Training in progress, step 4500, checkpoint

last-checkpoint/optimizer_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7f8989f3a0d8584382615f4397f8d4b27a3bb5bb58c147ec34dfaf38bf4d75b
+oid sha256:f951b968c4755cc04444ff89c294ed24a88cd59b92deeef1299419208f3927de
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5135e373f8271ffcec4516ac6242e4510c2c866a3a693b253ac1397344dc4b63
+oid sha256:7fe1edb2059b7e4ea7853e16d65cb5d1e9a62eb87e911652846cfde1d7bf8353
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:265960cd86c82cdead8d5b2fca3a2f14b21c9250b561d3bcf79a58bef25c786f
+oid sha256:91daca939c297361fdd0f2ebb643b3739956df5f47d1c48ce7b7bd6b3b47882a
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b344094f4db226a3e8dac1657f37278061ed3d42f32d50473723a6f3868b24c5
+oid sha256:3de0fc95af80faaacf24723652f89f260ef79df769fbf44db166f344846f8260
 size 13990904

last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1949d5ac698d91f360268a83ae3807e3e9705158c7f9801dbced3b0c7746e9a5
+oid sha256:b2e7ce8790aeda75570c6583b8fa711fcbcd7ac67108ce1f19dd98c331b729a9
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88333ce8d2390f7cd70ed4a310386ea585d7288af2cf159efbbbf8d4900cb9d4
+oid sha256:67af6f586b2cc1b9d4a4caabc6603d2cf8ea666a0eddf8077247bbe6e796cd7d
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48bdff441e90d7a27a97064706cff834e2526f0f8d5ded539cbff48cc58dd96c
+oid sha256:3b4294c4c61ac4e42e537a5af995fbcdc96bf9fe27fefe63b31a0d011ae27cac
 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:b0c03502ba4781dbe87ff451e4a84d75d7efea4f6879cde6b82da87663a62c6f
+oid sha256:ef940f09526088cb5107080ca90bb0826b218de62bb2fd0b3c9ecf53e6d7acfd
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7bbfa52bbb5b233aa31c417fb2896ff6a772316c108ab1140779ed54cb3e354
+oid sha256:b85ef5c9fbdea62e319b577e429a70a348840a4617cbaa53ee7b7f9b7e04796c
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:603268a08657d53f2a6921b109f18e972a408209ab15d4f547cb9103f2989973
+oid sha256:a77b778ba8f23c1b297bd37db84866e64c64b9181236622614ccfe172efb0aef
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1949be2dbfb33ecd904ee83b365f7b90a89eb98906e7674d56fd103937f09e90
+oid sha256:02777d8a71dfc2621d84f04a89d95e1fda82aa34778699593e7fc4bd2d678550
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a06eebc0a571b5987ee0a0feefac77d54dcd794d9d3811d80b62265366921f5a
+oid sha256:889f5b263e38b83de470ace0f8618baea3ae601a6e8197710847bd5673f7f684
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1740732e2bee92af7f70ac41f4aee144d887eeff84a5198af738baaaf5b5a364
+oid sha256:66559bcf2e677322205dbd2ab67f672f9032c0a1ca0c27656dc7c0363a894e1f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.649206934710439,
+  "epoch": 0.6639616377720399,
   "eval_steps": 20,
-  "global_step": 4400,
+  "global_step": 4500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -33459,6 +33459,766 @@
       "eval_samples_per_second": 5.915,
       "eval_steps_per_second": 0.203,
       "step": 4400
+    },
+    {
+      "epoch": 0.6493544817410549,
+      "grad_norm": 2.757441520690918,
+      "learning_rate": 6.599974567086871e-06,
+      "loss": 0.0286,
+      "step": 4401
+    },
+    {
+      "epoch": 0.649502028771671,
+      "grad_norm": 3.9749069213867188,
+      "learning_rate": 6.595130895142601e-06,
+      "loss": 0.033,
