Training in progress, step 1700, checkpoint

last-checkpoint/optimizer_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:288218a5b8142a31016017d5a1a22a4ebafda31be50778f8dacb2fbcb37f8828
+oid sha256:85962da1d94a1d14005b4253e4a50e923d9a39cbc0e312870a33b7168aa8374a
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7c8394667156ee984c596393f67693a9b5cc418840178c5b43f8cbb09dfa0ff
+oid sha256:56782b0e4caa6d241d8b3d4783c5dcd4d145f869ac96de46fdaa0a8151220694
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:150298c81e3e150533ab45911b6897809bb0166b09d5d2cdcb93e305fed39d8e
+oid sha256:7511705737a7793f9a8f8c9b36c92d09abd33de20c399c92c82066fed75b855e
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e14beee0f55f4ec295a30441a43fa507d9883b8439b259e701da102e2c8ad35
+oid sha256:e6137155b55fbd8cc41045482398a6956043c027297043052e7964e5fc63de66
 size 13990904

last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8222b327cb2d98f6da309bd0a42c7208936ac61c1ad5f27d8bff24fd76b88586
+oid sha256:4ef07e22a52809f46a7c2ae75dc39dc6e0bdbdeab0633c8ccc880b16e4925013
 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:ec30db50d388907127b643e7ebb00b2602f24e58146977f60e3ea1cfaa8d0445
+oid sha256:e4d5138e76782812b7a39315541ceba25964dac848a1c0c2e5ebffa25fe3746e
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:680e92e6643c306b7d3cc36878f17632510cb339cbadb6a63460afe19b9415f0
+oid sha256:6d07999800664897d6fb1a2323f007d63051d8ed7a7651443e9e8e9f617aa90e
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d3a292fa964a6c481019c2cdbcb906249b25ea2f7f5191931355d87ec08b945
+oid sha256:7e22ffa3459b7d0a79f52d958a6a4da9fd7f5643e9390d5ead2fba778e8869c5
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bab15d49e111f0bc53116f47dd1c18ed19a8a40b035367851f11b6467b41a182
+oid sha256:0acf66cdd3277c619b1c7a0e3c8cc4f09bd0828ecf9d9ef0d0ad811d21f43758
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65d52f52123e9ca62ec559b716f1940ca4a8a53f714c3b02698efcd0b18cc4b5
+oid sha256:93f737e8534bf0d32d635cae39e128503c41f663422801b91c42be0efcf1c3c0
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:428391090278e9ca780fb13b62e3204e782b11aac1dab708ebc31e8f7e702b31
+oid sha256:d0e4ea9c22a4dd3329392569ee322c6a72133d25e8dc310620585148dbb3b1d0
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc25b8cf5fa2d06ace0f1f8e357c05618d2c923319b6626233fa2e91b25c5f95
+oid sha256:72cd63d54bf626b1ec79250977df50a1d78b2a6059d11ce4a343f6b001f610c7
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c15760f648f2547093753a06ed41d5008e5c3eaa0be8ecdcb2e32f6d35c8269a
+oid sha256:5c051cdb67600fb9bc7d89ced7dd0d6982fb8567a894f2c94b0adbb1ef594dfb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.23607524898561416,
+  "epoch": 0.25082995204721503,
   "eval_steps": 20,
-  "global_step": 1600,
+  "global_step": 1700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -12179,6 +12179,766 @@
       "eval_samples_per_second": 5.835,
       "eval_steps_per_second": 0.201,
       "step": 1600
+    },
+    {
+      "epoch": 0.23622279601623017,
+      "grad_norm": 3.008150815963745,
+      "learning_rate": 1.8890927981067583e-05,
+      "loss": 0.1196,
+      "step": 1601
+    },
+    {
+      "epoch": 0.23637034304684618,
+      "grad_norm": 1.6604888439178467,
+      "learning_rate": 1.8888569051633613e-05,
+      "loss": 0.0921,
+      "step": 1602
