Training in progress, step 2400, checkpoint

last-checkpoint/optimizer_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24312d61fce7e299202c695b1044a4796f624960d1404b905c54d6abb222cb8c
+oid sha256:ca9dc568df4ff33c09ef1ebec221c7fc9923de1130c221e73561e9b026a12701
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:175580163ae0def91026c5949833e86bc785d770db0b7757db53ef22072ca767
+oid sha256:81c9284accbdeb4c42587a79c4d7808341bc36141fd338a7532e134e98aa683b
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad31dbc2f54266d2c8e70ecf0aff447c10d4f855b87fe47ea62bb570e0d0da60
+oid sha256:9e67749ec026a2cc51286d7e9788a5d94dfab3360aad748aa06eea443f180d5c
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed8fb729039a78ead4b30a81f2aa16e8676ad408bc1552e8a482246f196e5cd6
+oid sha256:cf1f9d2e2be7a29e4571c553d3ff5691146e6f50cbe2dfe4ef481d9f7114e653
 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:adc3191d4cd665294dae5d0b36dbd57fee0d46d4c50f53249cdc0fd7e20b544f
+oid sha256:41582a536ea9cacc8d2937497430a6d82bde276a4242bfb0bb694a5f45cab783
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f6d689ceda9e9207e60fc38cd63eb39402b23c7d72b220cb0090e249e3e16b9
+oid sha256:8c7e81b6053f257397c0bbdd11633516e6adf1206ddad7e8dc93940e78bf9123
 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:e1fc9f3b557eb444ea344ecab856d01b57a7c4ce5e5f21b392509cf9b23a08f9
+oid sha256:81b1505e8f95c8de4f6f54ec4ffe595bf66d920664d32091c0abc6df49f3e8b4
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26e3dfe37061cd49d4cf48ef43c81018d73e05d1fa8c28a8822941449ee16073
+oid sha256:3ff3f972604df44c188de8c27bcca47cb7ae6ff39e182d1118d67f41818dde00
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6156d87a3edede0bd5fd215821a85320c517eca74046d12541e75ed03a44b648
+oid sha256:d697b23f5c330daa081ce49f435fdb1c5ab61ec113a016fb6f24b6c06e80fdb2
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f955a45267863f61f92f070f53d94052173924ff6923f8feaf17591492da3f8b
+oid sha256:4f23a02edc6e76f45f27839e965507f27f28eff09236bedac9e257624cf72591
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:affd28df85e029ed8ca9bcf5517998774ba1dc8d60a95c2935db00fe19d3e9cc
+oid sha256:13335d64984e53afd1451e386b6d637500f4346d30b75c66b40ddda25c7c1686
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:681f001f5104f634663b499f6e9d4e2abb34e750656370cc2aa7892a48040504
+oid sha256:263f3c76f3626e19c092ffda8934348d87d198a12a31c7c35b85857ee7b3a245
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71036ba3d5162c1e85b3994e14213b578278c107fdc908a31152acd41e824990
+oid sha256:0d0e39704c7a091da3052c3430e86ea60d1e6bf48c04b4d6c7e2a30adee885e4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.33935817041682037,
+  "epoch": 0.35411287347842124,
   "eval_steps": 20,
-  "global_step": 2300,
+  "global_step": 2400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -17499,6 +17499,766 @@
       "eval_samples_per_second": 5.871,
       "eval_steps_per_second": 0.202,
       "step": 2300
+    },
+    {
+      "epoch": 0.33950571744743635,
+      "grad_norm": 3.165992498397827,
+      "learning_rate": 1.6704310778473216e-05,
+      "loss": 0.1267,
+      "step": 2301
+    },
+    {
+      "epoch": 0.3396532644780524,
+      "grad_norm": 1.883520483970642,
+      "learning_rate": 1.670048799515186e-05,
+      "loss": 0.0585,
+      "step": 2302
