Training in progress, step 700, checkpoint

last-checkpoint/optimizer_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d887d13337c308c5ca733d6323a9864415d8d7fdb689e7054b8b65fc58af94a6
+oid sha256:47369349058d9f265a07a2c0ef08b67452bffc5187fd4c745c4bac94546a6fe1
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b06daf412411fb1721690a1827cb6e1038a59c2d2dc7e7999d0561604a9799f2
+oid sha256:d50510b0f730cb5c824594a257dc78d9cd0f0f324db4149d578f71b4f5f6b523
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7aff80990d5d3dea0a8ba059b313ef8993ab8cddb3b3079270f3d150397961f
+oid sha256:b5c62ca5412596eb2cd44f1d5b0431527944d399ca97f86771a01c08e2bcdef8
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b2cfeefe6c41b4091cb2d5b0fdfa5ff9456b7db0f81ce256bdc2e5c5cfd9de5
+oid sha256:0436864f261cedc81f4c1934c7762f1c640c553dea76637d2c3365a5862998bb
 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:e6e7f5bf95c7024205a8119ce9bcf03a4fdd51aae9f436a0a35acb375bb3884b
+oid sha256:4d9ef70e9be95016e13a78937658f66404e8ede47727af102e7f241f7cf7ad77
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b48bfb689ef000812053e33e2dc970f52c5dd0b8bea9cda6777c2c298951a80
+oid sha256:ed14a8743524674aa130aa11171caec211afebea652849304a313fa02bc1e7b4
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:516752f1fbf9ee4f98d0697eb89075aa40a9ed64fdd213cf582c9b1a40cf8d2d
+oid sha256:fea02b7b1ee15158d6e0a23d9860f1c01ae8d91c79e2f7e42f8a04e7ef88ad41
 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:f5b0bde13b911b7337906544cf9c5bd2107b176fc7783ebbbad8f40ece936477
+oid sha256:9623875cc6f8148d10a3ff5e872de2c2987ad9473b4a6a560df1d8ef4e01a0f6
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cedc08212b07c1673536f40c11159242b59a9f0aadf57db9bad6f13ac81a6af
+oid sha256:eb98a3c24bcf7750fa7750f116a6d10d5ccebb8daba33a53a7f270b36b2ce893
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7218e38300ea7b9c89377dc67299aac317cf89fbd5fed41930f1224bfa1fab89
+oid sha256:9898bf1f7135405f4bbf1fe87622d1d22a7516940bda0af13d0cb131fe2777fc
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dd6521f2fc3283d23bd25a27f2810cab0424e95a40073d1ed6cfb13ed15dc2f
+oid sha256:407914c8984b50d2b06804e7b77fcfba533e794950feb19c63755a81cb2e26bb
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b47a7144b9ff045949aa91aea787001a456200397c8e845704484a0656bbbacc
+oid sha256:c3ea4cc6c9042fb168359b86795e303250effc227e0d4527d836efe07f4521a6
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cbab2b6a44c6ac01a6a8e4c5859b2a55eaebd5654b8efdeeaf69b4dbf690320
+oid sha256:c7b231cefd198a0bea4e7101f5c354fb7215e43b749b513c26e32fa2c6c06e95
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4059539918809202,
+  "epoch": 0.4736129905277402,
   "eval_steps": 20,
-  "global_step": 600,
+  "global_step": 700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4579,6 +4579,766 @@
       "eval_samples_per_second": 5.569,
       "eval_steps_per_second": 0.187,
       "step": 600
+    },
+    {
+      "epoch": 0.4066305818673884,
+      "grad_norm": 5.193844795227051,
+      "learning_rate": 1.4800968759183288e-05,
+      "loss": 0.1437,
+      "step": 601
+    },
+    {
+      "epoch": 0.40730717185385656,
+      "grad_norm": 4.853598117828369,
+      "learning_rate": 1.4780234680466792e-05,
+      "loss": 0.2045,
+      "step": 602
