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:cf29adef47a01f1839db50f74f3247c91da91a41c58aa795577895d88d9fd52b
+oid sha256:795b7f6b14618c8d2f3126c050c747db33847a0d58bd5aee9fd555d8072054d4
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b5d78fe467d251682a62c692c21198dafddffa8c672df52612cc8e4b6156620
+oid sha256:ca055109122571586c2a64df4ff7cbfe48d022bc8722566c0895ac272edc3c78
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35796afb68607d9adcbab1d83a0007262ca1b06caaa26bba58abdb19f3c35355
+oid sha256:86c3c549ce130a9ab4d45068f1c63e35984edd9e565e1205374afe3fd1bd9f49
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f31a17cd26d9f1fa1d4eaeb54a063bff932151bd52c8c1cd1bba07cae159890b
+oid sha256:0b1101f8377361468d680d48119c20867c8d300a96337536353857f42fd2abf3
 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:b98669d63178d36bef48e8bad3c756d88df76cdef5d65588e3af93712104f538
+oid sha256:e9eeccce1ea7069a8e741721cfd0ff7753c42789e7631b2bb13751b0262b8471
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:967170b82471e089ed052ab22a0c331238ebb23d2221614787a6f6ac1252d950
+oid sha256:66d3c3983e0244f589f3c97391149136519c0ae2cb30573bc57afef1b7fecaa9
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02beb45b7cbcb185ea348fe1e71987bdab500dc5954ee0c3606facdbdb689400
+oid sha256:c3cccf70ced1d6c40e4cd73d50ab8d98ca34680aa33a692208ccd7e3f14b89ff
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d4e1f6f46c84432b86962fbca8f956b4f076b39f4d3facfbc3ebef94918ea06
+oid sha256:4e67188121d44320e3e4446d495eac2f4a44fb1b8839c93a496a50e5e6ce242b
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0e0229b85afd4f35b3b5458b93d1937fdd318fc246ecebb318cd10752250782
+oid sha256:a48a7b3dc91adc39858108306f7d4532b1fd3e6514365ab372dc62dfd9ee10e2
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:102b853708827c3c7a6a0bc88e434e5b85b7b7b32e20c9466253c20500e6e241
+oid sha256:be021af7b36e06a7835029caab84a249be037bdd789560931d603f08da17b1cf
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83390b28446e79697a8dfb75c559ff4a99e20ec31914dfa2a2fd3049e6e8c112
+oid sha256:3b4a02e9af72c5cebb6c447096e61f1d87135b21700c6e8b096a268a56e20c67
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:413496f937c9d56ec6060523d7c58fc1d2904315b979054640d1b736b9dbb9da
+oid sha256:3549f26e113bbe422032c22e335cbabac24ad3593e9e3e43ecfa59c401538f39
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:453f10a1cf1c53aacfd897b6d5502ea8618466960f769bb5692fceebd23d5be8
+oid sha256:4910675856682caf109c9ff6535f1bae50ae0cf757d7603f89fd4ad22523009c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7425742574257426,
+  "epoch": 0.9900990099009901,
   "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": 5.405,
       "eval_steps_per_second": 0.176,
       "step": 300
+    },
+    {
+      "epoch": 0.745049504950495,
+      "grad_norm": 2.5315749645233154,
+      "learning_rate": 3.7168901335157313e-06,
+      "loss": 0.2213,
+      "step": 301
+    },
+    {
+      "epoch": 0.7475247524752475,
+      "grad_norm": 2.8023202419281006,
+      "learning_rate": 3.6497973361246153e-06,
+      "loss": 0.1547,
+      "step": 302
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 1.9556550979614258,
+      "learning_rate": 3.583180171067101e-06,
+      "loss": 0.1629,
