Training in progress, step 600, checkpoint

last-checkpoint/optimizer_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c379ef2a6d06f1b6d62f1076fd4c921adfce1635cf0e33794870aa4e4c50cd5
+oid sha256:99da1138da71c7a590a2707e483883e957340e06dae08b8827f18835c34a64b4
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6c6149211a936e9509b71caa3038d2974cbc24f16d2f139c4bce1f7f929ca96
+oid sha256:79c4ba664980c19c5ef3783c79e3d4e043fca5bb4c60f89d82faac7a943cf243
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca8239e8b89a1f8c74d7a7c79a3cdb93732f2743fa3971d79b6663a4fc675a9e
+oid sha256:f424fd03327ecb5ff630a9df1d98261931fcdfc83c1716e339b348d51df7d478
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0ec3076d00cd1127df3b4ac55a666860fa921fb02d4b5b8f30867f96acb82ce
+oid sha256:1a13d0c056d2946548a4902bc1af045b538f2ae540c6e2ef689c1bb7482253a0
 size 13990904

last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:931a5ebaf87bed2e7bed3aa5b3ecd7d4da726d7c7d64726db93912347ac7a58e
+oid sha256:4b31287f991033846081b020484b6de0532ffe6b03b8cf50698e3f201f2e56e9
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a4b8b1241a63c17dd12c1ce295952c7a1c8e1f86004b01703d7542255f0387f
+oid sha256:82e80cce203211b2c2441e9d6c1bb6224c0d09baf614394b407b0f9ce1ded28a
 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:c7ea0758e0b5550a0bad05276c2c8f8f6bed79e6d2e051cca07c9b0179ca83f1
+oid sha256:1e7beb1931987579881f896dde9404f4b409e252ef531ece93cbf739876254fe
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:364a002390ab0186583237ae427b0edf353723a14dec95eb28db15d33d2b2de4
+oid sha256:ddb5450bd834dd38bde6c77563d509a72456d15718acf61980ebcccc75aef710
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c0996004e3280ba2b8c5308142e245e93b9a3d5870de383914360145085a647
+oid sha256:ae91bbe4bb3448f9fe588b5f12c6d570f98cbeb7f79c6b4c021fdd413e35a673
 size 15088

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b99dae60d08ae089466b878474ef297a0b281547cd1097ea214ecee77244b16
+oid sha256:a5e2bdfc538b632be76938bdc369215d9c9e9696454b505d6d5c099a19d59619
 size 15088

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c3acfb47638e30fe1106672a6fd0db74c9187c94c19467e9d22bd366fbb5472
+oid sha256:654f94a53cbd3a4c0aa96462f7eefb36cea6a40f65967f82f41333fe8d59b3e6
 size 15088

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9723827a668573edbd596a65e0f225b208491adf853284b8da3f11b792077fdc
+oid sha256:24ee86115e5e887f663c435c280ac37373efa53275c443e874691073017d1363
 size 15088

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a124d1e9d8a7b4a76d7294be394802bfec19da05b0209e12c8dc6b8ab250293
+oid sha256:b85ee37d9a532de8cdb09f3a64e5b2fe9e638521f567e2b493ae4f1f2c3b0617
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6443298969072165,
+  "epoch": 0.7731958762886598,
   "eval_steps": 20,
-  "global_step": 500,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3819,6 +3819,766 @@
       "eval_samples_per_second": 5.335,
       "eval_steps_per_second": 0.176,
       "step": 500
+    },
+    {
+      "epoch": 0.645618556701031,
+      "grad_norm": 0.2069253921508789,
+      "learning_rate": 6.730609277866644e-06,
+      "loss": 0.0008,
+      "step": 501
+    },
+    {
+      "epoch": 0.6469072164948454,
+      "grad_norm": 0.7460423111915588,
+      "learning_rate": 6.688107468527297e-06,
