Training in progress, step 2200, checkpoint

last-checkpoint/optimizer_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c0d62d2028703955c4f3d646339860dd0bbceb4a15725c168f6c84c55250b8f
+oid sha256:7750d855d924ceddc42b25d22102dca161947437c25b8419a6816d7b96741aeb
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d44131d1bcd453d009ee709ae3eb6b0b5c95455ebb3aa7223868da1ad2ab97af
+oid sha256:fe99c75ae54f8e353ca6b14a2263f36030ed5f3401ce134e4635385755a900b7
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4379faa5b7d55d3a4badc78bcd294998819883a2d59ff2b111187bdcd4d95a4a
+oid sha256:4d05e150230f6c9e3e975cd33a3210ca9291eb2e64c2ecdbf0603dafea8eea91
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:846544fc898fcaab3118bb5b0a59beea20abcf3d8ac45a447b88009c0f350e89
+oid sha256:8db5587c2ec1c9e3f57bc569cd655e9a5f4ffd08bc65175e481ebe68e67f7635
 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:be9252d8d0768775db03040718884e0b2bd7b5f6fa6171efc55534699f467b80
+oid sha256:93bb3e67ee6ceedf8551709955d00de6d38ab5803dccee94006f2d5c386ec341
 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:e2768dd0f6729301a0a5792ec6ddcde386903d87c3257eecbe4d6d10e2683368
+oid sha256:4a83f77a5fe6ac8a4884389cb8ed767cc29a586c30e61019c17e47cadd3f5525
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:502f8e3c49fc009af8dd78f612ddb43cfa4a8c39a7095adec01b2e78b3e606ae
+oid sha256:d3332e607aef586ed304912c7552b3516178a31f86acd384c43600315294afcd
 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:fdee8e3523c4af3d4e2e67b16018e17acd8fd309073149132e4fcd811e32be23
+oid sha256:c7f13e6b4d3e3cab59a425ff7c039652ef325d0fdbb428bc8660095468057bd1
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4cc453eb36c5b4b199fa46cfa81de79a85081e0d52daf6abcd21f6e148da39a
+oid sha256:6a4586a2997b0b408d270738eb8db1b3f9fa8a1af8d3e8e24278c513ee508542
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ed11393b53ac60ffc874c8cb15088bc7892ceb270c99092eec2f7c0ee6ad586
+oid sha256:411997a661a7b55a5c8ced9a28b09cc84c038cb5ccecb6043e26e62fd0dd502d
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3e08b0e0c75bcbdf0bce090d48cac5fce1396aef2e9b4728153f6e8afc305ef
+oid sha256:e1e8ad9fcb9ebe7d67655466925d5d831d7f2cfce33712846d8b9653de23bd8e
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bba7a57cc6bd4c4d7481da393f27921e77b361eb75d83c66e814992ac2a0f11
+oid sha256:415a0bb82a0f7a72dd88fb835daa9883d9328dba7cb35db534eff4f51e188465
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d50b83278cc41509b62ba992a64a52719571e26ec2f84675ee1c0515e5db440
+oid sha256:99ebe1c7d19cd6162f873b3b499cafe7fbbaa105c5efc40272cb3d608ff4b0e4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3098487642936186,
+  "epoch": 0.3246034673552195,
   "eval_steps": 20,
-  "global_step": 2100,
+  "global_step": 2200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -15979,6 +15979,766 @@
       "eval_samples_per_second": 5.817,
       "eval_steps_per_second": 0.2,
       "step": 2100
+    },
+    {
+      "epoch": 0.3099963113242346,
+      "grad_norm": 3.3443610668182373,
+      "learning_rate": 1.7431792913843826e-05,
+      "loss": 0.1319,
+      "step": 2101
+    },
+    {
+      "epoch": 0.3101438583548506,
+      "grad_norm": 1.7402970790863037,
+      "learning_rate": 1.74283454359589e-05,
+      "loss": 0.0387,
+      "step": 2102
+    },
