Training in progress, step 3700, checkpoint

last-checkpoint/optimizer_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20341a5db0928170548e9d4eb5993cb2e15527b53cbd9d37ae4eefd083dd738f
+oid sha256:a756bdeb458981b7ce36c49e33ebc00c7d3dff70f4a702671a5491255b2d614f
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37d0655a5c6ff373dfb712f627106345ec6d39275d8f6710e47b1e421e5fc12f
+oid sha256:068d624fa71bfdac56c777909bf351c636dbd999dea303af1789e20805885e9b
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bb5d4ff1981eedbfa382a52daaf94f5e4d327c2791ddbba8ce42947f1faed80
+oid sha256:9bae72db6b35d1bbed35cff7bbafc33aad004e4aa00ae84b3e5a6d2e6cde45c1
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9948d5b8cf09dcdbdfb9a349a8d0b29905c49a16863a96357c9d2a167d4594b6
+oid sha256:a2621c5ebc5d5b39617c43c0cdfd61252b937441460321ca1d2877a952964357
 size 13990904

last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:773f63cfbbca499e57a6b1c26f07d1ff64a12064f8efc5697a5c6ec4acc3f9af
+oid sha256:624d3ba2b5b2d1ad12c4a7a9a22fa88d61729ec2635ebb0ee44fbff5b2a0fd73
 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:d848ac36c96e3361918d5881a58962bbc9487ac40028bf8166aa8cf052ba2224
+oid sha256:ccc1b3b458aa73a653e34cce670716400550c5fe6e53b34b3a09b9bcc1407b20
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:996552dc812062afe63350faae11d499e4888d07ecd9389eb16dbdd953080b05
+oid sha256:80d7aecdb58a2ebc778d181e283b462112e90ad5f7ea7100562e2c4075ab111e
 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:e35b965f00c20776496b1a86953ce335b1405f30773e8ad65847507becdffb40
+oid sha256:6cdc3a146873c921d0536d064cdfd89778215235151dbf9a0f8639ab11fc3c3b
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e5808effcdebd7a3be2031acb94a582a6b2acd7fdded70ad918c0e244b5af31
+oid sha256:e507be335c9a88326c94bf18d3e1aac91de6339f8df416cddbe6f157901c92aa
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b659774061b4a9fe1771f5b849cb61766eb1e83dff28b336947fdd50ba2c425
+oid sha256:6d7dcdb6999660c02d2cc5dad8d401f9648f8164ab4d8f788e986503a2421815
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3073e049caa29de490cb95f0c4ff8156a42990acb73fc31545188bb0c56a241c
+oid sha256:eb07725c26a04a53a1dfbb2c8ed5ae934aa3d7e8763c79ce1f6ae18a34c6c86c
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03a1c9f69774d333fb89fa1471ffc1f35ad85f1122c910027cf7e50924e37c9c
+oid sha256:770d99fba16f63f53eb15af79df8e70bd147bc3446e69b566765fce35a06f2c8
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9597d79022068ceebb9509c33370c3e389771e5b77adc2a3470d46a567aa4406
+oid sha256:c1e8a9ea075e95389f54df2c0467f896560203802589c351f4f852d5957e90b4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5311693102176319,
+  "epoch": 0.5459240132792328,
   "eval_steps": 20,
-  "global_step": 3600,
+  "global_step": 3700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -27379,6 +27379,766 @@
       "eval_samples_per_second": 5.79,
       "eval_steps_per_second": 0.199,
       "step": 3600
+    },
+    {
+      "epoch": 0.5313168572482478,
+      "grad_norm": 2.427949905395508,
+      "learning_rate": 1.0651140033091978e-05,
+      "loss": 0.0438,
+      "step": 3601
+    },
+    {
+      "epoch": 0.5314644042788639,
+      "grad_norm": 2.9920191764831543,
+      "learning_rate": 1.0645999881901995e-05,
+      "loss": 0.0779,
