Training in progress, step 1900, checkpoint

last-checkpoint/optimizer_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b85cfa532e3be66559e4eded0079f59370684d0066f69df72c3c9400a7beff1
+oid sha256:28857cb9e0be49da9e27b629ebac0b929e26615e0cb956826785696ab72d46d4
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:006b7270ce13a5f5dc6c6a33b3cff5a74eb16868579d3e30b1763ba1e93c404e
+oid sha256:d8c49e559b6b4f416bbe71ab95eb809cd2152322194e0d82ce2ee4782b54b733
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76fb1455319679d06cc858e9dcdfaa6350bfd77929cb26479f070cf1390648b7
+oid sha256:826620eef496dada5a0bd10fd0501ed9e3b917ca5d53b7b3307adaa0c40e9c0a
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff50ca45d668f5ecdc7cd80ec4261fe42369ac91ece544c0f807f49f4cf7ec9b
+oid sha256:f053736a8d18b88eaf16fb0091e3eea791582d19b4998fffa205527eb11fd842
 size 13990904

last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:066b8637e1804a15a6478d4144b24ac2b27af8920ee58edf2c6d9a0550266da5
+oid sha256:42a878482407bd5cdcaca595c5d1f0f5f18292843a2df8afd0805b66f7053fd1
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3279d5ccb156c3893823aae49726395635fa6e716ad7192103c8ce3199585117
+oid sha256:ffb4a03660b6ae6e7f36eab2c9c6d5b94fe0520d91a8f118e3c7dc78a83a43d3
 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:e9e61b3efbb77c5def50573a42ce6977dc365728552420a3be0f27de4b665dd3
+oid sha256:179437bc530d7a38360550cadbd486ec3f690176eb97bfc0016467a21bf75f3e
 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:ca72d98e1539ac78ef5f48fd38c13952c6ddf6f9976d7f506cb6d755e8df2db7
+oid sha256:8c98c962767e2e776d9f1fe125e10b1b9e80f0ff26ef335faee7b8aea592217e
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:473f41c5ecf5a91a8877bf819cd4fb40af5726999f740a4900d1725a79f97652
+oid sha256:0a80971c6a3cdf0a64db6f36cdbcbbc3fa78a696c4eacb96b285adb3a141dee3
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:214988d608c94f3b98fd14e7214497626c32df0dc44c1828bebcce6a105eb939
+oid sha256:210bd75a910ba5f2aee3689c5be7cad07f43353aa6618c4b5b0b6c4fc25b8d13
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b17baeb1a788abd9072f968ef0c2b9f4a57cac0fce20296a5a188b25a744f6e
+oid sha256:3cc6493a390929eaeac1071931e6cab5c12abcdef1b1c1ac9ee2465743bb62b0
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dec491f21fa25d9c558566ae69f94017b4507d08b4e301cbc032a487f686fc1c
+oid sha256:ad07cb5cf5ed67904b110911fdc132a304b947b62c27deb9599f9c2a005a0ee4
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6da1eeff6bbf88f1aa9e5a37469b6c8087c23d3160c8f0dc8d1272c55df086e
+oid sha256:0ed00353c07d3c7708b999e1b228d01d26bab698f0a06f28a4a595970adaea50
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.26558465510881596,
+  "epoch": 0.28033935817041683,
   "eval_steps": 20,
-  "global_step": 1800,
+  "global_step": 1900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -13699,6 +13699,766 @@
       "eval_samples_per_second": 5.803,
       "eval_steps_per_second": 0.199,
       "step": 1800
+    },
+    {
+      "epoch": 0.26573220213943194,
+      "grad_norm": 4.462726593017578,
+      "learning_rate": 1.837307316892944e-05,
+      "loss": 0.0945,
+      "step": 1801
+    },
+    {
+      "epoch": 0.265879749170048,
+      "grad_norm": 2.278245687484741,
+      "learning_rate": 1.837025584101264e-05,
+      "loss": 0.09,