+    },
+    {
+      "epoch": 0.23651789007746218,
+      "grad_norm": 2.6593024730682373,
+      "learning_rate": 1.8886207763816732e-05,
+      "loss": 0.0476,
+      "step": 1603
+    },
+    {
+      "epoch": 0.2366654371080782,
+      "grad_norm": 2.5641930103302,
+      "learning_rate": 1.888384411824345e-05,
+      "loss": 0.1078,
+      "step": 1604
+    },
+    {
+      "epoch": 0.2368129841386942,
+      "grad_norm": 1.1254023313522339,
+      "learning_rate": 1.8881478115540907e-05,
+      "loss": 0.0171,
+      "step": 1605
+    },
+    {
+      "epoch": 0.2369605311693102,
+      "grad_norm": 1.325793981552124,
+      "learning_rate": 1.8879109756336876e-05,
+      "loss": 0.0377,
+      "step": 1606
+    },
+    {
+      "epoch": 0.23710807819992621,
+      "grad_norm": 7.710003852844238,
+      "learning_rate": 1.8876739041259742e-05,
+      "loss": 0.114,
+      "step": 1607
+    },
+    {
+      "epoch": 0.23725562523054222,
+      "grad_norm": 1.0816516876220703,
+      "learning_rate": 1.8874365970938524e-05,
+      "loss": 0.0315,
+      "step": 1608
+    },
+    {
+      "epoch": 0.23740317226115826,
+      "grad_norm": 1.852760910987854,
+      "learning_rate": 1.887199054600286e-05,
+      "loss": 0.0433,
+      "step": 1609
+    },
+    {
+      "epoch": 0.23755071929177426,
+      "grad_norm": 4.503643989562988,
+      "learning_rate": 1.886961276708302e-05,
+      "loss": 0.0586,
+      "step": 1610
+    },
+    {
+      "epoch": 0.23769826632239027,
+      "grad_norm": 2.2752246856689453,
+      "learning_rate": 1.8867232634809895e-05,
+      "loss": 0.0571,
+      "step": 1611
+    },
+    {
+      "epoch": 0.23784581335300628,
+      "grad_norm": 1.762903094291687,
+      "learning_rate": 1.8864850149814995e-05,
+      "loss": 0.0236,
+      "step": 1612
+    },
+    {
+      "epoch": 0.2379933603836223,
+      "grad_norm": 2.781127452850342,
+      "learning_rate": 1.886246531273046e-05,
+      "loss": 0.1219,
+      "step": 1613
+    },
+    {
+      "epoch": 0.2381409074142383,
+      "grad_norm": 1.7541805505752563,
+      "learning_rate": 1.886007812418906e-05,
+      "loss": 0.0381,
+      "step": 1614
+    },
+    {
+      "epoch": 0.2382884544448543,
+      "grad_norm": 1.8100532293319702,
+      "learning_rate": 1.8857688584824172e-05,
+      "loss": 0.0707,
+      "step": 1615
+    },
+    {
+      "epoch": 0.2384360014754703,
+      "grad_norm": 5.112905025482178,
+      "learning_rate": 1.8855296695269815e-05,
+      "loss": 0.0493,
+      "step": 1616
+    },
+    {
+      "epoch": 0.23858354850608632,
+      "grad_norm": 3.7628955841064453,
+      "learning_rate": 1.8852902456160618e-05,
+      "loss": 0.0739,
+      "step": 1617
+    },
+    {
+      "epoch": 0.23873109553670233,
+      "grad_norm": 2.7358105182647705,
+      "learning_rate": 1.885050586813184e-05,
+      "loss": 0.1133,
+      "step": 1618
+    },
+    {
+      "epoch": 0.23887864256731833,
+      "grad_norm": 4.206934928894043,
+      "learning_rate": 1.8848106931819363e-05,
+      "loss": 0.1211,
+      "step": 1619
+    },
+    {
+      "epoch": 0.23902618959793434,
+      "grad_norm": 1.8442342281341553,
+      "learning_rate": 1.8845705647859687e-05,
+      "loss": 0.0693,
+      "step": 1620
+    },
+    {
+      "epoch": 0.23902618959793434,