+      "step": 303
+    },
+    {
+      "epoch": 0.7524752475247525,
+      "grad_norm": 2.5738537311553955,
+      "learning_rate": 3.517043627991441e-06,
+      "loss": 0.2262,
+      "step": 304
+    },
+    {
+      "epoch": 0.754950495049505,
+      "grad_norm": 2.6422410011291504,
+      "learning_rate": 3.4513926605471504e-06,
+      "loss": 0.2188,
+      "step": 305
+    },
+    {
+      "epoch": 0.7574257425742574,
+      "grad_norm": 2.3228068351745605,
+      "learning_rate": 3.3862321860139578e-06,
+      "loss": 0.1769,
+      "step": 306
+    },
+    {
+      "epoch": 0.7599009900990099,
+      "grad_norm": 2.501941680908203,
+      "learning_rate": 3.3215670849335156e-06,
+      "loss": 0.1984,
+      "step": 307
+    },
+    {
+      "epoch": 0.7623762376237624,
+      "grad_norm": 2.3544158935546875,
+      "learning_rate": 3.257402200743821e-06,
+      "loss": 0.1806,
+      "step": 308
+    },
+    {
+      "epoch": 0.7648514851485149,
+      "grad_norm": 2.6395740509033203,
+      "learning_rate": 3.19374233941647e-06,
+      "loss": 0.232,
+      "step": 309
+    },
+    {
+      "epoch": 0.7673267326732673,
+      "grad_norm": 2.306347608566284,
+      "learning_rate": 3.1305922690966705e-06,
+      "loss": 0.1799,
+      "step": 310
+    },
+    {
+      "epoch": 0.7698019801980198,
+      "grad_norm": 2.154937744140625,
+      "learning_rate": 3.0679567197461135e-06,
+      "loss": 0.2044,
+      "step": 311
+    },
+    {
+      "epoch": 0.7722772277227723,
+      "grad_norm": 3.7053334712982178,
+      "learning_rate": 3.005840382788685e-06,
+      "loss": 0.2634,
+      "step": 312
+    },
+    {
+      "epoch": 0.7747524752475248,
+      "grad_norm": 2.617936134338379,
+      "learning_rate": 2.944247910759097e-06,
+      "loss": 0.1606,
+      "step": 313
+    },
+    {
+      "epoch": 0.7772277227722773,
+      "grad_norm": 2.9620141983032227,
+      "learning_rate": 2.8831839169543998e-06,
+      "loss": 0.2267,
+      "step": 314
+    },
+    {
+      "epoch": 0.7797029702970297,
+      "grad_norm": 2.768303871154785,
+      "learning_rate": 2.8226529750884403e-06,
+      "loss": 0.1704,
+      "step": 315
+    },
+    {
+      "epoch": 0.7821782178217822,
+      "grad_norm": 2.5790133476257324,
+      "learning_rate": 2.7626596189492983e-06,
+      "loss": 0.249,
+      "step": 316
+    },
+    {
+      "epoch": 0.7846534653465347,
+      "grad_norm": 3.070465326309204,
+      "learning_rate": 2.7032083420597e-06,
+      "loss": 0.2035,
+      "step": 317
+    },
+    {
+      "epoch": 0.7871287128712872,
+      "grad_norm": 2.414353132247925,
+      "learning_rate": 2.6443035973404497e-06,
+      "loss": 0.1941,
+      "step": 318
+    },
+    {
+      "epoch": 0.7896039603960396,
+      "grad_norm": 3.1308748722076416,
+      "learning_rate": 2.585949796776912e-06,
+      "loss": 0.2452,
+      "step": 319
+    },
+    {
+      "epoch": 0.7920792079207921,
+      "grad_norm": 2.4484174251556396,
+      "learning_rate": 2.528151311088537e-06,
+      "loss": 0.1693,
+      "step": 320
+    },
+    {
+      "epoch": 0.7920792079207921,
+      "eval_accuracy": 0.852549889135255,
+      "eval_f1": 0.6825775656324582,
+      "eval_loss": 0.3095855712890625,
