Training in progress, step 3500, checkpoint

last-checkpoint/optimizer_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02e164e50fb0e1b1e47c7bf23bdb19271b2cef9843910da2706efea30eced66a
+oid sha256:b16e67baf5cfceecccbeaca8b58da303eaf73b17a51a7a27d2eeb645c7b1f9e4
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddd1590c457db5d04d80b6243a1685d2cdc74a0c617f48321ed49d94f56596d7
+oid sha256:df6d15578ce7461a65e3d4573631629600f16341c2e151f5618c1a8e05be12e7
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2650dcea9a33f085ae7c54c740aa3883ebe47b6e6c2e31c9d736d5290180712b
+oid sha256:2c8d953afc881ab0dd7c35d8bed0bf96b70919c9bc96a27c7970d3d8561f492e
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec94ef188ea157184f371227eeaba2d364cc39a04fd9479cdf0edda257dd9f99
+oid sha256:9952a55ee296a52f4b41a79416235ca4e467bfb2d38e406014037f6296cb8bd3
 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:ce699adeefb27df9eee6e6aeae2ade775456ead2bb7b6f84a19b77bf5200e05c
+oid sha256:f116d69ef453f4a4e9e385b98d7cc4c1269cb0a068b07c53b34efc9aa8a3e06c
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72c2e5a5bb2d54f7bfa01f857e39f84f07a54da7ccc14c75da0f982159b6f1f3
+oid sha256:54743e3ec92e6bba23e12a00c6fc7a862a8c703ccec27d001cceac7b972ba11f
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:451677245f6d4acd3e422b574c37a08013c2b7a054cded9e1a8c6f0f94d9cfe9
+oid sha256:a74fffaefc1e6daba654c4aae129ffa7a374f17ee3470a05b2d2cfc5fb713335
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74926a78c6372ca04cfbe37aadd6f143223acc7ed80a9855e3d9e801cd349912
+oid sha256:627d9fd686c5312231b69470a8c938f0b89f58eb7b46a5397cd0de6ae9cfc6db
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:923ff8ff5e40d5b36fc5a5f49a51828be98a220ed0e61312c7b91aa63406e8c9
+oid sha256:2959b7d0cc6a73dd7a982a0ebc0dcad24dc8fe4cf1adb63e6422a7b207cbcd36
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2951ea5d1098af07baad4add1b4baf57b6e552263a2ec173fd02212840ee1b90
+oid sha256:015d45f86fc1a9d22364b86b52fa480ca21a653f465a66b7d9e373571a4d3052
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77ba5b96e725c2a5948be5d17e751b1a7d869a0ceaac116ac144b099d4e6c811
+oid sha256:0d0b2147472e5ebbb5ec01a3bf49c458cdba6b0342e907e3d15b25d8f1cdf015
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61598bb58957ba5a4d40ca1b1b5f95d897b94b83a68325ac748dc609d924f9f4
+oid sha256:5eba81b72522c20179f6a9e5bd4eb0fea662f295dd50c509d5cca3ea3ab4da5d
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e4b5eda3413351532ab1251ec00c06df0b883b91fabf65baf8537f41dbf3493
+oid sha256:79d9433244954a0989e91ba334032147c20bc4a07ead6f002c05049b1192b520
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5016599040944301,
+  "epoch": 0.5164146071560309,
   "eval_steps": 20,
-  "global_step": 3400,
+  "global_step": 3500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -25859,6 +25859,766 @@
       "eval_samples_per_second": 5.915,
       "eval_steps_per_second": 0.203,
       "step": 3400
+    },
+    {
+      "epoch": 0.5018074511250461,
+      "grad_norm": 1.2393238544464111,
+      "learning_rate": 1.1673883349042388e-05,
+      "loss": 0.0372,
+      "step": 3401
+    },
+    {
+      "epoch": 0.5019549981556621,
+      "grad_norm": 3.2965199947357178,
+      "learning_rate": 1.1668804806080693e-05,
+      "loss": 0.0383,
+      "step": 3402
+    },