+      "loss": 0.0043,
+      "step": 502
+    },
+    {
+      "epoch": 0.6481958762886598,
+      "grad_norm": 0.1024048775434494,
+      "learning_rate": 6.645672750209216e-06,
+      "loss": 0.0008,
+      "step": 503
+    },
+    {
+      "epoch": 0.6494845360824743,
+      "grad_norm": 3.0588488578796387,
+      "learning_rate": 6.603305982538295e-06,
+      "loss": 0.0153,
+      "step": 504
+    },
+    {
+      "epoch": 0.6507731958762887,
+      "grad_norm": 0.7051161527633667,
+      "learning_rate": 6.561008023763915e-06,
+      "loss": 0.0014,
+      "step": 505
+    },
+    {
+      "epoch": 0.6520618556701031,
+      "grad_norm": 1.1912554502487183,
+      "learning_rate": 6.518779730741555e-06,
+      "loss": 0.0085,
+      "step": 506
+    },
+    {
+      "epoch": 0.6533505154639175,
+      "grad_norm": 0.12031827121973038,
+      "learning_rate": 6.476621958915426e-06,
+      "loss": 0.0008,
+      "step": 507
+    },
+    {
+      "epoch": 0.654639175257732,
+      "grad_norm": 0.19412291049957275,
+      "learning_rate": 6.434535562301153e-06,
+      "loss": 0.0005,
+      "step": 508
+    },
+    {
+      "epoch": 0.6559278350515464,
+      "grad_norm": 1.5401062965393066,
+      "learning_rate": 6.392521393468471e-06,
+      "loss": 0.003,
+      "step": 509
+    },
+    {
+      "epoch": 0.6572164948453608,
+      "grad_norm": 1.881408929824829,
+      "learning_rate": 6.350580303523947e-06,
+      "loss": 0.0053,
+      "step": 510
+    },
+    {
+      "epoch": 0.6585051546391752,
+      "grad_norm": 1.8034359216690063,
+      "learning_rate": 6.308713142093749e-06,
+      "loss": 0.0255,
+      "step": 511
+    },
+    {
+      "epoch": 0.6597938144329897,
+      "grad_norm": 2.4420573711395264,
+      "learning_rate": 6.266920757306429e-06,
+      "loss": 0.0248,
+      "step": 512
+    },
+    {
+      "epoch": 0.6610824742268041,
+      "grad_norm": 2.5794460773468018,
+      "learning_rate": 6.225203995775746e-06,
+      "loss": 0.0085,
+      "step": 513
+    },
+    {
+      "epoch": 0.6623711340206185,
+      "grad_norm": 0.4044947922229767,
+      "learning_rate": 6.183563702583506e-06,
+      "loss": 0.0016,
+      "step": 514
+    },
+    {
+      "epoch": 0.663659793814433,
+      "grad_norm": 0.47102847695350647,
+      "learning_rate": 6.1420007212624584e-06,
+      "loss": 0.0011,
+      "step": 515
+    },
+    {
+      "epoch": 0.6649484536082474,
+      "grad_norm": 0.08942103385925293,
+      "learning_rate": 6.100515893779188e-06,
+      "loss": 0.0006,
+      "step": 516
+    },
+    {
+      "epoch": 0.6662371134020618,
+      "grad_norm": 1.772922158241272,
+      "learning_rate": 6.05911006051708e-06,
+      "loss": 0.0078,
+      "step": 517
+    },
+    {
+      "epoch": 0.6675257731958762,
+      "grad_norm": 1.0783969163894653,
+      "learning_rate": 6.01778406025928e-06,
+      "loss": 0.0041,
+      "step": 518
+    },
+    {
+      "epoch": 0.6688144329896907,
+      "grad_norm": 1.0612661838531494,
+      "learning_rate": 5.976538730171708e-06,
+      "loss": 0.0064,
+      "step": 519
+    },
+    {
+      "epoch": 0.6701030927835051,
+      "grad_norm": 3.4996323585510254,
+      "learning_rate": 5.935374905786102e-06,
+      "loss": 0.0078,
+      "step": 520
+    },
+    {
