Training in progress, step 5800, checkpoint

last-checkpoint/optimizer_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:323593aaf478654c4c84395f44d68d325be67e00b52048e7bf1265f40205678a
+oid sha256:b05c7176b0d8b2ea13d5e840e561875304ae41b77106cb95b9ab88f722f81b89
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b47201053fbcc4557e60d3d17db4733b5710d94e7f48d1b5ac7f27ecc8f73c10
+oid sha256:c7164343f50ec5f92e2aa03f476a2ae0f77e7f6b8151ff3f5c70ca10923db4a2
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc469c7929b4a16dd0af75e3463a471bb004d4df11e357a47195fe58f84c8b01
+oid sha256:6e163ef65ff7de8f54cc79cf70e16c054d678f75c196b74f5ae1095c83faf5ca
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4abb2ee717d219800c0157e5c4da401a279c869c0e47fd10dfe920c43289ac0
+oid sha256:86225dc6c8c91a1c20387c141fd75872dae4aa8156d83e3cf4fa8ef99ab8e9d3
 size 13990904

last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bf8fc9f010947014eb27bb723b0612c83e5b7de0be1f60ae868bdf959211d98
+oid sha256:850f552f3952cf1e9589a8196f512def9a9df70b2e2dea52b3b29ba49faa81fe
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36a19bd3fe7713935f16cda1edce71e068c8e8540e208e282fbf5909f7b57eb9
+oid sha256:322602441a9b550ec27ce627eb8d0fd34be78a7a1d79fccf7db9fdb4e556983f
 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:b34e18a97bf62613b29d90cc266fd299a72f0aa1155a62d7cc3755ec36c07384
+oid sha256:07c7df69cf91ea7cfce299929905397f3e4b20d96119d0464fbfc6871a0fa3ce
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a56bcdbc7a93c77dd54b1f01e5d7075bcdb8cf5f5ef74ec957a9e0f490b3363
+oid sha256:bf39c2704d1323810676f1b8d0ca0ba1dd2a23fec0b6eabca667156d762bae12
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a35f499a70a612db8820af15407688adb91e47e26a75b81f87a7bc2288c6b8e6
+oid sha256:2545a90cb8cc35885b917cbad80d1e2e7bdd643a2349e849a6541b698f73c2bc
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14b08b2743b0b959b0b922a5d5ced611a23433d657351053a9aae6bec44f39c9
+oid sha256:7d1b235de73c159a7471618a53b7822ca9ec9e530a86084d8d1d92569c2cf2ba
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fbadcacf053d499aa403f31b5c34cca57e04f551d37d8d70090a5c39bfbcc99
+oid sha256:5a835e749972fe06e6e1f1769253bf4bd39dc8c63bee6df1ca3b73c0c81f99ab
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:612f21a86961278058a69e3fbd5a869ab48adcaa082dde48ff32892df6d5831e
+oid sha256:6d5d5da678b54a3dc522fdbf7e963c69797a6882cec4bda5a4b03deba0a9f4b8
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88cbf90edbc28a5c9f752799e3c9fb7e7a34d3763eec39b36fadc9beec06b79b
+oid sha256:68697f859594e0b6d7229896b03ce34031d668cc9963cd62fa30ad6d9f00ef1a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8410180745112504,
+  "epoch": 0.8557727775728513,
   "eval_steps": 20,
-  "global_step": 5700,
+  "global_step": 5800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -43339,6 +43339,766 @@
       "eval_samples_per_second": 5.827,
       "eval_steps_per_second": 0.2,
       "step": 5700
+    },
+    {
+      "epoch": 0.8411656215418665,
+      "grad_norm": 2.1464152336120605,
+      "learning_rate": 1.4970311961222795e-06,
+      "loss": 0.0256,
+      "step": 5701
+    },
+    {
+      "epoch": 0.8413131685724825,
+      "grad_norm": 1.440287709236145,
+      "learning_rate": 1.4943213376660593e-06,
+      "loss": 0.0346,
+      "step": 5702
