Training in progress, step 700, checkpoint

last-checkpoint/optimizer_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdf5df774f521d954ee3e726d41ddb9daedd6d311faf9fcda593a13068d34a8e
+oid sha256:c7593ff48c88558ba36c548d26441da5f290ef98c23ce57e6796ac17a59eed1f
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd10cb51f5c667371250ddfc6c47bc9a61bf774150f87602c3c87fcbad63ad83
+oid sha256:2470c368cf06cbd81fec456b31d73c7acff78015ce59e628a4f867e5ec668c81
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48c19f630a9a5319e3d65078ce63fdb7dce42469a0548a8f8cbd5b913312443d
+oid sha256:62481a97a5c3fd786c7f1005b809e1e6e209c98d09a4c9f064093ec2ba198fee
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d02459ecb3ae6434ae5af7fbb47c2b17523d7a46389de9c32ca874536855e330
+oid sha256:1ceca27870983d9c89b8924db632fae92db84f13afa60f6e12f78d0cad43e4fc
 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:afc5fa67d8e5b83405d300b071a2e6ebe018b95a8e2a9a80de6080a2fff3a652
+oid sha256:f202acda5708effbaf409face7d3eedb22a40bf3bd7a92b81ce2418678c009ac
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e8ab05ad8eb2b256a4e4c2668966a9d6f6ba743e1c0d09c09f0d078db12f255
+oid sha256:1a48e13a828146c30be2d94090263941c8b6ddf5e87ef3462d06990806cd646c
 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:d6b4b4569fd538a14adbb3ff73357b58d937af7153c03281a674632445571715
+oid sha256:32158f1e838f18d2b2b96669893956b11d55c92c5cb7d6017f4cb46d81bbffdc
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a3b67a46525a89874ad28e21e79e69601fc48088c4ec5fe3a52d2ba66d99939
+oid sha256:77896bcd44c50795a8f115b0452d7f4a81ef0830014c75aa33f1885ded87b70c
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42792689a44458439ddf6e3814b85a523f5172e1f1d8d6256583f62855d76adf
+oid sha256:08983deab7482471b5356607644ee174930496b6a776490bee223acb95498984
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1461d142a8aef76c97f9d8ef564c77b1bf43c714ec58550b4de56dd32819a506
+oid sha256:ed8df81291f89e35c529228d7e093777460f847763cd5d64284c30e116475129
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a7ba4a5ad17e05963c139c4fac76a323d7246eaf407228b6c64d8b7736268d2
+oid sha256:c17da80f8f391ac4510c9584eaef69df8cf205687f953f17c05cabecda56ada4
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5160827ac6e1d0c23e314e2363b801d8d05385ccd2be54654dbc5b66d06ce646
+oid sha256:28efcdf8fbac18da339ee09d94173f73a865d1fefbacbc717b00191ddf2de9e2
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de2f65c92a6a69efe83c1ce29f463f69b58d1cb2c5c6ece683245f08082e8130
+oid sha256:f44073483ca77a27e94fca043ee686f0075e2ffb61e22650917d82ace5ef1307
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4592422502870264,
+  "epoch": 0.5357826253348641,
   "eval_steps": 20,
-  "global_step": 600,
+  "global_step": 700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4579,6 +4579,766 @@
       "eval_samples_per_second": 6.909,
       "eval_steps_per_second": 0.23,
       "step": 600
+    },
+    {
+      "epoch": 0.46000765403750477,
+      "grad_norm": 5.956824779510498,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 0.2853,
+      "step": 601
+    },
+    {
+      "epoch": 0.46077305778798316,
+      "grad_norm": 5.746252536773682,
+      "learning_rate": 1.3064730569932467e-05,
+      "loss": 0.2419,
+      "step": 602