+      "step": 4402
+    },
+    {
+      "epoch": 0.649649575802287,
+      "grad_norm": 2.7191781997680664,
+      "learning_rate": 6.590288126604159e-06,
+      "loss": 0.0503,
+      "step": 4403
+    },
+    {
+      "epoch": 0.649797122832903,
+      "grad_norm": 1.5683810710906982,
+      "learning_rate": 6.585446262756474e-06,
+      "loss": 0.0423,
+      "step": 4404
+    },
+    {
+      "epoch": 0.649944669863519,
+      "grad_norm": 2.9194579124450684,
+      "learning_rate": 6.58060530488422e-06,
+      "loss": 0.0579,
+      "step": 4405
+    },
+    {
+      "epoch": 0.650092216894135,
+      "grad_norm": 1.7084243297576904,
+      "learning_rate": 6.5757652542718385e-06,
+      "loss": 0.0357,
+      "step": 4406
+    },
+    {
+      "epoch": 0.650239763924751,
+      "grad_norm": 6.491199493408203,
+      "learning_rate": 6.570926112203528e-06,
+      "loss": 0.023,
+      "step": 4407
+    },
+    {
+      "epoch": 0.6503873109553671,
+      "grad_norm": 4.800782680511475,
+      "learning_rate": 6.566087879963245e-06,
+      "loss": 0.1412,
+      "step": 4408
+    },
+    {
+      "epoch": 0.650534857985983,
+      "grad_norm": 3.0766396522521973,
+      "learning_rate": 6.561250558834712e-06,
+      "loss": 0.049,
+      "step": 4409
+    },
+    {
+      "epoch": 0.650682405016599,
+      "grad_norm": 1.7469078302383423,
+      "learning_rate": 6.556414150101399e-06,
+      "loss": 0.0304,
+      "step": 4410
+    },
+    {
+      "epoch": 0.650829952047215,
+      "grad_norm": 2.0975399017333984,
+      "learning_rate": 6.55157865504654e-06,
+      "loss": 0.0704,
+      "step": 4411
+    },
+    {
+      "epoch": 0.6509774990778311,
+      "grad_norm": 1.7246694564819336,
+      "learning_rate": 6.546744074953126e-06,
+      "loss": 0.0428,
+      "step": 4412
+    },
+    {
+      "epoch": 0.651125046108447,
+      "grad_norm": 6.032076835632324,
+      "learning_rate": 6.5419104111039e-06,
+      "loss": 0.1259,
+      "step": 4413
+    },
+    {
+      "epoch": 0.651272593139063,
+      "grad_norm": 2.2777020931243896,
+      "learning_rate": 6.537077664781374e-06,
+      "loss": 0.0643,
+      "step": 4414
+    },
+    {
+      "epoch": 0.6514201401696791,
+      "grad_norm": 3.9178431034088135,
+      "learning_rate": 6.532245837267807e-06,
+      "loss": 0.1072,
+      "step": 4415
+    },
+    {
+      "epoch": 0.6515676872002951,
+      "grad_norm": 2.0883002281188965,
+      "learning_rate": 6.527414929845214e-06,
+      "loss": 0.077,
+      "step": 4416
+    },
+    {
+      "epoch": 0.6517152342309112,
+      "grad_norm": 2.4088566303253174,
+      "learning_rate": 6.522584943795365e-06,
+      "loss": 0.0674,
+      "step": 4417
+    },
+    {
+      "epoch": 0.6518627812615271,
+      "grad_norm": 2.5000414848327637,
+      "learning_rate": 6.5177558803997976e-06,
+      "loss": 0.0632,
+      "step": 4418
+    },
+    {
+      "epoch": 0.6520103282921431,
+      "grad_norm": 3.176330327987671,
+      "learning_rate": 6.512927740939789e-06,
+      "loss": 0.0972,
+      "step": 4419
+    },
+    {
+      "epoch": 0.6521578753227592,
+      "grad_norm": 1.9688628911972046,
+      "learning_rate": 6.508100526696381e-06,
+      "loss": 0.0386,
+      "step": 4420
+    },
+    {
+      "epoch": 0.6521578753227592,
