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:d23824b3f642ae1c179f034608cd4b9f408d94d0f7fcb6cf1a4e20079b004e8c
+oid sha256:cf7f67d9c042a84566934bd461b320cae0199732bb35359e255b7014ef617231
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be21c5803484f0c4c0b0b4a16dbac528d0b5af1bd54d4586f3265080760294dc
+oid sha256:dbbdf5aa0c917d01262e7411790cb24667f76fa9d67155ab04bc58157a6c767c
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10500e9d5fe4432017d4802187cbc53c3d8e66cefb65b9df41e5b265ac7d3904
+oid sha256:ef074ecfe582d897c9f3e81908752da0466d5934adf9a851faaf9e6814a9aeb6
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd93fdfd38d485f3348d1401133ef3b5e8b9f318176a54d6a3de17e87a0cc244
+oid sha256:aab23bd2247244b7a9dac60183f440b8c1080e92bc625235610beea7c9109ec1
 size 13990904

last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d2d7f1f9c14930a0fe7b92e49a1a38aedb2f9b0b32cf2680ed384f5ea215db8
+oid sha256:9f7657557a389aa95493c296a136a17c26d7b20b6d42a6dfb304c1e8688ff232
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15f402b6d71f018c886c5b84826d5e72c63f77c6a19da8dfa4d1d2ae32c239cb
+oid sha256:ccc3e8f8d918ce66f701d481f767aed188a52ab74cd5386fb5f5f72c4ff6812b
 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:be1fa2d26d651df333ec36a0c11ff0a77d307383f8747a1e9b552d6a8c33f7d8
+oid sha256:513807ff9476886e4d2d2466c76e27875cd5ce88e3c22995487a03109afdc40d
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1880f07905fc31b9ac52835ef69014867a49aee88680a57b62a19264452b89c6
+oid sha256:cfe46ce5d210d66c96204628bd011e7c341fdbc9aab78fcbae2b8bc9c7d728bc
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a59db3724fd4bbce6ad60141d8e9b678e2c788fb1955c6c880b0f571d42b391
+oid sha256:1ba0e620538f416517936a3eab6524a32e98b6f57a853685e89d95c7534e1b02
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bf84d01b70a9160a4096ae20f0ffd66ca31c1e463be8b3c7a205beb67b59d79
+oid sha256:07bfe832d1e9096039f344c8603706dbf51d8a2520da53b6fb91c2a831e3c65c
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fe1aa7e3e5012afa45a34124a8768ba80f30f03a36c3082e890c6fec80f5130
+oid sha256:f806da0a270ca93d00536c431b16e74277199f672ba1a254a8c26faa0eba661b
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7971cf1ed3ade754f5376f0be2af02ca9956ac66a79f39ece9d08be9961f719f
+oid sha256:6a4acd0e09a01d2645011aa7cce0fbe01327e6aa40a58caa03b7a2ab1d8edd4a
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e43838c246602506a97d56d7f86c5c26c0b2b1f2b549429b3935fd043d6ac6c6
+oid sha256:eec0e04ded29cd8ec06d62d5d3cb5cc31918a604e3f09bfe3483ed17956fbbe9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5565862708719852,
+  "epoch": 0.6493506493506493,
   "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": 5.737,
       "eval_steps_per_second": 0.187,
       "step": 600
+    },
+    {
+      "epoch": 0.5575139146567718,
+      "grad_norm": 4.177931308746338,
+      "learning_rate": 9.740928564316369e-06,
+      "loss": 0.1734,
+      "step": 601
+    },
+    {
+      "epoch": 0.5584415584415584,
+      "grad_norm": 6.294393062591553,
+      "learning_rate": 9.708553297322407e-06,
+      "loss": 0.1923,
+      "step": 602
+    },
+    {
+      "epoch": 0.5593692022263451,
+      "grad_norm": 3.275909662246704,
+      "learning_rate": 9.676181087466444e-06,