+    },
+    {
+      "epoch": 0.33980081150866837,
+      "grad_norm": 3.8987653255462646,
+      "learning_rate": 1.669666343400594e-05,
+      "loss": 0.0849,
+      "step": 2303
+    },
+    {
+      "epoch": 0.3399483585392844,
+      "grad_norm": 4.0299506187438965,
+      "learning_rate": 1.669283709605022e-05,
+      "loss": 0.1268,
+      "step": 2304
+    },
+    {
+      "epoch": 0.3400959055699004,
+      "grad_norm": 1.843334436416626,
+      "learning_rate": 1.668900898229993e-05,
+      "loss": 0.0545,
+      "step": 2305
+    },
+    {
+      "epoch": 0.3402434526005164,
+      "grad_norm": 3.21661376953125,
+      "learning_rate": 1.668517909377078e-05,
+      "loss": 0.1062,
+      "step": 2306
+    },
+    {
+      "epoch": 0.3403909996311324,
+      "grad_norm": 5.5056986808776855,
+      "learning_rate": 1.6681347431478933e-05,
+      "loss": 0.0502,
+      "step": 2307
+    },
+    {
+      "epoch": 0.34053854666174843,
+      "grad_norm": 1.074285626411438,
+      "learning_rate": 1.6677513996441044e-05,
+      "loss": 0.0116,
+      "step": 2308
+    },
+    {
+      "epoch": 0.34068609369236447,
+      "grad_norm": 4.0778727531433105,
+      "learning_rate": 1.667367878967423e-05,
+      "loss": 0.1103,
+      "step": 2309
+    },
+    {
+      "epoch": 0.34083364072298045,
+      "grad_norm": 1.545832633972168,
+      "learning_rate": 1.6669841812196074e-05,
+      "loss": 0.0461,
+      "step": 2310
+    },
+    {
+      "epoch": 0.3409811877535965,
+      "grad_norm": 2.930983543395996,
+      "learning_rate": 1.6666003065024633e-05,
+      "loss": 0.0922,
+      "step": 2311
+    },
+    {
+      "epoch": 0.34112873478421246,
+      "grad_norm": 3.9265267848968506,
+      "learning_rate": 1.6662162549178433e-05,
+      "loss": 0.0512,
+      "step": 2312
+    },
+    {
+      "epoch": 0.3412762818148285,
+      "grad_norm": 16.14114761352539,
+      "learning_rate": 1.6658320265676465e-05,
+      "loss": 0.1144,
+      "step": 2313
+    },
+    {
+      "epoch": 0.3414238288454445,
+      "grad_norm": 2.545940637588501,
+      "learning_rate": 1.66544762155382e-05,
+      "loss": 0.0302,
+      "step": 2314
+    },
+    {
+      "epoch": 0.3415713758760605,
+      "grad_norm": 1.3965038061141968,
+      "learning_rate": 1.6650630399783567e-05,
+      "loss": 0.0551,
+      "step": 2315
+    },
+    {
+      "epoch": 0.3417189229066765,
+      "grad_norm": 4.396641254425049,
+      "learning_rate": 1.6646782819432967e-05,
+      "loss": 0.0921,
+      "step": 2316
+    },
+    {
+      "epoch": 0.3418664699372925,
+      "grad_norm": 4.47985315322876,
+      "learning_rate": 1.6642933475507268e-05,
+      "loss": 0.1322,
+      "step": 2317
+    },
+    {
+      "epoch": 0.3420140169679085,
+      "grad_norm": 1.0465424060821533,
+      "learning_rate": 1.6639082369027812e-05,
+      "loss": 0.0375,
+      "step": 2318
+    },
+    {
+      "epoch": 0.34216156399852454,
+      "grad_norm": 2.912580966949463,
+      "learning_rate": 1.6635229501016403e-05,
+      "loss": 0.03,
+      "step": 2319
+    },
+    {
+      "epoch": 0.3423091110291405,
+      "grad_norm": 1.5885111093521118,
+      "learning_rate": 1.6631374872495303e-05,
+      "loss": 0.0435,
+      "step": 2320
+    },
+    {
+      "epoch": 0.3423091110291405,