+      "eval_precision": 0.8614457831325302,
+      "eval_recall": 0.5652173913043478,
+      "eval_runtime": 47.4637,
+      "eval_samples_per_second": 5.815,
+      "eval_steps_per_second": 0.19,
+      "step": 320
+    },
+    {
+      "epoch": 0.7945544554455446,
+      "grad_norm": 2.0847697257995605,
+      "learning_rate": 2.470912469401512e-06,
+      "loss": 0.188,
+      "step": 321
+    },
+    {
+      "epoch": 0.7970297029702971,
+      "grad_norm": 2.2349650859832764,
+      "learning_rate": 2.414237558924496e-06,
+      "loss": 0.2171,
+      "step": 322
+    },
+    {
+      "epoch": 0.7995049504950495,
+      "grad_norm": 2.6552979946136475,
+      "learning_rate": 2.3581308246275103e-06,
+      "loss": 0.2226,
+      "step": 323
+    },
+    {
+      "epoch": 0.801980198019802,
+      "grad_norm": 3.2933454513549805,
+      "learning_rate": 2.302596468923981e-06,
+      "loss": 0.2393,
+      "step": 324
+    },
+    {
+      "epoch": 0.8044554455445545,
+      "grad_norm": 1.8228425979614258,
+      "learning_rate": 2.247638651355991e-06,
+      "loss": 0.1736,
+      "step": 325
+    },
+    {
+      "epoch": 0.806930693069307,
+      "grad_norm": 2.241750717163086,
+      "learning_rate": 2.1932614882827196e-06,
+      "loss": 0.2001,
+      "step": 326
+    },
+    {
+      "epoch": 0.8094059405940595,
+      "grad_norm": 2.1382362842559814,
+      "learning_rate": 2.1394690525721275e-06,
+      "loss": 0.1589,
+      "step": 327
+    },
+    {
+      "epoch": 0.8118811881188119,
+      "grad_norm": 2.5019314289093018,
+      "learning_rate": 2.0862653732958914e-06,
+      "loss": 0.1956,
+      "step": 328
+    },
+    {
+      "epoch": 0.8143564356435643,
+      "grad_norm": 2.254096031188965,
+      "learning_rate": 2.03365443542764e-06,
+      "loss": 0.1756,
+      "step": 329
+    },
+    {
+      "epoch": 0.8168316831683168,
+      "grad_norm": 3.644157648086548,
+      "learning_rate": 1.9816401795444664e-06,
+      "loss": 0.1899,
+      "step": 330
+    },
+    {
+      "epoch": 0.8193069306930693,
+      "grad_norm": 4.284032821655273,
+      "learning_rate": 1.93022650153178e-06,
+      "loss": 0.2255,
+      "step": 331
+    },
+    {
+      "epoch": 0.8217821782178217,
+      "grad_norm": 2.941634178161621,
+      "learning_rate": 1.8794172522915022e-06,
+      "loss": 0.2145,
+      "step": 332
+    },
+    {
+      "epoch": 0.8242574257425742,
+      "grad_norm": 3.4567208290100098,
+      "learning_rate": 1.829216237453637e-06,
+      "loss": 0.2454,
+      "step": 333
+    },
+    {
+      "epoch": 0.8267326732673267,
+      "grad_norm": 2.781095266342163,
+      "learning_rate": 1.7796272170912255e-06,
+      "loss": 0.2079,
+      "step": 334
+    },
+    {
+      "epoch": 0.8292079207920792,
+      "grad_norm": 2.1246063709259033,
+      "learning_rate": 1.730653905438714e-06,
+      "loss": 0.1863,
+      "step": 335
+    },
+    {
+      "epoch": 0.8316831683168316,
+      "grad_norm": 4.239376544952393,
+      "learning_rate": 1.6822999706137565e-06,
+      "loss": 0.2692,
+      "step": 336
+    },
+    {
+      "epoch": 0.8341584158415841,
+      "grad_norm": 2.4231953620910645,
+      "learning_rate": 1.6345690343424758e-06,
+      "loss": 0.2056,
+      "step": 337
+    },
+    {
