Training in progress, step 3800, checkpoint

last-checkpoint/optimizer_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a756bdeb458981b7ce36c49e33ebc00c7d3dff70f4a702671a5491255b2d614f
+oid sha256:0a6f7e2954a9d97b141f130afb1f6537cfa1498b75982ad5a659f80f10798f3d
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:068d624fa71bfdac56c777909bf351c636dbd999dea303af1789e20805885e9b
+oid sha256:ec2aa24808389e36190d6a559e86c2823bc4cecced5813cb42cf87bb8a27c1d6
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bae72db6b35d1bbed35cff7bbafc33aad004e4aa00ae84b3e5a6d2e6cde45c1
+oid sha256:ff0fe3fe681f1ece017f885e7aff7be8cf74cecbecde796cb74ad8d33c5e3bb0
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2621c5ebc5d5b39617c43c0cdfd61252b937441460321ca1d2877a952964357
+oid sha256:b1c44684053c782e845ec80d9c01caa70c72f417fce402b7a70b060934d3d618
 size 13990904

last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:624d3ba2b5b2d1ad12c4a7a9a22fa88d61729ec2635ebb0ee44fbff5b2a0fd73
+oid sha256:2feb6240b1fa4c83000600bf312599140c9c11234d9790dc0acb1f32c65ce8c3
 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:ccc1b3b458aa73a653e34cce670716400550c5fe6e53b34b3a09b9bcc1407b20
+oid sha256:5e2a02b3b5c5b25c66df88d2f816c53403e95842b3997fe42442480b9decbb8d
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80d7aecdb58a2ebc778d181e283b462112e90ad5f7ea7100562e2c4075ab111e
+oid sha256:93f52f928795f2be63de4c7a430a040d0aadc4f630c7a4a7b67082a4fcca649f
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cdc3a146873c921d0536d064cdfd89778215235151dbf9a0f8639ab11fc3c3b
+oid sha256:5e7a60b4d6678ee9ae36e85dfc2e9caae763e734f703df07f47c855dbf3a49f9
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e507be335c9a88326c94bf18d3e1aac91de6339f8df416cddbe6f157901c92aa
+oid sha256:69e6be6efaedfde2b1d47293e94b2707779f1cff15fb52ecf87684fc7c0ea2ca
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d7dcdb6999660c02d2cc5dad8d401f9648f8164ab4d8f788e986503a2421815
+oid sha256:a4ce4d4068f26b4f70f5edfb19ea73473a9c6bdf3acb5f93776af348e20e40ea
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb07725c26a04a53a1dfbb2c8ed5ae934aa3d7e8763c79ce1f6ae18a34c6c86c
+oid sha256:517c3e398b096ca6304c01d0cc911dc0136d57afb31dac7034f8eef86054f960
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:770d99fba16f63f53eb15af79df8e70bd147bc3446e69b566765fce35a06f2c8
+oid sha256:efadf3c427d313f3784af1685962dc461da9481c0b29cdb84aa82c99ffe9214e
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1e8a9ea075e95389f54df2c0467f896560203802589c351f4f852d5957e90b4
+oid sha256:85400f81f12f25b5a491d6620260edbf6b143335da6b8b8d01c86f20ff477568
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5459240132792328,
+  "epoch": 0.5606787163408337,
   "eval_steps": 20,
-  "global_step": 3700,
+  "global_step": 3800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -28139,6 +28139,766 @@
       "eval_samples_per_second": 5.932,
       "eval_steps_per_second": 0.204,
       "step": 3700
+    },
+    {
+      "epoch": 0.5460715603098487,
+      "grad_norm": 0.927797257900238,
+      "learning_rate": 1.0136497163466014e-05,
+      "loss": 0.0212,
+      "step": 3701
+    },
+    {
+      "epoch": 0.5462191073404647,
+      "grad_norm": 1.628825068473816,
+      "learning_rate": 1.0131346629144452e-05,
+      "loss": 0.0271,
