Training in progress, step 400, checkpoint

last-checkpoint/optimizer_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0828710b640dbf68298e27271b529b25b9633dd7711dad19568b25686b79955f
+oid sha256:4963b2cd50e57f6b515f56f974dfe45d992517004fc520f6955d81d176f790a7
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09c7ac02ae4e3a773215b98acf254fe48c4e7de8555cfc804e4c8564253462d5
+oid sha256:c68fdb607ac4683a8dca2ee6fa979f122c8b9e4f5a8be05c199df9ffdf462632
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fe68aa5543c7e1858414222033d21efd3626ac60315b4e8919cae752773097c
+oid sha256:c8f1c5f0040695754e95cea31a92ba95b979e25d690f9d64c169d66dc419f228
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29b26a714efa8d1e7798d4d1a8c5ead91c9c253836ae76c8074e3b2d998b12ff
+oid sha256:b8e9491dc652893fb060e965d69962558957f031ecac809634247164f574e608
 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:c95f08281fb03852e4519ff6aa382f5c90ec236a0542a483b82c72cfa5ad848e
+oid sha256:d035efe305175a2f8bfbab2f8d3e62cee6f2ced0a908d7eb6c1e495846d0737b
 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:dae344d3faf7510fb590a7e7eaf2cfc188c6927842e743a0272a1df1c56f789d
+oid sha256:dc84a14f60fa5fc54638a6ef9c91a376a58f7ab98ea47d3c31d76ce89c680414
 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:d105c6f274366380374e805d8adf2ea780c3fcbf468ed3da0d30d931fdfebac8
+oid sha256:ac4073bdc83a079a4b6896bc4a6496aeea9ed2771c055d341f2925ac3e15b804
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94b26738ea842513efa4609b1427f3c23b0d37d48ad0efdbd4bd1f4842bfb006
+oid sha256:3a66dd53cdd3497de414d53e774c65997b79be629a8b45594ad103171f71988a
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e68dcb3ef0e8b7c7d625ab213042156e023f2a245865d688db9dd4fe92f207dc
+oid sha256:30f7efb14f830613ce1feb32c656507e2b2715abb7e03351d4ab24fdac833de9
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45b214c4a5ffd153814b8b271cfd3ef9fa8c2be4640619c8e4854dc05d7d1c97
+oid sha256:b570acbde5d360a8111669f646b87b723b1561b932314383883cb8d7631cf6a5
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96a5e4dab35f0ee0b3a7f32c0e07341ebe72be8848c24cfaf9766b3fa46c7222
+oid sha256:ce2f6e01a41ead5e1f0563b520db5e55e49adbcab1ba2767d62506fd2c2fd350
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b62411f66602767298f963adc60824709fbed6ee64305b82501b466a1c44c9e
+oid sha256:b05228164f2365d0c73a013ea3f0d6ff1002ba4a518c68a6670e0c417be0df02
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8d986f9845c2c79697397af5a78c52fea0f5eb71ebc653676ec6d3ab1848325
+oid sha256:feec47af43281c02d149007021796dc5997bea57643d860b75184d48d617927b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2029769959404601,
+  "epoch": 0.2706359945872801,
   "eval_steps": 20,
-  "global_step": 300,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2299,6 +2299,766 @@
       "eval_samples_per_second": 5.781,
       "eval_steps_per_second": 0.194,
       "step": 300
+    },
+    {
+      "epoch": 0.20365358592692828,
+      "grad_norm": 5.575674057006836,
+      "learning_rate": 1.935402277163988e-05,
+      "loss": 0.1904,
+      "step": 301
+    },
+    {
+      "epoch": 0.20433017591339647,
+      "grad_norm": 4.0572829246521,
+      "learning_rate": 1.934564464599461e-05,
+      "loss": 0.1882,
+      "step": 302
+    },
+    {