+      "step": 3602
+    },
+    {
+      "epoch": 0.5316119513094799,
+      "grad_norm": 2.497612714767456,
+      "learning_rate": 1.0640859559310402e-05,
+      "loss": 0.0447,
+      "step": 3603
+    },
+    {
+      "epoch": 0.531759498340096,
+      "grad_norm": 1.1314340829849243,
+      "learning_rate": 1.0635719066681064e-05,
+      "loss": 0.0263,
+      "step": 3604
+    },
+    {
+      "epoch": 0.5319070453707119,
+      "grad_norm": 1.788355827331543,
+      "learning_rate": 1.0630578405377894e-05,
+      "loss": 0.0318,
+      "step": 3605
+    },
+    {
+      "epoch": 0.5320545924013279,
+      "grad_norm": 2.9042913913726807,
+      "learning_rate": 1.062543757676485e-05,
+      "loss": 0.0462,
+      "step": 3606
+    },
+    {
+      "epoch": 0.5322021394319439,
+      "grad_norm": 3.9081053733825684,
+      "learning_rate": 1.0620296582205946e-05,
+      "loss": 0.1665,
+      "step": 3607
+    },
+    {
+      "epoch": 0.53234968646256,
+      "grad_norm": 2.334308385848999,
+      "learning_rate": 1.0615155423065218e-05,
+      "loss": 0.0879,
+      "step": 3608
+    },
+    {
+      "epoch": 0.5324972334931759,
+      "grad_norm": 2.932739734649658,
+      "learning_rate": 1.0610014100706768e-05,
+      "loss": 0.1005,
+      "step": 3609
+    },
+    {
+      "epoch": 0.5326447805237919,
+      "grad_norm": 1.4589275121688843,
+      "learning_rate": 1.0604872616494722e-05,
+      "loss": 0.0296,
+      "step": 3610
+    },
+    {
+      "epoch": 0.532792327554408,
+      "grad_norm": 2.4524049758911133,
+      "learning_rate": 1.059973097179326e-05,
+      "loss": 0.0809,
+      "step": 3611
+    },
+    {
+      "epoch": 0.532939874585024,
+      "grad_norm": 4.211121082305908,
+      "learning_rate": 1.0594589167966606e-05,
+      "loss": 0.1157,
+      "step": 3612
+    },
+    {
+      "epoch": 0.5330874216156399,
+      "grad_norm": 2.3657655715942383,
+      "learning_rate": 1.058944720637902e-05,
+      "loss": 0.0435,
+      "step": 3613
+    },
+    {
+      "epoch": 0.533234968646256,
+      "grad_norm": 3.1218788623809814,
+      "learning_rate": 1.058430508839481e-05,
+      "loss": 0.1024,
+      "step": 3614
+    },
+    {
+      "epoch": 0.533382515676872,
+      "grad_norm": 6.471559524536133,
+      "learning_rate": 1.0579162815378314e-05,
+      "loss": 0.0711,
+      "step": 3615
+    },
+    {
+      "epoch": 0.533530062707488,
+      "grad_norm": 2.9321231842041016,
+      "learning_rate": 1.0574020388693926e-05,
+      "loss": 0.0695,
+      "step": 3616
+    },
+    {
+      "epoch": 0.5336776097381041,
+      "grad_norm": 3.0945262908935547,
+      "learning_rate": 1.0568877809706072e-05,
+      "loss": 0.0614,
+      "step": 3617
+    },
+    {
+      "epoch": 0.53382515676872,
+      "grad_norm": 2.731660842895508,
+      "learning_rate": 1.056373507977922e-05,
+      "loss": 0.1243,
+      "step": 3618
+    },
+    {
+      "epoch": 0.533972703799336,
+      "grad_norm": 2.141627550125122,
+      "learning_rate": 1.0558592200277878e-05,
+      "loss": 0.0508,
+      "step": 3619
+    },
+    {
+      "epoch": 0.5341202508299521,
+      "grad_norm": 2.444028377532959,
+      "learning_rate": 1.0553449172566592e-05,
+      "loss": 0.0249,
+      "step": 3620
+    },
+    {
+      "epoch": 0.5341202508299521,