+    },
+    {
+      "epoch": 0.40798376184032475,
+      "grad_norm": 2.771559476852417,
+      "learning_rate": 1.4759473930370738e-05,
+      "loss": 0.0885,
+      "step": 603
+    },
+    {
+      "epoch": 0.40866035182679294,
+      "grad_norm": 2.854980945587158,
+      "learning_rate": 1.4738686624729987e-05,
+      "loss": 0.0996,
+      "step": 604
+    },
+    {
+      "epoch": 0.4093369418132612,
+      "grad_norm": 3.643080949783325,
+      "learning_rate": 1.4717872879527578e-05,
+      "loss": 0.1512,
+      "step": 605
+    },
+    {
+      "epoch": 0.4100135317997294,
+      "grad_norm": 3.83292555809021,
+      "learning_rate": 1.4697032810894062e-05,
+      "loss": 0.1761,
+      "step": 606
+    },
+    {
+      "epoch": 0.41069012178619757,
+      "grad_norm": 2.26672101020813,
+      "learning_rate": 1.4676166535106866e-05,
+      "loss": 0.116,
+      "step": 607
+    },
+    {
+      "epoch": 0.41136671177266576,
+      "grad_norm": 3.7530345916748047,
+      "learning_rate": 1.4655274168589635e-05,
+      "loss": 0.1392,
+      "step": 608
+    },
+    {
+      "epoch": 0.41204330175913395,
+      "grad_norm": 3.018079996109009,
+      "learning_rate": 1.463435582791159e-05,
+      "loss": 0.1159,
+      "step": 609
+    },
+    {
+      "epoch": 0.41271989174560214,
+      "grad_norm": 3.2969181537628174,
+      "learning_rate": 1.461341162978688e-05,
+      "loss": 0.2222,
+      "step": 610
+    },
+    {
+      "epoch": 0.4133964817320704,
+      "grad_norm": 4.386163711547852,
+      "learning_rate": 1.459244169107392e-05,
+      "loss": 0.1679,
+      "step": 611
+    },
+    {
+      "epoch": 0.4140730717185386,
+      "grad_norm": 3.1107709407806396,
+      "learning_rate": 1.4571446128774746e-05,
+      "loss": 0.0994,
+      "step": 612
+    },
+    {
+      "epoch": 0.41474966170500677,
+      "grad_norm": 4.727970600128174,
+      "learning_rate": 1.4550425060034367e-05,
+      "loss": 0.2336,
+      "step": 613
+    },
+    {
+      "epoch": 0.41542625169147496,
+      "grad_norm": 2.739393949508667,
+      "learning_rate": 1.4529378602140096e-05,
+      "loss": 0.1315,
+      "step": 614
+    },
+    {
+      "epoch": 0.41610284167794315,
+      "grad_norm": 3.5588788986206055,
+      "learning_rate": 1.4508306872520912e-05,
+      "loss": 0.128,
+      "step": 615
+    },
+    {
+      "epoch": 0.4167794316644114,
+      "grad_norm": 3.703800916671753,
+      "learning_rate": 1.4487209988746791e-05,
+      "loss": 0.1546,
+      "step": 616
+    },
+    {
+      "epoch": 0.4174560216508796,
+      "grad_norm": 4.310748100280762,
+      "learning_rate": 1.4466088068528068e-05,
+      "loss": 0.1225,
+      "step": 617
+    },
+    {
+      "epoch": 0.4181326116373478,
+      "grad_norm": 4.539455413818359,
+      "learning_rate": 1.444494122971476e-05,
+      "loss": 0.0978,
+      "step": 618
+    },
+    {
+      "epoch": 0.41880920162381596,
+      "grad_norm": 4.7135210037231445,
+      "learning_rate": 1.4423769590295917e-05,
+      "loss": 0.1628,
+      "step": 619
+    },
+    {
+      "epoch": 0.41948579161028415,
+      "grad_norm": 2.408241033554077,
+      "learning_rate": 1.4402573268398969e-05,
+      "loss": 0.1135,
+      "step": 620
+    },
+    {
+      "epoch": 0.41948579161028415,
