Training in progress, step 2100, checkpoint

last-checkpoint/optimizer_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57679cf778ba537aeea578f70353e820b9382b2a2be4627254211aa6cfb8e390
+oid sha256:0c0d62d2028703955c4f3d646339860dd0bbceb4a15725c168f6c84c55250b8f
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6aeec08f98512bc94601dc214d175cc82ac88ce864ae5430b96b84926e6e219
+oid sha256:d44131d1bcd453d009ee709ae3eb6b0b5c95455ebb3aa7223868da1ad2ab97af
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88321e77ba72c5578bbc496d6b61b50c73a323a5a68b403c9f3c585e85844543
+oid sha256:4379faa5b7d55d3a4badc78bcd294998819883a2d59ff2b111187bdcd4d95a4a
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b48f2f593736a9b12d52a6de321721008657384076f076397da2ced8b72c608f
+oid sha256:846544fc898fcaab3118bb5b0a59beea20abcf3d8ac45a447b88009c0f350e89
 size 13990904

last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cc82f8a10ecca23bfc2f9751158c857ec0f70f5f2a3ffd66cc332d5897ffe94
+oid sha256:be9252d8d0768775db03040718884e0b2bd7b5f6fa6171efc55534699f467b80
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:985b48185943e53515857456865cf7e3c7b896985b6688ec0d33f5b8282645e4
+oid sha256:e2768dd0f6729301a0a5792ec6ddcde386903d87c3257eecbe4d6d10e2683368
 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:ebeab2a0e156968cd3cc3b8b97b0f48a1fea2e7d631e99ee0879c63bf77e4219
+oid sha256:502f8e3c49fc009af8dd78f612ddb43cfa4a8c39a7095adec01b2e78b3e606ae
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e08c6bb0b0fda4234313649a35f7bb1b0877fbdd2d27fa8101979450ddd85b5
+oid sha256:fdee8e3523c4af3d4e2e67b16018e17acd8fd309073149132e4fcd811e32be23
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9c6a40ac1fe35a4dd1f410a7930a66b4807dae1faf616ecd9809861c98a2e40
+oid sha256:c4cc453eb36c5b4b199fa46cfa81de79a85081e0d52daf6abcd21f6e148da39a
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b43b812a16e1735eee38ee9f7cae38b9cc46e01d6424d7043ab347c53fd353a
+oid sha256:3ed11393b53ac60ffc874c8cb15088bc7892ceb270c99092eec2f7c0ee6ad586
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64063215e63df011a81965924df151473570bc8c8bdc639b6c42eee60177072f
+oid sha256:f3e08b0e0c75bcbdf0bce090d48cac5fce1396aef2e9b4728153f6e8afc305ef
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:116417f6ab2237a6b8155ab260754e19e52b6a7c2f5ac6dd05ab278a940fbb13
+oid sha256:5bba7a57cc6bd4c4d7481da393f27921e77b361eb75d83c66e814992ac2a0f11
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:178e615fcb785a6bd2dfa63ffeb788137b68a5a6696362adf9997eb7be4976a3
+oid sha256:5d50b83278cc41509b62ba992a64a52719571e26ec2f84675ee1c0515e5db440
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2950940612320177,
+  "epoch": 0.3098487642936186,
   "eval_steps": 20,
-  "global_step": 2000,
+  "global_step": 2100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -15219,6 +15219,766 @@
       "eval_samples_per_second": 5.896,
       "eval_steps_per_second": 0.203,
       "step": 2000
+    },
+    {
+      "epoch": 0.29524160826263374,
+      "grad_norm": 1.9098221063613892,
+      "learning_rate": 1.7766432616271263e-05,
+      "loss": 0.0981,
+      "step": 2001
+    },
+    {
+      "epoch": 0.2953891552932497,
+      "grad_norm": 2.293426513671875,
+      "learning_rate": 1.776318676403377e-05,
+      "loss": 0.0471,
+      "step": 2002