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 6.898614883422852,
+      "learning_rate": 1.3039269287443442e-05,
+      "loss": 0.2599,
+      "step": 603
+    },
+    {
+      "epoch": 0.4623038652889399,
+      "grad_norm": 5.138125896453857,
+      "learning_rate": 1.301378627829608e-05,
+      "loss": 0.346,
+      "step": 604
+    },
+    {
+      "epoch": 0.4630692690394183,
+      "grad_norm": 5.577975273132324,
+      "learning_rate": 1.2988281724659375e-05,
+      "loss": 0.4313,
+      "step": 605
+    },
+    {
+      "epoch": 0.46383467278989665,
+      "grad_norm": 6.451081275939941,
+      "learning_rate": 1.2962755808856341e-05,
+      "loss": 0.3364,
+      "step": 606
+    },
+    {
+      "epoch": 0.46460007654037505,
+      "grad_norm": 5.723383903503418,
+      "learning_rate": 1.2937208713362694e-05,
+      "loss": 0.285,
+      "step": 607
+    },
+    {
+      "epoch": 0.46536548029085345,
+      "grad_norm": 6.299584865570068,
+      "learning_rate": 1.2911640620805561e-05,
+      "loss": 0.3708,
+      "step": 608
+    },
+    {
+      "epoch": 0.4661308840413318,
+      "grad_norm": 5.189462661743164,
+      "learning_rate": 1.2886051713962172e-05,
+      "loss": 0.3041,
+      "step": 609
+    },
+    {
+      "epoch": 0.4668962877918102,
+      "grad_norm": 5.592836856842041,
+      "learning_rate": 1.2860442175758543e-05,
+      "loss": 0.3218,
+      "step": 610
+    },
+    {
+      "epoch": 0.46766169154228854,
+      "grad_norm": 6.396859645843506,
+      "learning_rate": 1.283481218926818e-05,
+      "loss": 0.3155,
+      "step": 611
+    },
+    {
+      "epoch": 0.46842709529276694,
+      "grad_norm": 6.612271785736084,
+      "learning_rate": 1.280916193771077e-05,
+      "loss": 0.4262,
+      "step": 612
+    },
+    {
+      "epoch": 0.46919249904324534,
+      "grad_norm": 6.376734256744385,
+      "learning_rate": 1.2783491604450869e-05,
+      "loss": 0.2233,
+      "step": 613
+    },
+    {
+      "epoch": 0.4699579027937237,
+      "grad_norm": 5.077390193939209,
+      "learning_rate": 1.2757801372996577e-05,
+      "loss": 0.2412,
+      "step": 614
+    },
+    {
+      "epoch": 0.4707233065442021,
+      "grad_norm": 6.0435872077941895,
+      "learning_rate": 1.2732091426998258e-05,
+      "loss": 0.4129,
+      "step": 615
+    },
+    {
+      "epoch": 0.4714887102946804,
+      "grad_norm": 6.408792495727539,
+      "learning_rate": 1.270636195024719e-05,
+      "loss": 0.3446,
+      "step": 616
+    },
+    {
+      "epoch": 0.4722541140451588,
+      "grad_norm": 5.99134635925293,
+      "learning_rate": 1.2680613126674285e-05,
+      "loss": 0.2502,
+      "step": 617
+    },
+    {
+      "epoch": 0.4730195177956372,
+      "grad_norm": 4.678402423858643,
+      "learning_rate": 1.2654845140348746e-05,
+      "loss": 0.3089,
+      "step": 618
+    },
+    {
+      "epoch": 0.47378492154611557,
+      "grad_norm": 6.420397758483887,
+      "learning_rate": 1.2629058175476774e-05,
+      "loss": 0.2951,
+      "step": 619
+    },
+    {
+      "epoch": 0.47455032529659397,
+      "grad_norm": 7.072854518890381,
+      "learning_rate": 1.2603252416400232e-05,
+      "loss": 0.3877,
+      "step": 620
+    },
+    {
+      "epoch": 0.47455032529659397,