+      "epoch": 0.2050067658998647,
+      "grad_norm": 3.6547298431396484,
+      "learning_rate": 1.9337214376207417e-05,
+      "loss": 0.2039,
+      "step": 303
+    },
+    {
+      "epoch": 0.20568335588633288,
+      "grad_norm": 4.347687721252441,
+      "learning_rate": 1.9328732009315107e-05,
+      "loss": 0.169,
+      "step": 304
+    },
+    {
+      "epoch": 0.20635994587280107,
+      "grad_norm": 4.556861400604248,
+      "learning_rate": 1.932019759264514e-05,
+      "loss": 0.203,
+      "step": 305
+    },
+    {
+      "epoch": 0.2070365358592693,
+      "grad_norm": 5.285150527954102,
+      "learning_rate": 1.931161117381541e-05,
+      "loss": 0.1871,
+      "step": 306
+    },
+    {
+      "epoch": 0.20771312584573748,
+      "grad_norm": 3.5677342414855957,
+      "learning_rate": 1.9302972800733945e-05,
+      "loss": 0.1735,
+      "step": 307
+    },
+    {
+      "epoch": 0.2083897158322057,
+      "grad_norm": 2.768244743347168,
+      "learning_rate": 1.929428252159866e-05,
+      "loss": 0.1313,
+      "step": 308
+    },
+    {
+      "epoch": 0.2090663058186739,
+      "grad_norm": 3.212564706802368,
+      "learning_rate": 1.9285540384897073e-05,
+      "loss": 0.1884,
+      "step": 309
+    },
+    {
+      "epoch": 0.20974289580514208,
+      "grad_norm": 3.121872901916504,
+      "learning_rate": 1.9276746439406046e-05,
+      "loss": 0.2129,
+      "step": 310
+    },
+    {
+      "epoch": 0.2104194857916103,
+      "grad_norm": 3.6964709758758545,
+      "learning_rate": 1.9267900734191515e-05,
+      "loss": 0.2355,
+      "step": 311
+    },
+    {
+      "epoch": 0.21109607577807848,
+      "grad_norm": 3.5150861740112305,
+      "learning_rate": 1.9259003318608192e-05,
+      "loss": 0.1878,
+      "step": 312
+    },
+    {
+      "epoch": 0.21177266576454667,
+      "grad_norm": 3.9340460300445557,
+      "learning_rate": 1.925005424229933e-05,
+      "loss": 0.15,
+      "step": 313
+    },
+    {
+      "epoch": 0.2124492557510149,
+      "grad_norm": 8.675088882446289,
+      "learning_rate": 1.9241053555196405e-05,
+      "loss": 0.2527,
+      "step": 314
+    },
+    {
+      "epoch": 0.21312584573748308,
+      "grad_norm": 7.502621173858643,
+      "learning_rate": 1.923200130751887e-05,
+      "loss": 0.2089,
+      "step": 315
+    },
+    {
+      "epoch": 0.21380243572395127,
+      "grad_norm": 2.9825868606567383,
+      "learning_rate": 1.922289754977385e-05,
+      "loss": 0.1341,
+      "step": 316
+    },
+    {
+      "epoch": 0.2144790257104195,
+      "grad_norm": 5.308103084564209,
+      "learning_rate": 1.9213742332755877e-05,
+      "loss": 0.1872,
+      "step": 317
+    },
+    {
+      "epoch": 0.21515561569688768,
+      "grad_norm": 5.801865577697754,
+      "learning_rate": 1.9204535707546602e-05,
+      "loss": 0.2068,
+      "step": 318
+    },
+    {
+      "epoch": 0.2158322056833559,
+      "grad_norm": 4.229133605957031,
+      "learning_rate": 1.919527772551451e-05,
+      "loss": 0.1741,
+      "step": 319
+    },
+    {
+      "epoch": 0.2165087956698241,
+      "grad_norm": 2.5876822471618652,
+      "learning_rate": 1.918596843831462e-05,
+      "loss": 0.1221,
+      "step": 320
+    },
+    {
+      "epoch": 0.2165087956698241,
+      "eval_accuracy": 0.771559633027523,