+      "eval_accuracy": 0.9739507959479016,
+      "eval_f1": 0.9552238805970149,
+      "eval_loss": 0.06539621949195862,
+      "eval_precision": 0.9795918367346939,
+      "eval_recall": 0.9320388349514563,
+      "eval_runtime": 48.9358,
+      "eval_samples_per_second": 5.947,
+      "eval_steps_per_second": 0.204,
+      "step": 3620
+    },
+    {
+      "epoch": 0.5342677978605681,
+      "grad_norm": 1.7489478588104248,
+      "learning_rate": 1.0548305998009957e-05,
+      "loss": 0.0331,
+      "step": 3621
+    },
+    {
+      "epoch": 0.534415344891184,
+      "grad_norm": 3.899421453475952,
+      "learning_rate": 1.054316267797259e-05,
+      "loss": 0.0584,
+      "step": 3622
+    },
+    {
+      "epoch": 0.5345628919218001,
+      "grad_norm": 1.6799280643463135,
+      "learning_rate": 1.053801921381916e-05,
+      "loss": 0.0229,
+      "step": 3623
+    },
+    {
+      "epoch": 0.5347104389524161,
+      "grad_norm": 2.7103888988494873,
+      "learning_rate": 1.0532875606914372e-05,
+      "loss": 0.1122,
+      "step": 3624
+    },
+    {
+      "epoch": 0.5348579859830321,
+      "grad_norm": 2.4744038581848145,
+      "learning_rate": 1.0527731858622962e-05,
+      "loss": 0.0386,
+      "step": 3625
+    },
+    {
+      "epoch": 0.5350055330136481,
+      "grad_norm": 1.2592852115631104,
+      "learning_rate": 1.0522587970309715e-05,
+      "loss": 0.0332,
+      "step": 3626
+    },
+    {
+      "epoch": 0.5351530800442641,
+      "grad_norm": 1.2552969455718994,
+      "learning_rate": 1.0517443943339438e-05,
+      "loss": 0.0467,
+      "step": 3627
+    },
+    {
+      "epoch": 0.5353006270748801,
+      "grad_norm": 2.6253955364227295,
+      "learning_rate": 1.0512299779076995e-05,
+      "loss": 0.0578,
+      "step": 3628
+    },
+    {
+      "epoch": 0.5354481741054962,
+      "grad_norm": 3.4663279056549072,
+      "learning_rate": 1.0507155478887263e-05,
+      "loss": 0.0606,
+      "step": 3629
+    },
+    {
+      "epoch": 0.5355957211361121,
+      "grad_norm": 2.210115432739258,
+      "learning_rate": 1.0502011044135176e-05,
+      "loss": 0.0837,
+      "step": 3630
+    },
+    {
+      "epoch": 0.5357432681667281,
+      "grad_norm": 1.6879552602767944,
+      "learning_rate": 1.049686647618569e-05,
+      "loss": 0.0416,
+      "step": 3631
+    },
+    {
+      "epoch": 0.5358908151973442,
+      "grad_norm": 2.3775551319122314,
+      "learning_rate": 1.0491721776403802e-05,
+      "loss": 0.0544,
+      "step": 3632
+    },
+    {
+      "epoch": 0.5360383622279602,
+      "grad_norm": 2.4179673194885254,
+      "learning_rate": 1.0486576946154545e-05,
+      "loss": 0.0796,
+      "step": 3633
+    },
+    {
+      "epoch": 0.5361859092585761,
+      "grad_norm": 4.693197250366211,
+      "learning_rate": 1.048143198680298e-05,
+      "loss": 0.1065,
+      "step": 3634
+    },
+    {
+      "epoch": 0.5363334562891922,
+      "grad_norm": 1.2805655002593994,
+      "learning_rate": 1.047628689971421e-05,
+      "loss": 0.0424,
+      "step": 3635
+    },
+    {
+      "epoch": 0.5364810033198082,
+      "grad_norm": 1.463444709777832,
+      "learning_rate": 1.0471141686253367e-05,
+      "loss": 0.0536,
+      "step": 3636
+    },
+    {
+      "epoch": 0.5366285503504242,
+      "grad_norm": 1.8686429262161255,