+    {
+      "epoch": 0.5021025451862782,
+      "grad_norm": 2.1697685718536377,
+      "learning_rate": 1.1663725820338985e-05,
+      "loss": 0.0325,
+      "step": 3403
+    },
+    {
+      "epoch": 0.5022500922168941,
+      "grad_norm": 3.793184995651245,
+      "learning_rate": 1.1658646393164853e-05,
+      "loss": 0.0689,
+      "step": 3404
+    },
+    {
+      "epoch": 0.5023976392475101,
+      "grad_norm": 4.530444145202637,
+      "learning_rate": 1.1653566525906018e-05,
+      "loss": 0.0915,
+      "step": 3405
+    },
+    {
+      "epoch": 0.5025451862781262,
+      "grad_norm": 2.261080026626587,
+      "learning_rate": 1.1648486219910297e-05,
+      "loss": 0.0843,
+      "step": 3406
+    },
+    {
+      "epoch": 0.5026927333087422,
+      "grad_norm": 3.6483511924743652,
+      "learning_rate": 1.1643405476525648e-05,
+      "loss": 0.0959,
+      "step": 3407
+    },
+    {
+      "epoch": 0.5028402803393581,
+      "grad_norm": 3.5210161209106445,
+      "learning_rate": 1.1638324297100129e-05,
+      "loss": 0.0576,
+      "step": 3408
+    },
+    {
+      "epoch": 0.5029878273699742,
+      "grad_norm": 2.061551094055176,
+      "learning_rate": 1.1633242682981914e-05,
+      "loss": 0.0625,
+      "step": 3409
+    },
+    {
+      "epoch": 0.5031353744005902,
+      "grad_norm": 2.662553071975708,
+      "learning_rate": 1.1628160635519298e-05,
+      "loss": 0.096,
+      "step": 3410
+    },
+    {
+      "epoch": 0.5032829214312062,
+      "grad_norm": 1.3100721836090088,
+      "learning_rate": 1.1623078156060688e-05,
+      "loss": 0.0342,
+      "step": 3411
+    },
+    {
+      "epoch": 0.5034304684618222,
+      "grad_norm": 1.8624759912490845,
+      "learning_rate": 1.1617995245954604e-05,
+      "loss": 0.0368,
+      "step": 3412
+    },
+    {
+      "epoch": 0.5035780154924382,
+      "grad_norm": 4.2568440437316895,
+      "learning_rate": 1.1612911906549687e-05,
+      "loss": 0.084,
+      "step": 3413
+    },
+    {
+      "epoch": 0.5037255625230542,
+      "grad_norm": 1.8648234605789185,
+      "learning_rate": 1.1607828139194683e-05,
+      "loss": 0.0643,
+      "step": 3414
+    },
+    {
+      "epoch": 0.5038731095536703,
+      "grad_norm": 3.886632204055786,
+      "learning_rate": 1.160274394523846e-05,
+      "loss": 0.0728,
+      "step": 3415
+    },
+    {
+      "epoch": 0.5040206565842862,
+      "grad_norm": 1.649542212486267,
+      "learning_rate": 1.159765932602999e-05,
+      "loss": 0.0425,
+      "step": 3416
+    },
+    {
+      "epoch": 0.5041682036149022,
+      "grad_norm": 3.0311574935913086,
+      "learning_rate": 1.159257428291837e-05,
+      "loss": 0.0612,
+      "step": 3417
+    },
+    {
+      "epoch": 0.5043157506455183,
+      "grad_norm": 2.325615406036377,
+      "learning_rate": 1.1587488817252796e-05,
+      "loss": 0.0544,
+      "step": 3418
+    },
+    {
+      "epoch": 0.5044632976761343,
+      "grad_norm": 2.380730152130127,
+      "learning_rate": 1.1582402930382585e-05,
+      "loss": 0.0806,
+      "step": 3419
+    },
+    {
+      "epoch": 0.5046108447067503,
+      "grad_norm": 2.337064504623413,
+      "learning_rate": 1.1577316623657163e-05,
+      "loss": 0.079,
+      "step": 3420
+    },
+    {
+      "epoch": 0.5046108447067503,