+      "loss": 0.1662,
+      "step": 603
+    },
+    {
+      "epoch": 0.5602968460111317,
+      "grad_norm": 3.7851905822753906,
+      "learning_rate": 9.643812274317644e-06,
+      "loss": 0.1521,
+      "step": 604
+    },
+    {
+      "epoch": 0.5612244897959183,
+      "grad_norm": 4.724743366241455,
+      "learning_rate": 9.611447197409544e-06,
+      "loss": 0.1713,
+      "step": 605
+    },
+    {
+      "epoch": 0.562152133580705,
+      "grad_norm": 6.553765773773193,
+      "learning_rate": 9.579086196236483e-06,
+      "loss": 0.1596,
+      "step": 606
+    },
+    {
+      "epoch": 0.5630797773654916,
+      "grad_norm": 3.5295910835266113,
+      "learning_rate": 9.54672961025005e-06,
+      "loss": 0.1436,
+      "step": 607
+    },
+    {
+      "epoch": 0.5640074211502782,
+      "grad_norm": 4.828715801239014,
+      "learning_rate": 9.514377778855521e-06,
+      "loss": 0.2361,
+      "step": 608
+    },
+    {
+      "epoch": 0.564935064935065,
+      "grad_norm": 6.0731072425842285,
+      "learning_rate": 9.482031041408296e-06,
+      "loss": 0.165,
+      "step": 609
+    },
+    {
+      "epoch": 0.5658627087198516,
+      "grad_norm": 8.083799362182617,
+      "learning_rate": 9.449689737210352e-06,
+      "loss": 0.1995,
+      "step": 610
+    },
+    {
+      "epoch": 0.5667903525046383,
+      "grad_norm": 3.7561042308807373,
+      "learning_rate": 9.417354205506663e-06,
+      "loss": 0.214,
+      "step": 611
+    },
+    {
+      "epoch": 0.5677179962894249,
+      "grad_norm": 4.848057746887207,
+      "learning_rate": 9.385024785481653e-06,
+      "loss": 0.2019,
+      "step": 612
+    },
+    {
+      "epoch": 0.5686456400742115,
+      "grad_norm": 5.188536167144775,
+      "learning_rate": 9.352701816255643e-06,
+      "loss": 0.1568,
+      "step": 613
+    },
+    {
+      "epoch": 0.5695732838589982,
+      "grad_norm": 2.897571325302124,
+      "learning_rate": 9.320385636881283e-06,
+      "loss": 0.1241,
+      "step": 614
+    },
+    {
+      "epoch": 0.5705009276437848,
+      "grad_norm": 5.466006278991699,
+      "learning_rate": 9.288076586340005e-06,
+      "loss": 0.195,
+      "step": 615
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 3.484766960144043,
+      "learning_rate": 9.255775003538462e-06,
+      "loss": 0.1419,
+      "step": 616
+    },
+    {
+      "epoch": 0.5723562152133581,
+      "grad_norm": 5.067159175872803,
+      "learning_rate": 9.22348122730497e-06,
+      "loss": 0.1938,
+      "step": 617
+    },
+    {
+      "epoch": 0.5732838589981447,
+      "grad_norm": 4.161076545715332,
+      "learning_rate": 9.19119559638596e-06,
+      "loss": 0.1925,
+      "step": 618
+    },
+    {
+      "epoch": 0.5742115027829313,
+      "grad_norm": 3.2418394088745117,
+      "learning_rate": 9.158918449442425e-06,
+      "loss": 0.1592,
+      "step": 619
+    },
+    {
+      "epoch": 0.575139146567718,
+      "grad_norm": 5.799723148345947,
+      "learning_rate": 9.126650125046361e-06,
+      "loss": 0.1655,
+      "step": 620
+    },
+    {
+      "epoch": 0.575139146567718,
+      "eval_accuracy": 0.835920177383592,
+      "eval_f1": 0.6224489795918368,
+      "eval_loss": 0.3387525677680969,