+      "eval_f1": 0.3178082191780822,
+      "eval_loss": 0.49765169620513916,
+      "eval_precision": 0.8656716417910447,
+      "eval_recall": 0.19463087248322147,
+      "eval_runtime": 51.4716,
+      "eval_samples_per_second": 5.79,
+      "eval_steps_per_second": 0.194,
+      "step": 320
+    },
+    {
+      "epoch": 0.21718538565629228,
+      "grad_norm": 3.950688600540161,
+      "learning_rate": 1.9176607897888217e-05,
+      "loss": 0.1415,
+      "step": 321
+    },
+    {
+      "epoch": 0.2178619756427605,
+      "grad_norm": 2.8493704795837402,
+      "learning_rate": 1.916719615646256e-05,
+      "loss": 0.1171,
+      "step": 322
+    },
+    {
+      "epoch": 0.2185385656292287,
+      "grad_norm": 2.8084137439727783,
+      "learning_rate": 1.9157733266550577e-05,
+      "loss": 0.1774,
+      "step": 323
+    },
+    {
+      "epoch": 0.21921515561569688,
+      "grad_norm": 3.1478347778320312,
+      "learning_rate": 1.914821928095058e-05,
+      "loss": 0.1816,
+      "step": 324
+    },
+    {
+      "epoch": 0.2198917456021651,
+      "grad_norm": 3.8505070209503174,
+      "learning_rate": 1.913865425274597e-05,
+      "loss": 0.1413,
+      "step": 325
+    },
+    {
+      "epoch": 0.22056833558863329,
+      "grad_norm": 4.398627281188965,
+      "learning_rate": 1.9129038235304946e-05,
+      "loss": 0.1745,
+      "step": 326
+    },
+    {
+      "epoch": 0.22124492557510148,
+      "grad_norm": 4.207502841949463,
+      "learning_rate": 1.9119371282280197e-05,
+      "loss": 0.1996,
+      "step": 327
+    },
+    {
+      "epoch": 0.2219215155615697,
+      "grad_norm": 3.8576388359069824,
+      "learning_rate": 1.9109653447608607e-05,
+      "loss": 0.1522,
+      "step": 328
+    },
+    {
+      "epoch": 0.22259810554803788,
+      "grad_norm": 3.856382369995117,
+      "learning_rate": 1.909988478551096e-05,
+      "loss": 0.1642,
+      "step": 329
+    },
+    {
+      "epoch": 0.2232746955345061,
+      "grad_norm": 5.088944911956787,
+      "learning_rate": 1.909006535049163e-05,
+      "loss": 0.1496,
+      "step": 330
+    },
+    {
+      "epoch": 0.2239512855209743,
+      "grad_norm": 3.050905704498291,
+      "learning_rate": 1.908019519733827e-05,
+      "loss": 0.1263,
+      "step": 331
+    },
+    {
+      "epoch": 0.22462787550744248,
+      "grad_norm": 2.3252899646759033,
+      "learning_rate": 1.907027438112153e-05,
+      "loss": 0.1323,
+      "step": 332
+    },
+    {
+      "epoch": 0.2253044654939107,
+      "grad_norm": 3.3663437366485596,
+      "learning_rate": 1.9060302957194732e-05,
+      "loss": 0.1085,
+      "step": 333
+    },
+    {
+      "epoch": 0.2259810554803789,
+      "grad_norm": 6.574558258056641,
+      "learning_rate": 1.9050280981193555e-05,
+      "loss": 0.2637,
+      "step": 334
+    },
+    {
+      "epoch": 0.22665764546684708,
+      "grad_norm": 4.396321773529053,
+      "learning_rate": 1.9040208509035745e-05,
+      "loss": 0.1464,
+      "step": 335
+    },
+    {
+      "epoch": 0.2273342354533153,
+      "grad_norm": 6.94221305847168,
+      "learning_rate": 1.9030085596920786e-05,
+      "loss": 0.1608,
+      "step": 336
+    },
+    {
+      "epoch": 0.2280108254397835,
+      "grad_norm": 3.8373563289642334,
