Training in progress, step 1400, checkpoint

last-checkpoint/optimizer_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7443417abf7271ff4c80b220fbc57de0f73c458a860abfcc083a82609e540dd0
+oid sha256:9ea9bc38b4c938ba56a2503b506e13ddc94bfb9799b21717156bd88e23ff709c
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69cfde4dc872d3ae3cb3ee2d8297c3ea8b0bcb261257d14e53316380a9062749
+oid sha256:74341f8be656b0903a52a822b1b6232ded60fe7dbc28ec68c86f405fd79dfafb
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d62ea877e2870369b0069fbde2d96de0e8822624d36f781e87f148150e0000c1
+oid sha256:02672cba890c16e3e5ae03111824e128946d0051127e3085567dc78d6ae9f509
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a2998992a8e359dfee4a90c8c9c92c57d079f5b4319ce32495520a3148fa4f6
+oid sha256:5e895868a2cf6a48f8ee449e0822b9ef22ffb466f178d483eecafa9770a32aeb
 size 13990904

last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0951bf15d5e8a29d5e74ffbe4a034e4691b794e407adeac56e401ef478163e27
+oid sha256:8406dc8939b1905e8edc2026609b86d12db4104628362466b09c5a4166d78cf6
 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:d533ad3bc84dd7392b5913079bdffdeb8b8258e9e466547392ce421d21189513
+oid sha256:2a0e9558c7ffa27a98d2a2853cc987de9707d36a21937bddefc79b4ac186a325
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f189a695b86ad194e7b477bf7e2e7c8759a2f9768bbcd21c29ff0028e2e53e6
+oid sha256:349884007ff6bcb9d2bd62b3fe04decf645da7a5b1436f4775991797cd4f7281
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fe4674f05ba91d18f63f589b78b3fbd0ed8caf3cc096927e492ae2fffdb7e00
+oid sha256:e751060ffc34885a00d80af6c52fa55b2f2c3ae97ba11b5750e5f444dc723872
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b890a86b0156346d7c2fe9f35e0ae906894a26f6209f5003c6c1e8354016e6f
+oid sha256:3cee7394517f454875f2de6b91f4b4b56f00fc267c771b5ed6ea059587e475c4
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdd665e4f623b31099dd94cd36dc08cdd2a1c0965a467bbcb6a35224bac7b122
+oid sha256:ec4c7bfad34548bde0313c286246a1ece1b2a3ad66076441dfa8ff3fdaf273c4
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:706ec2ed2de5c579c51fab02019448d4fa1afa0c075122383ca2ea73fe39a27a
+oid sha256:a95da00d618f49575faf13a6017ef2211d7d5936741475dfb2f0b4f20be74566
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79b3602e6219944ed2000a3db6a979100e95cb76c65601bf2c6614256ad7dbd3
+oid sha256:6dabde8dab81308d9d5f138f73f43c21218a46021091d5ea0f800395b3668859
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33815ccded423315ebc724ecd6f9a8be87b2fa83128d9c07eb2ad960e334ac09
+oid sha256:ea930d27c2807b3eeaecd23af448a0466ec22c57a1082bd3ada900cb95244f7b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6162597771983882,
+  "epoch": 0.6636643754444181,
   "eval_steps": 20,
-  "global_step": 1300,
+  "global_step": 1400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -9899,6 +9899,766 @@
       "eval_samples_per_second": 5.435,
       "eval_steps_per_second": 0.18,
       "step": 1300
+    },
+    {
+      "epoch": 0.6167338231808486,
+      "grad_norm": 6.278774261474609,
+      "learning_rate": 7.68728013128775e-06,
+      "loss": 0.1788,
+      "step": 1301
+    },
+    {
+      "epoch": 0.6172078691633088,
+      "grad_norm": 3.930607557296753,
+      "learning_rate": 7.671179927626651e-06,
+      "loss": 0.2176,