+      "eval_accuracy": 0.9782923299565847,
+      "eval_f1": 0.9629629629629629,
+      "eval_loss": 0.06419352442026138,
+      "eval_precision": 0.9798994974874372,
+      "eval_recall": 0.9466019417475728,
+      "eval_runtime": 49.8539,
+      "eval_samples_per_second": 5.837,
+      "eval_steps_per_second": 0.201,
+      "step": 2320
+    },
+    {
+      "epoch": 0.34245665805975656,
+      "grad_norm": 1.3954262733459473,
+      "learning_rate": 1.6627518484487266e-05,
+      "loss": 0.0511,
+      "step": 2321
+    },
+    {
+      "epoch": 0.34260420509037254,
+      "grad_norm": 0.9614152908325195,
+      "learning_rate": 1.662366033801549e-05,
+      "loss": 0.0366,
+      "step": 2322
+    },
+    {
+      "epoch": 0.3427517521209886,
+      "grad_norm": 5.605996608734131,
+      "learning_rate": 1.661980043410365e-05,
+      "loss": 0.1091,
+      "step": 2323
+    },
+    {
+      "epoch": 0.34289929915160455,
+      "grad_norm": 1.5293532609939575,
+      "learning_rate": 1.6615938773775885e-05,
+      "loss": 0.0472,
+      "step": 2324
+    },
+    {
+      "epoch": 0.3430468461822206,
+      "grad_norm": 1.7617485523223877,
+      "learning_rate": 1.66120753580568e-05,
+      "loss": 0.0416,
+      "step": 2325
+    },
+    {
+      "epoch": 0.34319439321283657,
+      "grad_norm": 2.8528995513916016,
+      "learning_rate": 1.6608210187971467e-05,
+      "loss": 0.0875,
+      "step": 2326
+    },
+    {
+      "epoch": 0.3433419402434526,
+      "grad_norm": 1.56826651096344,
+      "learning_rate": 1.660434326454542e-05,
+      "loss": 0.0456,
+      "step": 2327
+    },
+    {
+      "epoch": 0.3434894872740686,
+      "grad_norm": 3.3070790767669678,
+      "learning_rate": 1.6600474588804664e-05,
+      "loss": 0.1317,
+      "step": 2328
+    },
+    {
+      "epoch": 0.3436370343046846,
+      "grad_norm": 2.1225554943084717,
+      "learning_rate": 1.659660416177566e-05,
+      "loss": 0.0765,
+      "step": 2329
+    },
+    {
+      "epoch": 0.34378458133530065,
+      "grad_norm": 0.9811033606529236,
+      "learning_rate": 1.6592731984485343e-05,
+      "loss": 0.0293,
+      "step": 2330
+    },
+    {
+      "epoch": 0.34393212836591663,
+      "grad_norm": 2.6723105907440186,
+      "learning_rate": 1.658885805796111e-05,
+      "loss": 0.0435,
+      "step": 2331
+    },
+    {
+      "epoch": 0.34407967539653267,
+      "grad_norm": 3.923781156539917,
+      "learning_rate": 1.658498238323082e-05,
+      "loss": 0.0906,
+      "step": 2332
+    },
+    {
+      "epoch": 0.34422722242714865,
+      "grad_norm": 3.2581284046173096,
+      "learning_rate": 1.65811049613228e-05,
+      "loss": 0.0979,
+      "step": 2333
+    },
+    {
+      "epoch": 0.3443747694577647,
+      "grad_norm": 1.3880892992019653,
+      "learning_rate": 1.6577225793265826e-05,
+      "loss": 0.0395,
+      "step": 2334
+    },
+    {
+      "epoch": 0.34452231648838066,
+      "grad_norm": 1.3485021591186523,
+      "learning_rate": 1.6573344880089157e-05,
+      "loss": 0.0188,
+      "step": 2335
+    },
+    {
+      "epoch": 0.3446698635189967,
+      "grad_norm": 4.487036228179932,
+      "learning_rate": 1.6569462222822504e-05,
+      "loss": 0.0493,
+      "step": 2336
+    },
+    {
+      "epoch": 0.3448174105496127,
+      "grad_norm": 2.8430447578430176,