+      "step": 1802
+    },
+    {
+      "epoch": 0.26602729620066395,
+      "grad_norm": 2.3065855503082275,
+      "learning_rate": 1.8367436292235743e-05,
+      "loss": 0.0595,
+      "step": 1803
+    },
+    {
+      "epoch": 0.26617484323128,
+      "grad_norm": 2.1850202083587646,
+      "learning_rate": 1.8364614523346847e-05,
+      "loss": 0.0452,
+      "step": 1804
+    },
+    {
+      "epoch": 0.26632239026189597,
+      "grad_norm": 2.008924722671509,
+      "learning_rate": 1.836179053509465e-05,
+      "loss": 0.0625,
+      "step": 1805
+    },
+    {
+      "epoch": 0.266469937292512,
+      "grad_norm": 2.2581794261932373,
+      "learning_rate": 1.835896432822843e-05,
+      "loss": 0.075,
+      "step": 1806
+    },
+    {
+      "epoch": 0.266617484323128,
+      "grad_norm": 4.481566429138184,
+      "learning_rate": 1.835613590349806e-05,
+      "loss": 0.0996,
+      "step": 1807
+    },
+    {
+      "epoch": 0.266765031353744,
+      "grad_norm": 2.1959474086761475,
+      "learning_rate": 1.8353305261654003e-05,
+      "loss": 0.0506,
+      "step": 1808
+    },
+    {
+      "epoch": 0.26691257838436,
+      "grad_norm": 1.564278244972229,
+      "learning_rate": 1.83504724034473e-05,
+      "loss": 0.0766,
+      "step": 1809
+    },
+    {
+      "epoch": 0.26706012541497604,
+      "grad_norm": 1.711566686630249,
+      "learning_rate": 1.8347637329629585e-05,
+      "loss": 0.0549,
+      "step": 1810
+    },
+    {
+      "epoch": 0.267207672445592,
+      "grad_norm": 1.9015671014785767,
+      "learning_rate": 1.8344800040953092e-05,
+      "loss": 0.0871,
+      "step": 1811
+    },
+    {
+      "epoch": 0.26735521947620805,
+      "grad_norm": 1.4092458486557007,
+      "learning_rate": 1.8341960538170622e-05,
+      "loss": 0.056,
+      "step": 1812
+    },
+    {
+      "epoch": 0.26750276650682403,
+      "grad_norm": 1.2663614749908447,
+      "learning_rate": 1.833911882203558e-05,
+      "loss": 0.0361,
+      "step": 1813
+    },
+    {
+      "epoch": 0.26765031353744007,
+      "grad_norm": 2.314241886138916,
+      "learning_rate": 1.8336274893301947e-05,
+      "loss": 0.0667,
+      "step": 1814
+    },
+    {
+      "epoch": 0.26779786056805605,
+      "grad_norm": 1.9834822416305542,
+      "learning_rate": 1.83334287527243e-05,
+      "loss": 0.0494,
+      "step": 1815
+    },
+    {
+      "epoch": 0.2679454075986721,
+      "grad_norm": 2.036881446838379,
+      "learning_rate": 1.833058040105779e-05,
+      "loss": 0.0756,
+      "step": 1816
+    },
+    {
+      "epoch": 0.26809295462928806,
+      "grad_norm": 1.7831075191497803,
+      "learning_rate": 1.8327729839058176e-05,
+      "loss": 0.0371,
+      "step": 1817
+    },
+    {
+      "epoch": 0.2682405016599041,
+      "grad_norm": 1.0665255784988403,
+      "learning_rate": 1.8324877067481782e-05,
+      "loss": 0.0075,
+      "step": 1818
+    },
+    {
+      "epoch": 0.2683880486905201,
+      "grad_norm": 2.107034206390381,
+      "learning_rate": 1.8322022087085533e-05,
+      "loss": 0.0229,
+      "step": 1819
+    },
+    {
+      "epoch": 0.2685355957211361,
+      "grad_norm": 0.44284266233444214,
+      "learning_rate": 1.8319164898626927e-05,
+      "loss": 0.0079,
+      "step": 1820
+    },
+    {
+      "epoch": 0.2685355957211361,