+      "learning_rate": 1.9019912301329593e-05,
+      "loss": 0.2373,
+      "step": 337
+    },
+    {
+      "epoch": 0.22868741542625168,
+      "grad_norm": 2.109513998031616,
+      "learning_rate": 1.900968867902419e-05,
+      "loss": 0.1219,
+      "step": 338
+    },
+    {
+      "epoch": 0.2293640054127199,
+      "grad_norm": 2.0259997844696045,
+      "learning_rate": 1.899941478704742e-05,
+      "loss": 0.1093,
+      "step": 339
+    },
+    {
+      "epoch": 0.23004059539918809,
+      "grad_norm": 2.7739081382751465,
+      "learning_rate": 1.8989090682722583e-05,
+      "loss": 0.1666,
+      "step": 340
+    },
+    {
+      "epoch": 0.23004059539918809,
+      "eval_accuracy": 0.7779816513761468,
+      "eval_f1": 0.36649214659685864,
+      "eval_loss": 0.48961758613586426,
+      "eval_precision": 0.8333333333333334,
+      "eval_recall": 0.2348993288590604,
+      "eval_runtime": 51.6267,
+      "eval_samples_per_second": 5.772,
+      "eval_steps_per_second": 0.194,
+      "step": 340
+    },
+    {
+      "epoch": 0.2307171853856563,
+      "grad_norm": 2.2220234870910645,
+      "learning_rate": 1.8978716423653153e-05,
+      "loss": 0.1309,
+      "step": 341
+    },
+    {
+      "epoch": 0.2313937753721245,
+      "grad_norm": 2.679076910018921,
+      "learning_rate": 1.8968292067722433e-05,
+      "loss": 0.1182,
+      "step": 342
+    },
+    {
+      "epoch": 0.23207036535859268,
+      "grad_norm": 2.6752357482910156,
+      "learning_rate": 1.8957817673093258e-05,
+      "loss": 0.0976,
+      "step": 343
+    },
+    {
+      "epoch": 0.2327469553450609,
+      "grad_norm": 3.9076900482177734,
+      "learning_rate": 1.8947293298207637e-05,
+      "loss": 0.2482,
+      "step": 344
+    },
+    {
+      "epoch": 0.2334235453315291,
+      "grad_norm": 2.4209744930267334,
+      "learning_rate": 1.8936719001786453e-05,
+      "loss": 0.1294,
+      "step": 345
+    },
+    {
+      "epoch": 0.23410013531799728,
+      "grad_norm": 2.483504056930542,
+      "learning_rate": 1.8926094842829128e-05,
+      "loss": 0.1349,
+      "step": 346
+    },
+    {
+      "epoch": 0.2347767253044655,
+      "grad_norm": 5.663891315460205,
+      "learning_rate": 1.891542088061329e-05,
+      "loss": 0.247,
+      "step": 347
+    },
+    {
+      "epoch": 0.2354533152909337,
+      "grad_norm": 3.8202829360961914,
+      "learning_rate": 1.8904697174694447e-05,
+      "loss": 0.1991,
+      "step": 348
+    },
+    {
+      "epoch": 0.2361299052774019,
+      "grad_norm": 4.326652526855469,
+      "learning_rate": 1.8893923784905647e-05,
+      "loss": 0.2144,
+      "step": 349
+    },
+    {
+      "epoch": 0.2368064952638701,
+      "grad_norm": 4.610856056213379,
+      "learning_rate": 1.888310077135716e-05,
+      "loss": 0.2581,
+      "step": 350
+    },
+    {
+      "epoch": 0.2374830852503383,
+      "grad_norm": 1.77244234085083,
+      "learning_rate": 1.887222819443612e-05,
+      "loss": 0.1308,
+      "step": 351
+    },
+    {
+      "epoch": 0.2381596752368065,
+      "grad_norm": 3.1713812351226807,
+      "learning_rate": 1.886130611480621e-05,
+      "loss": 0.1067,
+      "step": 352
+    },
+    {
+      "epoch": 0.2388362652232747,
+      "grad_norm": 3.379279136657715,
+      "learning_rate": 1.885033459340731e-05,