+      "eval_accuracy": 0.9739507959479016,
+      "eval_f1": 0.9545454545454546,
+      "eval_loss": 0.07409653812646866,
+      "eval_precision": 0.9947368421052631,
+      "eval_recall": 0.9174757281553398,
+      "eval_runtime": 49.553,
+      "eval_samples_per_second": 5.873,
+      "eval_steps_per_second": 0.202,
+      "step": 1620
+    },
+    {
+      "epoch": 0.23917373662855035,
+      "grad_norm": 10.018924713134766,
+      "learning_rate": 1.884330201688995e-05,
+      "loss": 0.197,
+      "step": 1621
+    },
+    {
+      "epoch": 0.23932128365916636,
+      "grad_norm": 3.2351040840148926,
+      "learning_rate": 1.8840896039547894e-05,
+      "loss": 0.0677,
+      "step": 1622
+    },
+    {
+      "epoch": 0.23946883068978236,
+      "grad_norm": 3.178816795349121,
+      "learning_rate": 1.8838487716471885e-05,
+      "loss": 0.0813,
+      "step": 1623
+    },
+    {
+      "epoch": 0.23961637772039837,
+      "grad_norm": 3.182863235473633,
+      "learning_rate": 1.883607704830093e-05,
+      "loss": 0.1022,
+      "step": 1624
+    },
+    {
+      "epoch": 0.23976392475101438,
+      "grad_norm": 2.7225515842437744,
+      "learning_rate": 1.8833664035674643e-05,
+      "loss": 0.0387,
+      "step": 1625
+    },
+    {
+      "epoch": 0.2399114717816304,
+      "grad_norm": 2.1176841259002686,
+      "learning_rate": 1.8831248679233255e-05,
+      "loss": 0.0566,
+      "step": 1626
+    },
+    {
+      "epoch": 0.2400590188122464,
+      "grad_norm": 2.227962017059326,
+      "learning_rate": 1.882883097961763e-05,
+      "loss": 0.0786,
+      "step": 1627
+    },
+    {
+      "epoch": 0.2402065658428624,
+      "grad_norm": 2.132786750793457,
+      "learning_rate": 1.8826410937469256e-05,
+      "loss": 0.0624,
+      "step": 1628
+    },
+    {
+      "epoch": 0.2403541128734784,
+      "grad_norm": 2.2545626163482666,
+      "learning_rate": 1.8823988553430235e-05,
+      "loss": 0.0538,
+      "step": 1629
+    },
+    {
+      "epoch": 0.24050165990409442,
+      "grad_norm": 4.5056538581848145,
+      "learning_rate": 1.8821563828143284e-05,
+      "loss": 0.1264,
+      "step": 1630
+    },
+    {
+      "epoch": 0.24064920693471045,
+      "grad_norm": 0.7923541069030762,
+      "learning_rate": 1.8819136762251765e-05,
+      "loss": 0.0122,
+      "step": 1631
+    },
+    {
+      "epoch": 0.24079675396532646,
+      "grad_norm": 2.7172040939331055,
+      "learning_rate": 1.881670735639963e-05,
+      "loss": 0.0346,
+      "step": 1632
+    },
+    {
+      "epoch": 0.24094430099594247,
+      "grad_norm": 1.0857584476470947,
+      "learning_rate": 1.881427561123148e-05,
+      "loss": 0.0368,
+      "step": 1633
+    },
+    {
+      "epoch": 0.24109184802655848,
+      "grad_norm": 2.4387190341949463,
+      "learning_rate": 1.881184152739252e-05,
+      "loss": 0.1468,
+      "step": 1634
+    },
+    {
+      "epoch": 0.24123939505717448,
+      "grad_norm": 3.6060807704925537,
+      "learning_rate": 1.8809405105528572e-05,
+      "loss": 0.1154,
+      "step": 1635
+    },
+    {
+      "epoch": 0.2413869420877905,
+      "grad_norm": 2.9632816314697266,
+      "learning_rate": 1.8806966346286095e-05,
+      "loss": 0.0649,
+      "step": 1636
+    },
+    {
+      "epoch": 0.2415344891184065,
+      "grad_norm": 2.280517816543579,