+      "eval_accuracy": 0.9797395079594791,
+      "eval_f1": 0.9653465346534653,
+      "eval_loss": 0.057804737240076065,
+      "eval_precision": 0.9848484848484849,
+      "eval_recall": 0.9466019417475728,
+      "eval_runtime": 53.0749,
+      "eval_samples_per_second": 5.483,
+      "eval_steps_per_second": 0.188,
+      "step": 4420
+    },
+    {
+      "epoch": 0.6523054223533752,
+      "grad_norm": 3.077688217163086,
+      "learning_rate": 6.5032742389503676e-06,
+      "loss": 0.0519,
+      "step": 4421
+    },
+    {
+      "epoch": 0.6524529693839911,
+      "grad_norm": 1.935166835784912,
+      "learning_rate": 6.4984488789822905e-06,
+      "loss": 0.0555,
+      "step": 4422
+    },
+    {
+      "epoch": 0.6526005164146071,
+      "grad_norm": 2.046032190322876,
+      "learning_rate": 6.4936244480724575e-06,
+      "loss": 0.0555,
+      "step": 4423
+    },
+    {
+      "epoch": 0.6527480634452232,
+      "grad_norm": 12.51380443572998,
+      "learning_rate": 6.488800947500921e-06,
+      "loss": 0.0686,
+      "step": 4424
+    },
+    {
+      "epoch": 0.6528956104758392,
+      "grad_norm": 1.8526471853256226,
+      "learning_rate": 6.4839783785474884e-06,
+      "loss": 0.0701,
+      "step": 4425
+    },
+    {
+      "epoch": 0.6530431575064551,
+      "grad_norm": 3.5263936519622803,
+      "learning_rate": 6.479156742491721e-06,
+      "loss": 0.0854,
+      "step": 4426
+    },
+    {
+      "epoch": 0.6531907045370712,
+      "grad_norm": 3.3337717056274414,
+      "learning_rate": 6.4743360406129294e-06,
+      "loss": 0.0904,
+      "step": 4427
+    },
+    {
+      "epoch": 0.6533382515676872,
+      "grad_norm": 2.0364885330200195,
+      "learning_rate": 6.469516274190185e-06,
+      "loss": 0.0579,
+      "step": 4428
+    },
+    {
+      "epoch": 0.6534857985983032,
+      "grad_norm": 1.7969423532485962,
+      "learning_rate": 6.464697444502301e-06,
+      "loss": 0.0366,
+      "step": 4429
+    },
+    {
+      "epoch": 0.6536333456289192,
+      "grad_norm": 1.5288689136505127,
+      "learning_rate": 6.4598795528278495e-06,
+      "loss": 0.0425,
+      "step": 4430
+    },
+    {
+      "epoch": 0.6537808926595352,
+      "grad_norm": 1.8399264812469482,
+      "learning_rate": 6.455062600445143e-06,
+      "loss": 0.0547,
+      "step": 4431
+    },
+    {
+      "epoch": 0.6539284396901512,
+      "grad_norm": 1.8224679231643677,
+      "learning_rate": 6.450246588632254e-06,
+      "loss": 0.0411,
+      "step": 4432
+    },
+    {
+      "epoch": 0.6540759867207673,
+      "grad_norm": 2.015737771987915,
+      "learning_rate": 6.4454315186670125e-06,
+      "loss": 0.0847,
+      "step": 4433
+    },
+    {
+      "epoch": 0.6542235337513832,
+      "grad_norm": 1.4043141603469849,
+      "learning_rate": 6.44061739182698e-06,
+      "loss": 0.056,
+      "step": 4434
+    },
+    {
+      "epoch": 0.6543710807819992,
+      "grad_norm": 8.94338607788086,
+      "learning_rate": 6.43580420938948e-06,
+      "loss": 0.1093,
+      "step": 4435
+    },
+    {
+      "epoch": 0.6545186278126153,
+      "grad_norm": 1.838114857673645,
+      "learning_rate": 6.430991972631582e-06,
+      "loss": 0.0174,
+      "step": 4436
+    },
+    {
+      "epoch": 0.6546661748432313,
+      "grad_norm": 3.10587477684021,