+      "epoch": 0.8366336633663366,
+      "grad_norm": 2.665325164794922,
+      "learning_rate": 1.587464671688187e-06,
+      "loss": 0.2059,
+      "step": 338
+    },
+    {
+      "epoch": 0.8391089108910891,
+      "grad_norm": 2.3466625213623047,
+      "learning_rate": 1.540990410783636e-06,
+      "loss": 0.1975,
+      "step": 339
+    },
+    {
+      "epoch": 0.8415841584158416,
+      "grad_norm": 2.3948047161102295,
+      "learning_rate": 1.495149732566723e-06,
+      "loss": 0.1752,
+      "step": 340
+    },
+    {
+      "epoch": 0.8415841584158416,
+      "eval_accuracy": 0.8503325942350333,
+      "eval_f1": 0.6778042959427207,
+      "eval_loss": 0.310843825340271,
+      "eval_precision": 0.8554216867469879,
+      "eval_recall": 0.5612648221343873,
+      "eval_runtime": 48.401,
+      "eval_samples_per_second": 5.702,
+      "eval_steps_per_second": 0.186,
+      "step": 340
+    },
+    {
+      "epoch": 0.844059405940594,
+      "grad_norm": 2.258780002593994,
+      "learning_rate": 1.4499460705198e-06,
+      "loss": 0.1835,
+      "step": 341
+    },
+    {
+      "epoch": 0.8465346534653465,
+      "grad_norm": 2.5925920009613037,
+      "learning_rate": 1.4053828104124867e-06,
+      "loss": 0.2227,
+      "step": 342
+    },
+    {
+      "epoch": 0.849009900990099,
+      "grad_norm": 2.6612229347229004,
+      "learning_rate": 1.361463290048085e-06,
+      "loss": 0.1727,
+      "step": 343
+    },
+    {
+      "epoch": 0.8514851485148515,
+      "grad_norm": 2.3652000427246094,
+      "learning_rate": 1.3181907990135624e-06,
+      "loss": 0.1721,
+      "step": 344
+    },
+    {
+      "epoch": 0.8539603960396039,
+      "grad_norm": 2.8514909744262695,
+      "learning_rate": 1.2755685784331784e-06,
+      "loss": 0.1989,
+      "step": 345
+    },
+    {
+      "epoch": 0.8564356435643564,
+      "grad_norm": 2.7124602794647217,
+      "learning_rate": 1.2335998207257138e-06,
+      "loss": 0.2231,
+      "step": 346
+    },
+    {
+      "epoch": 0.8589108910891089,
+      "grad_norm": 3.1221795082092285,
+      "learning_rate": 1.1922876693653584e-06,
+      "loss": 0.2332,
+      "step": 347
+    },
+    {
+      "epoch": 0.8613861386138614,
+      "grad_norm": 3.280951738357544,
+      "learning_rate": 1.1516352186462588e-06,
+      "loss": 0.2876,
+      "step": 348
+    },
+    {
+      "epoch": 0.8638613861386139,
+      "grad_norm": 3.1071383953094482,
+      "learning_rate": 1.1116455134507665e-06,
+      "loss": 0.2009,
+      "step": 349
+    },
+    {
+      "epoch": 0.8663366336633663,
+      "grad_norm": 2.82293438911438,
+      "learning_rate": 1.0723215490213635e-06,
+      "loss": 0.1922,
+      "step": 350
+    },
+    {
+      "epoch": 0.8688118811881188,
+      "grad_norm": 2.4002768993377686,
+      "learning_rate": 1.0336662707363287e-06,
+      "loss": 0.185,
+      "step": 351
+    },
+    {
+      "epoch": 0.8712871287128713,
+      "grad_norm": 2.6212666034698486,
+      "learning_rate": 9.95682573889114e-07,
+      "loss": 0.1864,
+      "step": 352
+    },
+    {
+      "epoch": 0.8737623762376238,
+      "grad_norm": 2.9787867069244385,
+      "learning_rate": 9.583733034714982e-07,
+      "loss": 0.2573,
+      "step": 353
+    },
+    {