+      "step": 3702
+    },
+    {
+      "epoch": 0.5463666543710808,
+      "grad_norm": 0.6106228232383728,
+      "learning_rate": 1.0126196059973e-05,
+      "loss": 0.0175,
+      "step": 3703
+    },
+    {
+      "epoch": 0.5465142014016968,
+      "grad_norm": 1.9554325342178345,
+      "learning_rate": 1.0121045457318247e-05,
+      "loss": 0.0704,
+      "step": 3704
+    },
+    {
+      "epoch": 0.5466617484323129,
+      "grad_norm": 2.2551918029785156,
+      "learning_rate": 1.0115894822546788e-05,
+      "loss": 0.0811,
+      "step": 3705
+    },
+    {
+      "epoch": 0.5468092954629288,
+      "grad_norm": 1.5803611278533936,
+      "learning_rate": 1.0110744157025234e-05,
+      "loss": 0.0474,
+      "step": 3706
+    },
+    {
+      "epoch": 0.5469568424935448,
+      "grad_norm": 1.926823377609253,
+      "learning_rate": 1.0105593462120196e-05,
+      "loss": 0.0307,
+      "step": 3707
+    },
+    {
+      "epoch": 0.5471043895241609,
+      "grad_norm": 1.9144130945205688,
+      "learning_rate": 1.0100442739198293e-05,
+      "loss": 0.0449,
+      "step": 3708
+    },
+    {
+      "epoch": 0.5472519365547769,
+      "grad_norm": 1.6707820892333984,
+      "learning_rate": 1.009529198962616e-05,
+      "loss": 0.041,
+      "step": 3709
+    },
+    {
+      "epoch": 0.5473994835853928,
+      "grad_norm": 1.5497639179229736,
+      "learning_rate": 1.0090141214770426e-05,
+      "loss": 0.0295,
+      "step": 3710
+    },
+    {
+      "epoch": 0.5475470306160088,
+      "grad_norm": 2.402508020401001,
+      "learning_rate": 1.008499041599774e-05,
+      "loss": 0.0531,
+      "step": 3711
+    },
+    {
+      "epoch": 0.5476945776466249,
+      "grad_norm": 1.2764594554901123,
+      "learning_rate": 1.0079839594674749e-05,
+      "loss": 0.0321,
+      "step": 3712
+    },
+    {
+      "epoch": 0.5478421246772409,
+      "grad_norm": 1.8888596296310425,
+      "learning_rate": 1.0074688752168104e-05,
+      "loss": 0.038,
+      "step": 3713
+    },
+    {
+      "epoch": 0.5479896717078568,
+      "grad_norm": 2.022836923599243,
+      "learning_rate": 1.0069537889844476e-05,
+      "loss": 0.0605,
+      "step": 3714
+    },
+    {
+      "epoch": 0.5481372187384729,
+      "grad_norm": 1.7803722620010376,
+      "learning_rate": 1.006438700907052e-05,
+      "loss": 0.0681,
+      "step": 3715
+    },
+    {
+      "epoch": 0.5482847657690889,
+      "grad_norm": 4.56878662109375,
+      "learning_rate": 1.0059236111212914e-05,
+      "loss": 0.1236,
+      "step": 3716
+    },
+    {
+      "epoch": 0.548432312799705,
+      "grad_norm": 0.7959854006767273,
+      "learning_rate": 1.005408519763833e-05,
+      "loss": 0.0145,
+      "step": 3717
+    },
+    {
+      "epoch": 0.5485798598303209,
+      "grad_norm": 6.06070613861084,
+      "learning_rate": 1.004893426971345e-05,
+      "loss": 0.0377,
+      "step": 3718
+    },
+    {
+      "epoch": 0.5487274068609369,
+      "grad_norm": 3.700913190841675,
+      "learning_rate": 1.004378332880496e-05,
+      "loss": 0.0278,
+      "step": 3719
+    },
+    {
+      "epoch": 0.5488749538915529,
+      "grad_norm": 5.320037364959717,
+      "learning_rate": 1.0038632376279535e-05,
+      "loss": 0.077,
+      "step": 3720
+    },
+    {
+      "epoch": 0.5488749538915529,