+      "eval_accuracy": 0.8146788990825689,
+      "eval_f1": 0.5388127853881278,
+      "eval_loss": 0.4136140048503876,
+      "eval_precision": 0.8428571428571429,
+      "eval_recall": 0.3959731543624161,
+      "eval_runtime": 52.6653,
+      "eval_samples_per_second": 5.658,
+      "eval_steps_per_second": 0.19,
+      "step": 620
+    },
+    {
+      "epoch": 0.42016238159675234,
+      "grad_norm": 7.886865139007568,
+      "learning_rate": 1.4381352382289064e-05,
+      "loss": 0.2124,
+      "step": 621
+    },
+    {
+      "epoch": 0.4208389715832206,
+      "grad_norm": 4.534457206726074,
+      "learning_rate": 1.4360107050368403e-05,
+      "loss": 0.2076,
+      "step": 622
+    },
+    {
+      "epoch": 0.4215155615696888,
+      "grad_norm": 4.329330921173096,
+      "learning_rate": 1.4338837391175582e-05,
+      "loss": 0.1768,
+      "step": 623
+    },
+    {
+      "epoch": 0.42219215155615697,
+      "grad_norm": 4.343597412109375,
+      "learning_rate": 1.4317543523384928e-05,
+      "loss": 0.1652,
+      "step": 624
+    },
+    {
+      "epoch": 0.42286874154262516,
+      "grad_norm": 3.2291901111602783,
+      "learning_rate": 1.4296225565805854e-05,
+      "loss": 0.1808,
+      "step": 625
+    },
+    {
+      "epoch": 0.42354533152909335,
+      "grad_norm": 3.0291831493377686,
+      "learning_rate": 1.4274883637382162e-05,
+      "loss": 0.1375,
+      "step": 626
+    },
+    {
+      "epoch": 0.4242219215155616,
+      "grad_norm": 4.428736686706543,
+      "learning_rate": 1.4253517857191415e-05,
+      "loss": 0.125,
+      "step": 627
+    },
+    {
+      "epoch": 0.4248985115020298,
+      "grad_norm": 4.2908616065979,
+      "learning_rate": 1.4232128344444251e-05,
+      "loss": 0.2029,
+      "step": 628
+    },
+    {
+      "epoch": 0.425575101488498,
+      "grad_norm": 3.273651123046875,
+      "learning_rate": 1.4210715218483726e-05,
+      "loss": 0.156,
+      "step": 629
+    },
+    {
+      "epoch": 0.42625169147496617,
+      "grad_norm": 4.760056495666504,
+      "learning_rate": 1.4189278598784648e-05,
+      "loss": 0.1802,
+      "step": 630
+    },
+    {
+      "epoch": 0.42692828146143436,
+      "grad_norm": 4.106754302978516,
+      "learning_rate": 1.4167818604952906e-05,
+      "loss": 0.1104,
+      "step": 631
+    },
+    {
+      "epoch": 0.42760487144790255,
+      "grad_norm": 3.9572083950042725,
+      "learning_rate": 1.4146335356724803e-05,
+      "loss": 0.1584,
+      "step": 632
+    },
+    {
+      "epoch": 0.4282814614343708,
+      "grad_norm": 4.0582194328308105,
+      "learning_rate": 1.4124828973966393e-05,
+      "loss": 0.1678,
+      "step": 633
+    },
+    {
+      "epoch": 0.428958051420839,
+      "grad_norm": 3.1031177043914795,
+      "learning_rate": 1.410329957667281e-05,
+      "loss": 0.119,
+      "step": 634
+    },
+    {
+      "epoch": 0.42963464140730717,
+      "grad_norm": 6.854620456695557,
+      "learning_rate": 1.4081747284967602e-05,
+      "loss": 0.2084,
+      "step": 635
+    },
+    {
+      "epoch": 0.43031123139377536,
+      "grad_norm": 3.733327627182007,
+      "learning_rate": 1.4060172219102046e-05,
+      "loss": 0.0581,
+      "step": 636
+    },
+    {
+      "epoch": 0.43098782138024355,
+      "grad_norm": 6.749164581298828,
