.832607893766138,
+      "grad_norm": 4.887792587280273,
+      "learning_rate": 1.6580394618293816e-06,
+      "loss": 0.0516,
+      "step": 5643
+    },
+    {
+      "epoch": 0.832755440796754,
+      "grad_norm": 4.527590274810791,
+      "learning_rate": 1.6551999590469091e-06,
+      "loss": 0.0678,
+      "step": 5644
+    },
+    {
+      "epoch": 0.8329029878273699,
+      "grad_norm": 1.1300346851348877,
+      "learning_rate": 1.6523626703704155e-06,
+      "loss": 0.0253,
+      "step": 5645
+    },
+    {
+      "epoch": 0.833050534857986,
+      "grad_norm": 3.3112246990203857,
+      "learning_rate": 1.6495275965527057e-06,
+      "loss": 0.0288,
+      "step": 5646
+    },
+    {
+      "epoch": 0.833198081888602,
+      "grad_norm": 1.675912618637085,
+      "learning_rate": 1.6466947383460007e-06,
+      "loss": 0.0304,
+      "step": 5647
+    },
+    {
+      "epoch": 0.833345628919218,
+      "grad_norm": 2.1557228565216064,
+      "learning_rate": 1.6438640965019403e-06,
+      "loss": 0.0278,
+      "step": 5648
+    },
+    {
+      "epoch": 0.833493175949834,
+      "grad_norm": 3.1431148052215576,
+      "learning_rate": 1.6410356717715724e-06,
+      "loss": 0.0571,
+      "step": 5649
+    },
+    {
+      "epoch": 0.83364072298045,
+      "grad_norm": 1.0991026163101196,
+      "learning_rate": 1.6382094649053525e-06,
+      "loss": 0.033,
+      "step": 5650
+    },
+    {
+      "epoch": 0.833788270011066,
+      "grad_norm": 4.678040981292725,
+      "learning_rate": 1.6353854766531552e-06,
+      "loss": 0.1281,
+      "step": 5651
+    },
+    {
+      "epoch": 0.8339358170416821,
+      "grad_norm": 3.0620951652526855,
+      "learning_rate": 1.6325637077642598e-06,
+      "loss": 0.0513,
+      "step": 5652
+    },
+    {
+      "epoch": 0.834083364072298,
+      "grad_norm": 2.518862724304199,
+      "learning_rate": 1.6297441589873587e-06,
+      "loss": 0.0453,
+      "step": 5653
+    },
+    {
+      "epoch": 0.834230911102914,
+      "grad_norm": 1.7291972637176514,
+      "learning_rate": 1.626926831070561e-06,
+      "loss": 0.052,
+      "step": 5654
+    },
+    {
+      "epoch": 0.8343784581335301,
+      "grad_norm": 1.7597038745880127,
+      "learning_rate": 1.624111724761377e-06,
+      "loss": 0.0265,
+      "step": 5655
+    },
+    {
+      "epoch": 0.8345260051641461,
+      "grad_norm": 3.891979217529297,
+      "learning_rate": 1.6212988408067354e-06,
+      "loss": 0.041,
+      "step": 5656
+    },
+    {
+      "epoch": 0.834673552194762,
+      "grad_norm": 3.0513861179351807,
+      "learning_rate": 1.6184881799529695e-06,
+      "loss": 0.0833,
+      "step": 5657
+    },
+    {
+      "epoch": 0.8348210992253781,
+      "grad_norm": 1.5519582033157349,
+      "learning_rate": 1.6156797429458227e-06,
+      "loss": 0.0377,
+      "step": 5658
+    },
+    {
+      "epoch": 0.8349686462559941,
+      "grad_norm": 0.7139090895652771,
+      "learning_rate": 1.6128735305304588e-06,
+      "loss": 0.0099,
+      "step": 5659
+    },
+    {
+      "epoch": 0.8351161932866101,
+      "grad_norm": 0.9821717143058777,
+      "learning_rate": 1.6100695434514379e-06,
+      "loss": 0.0214,
+      "step": 5660
+    },
+    {
+      "epoch": 0.8351161932866101,
+      "eval_accuracy": 0.9797395079594791,
+      "eval_f1": 0.9651741293532339,
+      "eval_loss": 0.057609084993600845,
+      "eval_precision": 0.9897959183673469,
+      "eval_recall": 0.941747572815534,
+      "eval_runtime": 48.5709,
+      "eval_samples_per_second": 5.991,
+      "eval_steps_per_second": 0.206,
+      "step": 5660
+    },
+    {
+      "epoch": 0.8352637403172262,
+      "grad_norm": 1.504457950592041,
+      "learning_rate": 1.607267782452735e-06,
+      "loss": 0.0335,
+      "step": 5661
+    },
+    {
+      "epoch": 0.8354112873478421,
+      "grad_norm": 2.8167669773101807,
+      "learning_rate": 1.6044682482777386e-06,
+      "loss": 0.1283,