+    },
+    {
+      "epoch": 0.29553670232386575,
+      "grad_norm": 2.658841133117676,
+      "learning_rate": 1.7759938852008368e-05,
+      "loss": 0.1074,
+      "step": 2003
+    },
+    {
+      "epoch": 0.29568424935448173,
+      "grad_norm": 1.2824565172195435,
+      "learning_rate": 1.7756688881056824e-05,
+      "loss": 0.077,
+      "step": 2004
+    },
+    {
+      "epoch": 0.29583179638509777,
+      "grad_norm": 2.054882287979126,
+      "learning_rate": 1.775343685204144e-05,
+      "loss": 0.0397,
+      "step": 2005
+    },
+    {
+      "epoch": 0.29597934341571375,
+      "grad_norm": 2.451122522354126,
+      "learning_rate": 1.775018276582508e-05,
+      "loss": 0.0876,
+      "step": 2006
+    },
+    {
+      "epoch": 0.2961268904463298,
+      "grad_norm": 1.9787144660949707,
+      "learning_rate": 1.774692662327113e-05,
+      "loss": 0.077,
+      "step": 2007
+    },
+    {
+      "epoch": 0.29627443747694576,
+      "grad_norm": 1.9749809503555298,
+      "learning_rate": 1.7743668425243547e-05,
+      "loss": 0.0536,
+      "step": 2008
+    },
+    {
+      "epoch": 0.2964219845075618,
+      "grad_norm": 1.7527657747268677,
+      "learning_rate": 1.7740408172606808e-05,
+      "loss": 0.0643,
+      "step": 2009
+    },
+    {
+      "epoch": 0.2965695315381778,
+      "grad_norm": 2.3230299949645996,
+      "learning_rate": 1.7737145866225958e-05,
+      "loss": 0.09,
+      "step": 2010
+    },
+    {
+      "epoch": 0.2967170785687938,
+      "grad_norm": 2.791459798812866,
+      "learning_rate": 1.7733881506966574e-05,
+      "loss": 0.0614,
+      "step": 2011
+    },
+    {
+      "epoch": 0.2968646255994098,
+      "grad_norm": 1.4842112064361572,
+      "learning_rate": 1.7730615095694777e-05,
+      "loss": 0.0651,
+      "step": 2012
+    },
+    {
+      "epoch": 0.29701217263002583,
+      "grad_norm": 1.992242693901062,
+      "learning_rate": 1.772734663327724e-05,
+      "loss": 0.0689,
+      "step": 2013
+    },
+    {
+      "epoch": 0.2971597196606418,
+      "grad_norm": 1.381278157234192,
+      "learning_rate": 1.7724076120581174e-05,
+      "loss": 0.0315,
+      "step": 2014
+    },
+    {
+      "epoch": 0.29730726669125784,
+      "grad_norm": 2.3684511184692383,
+      "learning_rate": 1.772080355847434e-05,
+      "loss": 0.0675,
+      "step": 2015
+    },
+    {
+      "epoch": 0.2974548137218738,
+      "grad_norm": 3.954451560974121,
+      "learning_rate": 1.771752894782504e-05,
+      "loss": 0.0626,
+      "step": 2016
+    },
+    {
+      "epoch": 0.29760236075248986,
+      "grad_norm": 1.9097782373428345,
+      "learning_rate": 1.7714252289502115e-05,
+      "loss": 0.0554,
+      "step": 2017
+    },
+    {
+      "epoch": 0.29774990778310584,
+      "grad_norm": 1.399617314338684,
+      "learning_rate": 1.7710973584374952e-05,
+      "loss": 0.023,
+      "step": 2018
+    },
+    {
+      "epoch": 0.2978974548137219,
+      "grad_norm": 2.006929636001587,
+      "learning_rate": 1.7707692833313485e-05,
+      "loss": 0.0436,
+      "step": 2019
+    },
+    {
+      "epoch": 0.2980450018443379,
+      "grad_norm": 1.7862168550491333,
+      "learning_rate": 1.7704410037188185e-05,
+      "loss": 0.0647,
+      "step": 2020
+    },
+    {
+      "epoch": 0.2980450018443379,