+    {
+      "epoch": 0.3102914053854666,
+      "grad_norm": 2.536003828048706,
+      "learning_rate": 1.7424895987128723e-05,
+      "loss": 0.032,
+      "step": 2103
+    },
+    {
+      "epoch": 0.3104389524160826,
+      "grad_norm": 4.353453159332275,
+      "learning_rate": 1.742144456826853e-05,
+      "loss": 0.0702,
+      "step": 2104
+    },
+    {
+      "epoch": 0.31058649944669864,
+      "grad_norm": 1.7974307537078857,
+      "learning_rate": 1.7417991180294077e-05,
+      "loss": 0.0597,
+      "step": 2105
+    },
+    {
+      "epoch": 0.3107340464773146,
+      "grad_norm": 3.0360138416290283,
+      "learning_rate": 1.7414535824121644e-05,
+      "loss": 0.0842,
+      "step": 2106
+    },
+    {
+      "epoch": 0.31088159350793065,
+      "grad_norm": 1.7299362421035767,
+      "learning_rate": 1.7411078500668032e-05,
+      "loss": 0.0664,
+      "step": 2107
+    },
+    {
+      "epoch": 0.3110291405385467,
+      "grad_norm": 3.420109748840332,
+      "learning_rate": 1.7407619210850568e-05,
+      "loss": 0.1006,
+      "step": 2108
+    },
+    {
+      "epoch": 0.31117668756916267,
+      "grad_norm": 2.340759754180908,
+      "learning_rate": 1.7404157955587095e-05,
+      "loss": 0.0929,
+      "step": 2109
+    },
+    {
+      "epoch": 0.3113242345997787,
+      "grad_norm": 1.8463226556777954,
+      "learning_rate": 1.7400694735795974e-05,
+      "loss": 0.0536,
+      "step": 2110
+    },
+    {
+      "epoch": 0.3114717816303947,
+      "grad_norm": 2.033116579055786,
+      "learning_rate": 1.7397229552396104e-05,
+      "loss": 0.0606,
+      "step": 2111
+    },
+    {
+      "epoch": 0.3116193286610107,
+      "grad_norm": 1.240280270576477,
+      "learning_rate": 1.739376240630688e-05,
+      "loss": 0.0385,
+      "step": 2112
+    },
+    {
+      "epoch": 0.3117668756916267,
+      "grad_norm": 2.432034969329834,
+      "learning_rate": 1.7390293298448243e-05,
+      "loss": 0.0819,
+      "step": 2113
+    },
+    {
+      "epoch": 0.31191442272224273,
+      "grad_norm": 2.032050848007202,
+      "learning_rate": 1.7386822229740642e-05,
+      "loss": 0.0664,
+      "step": 2114
+    },
+    {
+      "epoch": 0.3120619697528587,
+      "grad_norm": 2.3717551231384277,
+      "learning_rate": 1.738334920110504e-05,
+      "loss": 0.0783,
+      "step": 2115
+    },
+    {
+      "epoch": 0.31220951678347475,
+      "grad_norm": 1.4648905992507935,
+      "learning_rate": 1.7379874213462936e-05,
+      "loss": 0.0784,
+      "step": 2116
+    },
+    {
+      "epoch": 0.31235706381409073,
+      "grad_norm": 1.3918699026107788,
+      "learning_rate": 1.7376397267736337e-05,
+      "loss": 0.0238,
+      "step": 2117
+    },
+    {
+      "epoch": 0.31250461084470676,
+      "grad_norm": 2.6029951572418213,
+      "learning_rate": 1.7372918364847767e-05,
+      "loss": 0.1066,
+      "step": 2118
+    },
+    {
+      "epoch": 0.31265215787532274,
+      "grad_norm": 2.328977584838867,
+      "learning_rate": 1.7369437505720284e-05,
+      "loss": 0.0149,
+      "step": 2119
+    },
+    {
+      "epoch": 0.3127997049059388,
+      "grad_norm": 3.0880587100982666,
+      "learning_rate": 1.7365954691277453e-05,
+      "loss": 0.136,
+      "step": 2120
+    },
+    {
+      "epoch": 0.3127997049059388,