+      "eval_accuracy": 0.8700361010830325,
+      "eval_f1": 0.817258883248731,
+      "eval_loss": 0.33253204822540283,
+      "eval_precision": 0.8341968911917098,
+      "eval_recall": 0.8009950248756219,
+      "eval_runtime": 43.8544,
+      "eval_samples_per_second": 6.864,
+      "eval_steps_per_second": 0.228,
+      "step": 620
+    },
+    {
+      "epoch": 0.4753157290470723,
+      "grad_norm": 7.795954704284668,
+      "learning_rate": 1.2577428047595343e-05,
+      "loss": 0.4187,
+      "step": 621
+    },
+    {
+      "epoch": 0.4760811327975507,
+      "grad_norm": 5.663315773010254,
+      "learning_rate": 1.255158525367136e-05,
+      "loss": 0.3266,
+      "step": 622
+    },
+    {
+      "epoch": 0.4768465365480291,
+      "grad_norm": 7.847259998321533,
+      "learning_rate": 1.2525724219369253e-05,
+      "loss": 0.4043,
+      "step": 623
+    },
+    {
+      "epoch": 0.47761194029850745,
+      "grad_norm": 5.627171993255615,
+      "learning_rate": 1.2499845129560386e-05,
+      "loss": 0.2725,
+      "step": 624
+    },
+    {
+      "epoch": 0.47837734404898585,
+      "grad_norm": 7.48345422744751,
+      "learning_rate": 1.2473948169245196e-05,
+      "loss": 0.3373,
+      "step": 625
+    },
+    {
+      "epoch": 0.4791427477994642,
+      "grad_norm": 5.870919704437256,
+      "learning_rate": 1.2448033523551866e-05,
+      "loss": 0.2746,
+      "step": 626
+    },
+    {
+      "epoch": 0.4799081515499426,
+      "grad_norm": 5.2100396156311035,
+      "learning_rate": 1.2422101377735007e-05,
+      "loss": 0.3173,
+      "step": 627
+    },
+    {
+      "epoch": 0.480673555300421,
+      "grad_norm": 6.408041954040527,
+      "learning_rate": 1.2396151917174335e-05,
+      "loss": 0.3533,
+      "step": 628
+    },
+    {
+      "epoch": 0.48143895905089934,
+      "grad_norm": 6.015228748321533,
+      "learning_rate": 1.2370185327373341e-05,
+      "loss": 0.3696,
+      "step": 629
+    },
+    {
+      "epoch": 0.48220436280137774,
+      "grad_norm": 7.102441310882568,
+      "learning_rate": 1.234420179395797e-05,
+      "loss": 0.4167,
+      "step": 630
+    },
+    {
+      "epoch": 0.4829697665518561,
+      "grad_norm": 6.134483814239502,
+      "learning_rate": 1.2318201502675285e-05,
+      "loss": 0.3047,
+      "step": 631
+    },
+    {
+      "epoch": 0.4837351703023345,
+      "grad_norm": 5.107813358306885,
+      "learning_rate": 1.2292184639392146e-05,
+      "loss": 0.21,
+      "step": 632
+    },
+    {
+      "epoch": 0.4845005740528129,
+      "grad_norm": 6.076941013336182,
+      "learning_rate": 1.2266151390093887e-05,
+      "loss": 0.3665,
+      "step": 633
+    },
+    {
+      "epoch": 0.4852659778032912,
+      "grad_norm": 4.5892863273620605,
+      "learning_rate": 1.224010194088297e-05,
+      "loss": 0.3551,
+      "step": 634
+    },
+    {
+      "epoch": 0.4860313815537696,
+      "grad_norm": 3.7130930423736572,
+      "learning_rate": 1.2214036477977675e-05,
+      "loss": 0.2009,
+      "step": 635
+    },
+    {
+      "epoch": 0.48679678530424797,
+      "grad_norm": 6.9683918952941895,
+      "learning_rate": 1.2187955187710752e-05,
+      "loss": 0.4284,
+      "step": 636
+    },
+    {
+      "epoch": 0.48756218905472637,
+      "grad_norm": 9.758392333984375,