+      "eval_accuracy": 0.9739507959479016,
+      "eval_f1": 0.9547738693467337,
+      "eval_loss": 0.07232852280139923,
+      "eval_precision": 0.9895833333333334,
+      "eval_recall": 0.9223300970873787,
+      "eval_runtime": 50.3001,
+      "eval_samples_per_second": 5.785,
+      "eval_steps_per_second": 0.199,
+      "step": 2020
+    },
+    {
+      "epoch": 0.2981925488749539,
+      "grad_norm": 4.871994495391846,
+      "learning_rate": 1.770112519687007e-05,
+      "loss": 0.1089,
+      "step": 2021
+    },
+    {
+      "epoch": 0.2983400959055699,
+      "grad_norm": 3.192202568054199,
+      "learning_rate": 1.76978383132307e-05,
+      "loss": 0.1199,
+      "step": 2022
+    },
+    {
+      "epoch": 0.2984876429361859,
+      "grad_norm": 2.528630495071411,
+      "learning_rate": 1.7694549387142177e-05,
+      "loss": 0.0659,
+      "step": 2023
+    },
+    {
+      "epoch": 0.29863518996680194,
+      "grad_norm": 2.4678826332092285,
+      "learning_rate": 1.769125841947714e-05,
+      "loss": 0.0606,
+      "step": 2024
+    },
+    {
+      "epoch": 0.2987827369974179,
+      "grad_norm": 2.455389976501465,
+      "learning_rate": 1.7687965411108778e-05,
+      "loss": 0.0696,
+      "step": 2025
+    },
+    {
+      "epoch": 0.29893028402803395,
+      "grad_norm": 3.206726312637329,
+      "learning_rate": 1.768467036291081e-05,
+      "loss": 0.0488,
+      "step": 2026
+    },
+    {
+      "epoch": 0.29907783105864993,
+      "grad_norm": 1.5881465673446655,
+      "learning_rate": 1.768137327575751e-05,
+      "loss": 0.0653,
+      "step": 2027
+    },
+    {
+      "epoch": 0.29922537808926597,
+      "grad_norm": 1.4814188480377197,
+      "learning_rate": 1.767807415052369e-05,
+      "loss": 0.0351,
+      "step": 2028
+    },
+    {
+      "epoch": 0.29937292511988195,
+      "grad_norm": 0.7718455791473389,
+      "learning_rate": 1.7674772988084688e-05,
+      "loss": 0.0225,
+      "step": 2029
+    },
+    {
+      "epoch": 0.299520472150498,
+      "grad_norm": 2.762436628341675,
+      "learning_rate": 1.7671469789316397e-05,
+      "loss": 0.0939,
+      "step": 2030
+    },
+    {
+      "epoch": 0.29966801918111396,
+      "grad_norm": 0.6224008202552795,
+      "learning_rate": 1.7668164555095252e-05,
+      "loss": 0.0077,
+      "step": 2031
+    },
+    {
+      "epoch": 0.29981556621173,
+      "grad_norm": 2.458287239074707,
+      "learning_rate": 1.7664857286298224e-05,
+      "loss": 0.0426,
+      "step": 2032
+    },
+    {
+      "epoch": 0.299963113242346,
+      "grad_norm": 1.0516847372055054,
+      "learning_rate": 1.766154798380281e-05,
+      "loss": 0.0511,
+      "step": 2033
+    },
+    {
+      "epoch": 0.300110660272962,
+      "grad_norm": 2.5216686725616455,
+      "learning_rate": 1.7658236648487074e-05,
+      "loss": 0.1235,
+      "step": 2034
+    },
+    {
+      "epoch": 0.300258207303578,
+      "grad_norm": 1.444677710533142,
+      "learning_rate": 1.7654923281229598e-05,
+      "loss": 0.0572,
+      "step": 2035
+    },
+    {
+      "epoch": 0.30040575433419403,
+      "grad_norm": 1.2242169380187988,
+      "learning_rate": 1.765160788290951e-05,
+      "loss": 0.0316,
+      "step": 2036
+    },
+    {
+      "epoch": 0.30055330136481,
+      "grad_norm": 2.5934975147247314,
