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 sha256:933b1f63d90c319542a4fd47759174fed83fc881d8cb4cb2a83a713fabd5a6a8
+oid sha256:9e243eb5a2e392baf6fbbd34e2880b92b192e8406253f7dbfdcc5bf34a27d48d
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25fa0e6ce8d54d0ff171f555366adec8729dd853388ab8d8c9f00eb8bd9371dd
+oid sha256:35be897abb2edd59e7e14cd584897fafab6ebcbe9d7b044ec3c0f24465e96641
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21407e44a54ae327fa01bf921b6d09dfdd5516385f912101dd79966b49088d89
+oid sha256:756519000cbd96a62a18f4b2593ac1531235ff43f81a97c750d5d508e0bb4895
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f41da44c9f99411f6202714d8e5e84be2ba87c642f032b48d842df5f62d4222
+oid sha256:9503408f5508841046560c3ab2f47fba69b29194960b3e332e210fb40344d3dc
 size 13990904

last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12b57b77c4bb1d00af9ed39553b6d0ea59b3e5d5141d103e1b5721d70f1c1075
+oid sha256:526dcd0450898f0723267644199cfb9a8075bd3c8768053837a8471c3071e1f8
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d1c230b287be50383ea4060312fe31d090370284705ec75e143fb62864c38fd
+oid sha256:5b8a091054d4117d69c92fe61df180bdff12c693387e2bf9406cb7a0c62fb550
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ada10e4fc29560cc70bbb7f18e8d12a735aff41ce11272efee5b1a4fe85f4c4
+oid sha256:97f4e093aada0ef569e1477e89853408435b9af062279297db8b59881fcbb194
 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:d9fc5c2486e572dc7f0881c6dd684dbcdd44bc14f5a416e106e39724f7005e6d
+oid sha256:69c3c82ad5b7f6e2fcf2155f310ae31260fa6abcafc63890af31474a7296f19d
 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": 5.341,
       "eval_steps_per_second": 0.176,
       "step": 600
+    },
+    {
+      "epoch": 0.7744845360824743,
+      "grad_norm": 0.11000218242406845,
+      "learning_rate": 2.944862984597068e-06,
+      "loss": 0.0006,
+      "step": 601
+    },
+    {
+      "epoch": 0.7757731958762887,
+      "grad_norm": 0.06000187247991562,
+      "learning_rate": 2.913037202447625e-06,
+      "loss": 0.0002,
+      "step": 602
+    },
+    {
+      "epoch": 0.7770618556701031,
+      "grad_norm": 1.5387769937515259,
+      "learning_rate": 2.8813549852137824e-06,
+      "loss": 0.0069,
+      "step": 603
+    },
+    {
+      "epoch": 0.7783505154639175,
+      "grad_norm": 0.052634306252002716,
+      "learning_rate": 2.8498169747014824e-06,
+      "loss": 0.0004,
+      "step": 604
+    },
+    {
+      "epoch": 0.779639175257732,
+      "grad_norm": 2.0702285766601562,
+      "learning_rate": 2.818423809795384e-06,
+      "loss": 0.0075,
+      "step": 605
+    },
+    {
+      "epoch": 0.7809278350515464,
+      "grad_norm": 2.145193099975586,
+      "learning_rate": 2.787176126445923e-06,
+      "loss": 0.0143,
+      "step": 606
+    },
+    {
+      "epoch": 0.7822164948453608,
+      "grad_norm": 1.94924795627594,
+      "learning_rate": 2.756074557656424e-06,
+      "loss": 0.0032,
+      "step": 607
+    },
+    {
+      "epoch": 0.7835051546391752,
+      "grad_norm": 0.6096054911613464,
+      "learning_rate": 2.725119733470284e-06,
+      "loss": 0.0019,
+      "step": 608
+    },
+    {
+      "epoch": 0.7847938144329897,
+      "grad_norm": 0.4482673406600952,
+      "learning_rate": 2.6943122809582e-06,
+      "loss": 0.0017,
+      "step": 609
+    },
+    {
+      "epoch": 0.7860824742268041,
+      "grad_norm": 0.4562239944934845,
+      "learning_rate": 2.663652824205476e-06,
+      "loss": 0.0018,
+      "step": 610
+    },
+    {
+      "epoch": 0.7873711340206185,
+      "grad_norm": 0.07097622007131577,