+      "learning_rate": 1.0465996347785621e-05,
+      "loss": 0.052,
+      "step": 3637
+    },
+    {
+      "epoch": 0.5367760973810402,
+      "grad_norm": 2.3696820735931396,
+      "learning_rate": 1.0460850885676173e-05,
+      "loss": 0.0637,
+      "step": 3638
+    },
+    {
+      "epoch": 0.5369236444116562,
+      "grad_norm": 1.668507695198059,
+      "learning_rate": 1.045570530129025e-05,
+      "loss": 0.0323,
+      "step": 3639
+    },
+    {
+      "epoch": 0.5370711914422722,
+      "grad_norm": 6.714794158935547,
+      "learning_rate": 1.0450559595993126e-05,
+      "loss": 0.131,
+      "step": 3640
+    },
+    {
+      "epoch": 0.5370711914422722,
+      "eval_accuracy": 0.9739507959479016,
+      "eval_f1": 0.9560975609756097,
+      "eval_loss": 0.05963349714875221,
+      "eval_precision": 0.9607843137254902,
+      "eval_recall": 0.9514563106796117,
+      "eval_runtime": 49.0203,
+      "eval_samples_per_second": 5.936,
+      "eval_steps_per_second": 0.204,
+      "step": 3640
+    },
+    {
+      "epoch": 0.5372187384728883,
+      "grad_norm": 1.5180429220199585,
+      "learning_rate": 1.044541377115009e-05,
+      "loss": 0.0472,
+      "step": 3641
+    },
+    {
+      "epoch": 0.5373662855035043,
+      "grad_norm": 2.118589162826538,
+      "learning_rate": 1.0440267828126478e-05,
+      "loss": 0.0403,
+      "step": 3642
+    },
+    {
+      "epoch": 0.5375138325341202,
+      "grad_norm": 1.6448218822479248,
+      "learning_rate": 1.0435121768287652e-05,
+      "loss": 0.0486,
+      "step": 3643
+    },
+    {
+      "epoch": 0.5376613795647363,
+      "grad_norm": 2.6264731884002686,
+      "learning_rate": 1.0429975592998998e-05,
+      "loss": 0.0305,
+      "step": 3644
+    },
+    {
+      "epoch": 0.5378089265953523,
+      "grad_norm": 1.7372239828109741,
+      "learning_rate": 1.0424829303625941e-05,
+      "loss": 0.0364,
+      "step": 3645
+    },
+    {
+      "epoch": 0.5379564736259683,
+      "grad_norm": 1.8526792526245117,
+      "learning_rate": 1.0419682901533934e-05,
+      "loss": 0.0309,
+      "step": 3646
+    },
+    {
+      "epoch": 0.5381040206565842,
+      "grad_norm": 1.8069508075714111,
+      "learning_rate": 1.041453638808846e-05,
+      "loss": 0.0466,
+      "step": 3647
+    },
+    {
+      "epoch": 0.5382515676872003,
+      "grad_norm": 1.4902995824813843,
+      "learning_rate": 1.0409389764655031e-05,
+      "loss": 0.0443,
+      "step": 3648
+    },
+    {
+      "epoch": 0.5383991147178163,
+      "grad_norm": 3.2903122901916504,
+      "learning_rate": 1.0404243032599188e-05,
+      "loss": 0.0458,
+      "step": 3649
+    },
+    {
+      "epoch": 0.5385466617484324,
+      "grad_norm": 2.076983690261841,
+      "learning_rate": 1.0399096193286504e-05,
+      "loss": 0.0518,
+      "step": 3650
+    },
+    {
+      "epoch": 0.5386942087790483,
+      "grad_norm": 1.6475075483322144,
+      "learning_rate": 1.0393949248082572e-05,
+      "loss": 0.02,
+      "step": 3651
+    },
+    {
+      "epoch": 0.5388417558096643,
+      "grad_norm": 1.3995980024337769,
+      "learning_rate": 1.038880219835302e-05,
+      "loss": 0.0402,
+      "step": 3652
+    },
+    {
+      "epoch": 0.5389893028402803,
+      "grad_norm": 3.903316020965576,
+      "learning_rate": 1.0383655045463508e-05,