+      "learning_rate": 1.8804525250312155e-05,
+      "loss": 0.0458,
+      "step": 1637
+    },
+    {
+      "epoch": 0.2416820361490225,
+      "grad_norm": 1.5791654586791992,
+      "learning_rate": 1.8802081818254446e-05,
+      "loss": 0.0591,
+      "step": 1638
+    },
+    {
+      "epoch": 0.2418295831796385,
+      "grad_norm": 3.066272258758545,
+      "learning_rate": 1.8799636050761276e-05,
+      "loss": 0.0735,
+      "step": 1639
+    },
+    {
+      "epoch": 0.24197713021025452,
+      "grad_norm": 3.7066493034362793,
+      "learning_rate": 1.8797187948481576e-05,
+      "loss": 0.0547,
+      "step": 1640
+    },
+    {
+      "epoch": 0.24197713021025452,
+      "eval_accuracy": 0.975397973950796,
+      "eval_f1": 0.9573934837092731,
+      "eval_loss": 0.07134856283664703,
+      "eval_precision": 0.9896373056994818,
+      "eval_recall": 0.9271844660194175,
+      "eval_runtime": 50.2461,
+      "eval_samples_per_second": 5.791,
+      "eval_steps_per_second": 0.199,
+      "step": 1640
+    },
+    {
+      "epoch": 0.24212467724087053,
+      "grad_norm": 2.341954231262207,
+      "learning_rate": 1.879473751206489e-05,
+      "loss": 0.0773,
+      "step": 1641
+    },
+    {
+      "epoch": 0.24227222427148654,
+      "grad_norm": 2.7641525268554688,
+      "learning_rate": 1.8792284742161394e-05,
+      "loss": 0.0995,
+      "step": 1642
+    },
+    {
+      "epoch": 0.24241977130210254,
+      "grad_norm": 3.9379851818084717,
+      "learning_rate": 1.8789829639421872e-05,
+      "loss": 0.1247,
+      "step": 1643
+    },
+    {
+      "epoch": 0.24256731833271855,
+      "grad_norm": 5.1747541427612305,
+      "learning_rate": 1.8787372204497727e-05,
+      "loss": 0.0858,
+      "step": 1644
+    },
+    {
+      "epoch": 0.24271486536333456,
+      "grad_norm": 1.9137122631072998,
+      "learning_rate": 1.878491243804099e-05,
+      "loss": 0.092,
+      "step": 1645
+    },
+    {
+      "epoch": 0.24286241239395057,
+      "grad_norm": 2.063175678253174,
+      "learning_rate": 1.87824503407043e-05,
+      "loss": 0.0578,
+      "step": 1646
+    },
+    {
+      "epoch": 0.24300995942456657,
+      "grad_norm": 4.144733428955078,
+      "learning_rate": 1.8779985913140927e-05,
+      "loss": 0.0883,
+      "step": 1647
+    },
+    {
+      "epoch": 0.24315750645518258,
+      "grad_norm": 2.499525308609009,
+      "learning_rate": 1.8777519156004742e-05,
+      "loss": 0.0933,
+      "step": 1648
+    },
+    {
+      "epoch": 0.2433050534857986,
+      "grad_norm": 4.733231544494629,
+      "learning_rate": 1.877505006995025e-05,
+      "loss": 0.0867,
+      "step": 1649
+    },
+    {
+      "epoch": 0.2434526005164146,
+      "grad_norm": 1.7096129655838013,
+      "learning_rate": 1.8772578655632568e-05,
+      "loss": 0.0595,
+      "step": 1650
+    },
+    {
+      "epoch": 0.2436001475470306,
+      "grad_norm": 3.6752445697784424,
+      "learning_rate": 1.8770104913707426e-05,
+      "loss": 0.0921,
+      "step": 1651
+    },
+    {
+      "epoch": 0.2437476945776466,
+      "grad_norm": 2.651184558868408,
+      "learning_rate": 1.8767628844831183e-05,
+      "loss": 0.0965,
+      "step": 1652
+    },
+    {
+      "epoch": 0.24389524160826265,
+      "grad_norm": 2.46650767326355,