+      "eval_accuracy": 0.9725036179450073,
+      "eval_f1": 0.9518987341772152,
+      "eval_loss": 0.06848844885826111,
+      "eval_precision": 0.9947089947089947,
+      "eval_recall": 0.912621359223301,
+      "eval_runtime": 49.3055,
+      "eval_samples_per_second": 5.902,
+      "eval_steps_per_second": 0.203,
+      "step": 2120
+    },
+    {
+      "epoch": 0.31294725193655476,
+      "grad_norm": 1.6658941507339478,
+      "learning_rate": 1.736246992244336e-05,
+      "loss": 0.0554,
+      "step": 2121
+    },
+    {
+      "epoch": 0.3130947989671708,
+      "grad_norm": 1.4149516820907593,
+      "learning_rate": 1.7358983200142608e-05,
+      "loss": 0.0629,
+      "step": 2122
+    },
+    {
+      "epoch": 0.3132423459977868,
+      "grad_norm": 1.4125851392745972,
+      "learning_rate": 1.7355494525300324e-05,
+      "loss": 0.0598,
+      "step": 2123
+    },
+    {
+      "epoch": 0.3133898930284028,
+      "grad_norm": 1.1009302139282227,
+      "learning_rate": 1.7352003898842152e-05,
+      "loss": 0.0234,
+      "step": 2124
+    },
+    {
+      "epoch": 0.3135374400590188,
+      "grad_norm": 1.810051441192627,
+      "learning_rate": 1.734851132169425e-05,
+      "loss": 0.0447,
+      "step": 2125
+    },
+    {
+      "epoch": 0.3136849870896348,
+      "grad_norm": 2.4140326976776123,
+      "learning_rate": 1.7345016794783287e-05,
+      "loss": 0.1102,
+      "step": 2126
+    },
+    {
+      "epoch": 0.3138325341202508,
+      "grad_norm": 1.550392746925354,
+      "learning_rate": 1.734152031903647e-05,
+      "loss": 0.0842,
+      "step": 2127
+    },
+    {
+      "epoch": 0.31398008115086684,
+      "grad_norm": 2.508880853652954,
+      "learning_rate": 1.7338021895381506e-05,
+      "loss": 0.0717,
+      "step": 2128
+    },
+    {
+      "epoch": 0.3141276281814828,
+      "grad_norm": 2.0103600025177,
+      "learning_rate": 1.7334521524746617e-05,
+      "loss": 0.0264,
+      "step": 2129
+    },
+    {
+      "epoch": 0.31427517521209886,
+      "grad_norm": 4.147952556610107,
+      "learning_rate": 1.733101920806056e-05,
+      "loss": 0.0752,
+      "step": 2130
+    },
+    {
+      "epoch": 0.3144227222427149,
+      "grad_norm": 2.0161080360412598,
+      "learning_rate": 1.7327514946252586e-05,
+      "loss": 0.0328,
+      "step": 2131
+    },
+    {
+      "epoch": 0.31457026927333087,
+      "grad_norm": 3.3436663150787354,
+      "learning_rate": 1.7324008740252478e-05,
+      "loss": 0.0976,
+      "step": 2132
+    },
+    {
+      "epoch": 0.3147178163039469,
+      "grad_norm": 5.70300817489624,
+      "learning_rate": 1.7320500590990525e-05,
+      "loss": 0.1025,
+      "step": 2133
+    },
+    {
+      "epoch": 0.3148653633345629,
+      "grad_norm": 2.568835496902466,
+      "learning_rate": 1.7316990499397544e-05,
+      "loss": 0.0993,
+      "step": 2134
+    },
+    {
+      "epoch": 0.3150129103651789,
+      "grad_norm": 1.7607049942016602,
+      "learning_rate": 1.7313478466404848e-05,
+      "loss": 0.0714,
+      "step": 2135
+    },
+    {
+      "epoch": 0.3151604573957949,
+      "grad_norm": 3.572340965270996,
+      "learning_rate": 1.7309964492944288e-05,
+      "loss": 0.0349,
+      "step": 2136
+    },
+    {
+      "epoch": 0.31530800442641094,
+      "grad_norm": 1.9686864614486694,