+      "loss": 0.0502,
+      "step": 3653
+    },
+    {
+      "epoch": 0.5391368498708964,
+      "grad_norm": 2.024240016937256,
+      "learning_rate": 1.0378507790779712e-05,
+      "loss": 0.0568,
+      "step": 3654
+    },
+    {
+      "epoch": 0.5392843969015123,
+      "grad_norm": 6.113285541534424,
+      "learning_rate": 1.0373360435667346e-05,
+      "loss": 0.1567,
+      "step": 3655
+    },
+    {
+      "epoch": 0.5394319439321283,
+      "grad_norm": 1.540674090385437,
+      "learning_rate": 1.0368212981492136e-05,
+      "loss": 0.0136,
+      "step": 3656
+    },
+    {
+      "epoch": 0.5395794909627444,
+      "grad_norm": 3.9668731689453125,
+      "learning_rate": 1.036306542961986e-05,
+      "loss": 0.0825,
+      "step": 3657
+    },
+    {
+      "epoch": 0.5397270379933604,
+      "grad_norm": 3.607522487640381,
+      "learning_rate": 1.0357917781416287e-05,
+      "loss": 0.0944,
+      "step": 3658
+    },
+    {
+      "epoch": 0.5398745850239763,
+      "grad_norm": 2.4661123752593994,
+      "learning_rate": 1.0352770038247242e-05,
+      "loss": 0.0518,
+      "step": 3659
+    },
+    {
+      "epoch": 0.5400221320545924,
+      "grad_norm": 1.7464462518692017,
+      "learning_rate": 1.0347622201478563e-05,
+      "loss": 0.0454,
+      "step": 3660
+    },
+    {
+      "epoch": 0.5400221320545924,
+      "eval_accuracy": 0.975397973950796,
+      "eval_f1": 0.9576059850374065,
+      "eval_loss": 0.06375893950462341,
+      "eval_precision": 0.9846153846153847,
+      "eval_recall": 0.9320388349514563,
+      "eval_runtime": 49.2446,
+      "eval_samples_per_second": 5.909,
+      "eval_steps_per_second": 0.203,
+      "step": 3660
+    },
+    {
+      "epoch": 0.5401696790852084,
+      "grad_norm": 5.017095565795898,
+      "learning_rate": 1.0342474272476108e-05,
+      "loss": 0.0776,
+      "step": 3661
+    },
+    {
+      "epoch": 0.5403172261158244,
+      "grad_norm": 2.051027774810791,
+      "learning_rate": 1.0337326252605768e-05,
+      "loss": 0.04,
+      "step": 3662
+    },
+    {
+      "epoch": 0.5404647731464405,
+      "grad_norm": 3.897878408432007,
+      "learning_rate": 1.0332178143233453e-05,
+      "loss": 0.0741,
+      "step": 3663
+    },
+    {
+      "epoch": 0.5406123201770564,
+      "grad_norm": 1.8527952432632446,
+      "learning_rate": 1.0327029945725107e-05,
+      "loss": 0.0352,
+      "step": 3664
+    },
+    {
+      "epoch": 0.5407598672076724,
+      "grad_norm": 2.326930522918701,
+      "learning_rate": 1.0321881661446675e-05,
+      "loss": 0.0915,
+      "step": 3665
+    },
+    {
+      "epoch": 0.5409074142382885,
+      "grad_norm": 1.5918142795562744,
+      "learning_rate": 1.0316733291764152e-05,
+      "loss": 0.0153,
+      "step": 3666
+    },
+    {
+      "epoch": 0.5410549612689045,
+      "grad_norm": 5.2848334312438965,
+      "learning_rate": 1.0311584838043533e-05,
+      "loss": 0.1226,
+      "step": 3667
+    },
+    {
+      "epoch": 0.5412025082995204,
+      "grad_norm": 3.7213995456695557,
+      "learning_rate": 1.030643630165085e-05,
+      "loss": 0.05,
+      "step": 3668
+    },
+    {
+      "epoch": 0.5413500553301365,
+      "grad_norm": 3.5198309421539307,
+      "learning_rate": 1.0301287683952153e-05,
+      "loss": 0.0339,
