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 sha256:99da1138da71c7a590a2707e483883e957340e06dae08b8827f18835c34a64b4
+oid sha256:b8a9b5df6415cf6aaf2fbd963784ca2798906e60cec2a4d96cedf776b0170bd5
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79c4ba664980c19c5ef3783c79e3d4e043fca5bb4c60f89d82faac7a943cf243
+oid sha256:a477ffe7b31b769212a07b084cb1d6fd6244ebaf19a4d7d0e204d6e487b1aa1c
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f424fd03327ecb5ff630a9df1d98261931fcdfc83c1716e339b348d51df7d478
+oid sha256:67bf1d290ebbe8581c52d47ca6e510d907a2305a5eebfef589fed6462f44754f
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a13d0c056d2946548a4902bc1af045b538f2ae540c6e2ef689c1bb7482253a0
+oid sha256:863d7a925082ef890f7e9f5fe37f69a475fb3c8a749f7db0ba29e80f4b2757d1
 size 13990904

last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b31287f991033846081b020484b6de0532ffe6b03b8cf50698e3f201f2e56e9
+oid sha256:44f0fee06777bc54d20e8cfadf02e1fcf062878ec77c27273222f443590d3ca7
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82e80cce203211b2c2441e9d6c1bb6224c0d09baf614394b407b0f9ce1ded28a
+oid sha256:b6b4dadb656bd2f818f65eedb04bde289d144e274b64e185d6aa6038f82edc5b
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e7beb1931987579881f896dde9404f4b409e252ef531ece93cbf739876254fe
+oid sha256:6714a698672b2edbe18148b125be564081dbe0c32820c4d2862c9ebbfc701d39
 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:ddb5450bd834dd38bde6c77563d509a72456d15718acf61980ebcccc75aef710
+oid sha256:f9f0d3ac60ec2c909466305ff9424e3153bb7f95f5b685220572eb0bd2fe45e0
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae91bbe4bb3448f9fe588b5f12c6d570f98cbeb7f79c6b4c021fdd413e35a673
+oid sha256:e6a53af4113d719a74be72b9b96e06ddfcf589f1c186482a58b06d91bc3e4d34
 size 15088

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5e2bdfc538b632be76938bdc369215d9c9e9696454b505d6d5c099a19d59619
+oid sha256:e3f79573df50dcf97b1bf70e5483cf9597da1b8a05214eb274fc3c3833cf3ad5
 size 15088

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:654f94a53cbd3a4c0aa96462f7eefb36cea6a40f65967f82f41333fe8d59b3e6
+oid sha256:f80c1cfb5ea86276cd48dd4a859d36d824a2fd5563d437a8a0c4be3eb6200b32
 size 15088

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24ee86115e5e887f663c435c280ac37373efa53275c443e874691073017d1363
+oid sha256:714110b482b507e1fb6219bf62e8ec1001b632b03d77db23a105560f7b48af04
 size 15088

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b85ee37d9a532de8cdb09f3a64e5b2fe9e638521f567e2b493ae4f1f2c3b0617
+oid sha256:9b38c3c47d3e1cfb698a7e53778b8d216b765546387a9e6bd3f149bea8249062
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7731958762886598,
+  "epoch": 0.9020618556701031,
   "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": 5.446,
       "eval_steps_per_second": 0.18,
       "step": 600
+    },
+    {
+      "epoch": 0.7744845360824743,
+      "grad_norm": 0.12384779006242752,
+      "learning_rate": 2.944862984597068e-06,
+      "loss": 0.0006,
+      "step": 601
+    },
+    {
+      "epoch": 0.7757731958762887,
+      "grad_norm": 0.06338214129209518,
+      "learning_rate": 2.913037202447625e-06,
+      "loss": 0.0003,
+      "step": 602
+    },
+    {
+      "epoch": 0.7770618556701031,
+      "grad_norm": 1.3061492443084717,