+      "step": 1302
+    },
+    {
+      "epoch": 0.6176819151457691,
+      "grad_norm": 3.799132823944092,
+      "learning_rate": 7.655086104295904e-06,
+      "loss": 0.1051,
+      "step": 1303
+    },
+    {
+      "epoch": 0.6181559611282295,
+      "grad_norm": 4.671762466430664,
+      "learning_rate": 7.638998705388188e-06,
+      "loss": 0.1648,
+      "step": 1304
+    },
+    {
+      "epoch": 0.6186300071106897,
+      "grad_norm": 6.8837504386901855,
+      "learning_rate": 7.622917774978579e-06,
+      "loss": 0.1712,
+      "step": 1305
+    },
+    {
+      "epoch": 0.6191040530931501,
+      "grad_norm": 3.0409445762634277,
+      "learning_rate": 7.606843357124426e-06,
+      "loss": 0.1149,
+      "step": 1306
+    },
+    {
+      "epoch": 0.6195780990756103,
+      "grad_norm": 3.255094289779663,
+      "learning_rate": 7.5907754958652365e-06,
+      "loss": 0.1327,
+      "step": 1307
+    },
+    {
+      "epoch": 0.6200521450580706,
+      "grad_norm": 5.722508430480957,
+      "learning_rate": 7.574714235222571e-06,
+      "loss": 0.1593,
+      "step": 1308
+    },
+    {
+      "epoch": 0.620526191040531,
+      "grad_norm": 17.10514259338379,
+      "learning_rate": 7.558659619199884e-06,
+      "loss": 0.3056,
+      "step": 1309
+    },
+    {
+      "epoch": 0.6210002370229912,
+      "grad_norm": 7.020135402679443,
+      "learning_rate": 7.542611691782433e-06,
+      "loss": 0.1793,
+      "step": 1310
+    },
+    {
+      "epoch": 0.6214742830054515,
+      "grad_norm": 4.9687066078186035,
+      "learning_rate": 7.526570496937157e-06,
+      "loss": 0.1326,
+      "step": 1311
+    },
+    {
+      "epoch": 0.6219483289879119,
+      "grad_norm": 5.2314133644104,
+      "learning_rate": 7.5105360786125405e-06,
+      "loss": 0.1843,
+      "step": 1312
+    },
+    {
+      "epoch": 0.6224223749703721,
+      "grad_norm": 2.8971641063690186,
+      "learning_rate": 7.494508480738508e-06,
+      "loss": 0.1332,
+      "step": 1313
+    },
+    {
+      "epoch": 0.6228964209528324,
+      "grad_norm": 3.5975356101989746,
+      "learning_rate": 7.4784877472262994e-06,
+      "loss": 0.1212,
+      "step": 1314
+    },
+    {
+      "epoch": 0.6233704669352927,
+      "grad_norm": 4.035305976867676,
+      "learning_rate": 7.462473921968338e-06,
+      "loss": 0.1722,
+      "step": 1315
+    },
+    {
+      "epoch": 0.623844512917753,
+      "grad_norm": 4.344238758087158,
+      "learning_rate": 7.446467048838131e-06,
+      "loss": 0.1702,
+      "step": 1316
+    },
+    {
+      "epoch": 0.6243185589002134,
+      "grad_norm": 4.068875789642334,
+      "learning_rate": 7.430467171690134e-06,
+      "loss": 0.1253,
+      "step": 1317
+    },
+    {
+      "epoch": 0.6247926048826736,
+      "grad_norm": 4.388603210449219,
+      "learning_rate": 7.4144743343596385e-06,
+      "loss": 0.1894,
+      "step": 1318
+    },
+    {
+      "epoch": 0.6252666508651339,
+      "grad_norm": 2.7790372371673584,
+      "learning_rate": 7.398488580662644e-06,
+      "loss": 0.0985,
+      "step": 1319
+    },
+    {
+      "epoch": 0.6257406968475943,
+      "grad_norm": 6.451686382293701,
+      "learning_rate": 7.382509954395749e-06,
+      "loss": 0.1588,
+      "step": 1320
+    },
+    {
+      "epoch": 0.6257406968475943,