+      "learning_rate": 1.2161858256528092e-05,
+      "loss": 0.3854,
+      "step": 637
+    },
+    {
+      "epoch": 0.48832759280520477,
+      "grad_norm": 4.792107105255127,
+      "learning_rate": 1.2135745870987406e-05,
+      "loss": 0.2987,
+      "step": 638
+    },
+    {
+      "epoch": 0.4890929965556831,
+      "grad_norm": 4.2573347091674805,
+      "learning_rate": 1.2109618217756876e-05,
+      "loss": 0.2276,
+      "step": 639
+    },
+    {
+      "epoch": 0.4898584003061615,
+      "grad_norm": 5.893449306488037,
+      "learning_rate": 1.2083475483613828e-05,
+      "loss": 0.2342,
+      "step": 640
+    },
+    {
+      "epoch": 0.4898584003061615,
+      "eval_accuracy": 0.8736462093862816,
+      "eval_f1": 0.8157894736842105,
+      "eval_loss": 0.3177836537361145,
+      "eval_precision": 0.8659217877094972,
+      "eval_recall": 0.7711442786069652,
+      "eval_runtime": 44.0099,
+      "eval_samples_per_second": 6.839,
+      "eval_steps_per_second": 0.227,
+      "step": 640
+    },
+    {
+      "epoch": 0.49062380405663986,
+      "grad_norm": 3.7821764945983887,
+      "learning_rate": 1.2057317855443395e-05,
+      "loss": 0.2527,
+      "step": 641
+    },
+    {
+      "epoch": 0.49138920780711826,
+      "grad_norm": 6.740549087524414,
+      "learning_rate": 1.2031145520237194e-05,
+      "loss": 0.2847,
+      "step": 642
+    },
+    {
+      "epoch": 0.49215461155759666,
+      "grad_norm": 5.346322059631348,
+      "learning_rate": 1.2004958665091964e-05,
+      "loss": 0.2837,
+      "step": 643
+    },
+    {
+      "epoch": 0.492920015308075,
+      "grad_norm": 4.715932369232178,
+      "learning_rate": 1.1978757477208242e-05,
+      "loss": 0.2696,
+      "step": 644
+    },
+    {
+      "epoch": 0.4936854190585534,
+      "grad_norm": 5.284407615661621,
+      "learning_rate": 1.1952542143889034e-05,
+      "loss": 0.307,
+      "step": 645
+    },
+    {
+      "epoch": 0.49445082280903174,
+      "grad_norm": 5.576004505157471,
+      "learning_rate": 1.1926312852538456e-05,
+      "loss": 0.3274,
+      "step": 646
+    },
+    {
+      "epoch": 0.49521622655951014,
+      "grad_norm": 4.6278395652771,
+      "learning_rate": 1.1900069790660411e-05,
+      "loss": 0.2723,
+      "step": 647
+    },
+    {
+      "epoch": 0.49598163030998854,
+      "grad_norm": 6.354363441467285,
+      "learning_rate": 1.187381314585725e-05,
+      "loss": 0.2892,
+      "step": 648
+    },
+    {
+      "epoch": 0.4967470340604669,
+      "grad_norm": 5.980183124542236,
+      "learning_rate": 1.1847543105828404e-05,
+      "loss": 0.3154,
+      "step": 649
+    },
+    {
+      "epoch": 0.4975124378109453,
+      "grad_norm": 6.652758598327637,
+      "learning_rate": 1.1821259858369082e-05,
+      "loss": 0.31,
+      "step": 650
+    },
+    {
+      "epoch": 0.49827784156142363,
+      "grad_norm": 4.981330394744873,
+      "learning_rate": 1.1794963591368893e-05,
+      "loss": 0.1999,
+      "step": 651
+    },
+    {
+      "epoch": 0.49904324531190203,
+      "grad_norm": 7.559998035430908,
+      "learning_rate": 1.1768654492810525e-05,
+      "loss": 0.2701,
+      "step": 652
+    },
+    {
+      "epoch": 0.49980864906238043,
+      "grad_norm": 4.401430130004883,
+      "learning_rate": 1.1742332750768402e-05,