+      "learning_rate": 1.6565577822496042e-05,
+      "loss": 0.085,
+      "step": 2337
+    },
+    {
+      "epoch": 0.3449649575802287,
+      "grad_norm": 8.752228736877441,
+      "learning_rate": 1.6561691680140416e-05,
+      "loss": 0.1306,
+      "step": 2338
+    },
+    {
+      "epoch": 0.3451125046108447,
+      "grad_norm": 1.9699515104293823,
+      "learning_rate": 1.6557803796786723e-05,
+      "loss": 0.0232,
+      "step": 2339
+    },
+    {
+      "epoch": 0.34526005164146073,
+      "grad_norm": 2.071045398712158,
+      "learning_rate": 1.6553914173466523e-05,
+      "loss": 0.027,
+      "step": 2340
+    },
+    {
+      "epoch": 0.34526005164146073,
+      "eval_accuracy": 0.9768451519536903,
+      "eval_f1": 0.9603960396039604,
+      "eval_loss": 0.06641129404306412,
+      "eval_precision": 0.9797979797979798,
+      "eval_recall": 0.941747572815534,
+      "eval_runtime": 50.2292,
+      "eval_samples_per_second": 5.793,
+      "eval_steps_per_second": 0.199,
+      "step": 2340
+    },
+    {
+      "epoch": 0.3454075986720767,
+      "grad_norm": 1.799544334411621,
+      "learning_rate": 1.6550022811211842e-05,
+      "loss": 0.0379,
+      "step": 2341
+    },
+    {
+      "epoch": 0.34555514570269275,
+      "grad_norm": 3.7917068004608154,
+      "learning_rate": 1.6546129711055167e-05,
+      "loss": 0.0667,
+      "step": 2342
+    },
+    {
+      "epoch": 0.3457026927333087,
+      "grad_norm": 1.8615074157714844,
+      "learning_rate": 1.6542234874029448e-05,
+      "loss": 0.0434,
+      "step": 2343
+    },
+    {
+      "epoch": 0.34585023976392476,
+      "grad_norm": 3.230102777481079,
+      "learning_rate": 1.6538338301168088e-05,
+      "loss": 0.0807,
+      "step": 2344
+    },
+    {
+      "epoch": 0.34599778679454074,
+      "grad_norm": 3.9649109840393066,
+      "learning_rate": 1.6534439993504956e-05,
+      "loss": 0.135,
+      "step": 2345
+    },
+    {
+      "epoch": 0.3461453338251568,
+      "grad_norm": 2.0120749473571777,
+      "learning_rate": 1.653053995207438e-05,
+      "loss": 0.0335,
+      "step": 2346
+    },
+    {
+      "epoch": 0.34629288085577276,
+      "grad_norm": 3.698765754699707,
+      "learning_rate": 1.652663817791116e-05,
+      "loss": 0.0956,
+      "step": 2347
+    },
+    {
+      "epoch": 0.3464404278863888,
+      "grad_norm": 1.215096116065979,
+      "learning_rate": 1.6522734672050526e-05,
+      "loss": 0.0425,
+      "step": 2348
+    },
+    {
+      "epoch": 0.34658797491700477,
+      "grad_norm": 2.372612237930298,
+      "learning_rate": 1.6518829435528195e-05,
+      "loss": 0.0391,
+      "step": 2349
+    },
+    {
+      "epoch": 0.3467355219476208,
+      "grad_norm": 1.7483614683151245,
+      "learning_rate": 1.651492246938034e-05,
+      "loss": 0.0361,
+      "step": 2350
+    },
+    {
+      "epoch": 0.3468830689782368,
+      "grad_norm": 2.1177897453308105,
+      "learning_rate": 1.6511013774643578e-05,
+      "loss": 0.0804,
+      "step": 2351
+    },
+    {
+      "epoch": 0.3470306160088528,
+      "grad_norm": 2.710125207901001,
+      "learning_rate": 1.6507103352354998e-05,
+      "loss": 0.101,
+      "step": 2352
+    },
+    {
+      "epoch": 0.34717816303946886,
+      "grad_norm": 2.26253604888916,
+      "learning_rate": 1.6503191203552138e-05,