+      "learning_rate": 2.8813549852137824e-06,
+      "loss": 0.0066,
+      "step": 603
+    },
+    {
+      "epoch": 0.7783505154639175,
+      "grad_norm": 0.06470157206058502,
+      "learning_rate": 2.8498169747014824e-06,
+      "loss": 0.0005,
+      "step": 604
+    },
+    {
+      "epoch": 0.779639175257732,
+      "grad_norm": 1.6503907442092896,
+      "learning_rate": 2.818423809795384e-06,
+      "loss": 0.0081,
+      "step": 605
+    },
+    {
+      "epoch": 0.7809278350515464,
+      "grad_norm": 1.9376052618026733,
+      "learning_rate": 2.787176126445923e-06,
+      "loss": 0.0147,
+      "step": 606
+    },
+    {
+      "epoch": 0.7822164948453608,
+      "grad_norm": 2.6921439170837402,
+      "learning_rate": 2.756074557656424e-06,
+      "loss": 0.0037,
+      "step": 607
+    },
+    {
+      "epoch": 0.7835051546391752,
+      "grad_norm": 0.5326633453369141,
+      "learning_rate": 2.725119733470284e-06,
+      "loss": 0.0017,
+      "step": 608
+    },
+    {
+      "epoch": 0.7847938144329897,
+      "grad_norm": 0.4451991021633148,
+      "learning_rate": 2.6943122809582e-06,
+      "loss": 0.0017,
+      "step": 609
+    },
+    {
+      "epoch": 0.7860824742268041,
+      "grad_norm": 0.46482527256011963,
+      "learning_rate": 2.663652824205476e-06,
+      "loss": 0.0016,
+      "step": 610
+    },
+    {
+      "epoch": 0.7873711340206185,
+      "grad_norm": 0.07450009137392044,
+      "learning_rate": 2.6331419842993746e-06,
+      "loss": 0.0003,
+      "step": 611
+    },
+    {
+      "epoch": 0.788659793814433,
+      "grad_norm": 0.21978060901165009,
+      "learning_rate": 2.6027803793165353e-06,
+      "loss": 0.001,
+      "step": 612
+    },
+    {
+      "epoch": 0.7899484536082474,
+      "grad_norm": 0.566473662853241,
+      "learning_rate": 2.5725686243104586e-06,
+      "loss": 0.0007,
+      "step": 613
+    },
+    {
+      "epoch": 0.7912371134020618,
+      "grad_norm": 2.9466750621795654,
+      "learning_rate": 2.5425073312990334e-06,
+      "loss": 0.0208,
+      "step": 614
+    },
+    {
+      "epoch": 0.7925257731958762,
+      "grad_norm": 3.2940099239349365,
+      "learning_rate": 2.5125971092521607e-06,
+      "loss": 0.0521,
+      "step": 615
+    },
+    {
+      "epoch": 0.7938144329896907,
+      "grad_norm": 0.08639179915189743,
+      "learning_rate": 2.4828385640793974e-06,
+      "loss": 0.0003,
+      "step": 616
+    },
+    {
+      "epoch": 0.7951030927835051,
+      "grad_norm": 2.585515260696411,
+      "learning_rate": 2.4532322986176926e-06,
+      "loss": 0.0057,
+      "step": 617
+    },
+    {
+      "epoch": 0.7963917525773195,
+      "grad_norm": 0.4970383048057556,
+      "learning_rate": 2.4237789126191715e-06,
+      "loss": 0.0023,
+      "step": 618
+    },
+    {
+      "epoch": 0.7976804123711341,
+      "grad_norm": 0.30445781350135803,
+      "learning_rate": 2.3944790027389888e-06,
+      "loss": 0.0018,
+      "step": 619
+    },
+    {
+      "epoch": 0.7989690721649485,
+      "grad_norm": 0.4191214144229889,
+      "learning_rate": 2.3653331625232367e-06,
+      "loss": 0.0022,
+      "step": 620
+    },
+    {
+      "epoch": 0.7989690721649485,
+      "eval_accuracy": 0.9980139026812314,
+      "eval_f1": 0.9642857142857143,