+    },
+    {
+      "epoch": 0.8414607156030985,
+      "grad_norm": 4.759016036987305,
+      "learning_rate": 1.4916137360013515e-06,
+      "loss": 0.1046,
+      "step": 5703
+    },
+    {
+      "epoch": 0.8416082626337145,
+      "grad_norm": 1.751717448234558,
+      "learning_rate": 1.488908391846564e-06,
+      "loss": 0.0309,
+      "step": 5704
+    },
+    {
+      "epoch": 0.8417558096643305,
+      "grad_norm": 2.9776530265808105,
+      "learning_rate": 1.4862053059194936e-06,
+      "loss": 0.0618,
+      "step": 5705
+    },
+    {
+      "epoch": 0.8419033566949465,
+      "grad_norm": 4.0823564529418945,
+      "learning_rate": 1.4835044789373476e-06,
+      "loss": 0.0832,
+      "step": 5706
+    },
+    {
+      "epoch": 0.8420509037255626,
+      "grad_norm": 2.550696849822998,
+      "learning_rate": 1.4808059116167306e-06,
+      "loss": 0.0437,
+      "step": 5707
+    },
+    {
+      "epoch": 0.8421984507561785,
+      "grad_norm": 1.0314558744430542,
+      "learning_rate": 1.4781096046736421e-06,
+      "loss": 0.0139,
+      "step": 5708
+    },
+    {
+      "epoch": 0.8423459977867945,
+      "grad_norm": 2.7498323917388916,
+      "learning_rate": 1.475415558823493e-06,
+      "loss": 0.0488,
+      "step": 5709
+    },
+    {
+      "epoch": 0.8424935448174106,
+      "grad_norm": 4.794541835784912,
+      "learning_rate": 1.472723774781083e-06,
+      "loss": 0.0557,
+      "step": 5710
+    },
+    {
+      "epoch": 0.8426410918480266,
+      "grad_norm": 4.705298900604248,
+      "learning_rate": 1.4700342532606193e-06,
+      "loss": 0.022,
+      "step": 5711
+    },
+    {
+      "epoch": 0.8427886388786425,
+      "grad_norm": 1.9125524759292603,
+      "learning_rate": 1.467346994975708e-06,
+      "loss": 0.0452,
+      "step": 5712
+    },
+    {
+      "epoch": 0.8429361859092586,
+      "grad_norm": 2.408352851867676,
+      "learning_rate": 1.4646620006393497e-06,
+      "loss": 0.0401,
+      "step": 5713
+    },
+    {
+      "epoch": 0.8430837329398746,
+      "grad_norm": 1.7403894662857056,
+      "learning_rate": 1.461979270963947e-06,
+      "loss": 0.0423,
+      "step": 5714
+    },
+    {
+      "epoch": 0.8432312799704906,
+      "grad_norm": 2.193599224090576,
+      "learning_rate": 1.4592988066613045e-06,
+      "loss": 0.0303,
+      "step": 5715
+    },
+    {
+      "epoch": 0.8433788270011066,
+      "grad_norm": 3.449028491973877,
+      "learning_rate": 1.4566206084426238e-06,
+      "loss": 0.0829,
+      "step": 5716
+    },
+    {
+      "epoch": 0.8435263740317226,
+      "grad_norm": 2.0021655559539795,
+      "learning_rate": 1.453944677018503e-06,
+      "loss": 0.0562,
+      "step": 5717
+    },
+    {
+      "epoch": 0.8436739210623386,
+      "grad_norm": 2.076805830001831,
+      "learning_rate": 1.4512710130989427e-06,
+      "loss": 0.0621,
+      "step": 5718
+    },
+    {
+      "epoch": 0.8438214680929547,
+      "grad_norm": 2.1435418128967285,
+      "learning_rate": 1.448599617393337e-06,
+      "loss": 0.1112,
+      "step": 5719
+    },
+    {
+      "epoch": 0.8439690151235706,
+      "grad_norm": 1.225638747215271,
+      "learning_rate": 1.4459304906104821e-06,
+      "loss": 0.0269,
+      "step": 5720
+    },
+    {
+      "epoch": 0.8439690151235706,