+      "learning_rate": 1.4038574499454496e-05,
+      "loss": 0.1663,
+      "step": 637
+    },
+    {
+      "epoch": 0.4316644113667118,
+      "grad_norm": 4.190524101257324,
+      "learning_rate": 1.4016954246529697e-05,
+      "loss": 0.1851,
+      "step": 638
+    },
+    {
+      "epoch": 0.43234100135318,
+      "grad_norm": 5.539178371429443,
+      "learning_rate": 1.3995311580958124e-05,
+      "loss": 0.1292,
+      "step": 639
+    },
+    {
+      "epoch": 0.4330175913396482,
+      "grad_norm": 3.6414852142333984,
+      "learning_rate": 1.3973646623495305e-05,
+      "loss": 0.1331,
+      "step": 640
+    },
+    {
+      "epoch": 0.4330175913396482,
+      "eval_accuracy": 0.791743119266055,
+      "eval_f1": 0.44226044226044225,
+      "eval_loss": 0.46029743552207947,
+      "eval_precision": 0.8256880733944955,
+      "eval_recall": 0.30201342281879195,
+      "eval_runtime": 52.6165,
+      "eval_samples_per_second": 5.664,
+      "eval_steps_per_second": 0.19,
+      "step": 640
+    },
+    {
+      "epoch": 0.43369418132611637,
+      "grad_norm": 2.1139845848083496,
+      "learning_rate": 1.395195949502114e-05,
+      "loss": 0.1142,
+      "step": 641
+    },
+    {
+      "epoch": 0.43437077131258456,
+      "grad_norm": 4.319032669067383,
+      "learning_rate": 1.3930250316539237e-05,
+      "loss": 0.1261,
+      "step": 642
+    },
+    {
+      "epoch": 0.43504736129905275,
+      "grad_norm": 6.74521017074585,
+      "learning_rate": 1.3908519209176227e-05,
+      "loss": 0.1988,
+      "step": 643
+    },
+    {
+      "epoch": 0.435723951285521,
+      "grad_norm": 4.900043487548828,
+      "learning_rate": 1.3886766294181105e-05,
+      "loss": 0.1694,
+      "step": 644
+    },
+    {
+      "epoch": 0.4364005412719892,
+      "grad_norm": 3.822930097579956,
+      "learning_rate": 1.3864991692924524e-05,
+      "loss": 0.1607,
+      "step": 645
+    },
+    {
+      "epoch": 0.4370771312584574,
+      "grad_norm": 6.831581115722656,
+      "learning_rate": 1.384319552689815e-05,
+      "loss": 0.1969,
+      "step": 646
+    },
+    {
+      "epoch": 0.43775372124492556,
+      "grad_norm": 4.031900405883789,
+      "learning_rate": 1.3821377917713969e-05,
+      "loss": 0.1413,
+      "step": 647
+    },
+    {
+      "epoch": 0.43843031123139375,
+      "grad_norm": 4.6610565185546875,
+      "learning_rate": 1.37995389871036e-05,
+      "loss": 0.1502,
+      "step": 648
+    },
+    {
+      "epoch": 0.439106901217862,
+      "grad_norm": 5.273025035858154,
+      "learning_rate": 1.3777678856917637e-05,
+      "loss": 0.1584,
+      "step": 649
+    },
+    {
+      "epoch": 0.4397834912043302,
+      "grad_norm": 4.015101909637451,
+      "learning_rate": 1.3755797649124944e-05,
+      "loss": 0.1968,
+      "step": 650
+    },
+    {
+      "epoch": 0.4404600811907984,
+      "grad_norm": 3.669017791748047,
+      "learning_rate": 1.3733895485812005e-05,
+      "loss": 0.1168,
+      "step": 651
+    },
+    {
+      "epoch": 0.44113667117726657,
+      "grad_norm": 4.213320732116699,
+      "learning_rate": 1.3711972489182208e-05,
+      "loss": 0.1717,
+      "step": 652
+    },
+    {
+      "epoch": 0.44181326116373476,
+      "grad_norm": 4.028888702392578,
