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 sha256:6bdd41feecab147e3702fc9a09ae4f3759d0fd2eaf5075a4794809ea853b57dd
+oid sha256:0e2356ab40c12010f82e0468e01d29e496b88111fe03b82cd7feccd2244f2d76
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f2060b9ac678bc735c6aa21c657746c6a3eb4a708a65a556806c9e6a69997c6
+oid sha256:ccda15c137674757272ca9a1e7faeeeacab02505d67e05c4d7ebe44cc6a4b153
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebff2e905977f2cd428ca1b24f49468350b74d9cb1dcc0461fc80243ceab581f
+oid sha256:5dc157f03faa1207462cb37f715cc653baa805f5c414cfb69f73f1ef19a61118
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49631406cb95eb8f8daf261c6428aa3afdceb3aad5aba318de0a43ed481d41ef
+oid sha256:40f7ba7f95601c31b92888b340de1db5d112c903a5f054ef378fa8d334b109d8
 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:a376864c68cd8140d4a8c8d1313d2085fad00b426c9d7c50f67377d9024c806b
+oid sha256:f8da404dd915ddc5786378001a5d8b341c178642cef0fa5e08b8f3beb67dc7cb
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9094a7c70774e5fb0f079bf19e64d3aeedab732ea28f3fdbd261beb1471e797d
+oid sha256:d5d35bb59f4f49474e830ccd46842fcc6946c9f086e93024ff04f721199acc57
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91267c676fe033603ed303ba35beb8e62450b6e31dad2048d004a26b33530e19
+oid sha256:ac6a1ff009a6db976158959cb8041df84e0cca3b33030728e6faf834e7ec72cf
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3945204a1afc847a21741b668c19c312b7ccf92d58c6fff63a70c9d4b3319dfb
+oid sha256:0699607949cd765eebdf60840d7ed5f0aebefee59edbb9463b802af0f820f2d1
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:076df3ee78299c9288fa283b2488d4715dfacbcac9821b1d2a66d28531d8f15a
+oid sha256:e1854f3cbc2d043054722525ddb7c6d840fe619ac6e722abc90668756a2bf03d
 size 15088

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b361c84c477f7c6235201218f1bc29b4f72aab9464107d1a89dee126263148f
+oid sha256:0ca1b3957819960b03608de19c4085d857ce0ee70b4144698881329d19543373
 size 15088

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9e69d08de85b535829406b9c04296fe936a0eae9bdb9304ab3a2b07dbf3dab6
+oid sha256:26304480186583ed12a61dfc367660400975b17b195ce7f553e02600fcda72cc
 size 15088

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de91bcd34728c2f7b26ffa826160ccbb9c4c2a7079f6d8d402251e4d4d317506
+oid sha256:bf1df145d3bf08ae4663cfb2c2935b2a282725834f65fde0348128bf1964387b
 size 15088

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60135211e354b13f48a59683d9bc3cfc0bb1db62799fa50234aa03cb59f58850
+oid sha256:955e64c88de6579928ca795c761cef4142e056dbf769931deca6f0e3847c6550
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5084745762711864,
+  "epoch": 0.5932203389830508,
   "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": 5.849,
       "eval_steps_per_second": 0.2,
       "step": 600
+    },
+    {
+      "epoch": 0.5093220338983051,
+      "grad_norm": 2.220385789871216,
+      "learning_rate": 1.1415162261042849e-05,
+      "loss": 0.0195,
+      "step": 601
+    },
+    {
+      "epoch": 0.5101694915254237,
+      "grad_norm": 2.395817279815674,
+      "learning_rate": 1.138587197372937e-05,
+      "loss": 0.0189,
+      "step": 602
+    },
+    {
+      "epoch": 0.5110169491525424,