+      "learning_rate": 2.6331419842993746e-06,
+      "loss": 0.0003,
+      "step": 611
+    },
+    {
+      "epoch": 0.788659793814433,
+      "grad_norm": 0.23742669820785522,
+      "learning_rate": 2.6027803793165353e-06,
+      "loss": 0.0012,
+      "step": 612
+    },
+    {
+      "epoch": 0.7899484536082474,
+      "grad_norm": 0.7744345664978027,
+      "learning_rate": 2.5725686243104586e-06,
+      "loss": 0.0009,
+      "step": 613
+    },
+    {
+      "epoch": 0.7912371134020618,
+      "grad_norm": 2.8336048126220703,
+      "learning_rate": 2.5425073312990334e-06,
+      "loss": 0.0189,
+      "step": 614
+    },
+    {
+      "epoch": 0.7925257731958762,
+      "grad_norm": 3.236351728439331,
+      "learning_rate": 2.5125971092521607e-06,
+      "loss": 0.0504,
+      "step": 615
+    },
+    {
+      "epoch": 0.7938144329896907,
+      "grad_norm": 0.09571472555398941,
+      "learning_rate": 2.4828385640793974e-06,
+      "loss": 0.0004,
+      "step": 616
+    },
+    {
+      "epoch": 0.7951030927835051,
+      "grad_norm": 3.24649977684021,
+      "learning_rate": 2.4532322986176926e-06,
+      "loss": 0.0066,
+      "step": 617
+    },
+    {
+      "epoch": 0.7963917525773195,
+      "grad_norm": 0.6379624605178833,
+      "learning_rate": 2.4237789126191715e-06,
+      "loss": 0.0025,
+      "step": 618
+    },
+    {
+      "epoch": 0.7976804123711341,
+      "grad_norm": 0.4450211226940155,
+      "learning_rate": 2.3944790027389888e-06,
+      "loss": 0.0024,
+      "step": 619
+    },
+    {
+      "epoch": 0.7989690721649485,
+      "grad_norm": 0.42626920342445374,
+      "learning_rate": 2.3653331625232367e-06,
+      "loss": 0.0018,
+      "step": 620
+    },
+    {
+      "epoch": 0.7989690721649485,
+      "eval_accuracy": 0.9975173783515392,
+      "eval_f1": 0.9557522123893806,
+      "eval_loss": 0.013614228926599026,
+      "eval_precision": 0.9642857142857143,
+      "eval_recall": 0.9473684210526315,
+      "eval_runtime": 85.5414,
+      "eval_samples_per_second": 5.319,
+      "eval_steps_per_second": 0.175,
+      "step": 620
+    },
+    {
+      "epoch": 0.8002577319587629,
+      "grad_norm": 1.3859606981277466,
+      "learning_rate": 2.336341982396928e-06,
+      "loss": 0.0018,
+      "step": 621
+    },
+    {
+      "epoch": 0.8015463917525774,
+      "grad_norm": 0.29047346115112305,
+      "learning_rate": 2.307506049652031e-06,
+      "loss": 0.0033,
+      "step": 622
+    },
+    {
+      "epoch": 0.8028350515463918,
+      "grad_norm": 4.054072856903076,
+      "learning_rate": 2.2788259484355712e-06,
+      "loss": 0.0358,
+      "step": 623
+    },
+    {
+      "epoch": 0.8041237113402062,
+      "grad_norm": 1.3279507160186768,
+      "learning_rate": 2.250302259737803e-06,
+      "loss": 0.0047,
+      "step": 624
+    },
+    {
+      "epoch": 0.8054123711340206,
+      "grad_norm": 1.3657283782958984,
+      "learning_rate": 2.2219355613804406e-06,
+      "loss": 0.0027,
+      "step": 625
+    },
+    {
+      "epoch": 0.8067010309278351,
+      "grad_norm": 0.02000313624739647,
+      "learning_rate": 2.1937264280049365e-06,
+      "loss": 0.0001,
+      "step": 626
+    },
+    {
+      "epoch": 0.8079896907216495,
+      "grad_norm": 0.022800248116254807,
+      "learning_rate": 2.1656754310608663e-06,
+      "loss": 0.0001,
+      "step": 627
+    },
+    {
+      "epoch": 0.8092783505154639,
+      "grad_norm": 2.1615025997161865,
+      "learning_rate": 2.137783138794335e-06,
+      "loss": 0.005,
+      "step": 628
+    },
+    {
+      "epoch": 0.8105670103092784,
+      "grad_norm": 2.5483734607696533,