+      "epoch": 0.6701030927835051,
+      "eval_accuracy": 0.997020854021847,
+      "eval_f1": 0.9473684210526315,
+      "eval_loss": 0.014883686788380146,
+      "eval_precision": 0.9473684210526315,
+      "eval_recall": 0.9473684210526315,
+      "eval_runtime": 83.6623,
+      "eval_samples_per_second": 5.439,
+      "eval_steps_per_second": 0.179,
+      "step": 520
+    },
+    {
+      "epoch": 0.6713917525773195,
+      "grad_norm": 4.155304431915283,
+      "learning_rate": 5.89429342098309e-06,
+      "loss": 0.0209,
+      "step": 521
+    },
+    {
+      "epoch": 0.6726804123711341,
+      "grad_norm": 1.2153571844100952,
+      "learning_rate": 5.8532951079752895e-06,
+      "loss": 0.0045,
+      "step": 522
+    },
+    {
+      "epoch": 0.6739690721649485,
+      "grad_norm": 0.23559901118278503,
+      "learning_rate": 5.812380797290465e-06,
+      "loss": 0.0011,
+      "step": 523
+    },
+    {
+      "epoch": 0.6752577319587629,
+      "grad_norm": 0.7906387448310852,
+      "learning_rate": 5.771551317754691e-06,
+      "loss": 0.0016,
+      "step": 524
+    },
+    {
+      "epoch": 0.6765463917525774,
+      "grad_norm": 0.6385716199874878,
+      "learning_rate": 5.730807496475568e-06,
+      "loss": 0.0028,
+      "step": 525
+    },
+    {
+      "epoch": 0.6778350515463918,
+      "grad_norm": 0.6003400087356567,
+      "learning_rate": 5.690150158825462e-06,
+      "loss": 0.0017,
+      "step": 526
+    },
+    {
+      "epoch": 0.6791237113402062,
+      "grad_norm": 0.0828804075717926,
+      "learning_rate": 5.649580128424792e-06,
+      "loss": 0.0013,
+      "step": 527
+    },
+    {
+      "epoch": 0.6804123711340206,
+      "grad_norm": 0.4008159637451172,
+      "learning_rate": 5.609098227125334e-06,
+      "loss": 0.0012,
+      "step": 528
+    },
+    {
+      "epoch": 0.6817010309278351,
+      "grad_norm": 1.0619193315505981,
+      "learning_rate": 5.568705274993584e-06,
+      "loss": 0.0026,
+      "step": 529
+    },
+    {
+      "epoch": 0.6829896907216495,
+      "grad_norm": 0.24862630665302277,
+      "learning_rate": 5.528402090294142e-06,
+      "loss": 0.0013,
+      "step": 530
+    },
+    {
+      "epoch": 0.6842783505154639,
+      "grad_norm": 2.5749034881591797,
+      "learning_rate": 5.488189489473133e-06,
+      "loss": 0.0279,
+      "step": 531
+    },
+    {
+      "epoch": 0.6855670103092784,
+      "grad_norm": 0.7257778644561768,
+      "learning_rate": 5.448068287141663e-06,
+      "loss": 0.0029,
+      "step": 532
+    },
+    {
+      "epoch": 0.6868556701030928,
+      "grad_norm": 0.047684453427791595,
+      "learning_rate": 5.4080392960593355e-06,
+      "loss": 0.0003,
+      "step": 533
+    },
+    {
+      "epoch": 0.6881443298969072,
+      "grad_norm": 2.056273937225342,
+      "learning_rate": 5.368103327117768e-06,
+      "loss": 0.017,
+      "step": 534
+    },
+    {
+      "epoch": 0.6894329896907216,
+      "grad_norm": 2.3359081745147705,
+      "learning_rate": 5.328261189324166e-06,
+      "loss": 0.0234,
+      "step": 535
+    },
+    {
+      "epoch": 0.6907216494845361,
+      "grad_norm": 0.4394116699695587,
+      "learning_rate": 5.288513689784951e-06,
+      "loss": 0.0013,
+      "step": 536
+    },
+    {
+      "epoch": 0.6920103092783505,