+      "eval_accuracy": 0.975397973950796,
+      "eval_f1": 0.9578163771712159,
+      "eval_loss": 0.05850488319993019,
+      "eval_precision": 0.9796954314720813,
+      "eval_recall": 0.9368932038834952,
+      "eval_runtime": 49.9661,
+      "eval_samples_per_second": 5.824,
+      "eval_steps_per_second": 0.2,
+      "step": 3720
+    },
+    {
+      "epoch": 0.549022500922169,
+      "grad_norm": 2.794523000717163,
+      "learning_rate": 1.0033481413503883e-05,
+      "loss": 0.0327,
+      "step": 3721
+    },
+    {
+      "epoch": 0.5491700479527849,
+      "grad_norm": 1.0081136226654053,
+      "learning_rate": 1.0028330441844678e-05,
+      "loss": 0.0218,
+      "step": 3722
+    },
+    {
+      "epoch": 0.5493175949834009,
+      "grad_norm": 2.727607011795044,
+      "learning_rate": 1.002317946266863e-05,
+      "loss": 0.0634,
+      "step": 3723
+    },
+    {
+      "epoch": 0.549465142014017,
+      "grad_norm": 0.6229975819587708,
+      "learning_rate": 1.001802847734243e-05,
+      "loss": 0.0194,
+      "step": 3724
+    },
+    {
+      "epoch": 0.549612689044633,
+      "grad_norm": 5.12562894821167,
+      "learning_rate": 1.0012877487232774e-05,
+      "loss": 0.0319,
+      "step": 3725
+    },
+    {
+      "epoch": 0.5497602360752489,
+      "grad_norm": 2.87324595451355,
+      "learning_rate": 1.0007726493706367e-05,
+      "loss": 0.0708,
+      "step": 3726
+    },
+    {
+      "epoch": 0.549907783105865,
+      "grad_norm": 5.746551036834717,
+      "learning_rate": 1.0002575498129905e-05,
+      "loss": 0.0559,
+      "step": 3727
+    },
+    {
+      "epoch": 0.550055330136481,
+      "grad_norm": 2.7586886882781982,
+      "learning_rate": 9.997424501870095e-06,
+      "loss": 0.0571,
+      "step": 3728
+    },
+    {
+      "epoch": 0.550202877167097,
+      "grad_norm": 2.8424432277679443,
+      "learning_rate": 9.992273506293636e-06,
+      "loss": 0.1035,
+      "step": 3729
+    },
+    {
+      "epoch": 0.5503504241977131,
+      "grad_norm": 3.6614279747009277,
+      "learning_rate": 9.987122512767229e-06,
+      "loss": 0.0861,
+      "step": 3730
+    },
+    {
+      "epoch": 0.550497971228329,
+      "grad_norm": 1.9463998079299927,
+      "learning_rate": 9.981971522657575e-06,
+      "loss": 0.0671,
+      "step": 3731
+    },
+    {
+      "epoch": 0.550645518258945,
+      "grad_norm": 1.3599612712860107,
+      "learning_rate": 9.976820537331375e-06,
+      "loss": 0.0494,
+      "step": 3732
+    },
+    {
+      "epoch": 0.5507930652895611,
+      "grad_norm": 2.320894956588745,
+      "learning_rate": 9.971669558155322e-06,
+      "loss": 0.0593,
+      "step": 3733
+    },
+    {
+      "epoch": 0.5509406123201771,
+      "grad_norm": 2.7197000980377197,
+      "learning_rate": 9.96651858649612e-06,
+      "loss": 0.1013,
+      "step": 3734
+    },
+    {
+      "epoch": 0.551088159350793,
+      "grad_norm": 1.2852067947387695,
+      "learning_rate": 9.961367623720467e-06,
+      "loss": 0.0303,
+      "step": 3735
+    },
+    {
+      "epoch": 0.5512357063814091,
+      "grad_norm": 2.8085477352142334,
+      "learning_rate": 9.956216671195047e-06,
+      "loss": 0.0701,
+      "step": 3736
+    },
+    {
+      "epoch": 0.5513832534120251,
+      "grad_norm": 2.4579927921295166,