+      "learning_rate": 2.1100501162364707e-06,
+      "loss": 0.0407,
+      "step": 629
+    },
+    {
+      "epoch": 0.8118556701030928,
+      "grad_norm": 0.29894164204597473,
+      "learning_rate": 2.0824769251919775e-06,
+      "loss": 0.0005,
+      "step": 630
+    },
+    {
+      "epoch": 0.8131443298969072,
+      "grad_norm": 1.0408016443252563,
+      "learning_rate": 2.055064124227758e-06,
+      "loss": 0.0018,
+      "step": 631
+    },
+    {
+      "epoch": 0.8144329896907216,
+      "grad_norm": 0.12250500172376633,
+      "learning_rate": 2.027812268661592e-06,
+      "loss": 0.0005,
+      "step": 632
+    },
+    {
+      "epoch": 0.8157216494845361,
+      "grad_norm": 0.30518946051597595,
+      "learning_rate": 2.0007219105508935e-06,
+      "loss": 0.0015,
+      "step": 633
+    },
+    {
+      "epoch": 0.8170103092783505,
+      "grad_norm": 0.46933111548423767,
+      "learning_rate": 1.9737935986815205e-06,
+      "loss": 0.0014,
+      "step": 634
+    },
+    {
+      "epoch": 0.8182989690721649,
+      "grad_norm": 0.45417195558547974,
+      "learning_rate": 1.9470278785566653e-06,
+      "loss": 0.0016,
+      "step": 635
+    },
+    {
+      "epoch": 0.8195876288659794,
+      "grad_norm": 2.510430335998535,
+      "learning_rate": 1.9204252923858003e-06,
+      "loss": 0.0114,
+      "step": 636
+    },
+    {
+      "epoch": 0.8208762886597938,
+      "grad_norm": 0.9059619903564453,
+      "learning_rate": 1.8939863790736923e-06,
+      "loss": 0.0041,
+      "step": 637
+    },
+    {
+      "epoch": 0.8221649484536082,
+      "grad_norm": 0.9617973566055298,
+      "learning_rate": 1.8677116742094858e-06,
+      "loss": 0.0038,
+      "step": 638
+    },
+    {
+      "epoch": 0.8234536082474226,
+      "grad_norm": 2.0744788646698,
+      "learning_rate": 1.8416017100558592e-06,
+      "loss": 0.0046,
+      "step": 639
+    },
+    {
+      "epoch": 0.8247422680412371,
+      "grad_norm": 1.710120439529419,
+      "learning_rate": 1.8156570155382357e-06,
+      "loss": 0.0164,
+      "step": 640
+    },
+    {
+      "epoch": 0.8247422680412371,
+      "eval_accuracy": 0.9975173783515392,
+      "eval_f1": 0.9557522123893806,
+      "eval_loss": 0.014028658159077168,
+      "eval_precision": 0.9642857142857143,
+      "eval_recall": 0.9473684210526315,
+      "eval_runtime": 85.1596,
+      "eval_samples_per_second": 5.343,
+      "eval_steps_per_second": 0.176,
+      "step": 640
+    },
+    {
+      "epoch": 0.8260309278350515,
+      "grad_norm": 0.4058464765548706,
+      "learning_rate": 1.7898781162340683e-06,
+      "loss": 0.0015,
+      "step": 641
+    },
+    {
+      "epoch": 0.8273195876288659,
+      "grad_norm": 2.3487915992736816,
+      "learning_rate": 1.764265534362205e-06,
+      "loss": 0.0046,
+      "step": 642
+    },
+    {
+      "epoch": 0.8286082474226805,
+      "grad_norm": 1.4977848529815674,
+      "learning_rate": 1.7388197887722914e-06,
+      "loss": 0.0025,
+      "step": 643
+    },
+    {
+      "epoch": 0.8298969072164949,
+      "grad_norm": 0.7546347379684448,
+      "learning_rate": 1.7135413949342706e-06,
+      "loss": 0.0034,
+      "step": 644
+    },
+    {
+      "epoch": 0.8311855670103093,
+      "grad_norm": 1.2620099782943726,
+      "learning_rate": 1.6884308649279413e-06,
+      "loss": 0.0026,
+      "step": 645
+    },
+    {
+      "epoch": 0.8324742268041238,
+      "grad_norm": 0.3899240791797638,
+      "learning_rate": 1.6634887074325844e-06,
+      "loss": 0.0042,
+      "step": 646
+    },
+    {
+      "epoch": 0.8337628865979382,