+      "loss": 0.0586,
+      "step": 2353
+    },
+    {
+      "epoch": 0.34732571007008484,
+      "grad_norm": 2.8633363246917725,
+      "learning_rate": 1.6499277329273006e-05,
+      "loss": 0.0986,
+      "step": 2354
+    },
+    {
+      "epoch": 0.34747325710070087,
+      "grad_norm": 3.533268690109253,
+      "learning_rate": 1.649536173055606e-05,
+      "loss": 0.1384,
+      "step": 2355
+    },
+    {
+      "epoch": 0.34762080413131685,
+      "grad_norm": 1.1151478290557861,
+      "learning_rate": 1.6491444408440212e-05,
+      "loss": 0.045,
+      "step": 2356
+    },
+    {
+      "epoch": 0.3477683511619329,
+      "grad_norm": 2.5397818088531494,
+      "learning_rate": 1.648752536396484e-05,
+      "loss": 0.0585,
+      "step": 2357
+    },
+    {
+      "epoch": 0.34791589819254887,
+      "grad_norm": 2.7460968494415283,
+      "learning_rate": 1.6483604598169768e-05,
+      "loss": 0.0747,
+      "step": 2358
+    },
+    {
+      "epoch": 0.3480634452231649,
+      "grad_norm": 2.952080488204956,
+      "learning_rate": 1.6479682112095295e-05,
+      "loss": 0.072,
+      "step": 2359
+    },
+    {
+      "epoch": 0.3482109922537809,
+      "grad_norm": 2.2750353813171387,
+      "learning_rate": 1.647575790678215e-05,
+      "loss": 0.075,
+      "step": 2360
+    },
+    {
+      "epoch": 0.3482109922537809,
+      "eval_accuracy": 0.975397973950796,
+      "eval_f1": 0.9584352078239609,
+      "eval_loss": 0.0662899762392044,
+      "eval_precision": 0.9655172413793104,
+      "eval_recall": 0.9514563106796117,
+      "eval_runtime": 50.1902,
+      "eval_samples_per_second": 5.798,
+      "eval_steps_per_second": 0.199,
+      "step": 2360
+    },
+    {
+      "epoch": 0.3483585392843969,
+      "grad_norm": 1.847737431526184,
+      "learning_rate": 1.6471831983271555e-05,
+      "loss": 0.0352,
+      "step": 2361
+    },
+    {
+      "epoch": 0.3485060863150129,
+      "grad_norm": 3.476930618286133,
+      "learning_rate": 1.6467904342605142e-05,
+      "loss": 0.1174,
+      "step": 2362
+    },
+    {
+      "epoch": 0.34865363334562893,
+      "grad_norm": 1.9660117626190186,
+      "learning_rate": 1.6463974985825038e-05,
+      "loss": 0.0256,
+      "step": 2363
+    },
+    {
+      "epoch": 0.3488011803762449,
+      "grad_norm": 2.007992744445801,
+      "learning_rate": 1.64600439139738e-05,
+      "loss": 0.0526,
+      "step": 2364
+    },
+    {
+      "epoch": 0.34894872740686095,
+      "grad_norm": 2.0181987285614014,
+      "learning_rate": 1.6456111128094458e-05,
+      "loss": 0.0426,
+      "step": 2365
+    },
+    {
+      "epoch": 0.34909627443747693,
+      "grad_norm": 1.851974606513977,
+      "learning_rate": 1.6452176629230486e-05,
+      "loss": 0.0249,
+      "step": 2366
+    },
+    {
+      "epoch": 0.34924382146809296,
+      "grad_norm": 1.7971105575561523,
+      "learning_rate": 1.6448240418425815e-05,
+      "loss": 0.0513,
+      "step": 2367
+    },
+    {
+      "epoch": 0.34939136849870894,
+      "grad_norm": 2.0325169563293457,
+      "learning_rate": 1.644430249672483e-05,
+      "loss": 0.0848,
+      "step": 2368
+    },
+    {
+      "epoch": 0.349538915529325,
+      "grad_norm": 1.832484245300293,
+      "learning_rate": 1.6440362865172373e-05,