+      "epoch": 0.8762376237623762,
+      "grad_norm": 2.4197521209716797,
+      "learning_rate": 9.217412539604942e-07,
+      "loss": 0.1921,
+      "step": 354
+    },
+    {
+      "epoch": 0.8787128712871287,
+      "grad_norm": 2.3588428497314453,
+      "learning_rate": 8.857891691090336e-07,
+      "loss": 0.1531,
+      "step": 355
+    },
+    {
+      "epoch": 0.8811881188118812,
+      "grad_norm": 3.0741777420043945,
+      "learning_rate": 8.505197417404687e-07,
+      "loss": 0.1766,
+      "step": 356
+    },
+    {
+      "epoch": 0.8836633663366337,
+      "grad_norm": 2.2599122524261475,
+      "learning_rate": 8.159356135468721e-07,
+      "loss": 0.1667,
+      "step": 357
+    },
+    {
+      "epoch": 0.8861386138613861,
+      "grad_norm": 2.859726667404175,
+      "learning_rate": 7.820393748911792e-07,
+      "loss": 0.1559,
+      "step": 358
+    },
+    {
+      "epoch": 0.8886138613861386,
+      "grad_norm": 3.204777717590332,
+      "learning_rate": 7.488335646131628e-07,
+      "loss": 0.1982,
+      "step": 359
+    },
+    {
+      "epoch": 0.8910891089108911,
+      "grad_norm": 2.8709557056427,
+      "learning_rate": 7.163206698392744e-07,
+      "loss": 0.2353,
+      "step": 360
+    },
+    {
+      "epoch": 0.8910891089108911,
+      "eval_accuracy": 0.8592017738359202,
+      "eval_f1": 0.703962703962704,
+      "eval_loss": 0.30721068382263184,
+      "eval_precision": 0.8579545454545454,
+      "eval_recall": 0.5968379446640316,
+      "eval_runtime": 47.4337,
+      "eval_samples_per_second": 5.819,
+      "eval_steps_per_second": 0.19,
+      "step": 360
+    },
+    {
+      "epoch": 0.8935643564356436,
+      "grad_norm": 2.5089986324310303,
+      "learning_rate": 6.845031257963619e-07,
+      "loss": 0.1982,
+      "step": 361
+    },
+    {
+      "epoch": 0.8960396039603961,
+      "grad_norm": 3.298999071121216,
+      "learning_rate": 6.53383315629268e-07,
+      "loss": 0.223,
+      "step": 362
+    },
+    {
+      "epoch": 0.8985148514851485,
+      "grad_norm": 2.1518023014068604,
+      "learning_rate": 6.229635702223325e-07,
+      "loss": 0.1817,
+      "step": 363
+    },
+    {
+      "epoch": 0.900990099009901,
+      "grad_norm": 2.3566782474517822,
+      "learning_rate": 5.932461680248014e-07,
+      "loss": 0.1671,
+      "step": 364
+    },
+    {
+      "epoch": 0.9034653465346535,
+      "grad_norm": 2.9410693645477295,
+      "learning_rate": 5.64233334880181e-07,
+      "loss": 0.2491,
+      "step": 365
+    },
+    {
+      "epoch": 0.905940594059406,
+      "grad_norm": 3.5622243881225586,
+      "learning_rate": 5.359272438595153e-07,
+      "loss": 0.1792,
+      "step": 366
+    },
+    {
+      "epoch": 0.9084158415841584,
+      "grad_norm": 3.029758930206299,
+      "learning_rate": 5.083300150986259e-07,
+      "loss": 0.2021,
+      "step": 367
+    },
+    {
+      "epoch": 0.9108910891089109,
+      "grad_norm": 2.3247830867767334,
+      "learning_rate": 4.814437156393048e-07,
+      "loss": 0.1533,
+      "step": 368
+    },
+    {
+      "epoch": 0.9133663366336634,
+      "grad_norm": 2.890040397644043,
+      "learning_rate": 4.5527035927450337e-07,
+      "loss": 0.1625,
+      "step": 369
+    },
+    {