+      "learning_rate": 1.730644857994821e-05,
+      "loss": 0.0598,
+      "step": 2137
+    },
+    {
+      "epoch": 0.3154555514570269,
+      "grad_norm": 1.995460867881775,
+      "learning_rate": 1.7302930728349485e-05,
+      "loss": 0.0291,
+      "step": 2138
+    },
+    {
+      "epoch": 0.31560309848764295,
+      "grad_norm": 2.1415622234344482,
+      "learning_rate": 1.7299410939081498e-05,
+      "loss": 0.0887,
+      "step": 2139
+    },
+    {
+      "epoch": 0.31575064551825893,
+      "grad_norm": 2.0583574771881104,
+      "learning_rate": 1.7295889213078143e-05,
+      "loss": 0.0833,
+      "step": 2140
+    },
+    {
+      "epoch": 0.31575064551825893,
+      "eval_accuracy": 0.9768451519536903,
+      "eval_f1": 0.9603960396039604,
+      "eval_loss": 0.06603804975748062,
+      "eval_precision": 0.9797979797979798,
+      "eval_recall": 0.941747572815534,
+      "eval_runtime": 49.8262,
+      "eval_samples_per_second": 5.84,
+      "eval_steps_per_second": 0.201,
+      "step": 2140
+    },
+    {
+      "epoch": 0.31589819254887497,
+      "grad_norm": 2.9655098915100098,
+      "learning_rate": 1.7292365551273835e-05,
+      "loss": 0.0847,
+      "step": 2141
+    },
+    {
+      "epoch": 0.31604573957949095,
+      "grad_norm": 1.5837337970733643,
+      "learning_rate": 1.7288839954603495e-05,
+      "loss": 0.0563,
+      "step": 2142
+    },
+    {
+      "epoch": 0.316193286610107,
+      "grad_norm": 3.348179578781128,
+      "learning_rate": 1.7285312424002564e-05,
+      "loss": 0.0959,
+      "step": 2143
+    },
+    {
+      "epoch": 0.31634083364072296,
+      "grad_norm": 3.233232021331787,
+      "learning_rate": 1.728178296040699e-05,
+      "loss": 0.1235,
+      "step": 2144
+    },
+    {
+      "epoch": 0.316488380671339,
+      "grad_norm": 5.451711654663086,
+      "learning_rate": 1.7278251564753247e-05,
+      "loss": 0.0784,
+      "step": 2145
+    },
+    {
+      "epoch": 0.316635927701955,
+      "grad_norm": 4.001325607299805,
+      "learning_rate": 1.7274718237978296e-05,
+      "loss": 0.0405,
+      "step": 2146
+    },
+    {
+      "epoch": 0.316783474732571,
+      "grad_norm": 3.600191831588745,
+      "learning_rate": 1.727118298101964e-05,
+      "loss": 0.086,
+      "step": 2147
+    },
+    {
+      "epoch": 0.316931021763187,
+      "grad_norm": 1.718353033065796,
+      "learning_rate": 1.7267645794815274e-05,
+      "loss": 0.0982,
+      "step": 2148
+    },
+    {
+      "epoch": 0.31707856879380303,
+      "grad_norm": 4.251434326171875,
+      "learning_rate": 1.726410668030371e-05,
+      "loss": 0.113,
+      "step": 2149
+    },
+    {
+      "epoch": 0.317226115824419,
+      "grad_norm": 1.4363844394683838,
+      "learning_rate": 1.7260565638423975e-05,
+      "loss": 0.036,
+      "step": 2150
+    },
+    {
+      "epoch": 0.31737366285503504,
+      "grad_norm": 1.8766740560531616,
+      "learning_rate": 1.725702267011561e-05,
+      "loss": 0.0589,
+      "step": 2151
+    },
+    {
+      "epoch": 0.3175212098856511,
+      "grad_norm": 2.134807586669922,
+      "learning_rate": 1.7253477776318653e-05,
+      "loss": 0.0504,
+      "step": 2152
+    },
+    {
+      "epoch": 0.31766875691626706,
+      "grad_norm": 1.7791506052017212,
+      "learning_rate": 1.7249930957973668e-05,