+      "learning_rate": 9.951065730286553e-06,
+      "loss": 0.0677,
+      "step": 3737
+    },
+    {
+      "epoch": 0.5515308004426411,
+      "grad_norm": 2.144411325454712,
+      "learning_rate": 9.945914802361672e-06,
+      "loss": 0.0607,
+      "step": 3738
+    },
+    {
+      "epoch": 0.5516783474732571,
+      "grad_norm": 1.9104830026626587,
+      "learning_rate": 9.940763888787088e-06,
+      "loss": 0.0403,
+      "step": 3739
+    },
+    {
+      "epoch": 0.5518258945038731,
+      "grad_norm": 2.6878914833068848,
+      "learning_rate": 9.935612990929482e-06,
+      "loss": 0.0403,
+      "step": 3740
+    },
+    {
+      "epoch": 0.5518258945038731,
+      "eval_accuracy": 0.9782923299565847,
+      "eval_f1": 0.9629629629629629,
+      "eval_loss": 0.05521642044186592,
+      "eval_precision": 0.9798994974874372,
+      "eval_recall": 0.9466019417475728,
+      "eval_runtime": 49.6835,
+      "eval_samples_per_second": 5.857,
+      "eval_steps_per_second": 0.201,
+      "step": 3740
+    },
+    {
+      "epoch": 0.5519734415344891,
+      "grad_norm": 1.8800990581512451,
+      "learning_rate": 9.930462110155529e-06,
+      "loss": 0.0719,
+      "step": 3741
+    },
+    {
+      "epoch": 0.5521209885651052,
+      "grad_norm": 1.9986878633499146,
+      "learning_rate": 9.925311247831896e-06,
+      "loss": 0.0581,
+      "step": 3742
+    },
+    {
+      "epoch": 0.5522685355957211,
+      "grad_norm": 3.641836166381836,
+      "learning_rate": 9.920160405325254e-06,
+      "loss": 0.0726,
+      "step": 3743
+    },
+    {
+      "epoch": 0.5524160826263371,
+      "grad_norm": 5.52808141708374,
+      "learning_rate": 9.915009584002263e-06,
+      "loss": 0.0852,
+      "step": 3744
+    },
+    {
+      "epoch": 0.5525636296569532,
+      "grad_norm": 1.0799669027328491,
+      "learning_rate": 9.909858785229576e-06,
+      "loss": 0.0342,
+      "step": 3745
+    },
+    {
+      "epoch": 0.5527111766875692,
+      "grad_norm": 3.680673599243164,
+      "learning_rate": 9.904708010373847e-06,
+      "loss": 0.0844,
+      "step": 3746
+    },
+    {
+      "epoch": 0.5528587237181851,
+      "grad_norm": 1.3180592060089111,
+      "learning_rate": 9.899557260801707e-06,
+      "loss": 0.0474,
+      "step": 3747
+    },
+    {
+      "epoch": 0.5530062707488012,
+      "grad_norm": 2.9669387340545654,
+      "learning_rate": 9.894406537879805e-06,
+      "loss": 0.083,
+      "step": 3748
+    },
+    {
+      "epoch": 0.5531538177794172,
+      "grad_norm": 3.1382808685302734,
+      "learning_rate": 9.88925584297477e-06,
+      "loss": 0.0916,
+      "step": 3749
+    },
+    {
+      "epoch": 0.5533013648100332,
+      "grad_norm": 4.144131183624268,
+      "learning_rate": 9.884105177453216e-06,
+      "loss": 0.0752,
+      "step": 3750
+    },
+    {
+      "epoch": 0.5534489118406493,
+      "grad_norm": 1.2315720319747925,
+      "learning_rate": 9.878954542681758e-06,
+      "loss": 0.0259,
+      "step": 3751
+    },
+    {
+      "epoch": 0.5535964588712652,
+      "grad_norm": 3.0691041946411133,
+      "learning_rate": 9.873803940027004e-06,
+      "loss": 0.0566,
+      "step": 3752
+    },
+    {
+      "epoch": 0.5537440059018812,
+      "grad_norm": 1.3682444095611572,