+      "loss": 0.1363,
+      "step": 353
+    },
+    {
+      "epoch": 0.2395128552097429,
+      "grad_norm": 3.649993896484375,
+      "learning_rate": 1.8839313691455163e-05,
+      "loss": 0.1521,
+      "step": 354
+    },
+    {
+      "epoch": 0.2401894451962111,
+      "grad_norm": 3.849156379699707,
+      "learning_rate": 1.8828243470441026e-05,
+      "loss": 0.2396,
+      "step": 355
+    },
+    {
+      "epoch": 0.2408660351826793,
+      "grad_norm": 2.089524745941162,
+      "learning_rate": 1.8817123992131344e-05,
+      "loss": 0.1016,
+      "step": 356
+    },
+    {
+      "epoch": 0.24154262516914748,
+      "grad_norm": 5.252878665924072,
+      "learning_rate": 1.880595531856738e-05,
+      "loss": 0.1606,
+      "step": 357
+    },
+    {
+      "epoch": 0.2422192151556157,
+      "grad_norm": 2.9322009086608887,
+      "learning_rate": 1.879473751206489e-05,
+      "loss": 0.1346,
+      "step": 358
+    },
+    {
+      "epoch": 0.2428958051420839,
+      "grad_norm": 3.819847822189331,
+      "learning_rate": 1.878347063521377e-05,
+      "loss": 0.2052,
+      "step": 359
+    },
+    {
+      "epoch": 0.2435723951285521,
+      "grad_norm": 3.4725139141082764,
+      "learning_rate": 1.8772154750877696e-05,
+      "loss": 0.1843,
+      "step": 360
+    },
+    {
+      "epoch": 0.2435723951285521,
+      "eval_accuracy": 0.8009174311926606,
+      "eval_f1": 0.49417249417249415,
+      "eval_loss": 0.4227532148361206,
+      "eval_precision": 0.8091603053435115,
+      "eval_recall": 0.35570469798657717,
+      "eval_runtime": 51.8917,
+      "eval_samples_per_second": 5.743,
+      "eval_steps_per_second": 0.193,
+      "step": 360
+    },
+    {
+      "epoch": 0.2442489851150203,
+      "grad_norm": 5.326034069061279,
+      "learning_rate": 1.876078992219379e-05,
+      "loss": 0.1945,
+      "step": 361
+    },
+    {
+      "epoch": 0.2449255751014885,
+      "grad_norm": 7.080038070678711,
+      "learning_rate": 1.8749376212572254e-05,
+      "loss": 0.2108,
+      "step": 362
+    },
+    {
+      "epoch": 0.2456021650879567,
+      "grad_norm": 4.56862211227417,
+      "learning_rate": 1.873791368569603e-05,
+      "loss": 0.1117,
+      "step": 363
+    },
+    {
+      "epoch": 0.2462787550744249,
+      "grad_norm": 5.154612064361572,
+      "learning_rate": 1.8726402405520425e-05,
+      "loss": 0.1771,
+      "step": 364
+    },
+    {
+      "epoch": 0.2469553450608931,
+      "grad_norm": 4.204885005950928,
+      "learning_rate": 1.8714842436272774e-05,
+      "loss": 0.1878,
+      "step": 365
+    },
+    {
+      "epoch": 0.2476319350473613,
+      "grad_norm": 3.4089162349700928,
+      "learning_rate": 1.8703233842452072e-05,
+      "loss": 0.1567,
+      "step": 366
+    },
+    {
+      "epoch": 0.2483085250338295,
+      "grad_norm": 3.831226348876953,
+      "learning_rate": 1.8691576688828613e-05,
+      "loss": 0.1782,
+      "step": 367
+    },
+    {
+      "epoch": 0.2489851150202977,
+      "grad_norm": 7.267455577850342,
+      "learning_rate": 1.8679871040443632e-05,
+      "loss": 0.2087,
+      "step": 368
+    },
+    {
+      "epoch": 0.2496617050067659,
+      "grad_norm": 4.274538993835449,
+      "learning_rate": 1.866811696260894e-05,
+      "loss": 0.1906,