+      "learning_rate": 6.426180682830108e-06,
+      "loss": 0.0434,
+      "step": 4437
+    },
+    {
+      "epoch": 0.6548137218738473,
+      "grad_norm": 2.1863956451416016,
+      "learning_rate": 6.421370341261624e-06,
+      "loss": 0.1018,
+      "step": 4438
+    },
+    {
+      "epoch": 0.6549612689044633,
+      "grad_norm": 3.246185064315796,
+      "learning_rate": 6.416560949202449e-06,
+      "loss": 0.1015,
+      "step": 4439
+    },
+    {
+      "epoch": 0.6551088159350793,
+      "grad_norm": 2.234623670578003,
+      "learning_rate": 6.411752507928643e-06,
+      "loss": 0.0986,
+      "step": 4440
+    },
+    {
+      "epoch": 0.6551088159350793,
+      "eval_accuracy": 0.9768451519536903,
+      "eval_f1": 0.9601990049751243,
+      "eval_loss": 0.06005861982703209,
+      "eval_precision": 0.9846938775510204,
+      "eval_recall": 0.9368932038834952,
+      "eval_runtime": 50.2076,
+      "eval_samples_per_second": 5.796,
+      "eval_steps_per_second": 0.199,
+      "step": 4440
+    },
+    {
+      "epoch": 0.6552563629656953,
+      "grad_norm": 1.7946083545684814,
+      "learning_rate": 6.40694501871602e-06,
+      "loss": 0.0633,
+      "step": 4441
+    },
+    {
+      "epoch": 0.6554039099963114,
+      "grad_norm": 1.7781100273132324,
+      "learning_rate": 6.402138482840141e-06,
+      "loss": 0.0698,
+      "step": 4442
+    },
+    {
+      "epoch": 0.6555514570269273,
+      "grad_norm": 1.7382947206497192,
+      "learning_rate": 6.397332901576314e-06,
+      "loss": 0.036,
+      "step": 4443
+    },
+    {
+      "epoch": 0.6556990040575433,
+      "grad_norm": 2.0687174797058105,
+      "learning_rate": 6.392528276199592e-06,
+      "loss": 0.0691,
+      "step": 4444
+    },
+    {
+      "epoch": 0.6558465510881594,
+      "grad_norm": 2.8955514430999756,
+      "learning_rate": 6.387724607984772e-06,
+      "loss": 0.0881,
+      "step": 4445
+    },
+    {
+      "epoch": 0.6559940981187754,
+      "grad_norm": 1.676020622253418,
+      "learning_rate": 6.382921898206398e-06,
+      "loss": 0.0279,
+      "step": 4446
+    },
+    {
+      "epoch": 0.6561416451493913,
+      "grad_norm": 2.6807148456573486,
+      "learning_rate": 6.37812014813877e-06,
+      "loss": 0.0223,
+      "step": 4447
+    },
+    {
+      "epoch": 0.6562891921800074,
+      "grad_norm": 1.6488813161849976,
+      "learning_rate": 6.373319359055919e-06,
+      "loss": 0.0535,
+      "step": 4448
+    },
+    {
+      "epoch": 0.6564367392106234,
+      "grad_norm": 2.6411168575286865,
+      "learning_rate": 6.368519532231627e-06,
+      "loss": 0.0428,
+      "step": 4449
+    },
+    {
+      "epoch": 0.6565842862412394,
+      "grad_norm": 2.7337758541107178,
+      "learning_rate": 6.363720668939421e-06,
+      "loss": 0.0866,
+      "step": 4450
+    },
+    {
+      "epoch": 0.6567318332718554,
+      "grad_norm": 1.1719896793365479,
+      "learning_rate": 6.358922770452573e-06,
+      "loss": 0.0301,
+      "step": 4451
+    },
+    {
+      "epoch": 0.6568793803024714,
+      "grad_norm": 1.586561918258667,
+      "learning_rate": 6.354125838044099e-06,
+      "loss": 0.0819,
+      "step": 4452
+    },
+    {
+      "epoch": 0.6570269273330874,
+      "grad_norm": 1.3872873783111572,
+      "learning_rate": 6.349329872986754e-06,