+      "eval_precision": 0.8776978417266187,
+      "eval_recall": 0.48221343873517786,
+      "eval_runtime": 47.1826,
+      "eval_samples_per_second": 5.85,
+      "eval_steps_per_second": 0.191,
+      "step": 620
+    },
+    {
+      "epoch": 0.5760667903525046,
+      "grad_norm": 4.049962997436523,
+      "learning_rate": 9.094390961677223e-06,
+      "loss": 0.1364,
+      "step": 621
+    },
+    {
+      "epoch": 0.5769944341372912,
+      "grad_norm": 3.7945103645324707,
+      "learning_rate": 9.062141297718372e-06,
+      "loss": 0.18,
+      "step": 622
+    },
+    {
+      "epoch": 0.577922077922078,
+      "grad_norm": 3.9919049739837646,
+      "learning_rate": 9.02990147145352e-06,
+      "loss": 0.1833,
+      "step": 623
+    },
+    {
+      "epoch": 0.5788497217068646,
+      "grad_norm": 2.300546407699585,
+      "learning_rate": 8.99767182106319e-06,
+      "loss": 0.0625,
+      "step": 624
+    },
+    {
+      "epoch": 0.5797773654916512,
+      "grad_norm": 4.982729911804199,
+      "learning_rate": 8.965452684621164e-06,
+      "loss": 0.1884,
+      "step": 625
+    },
+    {
+      "epoch": 0.5807050092764379,
+      "grad_norm": 4.047850131988525,
+      "learning_rate": 8.933244400090937e-06,
+      "loss": 0.1206,
+      "step": 626
+    },
+    {
+      "epoch": 0.5816326530612245,
+      "grad_norm": 4.123579978942871,
+      "learning_rate": 8.901047305322172e-06,
+      "loss": 0.1503,
+      "step": 627
+    },
+    {
+      "epoch": 0.5825602968460112,
+      "grad_norm": 4.2010273933410645,
+      "learning_rate": 8.868861738047158e-06,
+      "loss": 0.1311,
+      "step": 628
+    },
+    {
+      "epoch": 0.5834879406307978,
+      "grad_norm": 4.511427402496338,
+      "learning_rate": 8.836688035877268e-06,
+      "loss": 0.1521,
+      "step": 629
+    },
+    {
+      "epoch": 0.5844155844155844,
+      "grad_norm": 5.0462775230407715,
+      "learning_rate": 8.804526536299413e-06,
+      "loss": 0.1746,
+      "step": 630
+    },
+    {
+      "epoch": 0.5853432282003711,
+      "grad_norm": 6.308788299560547,
+      "learning_rate": 8.772377576672502e-06,
+      "loss": 0.2369,
+      "step": 631
+    },
+    {
+      "epoch": 0.5862708719851577,
+      "grad_norm": 4.165151596069336,
+      "learning_rate": 8.740241494223911e-06,
+      "loss": 0.2034,
+      "step": 632
+    },
+    {
+      "epoch": 0.5871985157699443,
+      "grad_norm": 4.502403259277344,
+      "learning_rate": 8.708118626045939e-06,
+      "loss": 0.1893,
+      "step": 633
+    },
+    {
+      "epoch": 0.588126159554731,
+      "grad_norm": 3.4875142574310303,
+      "learning_rate": 8.676009309092273e-06,
+      "loss": 0.1328,
+      "step": 634
+    },
+    {
+      "epoch": 0.5890538033395176,
+      "grad_norm": 4.179616928100586,
+      "learning_rate": 8.643913880174449e-06,
+      "loss": 0.1466,
+      "step": 635
+    },
+    {
+      "epoch": 0.5899814471243042,
+      "grad_norm": 3.073174476623535,
+      "learning_rate": 8.611832675958335e-06,
+      "loss": 0.1269,
+      "step": 636
+    },
+    {
+      "epoch": 0.5909090909090909,
+      "grad_norm": 3.9491851329803467,
+      "learning_rate": 8.579766032960582e-06,
+      "loss": 0.1247,
+      "step": 637
+    },