+      "eval_loss": 0.013430897146463394,
+      "eval_precision": 0.9818181818181818,
+      "eval_recall": 0.9473684210526315,
+      "eval_runtime": 84.121,
+      "eval_samples_per_second": 5.409,
+      "eval_steps_per_second": 0.178,
+      "step": 620
+    },
+    {
+      "epoch": 0.8002577319587629,
+      "grad_norm": 0.36169302463531494,
+      "learning_rate": 2.336341982396928e-06,
+      "loss": 0.0006,
+      "step": 621
+    },
+    {
+      "epoch": 0.8015463917525774,
+      "grad_norm": 0.40979477763175964,
+      "learning_rate": 2.307506049652031e-06,
+      "loss": 0.0036,
+      "step": 622
+    },
+    {
+      "epoch": 0.8028350515463918,
+      "grad_norm": 4.417389392852783,
+      "learning_rate": 2.2788259484355712e-06,
+      "loss": 0.0303,
+      "step": 623
+    },
+    {
+      "epoch": 0.8041237113402062,
+      "grad_norm": 1.4798436164855957,
+      "learning_rate": 2.250302259737803e-06,
+      "loss": 0.006,
+      "step": 624
+    },
+    {
+      "epoch": 0.8054123711340206,
+      "grad_norm": 0.44748619198799133,
+      "learning_rate": 2.2219355613804406e-06,
+      "loss": 0.0018,
+      "step": 625
+    },
+    {
+      "epoch": 0.8067010309278351,
+      "grad_norm": 0.01932459883391857,
+      "learning_rate": 2.1937264280049365e-06,
+      "loss": 0.0001,
+      "step": 626
+    },
+    {
+      "epoch": 0.8079896907216495,
+      "grad_norm": 0.01475608441978693,
+      "learning_rate": 2.1656754310608663e-06,
+      "loss": 0.0001,
+      "step": 627
+    },
+    {
+      "epoch": 0.8092783505154639,
+      "grad_norm": 2.7333805561065674,
+      "learning_rate": 2.137783138794335e-06,
+      "loss": 0.0055,
+      "step": 628
+    },
+    {
+      "epoch": 0.8105670103092784,
+      "grad_norm": 2.6362922191619873,
+      "learning_rate": 2.1100501162364707e-06,
+      "loss": 0.0365,
+      "step": 629
+    },
+    {
+      "epoch": 0.8118556701030928,
+      "grad_norm": 0.2980014383792877,
+      "learning_rate": 2.0824769251919775e-06,
+      "loss": 0.0006,
+      "step": 630
+    },
+    {
+      "epoch": 0.8131443298969072,
+      "grad_norm": 0.7731969356536865,
+      "learning_rate": 2.055064124227758e-06,
+      "loss": 0.0016,
+      "step": 631
+    },
+    {
+      "epoch": 0.8144329896907216,
+      "grad_norm": 0.166972815990448,
+      "learning_rate": 2.027812268661592e-06,
+      "loss": 0.0006,
+      "step": 632
+    },
+    {
+      "epoch": 0.8157216494845361,
+      "grad_norm": 0.33119046688079834,
+      "learning_rate": 2.0007219105508935e-06,
+      "loss": 0.0015,
+      "step": 633
+    },
+    {
+      "epoch": 0.8170103092783505,
+      "grad_norm": 0.7209166884422302,
+      "learning_rate": 1.9737935986815205e-06,
+      "loss": 0.0023,
+      "step": 634
+    },
+    {
+      "epoch": 0.8182989690721649,
+      "grad_norm": 0.3935668170452118,
+      "learning_rate": 1.9470278785566653e-06,
+      "loss": 0.0015,
+      "step": 635
+    },
+    {
+      "epoch": 0.8195876288659794,
+      "grad_norm": 2.5623619556427,
+      "learning_rate": 1.9204252923858003e-06,
+      "loss": 0.0139,
+      "step": 636
+    },
+    {
+      "epoch": 0.8208762886597938,
+      "grad_norm": 1.0038329362869263,
+      "learning_rate": 1.8939863790736923e-06,