+      "epoch": 0.9158415841584159,
+      "grad_norm": 2.3857712745666504,
+      "learning_rate": 4.298119063974915e-07,
+      "loss": 0.1879,
+      "step": 370
+    },
+    {
+      "epoch": 0.9183168316831684,
+      "grad_norm": 3.242441177368164,
+      "learning_rate": 4.0507026385502747e-07,
+      "loss": 0.1903,
+      "step": 371
+    },
+    {
+      "epoch": 0.9207920792079208,
+      "grad_norm": 3.2090890407562256,
+      "learning_rate": 3.810472848045266e-07,
+      "loss": 0.2244,
+      "step": 372
+    },
+    {
+      "epoch": 0.9232673267326733,
+      "grad_norm": 3.073902130126953,
+      "learning_rate": 3.5774476857527107e-07,
+      "loss": 0.1832,
+      "step": 373
+    },
+    {
+      "epoch": 0.9257425742574258,
+      "grad_norm": 2.3574068546295166,
+      "learning_rate": 3.3516446053363015e-07,
+      "loss": 0.1447,
+      "step": 374
+    },
+    {
+      "epoch": 0.9282178217821783,
+      "grad_norm": 2.8709933757781982,
+      "learning_rate": 3.1330805195233684e-07,
+      "loss": 0.1463,
+      "step": 375
+    },
+    {
+      "epoch": 0.9306930693069307,
+      "grad_norm": 2.224475145339966,
+      "learning_rate": 2.921771798838069e-07,
+      "loss": 0.176,
+      "step": 376
+    },
+    {
+      "epoch": 0.9331683168316832,
+      "grad_norm": 3.6477129459381104,
+      "learning_rate": 2.717734270375272e-07,
+      "loss": 0.2283,
+      "step": 377
+    },
+    {
+      "epoch": 0.9356435643564357,
+      "grad_norm": 2.706246852874756,
+      "learning_rate": 2.520983216615047e-07,
+      "loss": 0.1814,
+      "step": 378
+    },
+    {
+      "epoch": 0.9381188118811881,
+      "grad_norm": 2.5630269050598145,
+      "learning_rate": 2.3315333742780942e-07,
+      "loss": 0.2032,
+      "step": 379
+    },
+    {
+      "epoch": 0.9405940594059405,
+      "grad_norm": 2.807539224624634,
+      "learning_rate": 2.1493989332218468e-07,
+      "loss": 0.1984,
+      "step": 380
+    },
+    {
+      "epoch": 0.9405940594059405,
+      "eval_accuracy": 0.8603104212860311,
+      "eval_f1": 0.705607476635514,
+      "eval_loss": 0.3077787458896637,
+      "eval_precision": 0.8628571428571429,
+      "eval_recall": 0.5968379446640316,
+      "eval_runtime": 48.5537,
+      "eval_samples_per_second": 5.684,
+      "eval_steps_per_second": 0.185,
+      "step": 380
+    },
+    {
+      "epoch": 0.943069306930693,
+      "grad_norm": 2.647665500640869,
+      "learning_rate": 1.9745935353777222e-07,
+      "loss": 0.2097,
+      "step": 381
+    },
+    {
+      "epoch": 0.9455445544554455,
+      "grad_norm": 2.421297073364258,
+      "learning_rate": 1.8071302737293294e-07,
+      "loss": 0.1927,
+      "step": 382
+    },
+    {
+      "epoch": 0.948019801980198,
+      "grad_norm": 2.902292013168335,
+      "learning_rate": 1.6470216913317628e-07,
+      "loss": 0.1959,
+      "step": 383
+    },
+    {
+      "epoch": 0.9504950495049505,
+      "grad_norm": 2.626032829284668,
+      "learning_rate": 1.4942797803721543e-07,
+      "loss": 0.1819,
+      "step": 384
+    },
+    {
+      "epoch": 0.9529702970297029,
+      "grad_norm": 2.454671859741211,
+      "learning_rate": 1.348915981271437e-07,
+      "loss": 0.1633,
+      "step": 385
+    },
+    {
+      "epoch": 0.9554455445544554,