+    {
+      "epoch": 0.5918367346938775,
+      "grad_norm": 3.502418041229248,
+      "learning_rate": 8.5477142875451e-06,
+      "loss": 0.1536,
+      "step": 638
+    },
+    {
+      "epoch": 0.5927643784786641,
+      "grad_norm": 5.294571876525879,
+      "learning_rate": 8.515677775919528e-06,
+      "loss": 0.213,
+      "step": 639
+    },
+    {
+      "epoch": 0.5936920222634509,
+      "grad_norm": 3.3282008171081543,
+      "learning_rate": 8.48365683413172e-06,
+      "loss": 0.1468,
+      "step": 640
+    },
+    {
+      "epoch": 0.5936920222634509,
+      "eval_accuracy": 0.8592017738359202,
+      "eval_f1": 0.7093821510297483,
+      "eval_loss": 0.3021511137485504,
+      "eval_precision": 0.842391304347826,
+      "eval_recall": 0.6126482213438735,
+      "eval_runtime": 46.8153,
+      "eval_samples_per_second": 5.896,
+      "eval_steps_per_second": 0.192,
+      "step": 640
+    },
+    {
+      "epoch": 0.5946196660482375,
+      "grad_norm": 5.158597946166992,
+      "learning_rate": 8.451651798066203e-06,
+      "loss": 0.2459,
+      "step": 641
+    },
+    {
+      "epoch": 0.5955473098330241,
+      "grad_norm": 7.210265159606934,
+      "learning_rate": 8.419663003440657e-06,
+      "loss": 0.1745,
+      "step": 642
+    },
+    {
+      "epoch": 0.5964749536178108,
+      "grad_norm": 4.469946384429932,
+      "learning_rate": 8.387690785802403e-06,
+      "loss": 0.1879,
+      "step": 643
+    },
+    {
+      "epoch": 0.5974025974025974,
+      "grad_norm": 3.5130228996276855,
+      "learning_rate": 8.355735480524874e-06,
+      "loss": 0.1453,
+      "step": 644
+    },
+    {
+      "epoch": 0.5983302411873841,
+      "grad_norm": 3.8892977237701416,
+      "learning_rate": 8.3237974228041e-06,
+      "loss": 0.1852,
+      "step": 645
+    },
+    {
+      "epoch": 0.5992578849721707,
+      "grad_norm": 4.912310600280762,
+      "learning_rate": 8.291876947655197e-06,
+      "loss": 0.1595,
+      "step": 646
+    },
+    {
+      "epoch": 0.6001855287569573,
+      "grad_norm": 3.8313469886779785,
+      "learning_rate": 8.259974389908842e-06,
+      "loss": 0.1207,
+      "step": 647
+    },
+    {
+      "epoch": 0.601113172541744,
+      "grad_norm": 4.376918792724609,
+      "learning_rate": 8.228090084207773e-06,
+      "loss": 0.2188,
+      "step": 648
+    },
+    {
+      "epoch": 0.6020408163265306,
+      "grad_norm": 4.086894989013672,
+      "learning_rate": 8.196224365003267e-06,
+      "loss": 0.1806,
+      "step": 649
+    },
+    {
+      "epoch": 0.6029684601113172,
+      "grad_norm": 2.9185261726379395,
+      "learning_rate": 8.16437756655164e-06,
+      "loss": 0.1301,
+      "step": 650
+    },
+    {
+      "epoch": 0.6038961038961039,
+      "grad_norm": 5.638646125793457,
+      "learning_rate": 8.132550022910737e-06,
+      "loss": 0.2069,
+      "step": 651
+    },
+    {
+      "epoch": 0.6048237476808905,
+      "grad_norm": 6.044648170471191,
+      "learning_rate": 8.100742067936432e-06,
+      "loss": 0.2543,
+      "step": 652
+    },
+    {
+      "epoch": 0.6057513914656771,
+      "grad_norm": 5.261450290679932,
+      "learning_rate": 8.068954035279121e-06,
+      "loss": 0.1861,
+      "step": 653
+    },
+    {