+      "loss": 0.0601,
+      "step": 2153
+    },
+    {
+      "epoch": 0.3178163039468831,
+      "grad_norm": 0.8975431323051453,
+      "learning_rate": 1.7246382216021725e-05,
+      "loss": 0.0153,
+      "step": 2154
+    },
+    {
+      "epoch": 0.3179638509774991,
+      "grad_norm": 1.7321504354476929,
+      "learning_rate": 1.7242831551404397e-05,
+      "loss": 0.056,
+      "step": 2155
+    },
+    {
+      "epoch": 0.3181113980081151,
+      "grad_norm": 1.682796835899353,
+      "learning_rate": 1.723927896506378e-05,
+      "loss": 0.0257,
+      "step": 2156
+    },
+    {
+      "epoch": 0.3182589450387311,
+      "grad_norm": 4.231181621551514,
+      "learning_rate": 1.7235724457942468e-05,
+      "loss": 0.0942,
+      "step": 2157
+    },
+    {
+      "epoch": 0.3184064920693471,
+      "grad_norm": 1.9627528190612793,
+      "learning_rate": 1.7232168030983577e-05,
+      "loss": 0.0489,
+      "step": 2158
+    },
+    {
+      "epoch": 0.3185540390999631,
+      "grad_norm": 1.3976247310638428,
+      "learning_rate": 1.722860968513072e-05,
+      "loss": 0.0415,
+      "step": 2159
+    },
+    {
+      "epoch": 0.31870158613057914,
+      "grad_norm": 4.44366455078125,
+      "learning_rate": 1.7225049421328024e-05,
+      "loss": 0.0643,
+      "step": 2160
+    },
+    {
+      "epoch": 0.31870158613057914,
+      "eval_accuracy": 0.975397973950796,
+      "eval_f1": 0.9571788413098237,
+      "eval_loss": 0.06960581243038177,
+      "eval_precision": 0.9947643979057592,
+      "eval_recall": 0.9223300970873787,
+      "eval_runtime": 49.5923,
+      "eval_samples_per_second": 5.868,
+      "eval_steps_per_second": 0.202,
+      "step": 2160
+    },
+    {
+      "epoch": 0.3188491331611951,
+      "grad_norm": 2.6021177768707275,
+      "learning_rate": 1.7221487240520127e-05,
+      "loss": 0.1243,
+      "step": 2161
+    },
+    {
+      "epoch": 0.31899668019181115,
+      "grad_norm": 2.948322296142578,
+      "learning_rate": 1.7217923143652173e-05,
+      "loss": 0.0406,
+      "step": 2162
+    },
+    {
+      "epoch": 0.31914422722242713,
+      "grad_norm": 2.37955379486084,
+      "learning_rate": 1.721435713166982e-05,
+      "loss": 0.1008,
+      "step": 2163
+    },
+    {
+      "epoch": 0.31929177425304317,
+      "grad_norm": 3.536679744720459,
+      "learning_rate": 1.7210789205519224e-05,
+      "loss": 0.0458,
+      "step": 2164
+    },
+    {
+      "epoch": 0.31943932128365915,
+      "grad_norm": 2.160754680633545,
+      "learning_rate": 1.7207219366147053e-05,
+      "loss": 0.0647,
+      "step": 2165
+    },
+    {
+      "epoch": 0.3195868683142752,
+      "grad_norm": 1.1617878675460815,
+      "learning_rate": 1.720364761450049e-05,
+      "loss": 0.0294,
+      "step": 2166
+    },
+    {
+      "epoch": 0.31973441534489117,
+      "grad_norm": 2.2255806922912598,
+      "learning_rate": 1.7200073951527212e-05,
+      "loss": 0.0595,
+      "step": 2167
+    },
+    {
+      "epoch": 0.3198819623755072,
+      "grad_norm": 2.3716604709625244,
+      "learning_rate": 1.7196498378175418e-05,
+      "loss": 0.0784,
+      "step": 2168
+    },
+    {
+      "epoch": 0.3200295094061232,
+      "grad_norm": 2.182983875274658,
+      "learning_rate": 1.7192920895393806e-05,
+      "loss": 0.0192,