+      "learning_rate": 1.369002878155519e-05,
+      "loss": 0.1231,
+      "step": 653
+    },
+    {
+      "epoch": 0.44248985115020295,
+      "grad_norm": 4.561563968658447,
+      "learning_rate": 1.366806448536615e-05,
+      "loss": 0.1529,
+      "step": 654
+    },
+    {
+      "epoch": 0.4431664411366712,
+      "grad_norm": 5.331336975097656,
+      "learning_rate": 1.3646079723165148e-05,
+      "loss": 0.1654,
+      "step": 655
+    },
+    {
+      "epoch": 0.4438430311231394,
+      "grad_norm": 3.651341199874878,
+      "learning_rate": 1.3624074617616443e-05,
+      "loss": 0.1898,
+      "step": 656
+    },
+    {
+      "epoch": 0.4445196211096076,
+      "grad_norm": 3.460707187652588,
+      "learning_rate": 1.3602049291497798e-05,
+      "loss": 0.132,
+      "step": 657
+    },
+    {
+      "epoch": 0.44519621109607577,
+      "grad_norm": 4.810662269592285,
+      "learning_rate": 1.3580003867699801e-05,
+      "loss": 0.2468,
+      "step": 658
+    },
+    {
+      "epoch": 0.44587280108254396,
+      "grad_norm": 3.721719264984131,
+      "learning_rate": 1.3557938469225167e-05,
+      "loss": 0.1419,
+      "step": 659
+    },
+    {
+      "epoch": 0.4465493910690122,
+      "grad_norm": 2.96408748626709,
+      "learning_rate": 1.3535853219188064e-05,
+      "loss": 0.1433,
+      "step": 660
+    },
+    {
+      "epoch": 0.4465493910690122,
+      "eval_accuracy": 0.7779816513761468,
+      "eval_f1": 0.35978835978835977,
+      "eval_loss": 0.45713141560554504,
+      "eval_precision": 0.85,
+      "eval_recall": 0.22818791946308725,
+      "eval_runtime": 52.7449,
+      "eval_samples_per_second": 5.65,
+      "eval_steps_per_second": 0.19,
+      "step": 660
+    },
+    {
+      "epoch": 0.4472259810554804,
+      "grad_norm": 4.556414604187012,
+      "learning_rate": 1.3513748240813429e-05,
+      "loss": 0.2081,
+      "step": 661
+    },
+    {
+      "epoch": 0.4479025710419486,
+      "grad_norm": 3.337388515472412,
+      "learning_rate": 1.349162365743626e-05,
+      "loss": 0.1469,
+      "step": 662
+    },
+    {
+      "epoch": 0.4485791610284168,
+      "grad_norm": 2.080909252166748,
+      "learning_rate": 1.3469479592500954e-05,
+      "loss": 0.084,
+      "step": 663
+    },
+    {
+      "epoch": 0.44925575101488496,
+      "grad_norm": 2.1243245601654053,
+      "learning_rate": 1.3447316169560593e-05,
+      "loss": 0.1212,
+      "step": 664
+    },
+    {
+      "epoch": 0.44993234100135315,
+      "grad_norm": 6.11072301864624,
+      "learning_rate": 1.3425133512276284e-05,
+      "loss": 0.18,
+      "step": 665
+    },
+    {
+      "epoch": 0.4506089309878214,
+      "grad_norm": 3.8702616691589355,
+      "learning_rate": 1.3402931744416432e-05,
+      "loss": 0.1654,
+      "step": 666
+    },
+    {
+      "epoch": 0.4512855209742896,
+      "grad_norm": 2.126553535461426,
+      "learning_rate": 1.3380710989856086e-05,
+      "loss": 0.0749,
+      "step": 667
+    },
+    {
+      "epoch": 0.4519621109607578,
+      "grad_norm": 3.0334889888763428,
+      "learning_rate": 1.3358471372576229e-05,
+      "loss": 0.1168,
+      "step": 668
+    },
+    {
+      "epoch": 0.45263870094722597,
+      "grad_norm": 4.436944484710693,
+      "learning_rate": 1.3336213016663078e-05,