+      "loss": 0.2127,
+      "step": 653
+    },
+    {
+      "epoch": 0.5005740528128588,
+      "grad_norm": 8.975022315979004,
+      "learning_rate": 1.1715998553407315e-05,
+      "loss": 0.4186,
+      "step": 654
+    },
+    {
+      "epoch": 0.5013394565633371,
+      "grad_norm": 8.256175994873047,
+      "learning_rate": 1.1689652088981102e-05,
+      "loss": 0.3824,
+      "step": 655
+    },
+    {
+      "epoch": 0.5021048603138155,
+      "grad_norm": 8.785820007324219,
+      "learning_rate": 1.1663293545831302e-05,
+      "loss": 0.4255,
+      "step": 656
+    },
+    {
+      "epoch": 0.5028702640642939,
+      "grad_norm": 4.359196662902832,
+      "learning_rate": 1.1636923112385785e-05,
+      "loss": 0.2107,
+      "step": 657
+    },
+    {
+      "epoch": 0.5036356678147723,
+      "grad_norm": 9.45128059387207,
+      "learning_rate": 1.161054097715743e-05,
+      "loss": 0.3538,
+      "step": 658
+    },
+    {
+      "epoch": 0.5044010715652507,
+      "grad_norm": 6.700775146484375,
+      "learning_rate": 1.1584147328742767e-05,
+      "loss": 0.3089,
+      "step": 659
+    },
+    {
+      "epoch": 0.505166475315729,
+      "grad_norm": 5.239867687225342,
+      "learning_rate": 1.155774235582063e-05,
+      "loss": 0.2483,
+      "step": 660
+    },
+    {
+      "epoch": 0.505166475315729,
+      "eval_accuracy": 0.871841155234657,
+      "eval_f1": 0.8054794520547945,
+      "eval_loss": 0.3145829141139984,
+      "eval_precision": 0.8963414634146342,
+      "eval_recall": 0.7313432835820896,
+      "eval_runtime": 45.0474,
+      "eval_samples_per_second": 6.682,
+      "eval_steps_per_second": 0.222,
+      "step": 660
+    },
+    {
+      "epoch": 0.5059318790662074,
+      "grad_norm": 7.80463171005249,
+      "learning_rate": 1.1531326247150802e-05,
+      "loss": 0.3278,
+      "step": 661
+    },
+    {
+      "epoch": 0.5066972828166858,
+      "grad_norm": 5.086753845214844,
+      "learning_rate": 1.1504899191572682e-05,
+      "loss": 0.2196,
+      "step": 662
+    },
+    {
+      "epoch": 0.5074626865671642,
+      "grad_norm": 7.081567287445068,
+      "learning_rate": 1.1478461378003913e-05,
+      "loss": 0.3013,
+      "step": 663
+    },
+    {
+      "epoch": 0.5082280903176426,
+      "grad_norm": 8.720135688781738,
+      "learning_rate": 1.145201299543905e-05,
+      "loss": 0.4044,
+      "step": 664
+    },
+    {
+      "epoch": 0.5089934940681209,
+      "grad_norm": 5.741237640380859,
+      "learning_rate": 1.1425554232948206e-05,
+      "loss": 0.2103,
+      "step": 665
+    },
+    {
+      "epoch": 0.5097588978185993,
+      "grad_norm": 10.087435722351074,
+      "learning_rate": 1.1399085279675688e-05,
+      "loss": 0.3157,
+      "step": 666
+    },
+    {
+      "epoch": 0.5105243015690777,
+      "grad_norm": 8.691031455993652,
+      "learning_rate": 1.1372606324838651e-05,
+      "loss": 0.2895,
+      "step": 667
+    },
+    {
+      "epoch": 0.5112897053195561,
+      "grad_norm": 7.523034572601318,
+      "learning_rate": 1.1346117557725757e-05,
+      "loss": 0.2872,
+      "step": 668
+    },
+    {
+      "epoch": 0.5120551090700345,
+      "grad_norm": 5.898047924041748,
+      "learning_rate": 1.1319619167695814e-05,