+      "eval_accuracy": 0.9911433172302737,
+      "eval_f1": 0.9026548672566371,
+      "eval_loss": 0.01939067617058754,
+      "eval_precision": 0.8360655737704918,
+      "eval_recall": 0.9807692307692307,
+      "eval_runtime": 49.8529,
+      "eval_samples_per_second": 5.436,
+      "eval_steps_per_second": 0.181,
+      "step": 1320
+    },
+    {
+      "epoch": 0.6262147428300545,
+      "grad_norm": 5.8468918800354,
+      "learning_rate": 7.366538499336018e-06,
+      "loss": 0.1876,
+      "step": 1321
+    },
+    {
+      "epoch": 0.6266887888125148,
+      "grad_norm": 5.291234970092773,
+      "learning_rate": 7.35057425924087e-06,
+      "loss": 0.2141,
+      "step": 1322
+    },
+    {
+      "epoch": 0.6271628347949751,
+      "grad_norm": 4.23124885559082,
+      "learning_rate": 7.334617277847963e-06,
+      "loss": 0.1612,
+      "step": 1323
+    },
+    {
+      "epoch": 0.6276368807774354,
+      "grad_norm": 3.941624879837036,
+      "learning_rate": 7.31866759887506e-06,
+      "loss": 0.1906,
+      "step": 1324
+    },
+    {
+      "epoch": 0.6281109267598957,
+      "grad_norm": 7.514248371124268,
+      "learning_rate": 7.302725266019924e-06,
+      "loss": 0.1179,
+      "step": 1325
+    },
+    {
+      "epoch": 0.628584972742356,
+      "grad_norm": 3.3683080673217773,
+      "learning_rate": 7.286790322960189e-06,
+      "loss": 0.1339,
+      "step": 1326
+    },
+    {
+      "epoch": 0.6290590187248163,
+      "grad_norm": 6.781601905822754,
+      "learning_rate": 7.270862813353241e-06,
+      "loss": 0.237,
+      "step": 1327
+    },
+    {
+      "epoch": 0.6295330647072767,
+      "grad_norm": 2.775303602218628,
+      "learning_rate": 7.254942780836103e-06,
+      "loss": 0.109,
+      "step": 1328
+    },
+    {
+      "epoch": 0.6300071106897369,
+      "grad_norm": 6.326327323913574,
+      "learning_rate": 7.239030269025311e-06,
+      "loss": 0.1799,
+      "step": 1329
+    },
+    {
+      "epoch": 0.6304811566721972,
+      "grad_norm": 3.2964067459106445,
+      "learning_rate": 7.2231253215168e-06,
+      "loss": 0.1008,
+      "step": 1330
+    },
+    {
+      "epoch": 0.6309552026546575,
+      "grad_norm": 4.055788040161133,
+      "learning_rate": 7.2072279818857745e-06,
+      "loss": 0.1524,
+      "step": 1331
+    },
+    {
+      "epoch": 0.6314292486371178,
+      "grad_norm": 8.913673400878906,
+      "learning_rate": 7.191338293686601e-06,
+      "loss": 0.1624,
+      "step": 1332
+    },
+    {
+      "epoch": 0.6319032946195781,
+      "grad_norm": 3.2821767330169678,
+      "learning_rate": 7.175456300452681e-06,
+      "loss": 0.1139,
+      "step": 1333
+    },
+    {
+      "epoch": 0.6323773406020384,
+      "grad_norm": 4.261881351470947,
+      "learning_rate": 7.159582045696334e-06,
+      "loss": 0.117,
+      "step": 1334
+    },
+    {
+      "epoch": 0.6328513865844987,
+      "grad_norm": 3.6744134426116943,
+      "learning_rate": 7.143715572908679e-06,
+      "loss": 0.1175,
+      "step": 1335
+    },
+    {
+      "epoch": 0.633325432566959,
+      "grad_norm": 6.114347457885742,
+      "learning_rate": 7.127856925559513e-06,
+      "loss": 0.2092,
+      "step": 1336
+    },
+    {
+      "epoch": 0.6337994785494193,
+      "grad_norm": 6.3057451248168945,