+      "loss": 0.0608,
+      "step": 2369
+    },
+    {
+      "epoch": 0.34968646255994096,
+      "grad_norm": 2.5634117126464844,
+      "learning_rate": 1.643642152481373e-05,
+      "loss": 0.0657,
+      "step": 2370
+    },
+    {
+      "epoch": 0.349834009590557,
+      "grad_norm": 2.4291880130767822,
+      "learning_rate": 1.6432478476694654e-05,
+      "loss": 0.1045,
+      "step": 2371
+    },
+    {
+      "epoch": 0.349981556621173,
+      "grad_norm": 1.7768257856369019,
+      "learning_rate": 1.6428533721861346e-05,
+      "loss": 0.0642,
+      "step": 2372
+    },
+    {
+      "epoch": 0.350129103651789,
+      "grad_norm": 2.673724889755249,
+      "learning_rate": 1.6424587261360452e-05,
+      "loss": 0.0779,
+      "step": 2373
+    },
+    {
+      "epoch": 0.35027665068240504,
+      "grad_norm": 1.1445502042770386,
+      "learning_rate": 1.642063909623908e-05,
+      "loss": 0.0277,
+      "step": 2374
+    },
+    {
+      "epoch": 0.350424197713021,
+      "grad_norm": 1.6839622259140015,
+      "learning_rate": 1.641668922754479e-05,
+      "loss": 0.0186,
+      "step": 2375
+    },
+    {
+      "epoch": 0.35057174474363706,
+      "grad_norm": 0.8631309866905212,
+      "learning_rate": 1.641273765632559e-05,
+      "loss": 0.0226,
+      "step": 2376
+    },
+    {
+      "epoch": 0.35071929177425304,
+      "grad_norm": 4.310630798339844,
+      "learning_rate": 1.6408784383629937e-05,
+      "loss": 0.127,
+      "step": 2377
+    },
+    {
+      "epoch": 0.3508668388048691,
+      "grad_norm": 2.018258571624756,
+      "learning_rate": 1.6404829410506747e-05,
+      "loss": 0.0359,
+      "step": 2378
+    },
+    {
+      "epoch": 0.35101438583548505,
+      "grad_norm": 1.7199050188064575,
+      "learning_rate": 1.6400872738005385e-05,
+      "loss": 0.0526,
+      "step": 2379
+    },
+    {
+      "epoch": 0.3511619328661011,
+      "grad_norm": 3.265058755874634,
+      "learning_rate": 1.639691436717566e-05,
+      "loss": 0.071,
+      "step": 2380
+    },
+    {
+      "epoch": 0.3511619328661011,
+      "eval_accuracy": 0.9739507959479016,
+      "eval_f1": 0.955,
+      "eval_loss": 0.0693851187825203,
+      "eval_precision": 0.9845360824742269,
+      "eval_recall": 0.9271844660194175,
+      "eval_runtime": 50.6047,
+      "eval_samples_per_second": 5.75,
+      "eval_steps_per_second": 0.198,
+      "step": 2380
+    },
+    {
+      "epoch": 0.35130947989671707,
+      "grad_norm": 1.8791478872299194,
+      "learning_rate": 1.6392954299067843e-05,
+      "loss": 0.0339,
+      "step": 2381
+    },
+    {
+      "epoch": 0.3514570269273331,
+      "grad_norm": 1.8809936046600342,
+      "learning_rate": 1.6388992534732645e-05,
+      "loss": 0.0407,
+      "step": 2382
+    },
+    {
+      "epoch": 0.3516045739579491,
+      "grad_norm": 1.4170249700546265,
+      "learning_rate": 1.6385029075221238e-05,
+      "loss": 0.0351,
+      "step": 2383
+    },
+    {
+      "epoch": 0.3517521209885651,
+      "grad_norm": 5.98276948928833,
+      "learning_rate": 1.638106392158523e-05,
+      "loss": 0.1323,
+      "step": 2384
+    },
+    {
+      "epoch": 0.3518996680191811,
+      "grad_norm": 2.3200674057006836,
+      "learning_rate": 1.6377097074876687e-05,
+      "loss": 0.027,
+      "step": 2385
+    },
+    {