+      "learning_rate": 9.868653370855552e-06,
+      "loss": 0.0314,
+      "step": 3753
+    },
+    {
+      "epoch": 0.5538915529324973,
+      "grad_norm": 1.8178353309631348,
+      "learning_rate": 9.863502836533988e-06,
+      "loss": 0.0739,
+      "step": 3754
+    },
+    {
+      "epoch": 0.5540390999631133,
+      "grad_norm": 1.305626392364502,
+      "learning_rate": 9.858352338428894e-06,
+      "loss": 0.0497,
+      "step": 3755
+    },
+    {
+      "epoch": 0.5541866469937292,
+      "grad_norm": 2.9078972339630127,
+      "learning_rate": 9.853201877906836e-06,
+      "loss": 0.0698,
+      "step": 3756
+    },
+    {
+      "epoch": 0.5543341940243453,
+      "grad_norm": 2.165985584259033,
+      "learning_rate": 9.848051456334373e-06,
+      "loss": 0.0694,
+      "step": 3757
+    },
+    {
+      "epoch": 0.5544817410549613,
+      "grad_norm": 2.040043830871582,
+      "learning_rate": 9.84290107507806e-06,
+      "loss": 0.0768,
+      "step": 3758
+    },
+    {
+      "epoch": 0.5546292880855773,
+      "grad_norm": 3.4539248943328857,
+      "learning_rate": 9.83775073550443e-06,
+      "loss": 0.0918,
+      "step": 3759
+    },
+    {
+      "epoch": 0.5547768351161932,
+      "grad_norm": 1.5912948846817017,
+      "learning_rate": 9.832600438980012e-06,
+      "loss": 0.0228,
+      "step": 3760
+    },
+    {
+      "epoch": 0.5547768351161932,
+      "eval_accuracy": 0.9797395079594791,
+      "eval_f1": 0.9653465346534653,
+      "eval_loss": 0.054135989397764206,
+      "eval_precision": 0.9848484848484849,
+      "eval_recall": 0.9466019417475728,
+      "eval_runtime": 49.6086,
+      "eval_samples_per_second": 5.866,
+      "eval_steps_per_second": 0.202,
+      "step": 3760
+    },
+    {
+      "epoch": 0.5549243821468093,
+      "grad_norm": 2.391852378845215,
+      "learning_rate": 9.82745018687132e-06,
+      "loss": 0.117,
+      "step": 3761
+    },
+    {
+      "epoch": 0.5550719291774253,
+      "grad_norm": 2.916215419769287,
+      "learning_rate": 9.822299980544862e-06,
+      "loss": 0.0331,
+      "step": 3762
+    },
+    {
+      "epoch": 0.5552194762080414,
+      "grad_norm": 1.3798753023147583,
+      "learning_rate": 9.81714982136713e-06,
+      "loss": 0.0258,
+      "step": 3763
+    },
+    {
+      "epoch": 0.5553670232386573,
+      "grad_norm": 5.286415100097656,
+      "learning_rate": 9.811999710704601e-06,
+      "loss": 0.0462,
+      "step": 3764
+    },
+    {
+      "epoch": 0.5555145702692733,
+      "grad_norm": 1.4460058212280273,
+      "learning_rate": 9.806849649923742e-06,
+      "loss": 0.0545,
+      "step": 3765
+    },
+    {
+      "epoch": 0.5556621172998893,
+      "grad_norm": 1.8188203573226929,
+      "learning_rate": 9.801699640391001e-06,
+      "loss": 0.0381,
+      "step": 3766
+    },
+    {
+      "epoch": 0.5558096643305054,
+      "grad_norm": 1.858678936958313,
+      "learning_rate": 9.79654968347283e-06,
+      "loss": 0.0585,
+      "step": 3767
+    },
+    {
+      "epoch": 0.5559572113611213,
+      "grad_norm": 2.441951036453247,
+      "learning_rate": 9.791399780535648e-06,
+      "loss": 0.0571,
+      "step": 3768
+    },
+    {
+      "epoch": 0.5561047583917373,
+      "grad_norm": 1.4246195554733276,
+      "learning_rate": 9.786249932945865e-06,