+      "grad_norm": 0.6693306565284729,
+      "learning_rate": 5.2488616336893915e-06,
+      "loss": 0.0016,
+      "step": 537
+    },
+    {
+      "epoch": 0.6932989690721649,
+      "grad_norm": 1.8861000537872314,
+      "learning_rate": 5.209305824293307e-06,
+      "loss": 0.0068,
+      "step": 538
+    },
+    {
+      "epoch": 0.6945876288659794,
+      "grad_norm": 1.8001142740249634,
+      "learning_rate": 5.1698470629027845e-06,
+      "loss": 0.0163,
+      "step": 539
+    },
+    {
+      "epoch": 0.6958762886597938,
+      "grad_norm": 1.7382943630218506,
+      "learning_rate": 5.130486148857952e-06,
+      "loss": 0.0291,
+      "step": 540
+    },
+    {
+      "epoch": 0.6958762886597938,
+      "eval_accuracy": 0.9975173783515392,
+      "eval_f1": 0.9557522123893806,
+      "eval_loss": 0.014678677543997765,
+      "eval_precision": 0.9642857142857143,
+      "eval_recall": 0.9473684210526315,
+      "eval_runtime": 83.1931,
+      "eval_samples_per_second": 5.469,
+      "eval_steps_per_second": 0.18,
+      "step": 540
+    },
+    {
+      "epoch": 0.6971649484536082,
+      "grad_norm": 1.584878921508789,
+      "learning_rate": 5.0912238795167845e-06,
+      "loss": 0.0218,
+      "step": 541
+    },
+    {
+      "epoch": 0.6984536082474226,
+      "grad_norm": 0.42845746874809265,
+      "learning_rate": 5.05206105023895e-06,
+      "loss": 0.0022,
+      "step": 542
+    },
+    {
+      "epoch": 0.6997422680412371,
+      "grad_norm": 3.7735812664031982,
+      "learning_rate": 5.012998454369701e-06,
+      "loss": 0.0381,
+      "step": 543
+    },
+    {
+      "epoch": 0.7010309278350515,
+      "grad_norm": 1.2307202816009521,
+      "learning_rate": 4.974036883223798e-06,
+      "loss": 0.0065,
+      "step": 544
+    },
+    {
+      "epoch": 0.7023195876288659,
+      "grad_norm": 0.17536193132400513,
+      "learning_rate": 4.935177126069485e-06,
+      "loss": 0.0006,
+      "step": 545
+    },
+    {
+      "epoch": 0.7036082474226805,
+      "grad_norm": 1.0268815755844116,
+      "learning_rate": 4.896419970112499e-06,
+      "loss": 0.0072,
+      "step": 546
+    },
+    {
+      "epoch": 0.7048969072164949,
+      "grad_norm": 0.6802368760108948,
+      "learning_rate": 4.857766200480115e-06,
+      "loss": 0.0018,
+      "step": 547
+    },
+    {
+      "epoch": 0.7061855670103093,
+      "grad_norm": 0.3945528268814087,
+      "learning_rate": 4.819216600205254e-06,
+      "loss": 0.0019,
+      "step": 548
+    },
+    {
+      "epoch": 0.7074742268041238,
+      "grad_norm": 1.625831127166748,
+      "learning_rate": 4.780771950210616e-06,
+      "loss": 0.0087,
+      "step": 549
+    },
+    {
+      "epoch": 0.7087628865979382,
+      "grad_norm": 1.2541440725326538,
+      "learning_rate": 4.742433029292856e-06,
+      "loss": 0.0031,
+      "step": 550
+    },
+    {
+      "epoch": 0.7100515463917526,
+      "grad_norm": 0.1559123545885086,
+      "learning_rate": 4.704200614106813e-06,
+      "loss": 0.0011,
+      "step": 551
+    },
+    {
+      "epoch": 0.711340206185567,
+      "grad_norm": 1.7901103496551514,
+      "learning_rate": 4.6660754791497755e-06,
+      "loss": 0.008,
+      "step": 552
+    },
+    {
+      "epoch": 0.7126288659793815,
+      "grad_norm": 2.5184080600738525,