+      "step": 5662
+    },
+    {
+      "epoch": 0.8355588343784581,
+      "grad_norm": 1.8938806056976318,
+      "learning_rate": 1.6016709416692367e-06,
+      "loss": 0.0409,
+      "step": 5663
+    },
+    {
+      "epoch": 0.8357063814090742,
+      "grad_norm": 1.4544540643692017,
+      "learning_rate": 1.5988758633694356e-06,
+      "loss": 0.0494,
+      "step": 5664
+    },
+    {
+      "epoch": 0.8358539284396902,
+      "grad_norm": 1.8806601762771606,
+      "learning_rate": 1.596083014119948e-06,
+      "loss": 0.0656,
+      "step": 5665
+    },
+    {
+      "epoch": 0.8360014754703061,
+      "grad_norm": 2.814997673034668,
+      "learning_rate": 1.5932923946617907e-06,
+      "loss": 0.084,
+      "step": 5666
+    },
+    {
+      "epoch": 0.8361490225009222,
+      "grad_norm": 2.6153440475463867,
+      "learning_rate": 1.590504005735396e-06,
+      "loss": 0.0475,
+      "step": 5667
+    },
+    {
+      "epoch": 0.8362965695315382,
+      "grad_norm": 4.640908718109131,
+      "learning_rate": 1.5877178480805954e-06,
+      "loss": 0.1177,
+      "step": 5668
+    },
+    {
+      "epoch": 0.8364441165621542,
+      "grad_norm": 1.7950429916381836,
+      "learning_rate": 1.5849339224366377e-06,
+      "loss": 0.0437,
+      "step": 5669
+    },
+    {
+      "epoch": 0.8365916635927702,
+      "grad_norm": 3.886131525039673,
+      "learning_rate": 1.5821522295421753e-06,
+      "loss": 0.0694,
+      "step": 5670
+    },
+    {
+      "epoch": 0.8367392106233862,
+      "grad_norm": 3.2617337703704834,
+      "learning_rate": 1.579372770135267e-06,
+      "loss": 0.1242,
+      "step": 5671
+    },
+    {
+      "epoch": 0.8368867576540022,
+      "grad_norm": 1.9004480838775635,
+      "learning_rate": 1.5765955449533743e-06,
+      "loss": 0.0319,
+      "step": 5672
+    },
+    {
+      "epoch": 0.8370343046846183,
+      "grad_norm": 1.8157849311828613,
+      "learning_rate": 1.573820554733384e-06,
+      "loss": 0.0164,
+      "step": 5673
+    },
+    {
+      "epoch": 0.8371818517152342,
+      "grad_norm": 1.7056431770324707,
+      "learning_rate": 1.5710478002115692e-06,
+      "loss": 0.0316,
+      "step": 5674
+    },
+    {
+      "epoch": 0.8373293987458502,
+      "grad_norm": 5.834029674530029,
+      "learning_rate": 1.5682772821236192e-06,
+      "loss": 0.1158,
+      "step": 5675
+    },
+    {
+      "epoch": 0.8374769457764663,
+      "grad_norm": 1.8330997228622437,
+      "learning_rate": 1.5655090012046315e-06,
+      "loss": 0.0559,
+      "step": 5676
+    },
+    {
+      "epoch": 0.8376244928070823,
+      "grad_norm": 3.6596038341522217,
+      "learning_rate": 1.562742958189104e-06,
+      "loss": 0.0708,
+      "step": 5677
+    },
+    {
+      "epoch": 0.8377720398376982,
+      "grad_norm": 1.3743090629577637,
+      "learning_rate": 1.5599791538109466e-06,
+      "loss": 0.023,
+      "step": 5678
+    },
+    {
+      "epoch": 0.8379195868683142,
+      "grad_norm": 2.024369716644287,
+      "learning_rate": 1.5572175888034747e-06,
+      "loss": 0.0466,
+      "step": 5679
+    },
+    {
+      "epoch": 0.8380671338989303,
+      "grad_norm": 1.4012556076049805,
+      "learning_rate": 1.554458263899402e-06,
+      "loss": 0.02,
+      "step": 5680
+    },
+    {
+      "epoch": 0.8380671338989303,
+      "eval_accuracy": 0.9811866859623734,
+      "eval_f1": 0.967741935483871,
+      "eval_loss": 0.05637633427977562,
+      "eval_precision": 0.9898477157360406,
+      "eval_recall": 0.9466019417475728,
+      "eval_runtime": 48.6506,
+      "eval_samples_per_second": 5.981,
+      "eval_steps_per_second": 0.206,
+      "step": 5680
+    },
+    {
+      "epoch": 0.8382146809295463,
+      "grad_norm": 2.209381103515625,
+      "learning_rate": 1.5517011798308612e-06,
+      "loss": 0.0758,
+      "step": 5681
+    },
+    {
+      "epoch": 0.8383622279601624,
+      "grad_norm": 2.144597291946411,