+      "eval_accuracy": 0.9797395079594791,
+      "eval_f1": 0.9651741293532339,
+      "eval_loss": 0.05757652968168259,
+      "eval_precision": 0.9897959183673469,
+      "eval_recall": 0.941747572815534,
+      "eval_runtime": 49.2938,
+      "eval_samples_per_second": 5.903,
+      "eval_steps_per_second": 0.203,
+      "step": 5720
+    },
+    {
+      "epoch": 0.8441165621541866,
+      "grad_norm": 1.08596670627594,
+      "learning_rate": 1.4432636334585736e-06,
+      "loss": 0.0421,
+      "step": 5721
+    },
+    {
+      "epoch": 0.8442641091848027,
+      "grad_norm": 3.0772130489349365,
+      "learning_rate": 1.440599046645198e-06,
+      "loss": 0.0793,
+      "step": 5722
+    },
+    {
+      "epoch": 0.8444116562154187,
+      "grad_norm": 2.5330147743225098,
+      "learning_rate": 1.4379367308773483e-06,
+      "loss": 0.07,
+      "step": 5723
+    },
+    {
+      "epoch": 0.8445592032460347,
+      "grad_norm": 0.7319562435150146,
+      "learning_rate": 1.4352766868614088e-06,
+      "loss": 0.0085,
+      "step": 5724
+    },
+    {
+      "epoch": 0.8447067502766507,
+      "grad_norm": 1.175978183746338,
+      "learning_rate": 1.4326189153031577e-06,
+      "loss": 0.0295,
+      "step": 5725
+    },
+    {
+      "epoch": 0.8448542973072667,
+      "grad_norm": 2.1906511783599854,
+      "learning_rate": 1.4299634169077836e-06,
+      "loss": 0.035,
+      "step": 5726
+    },
+    {
+      "epoch": 0.8450018443378827,
+      "grad_norm": 2.8638551235198975,
+      "learning_rate": 1.4273101923798593e-06,
+      "loss": 0.0444,
+      "step": 5727
+    },
+    {
+      "epoch": 0.8451493913684988,
+      "grad_norm": 1.8354886770248413,
+      "learning_rate": 1.4246592424233575e-06,
+      "loss": 0.0679,
+      "step": 5728
+    },
+    {
+      "epoch": 0.8452969383991147,
+      "grad_norm": 3.6023311614990234,
+      "learning_rate": 1.4220105677416485e-06,
+      "loss": 0.072,
+      "step": 5729
+    },
+    {
+      "epoch": 0.8454444854297307,
+      "grad_norm": 1.198553204536438,
+      "learning_rate": 1.4193641690375037e-06,
+      "loss": 0.0114,
+      "step": 5730
+    },
+    {
+      "epoch": 0.8455920324603468,
+      "grad_norm": 3.0524094104766846,
+      "learning_rate": 1.4167200470130794e-06,
+      "loss": 0.0847,
+      "step": 5731
+    },
+    {
+      "epoch": 0.8457395794909628,
+      "grad_norm": 3.2249886989593506,
+      "learning_rate": 1.4140782023699396e-06,
+      "loss": 0.0754,
+      "step": 5732
+    },
+    {
+      "epoch": 0.8458871265215787,
+      "grad_norm": 0.9703981876373291,
+      "learning_rate": 1.4114386358090325e-06,
+      "loss": 0.0109,
+      "step": 5733
+    },
+    {
+      "epoch": 0.8460346735521947,
+      "grad_norm": 1.8067426681518555,
+      "learning_rate": 1.4088013480307128e-06,
+      "loss": 0.0368,
+      "step": 5734
+    },
+    {
+      "epoch": 0.8461822205828108,
+      "grad_norm": 2.0494327545166016,
+      "learning_rate": 1.406166339734727e-06,
+      "loss": 0.0446,
+      "step": 5735
+    },
+    {
+      "epoch": 0.8463297676134268,
+      "grad_norm": 3.375311851501465,
+      "learning_rate": 1.4035336116202113e-06,
+      "loss": 0.0711,
+      "step": 5736
+    },
+    {
+      "epoch": 0.8464773146440427,
+      "grad_norm": 4.0707688331604,