+      "eval_accuracy": 0.9710564399421129,
+      "eval_f1": 0.9512195121951219,
+      "eval_loss": 0.06396031379699707,
+      "eval_precision": 0.9558823529411765,
+      "eval_recall": 0.9466019417475728,
+      "eval_runtime": 49.329,
+      "eval_samples_per_second": 5.899,
+      "eval_steps_per_second": 0.203,
+      "step": 3420
+    },
+    {
+      "epoch": 0.5047583917373663,
+      "grad_norm": 0.9309882521629333,
+      "learning_rate": 1.1572229898426068e-05,
+      "loss": 0.0165,
+      "step": 3421
+    },
+    {
+      "epoch": 0.5049059387679823,
+      "grad_norm": 2.355309247970581,
+      "learning_rate": 1.1567142756038954e-05,
+      "loss": 0.0363,
+      "step": 3422
+    },
+    {
+      "epoch": 0.5050534857985983,
+      "grad_norm": 1.6004250049591064,
+      "learning_rate": 1.1562055197845567e-05,
+      "loss": 0.0368,
+      "step": 3423
+    },
+    {
+      "epoch": 0.5052010328292144,
+      "grad_norm": 3.023813486099243,
+      "learning_rate": 1.1556967225195787e-05,
+      "loss": 0.0749,
+      "step": 3424
+    },
+    {
+      "epoch": 0.5053485798598303,
+      "grad_norm": 1.7470098733901978,
+      "learning_rate": 1.1551878839439592e-05,
+      "loss": 0.0399,
+      "step": 3425
+    },
+    {
+      "epoch": 0.5054961268904463,
+      "grad_norm": 4.3731560707092285,
+      "learning_rate": 1.1546790041927072e-05,
+      "loss": 0.1128,
+      "step": 3426
+    },
+    {
+      "epoch": 0.5056436739210624,
+      "grad_norm": 3.562906265258789,
+      "learning_rate": 1.1541700834008423e-05,
+      "loss": 0.0642,
+      "step": 3427
+    },
+    {
+      "epoch": 0.5057912209516784,
+      "grad_norm": 2.7933309078216553,
+      "learning_rate": 1.1536611217033953e-05,
+      "loss": 0.0836,
+      "step": 3428
+    },
+    {
+      "epoch": 0.5059387679822943,
+      "grad_norm": 6.0216546058654785,
+      "learning_rate": 1.1531521192354083e-05,
+      "loss": 0.1012,
+      "step": 3429
+    },
+    {
+      "epoch": 0.5060863150129103,
+      "grad_norm": 1.867408275604248,
+      "learning_rate": 1.1526430761319328e-05,
+      "loss": 0.0672,
+      "step": 3430
+    },
+    {
+      "epoch": 0.5062338620435264,
+      "grad_norm": 5.641247749328613,
+      "learning_rate": 1.1521339925280326e-05,
+      "loss": 0.1349,
+      "step": 3431
+    },
+    {
+      "epoch": 0.5063814090741424,
+      "grad_norm": 4.582265853881836,
+      "learning_rate": 1.1516248685587815e-05,
+      "loss": 0.0876,
+      "step": 3432
+    },
+    {
+      "epoch": 0.5065289561047583,
+      "grad_norm": 3.5694081783294678,
+      "learning_rate": 1.1511157043592642e-05,
+      "loss": 0.0701,
+      "step": 3433
+    },
+    {
+      "epoch": 0.5066765031353744,
+      "grad_norm": 2.2162024974823,
+      "learning_rate": 1.1506065000645758e-05,
+      "loss": 0.0705,
+      "step": 3434
+    },
+    {
+      "epoch": 0.5068240501659904,
+      "grad_norm": 1.5952503681182861,
+      "learning_rate": 1.1500972558098229e-05,
+      "loss": 0.0464,
+      "step": 3435
+    },
+    {
+      "epoch": 0.5069715971966064,
+      "grad_norm": 1.7615381479263306,
+      "learning_rate": 1.1495879717301217e-05,
+      "loss": 0.0403,
+      "step": 3436
+    },
+    {
+      "epoch": 0.5071191442272224,
+      "grad_norm": 2.962190866470337,