+      "step": 3669
+    },
+    {
+      "epoch": 0.5414976023607525,
+      "grad_norm": 3.1995413303375244,
+      "learning_rate": 1.0296138986313506e-05,
+      "loss": 0.0395,
+      "step": 3670
+    },
+    {
+      "epoch": 0.5416451493913685,
+      "grad_norm": 4.593168258666992,
+      "learning_rate": 1.0290990210101011e-05,
+      "loss": 0.0376,
+      "step": 3671
+    },
+    {
+      "epoch": 0.5417926964219845,
+      "grad_norm": 1.1846117973327637,
+      "learning_rate": 1.0285841356680771e-05,
+      "loss": 0.0281,
+      "step": 3672
+    },
+    {
+      "epoch": 0.5419402434526005,
+      "grad_norm": 2.156420946121216,
+      "learning_rate": 1.0280692427418923e-05,
+      "loss": 0.0522,
+      "step": 3673
+    },
+    {
+      "epoch": 0.5420877904832165,
+      "grad_norm": 2.1500136852264404,
+      "learning_rate": 1.0275543423681622e-05,
+      "loss": 0.0592,
+      "step": 3674
+    },
+    {
+      "epoch": 0.5422353375138326,
+      "grad_norm": 2.7693979740142822,
+      "learning_rate": 1.0270394346835038e-05,
+      "loss": 0.1162,
+      "step": 3675
+    },
+    {
+      "epoch": 0.5423828845444485,
+      "grad_norm": 1.5747324228286743,
+      "learning_rate": 1.0265245198245364e-05,
+      "loss": 0.0453,
+      "step": 3676
+    },
+    {
+      "epoch": 0.5425304315750645,
+      "grad_norm": 1.7522733211517334,
+      "learning_rate": 1.0260095979278809e-05,
+      "loss": 0.0501,
+      "step": 3677
+    },
+    {
+      "epoch": 0.5426779786056806,
+      "grad_norm": 1.2786890268325806,
+      "learning_rate": 1.025494669130161e-05,
+      "loss": 0.0501,
+      "step": 3678
+    },
+    {
+      "epoch": 0.5428255256362966,
+      "grad_norm": 1.827549695968628,
+      "learning_rate": 1.0249797335680007e-05,
+      "loss": 0.0779,
+      "step": 3679
+    },
+    {
+      "epoch": 0.5429730726669125,
+      "grad_norm": 0.6877404451370239,
+      "learning_rate": 1.0244647913780272e-05,
+      "loss": 0.0219,
+      "step": 3680
+    },
+    {
+      "epoch": 0.5429730726669125,
+      "eval_accuracy": 0.9768451519536903,
+      "eval_f1": 0.96,
+      "eval_loss": 0.06361615657806396,
+      "eval_precision": 0.9896907216494846,
+      "eval_recall": 0.9320388349514563,
+      "eval_runtime": 48.9893,
+      "eval_samples_per_second": 5.94,
+      "eval_steps_per_second": 0.204,
+      "step": 3680
+    },
+    {
+      "epoch": 0.5431206196975286,
+      "grad_norm": 2.077110767364502,
+      "learning_rate": 1.0239498426968689e-05,
+      "loss": 0.0537,
+      "step": 3681
+    },
+    {
+      "epoch": 0.5432681667281446,
+      "grad_norm": 2.2908997535705566,
+      "learning_rate": 1.0234348876611556e-05,
+      "loss": 0.0915,
+      "step": 3682
+    },
+    {
+      "epoch": 0.5434157137587606,
+      "grad_norm": 2.7487967014312744,
+      "learning_rate": 1.0229199264075192e-05,
+      "loss": 0.0575,
+      "step": 3683
+    },
+    {
+      "epoch": 0.5435632607893767,
+      "grad_norm": 5.112874984741211,
+      "learning_rate": 1.0224049590725929e-05,
+      "loss": 0.1078,
+      "step": 3684
+    },
+    {
+      "epoch": 0.5437108078199926,
+      "grad_norm": 1.2296621799468994,
+      "learning_rate": 1.0218899857930125e-05,
+      "loss": 0.0174,
+      "step": 3685
+    },