+      "grad_norm": 2.038083076477051,
+      "learning_rate": 1.2109411818274851e-07,
+      "loss": 0.1411,
+      "step": 386
+    },
+    {
+      "epoch": 0.9579207920792079,
+      "grad_norm": 2.438631534576416,
+      "learning_rate": 1.0803657163995896e-07,
+      "loss": 0.1856,
+      "step": 387
+    },
+    {
+      "epoch": 0.9603960396039604,
+      "grad_norm": 2.0666630268096924,
+      "learning_rate": 9.571993651343869e-08,
+      "loss": 0.1592,
+      "step": 388
+    },
+    {
+      "epoch": 0.9628712871287128,
+      "grad_norm": 3.7644968032836914,
+      "learning_rate": 8.41451353233369e-08,
+      "loss": 0.2209,
+      "step": 389
+    },
+    {
+      "epoch": 0.9653465346534653,
+      "grad_norm": 2.5671634674072266,
+      "learning_rate": 7.331303502618903e-08,
+      "loss": 0.2061,
+      "step": 390
+    },
+    {
+      "epoch": 0.9678217821782178,
+      "grad_norm": 3.664409875869751,
+      "learning_rate": 6.32244469499832e-08,
+      "loss": 0.2457,
+      "step": 391
+    },
+    {
+      "epoch": 0.9702970297029703,
+      "grad_norm": 2.5305821895599365,
+      "learning_rate": 5.388012673338661e-08,
+      "loss": 0.2001,
+      "step": 392
+    },
+    {
+      "epoch": 0.9727722772277227,
+      "grad_norm": 2.4124999046325684,
+      "learning_rate": 4.528077426915412e-08,
+      "loss": 0.1909,
+      "step": 393
+    },
+    {
+      "epoch": 0.9752475247524752,
+      "grad_norm": 2.562199115753174,
+      "learning_rate": 3.7427033651702414e-08,
+      "loss": 0.2031,
+      "step": 394
+    },
+    {
+      "epoch": 0.9777227722772277,
+      "grad_norm": 3.321256399154663,
+      "learning_rate": 3.03194931288664e-08,
+      "loss": 0.2142,
+      "step": 395
+    },
+    {
+      "epoch": 0.9801980198019802,
+      "grad_norm": 2.6344470977783203,
+      "learning_rate": 2.3958685057844378e-08,
+      "loss": 0.1949,
+      "step": 396
+    },
+    {
+      "epoch": 0.9826732673267327,
+      "grad_norm": 2.2917704582214355,
+      "learning_rate": 1.83450858653178e-08,
+      "loss": 0.1938,
+      "step": 397
+    },
+    {
+      "epoch": 0.9851485148514851,
+      "grad_norm": 2.6536812782287598,
+      "learning_rate": 1.3479116011769766e-08,
+      "loss": 0.2173,
+      "step": 398
+    },
+    {
+      "epoch": 0.9876237623762376,
+      "grad_norm": 2.857429027557373,
+      "learning_rate": 9.361139959993549e-09,
+      "loss": 0.2062,
+      "step": 399
+    },
+    {
+      "epoch": 0.9900990099009901,
+      "grad_norm": 2.745120048522949,
+      "learning_rate": 5.991466147791114e-09,
+      "loss": 0.2194,
+      "step": 400
+    },
+    {
+      "epoch": 0.9900990099009901,
+      "eval_accuracy": 0.8592017738359202,
+      "eval_f1": 0.703962703962704,
+      "eval_loss": 0.3067491054534912,
+      "eval_precision": 0.8579545454545454,
+      "eval_recall": 0.5968379446640316,
+      "eval_runtime": 48.0292,
+      "eval_samples_per_second": 5.747,
+      "eval_steps_per_second": 0.187,
+      "step": 400
     }
   ],
   "logging_steps": 1,
@@ -2318,7 +3078,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.8390793726407475e+17,
+  "total_flos": 2.454079047550894e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null