+      "learning_rate": 1.149078647960599e-05,
+      "loss": 0.0682,
+      "step": 3437
+    },
+    {
+      "epoch": 0.5072666912578384,
+      "grad_norm": 2.2013590335845947,
+      "learning_rate": 1.1485692846363927e-05,
+      "loss": 0.0723,
+      "step": 3438
+    },
+    {
+      "epoch": 0.5074142382884544,
+      "grad_norm": 2.3486366271972656,
+      "learning_rate": 1.1480598818926511e-05,
+      "loss": 0.0722,
+      "step": 3439
+    },
+    {
+      "epoch": 0.5075617853190705,
+      "grad_norm": 5.332746505737305,
+      "learning_rate": 1.1475504398645328e-05,
+      "loss": 0.0976,
+      "step": 3440
+    },
+    {
+      "epoch": 0.5075617853190705,
+      "eval_accuracy": 0.9696092619392185,
+      "eval_f1": 0.9484029484029484,
+      "eval_loss": 0.06323620676994324,
+      "eval_precision": 0.9601990049751243,
+      "eval_recall": 0.9368932038834952,
+      "eval_runtime": 48.7257,
+      "eval_samples_per_second": 5.972,
+      "eval_steps_per_second": 0.205,
+      "step": 3440
+    },
+    {
+      "epoch": 0.5077093323496865,
+      "grad_norm": 5.610714435577393,
+      "learning_rate": 1.1470409586872067e-05,
+      "loss": 0.0861,
+      "step": 3441
+    },
+    {
+      "epoch": 0.5078568793803024,
+      "grad_norm": 4.403682231903076,
+      "learning_rate": 1.1465314384958521e-05,
+      "loss": 0.1044,
+      "step": 3442
+    },
+    {
+      "epoch": 0.5080044264109185,
+      "grad_norm": 1.1849644184112549,
+      "learning_rate": 1.1460218794256594e-05,
+      "loss": 0.0313,
+      "step": 3443
+    },
+    {
+      "epoch": 0.5081519734415345,
+      "grad_norm": 2.254742383956909,
+      "learning_rate": 1.1455122816118281e-05,
+      "loss": 0.0532,
+      "step": 3444
+    },
+    {
+      "epoch": 0.5082995204721505,
+      "grad_norm": 3.868600368499756,
+      "learning_rate": 1.1450026451895686e-05,
+      "loss": 0.0209,
+      "step": 3445
+    },
+    {
+      "epoch": 0.5084470675027665,
+      "grad_norm": 2.215444326400757,
+      "learning_rate": 1.1444929702941019e-05,
+      "loss": 0.0761,
+      "step": 3446
+    },
+    {
+      "epoch": 0.5085946145333825,
+      "grad_norm": 2.021327018737793,
+      "learning_rate": 1.1439832570606585e-05,
+      "loss": 0.0784,
+      "step": 3447
+    },
+    {
+      "epoch": 0.5087421615639985,
+      "grad_norm": 1.8668911457061768,
+      "learning_rate": 1.1434735056244795e-05,
+      "loss": 0.0389,
+      "step": 3448
+    },
+    {
+      "epoch": 0.5088897085946146,
+      "grad_norm": 1.9178575277328491,
+      "learning_rate": 1.142963716120816e-05,
+      "loss": 0.0527,
+      "step": 3449
+    },
+    {
+      "epoch": 0.5090372556252305,
+      "grad_norm": 2.1388702392578125,
+      "learning_rate": 1.1424538886849294e-05,
+      "loss": 0.0997,
+      "step": 3450
+    },
+    {
+      "epoch": 0.5091848026558465,
+      "grad_norm": 1.4415851831436157,
+      "learning_rate": 1.1419440234520906e-05,
+      "loss": 0.0421,
+      "step": 3451
+    },
+    {
+      "epoch": 0.5093323496864626,
+      "grad_norm": 3.691077947616577,
+      "learning_rate": 1.1414341205575817e-05,
+      "loss": 0.1069,
+      "step": 3452
+    },
+    {
+      "epoch": 0.5094798967170786,
+      "grad_norm": 3.339951753616333,
+      "learning_rate": 1.1409241801366932e-05,