+      "step": 2169
+    },
+    {
+      "epoch": 0.3201770564367392,
+      "grad_norm": 9.193492889404297,
+      "learning_rate": 1.7189341504131574e-05,
+      "loss": 0.1631,
+      "step": 2170
+    },
+    {
+      "epoch": 0.3203246034673552,
+      "grad_norm": 2.255892038345337,
+      "learning_rate": 1.7185760205338443e-05,
+      "loss": 0.0393,
+      "step": 2171
+    },
+    {
+      "epoch": 0.32047215049797123,
+      "grad_norm": 1.9479318857192993,
+      "learning_rate": 1.7182176999964618e-05,
+      "loss": 0.0252,
+      "step": 2172
+    },
+    {
+      "epoch": 0.3206196975285872,
+      "grad_norm": 0.6452316641807556,
+      "learning_rate": 1.7178591888960835e-05,
+      "loss": 0.007,
+      "step": 2173
+    },
+    {
+      "epoch": 0.32076724455920325,
+      "grad_norm": 1.8716485500335693,
+      "learning_rate": 1.7175004873278312e-05,
+      "loss": 0.051,
+      "step": 2174
+    },
+    {
+      "epoch": 0.3209147915898193,
+      "grad_norm": 2.7840285301208496,
+      "learning_rate": 1.7171415953868793e-05,
+      "loss": 0.0951,
+      "step": 2175
+    },
+    {
+      "epoch": 0.32106233862043526,
+      "grad_norm": 3.441535711288452,
+      "learning_rate": 1.7167825131684516e-05,
+      "loss": 0.0594,
+      "step": 2176
+    },
+    {
+      "epoch": 0.3212098856510513,
+      "grad_norm": 0.9892779588699341,
+      "learning_rate": 1.7164232407678216e-05,
+      "loss": 0.0242,
+      "step": 2177
+    },
+    {
+      "epoch": 0.3213574326816673,
+      "grad_norm": 1.6680243015289307,
+      "learning_rate": 1.7160637782803155e-05,
+      "loss": 0.0971,
+      "step": 2178
+    },
+    {
+      "epoch": 0.3215049797122833,
+      "grad_norm": 2.6267309188842773,
+      "learning_rate": 1.7157041258013074e-05,
+      "loss": 0.0564,
+      "step": 2179
+    },
+    {
+      "epoch": 0.3216525267428993,
+      "grad_norm": 1.4788562059402466,
+      "learning_rate": 1.715344283426224e-05,
+      "loss": 0.032,
+      "step": 2180
+    },
+    {
+      "epoch": 0.3216525267428993,
+      "eval_accuracy": 0.975397973950796,
+      "eval_f1": 0.9582309582309583,
+      "eval_loss": 0.06722773611545563,
+      "eval_precision": 0.9701492537313433,
+      "eval_recall": 0.9466019417475728,
+      "eval_runtime": 49.3598,
+      "eval_samples_per_second": 5.895,
+      "eval_steps_per_second": 0.203,
+      "step": 2180
+    },
+    {
+      "epoch": 0.3218000737735153,
+      "grad_norm": 1.4854892492294312,
+      "learning_rate": 1.7149842512505407e-05,
+      "loss": 0.0409,
+      "step": 2181
+    },
+    {
+      "epoch": 0.3219476208041313,
+      "grad_norm": 2.132868766784668,
+      "learning_rate": 1.7146240293697847e-05,
+      "loss": 0.0376,
+      "step": 2182
+    },
+    {
+      "epoch": 0.32209516783474734,
+      "grad_norm": 3.089017152786255,
+      "learning_rate": 1.7142636178795326e-05,
+      "loss": 0.0878,
+      "step": 2183
+    },
+    {
+      "epoch": 0.3222427148653633,
+      "grad_norm": 2.3784422874450684,
+      "learning_rate": 1.7139030168754108e-05,
+      "loss": 0.0594,
+      "step": 2184
+    },
+    {
+      "epoch": 0.32239026189597936,
+      "grad_norm": 1.111702799797058,
+      "learning_rate": 1.7135422264530977e-05,
+      "loss": 0.0367,
+      "step": 2185