+      "learning_rate": 1.4009031643857041e-06,
+      "loss": 0.0532,
+      "step": 5737
+    },
+    {
+      "epoch": 0.8466248616746588,
+      "grad_norm": 6.29263162612915,
+      "learning_rate": 1.3982749987291333e-06,
+      "loss": 0.1401,
+      "step": 5738
+    },
+    {
+      "epoch": 0.8467724087052748,
+      "grad_norm": 2.0079193115234375,
+      "learning_rate": 1.3956491153478258e-06,
+      "loss": 0.053,
+      "step": 5739
+    },
+    {
+      "epoch": 0.8469199557358909,
+      "grad_norm": 1.6431809663772583,
+      "learning_rate": 1.393025514938502e-06,
+      "loss": 0.0441,
+      "step": 5740
+    },
+    {
+      "epoch": 0.8469199557358909,
+      "eval_accuracy": 0.9811866859623734,
+      "eval_f1": 0.967741935483871,
+      "eval_loss": 0.05722363665699959,
+      "eval_precision": 0.9898477157360406,
+      "eval_recall": 0.9466019417475728,
+      "eval_runtime": 50.1974,
+      "eval_samples_per_second": 5.797,
+      "eval_steps_per_second": 0.199,
+      "step": 5740
+    },
+    {
+      "epoch": 0.8470675027665068,
+      "grad_norm": 1.8669764995574951,
+      "learning_rate": 1.3904041981972715e-06,
+      "loss": 0.0562,
+      "step": 5741
+    },
+    {
+      "epoch": 0.8472150497971228,
+      "grad_norm": 3.058616876602173,
+      "learning_rate": 1.3877851658196473e-06,
+      "loss": 0.0533,
+      "step": 5742
+    },
+    {
+      "epoch": 0.8473625968277388,
+      "grad_norm": 0.4952690303325653,
+      "learning_rate": 1.3851684185005275e-06,
+      "loss": 0.0046,
+      "step": 5743
+    },
+    {
+      "epoch": 0.8475101438583549,
+      "grad_norm": 3.9359915256500244,
+      "learning_rate": 1.382553956934205e-06,
+      "loss": 0.0784,
+      "step": 5744
+    },
+    {
+      "epoch": 0.8476576908889708,
+      "grad_norm": 2.8091506958007812,
+      "learning_rate": 1.3799417818143758e-06,
+      "loss": 0.0859,
+      "step": 5745
+    },
+    {
+      "epoch": 0.8478052379195868,
+      "grad_norm": 3.728245735168457,
+      "learning_rate": 1.3773318938341186e-06,
+      "loss": 0.0574,
+      "step": 5746
+    },
+    {
+      "epoch": 0.8479527849502029,
+      "grad_norm": 5.488831520080566,
+      "learning_rate": 1.3747242936859062e-06,
+      "loss": 0.1272,
+      "step": 5747
+    },
+    {
+      "epoch": 0.8481003319808189,
+      "grad_norm": 2.9584414958953857,
+      "learning_rate": 1.3721189820616098e-06,
+      "loss": 0.089,
+      "step": 5748
+    },
+    {
+      "epoch": 0.848247879011435,
+      "grad_norm": 3.1330299377441406,
+      "learning_rate": 1.369515959652491e-06,
+      "loss": 0.1249,
+      "step": 5749
+    },
+    {
+      "epoch": 0.8483954260420509,
+      "grad_norm": 1.467090129852295,
+      "learning_rate": 1.3669152271492015e-06,
+      "loss": 0.0427,
+      "step": 5750
+    },
+    {
+      "epoch": 0.8485429730726669,
+      "grad_norm": 3.071939468383789,
+      "learning_rate": 1.3643167852417894e-06,
+      "loss": 0.0431,
+      "step": 5751
+    },
+    {
+      "epoch": 0.8486905201032829,
+      "grad_norm": 2.546959638595581,
+      "learning_rate": 1.361720634619691e-06,
+      "loss": 0.0879,
+      "step": 5752
+    },
+    {
+      "epoch": 0.848838067133899,
+      "grad_norm": 2.3573038578033447,
+      "learning_rate": 1.3591267759717374e-06,