+    {
+      "epoch": 0.5438583548506086,
+      "grad_norm": 0.8048681020736694,
+      "learning_rate": 1.0213750067054137e-05,
+      "loss": 0.0085,
+      "step": 3686
+    },
+    {
+      "epoch": 0.5440059018812247,
+      "grad_norm": 2.3535094261169434,
+      "learning_rate": 1.0208600219464355e-05,
+      "loss": 0.0791,
+      "step": 3687
+    },
+    {
+      "epoch": 0.5441534489118407,
+      "grad_norm": 2.2542917728424072,
+      "learning_rate": 1.0203450316527173e-05,
+      "loss": 0.0739,
+      "step": 3688
+    },
+    {
+      "epoch": 0.5443009959424566,
+      "grad_norm": 1.5458574295043945,
+      "learning_rate": 1.0198300359608998e-05,
+      "loss": 0.0474,
+      "step": 3689
+    },
+    {
+      "epoch": 0.5444485429730727,
+      "grad_norm": 2.1573433876037598,
+      "learning_rate": 1.0193150350076265e-05,
+      "loss": 0.0721,
+      "step": 3690
+    },
+    {
+      "epoch": 0.5445960900036887,
+      "grad_norm": 5.027381896972656,
+      "learning_rate": 1.01880002892954e-05,
+      "loss": 0.0401,
+      "step": 3691
+    },
+    {
+      "epoch": 0.5447436370343047,
+      "grad_norm": 3.6800339221954346,
+      "learning_rate": 1.0182850178632872e-05,
+      "loss": 0.0526,
+      "step": 3692
+    },
+    {
+      "epoch": 0.5448911840649207,
+      "grad_norm": 1.688063621520996,
+      "learning_rate": 1.017770001945514e-05,
+      "loss": 0.052,
+      "step": 3693
+    },
+    {
+      "epoch": 0.5450387310955367,
+      "grad_norm": 3.0386409759521484,
+      "learning_rate": 1.017254981312868e-05,
+      "loss": 0.1287,
+      "step": 3694
+    },
+    {
+      "epoch": 0.5451862781261527,
+      "grad_norm": 2.4379842281341553,
+      "learning_rate": 1.016739956101999e-05,
+      "loss": 0.0852,
+      "step": 3695
+    },
+    {
+      "epoch": 0.5453338251567688,
+      "grad_norm": 1.9624031782150269,
+      "learning_rate": 1.0162249264495573e-05,
+      "loss": 0.0392,
+      "step": 3696
+    },
+    {
+      "epoch": 0.5454813721873847,
+      "grad_norm": 2.183525323867798,
+      "learning_rate": 1.0157098924921944e-05,
+      "loss": 0.0902,
+      "step": 3697
+    },
+    {
+      "epoch": 0.5456289192180007,
+      "grad_norm": 2.8118762969970703,
+      "learning_rate": 1.0151948543665627e-05,
+      "loss": 0.0995,
+      "step": 3698
+    },
+    {
+      "epoch": 0.5457764662486168,
+      "grad_norm": 2.5438857078552246,
+      "learning_rate": 1.0146798122093167e-05,
+      "loss": 0.0924,
+      "step": 3699
+    },
+    {
+      "epoch": 0.5459240132792328,
+      "grad_norm": 1.5641134977340698,
+      "learning_rate": 1.0141647661571112e-05,
+      "loss": 0.0547,
+      "step": 3700
+    },
+    {
+      "epoch": 0.5459240132792328,
+      "eval_accuracy": 0.975397973950796,
+      "eval_f1": 0.9582309582309583,
+      "eval_loss": 0.06087513640522957,
+      "eval_precision": 0.9701492537313433,
+      "eval_recall": 0.9466019417475728,
+      "eval_runtime": 49.054,
+      "eval_samples_per_second": 5.932,
+      "eval_steps_per_second": 0.204,
+      "step": 3700
     }
   ],
   "logging_steps": 1,
@@ -27398,7 +28158,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1091422408962212e+18,
+  "total_flos": 1.1398356968155382e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null