+      "learning_rate": 7.112006147097195e-06,
+      "loss": 0.1928,
+      "step": 1337
+    },
+    {
+      "epoch": 0.6342735245318796,
+      "grad_norm": 3.8282015323638916,
+      "learning_rate": 7.096163280948523e-06,
+      "loss": 0.1564,
+      "step": 1338
+    },
+    {
+      "epoch": 0.6347475705143399,
+      "grad_norm": 3.46825909614563,
+      "learning_rate": 7.080328370518623e-06,
+      "loss": 0.1227,
+      "step": 1339
+    },
+    {
+      "epoch": 0.6352216164968002,
+      "grad_norm": 2.634822368621826,
+      "learning_rate": 7.064501459190816e-06,
+      "loss": 0.1101,
+      "step": 1340
+    },
+    {
+      "epoch": 0.6352216164968002,
+      "eval_accuracy": 0.9935587761674718,
+      "eval_f1": 0.9259259259259259,
+      "eval_loss": 0.014886138029396534,
+      "eval_precision": 0.8928571428571429,
+      "eval_recall": 0.9615384615384616,
+      "eval_runtime": 50.0008,
+      "eval_samples_per_second": 5.42,
+      "eval_steps_per_second": 0.18,
+      "step": 1340
+    },
+    {
+      "epoch": 0.6356956624792605,
+      "grad_norm": 4.82327938079834,
+      "learning_rate": 7.048682590326519e-06,
+      "loss": 0.1271,
+      "step": 1341
+    },
+    {
+      "epoch": 0.6361697084617208,
+      "grad_norm": 7.885534763336182,
+      "learning_rate": 7.032871807265097e-06,
+      "loss": 0.2163,
+      "step": 1342
+    },
+    {
+      "epoch": 0.6366437544441811,
+      "grad_norm": 13.83066177368164,
+      "learning_rate": 7.017069153323785e-06,
+      "loss": 0.2698,
+      "step": 1343
+    },
+    {
+      "epoch": 0.6371178004266413,
+      "grad_norm": 3.2929160594940186,
+      "learning_rate": 7.0012746717975284e-06,
+      "loss": 0.1059,
+      "step": 1344
+    },
+    {
+      "epoch": 0.6375918464091017,
+      "grad_norm": 3.376429319381714,
+      "learning_rate": 6.9854884059588934e-06,
+      "loss": 0.0846,
+      "step": 1345
+    },
+    {
+      "epoch": 0.638065892391562,
+      "grad_norm": 4.017861843109131,
+      "learning_rate": 6.969710399057927e-06,
+      "loss": 0.1109,
+      "step": 1346
+    },
+    {
+      "epoch": 0.6385399383740222,
+      "grad_norm": 3.740814447402954,
+      "learning_rate": 6.953940694322059e-06,
+      "loss": 0.1207,
+      "step": 1347
+    },
+    {
+      "epoch": 0.6390139843564826,
+      "grad_norm": 8.038143157958984,
+      "learning_rate": 6.938179334955967e-06,
+      "loss": 0.119,
+      "step": 1348
+    },
+    {
+      "epoch": 0.6394880303389429,
+      "grad_norm": 3.9361705780029297,
+      "learning_rate": 6.9224263641414675e-06,
+      "loss": 0.1581,
+      "step": 1349
+    },
+    {
+      "epoch": 0.6399620763214032,
+      "grad_norm": 2.7756080627441406,
+      "learning_rate": 6.906681825037395e-06,
+      "loss": 0.0784,
+      "step": 1350
+    },
+    {
+      "epoch": 0.6404361223038635,
+      "grad_norm": 5.108663082122803,
+      "learning_rate": 6.8909457607794824e-06,
+      "loss": 0.1245,
+      "step": 1351
+    },
+    {
+      "epoch": 0.6409101682863237,
+      "grad_norm": 7.079373836517334,
+      "learning_rate": 6.8752182144802415e-06,
+      "loss": 0.1754,
+      "step": 1352
+    },
+    {
+      "epoch": 0.6413842142687841,
+      "grad_norm": 4.77249813079834,