+      "loss": 0.0795,
+      "step": 3453
+    },
+    {
+      "epoch": 0.5096274437476945,
+      "grad_norm": 3.0262269973754883,
+      "learning_rate": 1.140414202324727e-05,
+      "loss": 0.0616,
+      "step": 3454
+    },
+    {
+      "epoch": 0.5097749907783106,
+      "grad_norm": 1.3839607238769531,
+      "learning_rate": 1.1399041872569938e-05,
+      "loss": 0.0338,
+      "step": 3455
+    },
+    {
+      "epoch": 0.5099225378089266,
+      "grad_norm": 1.7392637729644775,
+      "learning_rate": 1.1393941350688147e-05,
+      "loss": 0.0559,
+      "step": 3456
+    },
+    {
+      "epoch": 0.5100700848395426,
+      "grad_norm": 1.4031736850738525,
+      "learning_rate": 1.1388840458955212e-05,
+      "loss": 0.0362,
+      "step": 3457
+    },
+    {
+      "epoch": 0.5102176318701586,
+      "grad_norm": 2.8859026432037354,
+      "learning_rate": 1.1383739198724537e-05,
+      "loss": 0.1129,
+      "step": 3458
+    },
+    {
+      "epoch": 0.5103651789007746,
+      "grad_norm": 2.3893625736236572,
+      "learning_rate": 1.1378637571349626e-05,
+      "loss": 0.1154,
+      "step": 3459
+    },
+    {
+      "epoch": 0.5105127259313906,
+      "grad_norm": 2.337246894836426,
+      "learning_rate": 1.1373535578184083e-05,
+      "loss": 0.0756,
+      "step": 3460
+    },
+    {
+      "epoch": 0.5105127259313906,
+      "eval_accuracy": 0.9710564399421129,
+      "eval_f1": 0.9509803921568627,
+      "eval_loss": 0.06456489115953445,
+      "eval_precision": 0.9603960396039604,
+      "eval_recall": 0.941747572815534,
+      "eval_runtime": 49.1501,
+      "eval_samples_per_second": 5.921,
+      "eval_steps_per_second": 0.203,
+      "step": 3460
+    },
+    {
+      "epoch": 0.5106602729620067,
+      "grad_norm": 2.6703622341156006,
+      "learning_rate": 1.136843322058161e-05,
+      "loss": 0.0705,
+      "step": 3461
+    },
+    {
+      "epoch": 0.5108078199926227,
+      "grad_norm": 2.123413562774658,
+      "learning_rate": 1.1363330499895996e-05,
+      "loss": 0.0663,
+      "step": 3462
+    },
+    {
+      "epoch": 0.5109553670232386,
+      "grad_norm": 2.953259229660034,
+      "learning_rate": 1.1358227417481143e-05,
+      "loss": 0.0867,
+      "step": 3463
+    },
+    {
+      "epoch": 0.5111029140538547,
+      "grad_norm": 1.2372174263000488,
+      "learning_rate": 1.1353123974691034e-05,
+      "loss": 0.0416,
+      "step": 3464
+    },
+    {
+      "epoch": 0.5112504610844707,
+      "grad_norm": 1.8095917701721191,
+      "learning_rate": 1.1348020172879755e-05,
+      "loss": 0.0484,
+      "step": 3465
+    },
+    {
+      "epoch": 0.5113980081150867,
+      "grad_norm": 2.4721059799194336,
+      "learning_rate": 1.1342916013401486e-05,
+      "loss": 0.0664,
+      "step": 3466
+    },
+    {
+      "epoch": 0.5115455551457027,
+      "grad_norm": 0.934148907661438,
+      "learning_rate": 1.13378114976105e-05,
+      "loss": 0.0274,
+      "step": 3467
+    },
+    {
+      "epoch": 0.5116931021763187,
+      "grad_norm": 1.3078500032424927,
+      "learning_rate": 1.1332706626861167e-05,
+      "loss": 0.0392,
+      "step": 3468
+    },
+    {
+      "epoch": 0.5118406492069347,
+      "grad_norm": 2.1768994331359863,
+      "learning_rate": 1.1327601402507953e-05,
+      "loss": 0.0382,