+      "loss": 0.0535,
+      "step": 5753
+    },
+    {
+      "epoch": 0.8489856141645149,
+      "grad_norm": 2.136235475540161,
+      "learning_rate": 1.3565352099861539e-06,
+      "loss": 0.0416,
+      "step": 5754
+    },
+    {
+      "epoch": 0.8491331611951309,
+      "grad_norm": 2.895474433898926,
+      "learning_rate": 1.3539459373505503e-06,
+      "loss": 0.0762,
+      "step": 5755
+    },
+    {
+      "epoch": 0.849280708225747,
+      "grad_norm": 1.7000274658203125,
+      "learning_rate": 1.351358958751936e-06,
+      "loss": 0.0323,
+      "step": 5756
+    },
+    {
+      "epoch": 0.849428255256363,
+      "grad_norm": 0.9407041072845459,
+      "learning_rate": 1.3487742748767051e-06,
+      "loss": 0.0127,
+      "step": 5757
+    },
+    {
+      "epoch": 0.8495758022869789,
+      "grad_norm": 7.56793212890625,
+      "learning_rate": 1.3461918864106438e-06,
+      "loss": 0.0745,
+      "step": 5758
+    },
+    {
+      "epoch": 0.849723349317595,
+      "grad_norm": 1.6602380275726318,
+      "learning_rate": 1.343611794038937e-06,
+      "loss": 0.0482,
+      "step": 5759
+    },
+    {
+      "epoch": 0.849870896348211,
+      "grad_norm": 1.466604471206665,
+      "learning_rate": 1.3410339984461518e-06,
+      "loss": 0.0413,
+      "step": 5760
+    },
+    {
+      "epoch": 0.849870896348211,
+      "eval_accuracy": 0.9797395079594791,
+      "eval_f1": 0.9653465346534653,
+      "eval_loss": 0.05454903468489647,
+      "eval_precision": 0.9848484848484849,
+      "eval_recall": 0.9466019417475728,
+      "eval_runtime": 48.9571,
+      "eval_samples_per_second": 5.944,
+      "eval_steps_per_second": 0.204,
+      "step": 5760
+    },
+    {
+      "epoch": 0.850018443378827,
+      "grad_norm": 1.593299388885498,
+      "learning_rate": 1.3384585003162455e-06,
+      "loss": 0.0262,
+      "step": 5761
+    },
+    {
+      "epoch": 0.850165990409443,
+      "grad_norm": 1.3665624856948853,
+      "learning_rate": 1.3358853003325733e-06,
+      "loss": 0.0251,
+      "step": 5762
+    },
+    {
+      "epoch": 0.850313537440059,
+      "grad_norm": 0.8125731945037842,
+      "learning_rate": 1.333314399177873e-06,
+      "loss": 0.0128,
+      "step": 5763
+    },
+    {
+      "epoch": 0.850461084470675,
+      "grad_norm": 1.1369338035583496,
+      "learning_rate": 1.3307457975342764e-06,
+      "loss": 0.0297,
+      "step": 5764
+    },
+    {
+      "epoch": 0.8506086315012911,
+      "grad_norm": 1.9386367797851562,
+      "learning_rate": 1.3281794960833072e-06,
+      "loss": 0.0523,
+      "step": 5765
+    },
+    {
+      "epoch": 0.850756178531907,
+      "grad_norm": 1.1021301746368408,
+      "learning_rate": 1.325615495505872e-06,
+      "loss": 0.0218,
+      "step": 5766
+    },
+    {
+      "epoch": 0.850903725562523,
+      "grad_norm": 1.1594314575195312,
+      "learning_rate": 1.3230537964822732e-06,
+      "loss": 0.0364,
+      "step": 5767
+    },
+    {
+      "epoch": 0.8510512725931391,
+      "grad_norm": 1.921069622039795,
+      "learning_rate": 1.3204943996922025e-06,
+      "loss": 0.03,
+      "step": 5768
+    },
+    {
+      "epoch": 0.8511988196237551,
+      "grad_norm": 2.836876630783081,
+      "learning_rate": 1.3179373058147337e-06,
+      "loss": 0.0601,