+      "learning_rate": 1.8765150449660804e-05,
+      "loss": 0.0642,
+      "step": 1653
+    },
+    {
+      "epoch": 0.24404278863887865,
+      "grad_norm": 1.9928101301193237,
+      "learning_rate": 1.876266972885387e-05,
+      "loss": 0.0633,
+      "step": 1654
+    },
+    {
+      "epoch": 0.24419033566949466,
+      "grad_norm": 1.8227845430374146,
+      "learning_rate": 1.87601866830686e-05,
+      "loss": 0.0282,
+      "step": 1655
+    },
+    {
+      "epoch": 0.24433788270011067,
+      "grad_norm": 1.8954331874847412,
+      "learning_rate": 1.87577013129638e-05,
+      "loss": 0.0936,
+      "step": 1656
+    },
+    {
+      "epoch": 0.24448542973072668,
+      "grad_norm": 1.4748156070709229,
+      "learning_rate": 1.8755213619198915e-05,
+      "loss": 0.0548,
+      "step": 1657
+    },
+    {
+      "epoch": 0.24463297676134269,
+      "grad_norm": 2.6450955867767334,
+      "learning_rate": 1.8752723602433997e-05,
+      "loss": 0.0697,
+      "step": 1658
+    },
+    {
+      "epoch": 0.2447805237919587,
+      "grad_norm": 1.495141625404358,
+      "learning_rate": 1.8750231263329716e-05,
+      "loss": 0.0529,
+      "step": 1659
+    },
+    {
+      "epoch": 0.2449280708225747,
+      "grad_norm": 3.938822031021118,
+      "learning_rate": 1.8747736602547358e-05,
+      "loss": 0.0983,
+      "step": 1660
+    },
+    {
+      "epoch": 0.2449280708225747,
+      "eval_accuracy": 0.9739507959479016,
+      "eval_f1": 0.9547738693467337,
+      "eval_loss": 0.07112825661897659,
+      "eval_precision": 0.9895833333333334,
+      "eval_recall": 0.9223300970873787,
+      "eval_runtime": 49.5534,
+      "eval_samples_per_second": 5.872,
+      "eval_steps_per_second": 0.202,
+      "step": 1660
+    },
+    {
+      "epoch": 0.2450756178531907,
+      "grad_norm": 1.5419602394104004,
+      "learning_rate": 1.8745239620748822e-05,
+      "loss": 0.0493,
+      "step": 1661
+    },
+    {
+      "epoch": 0.24522316488380672,
+      "grad_norm": 2.9517505168914795,
+      "learning_rate": 1.8742740318596632e-05,
+      "loss": 0.0674,
+      "step": 1662
+    },
+    {
+      "epoch": 0.24537071191442272,
+      "grad_norm": 1.3199691772460938,
+      "learning_rate": 1.8740238696753925e-05,
+      "loss": 0.0372,
+      "step": 1663
+    },
+    {
+      "epoch": 0.24551825894503873,
+      "grad_norm": 5.415014743804932,
+      "learning_rate": 1.873773475588444e-05,
+      "loss": 0.06,
+      "step": 1664
+    },
+    {
+      "epoch": 0.24566580597565474,
+      "grad_norm": 2.477362871170044,
+      "learning_rate": 1.873522849665255e-05,
+      "loss": 0.113,
+      "step": 1665
+    },
+    {
+      "epoch": 0.24581335300627075,
+      "grad_norm": 2.2444581985473633,
+      "learning_rate": 1.873271991972323e-05,
+      "loss": 0.0704,
+      "step": 1666
+    },
+    {
+      "epoch": 0.24596090003688675,
+      "grad_norm": 2.8318018913269043,
+      "learning_rate": 1.8730209025762077e-05,
+      "loss": 0.0688,
+      "step": 1667
+    },
+    {
+      "epoch": 0.24610844706750276,
+      "grad_norm": 3.7584753036499023,
+      "learning_rate": 1.87276958154353e-05,
+      "loss": 0.1223,
+      "step": 1668
+    },
+    {
+      "epoch": 0.24625599409811877,
+      "grad_norm": 2.150073289871216,
+      "learning_rate": 1.8725180289409725e-05,