+      "grad_norm": 3.041154146194458,
+      "learning_rate": 1.1356569558853783e-05,
+      "loss": 0.0231,
+      "step": 603
+    },
+    {
+      "epoch": 0.511864406779661,
+      "grad_norm": 2.976128339767456,
+      "learning_rate": 1.1327255272837221e-05,
+      "loss": 0.0335,
+      "step": 604
+    },
+    {
+      "epoch": 0.5127118644067796,
+      "grad_norm": 1.8595855236053467,
+      "learning_rate": 1.1297929372204692e-05,
+      "loss": 0.0115,
+      "step": 605
+    },
+    {
+      "epoch": 0.5135593220338983,
+      "grad_norm": 0.9439570307731628,
+      "learning_rate": 1.1268592113582848e-05,
+      "loss": 0.0045,
+      "step": 606
+    },
+    {
+      "epoch": 0.514406779661017,
+      "grad_norm": 0.2880883514881134,
+      "learning_rate": 1.1239243753697728e-05,
+      "loss": 0.0026,
+      "step": 607
+    },
+    {
+      "epoch": 0.5152542372881356,
+      "grad_norm": 3.2744438648223877,
+      "learning_rate": 1.120988454937252e-05,
+      "loss": 0.0315,
+      "step": 608
+    },
+    {
+      "epoch": 0.5161016949152543,
+      "grad_norm": 0.40230241417884827,
+      "learning_rate": 1.118051475752531e-05,
+      "loss": 0.0024,
+      "step": 609
+    },
+    {
+      "epoch": 0.5169491525423728,
+      "grad_norm": 1.0340898036956787,
+      "learning_rate": 1.115113463516683e-05,
+      "loss": 0.0022,
+      "step": 610
+    },
+    {
+      "epoch": 0.5177966101694915,
+      "grad_norm": 1.4035919904708862,
+      "learning_rate": 1.112174443939822e-05,
+      "loss": 0.0084,
+      "step": 611
+    },
+    {
+      "epoch": 0.5186440677966102,
+      "grad_norm": 1.525558590888977,
+      "learning_rate": 1.1092344427408767e-05,
+      "loss": 0.0205,
+      "step": 612
+    },
+    {
+      "epoch": 0.5194915254237288,
+      "grad_norm": 0.6529274582862854,
+      "learning_rate": 1.1062934856473655e-05,
+      "loss": 0.0044,
+      "step": 613
+    },
+    {
+      "epoch": 0.5203389830508475,
+      "grad_norm": 0.5694882273674011,
+      "learning_rate": 1.1033515983951722e-05,
+      "loss": 0.0066,
+      "step": 614
+    },
+    {
+      "epoch": 0.5211864406779662,
+      "grad_norm": 0.8706492781639099,
+      "learning_rate": 1.10040880672832e-05,
+      "loss": 0.0042,
+      "step": 615
+    },
+    {
+      "epoch": 0.5220338983050847,
+      "grad_norm": 1.458556056022644,
+      "learning_rate": 1.0974651363987465e-05,
+      "loss": 0.0052,
+      "step": 616
+    },
+    {
+      "epoch": 0.5228813559322034,
+      "grad_norm": 2.5780954360961914,
+      "learning_rate": 1.0945206131660787e-05,
+      "loss": 0.0284,
+      "step": 617
+    },
+    {
+      "epoch": 0.523728813559322,
+      "grad_norm": 1.741313099861145,
+      "learning_rate": 1.0915752627974068e-05,
+      "loss": 0.017,
+      "step": 618
+    },
+    {
+      "epoch": 0.5245762711864407,
+      "grad_norm": 0.1626061648130417,
+      "learning_rate": 1.0886291110670592e-05,
+      "loss": 0.0012,
+      "step": 619
+    },
+    {
+      "epoch": 0.5254237288135594,
+      "grad_norm": 1.2944737672805786,
+      "learning_rate": 1.085682183756377e-05,
+      "loss": 0.012,
+      "step": 620
+    },
+    {
+      "epoch": 0.5254237288135594,