+      "learning_rate": 4.628058396745787e-06,
+      "loss": 0.0062,
+      "step": 553
+    },
+    {
+      "epoch": 0.7139175257731959,
+      "grad_norm": 1.7694346904754639,
+      "learning_rate": 4.590150137030009e-06,
+      "loss": 0.0067,
+      "step": 554
+    },
+    {
+      "epoch": 0.7152061855670103,
+      "grad_norm": 0.8861400485038757,
+      "learning_rate": 4.552351467933115e-06,
+      "loss": 0.0027,
+      "step": 555
+    },
+    {
+      "epoch": 0.7164948453608248,
+      "grad_norm": 1.867985725402832,
+      "learning_rate": 4.514663155165731e-06,
+      "loss": 0.0076,
+      "step": 556
+    },
+    {
+      "epoch": 0.7177835051546392,
+      "grad_norm": 0.6749151945114136,
+      "learning_rate": 4.477085962202931e-06,
+      "loss": 0.0026,
+      "step": 557
+    },
+    {
+      "epoch": 0.7190721649484536,
+      "grad_norm": 0.47943294048309326,
+      "learning_rate": 4.439620650268771e-06,
+      "loss": 0.0014,
+      "step": 558
+    },
+    {
+      "epoch": 0.720360824742268,
+      "grad_norm": 0.7041411399841309,
+      "learning_rate": 4.402267978320854e-06,
+      "loss": 0.0024,
+      "step": 559
+    },
+    {
+      "epoch": 0.7216494845360825,
+      "grad_norm": 2.199207067489624,
+      "learning_rate": 4.365028703034976e-06,
+      "loss": 0.0119,
+      "step": 560
+    },
+    {
+      "epoch": 0.7216494845360825,
+      "eval_accuracy": 0.997020854021847,
+      "eval_f1": 0.9473684210526315,
+      "eval_loss": 0.013599889352917671,
+      "eval_precision": 0.9473684210526315,
+      "eval_recall": 0.9473684210526315,
+      "eval_runtime": 84.0133,
+      "eval_samples_per_second": 5.416,
+      "eval_steps_per_second": 0.179,
+      "step": 560
+    },
+    {
+      "epoch": 0.7229381443298969,
+      "grad_norm": 2.070563554763794,
+      "learning_rate": 4.327903578789785e-06,
+      "loss": 0.0297,
+      "step": 561
+    },
+    {
+      "epoch": 0.7242268041237113,
+      "grad_norm": 0.7736282348632812,
+      "learning_rate": 4.290893357651502e-06,
+      "loss": 0.0014,
+      "step": 562
+    },
+    {
+      "epoch": 0.7255154639175257,
+      "grad_norm": 1.5043028593063354,
+      "learning_rate": 4.253998789358683e-06,
+      "loss": 0.0121,
+      "step": 563
+    },
+    {
+      "epoch": 0.7268041237113402,
+      "grad_norm": 2.060772180557251,
+      "learning_rate": 4.217220621307043e-06,
+      "loss": 0.0076,
+      "step": 564
+    },
+    {
+      "epoch": 0.7280927835051546,
+      "grad_norm": 0.3604072034358978,
+      "learning_rate": 4.180559598534297e-06,
+      "loss": 0.0012,
+      "step": 565
+    },
+    {
+      "epoch": 0.729381443298969,
+      "grad_norm": 1.343294382095337,
+      "learning_rate": 4.144016463705081e-06,
+      "loss": 0.0043,
+      "step": 566
+    },
+    {
+      "epoch": 0.7306701030927835,
+      "grad_norm": 1.6220418214797974,
+      "learning_rate": 4.107591957095903e-06,
+      "loss": 0.0232,
+      "step": 567
+    },
+    {
+      "epoch": 0.7319587628865979,
+      "grad_norm": 0.1144634336233139,
+      "learning_rate": 4.071286816580142e-06,
+      "loss": 0.001,
+      "step": 568
+    },
+    {
+      "epoch": 0.7332474226804123,
+      "grad_norm": 0.7282357811927795,
+      "learning_rate": 4.035101777613113e-06,