+      "learning_rate": 6.859499229228852e-06,
+      "loss": 0.1782,
+      "step": 1353
+    },
+    {
+      "epoch": 0.6418582602512444,
+      "grad_norm": 4.985091209411621,
+      "learning_rate": 6.8437888480910355e-06,
+      "loss": 0.129,
+      "step": 1354
+    },
+    {
+      "epoch": 0.6423323062337046,
+      "grad_norm": 6.746637344360352,
+      "learning_rate": 6.8280871141089415e-06,
+      "loss": 0.2279,
+      "step": 1355
+    },
+    {
+      "epoch": 0.642806352216165,
+      "grad_norm": 4.10652494430542,
+      "learning_rate": 6.81239407030103e-06,
+      "loss": 0.143,
+      "step": 1356
+    },
+    {
+      "epoch": 0.6432803981986253,
+      "grad_norm": 4.236819267272949,
+      "learning_rate": 6.7967097596619495e-06,
+      "loss": 0.1236,
+      "step": 1357
+    },
+    {
+      "epoch": 0.6437544441810855,
+      "grad_norm": 8.469802856445312,
+      "learning_rate": 6.781034225162422e-06,
+      "loss": 0.1694,
+      "step": 1358
+    },
+    {
+      "epoch": 0.6442284901635459,
+      "grad_norm": 4.33465051651001,
+      "learning_rate": 6.765367509749123e-06,
+      "loss": 0.1511,
+      "step": 1359
+    },
+    {
+      "epoch": 0.6447025361460061,
+      "grad_norm": 5.169299602508545,
+      "learning_rate": 6.749709656344584e-06,
+      "loss": 0.1533,
+      "step": 1360
+    },
+    {
+      "epoch": 0.6447025361460061,
+      "eval_accuracy": 0.9935587761674718,
+      "eval_f1": 0.9285714285714286,
+      "eval_loss": 0.015230515040457249,
+      "eval_precision": 0.8666666666666667,
+      "eval_recall": 1.0,
+      "eval_runtime": 50.0425,
+      "eval_samples_per_second": 5.415,
+      "eval_steps_per_second": 0.18,
+      "step": 1360
+    },
+    {
+      "epoch": 0.6451765821284665,
+      "grad_norm": 5.502664089202881,
+      "learning_rate": 6.73406070784703e-06,
+      "loss": 0.1049,
+      "step": 1361
+    },
+    {
+      "epoch": 0.6456506281109268,
+      "grad_norm": 3.8858397006988525,
+      "learning_rate": 6.7184207071303065e-06,
+      "loss": 0.1058,
+      "step": 1362
+    },
+    {
+      "epoch": 0.646124674093387,
+      "grad_norm": 3.3023645877838135,
+      "learning_rate": 6.702789697043739e-06,
+      "loss": 0.1119,
+      "step": 1363
+    },
+    {
+      "epoch": 0.6465987200758474,
+      "grad_norm": 6.430544376373291,
+      "learning_rate": 6.687167720412022e-06,
+      "loss": 0.2107,
+      "step": 1364
+    },
+    {
+      "epoch": 0.6470727660583077,
+      "grad_norm": 3.9412176609039307,
+      "learning_rate": 6.6715548200351025e-06,
+      "loss": 0.1272,
+      "step": 1365
+    },
+    {
+      "epoch": 0.6475468120407679,
+      "grad_norm": 6.815352439880371,
+      "learning_rate": 6.6559510386880575e-06,
+      "loss": 0.172,
+      "step": 1366
+    },
+    {
+      "epoch": 0.6480208580232283,
+      "grad_norm": 6.693808555603027,
+      "learning_rate": 6.640356419120981e-06,
+      "loss": 0.1169,
+      "step": 1367
+    },
+    {
+      "epoch": 0.6484949040056885,
+      "grad_norm": 7.749126434326172,
+      "learning_rate": 6.624771004058869e-06,
+      "loss": 0.2337,
+      "step": 1368
+    },
+    {
+      "epoch": 0.6489689499881488,
+      "grad_norm": 5.6740336418151855,
+      "learning_rate": 6.609194836201498e-06,
+      "loss": 0.1464,