+      "step": 5769
+    },
+    {
+      "epoch": 0.8513463666543711,
+      "grad_norm": 2.206815719604492,
+      "learning_rate": 1.3153825155283395e-06,
+      "loss": 0.0651,
+      "step": 5770
+    },
+    {
+      "epoch": 0.8514939136849871,
+      "grad_norm": 1.552211046218872,
+      "learning_rate": 1.312830029510873e-06,
+      "loss": 0.0603,
+      "step": 5771
+    },
+    {
+      "epoch": 0.8516414607156031,
+      "grad_norm": 2.625312328338623,
+      "learning_rate": 1.3102798484395761e-06,
+      "loss": 0.0581,
+      "step": 5772
+    },
+    {
+      "epoch": 0.8517890077462191,
+      "grad_norm": 2.256977081298828,
+      "learning_rate": 1.307731972991091e-06,
+      "loss": 0.0579,
+      "step": 5773
+    },
+    {
+      "epoch": 0.8519365547768352,
+      "grad_norm": 2.2679216861724854,
+      "learning_rate": 1.3051864038414342e-06,
+      "loss": 0.0561,
+      "step": 5774
+    },
+    {
+      "epoch": 0.8520841018074511,
+      "grad_norm": 1.9951554536819458,
+      "learning_rate": 1.3026431416660135e-06,
+      "loss": 0.0175,
+      "step": 5775
+    },
+    {
+      "epoch": 0.8522316488380671,
+      "grad_norm": 1.83767569065094,
+      "learning_rate": 1.3001021871396313e-06,
+      "loss": 0.0652,
+      "step": 5776
+    },
+    {
+      "epoch": 0.8523791958686832,
+      "grad_norm": 2.527323007583618,
+      "learning_rate": 1.2975635409364684e-06,
+      "loss": 0.1043,
+      "step": 5777
+    },
+    {
+      "epoch": 0.8525267428992992,
+      "grad_norm": 3.0767338275909424,
+      "learning_rate": 1.2950272037301015e-06,
+      "loss": 0.1132,
+      "step": 5778
+    },
+    {
+      "epoch": 0.8526742899299151,
+      "grad_norm": 6.410322189331055,
+      "learning_rate": 1.29249317619349e-06,
+      "loss": 0.0782,
+      "step": 5779
+    },
+    {
+      "epoch": 0.8528218369605312,
+      "grad_norm": 2.966045618057251,
+      "learning_rate": 1.2899614589989795e-06,
+      "loss": 0.061,
+      "step": 5780
+    },
+    {
+      "epoch": 0.8528218369605312,
+      "eval_accuracy": 0.9782923299565847,
+      "eval_f1": 0.9629629629629629,
+      "eval_loss": 0.054151300340890884,
+      "eval_precision": 0.9798994974874372,
+      "eval_recall": 0.9466019417475728,
+      "eval_runtime": 49.0986,
+      "eval_samples_per_second": 5.927,
+      "eval_steps_per_second": 0.204,
+      "step": 5780
+    },
+    {
+      "epoch": 0.8529693839911472,
+      "grad_norm": 3.7127346992492676,
+      "learning_rate": 1.2874320528183081e-06,
+      "loss": 0.0686,
+      "step": 5781
+    },
+    {
+      "epoch": 0.8531169310217632,
+      "grad_norm": 0.8974189162254333,
+      "learning_rate": 1.2849049583225937e-06,
+      "loss": 0.0346,
+      "step": 5782
+    },
+    {
+      "epoch": 0.8532644780523791,
+      "grad_norm": 1.8226568698883057,
+      "learning_rate": 1.282380176182345e-06,
+      "loss": 0.0364,
+      "step": 5783
+    },
+    {
+      "epoch": 0.8534120250829952,
+      "grad_norm": 1.6044015884399414,
+      "learning_rate": 1.279857707067459e-06,
+      "loss": 0.0351,
+      "step": 5784
+    },
+    {
+      "epoch": 0.8535595721136112,
+      "grad_norm": 1.8267277479171753,
+      "learning_rate": 1.2773375516472153e-06,
+      "loss": 0.0491,
+      "step": 5785
+    },