+      "eval_accuracy": 0.9739507959479016,
+      "eval_f1": 0.9545454545454546,
+      "eval_loss": 0.07334955036640167,
+      "eval_precision": 0.9947368421052631,
+      "eval_recall": 0.9174757281553398,
+      "eval_runtime": 49.9163,
+      "eval_samples_per_second": 5.83,
+      "eval_steps_per_second": 0.2,
+      "step": 1820
+    },
+    {
+      "epoch": 0.26868314275175215,
+      "grad_norm": 5.438878536224365,
+      "learning_rate": 1.8316305502864064e-05,
+      "loss": 0.0422,
+      "step": 1821
+    },
+    {
+      "epoch": 0.2688306897823681,
+      "grad_norm": 4.154041290283203,
+      "learning_rate": 1.8313443900555615e-05,
+      "loss": 0.1081,
+      "step": 1822
+    },
+    {
+      "epoch": 0.26897823681298416,
+      "grad_norm": 1.2309131622314453,
+      "learning_rate": 1.8310580092460838e-05,
+      "loss": 0.0518,
+      "step": 1823
+    },
+    {
+      "epoch": 0.26912578384360014,
+      "grad_norm": 1.512600064277649,
+      "learning_rate": 1.830771407933959e-05,
+      "loss": 0.0522,
+      "step": 1824
+    },
+    {
+      "epoch": 0.2692733308742162,
+      "grad_norm": 1.9559988975524902,
+      "learning_rate": 1.8304845861952295e-05,
+      "loss": 0.0539,
+      "step": 1825
+    },
+    {
+      "epoch": 0.26942087790483216,
+      "grad_norm": 2.5186820030212402,
+      "learning_rate": 1.830197544105998e-05,
+      "loss": 0.0358,
+      "step": 1826
+    },
+    {
+      "epoch": 0.2695684249354482,
+      "grad_norm": 1.0470854043960571,
+      "learning_rate": 1.8299102817424234e-05,
+      "loss": 0.0123,
+      "step": 1827
+    },
+    {
+      "epoch": 0.26971597196606417,
+      "grad_norm": 3.760580539703369,
+      "learning_rate": 1.8296227991807253e-05,
+      "loss": 0.045,
+      "step": 1828
+    },
+    {
+      "epoch": 0.2698635189966802,
+      "grad_norm": 5.5353546142578125,
+      "learning_rate": 1.829335096497181e-05,
+      "loss": 0.1079,
+      "step": 1829
+    },
+    {
+      "epoch": 0.2700110660272962,
+      "grad_norm": 5.633973598480225,
+      "learning_rate": 1.829047173768125e-05,
+      "loss": 0.0781,
+      "step": 1830
+    },
+    {
+      "epoch": 0.2701586130579122,
+      "grad_norm": 2.8763039112091064,
+      "learning_rate": 1.8287590310699515e-05,
+      "loss": 0.0832,
+      "step": 1831
+    },
+    {
+      "epoch": 0.2703061600885282,
+      "grad_norm": 7.963526248931885,
+      "learning_rate": 1.828470668479113e-05,
+      "loss": 0.1088,
+      "step": 1832
+    },
+    {
+      "epoch": 0.27045370711914424,
+      "grad_norm": 14.26453685760498,
+      "learning_rate": 1.82818208607212e-05,
+      "loss": 0.1011,
+      "step": 1833
+    },
+    {
+      "epoch": 0.2706012541497602,
+      "grad_norm": 2.874347448348999,
+      "learning_rate": 1.8278932839255412e-05,
+      "loss": 0.0487,
+      "step": 1834
+    },
+    {
+      "epoch": 0.27074880118037625,
+      "grad_norm": 2.6893510818481445,
+      "learning_rate": 1.827604262116004e-05,
+      "loss": 0.0854,
+      "step": 1835
+    },
+    {
+      "epoch": 0.27089634821099223,
+      "grad_norm": 2.124901056289673,
+      "learning_rate": 1.8273150207201938e-05,
+      "loss": 0.0723,
+      "step": 1836
+    },
+    {
+      "epoch": 0.27104389524160827,
+      "grad_norm": 1.1771577596664429,