+      "loss": 0.0715,
+      "step": 3769
+    },
+    {
+      "epoch": 0.5562523054223534,
+      "grad_norm": 1.7215012311935425,
+      "learning_rate": 9.781100142069879e-06,
+      "loss": 0.0237,
+      "step": 3770
+    },
+    {
+      "epoch": 0.5563998524529694,
+      "grad_norm": 1.2334809303283691,
+      "learning_rate": 9.775950409274071e-06,
+      "loss": 0.048,
+      "step": 3771
+    },
+    {
+      "epoch": 0.5565473994835854,
+      "grad_norm": 1.7480311393737793,
+      "learning_rate": 9.770800735924811e-06,
+      "loss": 0.0436,
+      "step": 3772
+    },
+    {
+      "epoch": 0.5566949465142014,
+      "grad_norm": 1.593654751777649,
+      "learning_rate": 9.765651123388448e-06,
+      "loss": 0.0335,
+      "step": 3773
+    },
+    {
+      "epoch": 0.5568424935448174,
+      "grad_norm": 1.513624668121338,
+      "learning_rate": 9.760501573031314e-06,
+      "loss": 0.0529,
+      "step": 3774
+    },
+    {
+      "epoch": 0.5569900405754334,
+      "grad_norm": 1.5197149515151978,
+      "learning_rate": 9.755352086219733e-06,
+      "loss": 0.0559,
+      "step": 3775
+    },
+    {
+      "epoch": 0.5571375876060495,
+      "grad_norm": 1.9495011568069458,
+      "learning_rate": 9.750202664319993e-06,
+      "loss": 0.0655,
+      "step": 3776
+    },
+    {
+      "epoch": 0.5572851346366654,
+      "grad_norm": 0.9071054458618164,
+      "learning_rate": 9.745053308698392e-06,
+      "loss": 0.0193,
+      "step": 3777
+    },
+    {
+      "epoch": 0.5574326816672814,
+      "grad_norm": 1.7866899967193604,
+      "learning_rate": 9.739904020721193e-06,
+      "loss": 0.0312,
+      "step": 3778
+    },
+    {
+      "epoch": 0.5575802286978975,
+      "grad_norm": 3.7618916034698486,
+      "learning_rate": 9.734754801754643e-06,
+      "loss": 0.0442,
+      "step": 3779
+    },
+    {
+      "epoch": 0.5577277757285135,
+      "grad_norm": 1.682389497756958,
+      "learning_rate": 9.729605653164962e-06,
+      "loss": 0.0321,
+      "step": 3780
+    },
+    {
+      "epoch": 0.5577277757285135,
+      "eval_accuracy": 0.9797395079594791,
+      "eval_f1": 0.9651741293532339,
+      "eval_loss": 0.053348224610090256,
+      "eval_precision": 0.9897959183673469,
+      "eval_recall": 0.941747572815534,
+      "eval_runtime": 49.4818,
+      "eval_samples_per_second": 5.881,
+      "eval_steps_per_second": 0.202,
+      "step": 3780
+    },
+    {
+      "epoch": 0.5578753227591294,
+      "grad_norm": 2.075875759124756,
+      "learning_rate": 9.724456576318383e-06,
+      "loss": 0.0552,
+      "step": 3781
+    },
+    {
+      "epoch": 0.5580228697897455,
+      "grad_norm": 5.893950462341309,
+      "learning_rate": 9.71930757258108e-06,
+      "loss": 0.1236,
+      "step": 3782
+    },
+    {
+      "epoch": 0.5581704168203615,
+      "grad_norm": 1.4630471467971802,
+      "learning_rate": 9.714158643319232e-06,
+      "loss": 0.0175,
+      "step": 3783
+    },
+    {
+      "epoch": 0.5583179638509775,
+      "grad_norm": 6.606502532958984,
+      "learning_rate": 9.709009789898994e-06,
+      "loss": 0.0888,
+      "step": 3784
+    },
+    {
+      "epoch": 0.5584655108815935,
+      "grad_norm": 1.5867756605148315,
+      "learning_rate": 9.703861013686494e-06,
+      "loss": 0.0337,
+      "step": 3785