+      "learning_rate": 1.7648290454406475e-05,
+      "loss": 0.0302,
+      "step": 2037
+    },
+    {
+      "epoch": 0.30070084839542605,
+      "grad_norm": 1.539410948753357,
+      "learning_rate": 1.7644970996600706e-05,
+      "loss": 0.0423,
+      "step": 2038
+    },
+    {
+      "epoch": 0.300848395426042,
+      "grad_norm": 2.736931085586548,
+      "learning_rate": 1.7641649510372938e-05,
+      "loss": 0.0485,
+      "step": 2039
+    },
+    {
+      "epoch": 0.30099594245665806,
+      "grad_norm": 3.35821795463562,
+      "learning_rate": 1.7638325996604456e-05,
+      "loss": 0.0637,
+      "step": 2040
+    },
+    {
+      "epoch": 0.30099594245665806,
+      "eval_accuracy": 0.975397973950796,
+      "eval_f1": 0.9584352078239609,
+      "eval_loss": 0.06988977640867233,
+      "eval_precision": 0.9655172413793104,
+      "eval_recall": 0.9514563106796117,
+      "eval_runtime": 50.3385,
+      "eval_samples_per_second": 5.781,
+      "eval_steps_per_second": 0.199,
+      "step": 2040
+    },
+    {
+      "epoch": 0.30114348948727404,
+      "grad_norm": 1.4133102893829346,
+      "learning_rate": 1.7635000456177085e-05,
+      "loss": 0.0186,
+      "step": 2041
+    },
+    {
+      "epoch": 0.3012910365178901,
+      "grad_norm": 3.4392263889312744,
+      "learning_rate": 1.7631672889973173e-05,
+      "loss": 0.0771,
+      "step": 2042
+    },
+    {
+      "epoch": 0.3014385835485061,
+      "grad_norm": 3.163463830947876,
+      "learning_rate": 1.7628343298875626e-05,
+      "loss": 0.0355,
+      "step": 2043
+    },
+    {
+      "epoch": 0.3015861305791221,
+      "grad_norm": 3.125253200531006,
+      "learning_rate": 1.7625011683767867e-05,
+      "loss": 0.1054,
+      "step": 2044
+    },
+    {
+      "epoch": 0.3017336776097381,
+      "grad_norm": 3.791630744934082,
+      "learning_rate": 1.7621678045533873e-05,
+      "loss": 0.0508,
+      "step": 2045
+    },
+    {
+      "epoch": 0.3018812246403541,
+      "grad_norm": 3.480570077896118,
+      "learning_rate": 1.7618342385058147e-05,
+      "loss": 0.1314,
+      "step": 2046
+    },
+    {
+      "epoch": 0.30202877167097014,
+      "grad_norm": 2.3844668865203857,
+      "learning_rate": 1.7615004703225727e-05,
+      "loss": 0.064,
+      "step": 2047
+    },
+    {
+      "epoch": 0.3021763187015861,
+      "grad_norm": 6.523024082183838,
+      "learning_rate": 1.7611665000922206e-05,
+      "loss": 0.05,
+      "step": 2048
+    },
+    {
+      "epoch": 0.30232386573220216,
+      "grad_norm": 2.540951728820801,
+      "learning_rate": 1.7608323279033685e-05,
+      "loss": 0.0403,
+      "step": 2049
+    },
+    {
+      "epoch": 0.30247141276281814,
+      "grad_norm": 1.9776675701141357,
+      "learning_rate": 1.7604979538446818e-05,
+      "loss": 0.0376,
+      "step": 2050
+    },
+    {
+      "epoch": 0.3026189597934342,
+      "grad_norm": 3.6032168865203857,
+      "learning_rate": 1.7601633780048797e-05,
+      "loss": 0.1119,
+      "step": 2051
+    },
+    {
+      "epoch": 0.30276650682405015,
+      "grad_norm": 1.87938392162323,
+      "learning_rate": 1.759828600472734e-05,
+      "loss": 0.0541,
+      "step": 2052
+    },
+    {
+      "epoch": 0.3029140538546662,
+      "grad_norm": 1.8706809282302856,
+      "learning_rate": 1.7594936213370708e-05,