+      "learning_rate": 1.8270255598148542e-05,
+      "loss": 0.0286,
+      "step": 1837
+    },
+    {
+      "epoch": 0.27119144227222425,
+      "grad_norm": 1.573038101196289,
+      "learning_rate": 1.8267358794767873e-05,
+      "loss": 0.0271,
+      "step": 1838
+    },
+    {
+      "epoch": 0.2713389893028403,
+      "grad_norm": 4.747241020202637,
+      "learning_rate": 1.8264459797828528e-05,
+      "loss": 0.0473,
+      "step": 1839
+    },
+    {
+      "epoch": 0.27148653633345626,
+      "grad_norm": 2.565274477005005,
+      "learning_rate": 1.82615586080997e-05,
+      "loss": 0.056,
+      "step": 1840
+    },
+    {
+      "epoch": 0.27148653633345626,
+      "eval_accuracy": 0.9739507959479016,
+      "eval_f1": 0.9552238805970149,
+      "eval_loss": 0.07094237208366394,
+      "eval_precision": 0.9795918367346939,
+      "eval_recall": 0.9320388349514563,
+      "eval_runtime": 49.1776,
+      "eval_samples_per_second": 5.917,
+      "eval_steps_per_second": 0.203,
+      "step": 1840
+    },
+    {
+      "epoch": 0.2716340833640723,
+      "grad_norm": 3.047848701477051,
+      "learning_rate": 1.825865522635115e-05,
+      "loss": 0.0683,
+      "step": 1841
+    },
+    {
+      "epoch": 0.27178163039468833,
+      "grad_norm": 3.3757214546203613,
+      "learning_rate": 1.8255749653353225e-05,
+      "loss": 0.1105,
+      "step": 1842
+    },
+    {
+      "epoch": 0.2719291774253043,
+      "grad_norm": 4.784446716308594,
+      "learning_rate": 1.8252841889876854e-05,
+      "loss": 0.0595,
+      "step": 1843
+    },
+    {
+      "epoch": 0.27207672445592035,
+      "grad_norm": 2.870875835418701,
+      "learning_rate": 1.824993193669355e-05,
+      "loss": 0.0718,
+      "step": 1844
+    },
+    {
+      "epoch": 0.27222427148653633,
+      "grad_norm": 3.5102977752685547,
+      "learning_rate": 1.82470197945754e-05,
+      "loss": 0.0824,
+      "step": 1845
+    },
+    {
+      "epoch": 0.27237181851715236,
+      "grad_norm": 0.9509576559066772,
+      "learning_rate": 1.8244105464295073e-05,
+      "loss": 0.0225,
+      "step": 1846
+    },
+    {
+      "epoch": 0.27251936554776834,
+      "grad_norm": 1.8587613105773926,
+      "learning_rate": 1.8241188946625832e-05,
+      "loss": 0.0779,
+      "step": 1847
+    },
+    {
+      "epoch": 0.2726669125783844,
+      "grad_norm": 1.541709065437317,
+      "learning_rate": 1.82382702423415e-05,
+      "loss": 0.0283,
+      "step": 1848
+    },
+    {
+      "epoch": 0.27281445960900036,
+      "grad_norm": 2.8956470489501953,
+      "learning_rate": 1.8235349352216495e-05,
+      "loss": 0.1142,
+      "step": 1849
+    },
+    {
+      "epoch": 0.2729620066396164,
+      "grad_norm": 1.300102710723877,
+      "learning_rate": 1.8232426277025804e-05,
+      "loss": 0.0639,
+      "step": 1850
+    },
+    {
+      "epoch": 0.2731095536702324,
+      "grad_norm": 1.6062426567077637,
+      "learning_rate": 1.822950101754501e-05,
+      "loss": 0.048,
+      "step": 1851
+    },
+    {
+      "epoch": 0.2732571007008484,
+      "grad_norm": 4.50151252746582,
+      "learning_rate": 1.8226573574550253e-05,
+      "loss": 0.0561,
+      "step": 1852
+    },
+    {
+      "epoch": 0.2734046477314644,
+      "grad_norm": 2.7688539028167725,