+      "loss": 0.0047,
+      "step": 637
+    },
+    {
+      "epoch": 0.8221649484536082,
+      "grad_norm": 1.09479820728302,
+      "learning_rate": 1.8677116742094858e-06,
+      "loss": 0.0043,
+      "step": 638
+    },
+    {
+      "epoch": 0.8234536082474226,
+      "grad_norm": 1.43467116355896,
+      "learning_rate": 1.8416017100558592e-06,
+      "loss": 0.0031,
+      "step": 639
+    },
+    {
+      "epoch": 0.8247422680412371,
+      "grad_norm": 1.7519943714141846,
+      "learning_rate": 1.8156570155382357e-06,
+      "loss": 0.0149,
+      "step": 640
+    },
+    {
+      "epoch": 0.8247422680412371,
+      "eval_accuracy": 0.9980139026812314,
+      "eval_f1": 0.9642857142857143,
+      "eval_loss": 0.013629155233502388,
+      "eval_precision": 0.9818181818181818,
+      "eval_recall": 0.9473684210526315,
+      "eval_runtime": 83.6673,
+      "eval_samples_per_second": 5.438,
+      "eval_steps_per_second": 0.179,
+      "step": 640
+    },
+    {
+      "epoch": 0.8260309278350515,
+      "grad_norm": 0.3471926748752594,
+      "learning_rate": 1.7898781162340683e-06,
+      "loss": 0.0013,
+      "step": 641
+    },
+    {
+      "epoch": 0.8273195876288659,
+      "grad_norm": 2.4162745475769043,
+      "learning_rate": 1.764265534362205e-06,
+      "loss": 0.0047,
+      "step": 642
+    },
+    {
+      "epoch": 0.8286082474226805,
+      "grad_norm": 1.6409410238265991,
+      "learning_rate": 1.7388197887722914e-06,
+      "loss": 0.0027,
+      "step": 643
+    },
+    {
+      "epoch": 0.8298969072164949,
+      "grad_norm": 0.545690655708313,
+      "learning_rate": 1.7135413949342706e-06,
+      "loss": 0.0025,
+      "step": 644
+    },
+    {
+      "epoch": 0.8311855670103093,
+      "grad_norm": 1.0303876399993896,
+      "learning_rate": 1.6884308649279413e-06,
+      "loss": 0.0023,
+      "step": 645
+    },
+    {
+      "epoch": 0.8324742268041238,
+      "grad_norm": 0.33830779790878296,
+      "learning_rate": 1.6634887074325844e-06,
+      "loss": 0.0037,
+      "step": 646
+    },
+    {
+      "epoch": 0.8337628865979382,
+      "grad_norm": 3.1400089263916016,
+      "learning_rate": 1.6387154277166484e-06,
+      "loss": 0.0166,
+      "step": 647
+    },
+    {
+      "epoch": 0.8350515463917526,
+      "grad_norm": 4.601196765899658,
+      "learning_rate": 1.6141115276275298e-06,
+      "loss": 0.0089,
+      "step": 648
+    },
+    {
+      "epoch": 0.836340206185567,
+      "grad_norm": 2.343628168106079,
+      "learning_rate": 1.5896775055813973e-06,
+      "loss": 0.0135,
+      "step": 649
+    },
+    {
+      "epoch": 0.8376288659793815,
+      "grad_norm": 0.42886826395988464,
+      "learning_rate": 1.565413856553095e-06,
+      "loss": 0.0009,
+      "step": 650
+    },
+    {
+      "epoch": 0.8389175257731959,
+      "grad_norm": 2.6612963676452637,
+      "learning_rate": 1.5413210720661187e-06,
+      "loss": 0.0107,
+      "step": 651
+    },
+    {
+      "epoch": 0.8402061855670103,
+      "grad_norm": 2.667137384414673,
+      "learning_rate": 1.5173996401826563e-06,
+      "loss": 0.0063,
+      "step": 652
+    },
+    {
+      "epoch": 0.8414948453608248,
+      "grad_norm": 0.3507553040981293,
+      "learning_rate": 1.493650045493703e-06,