+      "loss": 0.0685,
+      "step": 2053
+    },
+    {
+      "epoch": 0.30306160088528217,
+      "grad_norm": 3.2565836906433105,
+      "learning_rate": 1.759158440686769e-05,
+      "loss": 0.0501,
+      "step": 2054
+    },
+    {
+      "epoch": 0.3032091479158982,
+      "grad_norm": 1.5893309116363525,
+      "learning_rate": 1.7588230586107613e-05,
+      "loss": 0.0652,
+      "step": 2055
+    },
+    {
+      "epoch": 0.3033566949465142,
+      "grad_norm": 1.8227797746658325,
+      "learning_rate": 1.758487475198034e-05,
+      "loss": 0.0597,
+      "step": 2056
+    },
+    {
+      "epoch": 0.3035042419771302,
+      "grad_norm": 3.258263349533081,
+      "learning_rate": 1.7581516905376266e-05,
+      "loss": 0.0286,
+      "step": 2057
+    },
+    {
+      "epoch": 0.3036517890077462,
+      "grad_norm": 4.387876033782959,
+      "learning_rate": 1.7578157047186318e-05,
+      "loss": 0.1144,
+      "step": 2058
+    },
+    {
+      "epoch": 0.30379933603836223,
+      "grad_norm": 4.693922996520996,
+      "learning_rate": 1.7574795178301963e-05,
+      "loss": 0.1051,
+      "step": 2059
+    },
+    {
+      "epoch": 0.3039468830689782,
+      "grad_norm": 4.034201622009277,
+      "learning_rate": 1.7571431299615195e-05,
+      "loss": 0.07,
+      "step": 2060
+    },
+    {
+      "epoch": 0.3039468830689782,
+      "eval_accuracy": 0.9739507959479016,
+      "eval_f1": 0.9552238805970149,
+      "eval_loss": 0.06562598049640656,
+      "eval_precision": 0.9795918367346939,
+      "eval_recall": 0.9320388349514563,
+      "eval_runtime": 49.8669,
+      "eval_samples_per_second": 5.836,
+      "eval_steps_per_second": 0.201,
+      "step": 2060
+    },
+    {
+      "epoch": 0.30409443009959425,
+      "grad_norm": 3.5295114517211914,
+      "learning_rate": 1.7568065412018543e-05,
+      "loss": 0.1046,
+      "step": 2061
+    },
+    {
+      "epoch": 0.30424197713021023,
+      "grad_norm": 2.2974231243133545,
+      "learning_rate": 1.7564697516405074e-05,
+      "loss": 0.0658,
+      "step": 2062
+    },
+    {
+      "epoch": 0.30438952416082626,
+      "grad_norm": 5.0034942626953125,
+      "learning_rate": 1.7561327613668382e-05,
+      "loss": 0.0556,
+      "step": 2063
+    },
+    {
+      "epoch": 0.3045370711914423,
+      "grad_norm": 2.9695205688476562,
+      "learning_rate": 1.7557955704702597e-05,
+      "loss": 0.1117,
+      "step": 2064
+    },
+    {
+      "epoch": 0.3046846182220583,
+      "grad_norm": 3.0170087814331055,
+      "learning_rate": 1.7554581790402372e-05,
+      "loss": 0.0589,
+      "step": 2065
+    },
+    {
+      "epoch": 0.3048321652526743,
+      "grad_norm": 1.7038782835006714,
+      "learning_rate": 1.7551205871662906e-05,
+      "loss": 0.0362,
+      "step": 2066
+    },
+    {
+      "epoch": 0.3049797122832903,
+      "grad_norm": 3.1643404960632324,
+      "learning_rate": 1.7547827949379927e-05,
+      "loss": 0.0417,
+      "step": 2067
+    },
+    {
+      "epoch": 0.30512725931390633,
+      "grad_norm": 3.3591418266296387,
+      "learning_rate": 1.7544448024449683e-05,
+      "loss": 0.1141,
+      "step": 2068
+    },
+    {
+      "epoch": 0.3052748063445223,
+      "grad_norm": 1.7569690942764282,
+      "learning_rate": 1.7541066097768965e-05,