+      "loss": 0.0549,
+      "step": 1669
+    },
+    {
+      "epoch": 0.24640354112873478,
+      "grad_norm": 2.330817699432373,
+      "learning_rate": 1.872266244835279e-05,
+      "loss": 0.0545,
+      "step": 1670
+    },
+    {
+      "epoch": 0.24655108815935078,
+      "grad_norm": 4.182545185089111,
+      "learning_rate": 1.8720142292932544e-05,
+      "loss": 0.0861,
+      "step": 1671
+    },
+    {
+      "epoch": 0.2466986351899668,
+      "grad_norm": 2.2650673389434814,
+      "learning_rate": 1.8717619823817655e-05,
+      "loss": 0.0871,
+      "step": 1672
+    },
+    {
+      "epoch": 0.2468461822205828,
+      "grad_norm": 2.7728540897369385,
+      "learning_rate": 1.871509504167741e-05,
+      "loss": 0.0798,
+      "step": 1673
+    },
+    {
+      "epoch": 0.2469937292511988,
+      "grad_norm": 1.604771614074707,
+      "learning_rate": 1.8712567947181695e-05,
+      "loss": 0.0634,
+      "step": 1674
+    },
+    {
+      "epoch": 0.24714127628181484,
+      "grad_norm": 1.5157824754714966,
+      "learning_rate": 1.8710038541001024e-05,
+      "loss": 0.045,
+      "step": 1675
+    },
+    {
+      "epoch": 0.24728882331243085,
+      "grad_norm": 1.7582708597183228,
+      "learning_rate": 1.8707506823806514e-05,
+      "loss": 0.0654,
+      "step": 1676
+    },
+    {
+      "epoch": 0.24743637034304686,
+      "grad_norm": 2.13720965385437,
+      "learning_rate": 1.87049727962699e-05,
+      "loss": 0.0637,
+      "step": 1677
+    },
+    {
+      "epoch": 0.24758391737366287,
+      "grad_norm": 1.3255536556243896,
+      "learning_rate": 1.8702436459063533e-05,
+      "loss": 0.037,
+      "step": 1678
+    },
+    {
+      "epoch": 0.24773146440427887,
+      "grad_norm": 3.8610284328460693,
+      "learning_rate": 1.8699897812860374e-05,
+      "loss": 0.1258,
+      "step": 1679
+    },
+    {
+      "epoch": 0.24787901143489488,
+      "grad_norm": 3.3714330196380615,
+      "learning_rate": 1.869735685833399e-05,
+      "loss": 0.0599,
+      "step": 1680
+    },
+    {
+      "epoch": 0.24787901143489488,
+      "eval_accuracy": 0.9739507959479016,
+      "eval_f1": 0.955,
+      "eval_loss": 0.0660150945186615,
+      "eval_precision": 0.9845360824742269,
+      "eval_recall": 0.9271844660194175,
+      "eval_runtime": 50.4891,
+      "eval_samples_per_second": 5.764,
+      "eval_steps_per_second": 0.198,
+      "step": 1680
+    },
+    {
+      "epoch": 0.2480265584655109,
+      "grad_norm": 7.666978359222412,
+      "learning_rate": 1.8694813596158568e-05,
+      "loss": 0.065,
+      "step": 1681
+    },
+    {
+      "epoch": 0.2481741054961269,
+      "grad_norm": 1.7158877849578857,
+      "learning_rate": 1.8692268027008912e-05,
+      "loss": 0.0468,
+      "step": 1682
+    },
+    {
+      "epoch": 0.2483216525267429,
+      "grad_norm": 2.407661199569702,
+      "learning_rate": 1.8689720151560425e-05,
+      "loss": 0.0526,
+      "step": 1683
+    },
+    {
+      "epoch": 0.2484691995573589,
+      "grad_norm": 1.6817408800125122,
+      "learning_rate": 1.868716997048913e-05,
+      "loss": 0.0444,
+      "step": 1684
+    },
+    {
+      "epoch": 0.24861674658797492,
+      "grad_norm": 1.7822405099868774,
+      "learning_rate": 1.8684617484471662e-05,
+      "loss": 0.0706,
+      "step": 1685
+    },