+      "grad_norm": 3.6986889839172363,
+      "learning_rate": 1.6387154277166484e-06,
+      "loss": 0.014,
+      "step": 647
+    },
+    {
+      "epoch": 0.8350515463917526,
+      "grad_norm": 4.560563087463379,
+      "learning_rate": 1.6141115276275298e-06,
+      "loss": 0.0071,
+      "step": 648
+    },
+    {
+      "epoch": 0.836340206185567,
+      "grad_norm": 2.40631365776062,
+      "learning_rate": 1.5896775055813973e-06,
+      "loss": 0.0155,
+      "step": 649
+    },
+    {
+      "epoch": 0.8376288659793815,
+      "grad_norm": 0.34469377994537354,
+      "learning_rate": 1.565413856553095e-06,
+      "loss": 0.0008,
+      "step": 650
+    },
+    {
+      "epoch": 0.8389175257731959,
+      "grad_norm": 2.645254611968994,
+      "learning_rate": 1.5413210720661187e-06,
+      "loss": 0.0087,
+      "step": 651
+    },
+    {
+      "epoch": 0.8402061855670103,
+      "grad_norm": 3.504944324493408,
+      "learning_rate": 1.5173996401826563e-06,
+      "loss": 0.0076,
+      "step": 652
+    },
+    {
+      "epoch": 0.8414948453608248,
+      "grad_norm": 0.9376299977302551,
+      "learning_rate": 1.493650045493703e-06,
+      "loss": 0.0011,
+      "step": 653
+    },
+    {
+      "epoch": 0.8427835051546392,
+      "grad_norm": 0.07310164719820023,
+      "learning_rate": 1.470072769109242e-06,
+      "loss": 0.0002,
+      "step": 654
+    },
+    {
+      "epoch": 0.8440721649484536,
+      "grad_norm": 0.9804725050926208,
+      "learning_rate": 1.4466682886485007e-06,
+      "loss": 0.0248,
+      "step": 655
+    },
+    {
+      "epoch": 0.845360824742268,
+      "grad_norm": 1.2410582304000854,
+      "learning_rate": 1.4234370782302742e-06,
+      "loss": 0.0027,
+      "step": 656
+    },
+    {
+      "epoch": 0.8466494845360825,
+      "grad_norm": 1.5435892343521118,
+      "learning_rate": 1.4003796084633204e-06,
+      "loss": 0.0021,
+      "step": 657
+    },
+    {
+      "epoch": 0.8479381443298969,
+      "grad_norm": 1.6477559804916382,
+      "learning_rate": 1.3774963464368295e-06,
+      "loss": 0.0219,
+      "step": 658
+    },
+    {
+      "epoch": 0.8492268041237113,
+      "grad_norm": 1.8819410800933838,
+      "learning_rate": 1.3547877557109546e-06,
+      "loss": 0.0033,
+      "step": 659
+    },
+    {
+      "epoch": 0.8505154639175257,
+      "grad_norm": 4.333096981048584,
+      "learning_rate": 1.3322542963074314e-06,
+      "loss": 0.0359,
+      "step": 660
+    },
+    {
+      "epoch": 0.8505154639175257,
+      "eval_accuracy": 0.9980139026812314,
+      "eval_f1": 0.9642857142857143,
+      "eval_loss": 0.014260557480156422,
+      "eval_precision": 0.9818181818181818,
+      "eval_recall": 0.9473684210526315,
+      "eval_runtime": 85.7933,
+      "eval_samples_per_second": 5.303,
+      "eval_steps_per_second": 0.175,
+      "step": 660
+    },
+    {
+      "epoch": 0.8518041237113402,
+      "grad_norm": 1.0809779167175293,
+      "learning_rate": 1.3098964247002499e-06,
+      "loss": 0.0085,
+      "step": 661
+    },
+    {
+      "epoch": 0.8530927835051546,
+      "grad_norm": 1.4017481803894043,
+      "learning_rate": 1.287714593806415e-06,
+      "loss": 0.0429,
+      "step": 662
+    },
+    {
+      "epoch": 0.854381443298969,
+      "grad_norm": 1.9630863666534424,
+      "learning_rate": 1.2657092529767644e-06,
+      "loss": 0.017,
+      "step": 663
+    },
+    {
+      "epoch": 0.8556701030927835,
+      "grad_norm": 1.8519372940063477,
+      "learning_rate": 1.2438808479868715e-06,
+      "loss": 0.0054,
+      "step": 664
+    },
+    {
+      "epoch": 0.8569587628865979,