+      "eval_accuracy": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 0.00011476398503873497,
+      "eval_precision": 1.0,
+      "eval_recall": 1.0,
+      "eval_runtime": 49.5926,
+      "eval_samples_per_second": 5.888,
+      "eval_steps_per_second": 0.202,
+      "step": 620
+    },
+    {
+      "epoch": 0.5262711864406779,
+      "grad_norm": 0.913479208946228,
+      "learning_rate": 1.0827345066534887e-05,
+      "loss": 0.0033,
+      "step": 621
+    },
+    {
+      "epoch": 0.5271186440677966,
+      "grad_norm": 1.1390260457992554,
+      "learning_rate": 1.0797861055530832e-05,
+      "loss": 0.0083,
+      "step": 622
+    },
+    {
+      "epoch": 0.5279661016949152,
+      "grad_norm": 0.6345875263214111,
+      "learning_rate": 1.076837006256186e-05,
+      "loss": 0.0054,
+      "step": 623
+    },
+    {
+      "epoch": 0.5288135593220339,
+      "grad_norm": 1.8191931247711182,
+      "learning_rate": 1.0738872345699314e-05,
+      "loss": 0.0087,
+      "step": 624
+    },
+    {
+      "epoch": 0.5296610169491526,
+      "grad_norm": 0.6184027791023254,
+      "learning_rate": 1.0709368163073385e-05,
+      "loss": 0.0041,
+      "step": 625
+    },
+    {
+      "epoch": 0.5305084745762711,
+      "grad_norm": 0.8594485521316528,
+      "learning_rate": 1.0679857772870845e-05,
+      "loss": 0.0101,
+      "step": 626
+    },
+    {
+      "epoch": 0.5313559322033898,
+      "grad_norm": 1.234549880027771,
+      "learning_rate": 1.0650341433332778e-05,
+      "loss": 0.0075,
+      "step": 627
+    },
+    {
+      "epoch": 0.5322033898305085,
+      "grad_norm": 0.6435002088546753,
+      "learning_rate": 1.062081940275234e-05,
+      "loss": 0.0061,
+      "step": 628
+    },
+    {
+      "epoch": 0.5330508474576271,
+      "grad_norm": 2.0458498001098633,
+      "learning_rate": 1.0591291939472487e-05,
+      "loss": 0.0129,
+      "step": 629
+    },
+    {
+      "epoch": 0.5338983050847458,
+      "grad_norm": 2.5087852478027344,
+      "learning_rate": 1.0561759301883714e-05,
+      "loss": 0.0246,
+      "step": 630
+    },
+    {
+      "epoch": 0.5347457627118644,
+      "grad_norm": 1.4174385070800781,
+      "learning_rate": 1.0532221748421786e-05,
+      "loss": 0.0176,
+      "step": 631
+    },
+    {
+      "epoch": 0.535593220338983,
+      "grad_norm": 1.510528802871704,
+      "learning_rate": 1.0502679537565507e-05,
+      "loss": 0.0134,
+      "step": 632
+    },
+    {
+      "epoch": 0.5364406779661017,
+      "grad_norm": 1.4558008909225464,
+      "learning_rate": 1.047313292783442e-05,
+      "loss": 0.0092,
+      "step": 633
+    },
+    {
+      "epoch": 0.5372881355932203,
+      "grad_norm": 0.5714721083641052,
+      "learning_rate": 1.0443582177786564e-05,
+      "loss": 0.0028,
+      "step": 634
+    },
+    {
+      "epoch": 0.538135593220339,
+      "grad_norm": 0.8509529829025269,
+      "learning_rate": 1.0414027546016223e-05,
+      "loss": 0.0053,
+      "step": 635
+    },
+    {
+      "epoch": 0.5389830508474577,
+      "grad_norm": 1.3928581476211548,
+      "learning_rate": 1.0384469291151628e-05,
+      "loss": 0.0048,
+      "step": 636
+    },
+    {
+      "epoch": 0.5398305084745763,