+      "loss": 0.0018,
+      "step": 569
+    },
+    {
+      "epoch": 0.7345360824742269,
+      "grad_norm": 3.7139105796813965,
+      "learning_rate": 3.999037573217157e-06,
+      "loss": 0.0249,
+      "step": 570
+    },
+    {
+      "epoch": 0.7358247422680413,
+      "grad_norm": 2.923678159713745,
+      "learning_rate": 3.963094933966797e-06,
+      "loss": 0.0207,
+      "step": 571
+    },
+    {
+      "epoch": 0.7371134020618557,
+      "grad_norm": 0.20384177565574646,
+      "learning_rate": 3.927274587973935e-06,
+      "loss": 0.0006,
+      "step": 572
+    },
+    {
+      "epoch": 0.7384020618556701,
+      "grad_norm": 0.675167977809906,
+      "learning_rate": 3.8915772608731066e-06,
+      "loss": 0.0014,
+      "step": 573
+    },
+    {
+      "epoch": 0.7396907216494846,
+      "grad_norm": 3.719918727874756,
+      "learning_rate": 3.856003675806777e-06,
+      "loss": 0.0142,
+      "step": 574
+    },
+    {
+      "epoch": 0.740979381443299,
+      "grad_norm": 0.10527591407299042,
+      "learning_rate": 3.820554553410693e-06,
+      "loss": 0.0006,
+      "step": 575
+    },
+    {
+      "epoch": 0.7422680412371134,
+      "grad_norm": 2.821239948272705,
+      "learning_rate": 3.78523061179929e-06,
+      "loss": 0.0142,
+      "step": 576
+    },
+    {
+      "epoch": 0.7435567010309279,
+      "grad_norm": 0.972940981388092,
+      "learning_rate": 3.7500325665511337e-06,
+      "loss": 0.0039,
+      "step": 577
+    },
+    {
+      "epoch": 0.7448453608247423,
+      "grad_norm": 0.08761493116617203,
+      "learning_rate": 3.7149611306944356e-06,
+      "loss": 0.0008,
+      "step": 578
+    },
+    {
+      "epoch": 0.7461340206185567,
+      "grad_norm": 1.4573255777359009,
+      "learning_rate": 3.680017014692604e-06,
+      "loss": 0.0063,
+      "step": 579
+    },
+    {
+      "epoch": 0.7474226804123711,
+      "grad_norm": 0.7035017609596252,
+      "learning_rate": 3.645200926429844e-06,
+      "loss": 0.002,
+      "step": 580
+    },
+    {
+      "epoch": 0.7474226804123711,
+      "eval_accuracy": 0.9980139026812314,
+      "eval_f1": 0.9642857142857143,
+      "eval_loss": 0.0138359684497118,
+      "eval_precision": 0.9818181818181818,
+      "eval_recall": 0.9473684210526315,
+      "eval_runtime": 83.1039,
+      "eval_samples_per_second": 5.475,
+      "eval_steps_per_second": 0.18,
+      "step": 580
+    },
+    {
+      "epoch": 0.7487113402061856,
+      "grad_norm": 0.15962012112140656,
+      "learning_rate": 3.610513571196832e-06,
+      "loss": 0.0007,
+      "step": 581
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.1321505457162857,
+      "learning_rate": 3.5759556516764205e-06,
+      "loss": 0.0008,
+      "step": 582
+    },
+    {
+      "epoch": 0.7512886597938144,
+      "grad_norm": 0.07236671447753906,
+      "learning_rate": 3.541527867929403e-06,
+      "loss": 0.0004,
+      "step": 583
+    },
+    {
+      "epoch": 0.7525773195876289,
+      "grad_norm": 0.5433388352394104,
+      "learning_rate": 3.507230917380332e-06,
+      "loss": 0.0017,
+      "step": 584
+    },
+    {
+      "epoch": 0.7538659793814433,
+      "grad_norm": 3.733372449874878,
+      "learning_rate": 3.4730654948033957e-06,
+      "loss": 0.0024,
+      "step": 585
+    },