+    {
+      "epoch": 0.24876429361859093,
+      "grad_norm": 1.842396855354309,
+      "learning_rate": 1.8682062694185267e-05,
+      "loss": 0.0323,
+      "step": 1686
+    },
+    {
+      "epoch": 0.24891184064920693,
+      "grad_norm": 3.4837851524353027,
+      "learning_rate": 1.86795056003078e-05,
+      "loss": 0.1292,
+      "step": 1687
+    },
+    {
+      "epoch": 0.24905938767982294,
+      "grad_norm": 3.1840720176696777,
+      "learning_rate": 1.8676946203517728e-05,
+      "loss": 0.1145,
+      "step": 1688
+    },
+    {
+      "epoch": 0.24920693471043895,
+      "grad_norm": 4.872955799102783,
+      "learning_rate": 1.867438450449413e-05,
+      "loss": 0.0766,
+      "step": 1689
+    },
+    {
+      "epoch": 0.24935448174105496,
+      "grad_norm": 3.049365758895874,
+      "learning_rate": 1.8671820503916696e-05,
+      "loss": 0.1221,
+      "step": 1690
+    },
+    {
+      "epoch": 0.24950202877167096,
+      "grad_norm": 1.2856934070587158,
+      "learning_rate": 1.8669254202465725e-05,
+      "loss": 0.0264,
+      "step": 1691
+    },
+    {
+      "epoch": 0.24964957580228697,
+      "grad_norm": 2.228694438934326,
+      "learning_rate": 1.866668560082213e-05,
+      "loss": 0.0331,
+      "step": 1692
+    },
+    {
+      "epoch": 0.24979712283290298,
+      "grad_norm": 2.5879011154174805,
+      "learning_rate": 1.8664114699667427e-05,
+      "loss": 0.1078,
+      "step": 1693
+    },
+    {
+      "epoch": 0.249944669863519,
+      "grad_norm": 4.204154968261719,
+      "learning_rate": 1.8661541499683756e-05,
+      "loss": 0.1442,
+      "step": 1694
+    },
+    {
+      "epoch": 0.250092216894135,
+      "grad_norm": 1.7922683954238892,
+      "learning_rate": 1.865896600155385e-05,
+      "loss": 0.0385,
+      "step": 1695
+    },
+    {
+      "epoch": 0.250239763924751,
+      "grad_norm": 2.9584996700286865,
+      "learning_rate": 1.8656388205961066e-05,
+      "loss": 0.0558,
+      "step": 1696
+    },
+    {
+      "epoch": 0.25038731095536704,
+      "grad_norm": 2.5491790771484375,
+      "learning_rate": 1.8653808113589357e-05,
+      "loss": 0.022,
+      "step": 1697
+    },
+    {
+      "epoch": 0.250534857985983,
+      "grad_norm": 2.3495829105377197,
+      "learning_rate": 1.86512257251233e-05,
+      "loss": 0.0433,
+      "step": 1698
+    },
+    {
+      "epoch": 0.25068240501659905,
+      "grad_norm": 7.000943183898926,
+      "learning_rate": 1.8648641041248067e-05,
+      "loss": 0.1028,
+      "step": 1699
+    },
+    {
+      "epoch": 0.25082995204721503,
+      "grad_norm": 3.87225604057312,
+      "learning_rate": 1.864605406264945e-05,
+      "loss": 0.1337,
+      "step": 1700
+    },
+    {
+      "epoch": 0.25082995204721503,
+      "eval_accuracy": 0.9797395079594791,
+      "eval_f1": 0.9653465346534653,
+      "eval_loss": 0.06515882909297943,
+      "eval_precision": 0.9848484848484849,
+      "eval_recall": 0.9466019417475728,
+      "eval_runtime": 50.4012,
+      "eval_samples_per_second": 5.774,
+      "eval_steps_per_second": 0.198,
+      "step": 1700
     }
   ],
   "logging_steps": 1,
@@ -12198,7 +12958,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.9270782221195674e+17,
+  "total_flos": 5.234024881879777e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null