+      "grad_norm": 1.8540736436843872,
+      "learning_rate": 1.0354907671852733e-05,
+      "loss": 0.0116,
+      "step": 637
+    },
+    {
+      "epoch": 0.5406779661016949,
+      "grad_norm": 0.5891087651252747,
+      "learning_rate": 1.0325342946808923e-05,
+      "loss": 0.005,
+      "step": 638
+    },
+    {
+      "epoch": 0.5415254237288135,
+      "grad_norm": 2.605158805847168,
+      "learning_rate": 1.029577537473677e-05,
+      "loss": 0.0089,
+      "step": 639
+    },
+    {
+      "epoch": 0.5423728813559322,
+      "grad_norm": 1.4306203126907349,
+      "learning_rate": 1.026620521437775e-05,
+      "loss": 0.006,
+      "step": 640
+    },
+    {
+      "epoch": 0.5423728813559322,
+      "eval_accuracy": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 0.00012067957868566737,
+      "eval_precision": 1.0,
+      "eval_recall": 1.0,
+      "eval_runtime": 49.6065,
+      "eval_samples_per_second": 5.886,
+      "eval_steps_per_second": 0.202,
+      "step": 640
+    },
+    {
+      "epoch": 0.5432203389830509,
+      "grad_norm": 2.7418384552001953,
+      "learning_rate": 1.0236632724495995e-05,
+      "loss": 0.0281,
+      "step": 641
+    },
+    {
+      "epoch": 0.5440677966101695,
+      "grad_norm": 2.0800535678863525,
+      "learning_rate": 1.0207058163876021e-05,
+      "loss": 0.0117,
+      "step": 642
+    },
+    {
+      "epoch": 0.5449152542372881,
+      "grad_norm": 1.9006716012954712,
+      "learning_rate": 1.0177481791320463e-05,
+      "loss": 0.0084,
+      "step": 643
+    },
+    {
+      "epoch": 0.5457627118644067,
+      "grad_norm": 0.9068240523338318,
+      "learning_rate": 1.0147903865647814e-05,
+      "loss": 0.0073,
+      "step": 644
+    },
+    {
+      "epoch": 0.5466101694915254,
+      "grad_norm": 0.5592976808547974,
+      "learning_rate": 1.0118324645690161e-05,
+      "loss": 0.004,
+      "step": 645
+    },
+    {
+      "epoch": 0.5474576271186441,
+      "grad_norm": 1.2031232118606567,
+      "learning_rate": 1.008874439029091e-05,
+      "loss": 0.0031,
+      "step": 646
+    },
+    {
+      "epoch": 0.5483050847457627,
+      "grad_norm": 1.0401791334152222,
+      "learning_rate": 1.0059163358302537e-05,
+      "loss": 0.0066,
+      "step": 647
+    },
+    {
+      "epoch": 0.5491525423728814,
+      "grad_norm": 1.2891989946365356,
+      "learning_rate": 1.0029581808584298e-05,
+      "loss": 0.0113,
+      "step": 648
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 2.2454192638397217,
+      "learning_rate": 1e-05,
+      "loss": 0.0186,
+      "step": 649
+    },
+    {
+      "epoch": 0.5508474576271186,
+      "grad_norm": 1.310914158821106,
+      "learning_rate": 9.970418191415703e-06,
+      "loss": 0.0076,
+      "step": 650
+    },
+    {
+      "epoch": 0.5516949152542373,
+      "grad_norm": 1.0773290395736694,
+      "learning_rate": 9.940836641697465e-06,
+      "loss": 0.0064,
+      "step": 651
+    },
+    {
+      "epoch": 0.5525423728813559,
+      "grad_norm": 1.1092021465301514,
+      "learning_rate": 9.911255609709089e-06,
+      "loss": 0.014,
+      "step": 652
+    },
+    {
+      "epoch": 0.5533898305084746,
+      "grad_norm": 1.551621437072754,
+      "learning_rate": 9.88167535430984e-06,