+      "loss": 0.0005,
+      "step": 653
+    },
+    {
+      "epoch": 0.8427835051546392,
+      "grad_norm": 0.04581530764698982,
+      "learning_rate": 1.470072769109242e-06,
+      "loss": 0.0002,
+      "step": 654
+    },
+    {
+      "epoch": 0.8440721649484536,
+      "grad_norm": 1.1834570169448853,
+      "learning_rate": 1.4466682886485007e-06,
+      "loss": 0.024,
+      "step": 655
+    },
+    {
+      "epoch": 0.845360824742268,
+      "grad_norm": 1.0574672222137451,
+      "learning_rate": 1.4234370782302742e-06,
+      "loss": 0.0023,
+      "step": 656
+    },
+    {
+      "epoch": 0.8466494845360825,
+      "grad_norm": 2.036065101623535,
+      "learning_rate": 1.4003796084633204e-06,
+      "loss": 0.0025,
+      "step": 657
+    },
+    {
+      "epoch": 0.8479381443298969,
+      "grad_norm": 1.696574330329895,
+      "learning_rate": 1.3774963464368295e-06,
+      "loss": 0.0193,
+      "step": 658
+    },
+    {
+      "epoch": 0.8492268041237113,
+      "grad_norm": 1.5883897542953491,
+      "learning_rate": 1.3547877557109546e-06,
+      "loss": 0.0027,
+      "step": 659
+    },
+    {
+      "epoch": 0.8505154639175257,
+      "grad_norm": 4.670267581939697,
+      "learning_rate": 1.3322542963074314e-06,
+      "loss": 0.0397,
+      "step": 660
+    },
+    {
+      "epoch": 0.8505154639175257,
+      "eval_accuracy": 0.9980139026812314,
+      "eval_f1": 0.9642857142857143,
+      "eval_loss": 0.014034120365977287,
+      "eval_precision": 0.9818181818181818,
+      "eval_recall": 0.9473684210526315,
+      "eval_runtime": 83.9766,
+      "eval_samples_per_second": 5.418,
+      "eval_steps_per_second": 0.179,
+      "step": 660
+    },
+    {
+      "epoch": 0.8518041237113402,
+      "grad_norm": 1.0197376012802124,
+      "learning_rate": 1.3098964247002499e-06,
+      "loss": 0.0082,
+      "step": 661
+    },
+    {
+      "epoch": 0.8530927835051546,
+      "grad_norm": 1.4475185871124268,
+      "learning_rate": 1.287714593806415e-06,
+      "loss": 0.0407,
+      "step": 662
+    },
+    {
+      "epoch": 0.854381443298969,
+      "grad_norm": 1.8474105596542358,
+      "learning_rate": 1.2657092529767644e-06,
+      "loss": 0.0162,
+      "step": 663
+    },
+    {
+      "epoch": 0.8556701030927835,
+      "grad_norm": 1.8313465118408203,
+      "learning_rate": 1.2438808479868715e-06,
+      "loss": 0.0056,
+      "step": 664
+    },
+    {
+      "epoch": 0.8569587628865979,
+      "grad_norm": 0.1645200103521347,
+      "learning_rate": 1.2222298210280103e-06,
+      "loss": 0.0003,
+      "step": 665
+    },
+    {
+      "epoch": 0.8582474226804123,
+      "grad_norm": 0.8122232556343079,
+      "learning_rate": 1.200756610698205e-06,
+      "loss": 0.0013,
+      "step": 666
+    },
+    {
+      "epoch": 0.8595360824742269,
+      "grad_norm": 0.12824606895446777,
+      "learning_rate": 1.1794616519933344e-06,
+      "loss": 0.0006,
+      "step": 667
+    },
+    {
+      "epoch": 0.8608247422680413,
+      "grad_norm": 2.5258920192718506,
+      "learning_rate": 1.1583453762983289e-06,
+      "loss": 0.0158,
+      "step": 668
+    },
+    {
+      "epoch": 0.8621134020618557,
+      "grad_norm": 4.607170581817627,
+      "learning_rate": 1.137408211378429e-06,
+      "loss": 0.0285,