+      "loss": 0.0871,
+      "step": 2069
+    },
+    {
+      "epoch": 0.30542235337513834,
+      "grad_norm": 3.4121599197387695,
+      "learning_rate": 1.753768217023509e-05,
+      "loss": 0.0851,
+      "step": 2070
+    },
+    {
+      "epoch": 0.3055699004057543,
+      "grad_norm": 2.230632781982422,
+      "learning_rate": 1.7534296242745916e-05,
+      "loss": 0.0668,
+      "step": 2071
+    },
+    {
+      "epoch": 0.30571744743637036,
+      "grad_norm": 1.6636126041412354,
+      "learning_rate": 1.753090831619981e-05,
+      "loss": 0.0499,
+      "step": 2072
+    },
+    {
+      "epoch": 0.30586499446698634,
+      "grad_norm": 1.216579794883728,
+      "learning_rate": 1.752751839149569e-05,
+      "loss": 0.0246,
+      "step": 2073
+    },
+    {
+      "epoch": 0.3060125414976024,
+      "grad_norm": 1.7445745468139648,
+      "learning_rate": 1.7524126469532997e-05,
+      "loss": 0.0742,
+      "step": 2074
+    },
+    {
+      "epoch": 0.30616008852821835,
+      "grad_norm": 2.8874173164367676,
+      "learning_rate": 1.75207325512117e-05,
+      "loss": 0.0552,
+      "step": 2075
+    },
+    {
+      "epoch": 0.3063076355588344,
+      "grad_norm": 6.502613544464111,
+      "learning_rate": 1.7517336637432297e-05,
+      "loss": 0.0917,
+      "step": 2076
+    },
+    {
+      "epoch": 0.30645518258945037,
+      "grad_norm": 1.183326244354248,
+      "learning_rate": 1.751393872909582e-05,
+      "loss": 0.0524,
+      "step": 2077
+    },
+    {
+      "epoch": 0.3066027296200664,
+      "grad_norm": 3.1588449478149414,
+      "learning_rate": 1.751053882710383e-05,
+      "loss": 0.0655,
+      "step": 2078
+    },
+    {
+      "epoch": 0.3067502766506824,
+      "grad_norm": 2.601128578186035,
+      "learning_rate": 1.750713693235841e-05,
+      "loss": 0.0582,
+      "step": 2079
+    },
+    {
+      "epoch": 0.3068978236812984,
+      "grad_norm": 1.0544044971466064,
+      "learning_rate": 1.7503733045762185e-05,
+      "loss": 0.0264,
+      "step": 2080
+    },
+    {
+      "epoch": 0.3068978236812984,
+      "eval_accuracy": 0.9710564399421129,
+      "eval_f1": 0.9494949494949495,
+      "eval_loss": 0.0671740248799324,
+      "eval_precision": 0.9894736842105263,
+      "eval_recall": 0.912621359223301,
+      "eval_runtime": 49.9335,
+      "eval_samples_per_second": 5.828,
+      "eval_steps_per_second": 0.2,
+      "step": 2080
+    },
+    {
+      "epoch": 0.3070453707119144,
+      "grad_norm": 5.65303897857666,
+      "learning_rate": 1.7500327168218287e-05,
+      "loss": 0.0727,
+      "step": 2081
+    },
+    {
+      "epoch": 0.30719291774253044,
+      "grad_norm": 1.4922033548355103,
+      "learning_rate": 1.7496919300630405e-05,
+      "loss": 0.0614,
+      "step": 2082
+    },
+    {
+      "epoch": 0.3073404647731464,
+      "grad_norm": 3.6531383991241455,
+      "learning_rate": 1.7493509443902726e-05,
+      "loss": 0.0938,
+      "step": 2083
+    },
+    {
+      "epoch": 0.30748801180376245,
+      "grad_norm": 1.5921177864074707,
+      "learning_rate": 1.749009759893999e-05,
+      "loss": 0.0219,
+      "step": 2084
+    },
+    {
+      "epoch": 0.30763555883437843,
+      "grad_norm": 1.0543262958526611,
+      "learning_rate": 1.7486683766647447e-05,
+      "loss": 0.0258,
+      "step": 2085