+      "loss": 0.0138,
+      "step": 653
+    },
+    {
+      "epoch": 0.5542372881355933,
+      "grad_norm": 0.6066732406616211,
+      "learning_rate": 9.852096134352186e-06,
+      "loss": 0.0036,
+      "step": 654
+    },
+    {
+      "epoch": 0.5550847457627118,
+      "grad_norm": 1.743664026260376,
+      "learning_rate": 9.822518208679542e-06,
+      "loss": 0.0206,
+      "step": 655
+    },
+    {
+      "epoch": 0.5559322033898305,
+      "grad_norm": 0.5602774620056152,
+      "learning_rate": 9.792941836123984e-06,
+      "loss": 0.002,
+      "step": 656
+    },
+    {
+      "epoch": 0.5567796610169492,
+      "grad_norm": 0.8597205877304077,
+      "learning_rate": 9.76336727550401e-06,
+      "loss": 0.0057,
+      "step": 657
+    },
+    {
+      "epoch": 0.5576271186440678,
+      "grad_norm": 1.2528083324432373,
+      "learning_rate": 9.733794785622254e-06,
+      "loss": 0.0095,
+      "step": 658
+    },
+    {
+      "epoch": 0.5584745762711865,
+      "grad_norm": 2.5552995204925537,
+      "learning_rate": 9.704224625263233e-06,
+      "loss": 0.0174,
+      "step": 659
+    },
+    {
+      "epoch": 0.559322033898305,
+      "grad_norm": 0.4139198362827301,
+      "learning_rate": 9.674657053191079e-06,
+      "loss": 0.0025,
+      "step": 660
+    },
+    {
+      "epoch": 0.559322033898305,
+      "eval_accuracy": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 0.00013073084119241685,
+      "eval_precision": 1.0,
+      "eval_recall": 1.0,
+      "eval_runtime": 52.9786,
+      "eval_samples_per_second": 5.512,
+      "eval_steps_per_second": 0.189,
+      "step": 660
+    },
+    {
+      "epoch": 0.5601694915254237,
+      "grad_norm": 1.9302622079849243,
+      "learning_rate": 9.64509232814727e-06,
+      "loss": 0.0225,
+      "step": 661
+    },
+    {
+      "epoch": 0.5610169491525424,
+      "grad_norm": 1.2856723070144653,
+      "learning_rate": 9.615530708848373e-06,
+      "loss": 0.0099,
+      "step": 662
+    },
+    {
+      "epoch": 0.561864406779661,
+      "grad_norm": 2.7380619049072266,
+      "learning_rate": 9.585972453983779e-06,
+      "loss": 0.0136,
+      "step": 663
+    },
+    {
+      "epoch": 0.5627118644067797,
+      "grad_norm": 1.488617181777954,
+      "learning_rate": 9.556417822213436e-06,
+      "loss": 0.0139,
+      "step": 664
+    },
+    {
+      "epoch": 0.5635593220338984,
+      "grad_norm": 0.7547746300697327,
+      "learning_rate": 9.52686707216558e-06,
+      "loss": 0.0039,
+      "step": 665
+    },
+    {
+      "epoch": 0.5644067796610169,
+      "grad_norm": 1.0919615030288696,
+      "learning_rate": 9.497320462434498e-06,
+      "loss": 0.0112,
+      "step": 666
+    },
+    {
+      "epoch": 0.5652542372881356,
+      "grad_norm": 0.737077534198761,
+      "learning_rate": 9.467778251578217e-06,
+      "loss": 0.0054,
+      "step": 667
+    },
+    {
+      "epoch": 0.5661016949152542,
+      "grad_norm": 0.8337336778640747,
+      "learning_rate": 9.438240698116291e-06,
+      "loss": 0.0073,
+      "step": 668
+    },
+    {
+      "epoch": 0.5669491525423729,
+      "grad_norm": 0.32100099325180054,
+      "learning_rate": 9.408708060527515e-06,
+      "loss": 0.0014,