+      "grad_norm": 0.13302436470985413,
+      "learning_rate": 1.2222298210280103e-06,
+      "loss": 0.0003,
+      "step": 665
+    },
+    {
+      "epoch": 0.8582474226804123,
+      "grad_norm": 0.8774328231811523,
+      "learning_rate": 1.200756610698205e-06,
+      "loss": 0.0016,
+      "step": 666
+    },
+    {
+      "epoch": 0.8595360824742269,
+      "grad_norm": 0.1723754107952118,
+      "learning_rate": 1.1794616519933344e-06,
+      "loss": 0.0008,
+      "step": 667
+    },
+    {
+      "epoch": 0.8608247422680413,
+      "grad_norm": 4.612834930419922,
+      "learning_rate": 1.1583453762983289e-06,
+      "loss": 0.0165,
+      "step": 668
+    },
+    {
+      "epoch": 0.8621134020618557,
+      "grad_norm": 4.430521011352539,
+      "learning_rate": 1.137408211378429e-06,
+      "loss": 0.0274,
+      "step": 669
+    },
+    {
+      "epoch": 0.8634020618556701,
+      "grad_norm": 2.550323963165283,
+      "learning_rate": 1.1166505813705187e-06,
+      "loss": 0.0115,
+      "step": 670
+    },
+    {
+      "epoch": 0.8646907216494846,
+      "grad_norm": 3.418363094329834,
+      "learning_rate": 1.09607290677453e-06,
+      "loss": 0.0195,
+      "step": 671
+    },
+    {
+      "epoch": 0.865979381443299,
+      "grad_norm": 1.712893009185791,
+      "learning_rate": 1.0756756044449358e-06,
+      "loss": 0.0095,
+      "step": 672
+    },
+    {
+      "epoch": 0.8672680412371134,
+      "grad_norm": 0.8803926110267639,
+      "learning_rate": 1.0554590875822924e-06,
+      "loss": 0.0013,
+      "step": 673
+    },
+    {
+      "epoch": 0.8685567010309279,
+      "grad_norm": 0.15702317655086517,
+      "learning_rate": 1.035423765724879e-06,
+      "loss": 0.0006,
+      "step": 674
+    },
+    {
+      "epoch": 0.8698453608247423,
+      "grad_norm": 0.7960672974586487,
+      "learning_rate": 1.015570044740396e-06,
+      "loss": 0.004,
+      "step": 675
+    },
+    {
+      "epoch": 0.8711340206185567,
+      "grad_norm": 0.0636625736951828,
+      "learning_rate": 9.958983268177425e-07,
+      "loss": 0.0003,
+      "step": 676
+    },
+    {
+      "epoch": 0.8724226804123711,
+      "grad_norm": 0.5046800971031189,
+      "learning_rate": 9.764090104588741e-07,
+      "loss": 0.0011,
+      "step": 677
+    },
+    {
+      "epoch": 0.8737113402061856,
+      "grad_norm": 0.18947793543338776,
+      "learning_rate": 9.571024904707238e-07,
+      "loss": 0.0014,
+      "step": 678
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 1.3208938837051392,
+      "learning_rate": 9.379791579572118e-07,
+      "loss": 0.0047,
+      "step": 679
+    },
+    {
+      "epoch": 0.8762886597938144,
+      "grad_norm": 1.1269551515579224,
+      "learning_rate": 9.190394003113123e-07,
+      "loss": 0.0038,
+      "step": 680
+    },
+    {
+      "epoch": 0.8762886597938144,
+      "eval_accuracy": 0.9980139026812314,
+      "eval_f1": 0.9642857142857143,
+      "eval_loss": 0.013650565408170223,
+      "eval_precision": 0.9818181818181818,
+      "eval_recall": 0.9473684210526315,
+      "eval_runtime": 85.0138,
+      "eval_samples_per_second": 5.352,
+      "eval_steps_per_second": 0.176,
+      "step": 680
+    },
+    {
+      "epoch": 0.8775773195876289,
+      "grad_norm": 1.984449863433838,
+      "learning_rate": 9.002836012072169e-07,
+      "loss": 0.0023,
+      "step": 681
+    },
+    {
+      "epoch": 0.8788659793814433,
+      "grad_norm": 1.0982954502105713,
+      "learning_rate": 8.817121405925543e-07,
+      "loss": 0.006,
+      "step": 682
+    },
+    {
+      "epoch": 0.8801546391752577,