+      "step": 369
+    },
+    {
+      "epoch": 0.2503382949932341,
+      "grad_norm": 5.741366863250732,
+      "learning_rate": 1.865631452090657e-05,
+      "loss": 0.2119,
+      "step": 370
+    },
+    {
+      "epoch": 0.2510148849797023,
+      "grad_norm": 3.3094899654388428,
+      "learning_rate": 1.8644463781188387e-05,
+      "loss": 0.1853,
+      "step": 371
+    },
+    {
+      "epoch": 0.2516914749661705,
+      "grad_norm": 3.474271774291992,
+      "learning_rate": 1.863256480957574e-05,
+      "loss": 0.1849,
+      "step": 372
+    },
+    {
+      "epoch": 0.2523680649526387,
+      "grad_norm": 2.9809741973876953,
+      "learning_rate": 1.8620617672459097e-05,
+      "loss": 0.1298,
+      "step": 373
+    },
+    {
+      "epoch": 0.2530446549391069,
+      "grad_norm": 6.16650915145874,
+      "learning_rate": 1.8608622436497657e-05,
+      "loss": 0.2405,
+      "step": 374
+    },
+    {
+      "epoch": 0.25372124492557513,
+      "grad_norm": 2.5345046520233154,
+      "learning_rate": 1.859657916861899e-05,
+      "loss": 0.1597,
+      "step": 375
+    },
+    {
+      "epoch": 0.2543978349120433,
+      "grad_norm": 4.540293216705322,
+      "learning_rate": 1.8584487936018663e-05,
+      "loss": 0.2112,
+      "step": 376
+    },
+    {
+      "epoch": 0.2550744248985115,
+      "grad_norm": 1.9297409057617188,
+      "learning_rate": 1.8572348806159857e-05,
+      "loss": 0.181,
+      "step": 377
+    },
+    {
+      "epoch": 0.2557510148849797,
+      "grad_norm": 2.586928606033325,
+      "learning_rate": 1.8560161846773002e-05,
+      "loss": 0.1348,
+      "step": 378
+    },
+    {
+      "epoch": 0.2564276048714479,
+      "grad_norm": 2.4230494499206543,
+      "learning_rate": 1.854792712585539e-05,
+      "loss": 0.1307,
+      "step": 379
+    },
+    {
+      "epoch": 0.2571041948579161,
+      "grad_norm": 3.1270833015441895,
+      "learning_rate": 1.8535644711670804e-05,
+      "loss": 0.1995,
+      "step": 380
+    },
+    {
+      "epoch": 0.2571041948579161,
+      "eval_accuracy": 0.773394495412844,
+      "eval_f1": 0.35509138381201044,
+      "eval_loss": 0.45505937933921814,
+      "eval_precision": 0.8,
+      "eval_recall": 0.22818791946308725,
+      "eval_runtime": 51.9893,
+      "eval_samples_per_second": 5.732,
+      "eval_steps_per_second": 0.192,
+      "step": 380
+    },
+    {
+      "epoch": 0.2577807848443843,
+      "grad_norm": 3.090973138809204,
+      "learning_rate": 1.8523314672749123e-05,
+      "loss": 0.1002,
+      "step": 381
+    },
+    {
+      "epoch": 0.2584573748308525,
+      "grad_norm": 2.197547197341919,
+      "learning_rate": 1.851093707788596e-05,
+      "loss": 0.1507,
+      "step": 382
+    },
+    {
+      "epoch": 0.2591339648173207,
+      "grad_norm": 3.1576650142669678,
+      "learning_rate": 1.8498511996142255e-05,
+      "loss": 0.1499,
+      "step": 383
+    },
+    {
+      "epoch": 0.2598105548037889,
+      "grad_norm": 4.379716396331787,
+      "learning_rate": 1.848603949684391e-05,
+      "loss": 0.1485,
+      "step": 384
+    },
+    {
+      "epoch": 0.2604871447902571,
+      "grad_norm": 3.0266523361206055,
+      "learning_rate": 1.8473519649581396e-05,
+      "loss": 0.1738,
+      "step": 385
+    },
+    {