+      "step": 3469
+    },
+    {
+      "epoch": 0.5119881962375508,
+      "grad_norm": 8.157400131225586,
+      "learning_rate": 1.1322495825905406e-05,
+      "loss": 0.0549,
+      "step": 3470
+    },
+    {
+      "epoch": 0.5121357432681667,
+      "grad_norm": 1.0004053115844727,
+      "learning_rate": 1.1317389898408188e-05,
+      "loss": 0.0223,
+      "step": 3471
+    },
+    {
+      "epoch": 0.5122832902987827,
+      "grad_norm": 2.1725616455078125,
+      "learning_rate": 1.1312283621371036e-05,
+      "loss": 0.0589,
+      "step": 3472
+    },
+    {
+      "epoch": 0.5124308373293988,
+      "grad_norm": 1.3505425453186035,
+      "learning_rate": 1.130717699614879e-05,
+      "loss": 0.0352,
+      "step": 3473
+    },
+    {
+      "epoch": 0.5125783843600148,
+      "grad_norm": 4.985128402709961,
+      "learning_rate": 1.1302070024096374e-05,
+      "loss": 0.0559,
+      "step": 3474
+    },
+    {
+      "epoch": 0.5127259313906307,
+      "grad_norm": 2.157815456390381,
+      "learning_rate": 1.1296962706568814e-05,
+      "loss": 0.0188,
+      "step": 3475
+    },
+    {
+      "epoch": 0.5128734784212468,
+      "grad_norm": 2.7989468574523926,
+      "learning_rate": 1.1291855044921218e-05,
+      "loss": 0.0461,
+      "step": 3476
+    },
+    {
+      "epoch": 0.5130210254518628,
+      "grad_norm": 2.34574031829834,
+      "learning_rate": 1.128674704050879e-05,
+      "loss": 0.0784,
+      "step": 3477
+    },
+    {
+      "epoch": 0.5131685724824788,
+      "grad_norm": 1.7945078611373901,
+      "learning_rate": 1.1281638694686827e-05,
+      "loss": 0.0593,
+      "step": 3478
+    },
+    {
+      "epoch": 0.5133161195130947,
+      "grad_norm": 2.6016180515289307,
+      "learning_rate": 1.1276530008810718e-05,
+      "loss": 0.1086,
+      "step": 3479
+    },
+    {
+      "epoch": 0.5134636665437108,
+      "grad_norm": 2.5083601474761963,
+      "learning_rate": 1.1271420984235928e-05,
+      "loss": 0.0786,
+      "step": 3480
+    },
+    {
+      "epoch": 0.5134636665437108,
+      "eval_accuracy": 0.9681620839363242,
+      "eval_f1": 0.9455445544554455,
+      "eval_loss": 0.06514859199523926,
+      "eval_precision": 0.9646464646464646,
+      "eval_recall": 0.9271844660194175,
+      "eval_runtime": 49.166,
+      "eval_samples_per_second": 5.919,
+      "eval_steps_per_second": 0.203,
+      "step": 3480
+    },
+    {
+      "epoch": 0.5136112135743268,
+      "grad_norm": 3.769692897796631,
+      "learning_rate": 1.126631162231803e-05,
+      "loss": 0.0271,
+      "step": 3481
+    },
+    {
+      "epoch": 0.5137587606049429,
+      "grad_norm": 1.8234009742736816,
+      "learning_rate": 1.1261201924412677e-05,
+      "loss": 0.0455,
+      "step": 3482
+    },
+    {
+      "epoch": 0.5139063076355588,
+      "grad_norm": 2.0844228267669678,
+      "learning_rate": 1.1256091891875616e-05,
+      "loss": 0.0673,
+      "step": 3483
+    },
+    {
+      "epoch": 0.5140538546661748,
+      "grad_norm": 1.3127630949020386,
+      "learning_rate": 1.1250981526062672e-05,
+      "loss": 0.0451,
+      "step": 3484
+    },
+    {
+      "epoch": 0.5142014016967908,
+      "grad_norm": 2.6537387371063232,
+      "learning_rate": 1.1245870828329775e-05,
+      "loss": 0.0963,
+      "step": 3485