+      "loss": 0.3007,
+      "step": 669
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 3.7639052867889404,
+      "learning_rate": 1.1293111344176406e-05,
+      "loss": 0.2113,
+      "step": 670
+    },
+    {
+      "epoch": 0.5135859165709912,
+      "grad_norm": 7.386530876159668,
+      "learning_rate": 1.126659427666257e-05,
+      "loss": 0.3495,
+      "step": 671
+    },
+    {
+      "epoch": 0.5143513203214696,
+      "grad_norm": 5.551990985870361,
+      "learning_rate": 1.1240068154715416e-05,
+      "loss": 0.3122,
+      "step": 672
+    },
+    {
+      "epoch": 0.515116724071948,
+      "grad_norm": 7.6228156089782715,
+      "learning_rate": 1.121353316796078e-05,
+      "loss": 0.3292,
+      "step": 673
+    },
+    {
+      "epoch": 0.5158821278224264,
+      "grad_norm": 5.472020149230957,
+      "learning_rate": 1.1186989506087876e-05,
+      "loss": 0.3501,
+      "step": 674
+    },
+    {
+      "epoch": 0.5166475315729047,
+      "grad_norm": 5.9330525398254395,
+      "learning_rate": 1.116043735884793e-05,
+      "loss": 0.3392,
+      "step": 675
+    },
+    {
+      "epoch": 0.5174129353233831,
+      "grad_norm": 6.453945636749268,
+      "learning_rate": 1.1133876916052822e-05,
+      "loss": 0.2199,
+      "step": 676
+    },
+    {
+      "epoch": 0.5181783390738615,
+      "grad_norm": 6.126132488250732,
+      "learning_rate": 1.1107308367573744e-05,
+      "loss": 0.2892,
+      "step": 677
+    },
+    {
+      "epoch": 0.5189437428243399,
+      "grad_norm": 3.9714488983154297,
+      "learning_rate": 1.1080731903339825e-05,
+      "loss": 0.2664,
+      "step": 678
+    },
+    {
+      "epoch": 0.5197091465748183,
+      "grad_norm": 9.137075424194336,
+      "learning_rate": 1.1054147713336782e-05,
+      "loss": 0.3458,
+      "step": 679
+    },
+    {
+      "epoch": 0.5204745503252965,
+      "grad_norm": 5.681141376495361,
+      "learning_rate": 1.1027555987605562e-05,
+      "loss": 0.2841,
+      "step": 680
+    },
+    {
+      "epoch": 0.5204745503252965,
+      "eval_accuracy": 0.871841155234657,
+      "eval_f1": 0.8011204481792717,
+      "eval_loss": 0.3226017951965332,
+      "eval_precision": 0.9166666666666666,
+      "eval_recall": 0.7114427860696517,
+      "eval_runtime": 44.0834,
+      "eval_samples_per_second": 6.828,
+      "eval_steps_per_second": 0.227,
+      "step": 680
+    },
+    {
+      "epoch": 0.521239954075775,
+      "grad_norm": 5.028656005859375,
+      "learning_rate": 1.1000956916240985e-05,
+      "loss": 0.3274,
+      "step": 681
+    },
+    {
+      "epoch": 0.5220053578262533,
+      "grad_norm": 4.5937700271606445,
+      "learning_rate": 1.0974350689390376e-05,
+      "loss": 0.2103,
+      "step": 682
+    },
+    {
+      "epoch": 0.5227707615767317,
+      "grad_norm": 4.783949375152588,
+      "learning_rate": 1.094773749725222e-05,
+      "loss": 0.2575,
+      "step": 683
+    },
+    {
+      "epoch": 0.5235361653272101,
+      "grad_norm": 7.1982502937316895,
+      "learning_rate": 1.0921117530074785e-05,
+      "loss": 0.3264,
+      "step": 684
+    },
+    {
+      "epoch": 0.5243015690776884,
+      "grad_norm": 5.304211139678955,
+      "learning_rate": 1.0894490978154777e-05,
+      "loss": 0.3124,
+      "step": 685
+    },
+    {