+    },
+    {
+      "epoch": 0.32253780892659534,
+      "grad_norm": 3.1458306312561035,
+      "learning_rate": 1.7131812467083204e-05,
+      "loss": 0.0595,
+      "step": 2186
+    },
+    {
+      "epoch": 0.3226853559572114,
+      "grad_norm": 4.715087890625,
+      "learning_rate": 1.712820077736857e-05,
+      "loss": 0.0814,
+      "step": 2187
+    },
+    {
+      "epoch": 0.32283290298782735,
+      "grad_norm": 4.471789836883545,
+      "learning_rate": 1.7124587196345354e-05,
+      "loss": 0.0772,
+      "step": 2188
+    },
+    {
+      "epoch": 0.3229804500184434,
+      "grad_norm": 4.2753376960754395,
+      "learning_rate": 1.7120971724972343e-05,
+      "loss": 0.0965,
+      "step": 2189
+    },
+    {
+      "epoch": 0.32312799704905937,
+      "grad_norm": 1.4975053071975708,
+      "learning_rate": 1.7117354364208816e-05,
+      "loss": 0.0401,
+      "step": 2190
+    },
+    {
+      "epoch": 0.3232755440796754,
+      "grad_norm": 1.8241612911224365,
+      "learning_rate": 1.7113735115014563e-05,
+      "loss": 0.0624,
+      "step": 2191
+    },
+    {
+      "epoch": 0.3234230911102914,
+      "grad_norm": 2.369324207305908,
+      "learning_rate": 1.7110113978349867e-05,
+      "loss": 0.0869,
+      "step": 2192
+    },
+    {
+      "epoch": 0.3235706381409074,
+      "grad_norm": 1.3327139616012573,
+      "learning_rate": 1.710649095517552e-05,
+      "loss": 0.0224,
+      "step": 2193
+    },
+    {
+      "epoch": 0.3237181851715234,
+      "grad_norm": 2.886950969696045,
+      "learning_rate": 1.7102866046452807e-05,
+      "loss": 0.1318,
+      "step": 2194
+    },
+    {
+      "epoch": 0.32386573220213943,
+      "grad_norm": 4.114792346954346,
+      "learning_rate": 1.709923925314352e-05,
+      "loss": 0.11,
+      "step": 2195
+    },
+    {
+      "epoch": 0.3240132792327554,
+      "grad_norm": 1.9742048978805542,
+      "learning_rate": 1.709561057620994e-05,
+      "loss": 0.0389,
+      "step": 2196
+    },
+    {
+      "epoch": 0.32416082626337145,
+      "grad_norm": 2.6809005737304688,
+      "learning_rate": 1.7091980016614863e-05,
+      "loss": 0.0838,
+      "step": 2197
+    },
+    {
+      "epoch": 0.3243083732939875,
+      "grad_norm": 2.5167462825775146,
+      "learning_rate": 1.7088347575321575e-05,
+      "loss": 0.0896,
+      "step": 2198
+    },
+    {
+      "epoch": 0.32445592032460346,
+      "grad_norm": 1.6761678457260132,
+      "learning_rate": 1.708471325329386e-05,
+      "loss": 0.0448,
+      "step": 2199
+    },
+    {
+      "epoch": 0.3246034673552195,
+      "grad_norm": 2.724100351333618,
+      "learning_rate": 1.708107705149601e-05,
+      "loss": 0.0613,
+      "step": 2200
+    },
+    {
+      "epoch": 0.3246034673552195,
+      "eval_accuracy": 0.9768451519536903,
+      "eval_f1": 0.9605911330049262,
+      "eval_loss": 0.06580810993909836,
+      "eval_precision": 0.975,
+      "eval_recall": 0.9466019417475728,
+      "eval_runtime": 50.0082,
+      "eval_samples_per_second": 5.819,
+      "eval_steps_per_second": 0.2,
+      "step": 2200
     }
   ],
   "logging_steps": 1,
@@ -15998,7 +16758,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.467990375125484e+17,
+  "total_flos": 6.775547294038098e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null