+      "step": 1369
+    },
+    {
+      "epoch": 0.6494429959706092,
+      "grad_norm": 5.359683990478516,
+      "learning_rate": 6.59362795822331e-06,
+      "loss": 0.171,
+      "step": 1370
+    },
+    {
+      "epoch": 0.6499170419530694,
+      "grad_norm": 7.062665939331055,
+      "learning_rate": 6.578070412773294e-06,
+      "loss": 0.1379,
+      "step": 1371
+    },
+    {
+      "epoch": 0.6503910879355298,
+      "grad_norm": 3.281470775604248,
+      "learning_rate": 6.562522242474873e-06,
+      "loss": 0.124,
+      "step": 1372
+    },
+    {
+      "epoch": 0.6508651339179901,
+      "grad_norm": 3.4849565029144287,
+      "learning_rate": 6.546983489925783e-06,
+      "loss": 0.0776,
+      "step": 1373
+    },
+    {
+      "epoch": 0.6513391799004503,
+      "grad_norm": 9.621129989624023,
+      "learning_rate": 6.531454197697956e-06,
+      "loss": 0.2229,
+      "step": 1374
+    },
+    {
+      "epoch": 0.6518132258829107,
+      "grad_norm": 5.371448993682861,
+      "learning_rate": 6.51593440833741e-06,
+      "loss": 0.1627,
+      "step": 1375
+    },
+    {
+      "epoch": 0.6522872718653709,
+      "grad_norm": 3.7554807662963867,
+      "learning_rate": 6.5004241643641204e-06,
+      "loss": 0.1219,
+      "step": 1376
+    },
+    {
+      "epoch": 0.6527613178478312,
+      "grad_norm": 10.365527153015137,
+      "learning_rate": 6.484923508271921e-06,
+      "loss": 0.1246,
+      "step": 1377
+    },
+    {
+      "epoch": 0.6532353638302916,
+      "grad_norm": 3.904869556427002,
+      "learning_rate": 6.469432482528371e-06,
+      "loss": 0.1454,
+      "step": 1378
+    },
+    {
+      "epoch": 0.6537094098127518,
+      "grad_norm": 8.565876007080078,
+      "learning_rate": 6.453951129574644e-06,
+      "loss": 0.191,
+      "step": 1379
+    },
+    {
+      "epoch": 0.6541834557952121,
+      "grad_norm": 5.346278667449951,
+      "learning_rate": 6.4384794918254155e-06,
+      "loss": 0.1567,
+      "step": 1380
+    },
+    {
+      "epoch": 0.6541834557952121,
+      "eval_accuracy": 0.9927536231884058,
+      "eval_f1": 0.9174311926605505,
+      "eval_loss": 0.013926459476351738,
+      "eval_precision": 0.8771929824561403,
+      "eval_recall": 0.9615384615384616,
+      "eval_runtime": 50.4117,
+      "eval_samples_per_second": 5.376,
+      "eval_steps_per_second": 0.179,
+      "step": 1380
+    },
+    {
+      "epoch": 0.6546575017776725,
+      "grad_norm": 7.4207539558410645,
+      "learning_rate": 6.423017611668745e-06,
+      "loss": 0.2611,
+      "step": 1381
+    },
+    {
+      "epoch": 0.6551315477601327,
+      "grad_norm": 4.336532115936279,
+      "learning_rate": 6.407565531465958e-06,
+      "loss": 0.1129,
+      "step": 1382
+    },
+    {
+      "epoch": 0.6556055937425931,
+      "grad_norm": 8.779532432556152,
+      "learning_rate": 6.392123293551524e-06,
+      "loss": 0.2831,
+      "step": 1383
+    },
+    {
+      "epoch": 0.6560796397250533,
+      "grad_norm": 3.4393012523651123,
+      "learning_rate": 6.3766909402329595e-06,
+      "loss": 0.1244,
+      "step": 1384
+    },
+    {
+      "epoch": 0.6565536857075136,
+      "grad_norm": 8.261950492858887,
+      "learning_rate": 6.36126851379069e-06,
+      "loss": 0.2614,
+      "step": 1385