+      "epoch": 0.26116373477672533,
+      "grad_norm": 4.019914627075195,
+      "learning_rate": 1.8460952524209355e-05,
+      "loss": 0.2077,
+      "step": 386
+    },
+    {
+      "epoch": 0.2618403247631935,
+      "grad_norm": 4.621005535125732,
+      "learning_rate": 1.844833819084622e-05,
+      "loss": 0.1384,
+      "step": 387
+    },
+    {
+      "epoch": 0.2625169147496617,
+      "grad_norm": 3.632671594619751,
+      "learning_rate": 1.8435676719873828e-05,
+      "loss": 0.1214,
+      "step": 388
+    },
+    {
+      "epoch": 0.2631935047361299,
+      "grad_norm": 6.161576271057129,
+      "learning_rate": 1.842296818193701e-05,
+      "loss": 0.2652,
+      "step": 389
+    },
+    {
+      "epoch": 0.2638700947225981,
+      "grad_norm": 2.499661922454834,
+      "learning_rate": 1.8410212647943215e-05,
+      "loss": 0.1611,
+      "step": 390
+    },
+    {
+      "epoch": 0.2645466847090663,
+      "grad_norm": 2.6793367862701416,
+      "learning_rate": 1.8397410189062106e-05,
+      "loss": 0.1301,
+      "step": 391
+    },
+    {
+      "epoch": 0.2652232746955345,
+      "grad_norm": 3.2850935459136963,
+      "learning_rate": 1.8384560876725163e-05,
+      "loss": 0.1692,
+      "step": 392
+    },
+    {
+      "epoch": 0.2658998646820027,
+      "grad_norm": 4.6707682609558105,
+      "learning_rate": 1.8371664782625287e-05,
+      "loss": 0.1819,
+      "step": 393
+    },
+    {
+      "epoch": 0.2665764546684709,
+      "grad_norm": 2.8113269805908203,
+      "learning_rate": 1.8358721978716398e-05,
+      "loss": 0.1587,
+      "step": 394
+    },
+    {
+      "epoch": 0.2672530446549391,
+      "grad_norm": 2.5062456130981445,
+      "learning_rate": 1.834573253721303e-05,
+      "loss": 0.1458,
+      "step": 395
+    },
+    {
+      "epoch": 0.2679296346414073,
+      "grad_norm": 4.038453102111816,
+      "learning_rate": 1.8332696530589936e-05,
+      "loss": 0.1954,
+      "step": 396
+    },
+    {
+      "epoch": 0.26860622462787553,
+      "grad_norm": 4.07120418548584,
+      "learning_rate": 1.831961403158168e-05,
+      "loss": 0.1479,
+      "step": 397
+    },
+    {
+      "epoch": 0.2692828146143437,
+      "grad_norm": 3.7134037017822266,
+      "learning_rate": 1.830648511318223e-05,
+      "loss": 0.1507,
+      "step": 398
+    },
+    {
+      "epoch": 0.2699594046008119,
+      "grad_norm": 4.160938739776611,
+      "learning_rate": 1.8293309848644554e-05,
+      "loss": 0.1709,
+      "step": 399
+    },
+    {
+      "epoch": 0.2706359945872801,
+      "grad_norm": 3.3158607482910156,
+      "learning_rate": 1.8280088311480203e-05,
+      "loss": 0.0761,
+      "step": 400
+    },
+    {
+      "epoch": 0.2706359945872801,
+      "eval_accuracy": 0.8073394495412844,
+      "eval_f1": 0.5161290322580645,
+      "eval_loss": 0.42147114872932434,
+      "eval_precision": 0.8235294117647058,
+      "eval_recall": 0.37583892617449666,
+      "eval_runtime": 51.945,
+      "eval_samples_per_second": 5.737,
+      "eval_steps_per_second": 0.193,
+      "step": 400
     }
   ],
   "logging_steps": 1,
@@ -2318,7 +3078,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.054635921978163e+16,
+  "total_flos": 1.2098518370798797e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null