+      "step": 669
+    },
+    {
+      "epoch": 0.8634020618556701,
+      "grad_norm": 2.1147348880767822,
+      "learning_rate": 1.1166505813705187e-06,
+      "loss": 0.0086,
+      "step": 670
+    },
+    {
+      "epoch": 0.8646907216494846,
+      "grad_norm": 3.446589469909668,
+      "learning_rate": 1.09607290677453e-06,
+      "loss": 0.0197,
+      "step": 671
+    },
+    {
+      "epoch": 0.865979381443299,
+      "grad_norm": 1.567643404006958,
+      "learning_rate": 1.0756756044449358e-06,
+      "loss": 0.0097,
+      "step": 672
+    },
+    {
+      "epoch": 0.8672680412371134,
+      "grad_norm": 0.9470865726470947,
+      "learning_rate": 1.0554590875822924e-06,
+      "loss": 0.0016,
+      "step": 673
+    },
+    {
+      "epoch": 0.8685567010309279,
+      "grad_norm": 0.1424911469221115,
+      "learning_rate": 1.035423765724879e-06,
+      "loss": 0.0005,
+      "step": 674
+    },
+    {
+      "epoch": 0.8698453608247423,
+      "grad_norm": 0.6392320394515991,
+      "learning_rate": 1.015570044740396e-06,
+      "loss": 0.0032,
+      "step": 675
+    },
+    {
+      "epoch": 0.8711340206185567,
+      "grad_norm": 0.08668619394302368,
+      "learning_rate": 9.958983268177425e-07,
+      "loss": 0.0004,
+      "step": 676
+    },
+    {
+      "epoch": 0.8724226804123711,
+      "grad_norm": 1.2266596555709839,
+      "learning_rate": 9.764090104588741e-07,
+      "loss": 0.0025,
+      "step": 677
+    },
+    {
+      "epoch": 0.8737113402061856,
+      "grad_norm": 0.201644629240036,
+      "learning_rate": 9.571024904707238e-07,
+      "loss": 0.0014,
+      "step": 678
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 1.0185980796813965,
+      "learning_rate": 9.379791579572118e-07,
+      "loss": 0.0036,
+      "step": 679
+    },
+    {
+      "epoch": 0.8762886597938144,
+      "grad_norm": 1.772665023803711,
+      "learning_rate": 9.190394003113123e-07,
+      "loss": 0.0058,
+      "step": 680
+    },
+    {
+      "epoch": 0.8762886597938144,
+      "eval_accuracy": 0.9980139026812314,
+      "eval_f1": 0.9642857142857143,
+      "eval_loss": 0.013515458442270756,
+      "eval_precision": 0.9818181818181818,
+      "eval_recall": 0.9473684210526315,
+      "eval_runtime": 84.5145,
+      "eval_samples_per_second": 5.384,
+      "eval_steps_per_second": 0.177,
+      "step": 680
+    },
+    {
+      "epoch": 0.8775773195876289,
+      "grad_norm": 0.43585294485092163,
+      "learning_rate": 9.002836012072169e-07,
+      "loss": 0.001,
+      "step": 681
+    },
+    {
+      "epoch": 0.8788659793814433,
+      "grad_norm": 0.862573504447937,
+      "learning_rate": 8.817121405925543e-07,
+      "loss": 0.004,
+      "step": 682
+    },
+    {
+      "epoch": 0.8801546391752577,
+      "grad_norm": 1.9756450653076172,
+      "learning_rate": 8.633253946806974e-07,
+      "loss": 0.0131,
+      "step": 683
+    },
+    {
+      "epoch": 0.8814432989690721,
+      "grad_norm": 0.09257616102695465,
+      "learning_rate": 8.451237359431397e-07,
+      "loss": 0.0004,
+      "step": 684
+    },
+    {
+      "epoch": 0.8827319587628866,
+      "grad_norm": 0.9120633602142334,
+      "learning_rate": 8.271075331019541e-07,
+      "loss": 0.0085,
+      "step": 685
+    },
+    {