+      "step": 669
+    },
+    {
+      "epoch": 0.5677966101694916,
+      "grad_norm": 3.1640625,
+      "learning_rate": 9.379180597247661e-06,
+      "loss": 0.0172,
+      "step": 670
+    },
+    {
+      "epoch": 0.5686440677966101,
+      "grad_norm": 0.860525906085968,
+      "learning_rate": 9.349658566667225e-06,
+      "loss": 0.0055,
+      "step": 671
+    },
+    {
+      "epoch": 0.5694915254237288,
+      "grad_norm": 1.1916359663009644,
+      "learning_rate": 9.320142227129158e-06,
+      "loss": 0.0115,
+      "step": 672
+    },
+    {
+      "epoch": 0.5703389830508474,
+      "grad_norm": 0.5801283717155457,
+      "learning_rate": 9.290631836926616e-06,
+      "loss": 0.003,
+      "step": 673
+    },
+    {
+      "epoch": 0.5711864406779661,
+      "grad_norm": 1.943459391593933,
+      "learning_rate": 9.261127654300689e-06,
+      "loss": 0.0193,
+      "step": 674
+    },
+    {
+      "epoch": 0.5720338983050848,
+      "grad_norm": 0.7220546007156372,
+      "learning_rate": 9.231629937438142e-06,
+      "loss": 0.0039,
+      "step": 675
+    },
+    {
+      "epoch": 0.5728813559322034,
+      "grad_norm": 2.289808511734009,
+      "learning_rate": 9.202138944469168e-06,
+      "loss": 0.0165,
+      "step": 676
+    },
+    {
+      "epoch": 0.573728813559322,
+      "grad_norm": 0.4558367431163788,
+      "learning_rate": 9.172654933465114e-06,
+      "loss": 0.0028,
+      "step": 677
+    },
+    {
+      "epoch": 0.5745762711864407,
+      "grad_norm": 0.68553626537323,
+      "learning_rate": 9.143178162436232e-06,
+      "loss": 0.0034,
+      "step": 678
+    },
+    {
+      "epoch": 0.5754237288135593,
+      "grad_norm": 1.1303017139434814,
+      "learning_rate": 9.113708889329413e-06,
+      "loss": 0.0075,
+      "step": 679
+    },
+    {
+      "epoch": 0.576271186440678,
+      "grad_norm": 0.9036606550216675,
+      "learning_rate": 9.084247372025938e-06,
+      "loss": 0.0055,
+      "step": 680
+    },
+    {
+      "epoch": 0.576271186440678,
+      "eval_accuracy": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 0.0001349969388684258,
+      "eval_precision": 1.0,
+      "eval_recall": 1.0,
+      "eval_runtime": 50.0561,
+      "eval_samples_per_second": 5.833,
+      "eval_steps_per_second": 0.2,
+      "step": 680
+    },
+    {
+      "epoch": 0.5771186440677966,
+      "grad_norm": 1.685551404953003,
+      "learning_rate": 9.054793868339218e-06,
+      "loss": 0.0116,
+      "step": 681
+    },
+    {
+      "epoch": 0.5779661016949152,
+      "grad_norm": 0.9484760761260986,
+      "learning_rate": 9.025348636012537e-06,
+      "loss": 0.0047,
+      "step": 682
+    },
+    {
+      "epoch": 0.5788135593220339,
+      "grad_norm": 1.4319676160812378,
+      "learning_rate": 8.995911932716803e-06,
+      "loss": 0.0148,
+      "step": 683
+    },
+    {
+      "epoch": 0.5796610169491525,
+      "grad_norm": 0.5585588812828064,
+      "learning_rate": 8.966484016048282e-06,
+      "loss": 0.0024,
+      "step": 684
+    },
+    {
+      "epoch": 0.5805084745762712,
+      "grad_norm": 2.1300556659698486,
+      "learning_rate": 8.937065143526349e-06,
+      "loss": 0.0135,
+      "step": 685
+    },
+    {