+      "learning_rate": 1.822364394881827e-05,
+      "loss": 0.0327,
+      "step": 1853
+    },
+    {
+      "epoch": 0.2735521947620804,
+      "grad_norm": 1.9938652515411377,
+      "learning_rate": 1.8220712141126375e-05,
+      "loss": 0.0675,
+      "step": 1854
+    },
+    {
+      "epoch": 0.2736997417926964,
+      "grad_norm": 2.556931734085083,
+      "learning_rate": 1.821777815225245e-05,
+      "loss": 0.0899,
+      "step": 1855
+    },
+    {
+      "epoch": 0.27384728882331244,
+      "grad_norm": 4.636996269226074,
+      "learning_rate": 1.8214841982974975e-05,
+      "loss": 0.1662,
+      "step": 1856
+    },
+    {
+      "epoch": 0.2739948358539284,
+      "grad_norm": 2.0064525604248047,
+      "learning_rate": 1.8211903634072983e-05,
+      "loss": 0.0573,
+      "step": 1857
+    },
+    {
+      "epoch": 0.27414238288454446,
+      "grad_norm": 3.2013099193573,
+      "learning_rate": 1.8208963106326108e-05,
+      "loss": 0.0901,
+      "step": 1858
+    },
+    {
+      "epoch": 0.27428992991516044,
+      "grad_norm": 2.746439218521118,
+      "learning_rate": 1.820602040051455e-05,
+      "loss": 0.0737,
+      "step": 1859
+    },
+    {
+      "epoch": 0.27443747694577647,
+      "grad_norm": 3.1914734840393066,
+      "learning_rate": 1.8203075517419092e-05,
+      "loss": 0.0923,
+      "step": 1860
+    },
+    {
+      "epoch": 0.27443747694577647,
+      "eval_accuracy": 0.9739507959479016,
+      "eval_f1": 0.9556650246305419,
+      "eval_loss": 0.06761012226343155,
+      "eval_precision": 0.97,
+      "eval_recall": 0.941747572815534,
+      "eval_runtime": 49.2497,
+      "eval_samples_per_second": 5.909,
+      "eval_steps_per_second": 0.203,
+      "step": 1860
+    },
+    {
+      "epoch": 0.27458502397639245,
+      "grad_norm": 1.8137160539627075,
+      "learning_rate": 1.820012845782109e-05,
+      "loss": 0.0452,
+      "step": 1861
+    },
+    {
+      "epoch": 0.2747325710070085,
+      "grad_norm": 7.028554916381836,
+      "learning_rate": 1.8197179222502486e-05,
+      "loss": 0.0723,
+      "step": 1862
+    },
+    {
+      "epoch": 0.27488011803762447,
+      "grad_norm": 2.008192539215088,
+      "learning_rate": 1.819422781224579e-05,
+      "loss": 0.0827,
+      "step": 1863
+    },
+    {
+      "epoch": 0.2750276650682405,
+      "grad_norm": 2.3676629066467285,
+      "learning_rate": 1.8191274227834087e-05,
+      "loss": 0.0803,
+      "step": 1864
+    },
+    {
+      "epoch": 0.27517521209885654,
+      "grad_norm": 2.65525221824646,
+      "learning_rate": 1.8188318470051054e-05,
+      "loss": 0.1222,
+      "step": 1865
+    },
+    {
+      "epoch": 0.2753227591294725,
+      "grad_norm": 3.2418432235717773,
+      "learning_rate": 1.818536053968093e-05,
+      "loss": 0.1249,
+      "step": 1866
+    },
+    {
+      "epoch": 0.27547030616008855,
+      "grad_norm": 1.959547519683838,
+      "learning_rate": 1.8182400437508537e-05,
+      "loss": 0.0256,
+      "step": 1867
+    },
+    {
+      "epoch": 0.27561785319070453,
+      "grad_norm": 1.6460672616958618,
+      "learning_rate": 1.817943816431927e-05,
+      "loss": 0.0253,
+      "step": 1868
+    },
+    {
+      "epoch": 0.27576540022132057,
+      "grad_norm": 2.181018590927124,
+      "learning_rate": 1.8176473720899107e-05,
+      "loss": 0.0893,