+      "epoch": 0.35204721504979714,
+      "grad_norm": 7.031911373138428,
+      "learning_rate": 1.637312853614813e-05,
+      "loss": 0.111,
+      "step": 2386
+    },
+    {
+      "epoch": 0.3521947620804131,
+      "grad_norm": 1.8072407245635986,
+      "learning_rate": 1.636915830645251e-05,
+      "loss": 0.0809,
+      "step": 2387
+    },
+    {
+      "epoch": 0.35234230911102915,
+      "grad_norm": 1.564636468887329,
+      "learning_rate": 1.636518638684325e-05,
+      "loss": 0.0281,
+      "step": 2388
+    },
+    {
+      "epoch": 0.35248985614164513,
+      "grad_norm": 2.847052812576294,
+      "learning_rate": 1.6361212778374206e-05,
+      "loss": 0.0926,
+      "step": 2389
+    },
+    {
+      "epoch": 0.35263740317226117,
+      "grad_norm": 3.316835880279541,
+      "learning_rate": 1.6357237482099682e-05,
+      "loss": 0.1283,
+      "step": 2390
+    },
+    {
+      "epoch": 0.35278495020287715,
+      "grad_norm": 1.7379379272460938,
+      "learning_rate": 1.6353260499074437e-05,
+      "loss": 0.049,
+      "step": 2391
+    },
+    {
+      "epoch": 0.3529324972334932,
+      "grad_norm": 2.3816347122192383,
+      "learning_rate": 1.6349281830353677e-05,
+      "loss": 0.0739,
+      "step": 2392
+    },
+    {
+      "epoch": 0.35308004426410916,
+      "grad_norm": 3.8929433822631836,
+      "learning_rate": 1.6345301476993052e-05,
+      "loss": 0.0741,
+      "step": 2393
+    },
+    {
+      "epoch": 0.3532275912947252,
+      "grad_norm": 3.5631837844848633,
+      "learning_rate": 1.6341319440048657e-05,
+      "loss": 0.0788,
+      "step": 2394
+    },
+    {
+      "epoch": 0.3533751383253412,
+      "grad_norm": 1.5988062620162964,
+      "learning_rate": 1.6337335720577033e-05,
+      "loss": 0.0634,
+      "step": 2395
+    },
+    {
+      "epoch": 0.3535226853559572,
+      "grad_norm": 2.0330374240875244,
+      "learning_rate": 1.633335031963518e-05,
+      "loss": 0.0534,
+      "step": 2396
+    },
+    {
+      "epoch": 0.35367023238657325,
+      "grad_norm": 2.1022183895111084,
+      "learning_rate": 1.6329363238280528e-05,
+      "loss": 0.0438,
+      "step": 2397
+    },
+    {
+      "epoch": 0.3538177794171892,
+      "grad_norm": 2.7071707248687744,
+      "learning_rate": 1.6325374477570965e-05,
+      "loss": 0.0509,
+      "step": 2398
+    },
+    {
+      "epoch": 0.35396532644780526,
+      "grad_norm": 2.6731655597686768,
+      "learning_rate": 1.6321384038564816e-05,
+      "loss": 0.0327,
+      "step": 2399
+    },
+    {
+      "epoch": 0.35411287347842124,
+      "grad_norm": 1.992941975593567,
+      "learning_rate": 1.6317391922320857e-05,
+      "loss": 0.0724,
+      "step": 2400
+    },
+    {
+      "epoch": 0.35411287347842124,
+      "eval_accuracy": 0.975397973950796,
+      "eval_f1": 0.9576059850374065,
+      "eval_loss": 0.0716041848063469,
+      "eval_precision": 0.9846153846153847,
+      "eval_recall": 0.9320388349514563,
+      "eval_runtime": 50.0864,
+      "eval_samples_per_second": 5.81,
+      "eval_steps_per_second": 0.2,
+      "step": 2400
     }
   ],
   "logging_steps": 1,
@@ -17518,7 +18278,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.084455024457155e+17,
+  "total_flos": 7.39152253033644e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null