+      "loss": 0.1849,
+      "step": 669
+    },
+    {
+      "epoch": 0.45331529093369416,
+      "grad_norm": 2.813225030899048,
+      "learning_rate": 1.3313936046307411e-05,
+      "loss": 0.0991,
+      "step": 670
+    },
+    {
+      "epoch": 0.4539918809201624,
+      "grad_norm": 4.604645729064941,
+      "learning_rate": 1.3291640585803869e-05,
+      "loss": 0.181,
+      "step": 671
+    },
+    {
+      "epoch": 0.4546684709066306,
+      "grad_norm": 4.593608379364014,
+      "learning_rate": 1.3269326759550252e-05,
+      "loss": 0.1916,
+      "step": 672
+    },
+    {
+      "epoch": 0.4553450608930988,
+      "grad_norm": 4.45982551574707,
+      "learning_rate": 1.3246994692046837e-05,
+      "loss": 0.1576,
+      "step": 673
+    },
+    {
+      "epoch": 0.456021650879567,
+      "grad_norm": 3.094189167022705,
+      "learning_rate": 1.3224644507895672e-05,
+      "loss": 0.137,
+      "step": 674
+    },
+    {
+      "epoch": 0.45669824086603517,
+      "grad_norm": 4.386197090148926,
+      "learning_rate": 1.320227633179989e-05,
+      "loss": 0.1798,
+      "step": 675
+    },
+    {
+      "epoch": 0.45737483085250336,
+      "grad_norm": 6.814380168914795,
+      "learning_rate": 1.3179890288563015e-05,
+      "loss": 0.1869,
+      "step": 676
+    },
+    {
+      "epoch": 0.4580514208389716,
+      "grad_norm": 3.6425650119781494,
+      "learning_rate": 1.3157486503088255e-05,
+      "loss": 0.0971,
+      "step": 677
+    },
+    {
+      "epoch": 0.4587280108254398,
+      "grad_norm": 4.681551933288574,
+      "learning_rate": 1.3135065100377816e-05,
+      "loss": 0.1818,
+      "step": 678
+    },
+    {
+      "epoch": 0.459404600811908,
+      "grad_norm": 2.930051803588867,
+      "learning_rate": 1.3112626205532189e-05,
+      "loss": 0.1051,
+      "step": 679
+    },
+    {
+      "epoch": 0.46008119079837617,
+      "grad_norm": 4.322526454925537,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 0.1372,
+      "step": 680
+    },
+    {
+      "epoch": 0.46008119079837617,
+      "eval_accuracy": 0.8018348623853211,
+      "eval_f1": 0.4881516587677725,
+      "eval_loss": 0.4219379127025604,
+      "eval_precision": 0.8306451612903226,
+      "eval_recall": 0.34563758389261745,
+      "eval_runtime": 53.1579,
+      "eval_samples_per_second": 5.606,
+      "eval_steps_per_second": 0.188,
+      "step": 680
+    },
+    {
+      "epoch": 0.46075778078484436,
+      "grad_norm": 6.767197132110596,
+      "learning_rate": 1.3067696440324671e-05,
+      "loss": 0.2199,
+      "step": 681
+    },
+    {
+      "epoch": 0.4614343707713126,
+      "grad_norm": 6.519789218902588,
+      "learning_rate": 1.3045205820648969e-05,
+      "loss": 0.1482,
+      "step": 682
+    },
+    {
+      "epoch": 0.4621109607577808,
+      "grad_norm": 5.150829792022705,
+      "learning_rate": 1.3022698210209069e-05,
+      "loss": 0.1252,
+      "step": 683
+    },
+    {
+      "epoch": 0.462787550744249,
+      "grad_norm": 3.6090028285980225,
+      "learning_rate": 1.3000173734586461e-05,
+      "loss": 0.1423,
+      "step": 684
+    },
+    {
+      "epoch": 0.4634641407307172,
+      "grad_norm": 3.7701938152313232,
+      "learning_rate": 1.2977632519456745e-05,
+      "loss": 0.1346,
+      "step": 685
+    },