+      "step": 1869
+    },
+    {
+      "epoch": 0.27591294725193655,
+      "grad_norm": 1.9750832319259644,
+      "learning_rate": 1.817350710803459e-05,
+      "loss": 0.0389,
+      "step": 1870
+    },
+    {
+      "epoch": 0.2760604942825526,
+      "grad_norm": 3.312065601348877,
+      "learning_rate": 1.817053832651285e-05,
+      "loss": 0.0166,
+      "step": 1871
+    },
+    {
+      "epoch": 0.27620804131316856,
+      "grad_norm": 1.3024770021438599,
+      "learning_rate": 1.816756737712158e-05,
+      "loss": 0.0368,
+      "step": 1872
+    },
+    {
+      "epoch": 0.2763555883437846,
+      "grad_norm": 1.5345538854599,
+      "learning_rate": 1.816459426064906e-05,
+      "loss": 0.0656,
+      "step": 1873
+    },
+    {
+      "epoch": 0.2765031353744006,
+      "grad_norm": 2.562371015548706,
+      "learning_rate": 1.816161897788414e-05,
+      "loss": 0.0422,
+      "step": 1874
+    },
+    {
+      "epoch": 0.2766506824050166,
+      "grad_norm": 2.397543430328369,
+      "learning_rate": 1.815864152961624e-05,
+      "loss": 0.0366,
+      "step": 1875
+    },
+    {
+      "epoch": 0.2767982294356326,
+      "grad_norm": 3.582508087158203,
+      "learning_rate": 1.8155661916635362e-05,
+      "loss": 0.1649,
+      "step": 1876
+    },
+    {
+      "epoch": 0.2769457764662486,
+      "grad_norm": 4.200384140014648,
+      "learning_rate": 1.8152680139732083e-05,
+      "loss": 0.1155,
+      "step": 1877
+    },
+    {
+      "epoch": 0.2770933234968646,
+      "grad_norm": 4.91301965713501,
+      "learning_rate": 1.8149696199697547e-05,
+      "loss": 0.1864,
+      "step": 1878
+    },
+    {
+      "epoch": 0.27724087052748064,
+      "grad_norm": 1.6632002592086792,
+      "learning_rate": 1.8146710097323473e-05,
+      "loss": 0.0541,
+      "step": 1879
+    },
+    {
+      "epoch": 0.2773884175580966,
+      "grad_norm": 2.451502561569214,
+      "learning_rate": 1.8143721833402166e-05,
+      "loss": 0.0769,
+      "step": 1880
+    },
+    {
+      "epoch": 0.2773884175580966,
+      "eval_accuracy": 0.975397973950796,
+      "eval_f1": 0.9571788413098237,
+      "eval_loss": 0.07145875692367554,
+      "eval_precision": 0.9947643979057592,
+      "eval_recall": 0.9223300970873787,
+      "eval_runtime": 50.6396,
+      "eval_samples_per_second": 5.746,
+      "eval_steps_per_second": 0.197,
+      "step": 1880
+    },
+    {
+      "epoch": 0.27753596458871266,
+      "grad_norm": 3.385312080383301,
+      "learning_rate": 1.8140731408726484e-05,
+      "loss": 0.1248,
+      "step": 1881
+    },
+    {
+      "epoch": 0.27768351161932864,
+      "grad_norm": 1.4377604722976685,
+      "learning_rate": 1.8137738824089876e-05,
+      "loss": 0.0452,
+      "step": 1882
+    },
+    {
+      "epoch": 0.2778310586499447,
+      "grad_norm": 2.1186070442199707,
+      "learning_rate": 1.813474408028635e-05,
+      "loss": 0.0544,
+      "step": 1883
+    },
+    {
+      "epoch": 0.27797860568056065,
+      "grad_norm": 4.867067337036133,
+      "learning_rate": 1.8131747178110507e-05,
+      "loss": 0.1193,
+      "step": 1884
+    },
+    {
+      "epoch": 0.2781261527111767,
+      "grad_norm": 3.2188632488250732,
+      "learning_rate": 1.81287481183575e-05,
+      "loss": 0.1098,
+      "step": 1885
+    },