+      "epoch": 0.5813559322033899,
+      "grad_norm": 0.46091559529304504,
+      "learning_rate": 8.907655572591235e-06,
+      "loss": 0.0026,
+      "step": 686
+    },
+    {
+      "epoch": 0.5822033898305085,
+      "grad_norm": 0.28531086444854736,
+      "learning_rate": 8.878255560601781e-06,
+      "loss": 0.0015,
+      "step": 687
+    },
+    {
+      "epoch": 0.5830508474576271,
+      "grad_norm": 2.4347126483917236,
+      "learning_rate": 8.84886536483317e-06,
+      "loss": 0.0144,
+      "step": 688
+    },
+    {
+      "epoch": 0.5838983050847457,
+      "grad_norm": 1.346192717552185,
+      "learning_rate": 8.819485242474696e-06,
+      "loss": 0.0037,
+      "step": 689
+    },
+    {
+      "epoch": 0.5847457627118644,
+      "grad_norm": 1.6517138481140137,
+      "learning_rate": 8.790115450627486e-06,
+      "loss": 0.0151,
+      "step": 690
+    },
+    {
+      "epoch": 0.5855932203389831,
+      "grad_norm": 1.451384425163269,
+      "learning_rate": 8.760756246302277e-06,
+      "loss": 0.0183,
+      "step": 691
+    },
+    {
+      "epoch": 0.5864406779661017,
+      "grad_norm": 0.25365039706230164,
+      "learning_rate": 8.731407886417155e-06,
+      "loss": 0.0009,
+      "step": 692
+    },
+    {
+      "epoch": 0.5872881355932204,
+      "grad_norm": 2.36940860748291,
+      "learning_rate": 8.70207062779531e-06,
+      "loss": 0.0259,
+      "step": 693
+    },
+    {
+      "epoch": 0.588135593220339,
+      "grad_norm": 0.5836230516433716,
+      "learning_rate": 8.672744727162782e-06,
+      "loss": 0.0034,
+      "step": 694
+    },
+    {
+      "epoch": 0.5889830508474576,
+      "grad_norm": 0.7795729637145996,
+      "learning_rate": 8.64343044114622e-06,
+      "loss": 0.005,
+      "step": 695
+    },
+    {
+      "epoch": 0.5898305084745763,
+      "grad_norm": 0.3191084563732147,
+      "learning_rate": 8.614128026270633e-06,
+      "loss": 0.0014,
+      "step": 696
+    },
+    {
+      "epoch": 0.5906779661016949,
+      "grad_norm": 0.7273288369178772,
+      "learning_rate": 8.584837738957155e-06,
+      "loss": 0.0025,
+      "step": 697
+    },
+    {
+      "epoch": 0.5915254237288136,
+      "grad_norm": 1.6525626182556152,
+      "learning_rate": 8.555559835520786e-06,
+      "loss": 0.0059,
+      "step": 698
+    },
+    {
+      "epoch": 0.5923728813559322,
+      "grad_norm": 0.7382212281227112,
+      "learning_rate": 8.526294572168157e-06,
+      "loss": 0.0026,
+      "step": 699
+    },
+    {
+      "epoch": 0.5932203389830508,
+      "grad_norm": 3.2163925170898438,
+      "learning_rate": 8.497042204995299e-06,
+      "loss": 0.0116,
+      "step": 700
+    },
+    {
+      "epoch": 0.5932203389830508,
+      "eval_accuracy": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 9.157847671303898e-05,
+      "eval_precision": 1.0,
+      "eval_recall": 1.0,
+      "eval_runtime": 49.7798,
+      "eval_samples_per_second": 5.866,
+      "eval_steps_per_second": 0.201,
+      "step": 700
     }
   ],
   "logging_steps": 1,
@@ -4598,7 +5358,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.849773217934213e+17,
+  "total_flos": 2.1575362459520205e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null