+      "epoch": 0.6066790352504638,
+      "grad_norm": 2.6060245037078857,
+      "learning_rate": 8.037186258380226e-06,
+      "loss": 0.1102,
+      "step": 654
+    },
+    {
+      "epoch": 0.6076066790352505,
+      "grad_norm": 5.192462921142578,
+      "learning_rate": 8.005439070468692e-06,
+      "loss": 0.1196,
+      "step": 655
+    },
+    {
+      "epoch": 0.608534322820037,
+      "grad_norm": 4.267360210418701,
+      "learning_rate": 7.9737128045575e-06,
+      "loss": 0.1549,
+      "step": 656
+    },
+    {
+      "epoch": 0.6094619666048238,
+      "grad_norm": 2.9216721057891846,
+      "learning_rate": 7.942007793440165e-06,
+      "loss": 0.1326,
+      "step": 657
+    },
+    {
+      "epoch": 0.6103896103896104,
+      "grad_norm": 3.592209577560425,
+      "learning_rate": 7.91032436968725e-06,
+      "loss": 0.1399,
+      "step": 658
+    },
+    {
+      "epoch": 0.6113172541743971,
+      "grad_norm": 3.6594440937042236,
+      "learning_rate": 7.87866286564288e-06,
+      "loss": 0.1223,
+      "step": 659
+    },
+    {
+      "epoch": 0.6122448979591837,
+      "grad_norm": 6.019983291625977,
+      "learning_rate": 7.847023613421251e-06,
+      "loss": 0.1421,
+      "step": 660
+    },
+    {
+      "epoch": 0.6122448979591837,
+      "eval_accuracy": 0.843680709534368,
+      "eval_f1": 0.6483790523690773,
+      "eval_loss": 0.3296959400177002,
+      "eval_precision": 0.8783783783783784,
+      "eval_recall": 0.5138339920948617,
+      "eval_runtime": 47.6918,
+      "eval_samples_per_second": 5.787,
+      "eval_steps_per_second": 0.189,
+      "step": 660
+    },
+    {
+      "epoch": 0.6131725417439703,
+      "grad_norm": 3.82082462310791,
+      "learning_rate": 7.815406944903148e-06,
+      "loss": 0.1369,
+      "step": 661
+    },
+    {
+      "epoch": 0.614100185528757,
+      "grad_norm": 3.763209819793701,
+      "learning_rate": 7.78381319173246e-06,
+      "loss": 0.1345,
+      "step": 662
+    },
+    {
+      "epoch": 0.6150278293135436,
+      "grad_norm": 5.018528938293457,
+      "learning_rate": 7.752242685312709e-06,
+      "loss": 0.1762,
+      "step": 663
+    },
+    {
+      "epoch": 0.6159554730983302,
+      "grad_norm": 3.500230073928833,
+      "learning_rate": 7.720695756803569e-06,
+      "loss": 0.0632,
+      "step": 664
+    },
+    {
+      "epoch": 0.6168831168831169,
+      "grad_norm": 4.73206090927124,
+      "learning_rate": 7.689172737117389e-06,
+      "loss": 0.1771,
+      "step": 665
+    },
+    {
+      "epoch": 0.6178107606679035,
+      "grad_norm": 5.639405250549316,
+      "learning_rate": 7.657673956915735e-06,
+      "loss": 0.2544,
+      "step": 666
+    },
+    {
+      "epoch": 0.6187384044526901,
+      "grad_norm": 4.007811546325684,
+      "learning_rate": 7.6261997466059035e-06,
+      "loss": 0.1547,
+      "step": 667
+    },
+    {
+      "epoch": 0.6196660482374768,
+      "grad_norm": 4.930268287658691,
+      "learning_rate": 7.594750436337467e-06,
+      "loss": 0.1426,
+      "step": 668
+    },
+    {
+      "epoch": 0.6205936920222634,
+      "grad_norm": 5.008491516113281,
+      "learning_rate": 7.5633263559988035e-06,
+      "loss": 0.1129,
+      "step": 669
+    },
+    {