+    {
+      "epoch": 0.46414073071718537,
+      "grad_norm": 2.650648355484009,
+      "learning_rate": 1.295507469058891e-05,
+      "loss": 0.1563,
+      "step": 686
+    },
+    {
+      "epoch": 0.4648173207036536,
+      "grad_norm": 3.0055038928985596,
+      "learning_rate": 1.293250037384465e-05,
+      "loss": 0.12,
+      "step": 687
+    },
+    {
+      "epoch": 0.4654939106901218,
+      "grad_norm": 3.10675311088562,
+      "learning_rate": 1.2909909695177647e-05,
+      "loss": 0.1294,
+      "step": 688
+    },
+    {
+      "epoch": 0.46617050067659,
+      "grad_norm": 3.340036630630493,
+      "learning_rate": 1.2887302780632876e-05,
+      "loss": 0.1208,
+      "step": 689
+    },
+    {
+      "epoch": 0.4668470906630582,
+      "grad_norm": 3.540969133377075,
+      "learning_rate": 1.2864679756345905e-05,
+      "loss": 0.1568,
+      "step": 690
+    },
+    {
+      "epoch": 0.4675236806495264,
+      "grad_norm": 2.290696620941162,
+      "learning_rate": 1.284204074854218e-05,
+      "loss": 0.0659,
+      "step": 691
+    },
+    {
+      "epoch": 0.46820027063599456,
+      "grad_norm": 2.736776351928711,
+      "learning_rate": 1.2819385883536332e-05,
+      "loss": 0.1017,
+      "step": 692
+    },
+    {
+      "epoch": 0.4688768606224628,
+      "grad_norm": 4.793468952178955,
+      "learning_rate": 1.2796715287731463e-05,
+      "loss": 0.1693,
+      "step": 693
+    },
+    {
+      "epoch": 0.469553450608931,
+      "grad_norm": 5.424515724182129,
+      "learning_rate": 1.2774029087618448e-05,
+      "loss": 0.2241,
+      "step": 694
+    },
+    {
+      "epoch": 0.4702300405953992,
+      "grad_norm": 3.8648910522460938,
+      "learning_rate": 1.2751327409775227e-05,
+      "loss": 0.1706,
+      "step": 695
+    },
+    {
+      "epoch": 0.4709066305818674,
+      "grad_norm": 5.154799461364746,
+      "learning_rate": 1.2728610380866097e-05,
+      "loss": 0.1878,
+      "step": 696
+    },
+    {
+      "epoch": 0.47158322056833557,
+      "grad_norm": 4.5547261238098145,
+      "learning_rate": 1.2705878127641007e-05,
+      "loss": 0.1794,
+      "step": 697
+    },
+    {
+      "epoch": 0.4722598105548038,
+      "grad_norm": 4.59852409362793,
+      "learning_rate": 1.268313077693485e-05,
+      "loss": 0.1402,
+      "step": 698
+    },
+    {
+      "epoch": 0.472936400541272,
+      "grad_norm": 3.0397305488586426,
+      "learning_rate": 1.2660368455666752e-05,
+      "loss": 0.1126,
+      "step": 699
+    },
+    {
+      "epoch": 0.4736129905277402,
+      "grad_norm": 2.698749303817749,
+      "learning_rate": 1.2637591290839377e-05,
+      "loss": 0.0677,
+      "step": 700
+    },
+    {
+      "epoch": 0.4736129905277402,
+      "eval_accuracy": 0.7990825688073394,
+      "eval_f1": 0.46973365617433416,
+      "eval_loss": 0.442281574010849,
+      "eval_precision": 0.8434782608695652,
+      "eval_recall": 0.32550335570469796,
+      "eval_runtime": 52.9641,
+      "eval_samples_per_second": 5.626,
+      "eval_steps_per_second": 0.189,
+      "step": 700
     }
   ],
   "logging_steps": 1,
@@ -4598,7 +5358,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.81775286403072e+17,
+  "total_flos": 2.1229008750379008e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null