+    },
+    {
+      "epoch": 0.30778310586499447,
+      "grad_norm": 1.6033868789672852,
+      "learning_rate": 1.7483267947930884e-05,
+      "loss": 0.0572,
+      "step": 2086
+    },
+    {
+      "epoch": 0.3079306528956105,
+      "grad_norm": 2.187842845916748,
+      "learning_rate": 1.7479850143696614e-05,
+      "loss": 0.1,
+      "step": 2087
+    },
+    {
+      "epoch": 0.3080781999262265,
+      "grad_norm": 1.839615821838379,
+      "learning_rate": 1.747643035485147e-05,
+      "loss": 0.0387,
+      "step": 2088
+    },
+    {
+      "epoch": 0.3082257469568425,
+      "grad_norm": 2.7941935062408447,
+      "learning_rate": 1.747300858230282e-05,
+      "loss": 0.1078,
+      "step": 2089
+    },
+    {
+      "epoch": 0.3083732939874585,
+      "grad_norm": 2.140803337097168,
+      "learning_rate": 1.7469584826958554e-05,
+      "loss": 0.0817,
+      "step": 2090
+    },
+    {
+      "epoch": 0.30852084101807453,
+      "grad_norm": 1.14137864112854,
+      "learning_rate": 1.7466159089727084e-05,
+      "loss": 0.032,
+      "step": 2091
+    },
+    {
+      "epoch": 0.3086683880486905,
+      "grad_norm": 1.5074483156204224,
+      "learning_rate": 1.746273137151736e-05,
+      "loss": 0.0822,
+      "step": 2092
+    },
+    {
+      "epoch": 0.30881593507930655,
+      "grad_norm": 3.0813302993774414,
+      "learning_rate": 1.7459301673238853e-05,
+      "loss": 0.0903,
+      "step": 2093
+    },
+    {
+      "epoch": 0.3089634821099225,
+      "grad_norm": 2.7230687141418457,
+      "learning_rate": 1.7455869995801544e-05,
+      "loss": 0.047,
+      "step": 2094
+    },
+    {
+      "epoch": 0.30911102914053856,
+      "grad_norm": 1.7247334718704224,
+      "learning_rate": 1.745243634011596e-05,
+      "loss": 0.0621,
+      "step": 2095
+    },
+    {
+      "epoch": 0.30925857617115454,
+      "grad_norm": 2.046072483062744,
+      "learning_rate": 1.7449000707093145e-05,
+      "loss": 0.0641,
+      "step": 2096
+    },
+    {
+      "epoch": 0.3094061232017706,
+      "grad_norm": 4.232421875,
+      "learning_rate": 1.7445563097644664e-05,
+      "loss": 0.0799,
+      "step": 2097
+    },
+    {
+      "epoch": 0.30955367023238656,
+      "grad_norm": 2.046140432357788,
+      "learning_rate": 1.7442123512682615e-05,
+      "loss": 0.1188,
+      "step": 2098
+    },
+    {
+      "epoch": 0.3097012172630026,
+      "grad_norm": 5.812841892242432,
+      "learning_rate": 1.743868195311961e-05,
+      "loss": 0.1308,
+      "step": 2099
+    },
+    {
+      "epoch": 0.3098487642936186,
+      "grad_norm": 3.1564996242523193,
+      "learning_rate": 1.7435238419868793e-05,
+      "loss": 0.1048,
+      "step": 2100
+    },
+    {
+      "epoch": 0.3098487642936186,
+      "eval_accuracy": 0.9782923299565847,
+      "eval_f1": 0.9629629629629629,
+      "eval_loss": 0.06561989337205887,
+      "eval_precision": 0.9798994974874372,
+      "eval_recall": 0.9466019417475728,
+      "eval_runtime": 50.0258,
+      "eval_samples_per_second": 5.817,
+      "eval_steps_per_second": 0.2,
+      "step": 2100
     }
   ],
   "logging_steps": 1,
@@ -15238,7 +15998,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.159504792176558e+17,
+  "total_flos": 6.467990375125484e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null