+    {
+      "epoch": 0.8537071191442273,
+      "grad_norm": 2.8557074069976807,
+      "learning_rate": 1.2748197105902748e-06,
+      "loss": 0.063,
+      "step": 5786
+    },
+    {
+      "epoch": 0.8538546661748432,
+      "grad_norm": 1.9956883192062378,
+      "learning_rate": 1.2723041845647e-06,
+      "loss": 0.0622,
+      "step": 5787
+    },
+    {
+      "epoch": 0.8540022132054592,
+      "grad_norm": 7.793476581573486,
+      "learning_rate": 1.2697909742379243e-06,
+      "loss": 0.0918,
+      "step": 5788
+    },
+    {
+      "epoch": 0.8541497602360753,
+      "grad_norm": 2.934429883956909,
+      "learning_rate": 1.2672800802767715e-06,
+      "loss": 0.1029,
+      "step": 5789
+    },
+    {
+      "epoch": 0.8542973072666913,
+      "grad_norm": 3.2007949352264404,
+      "learning_rate": 1.264771503347454e-06,
+      "loss": 0.0534,
+      "step": 5790
+    },
+    {
+      "epoch": 0.8544448542973073,
+      "grad_norm": 1.6562820672988892,
+      "learning_rate": 1.2622652441155614e-06,
+      "loss": 0.0265,
+      "step": 5791
+    },
+    {
+      "epoch": 0.8545924013279232,
+      "grad_norm": 2.057903528213501,
+      "learning_rate": 1.2597613032460776e-06,
+      "loss": 0.0482,
+      "step": 5792
+    },
+    {
+      "epoch": 0.8547399483585393,
+      "grad_norm": 4.989871978759766,
+      "learning_rate": 1.257259681403369e-06,
+      "loss": 0.044,
+      "step": 5793
+    },
+    {
+      "epoch": 0.8548874953891553,
+      "grad_norm": 3.3362135887145996,
+      "learning_rate": 1.2547603792511787e-06,
+      "loss": 0.1074,
+      "step": 5794
+    },
+    {
+      "epoch": 0.8550350424197714,
+      "grad_norm": 2.7018706798553467,
+      "learning_rate": 1.2522633974526476e-06,
+      "loss": 0.0851,
+      "step": 5795
+    },
+    {
+      "epoch": 0.8551825894503873,
+      "grad_norm": 4.39471960067749,
+      "learning_rate": 1.2497687366702883e-06,
+      "loss": 0.1162,
+      "step": 5796
+    },
+    {
+      "epoch": 0.8553301364810033,
+      "grad_norm": 2.1254372596740723,
+      "learning_rate": 1.2472763975660051e-06,
+      "loss": 0.1178,
+      "step": 5797
+    },
+    {
+      "epoch": 0.8554776835116193,
+      "grad_norm": 1.8468786478042603,
+      "learning_rate": 1.2447863808010874e-06,
+      "loss": 0.0239,
+      "step": 5798
+    },
+    {
+      "epoch": 0.8556252305422354,
+      "grad_norm": 1.604872703552246,
+      "learning_rate": 1.242298687036203e-06,
+      "loss": 0.0556,
+      "step": 5799
+    },
+    {
+      "epoch": 0.8557727775728513,
+      "grad_norm": 2.3689584732055664,
+      "learning_rate": 1.2398133169314031e-06,
+      "loss": 0.0699,
+      "step": 5800
+    },
+    {
+      "epoch": 0.8557727775728513,
+      "eval_accuracy": 0.9782923299565847,
+      "eval_f1": 0.9629629629629629,
+      "eval_loss": 0.05439816415309906,
+      "eval_precision": 0.9798994974874372,
+      "eval_recall": 0.9466019417475728,
+      "eval_runtime": 48.645,
+      "eval_samples_per_second": 5.982,
+      "eval_steps_per_second": 0.206,
+      "step": 5800
     }
   ],
   "logging_steps": 1,
@@ -43358,7 +44118,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.7555460633363743e+18,
+  "total_flos": 1.7864445794828943e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null