+      "epoch": 0.62152133580705,
+      "grad_norm": 3.0749435424804688,
+      "learning_rate": 7.531927835213657e-06,
+      "loss": 0.1166,
+      "step": 670
+    },
+    {
+      "epoch": 0.6224489795918368,
+      "grad_norm": 5.739880084991455,
+      "learning_rate": 7.500555203337647e-06,
+      "loss": 0.1634,
+      "step": 671
+    },
+    {
+      "epoch": 0.6233766233766234,
+      "grad_norm": 3.3177554607391357,
+      "learning_rate": 7.469208789454838e-06,
+      "loss": 0.1388,
+      "step": 672
+    },
+    {
+      "epoch": 0.62430426716141,
+      "grad_norm": 4.005073070526123,
+      "learning_rate": 7.4378889223742766e-06,
+      "loss": 0.1429,
+      "step": 673
+    },
+    {
+      "epoch": 0.6252319109461967,
+      "grad_norm": 4.268346786499023,
+      "learning_rate": 7.40659593062655e-06,
+      "loss": 0.187,
+      "step": 674
+    },
+    {
+      "epoch": 0.6261595547309833,
+      "grad_norm": 6.763199329376221,
+      "learning_rate": 7.375330142460331e-06,
+      "loss": 0.2241,
+      "step": 675
+    },
+    {
+      "epoch": 0.62708719851577,
+      "grad_norm": 3.3440911769866943,
+      "learning_rate": 7.344091885838949e-06,
+      "loss": 0.1407,
+      "step": 676
+    },
+    {
+      "epoch": 0.6280148423005566,
+      "grad_norm": 5.204977035522461,
+      "learning_rate": 7.312881488436928e-06,
+      "loss": 0.2322,
+      "step": 677
+    },
+    {
+      "epoch": 0.6289424860853432,
+      "grad_norm": 4.433789253234863,
+      "learning_rate": 7.2816992776365714e-06,
+      "loss": 0.1657,
+      "step": 678
+    },
+    {
+      "epoch": 0.6298701298701299,
+      "grad_norm": 4.035289287567139,
+      "learning_rate": 7.250545580524515e-06,
+      "loss": 0.1994,
+      "step": 679
+    },
+    {
+      "epoch": 0.6307977736549165,
+      "grad_norm": 4.986621856689453,
+      "learning_rate": 7.219420723888301e-06,
+      "loss": 0.2483,
+      "step": 680
+    },
+    {
+      "epoch": 0.6307977736549165,
+      "eval_accuracy": 0.852549889135255,
+      "eval_f1": 0.6855791962174941,
+      "eval_loss": 0.30598554015159607,
+      "eval_precision": 0.8529411764705882,
+      "eval_recall": 0.5731225296442688,
+      "eval_runtime": 46.8299,
+      "eval_samples_per_second": 5.894,
+      "eval_steps_per_second": 0.192,
+      "step": 680
+    },
+    {
+      "epoch": 0.6317254174397031,
+      "grad_norm": 5.635754108428955,
+      "learning_rate": 7.188325034212944e-06,
+      "loss": 0.2133,
+      "step": 681
+    },
+    {
+      "epoch": 0.6326530612244898,
+      "grad_norm": 6.280815601348877,
+      "learning_rate": 7.157258837677514e-06,
+      "loss": 0.2312,
+      "step": 682
+    },
+    {
+      "epoch": 0.6335807050092764,
+      "grad_norm": 2.508446455001831,
+      "learning_rate": 7.126222460151719e-06,
+      "loss": 0.1189,
+      "step": 683
+    },
+    {
+      "epoch": 0.634508348794063,
+      "grad_norm": 3.8485682010650635,
+      "learning_rate": 7.095216227192467e-06,
+      "loss": 0.1505,
+      "step": 684
+    },
+    {
+      "epoch": 0.6354359925788498,
+      "grad_norm": 3.7377712726593018,
+      "learning_rate": 7.064240464040472e-06,
+      "loss": 0.129,
+      "step": 685
+    },
+    {