+    },
+    {
+      "epoch": 0.657027731689974,
+      "grad_norm": 6.831699848175049,
+      "learning_rate": 6.3458560564779506e-06,
+      "loss": 0.1364,
+      "step": 1386
+    },
+    {
+      "epoch": 0.6575017776724342,
+      "grad_norm": 3.5841522216796875,
+      "learning_rate": 6.330453610520659e-06,
+      "loss": 0.1327,
+      "step": 1387
+    },
+    {
+      "epoch": 0.6579758236548945,
+      "grad_norm": 9.064952850341797,
+      "learning_rate": 6.315061218117311e-06,
+      "loss": 0.164,
+      "step": 1388
+    },
+    {
+      "epoch": 0.6584498696373549,
+      "grad_norm": 3.6154866218566895,
+      "learning_rate": 6.299678921438845e-06,
+      "loss": 0.0897,
+      "step": 1389
+    },
+    {
+      "epoch": 0.6589239156198151,
+      "grad_norm": 4.849295616149902,
+      "learning_rate": 6.284306762628556e-06,
+      "loss": 0.1721,
+      "step": 1390
+    },
+    {
+      "epoch": 0.6593979616022754,
+      "grad_norm": 9.754378318786621,
+      "learning_rate": 6.268944783801954e-06,
+      "loss": 0.1912,
+      "step": 1391
+    },
+    {
+      "epoch": 0.6598720075847357,
+      "grad_norm": 5.799689292907715,
+      "learning_rate": 6.253593027046663e-06,
+      "loss": 0.1779,
+      "step": 1392
+    },
+    {
+      "epoch": 0.660346053567196,
+      "grad_norm": 3.9141523838043213,
+      "learning_rate": 6.238251534422295e-06,
+      "loss": 0.2328,
+      "step": 1393
+    },
+    {
+      "epoch": 0.6608200995496564,
+      "grad_norm": 5.237335205078125,
+      "learning_rate": 6.22292034796035e-06,
+      "loss": 0.179,
+      "step": 1394
+    },
+    {
+      "epoch": 0.6612941455321166,
+      "grad_norm": 3.3698062896728516,
+      "learning_rate": 6.20759950966409e-06,
+      "loss": 0.1331,
+      "step": 1395
+    },
+    {
+      "epoch": 0.6617681915145769,
+      "grad_norm": 5.780014991760254,
+      "learning_rate": 6.19228906150842e-06,
+      "loss": 0.1727,
+      "step": 1396
+    },
+    {
+      "epoch": 0.6622422374970373,
+      "grad_norm": 5.892086029052734,
+      "learning_rate": 6.176989045439785e-06,
+      "loss": 0.1575,
+      "step": 1397
+    },
+    {
+      "epoch": 0.6627162834794975,
+      "grad_norm": 5.020101070404053,
+      "learning_rate": 6.161699503376042e-06,
+      "loss": 0.1429,
+      "step": 1398
+    },
+    {
+      "epoch": 0.6631903294619578,
+      "grad_norm": 5.539973735809326,
+      "learning_rate": 6.14642047720636e-06,
+      "loss": 0.1591,
+      "step": 1399
+    },
+    {
+      "epoch": 0.6636643754444181,
+      "grad_norm": 8.077629089355469,
+      "learning_rate": 6.131152008791092e-06,
+      "loss": 0.1771,
+      "step": 1400
+    },
+    {
+      "epoch": 0.6636643754444181,
+      "eval_accuracy": 0.9935587761674718,
+      "eval_f1": 0.9272727272727272,
+      "eval_loss": 0.01761007122695446,
+      "eval_precision": 0.8793103448275862,
+      "eval_recall": 0.9807692307692307,
+      "eval_runtime": 49.9728,
+      "eval_samples_per_second": 5.423,
+      "eval_steps_per_second": 0.18,
+      "step": 1400
     }
   ],
   "logging_steps": 1,
@@ -9918,7 +10678,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.47410391891968e+17,
+  "total_flos": 3.74254460303573e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null