+    },
+    {
+      "epoch": 0.5586130579122095,
+      "grad_norm": 3.8968021869659424,
+      "learning_rate": 9.69871231604785e-06,
+      "loss": 0.0457,
+      "step": 3786
+    },
+    {
+      "epoch": 0.5587606049428255,
+      "grad_norm": 0.7190189957618713,
+      "learning_rate": 9.693563698349151e-06,
+      "loss": 0.0195,
+      "step": 3787
+    },
+    {
+      "epoch": 0.5589081519734416,
+      "grad_norm": 1.2359848022460938,
+      "learning_rate": 9.688415161956468e-06,
+      "loss": 0.0381,
+      "step": 3788
+    },
+    {
+      "epoch": 0.5590556990040575,
+      "grad_norm": 2.6988964080810547,
+      "learning_rate": 9.683266708235855e-06,
+      "loss": 0.0293,
+      "step": 3789
+    },
+    {
+      "epoch": 0.5592032460346735,
+      "grad_norm": 3.265552043914795,
+      "learning_rate": 9.678118338553325e-06,
+      "loss": 0.1007,
+      "step": 3790
+    },
+    {
+      "epoch": 0.5593507930652896,
+      "grad_norm": 1.6083853244781494,
+      "learning_rate": 9.672970054274896e-06,
+      "loss": 0.0314,
+      "step": 3791
+    },
+    {
+      "epoch": 0.5594983400959056,
+      "grad_norm": 2.069735050201416,
+      "learning_rate": 9.667821856766548e-06,
+      "loss": 0.032,
+      "step": 3792
+    },
+    {
+      "epoch": 0.5596458871265215,
+      "grad_norm": 3.529930830001831,
+      "learning_rate": 9.662673747394237e-06,
+      "loss": 0.133,
+      "step": 3793
+    },
+    {
+      "epoch": 0.5597934341571376,
+      "grad_norm": 1.4641337394714355,
+      "learning_rate": 9.657525727523897e-06,
+      "loss": 0.0386,
+      "step": 3794
+    },
+    {
+      "epoch": 0.5599409811877536,
+      "grad_norm": 2.047414779663086,
+      "learning_rate": 9.652377798521442e-06,
+      "loss": 0.0156,
+      "step": 3795
+    },
+    {
+      "epoch": 0.5600885282183696,
+      "grad_norm": 2.2744388580322266,
+      "learning_rate": 9.647229961752761e-06,
+      "loss": 0.0385,
+      "step": 3796
+    },
+    {
+      "epoch": 0.5602360752489857,
+      "grad_norm": 8.05351448059082,
+      "learning_rate": 9.642082218583718e-06,
+      "loss": 0.0934,
+      "step": 3797
+    },
+    {
+      "epoch": 0.5603836222796016,
+      "grad_norm": 1.128142237663269,
+      "learning_rate": 9.636934570380147e-06,
+      "loss": 0.0389,
+      "step": 3798
+    },
+    {
+      "epoch": 0.5605311693102176,
+      "grad_norm": 1.107566237449646,
+      "learning_rate": 9.631787018507864e-06,
+      "loss": 0.0389,
+      "step": 3799
+    },
+    {
+      "epoch": 0.5606787163408337,
+      "grad_norm": 2.5889945030212402,
+      "learning_rate": 9.626639564332659e-06,
+      "loss": 0.0698,
+      "step": 3800
+    },
+    {
+      "epoch": 0.5606787163408337,
+      "eval_accuracy": 0.9797395079594791,
+      "eval_f1": 0.9655172413793104,
+      "eval_loss": 0.05252087116241455,
+      "eval_precision": 0.98,
+      "eval_recall": 0.9514563106796117,
+      "eval_runtime": 50.0962,
+      "eval_samples_per_second": 5.809,
+      "eval_steps_per_second": 0.2,
+      "step": 3800
     }
   ],
   "logging_steps": 1,
@@ -28158,7 +28918,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1398356968155382e+18,
+  "total_flos": 1.1707223021117768e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null