+      "grad_norm": 1.77447509765625,
+      "learning_rate": 8.633253946806974e-07,
+      "loss": 0.0145,
+      "step": 683
+    },
+    {
+      "epoch": 0.8814432989690721,
+      "grad_norm": 0.07710134983062744,
+      "learning_rate": 8.451237359431397e-07,
+      "loss": 0.0004,
+      "step": 684
+    },
+    {
+      "epoch": 0.8827319587628866,
+      "grad_norm": 0.9491273760795593,
+      "learning_rate": 8.271075331019541e-07,
+      "loss": 0.0092,
+      "step": 685
+    },
+    {
+      "epoch": 0.884020618556701,
+      "grad_norm": 0.14051373302936554,
+      "learning_rate": 8.092771511223185e-07,
+      "loss": 0.0011,
+      "step": 686
+    },
+    {
+      "epoch": 0.8853092783505154,
+      "grad_norm": 0.11947651207447052,
+      "learning_rate": 7.916329512051235e-07,
+      "loss": 0.0006,
+      "step": 687
+    },
+    {
+      "epoch": 0.8865979381443299,
+      "grad_norm": 2.8755271434783936,
+      "learning_rate": 7.741752907796584e-07,
+      "loss": 0.0148,
+      "step": 688
+    },
+    {
+      "epoch": 0.8878865979381443,
+      "grad_norm": 0.33898699283599854,
+      "learning_rate": 7.56904523496369e-07,
+      "loss": 0.001,
+      "step": 689
+    },
+    {
+      "epoch": 0.8891752577319587,
+      "grad_norm": 1.2820080518722534,
+      "learning_rate": 7.398209992196914e-07,
+      "loss": 0.0021,
+      "step": 690
+    },
+    {
+      "epoch": 0.8904639175257731,
+      "grad_norm": 0.06955321133136749,
+      "learning_rate": 7.229250640209661e-07,
+      "loss": 0.0003,
+      "step": 691
+    },
+    {
+      "epoch": 0.8917525773195877,
+      "grad_norm": 0.3767196238040924,
+      "learning_rate": 7.062170601714302e-07,
+      "loss": 0.0014,
+      "step": 692
+    },
+    {
+      "epoch": 0.8930412371134021,
+      "grad_norm": 5.599634170532227,
+      "learning_rate": 6.896973261352779e-07,
+      "loss": 0.0293,
+      "step": 693
+    },
+    {
+      "epoch": 0.8943298969072165,
+      "grad_norm": 0.2771053910255432,
+      "learning_rate": 6.73366196562808e-07,
+      "loss": 0.0013,
+      "step": 694
+    },
+    {
+      "epoch": 0.895618556701031,
+      "grad_norm": 2.668797492980957,
+      "learning_rate": 6.572240022836451e-07,
+      "loss": 0.0139,
+      "step": 695
+    },
+    {
+      "epoch": 0.8969072164948454,
+      "grad_norm": 1.3741244077682495,
+      "learning_rate": 6.412710703000368e-07,
+      "loss": 0.004,
+      "step": 696
+    },
+    {
+      "epoch": 0.8981958762886598,
+      "grad_norm": 4.912818908691406,
+      "learning_rate": 6.255077237802288e-07,
+      "loss": 0.0207,
+      "step": 697
+    },
+    {
+      "epoch": 0.8994845360824743,
+      "grad_norm": 2.466047525405884,
+      "learning_rate": 6.099342820519183e-07,
+      "loss": 0.0217,
+      "step": 698
+    },
+    {
+      "epoch": 0.9007731958762887,
+      "grad_norm": 0.5519626140594482,
+      "learning_rate": 5.945510605957861e-07,
+      "loss": 0.0022,
+      "step": 699
+    },
+    {
+      "epoch": 0.9020618556701031,
+      "grad_norm": 2.488891124725342,
+      "learning_rate": 5.79358371039106e-07,
+      "loss": 0.011,
+      "step": 700
+    },
+    {
+      "epoch": 0.9020618556701031,
+      "eval_accuracy": 0.9975173783515392,
+      "eval_f1": 0.9557522123893806,
+      "eval_loss": 0.013403017073869705,
+      "eval_precision": 0.9642857142857143,
+      "eval_recall": 0.9473684210526315,
+      "eval_runtime": 85.6723,
+      "eval_samples_per_second": 5.311,
+      "eval_steps_per_second": 0.175,
+      "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