+      "learning_rate": 1.5489463373293768e-06,
+      "loss": 0.0765,
+      "step": 5682
+    },
+    {
+      "epoch": 0.8385097749907783,
+      "grad_norm": 4.175070762634277,
+      "learning_rate": 1.5461937371258862e-06,
+      "loss": 0.1402,
+      "step": 5683
+    },
+    {
+      "epoch": 0.8386573220213943,
+      "grad_norm": 3.235828399658203,
+      "learning_rate": 1.5434433799507331e-06,
+      "loss": 0.0699,
+      "step": 5684
+    },
+    {
+      "epoch": 0.8388048690520103,
+      "grad_norm": 6.306621551513672,
+      "learning_rate": 1.5406952665336616e-06,
+      "loss": 0.1684,
+      "step": 5685
+    },
+    {
+      "epoch": 0.8389524160826264,
+      "grad_norm": 2.249080181121826,
+      "learning_rate": 1.5379493976038185e-06,
+      "loss": 0.0817,
+      "step": 5686
+    },
+    {
+      "epoch": 0.8390999631132423,
+      "grad_norm": 4.360023498535156,
+      "learning_rate": 1.535205773889762e-06,
+      "loss": 0.0979,
+      "step": 5687
+    },
+    {
+      "epoch": 0.8392475101438583,
+      "grad_norm": 3.345550298690796,
+      "learning_rate": 1.532464396119453e-06,
+      "loss": 0.0952,
+      "step": 5688
+    },
+    {
+      "epoch": 0.8393950571744744,
+      "grad_norm": 0.9074431657791138,
+      "learning_rate": 1.529725265020251e-06,
+      "loss": 0.0163,
+      "step": 5689
+    },
+    {
+      "epoch": 0.8395426042050904,
+      "grad_norm": 1.0018547773361206,
+      "learning_rate": 1.5269883813189268e-06,
+      "loss": 0.0213,
+      "step": 5690
+    },
+    {
+      "epoch": 0.8396901512357063,
+      "grad_norm": 1.0021008253097534,
+      "learning_rate": 1.5242537457416472e-06,
+      "loss": 0.0224,
+      "step": 5691
+    },
+    {
+      "epoch": 0.8398376982663224,
+      "grad_norm": 2.912518262863159,
+      "learning_rate": 1.5215213590139888e-06,
+      "loss": 0.1009,
+      "step": 5692
+    },
+    {
+      "epoch": 0.8399852452969384,
+      "grad_norm": 1.1571531295776367,
+      "learning_rate": 1.5187912218609313e-06,
+      "loss": 0.0313,
+      "step": 5693
+    },
+    {
+      "epoch": 0.8401327923275544,
+      "grad_norm": 2.414637565612793,
+      "learning_rate": 1.516063335006851e-06,
+      "loss": 0.0815,
+      "step": 5694
+    },
+    {
+      "epoch": 0.8402803393581704,
+      "grad_norm": 2.117668628692627,
+      "learning_rate": 1.5133376991755366e-06,
+      "loss": 0.0555,
+      "step": 5695
+    },
+    {
+      "epoch": 0.8404278863887864,
+      "grad_norm": 2.501960515975952,
+      "learning_rate": 1.5106143150901698e-06,
+      "loss": 0.0639,
+      "step": 5696
+    },
+    {
+      "epoch": 0.8405754334194024,
+      "grad_norm": 1.5345666408538818,
+      "learning_rate": 1.5078931834733412e-06,
+      "loss": 0.0571,
+      "step": 5697
+    },
+    {
+      "epoch": 0.8407229804500185,
+      "grad_norm": 2.431872844696045,
+      "learning_rate": 1.5051743050470447e-06,
+      "loss": 0.0193,
+      "step": 5698
+    },
+    {
+      "epoch": 0.8408705274806344,
+      "grad_norm": 1.7443726062774658,
+      "learning_rate": 1.502457680532673e-06,
+      "loss": 0.0305,
+      "step": 5699
+    },
+    {
+      "epoch": 0.8410180745112504,
+      "grad_norm": 3.444777488708496,
+      "learning_rate": 1.4997433106510185e-06,
+      "loss": 0.0866,
+      "step": 5700
+    },
+    {
+      "epoch": 0.8410180745112504,
+      "eval_accuracy": 0.9797395079594791,
+      "eval_f1": 0.9653465346534653,
+      "eval_loss": 0.0559396967291832,
+      "eval_precision": 0.9848484848484849,
+      "eval_recall": 0.9466019417475728,
+      "eval_runtime": 49.9431,
+      "eval_samples_per_second": 5.827,
+      "eval_steps_per_second": 0.2,
+      "step": 5700
     }
   ],
   "logging_steps": 1,
@@ -42598,7 +43358,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.7247538975762022e+18,
+  "total_flos": 1.7555460633363743e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null