+      "epoch": 0.5250669728281668,
+      "grad_norm": 7.728262424468994,
+      "learning_rate": 1.0867858031835975e-05,
+      "loss": 0.3697,
+      "step": 686
+    },
+    {
+      "epoch": 0.5258323765786452,
+      "grad_norm": 5.3696465492248535,
+      "learning_rate": 1.084121888150787e-05,
+      "loss": 0.3055,
+      "step": 687
+    },
+    {
+      "epoch": 0.5265977803291236,
+      "grad_norm": 7.408420562744141,
+      "learning_rate": 1.0814573717604295e-05,
+      "loss": 0.3524,
+      "step": 688
+    },
+    {
+      "epoch": 0.527363184079602,
+      "grad_norm": 6.884669303894043,
+      "learning_rate": 1.0787922730602083e-05,
+      "loss": 0.2839,
+      "step": 689
+    },
+    {
+      "epoch": 0.5281285878300803,
+      "grad_norm": 8.420857429504395,
+      "learning_rate": 1.0761266111019685e-05,
+      "loss": 0.4047,
+      "step": 690
+    },
+    {
+      "epoch": 0.5288939915805587,
+      "grad_norm": 4.702800750732422,
+      "learning_rate": 1.0734604049415822e-05,
+      "loss": 0.2042,
+      "step": 691
+    },
+    {
+      "epoch": 0.5296593953310371,
+      "grad_norm": 7.388383865356445,
+      "learning_rate": 1.070793673638812e-05,
+      "loss": 0.2754,
+      "step": 692
+    },
+    {
+      "epoch": 0.5304247990815155,
+      "grad_norm": 7.465807914733887,
+      "learning_rate": 1.0681264362571744e-05,
+      "loss": 0.2907,
+      "step": 693
+    },
+    {
+      "epoch": 0.5311902028319939,
+      "grad_norm": 5.684911251068115,
+      "learning_rate": 1.0654587118638027e-05,
+      "loss": 0.2513,
+      "step": 694
+    },
+    {
+      "epoch": 0.5319556065824722,
+      "grad_norm": 5.584875583648682,
+      "learning_rate": 1.0627905195293135e-05,
+      "loss": 0.2658,
+      "step": 695
+    },
+    {
+      "epoch": 0.5327210103329506,
+      "grad_norm": 6.920920372009277,
+      "learning_rate": 1.0601218783276673e-05,
+      "loss": 0.3378,
+      "step": 696
+    },
+    {
+      "epoch": 0.533486414083429,
+      "grad_norm": 6.030942916870117,
+      "learning_rate": 1.0574528073360333e-05,
+      "loss": 0.2732,
+      "step": 697
+    },
+    {
+      "epoch": 0.5342518178339074,
+      "grad_norm": 8.450331687927246,
+      "learning_rate": 1.054783325634654e-05,
+      "loss": 0.3302,
+      "step": 698
+    },
+    {
+      "epoch": 0.5350172215843858,
+      "grad_norm": 8.008537292480469,
+      "learning_rate": 1.0521134523067076e-05,
+      "loss": 0.2018,
+      "step": 699
+    },
+    {
+      "epoch": 0.5357826253348641,
+      "grad_norm": 5.137029647827148,
+      "learning_rate": 1.0494432064381707e-05,
+      "loss": 0.3065,
+      "step": 700
+    },
+    {
+      "epoch": 0.5357826253348641,
+      "eval_accuracy": 0.8844765342960289,
+      "eval_f1": 0.8212290502793296,
+      "eval_loss": 0.31221428513526917,
+      "eval_precision": 0.9363057324840764,
+      "eval_recall": 0.7313432835820896,
+      "eval_runtime": 43.6609,
+      "eval_samples_per_second": 6.894,
+      "eval_steps_per_second": 0.229,
+      "step": 700
     }
   ],
   "logging_steps": 1,
@@ -4598,7 +5358,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.204121809086054e+16,
+  "total_flos": 1.0741809779467878e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null