+      "loss": 0.0434,
+      "step": 4453
+    },
+    {
+      "epoch": 0.6571744743637035,
+      "grad_norm": 2.2281954288482666,
+      "learning_rate": 6.344534876553044e-06,
+      "loss": 0.0736,
+      "step": 4454
+    },
+    {
+      "epoch": 0.6573220213943194,
+      "grad_norm": 2.525529146194458,
+      "learning_rate": 6.33974085001521e-06,
+      "loss": 0.0239,
+      "step": 4455
+    },
+    {
+      "epoch": 0.6574695684249354,
+      "grad_norm": 2.3365206718444824,
+      "learning_rate": 6.334947794645244e-06,
+      "loss": 0.0944,
+      "step": 4456
+    },
+    {
+      "epoch": 0.6576171154555515,
+      "grad_norm": 3.1038765907287598,
+      "learning_rate": 6.3301557117148746e-06,
+      "loss": 0.0443,
+      "step": 4457
+    },
+    {
+      "epoch": 0.6577646624861675,
+      "grad_norm": 1.8159865140914917,
+      "learning_rate": 6.325364602495575e-06,
+      "loss": 0.0413,
+      "step": 4458
+    },
+    {
+      "epoch": 0.6579122095167834,
+      "grad_norm": 1.2702845335006714,
+      "learning_rate": 6.3205744682585545e-06,
+      "loss": 0.0395,
+      "step": 4459
+    },
+    {
+      "epoch": 0.6580597565473995,
+      "grad_norm": 2.11480450630188,
+      "learning_rate": 6.3157853102747665e-06,
+      "loss": 0.0731,
+      "step": 4460
+    },
+    {
+      "epoch": 0.6580597565473995,
+      "eval_accuracy": 0.975397973950796,
+      "eval_f1": 0.9576059850374065,
+      "eval_loss": 0.05957798287272453,
+      "eval_precision": 0.9846153846153847,
+      "eval_recall": 0.9320388349514563,
+      "eval_runtime": 50.0277,
+      "eval_samples_per_second": 5.817,
+      "eval_steps_per_second": 0.2,
+      "step": 4460
+    },
+    {
+      "epoch": 0.6582073035780155,
+      "grad_norm": 2.299861192703247,
+      "learning_rate": 6.310997129814917e-06,
+      "loss": 0.0435,
+      "step": 4461
+    },
+    {
+      "epoch": 0.6583548506086315,
+      "grad_norm": 2.645285129547119,
+      "learning_rate": 6.306209928149436e-06,
+      "loss": 0.0596,
+      "step": 4462
+    },
+    {
+      "epoch": 0.6585023976392476,
+      "grad_norm": 1.9211374521255493,
+      "learning_rate": 6.301423706548499e-06,
+      "loss": 0.0587,
+      "step": 4463
+    },
+    {
+      "epoch": 0.6586499446698635,
+      "grad_norm": 2.9688777923583984,
+      "learning_rate": 6.296638466282026e-06,
+      "loss": 0.061,
+      "step": 4464
+    },
+    {
+      "epoch": 0.6587974917004795,
+      "grad_norm": 0.9423332810401917,
+      "learning_rate": 6.291854208619669e-06,
+      "loss": 0.0282,
+      "step": 4465
+    },
+    {
+      "epoch": 0.6589450387310956,
+      "grad_norm": 2.3356895446777344,
+      "learning_rate": 6.287070934830829e-06,
+      "loss": 0.0624,
+      "step": 4466
+    },
+    {
+      "epoch": 0.6590925857617116,
+      "grad_norm": 3.511073350906372,
+      "learning_rate": 6.282288646184638e-06,
+      "loss": 0.0648,
+      "step": 4467
+    },
+    {
+      "epoch": 0.6592401327923275,
+      "grad_norm": 3.802366018295288,
+      "learning_rate": 6.277507343949971e-06,
+      "loss": 0.1404,
+      "step": 4468
+    },
+    {
+      "epoch": 0.6593876798229436,
+      "grad_norm": 1.36722993850708,
+      "learning_rate": 6.2727270293954405e-06,
+      "loss": 0.021,