+    {
+      "epoch": 0.7551546391752577,
+      "grad_norm": 4.992002010345459,
+      "learning_rate": 3.4390322923083385e-06,
+      "loss": 0.0182,
+      "step": 586
+    },
+    {
+      "epoch": 0.7564432989690721,
+      "grad_norm": 0.3195149302482605,
+      "learning_rate": 3.4051319993264397e-06,
+      "loss": 0.0009,
+      "step": 587
+    },
+    {
+      "epoch": 0.7577319587628866,
+      "grad_norm": 0.13421054184436798,
+      "learning_rate": 3.3713653025965544e-06,
+      "loss": 0.0008,
+      "step": 588
+    },
+    {
+      "epoch": 0.759020618556701,
+      "grad_norm": 0.12820366024971008,
+      "learning_rate": 3.3377328861511927e-06,
+      "loss": 0.0005,
+      "step": 589
+    },
+    {
+      "epoch": 0.7603092783505154,
+      "grad_norm": 0.8797692060470581,
+      "learning_rate": 3.3042354313026702e-06,
+      "loss": 0.004,
+      "step": 590
+    },
+    {
+      "epoch": 0.7615979381443299,
+      "grad_norm": 0.11013241112232208,
+      "learning_rate": 3.2708736166293064e-06,
+      "loss": 0.0004,
+      "step": 591
+    },
+    {
+      "epoch": 0.7628865979381443,
+      "grad_norm": 0.743179202079773,
+      "learning_rate": 3.237648117961665e-06,
+      "loss": 0.0013,
+      "step": 592
+    },
+    {
+      "epoch": 0.7641752577319587,
+      "grad_norm": 4.201583385467529,
+      "learning_rate": 3.2045596083688814e-06,
+      "loss": 0.0186,
+      "step": 593
+    },
+    {
+      "epoch": 0.7654639175257731,
+      "grad_norm": 1.279377818107605,
+      "learning_rate": 3.1716087581450193e-06,
+      "loss": 0.0031,
+      "step": 594
+    },
+    {
+      "epoch": 0.7667525773195877,
+      "grad_norm": 2.0569307804107666,
+      "learning_rate": 3.1387962347954936e-06,
+      "loss": 0.009,
+      "step": 595
+    },
+    {
+      "epoch": 0.7680412371134021,
+      "grad_norm": 0.5968018174171448,
+      "learning_rate": 3.1061227030235442e-06,
+      "loss": 0.0011,
+      "step": 596
+    },
+    {
+      "epoch": 0.7693298969072165,
+      "grad_norm": 2.1051347255706787,
+      "learning_rate": 3.073588824716777e-06,
+      "loss": 0.005,
+      "step": 597
+    },
+    {
+      "epoch": 0.770618556701031,
+      "grad_norm": 0.3999452292919159,
+      "learning_rate": 3.041195258933749e-06,
+      "loss": 0.0024,
+      "step": 598
+    },
+    {
+      "epoch": 0.7719072164948454,
+      "grad_norm": 1.3566821813583374,
+      "learning_rate": 3.008942661890627e-06,
+      "loss": 0.0027,
+      "step": 599
+    },
+    {
+      "epoch": 0.7731958762886598,
+      "grad_norm": 0.30999279022216797,
+      "learning_rate": 2.976831686947884e-06,
+      "loss": 0.0009,
+      "step": 600
+    },
+    {
+      "epoch": 0.7731958762886598,
+      "eval_accuracy": 0.9980139026812314,
+      "eval_f1": 0.9642857142857143,
+      "eval_loss": 0.013978274539113045,
+      "eval_precision": 0.9818181818181818,
+      "eval_recall": 0.9473684210526315,
+      "eval_runtime": 83.5538,
+      "eval_samples_per_second": 5.446,
+      "eval_steps_per_second": 0.18,
+      "step": 600
     }
   ],
   "logging_steps": 1,
@@ -3838,7 +4598,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6687462625574912e+17,
+  "total_flos": 2.004089890144256e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null