+      "epoch": 0.6363636363636364,
+      "grad_norm": 3.6466944217681885,
+      "learning_rate": 7.033295495616834e-06,
+      "loss": 0.1457,
+      "step": 686
+    },
+    {
+      "epoch": 0.637291280148423,
+      "grad_norm": 4.0310564041137695,
+      "learning_rate": 7.002381646519625e-06,
+      "loss": 0.1739,
+      "step": 687
+    },
+    {
+      "epoch": 0.6382189239332097,
+      "grad_norm": 6.287572860717773,
+      "learning_rate": 6.971499241020495e-06,
+      "loss": 0.1513,
+      "step": 688
+    },
+    {
+      "epoch": 0.6391465677179963,
+      "grad_norm": 5.086080551147461,
+      "learning_rate": 6.940648603061263e-06,
+      "loss": 0.2203,
+      "step": 689
+    },
+    {
+      "epoch": 0.640074211502783,
+      "grad_norm": 3.155775785446167,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 0.1288,
+      "step": 690
+    },
+    {
+      "epoch": 0.6410018552875696,
+      "grad_norm": 4.002538204193115,
+      "learning_rate": 6.8790439238602576e-06,
+      "loss": 0.1526,
+      "step": 691
+    },
+    {
+      "epoch": 0.6419294990723562,
+      "grad_norm": 5.535161972045898,
+      "learning_rate": 6.848290528822417e-06,
+      "loss": 0.2223,
+      "step": 692
+    },
+    {
+      "epoch": 0.6428571428571429,
+      "grad_norm": 4.103289604187012,
+      "learning_rate": 6.8175701937255645e-06,
+      "loss": 0.1831,
+      "step": 693
+    },
+    {
+      "epoch": 0.6437847866419295,
+      "grad_norm": 4.057906150817871,
+      "learning_rate": 6.786883240811479e-06,
+      "loss": 0.1619,
+      "step": 694
+    },
+    {
+      "epoch": 0.6447124304267161,
+      "grad_norm": 2.6124215126037598,
+      "learning_rate": 6.756229991971779e-06,
+      "loss": 0.0988,
+      "step": 695
+    },
+    {
+      "epoch": 0.6456400742115028,
+      "grad_norm": 3.484631061553955,
+      "learning_rate": 6.725610768744535e-06,
+      "loss": 0.1127,
+      "step": 696
+    },
+    {
+      "epoch": 0.6465677179962894,
+      "grad_norm": 3.0936501026153564,
+      "learning_rate": 6.695025892310913e-06,
+      "loss": 0.1455,
+      "step": 697
+    },
+    {
+      "epoch": 0.647495361781076,
+      "grad_norm": 3.7610599994659424,
+      "learning_rate": 6.664475683491797e-06,
+      "loss": 0.1725,
+      "step": 698
+    },
+    {
+      "epoch": 0.6484230055658627,
+      "grad_norm": 3.537524700164795,
+      "learning_rate": 6.633960462744415e-06,
+      "loss": 0.1971,
+      "step": 699
+    },
+    {
+      "epoch": 0.6493506493506493,
+      "grad_norm": 4.47899055480957,
+      "learning_rate": 6.603480550158995e-06,
+      "loss": 0.1411,
+      "step": 700
+    },
+    {
+      "epoch": 0.6493506493506493,
+      "eval_accuracy": 0.8481152993348116,
+      "eval_f1": 0.6714628297362111,
+      "eval_loss": 0.31714314222335815,
+      "eval_precision": 0.8536585365853658,
+      "eval_recall": 0.5533596837944664,
+      "eval_runtime": 47.2966,
+      "eval_samples_per_second": 5.836,
+      "eval_steps_per_second": 0.19,
+      "step": 700
     }
   ],
   "logging_steps": 1,
@@ -4598,7 +5358,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.915741517465518e+17,
+  "total_flos": 2.238292485640028e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null