+    {
+      "epoch": 0.2782736997417927,
+      "grad_norm": 2.8877511024475098,
+      "learning_rate": 1.8125746901823064e-05,
+      "loss": 0.0532,
+      "step": 1886
+    },
+    {
+      "epoch": 0.2784212467724087,
+      "grad_norm": 1.40437650680542,
+      "learning_rate": 1.81227435293035e-05,
+      "loss": 0.0454,
+      "step": 1887
+    },
+    {
+      "epoch": 0.27856879380302474,
+      "grad_norm": 2.2449872493743896,
+      "learning_rate": 1.811973800159569e-05,
+      "loss": 0.057,
+      "step": 1888
+    },
+    {
+      "epoch": 0.2787163408336407,
+      "grad_norm": 3.3180947303771973,
+      "learning_rate": 1.811673031949708e-05,
+      "loss": 0.0645,
+      "step": 1889
+    },
+    {
+      "epoch": 0.27886388786425675,
+      "grad_norm": 3.3282129764556885,
+      "learning_rate": 1.8113720483805698e-05,
+      "loss": 0.0552,
+      "step": 1890
+    },
+    {
+      "epoch": 0.27901143489487273,
+      "grad_norm": 1.8338218927383423,
+      "learning_rate": 1.8110708495320132e-05,
+      "loss": 0.0447,
+      "step": 1891
+    },
+    {
+      "epoch": 0.27915898192548877,
+      "grad_norm": 2.270963430404663,
+      "learning_rate": 1.810769435483955e-05,
+      "loss": 0.0932,
+      "step": 1892
+    },
+    {
+      "epoch": 0.27930652895610475,
+      "grad_norm": 3.8612663745880127,
+      "learning_rate": 1.810467806316368e-05,
+      "loss": 0.087,
+      "step": 1893
+    },
+    {
+      "epoch": 0.2794540759867208,
+      "grad_norm": 1.1670207977294922,
+      "learning_rate": 1.8101659621092832e-05,
+      "loss": 0.0496,
+      "step": 1894
+    },
+    {
+      "epoch": 0.27960162301733676,
+      "grad_norm": 1.885435700416565,
+      "learning_rate": 1.809863902942788e-05,
+      "loss": 0.0275,
+      "step": 1895
+    },
+    {
+      "epoch": 0.2797491700479528,
+      "grad_norm": 4.63778018951416,
+      "learning_rate": 1.8095616288970268e-05,
+      "loss": 0.0579,
+      "step": 1896
+    },
+    {
+      "epoch": 0.2798967170785688,
+      "grad_norm": 2.977574110031128,
+      "learning_rate": 1.8092591400522018e-05,
+      "loss": 0.0993,
+      "step": 1897
+    },
+    {
+      "epoch": 0.2800442641091848,
+      "grad_norm": 3.402623414993286,
+      "learning_rate": 1.8089564364885716e-05,
+      "loss": 0.0883,
+      "step": 1898
+    },
+    {
+      "epoch": 0.2801918111398008,
+      "grad_norm": 2.1657140254974365,
+      "learning_rate": 1.8086535182864513e-05,
+      "loss": 0.0911,
+      "step": 1899
+    },
+    {
+      "epoch": 0.28033935817041683,
+      "grad_norm": 2.973764181137085,
+      "learning_rate": 1.808350385526214e-05,
+      "loss": 0.1452,
+      "step": 1900
+    },
+    {
+      "epoch": 0.28033935817041683,
+      "eval_accuracy": 0.975397973950796,
+      "eval_f1": 0.9573934837092731,
+      "eval_loss": 0.0686851218342781,
+      "eval_precision": 0.9896373056994818,
+      "eval_recall": 0.9271844660194175,
+      "eval_runtime": 50.2754,
+      "eval_samples_per_second": 5.788,
+      "eval_steps_per_second": 0.199,
+      "step": 1900
     }
   ],
   "logging_steps": 1,
@@ -13718,7 +14478,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.544433821815931e+17,
+  "total_flos": 5.853142560863683e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null