+      "step": 4469
+    },
+    {
+      "epoch": 0.6595352268535596,
+      "grad_norm": 1.5654717683792114,
+      "learning_rate": 6.267947703789385e-06,
+      "loss": 0.0595,
+      "step": 4470
+    },
+    {
+      "epoch": 0.6596827738841756,
+      "grad_norm": 1.5576167106628418,
+      "learning_rate": 6.263169368399908e-06,
+      "loss": 0.0602,
+      "step": 4471
+    },
+    {
+      "epoch": 0.6598303209147915,
+      "grad_norm": 0.7984778881072998,
+      "learning_rate": 6.258392024494826e-06,
+      "loss": 0.0172,
+      "step": 4472
+    },
+    {
+      "epoch": 0.6599778679454076,
+      "grad_norm": 2.393357276916504,
+      "learning_rate": 6.2536156733417e-06,
+      "loss": 0.0725,
+      "step": 4473
+    },
+    {
+      "epoch": 0.6601254149760236,
+      "grad_norm": 1.6943670511245728,
+      "learning_rate": 6.248840316207825e-06,
+      "loss": 0.0409,
+      "step": 4474
+    },
+    {
+      "epoch": 0.6602729620066397,
+      "grad_norm": 1.4864270687103271,
+      "learning_rate": 6.244065954360243e-06,
+      "loss": 0.0323,
+      "step": 4475
+    },
+    {
+      "epoch": 0.6604205090372556,
+      "grad_norm": 0.8731735348701477,
+      "learning_rate": 6.239292589065719e-06,
+      "loss": 0.0275,
+      "step": 4476
+    },
+    {
+      "epoch": 0.6605680560678716,
+      "grad_norm": 2.9448368549346924,
+      "learning_rate": 6.234520221590759e-06,
+      "loss": 0.0817,
+      "step": 4477
+    },
+    {
+      "epoch": 0.6607156030984876,
+      "grad_norm": 1.8645683526992798,
+      "learning_rate": 6.229748853201605e-06,
+      "loss": 0.0478,
+      "step": 4478
+    },
+    {
+      "epoch": 0.6608631501291037,
+      "grad_norm": 1.7074979543685913,
+      "learning_rate": 6.224978485164229e-06,
+      "loss": 0.0486,
+      "step": 4479
+    },
+    {
+      "epoch": 0.6610106971597196,
+      "grad_norm": 1.5328609943389893,
+      "learning_rate": 6.220209118744347e-06,
+      "loss": 0.0269,
+      "step": 4480
+    },
+    {
+      "epoch": 0.6610106971597196,
+      "eval_accuracy": 0.975397973950796,
+      "eval_f1": 0.9580246913580247,
+      "eval_loss": 0.057335324585437775,
+      "eval_precision": 0.9748743718592965,
+      "eval_recall": 0.941747572815534,
+      "eval_runtime": 50.1223,
+      "eval_samples_per_second": 5.806,
+      "eval_steps_per_second": 0.2,
+      "step": 4480
+    },
+    {
+      "epoch": 0.6611582441903356,
+      "grad_norm": 1.9285787343978882,
+      "learning_rate": 6.215440755207402e-06,
+      "loss": 0.0423,
+      "step": 4481
+    },
+    {
+      "epoch": 0.6613057912209517,
+      "grad_norm": 1.8386911153793335,
+      "learning_rate": 6.210673395818572e-06,
+      "loss": 0.0366,
+      "step": 4482
+    },
+    {
+      "epoch": 0.6614533382515677,
+      "grad_norm": 2.162466049194336,
+      "learning_rate": 6.205907041842771e-06,
+      "loss": 0.0675,
+      "step": 4483
+    },
+    {
+      "epoch": 0.6616008852821837,
+      "grad_norm": 1.4594266414642334,
+      "learning_rate": 6.201141694544637e-06,
+      "loss": 0.0317,
+      "step": 4484
+    },
+    {
+      "epoch": 0.6617484323127997,
+      "grad_norm": 0.9458202719688416,
+      "learning_rate": 6.196377355188556e-06,
+      "loss": 0.0123,
+      "step": 4485