+      "epoch": 0.884020618556701,
+      "grad_norm": 0.1704445630311966,
+      "learning_rate": 8.092771511223185e-07,
+      "loss": 0.0012,
+      "step": 686
+    },
+    {
+      "epoch": 0.8853092783505154,
+      "grad_norm": 0.10662536323070526,
+      "learning_rate": 7.916329512051235e-07,
+      "loss": 0.0006,
+      "step": 687
+    },
+    {
+      "epoch": 0.8865979381443299,
+      "grad_norm": 2.8713998794555664,
+      "learning_rate": 7.741752907796584e-07,
+      "loss": 0.0159,
+      "step": 688
+    },
+    {
+      "epoch": 0.8878865979381443,
+      "grad_norm": 0.5300127863883972,
+      "learning_rate": 7.56904523496369e-07,
+      "loss": 0.0013,
+      "step": 689
+    },
+    {
+      "epoch": 0.8891752577319587,
+      "grad_norm": 1.1316462755203247,
+      "learning_rate": 7.398209992196914e-07,
+      "loss": 0.0019,
+      "step": 690
+    },
+    {
+      "epoch": 0.8904639175257731,
+      "grad_norm": 0.06225062906742096,
+      "learning_rate": 7.229250640209661e-07,
+      "loss": 0.0003,
+      "step": 691
+    },
+    {
+      "epoch": 0.8917525773195877,
+      "grad_norm": 0.21658547222614288,
+      "learning_rate": 7.062170601714302e-07,
+      "loss": 0.0009,
+      "step": 692
+    },
+    {
+      "epoch": 0.8930412371134021,
+      "grad_norm": 5.541469573974609,
+      "learning_rate": 6.896973261352779e-07,
+      "loss": 0.0294,
+      "step": 693
+    },
+    {
+      "epoch": 0.8943298969072165,
+      "grad_norm": 0.24933123588562012,
+      "learning_rate": 6.73366196562808e-07,
+      "loss": 0.0013,
+      "step": 694
+    },
+    {
+      "epoch": 0.895618556701031,
+      "grad_norm": 2.7014365196228027,
+      "learning_rate": 6.572240022836451e-07,
+      "loss": 0.0166,
+      "step": 695
+    },
+    {
+      "epoch": 0.8969072164948454,
+      "grad_norm": 1.3881912231445312,
+      "learning_rate": 6.412710703000368e-07,
+      "loss": 0.0037,
+      "step": 696
+    },
+    {
+      "epoch": 0.8981958762886598,
+      "grad_norm": 4.935601711273193,
+      "learning_rate": 6.255077237802288e-07,
+      "loss": 0.0208,
+      "step": 697
+    },
+    {
+      "epoch": 0.8994845360824743,
+      "grad_norm": 2.3995628356933594,
+      "learning_rate": 6.099342820519183e-07,
+      "loss": 0.0219,
+      "step": 698
+    },
+    {
+      "epoch": 0.9007731958762887,
+      "grad_norm": 0.5882774591445923,
+      "learning_rate": 5.945510605957861e-07,
+      "loss": 0.0023,
+      "step": 699
+    },
+    {
+      "epoch": 0.9020618556701031,
+      "grad_norm": 3.2632617950439453,
+      "learning_rate": 5.79358371039106e-07,
+      "loss": 0.0153,
+      "step": 700
+    },
+    {
+      "epoch": 0.9020618556701031,
+      "eval_accuracy": 0.9980139026812314,
+      "eval_f1": 0.9642857142857143,
+      "eval_loss": 0.01318343449383974,
+      "eval_precision": 0.9818181818181818,
+      "eval_recall": 0.9473684210526315,
+      "eval_runtime": 83.7071,
+      "eval_samples_per_second": 5.436,
+      "eval_steps_per_second": 0.179,
+      "step": 700
     }
   ],
   "logging_steps": 1,
@@ -4598,7 +5358,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.004089890144256e+17,
+  "total_flos": 2.3348483995572634e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null