+    },
+    {
+      "epoch": 0.5143489487274069,
+      "grad_norm": 2.382176160812378,
+      "learning_rate": 1.1240759800032929e-05,
+      "loss": 0.0614,
+      "step": 3486
+    },
+    {
+      "epoch": 0.5144964957580229,
+      "grad_norm": 2.104100227355957,
+      "learning_rate": 1.1235648442528232e-05,
+      "loss": 0.0351,
+      "step": 3487
+    },
+    {
+      "epoch": 0.5146440427886388,
+      "grad_norm": 2.1463024616241455,
+      "learning_rate": 1.1230536757171871e-05,
+      "loss": 0.0708,
+      "step": 3488
+    },
+    {
+      "epoch": 0.5147915898192549,
+      "grad_norm": 0.8108016848564148,
+      "learning_rate": 1.1225424745320113e-05,
+      "loss": 0.0116,
+      "step": 3489
+    },
+    {
+      "epoch": 0.5149391368498709,
+      "grad_norm": 2.8194987773895264,
+      "learning_rate": 1.122031240832932e-05,
+      "loss": 0.0578,
+      "step": 3490
+    },
+    {
+      "epoch": 0.515086683880487,
+      "grad_norm": 1.612223505973816,
+      "learning_rate": 1.1215199747555932e-05,
+      "loss": 0.0583,
+      "step": 3491
+    },
+    {
+      "epoch": 0.5152342309111029,
+      "grad_norm": 7.699445724487305,
+      "learning_rate": 1.121008676435648e-05,
+      "loss": 0.0716,
+      "step": 3492
+    },
+    {
+      "epoch": 0.5153817779417189,
+      "grad_norm": 2.0828969478607178,
+      "learning_rate": 1.1204973460087587e-05,
+      "loss": 0.0631,
+      "step": 3493
+    },
+    {
+      "epoch": 0.515529324972335,
+      "grad_norm": 1.2769685983657837,
+      "learning_rate": 1.1199859836105941e-05,
+      "loss": 0.009,
+      "step": 3494
+    },
+    {
+      "epoch": 0.515676872002951,
+      "grad_norm": 7.922608852386475,
+      "learning_rate": 1.119474589376834e-05,
+      "loss": 0.082,
+      "step": 3495
+    },
+    {
+      "epoch": 0.5158244190335669,
+      "grad_norm": 1.4526466131210327,
+      "learning_rate": 1.1189631634431649e-05,
+      "loss": 0.0181,
+      "step": 3496
+    },
+    {
+      "epoch": 0.5159719660641829,
+      "grad_norm": 1.4317309856414795,
+      "learning_rate": 1.118451705945282e-05,
+      "loss": 0.0333,
+      "step": 3497
+    },
+    {
+      "epoch": 0.516119513094799,
+      "grad_norm": 3.841702938079834,
+      "learning_rate": 1.1179402170188893e-05,
+      "loss": 0.1089,
+      "step": 3498
+    },
+    {
+      "epoch": 0.516267060125415,
+      "grad_norm": 3.362285852432251,
+      "learning_rate": 1.1174286967996988e-05,
+      "loss": 0.0657,
+      "step": 3499
+    },
+    {
+      "epoch": 0.5164146071560309,
+      "grad_norm": 2.0894968509674072,
+      "learning_rate": 1.1169171454234315e-05,
+      "loss": 0.0663,
+      "step": 3500
+    },
+    {
+      "epoch": 0.5164146071560309,
+      "eval_accuracy": 0.9710564399421129,
+      "eval_f1": 0.9512195121951219,
+      "eval_loss": 0.05881144851446152,
+      "eval_precision": 0.9558823529411765,
+      "eval_recall": 0.9466019417475728,
+      "eval_runtime": 49.3038,
+      "eval_samples_per_second": 5.902,
+      "eval_steps_per_second": 0.203,
+      "step": 3500
     }
   ],
   "logging_steps": 1,
@@ -25878,7 +26638,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0477350387261112e+18,
+  "total_flos": 1.0784648068658627e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null