+    },
+    {
+      "epoch": 0.6618959793434157,
+      "grad_norm": 1.6956408023834229,
+      "learning_rate": 6.191614025038639e-06,
+      "loss": 0.0245,
+      "step": 4486
+    },
+    {
+      "epoch": 0.6620435263740317,
+      "grad_norm": 2.439507007598877,
+      "learning_rate": 6.186851705358725e-06,
+      "loss": 0.0253,
+      "step": 4487
+    },
+    {
+      "epoch": 0.6621910734046478,
+      "grad_norm": 2.100860357284546,
+      "learning_rate": 6.182090397412391e-06,
+      "loss": 0.0743,
+      "step": 4488
+    },
+    {
+      "epoch": 0.6623386204352637,
+      "grad_norm": 1.2288669347763062,
+      "learning_rate": 6.177330102462941e-06,
+      "loss": 0.0504,
+      "step": 4489
+    },
+    {
+      "epoch": 0.6624861674658797,
+      "grad_norm": 3.726640224456787,
+      "learning_rate": 6.1725708217734155e-06,
+      "loss": 0.0605,
+      "step": 4490
+    },
+    {
+      "epoch": 0.6626337144964958,
+      "grad_norm": 2.50217604637146,
+      "learning_rate": 6.167812556606585e-06,
+      "loss": 0.1003,
+      "step": 4491
+    },
+    {
+      "epoch": 0.6627812615271118,
+      "grad_norm": 9.090914726257324,
+      "learning_rate": 6.163055308224944e-06,
+      "loss": 0.0448,
+      "step": 4492
+    },
+    {
+      "epoch": 0.6629288085577277,
+      "grad_norm": 2.791994094848633,
+      "learning_rate": 6.158299077890724e-06,
+      "loss": 0.1023,
+      "step": 4493
+    },
+    {
+      "epoch": 0.6630763555883438,
+      "grad_norm": 2.8435914516448975,
+      "learning_rate": 6.1535438668658855e-06,
+      "loss": 0.0526,
+      "step": 4494
+    },
+    {
+      "epoch": 0.6632239026189598,
+      "grad_norm": 1.862433671951294,
+      "learning_rate": 6.148789676412114e-06,
+      "loss": 0.0369,
+      "step": 4495
+    },
+    {
+      "epoch": 0.6633714496495758,
+      "grad_norm": 1.6116923093795776,
+      "learning_rate": 6.1440365077908335e-06,
+      "loss": 0.0285,
+      "step": 4496
+    },
+    {
+      "epoch": 0.6635189966801918,
+      "grad_norm": 2.023977756500244,
+      "learning_rate": 6.139284362263185e-06,
+      "loss": 0.0303,
+      "step": 4497
+    },
+    {
+      "epoch": 0.6636665437108078,
+      "grad_norm": 2.118455648422241,
+      "learning_rate": 6.134533241090046e-06,
+      "loss": 0.0377,
+      "step": 4498
+    },
+    {
+      "epoch": 0.6638140907414238,
+      "grad_norm": 1.1348005533218384,
+      "learning_rate": 6.12978314553202e-06,
+      "loss": 0.0251,
+      "step": 4499
+    },
+    {
+      "epoch": 0.6639616377720399,
+      "grad_norm": 2.13145112991333,
+      "learning_rate": 6.125034076849441e-06,
+      "loss": 0.0509,
+      "step": 4500
+    },
+    {
+      "epoch": 0.6639616377720399,
+      "eval_accuracy": 0.9782923299565847,
+      "eval_f1": 0.9625935162094763,
+      "eval_loss": 0.05893443897366524,
+      "eval_precision": 0.9897435897435898,
+      "eval_recall": 0.9368932038834952,
+      "eval_runtime": 49.9972,
+      "eval_samples_per_second": 5.82,
+      "eval_steps_per_second": 0.2,
+      "step": 4500
     }
   ],
   "logging_steps": 1,
@@ -33478,7 +34238,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3559067494580224e+18,
+  "total_flos": 1.386469907746521e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null